francois/DeDRM_tools
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

tools v5.5

Browse Source 
Plugins now include unaltered stand-alone scripts, so no longer need to keep separate copies.
This commit is contained in:
Apprentice Alf
2012-12-19 13:48:11 +00:00
parent b661a6cdc5
commit 9fda194391
162 changed files with 7115 additions and 26596 deletions
Download Patch File Download Diff File Expand all files Collapse all files

217
Other_Tools/Additional_Tools/FindTopazEbooks.pyw
View File

@@ -1,217 +0,0 @@
#!/usr/bin/env python
# This is a simple tool to identify all Amazon Topaz ebooks in a specific directory.
# There always seems to be confusion since Topaz books downloaded to K4PC/Mac can have
# almost any extension (.azw, .azw1, .prc, tpz). While the .azw1 and .tpz extensions
# are fairly easy to indentify, the others are not (without opening the files in an editor).
# To run the tool with the GUI frontend, just double-click on the 'FindTopazFiles.pyw' file
# and select the folder where all of the ebooks in question are located. Then click 'Search'.
# The program will list the file names of the ebooks that are indentified as being Topaz.
# You can then isolate those books and use the Topaz tools to decrypt and convert them.
# You can also run the script from a command line... supplying the folder to search
# as a parameter: python FindTopazEbooks.pyw "C:\My Folder" (change appropriately for
# your particular O.S.)
# ** NOTE: This program does NOT decrypt or modify Topaz files in any way. It simply identifies them.
# PLEASE DO NOT PIRATE EBOOKS!
# We want all authors and publishers, and eBook stores to live
# long and prosperous lives but at the same time we just want to
# be able to read OUR books on whatever device we want and to keep
# readable for a long, long time
# This borrows very heavily from works by CMBDTC, IHeartCabbages, skindle,
# unswindle, DarkReverser, ApprenticeAlf, DiapDealer, some_updates
# and many many others
# Revision history:
# 1 - Initial release.
from __future__ import with_statement
__license__ = 'GPL v3'
import sys
import os
os.environ['PYTHONIOENCODING'] = "utf-8"
import re
import shutil
import Tkinter
import Tkconstants
import tkFileDialog
import tkMessageBox
class ScrolledText(Tkinter.Text):
def __init__(self, master=None, **kw):
self.frame = Tkinter.Frame(master)
self.vbar = Tkinter.Scrollbar(self.frame)
self.vbar.pack(side=Tkconstants.RIGHT, fill=Tkconstants.Y)
kw.update({'yscrollcommand': self.vbar.set})
Tkinter.Text.__init__(self, self.frame, **kw)
self.pack(side=Tkconstants.LEFT, fill=Tkconstants.BOTH, expand=True)
self.vbar['command'] = self.yview
# Copy geometry methods of self.frame without overriding Text
# methods = hack!
text_meths = vars(Tkinter.Text).keys()
methods = vars(Tkinter.Pack).keys() + vars(Tkinter.Grid).keys() + vars(Tkinter.Place).keys()
methods = set(methods).difference(text_meths)
for m in methods:
if m[0] != '_' and m != 'config' and m != 'configure':
setattr(self, m, getattr(self.frame, m))
def __str__(self):
return str(self.frame)
def cli_main(argv=sys.argv, obj=None):
progname = os.path.basename(argv[0])
if len(argv) != 2:
print "usage: %s DIRECTORY" % (progname,)
return 1
if obj == None:
print "\nTopaz search results:\n"
else:
obj.stext.insert(Tkconstants.END,"Topaz search results:\n\n")
inpath = argv[1]
files = os.listdir(inpath)
filefilter = re.compile("(\.azw$)|(\.azw1$)|(\.prc$)|(\.tpz$)", re.IGNORECASE)
files = filter(filefilter.search, files)
if files:
topazcount = 0
totalcount = 0
for filename in files:
with open(os.path.join(inpath, filename), 'rb') as f:
try:
if f.read().startswith('TPZ'):
f.close()
basename, extension = os.path.splitext(filename)
if obj == None:
print " %s is a Topaz formatted ebook." % filename
"""
if extension == '.azw' or extension == '.prc':
print " renaming to %s" % (basename + '.tpz')
shutil.move(os.path.join(inpath, filename),
os.path.join(inpath, basename + '.tpz'))
"""
else:
msg1 = " %s is a Topaz formatted ebook.\n" % filename
obj.stext.insert(Tkconstants.END,msg1)
"""
if extension == '.azw' or extension == '.prc':
msg2 = " renaming to %s\n" % (basename + '.tpz')
obj.stext.insert(Tkconstants.END,msg2)
shutil.move(os.path.join(inpath, filename),
os.path.join(inpath, basename + '.tpz'))
"""
topazcount += 1
except:
if obj == None:
print " Error reading %s." % filename
else:
msg = " Error reading or %s.\n" % filename
obj.stext.insert(Tkconstants.END,msg)
pass
totalcount += 1
if topazcount == 0:
if obj == None:
print "\nNo Topaz books found in %s." % inpath
else:
msg = "\nNo Topaz books found in %s.\n\n" % inpath
obj.stext.insert(Tkconstants.END,msg)
else:
if obj == None:
print "\n%i Topaz books found in %s\n%i total books checked.\n" % (topazcount, inpath, totalcount)
else:
msg = "\n%i Topaz books found in %s\n%i total books checked.\n\n" %(topazcount, inpath, totalcount)
obj.stext.insert(Tkconstants.END,msg)
else:
if obj == None:
print "No typical Topaz file extensions found in %s.\n" % inpath
else:
msg = "No typical Topaz file extensions found in %s.\n\n" % inpath
obj.stext.insert(Tkconstants.END,msg)
return 0
class DecryptionDialog(Tkinter.Frame):
def __init__(self, root):
Tkinter.Frame.__init__(self, root, border=5)
ltext='Search a directory for Topaz eBooks\n'
self.status = Tkinter.Label(self, text=ltext)
self.status.pack(fill=Tkconstants.X, expand=1)
body = Tkinter.Frame(self)
body.pack(fill=Tkconstants.X, expand=1)
sticky = Tkconstants.E + Tkconstants.W
body.grid_columnconfigure(1, weight=2)
Tkinter.Label(body, text='Directory to Search').grid(row=1)
self.inpath = Tkinter.Entry(body, width=30)
self.inpath.grid(row=1, column=1, sticky=sticky)
button = Tkinter.Button(body, text="...", command=self.get_inpath)
button.grid(row=1, column=2)
msg1 = 'Topaz search results \n\n'
self.stext = ScrolledText(body, bd=5, relief=Tkconstants.RIDGE,
height=15, width=60, wrap=Tkconstants.WORD)
self.stext.grid(row=4, column=0, columnspan=2,sticky=sticky)
#self.stext.insert(Tkconstants.END,msg1)
buttons = Tkinter.Frame(self)
buttons.pack()
self.botton = Tkinter.Button(
buttons, text="Search", width=10, command=self.search)
self.botton.pack(side=Tkconstants.LEFT)
Tkinter.Frame(buttons, width=10).pack(side=Tkconstants.LEFT)
self.button = Tkinter.Button(
buttons, text="Quit", width=10, command=self.quit)
self.button.pack(side=Tkconstants.RIGHT)
def get_inpath(self):
cwd = os.getcwdu()
cwd = cwd.encode('utf-8')
inpath = tkFileDialog.askdirectory(
parent=None, title='Directory to search',
initialdir=cwd, initialfile=None)
if inpath:
inpath = os.path.normpath(inpath)
self.inpath.delete(0, Tkconstants.END)
self.inpath.insert(0, inpath)
return
def search(self):
inpath = self.inpath.get()
if not inpath or not os.path.exists(inpath):
self.status['text'] = 'Specified directory does not exist'
return
argv = [sys.argv[0], inpath]
self.status['text'] = 'Searching...'
self.botton.configure(state='disabled')
cli_main(argv, self)
self.status['text'] = 'Search a directory for Topaz files'
self.botton.configure(state='normal')
return
def gui_main():
root = Tkinter.Tk()
root.title('Topaz eBook Finder')
root.resizable(True, False)
root.minsize(370, 0)
DecryptionDialog(root).pack(fill=Tkconstants.X, expand=1)
root.mainloop()
return 0
if __name__ == '__main__':
if len(sys.argv) > 1:
sys.exit(cli_main())
sys.exit(gui_main())

146
Other_Tools/Additional_Tools/KindlePID.pyw
View File

@@ -1,146 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import sys
sys.path.append('lib')
import os, os.path, urllib
os.environ['PYTHONIOENCODING'] = "utf-8"
import subprocess
from subprocess import Popen, PIPE, STDOUT
import subasyncio
from subasyncio import Process
import Tkinter
import Tkconstants
import tkFileDialog
import tkMessageBox
from scrolltextwidget import ScrolledText
class MainDialog(Tkinter.Frame):
def __init__(self, root):
Tkinter.Frame.__init__(self, root, border=5)
self.root = root
self.interval = 2000
self.p2 = None
self.status = Tkinter.Label(self, text='Find your Kindle PID')
self.status.pack(fill=Tkconstants.X, expand=1)
body = Tkinter.Frame(self)
body.pack(fill=Tkconstants.X, expand=1)
sticky = Tkconstants.E + Tkconstants.W
body.grid_columnconfigure(1, weight=2)
Tkinter.Label(body, text='Kindle Serial # or iPhone UDID').grid(row=1, sticky=Tkconstants.E)
self.serialnum = Tkinter.StringVar()
self.serialinfo = Tkinter.Entry(body, width=45, textvariable=self.serialnum)
self.serialinfo.grid(row=1, column=1, sticky=sticky)
msg1 = 'Conversion Log \n\n'
self.stext = ScrolledText(body, bd=5, relief=Tkconstants.RIDGE, height=15, width=60, wrap=Tkconstants.WORD)
self.stext.grid(row=3, column=0, columnspan=2,sticky=sticky)
self.stext.insert(Tkconstants.END,msg1)
buttons = Tkinter.Frame(self)
buttons.pack()
self.sbotton = Tkinter.Button(
buttons, text="Start", width=10, command=self.convertit)
self.sbotton.pack(side=Tkconstants.LEFT)
Tkinter.Frame(buttons, width=10).pack(side=Tkconstants.LEFT)
self.qbutton = Tkinter.Button(
buttons, text="Quit", width=10, command=self.quitting)
self.qbutton.pack(side=Tkconstants.RIGHT)
# read from subprocess pipe without blocking
# invoked every interval via the widget "after"
# option being used, so need to reset it for the next time
def processPipe(self):
poll = self.p2.wait('nowait')
if poll != None:
text = self.p2.readerr()
text += self.p2.read()
msg = text + '\n\n' + 'Kindle PID Successfully Determined\n'
if poll != 0:
msg = text + '\n\n' + 'Error: Kindle PID Failed\n'
self.showCmdOutput(msg)
self.p2 = None
self.sbotton.configure(state='normal')
return
text = self.p2.readerr()
text += self.p2.read()
self.showCmdOutput(text)
# make sure we get invoked again by event loop after interval
self.stext.after(self.interval,self.processPipe)
return
# post output from subprocess in scrolled text widget
def showCmdOutput(self, msg):
if msg and msg !='':
if sys.platform.startswith('win'):
msg = msg.replace('\r\n','\n')
self.stext.insert(Tkconstants.END,msg)
self.stext.yview_pickplace(Tkconstants.END)
return
# run as a subprocess via pipes and collect stdout
def pidrdr(self, serial):
# os.putenv('PYTHONUNBUFFERED', '1')
pengine = sys.executable
if pengine is None or pengine == '':
pengine = "python"
pengine = os.path.normpath(pengine)
cmdline = pengine + ' ./lib/kindlepid.py "' + serial + '"'
if sys.platform[0:3] == 'win':
# search_path = os.environ['PATH']
# search_path = search_path.lower()
# if search_path.find('python') >= 0:
# cmdline = 'python lib\kindlepid.py "' + serial + '"'
# else :
# cmdline = 'lib\kindlepid.py "' + serial + '"'
cmdline = pengine + ' lib\\kindlepid.py "' + serial + '"'
cmdline = cmdline.encode(sys.getfilesystemencoding())
p2 = Process(cmdline, shell=True, bufsize=1, stdin=None, stdout=PIPE, stderr=PIPE, close_fds=False)
return p2
def quitting(self):
# kill any still running subprocess
if self.p2 != None:
if (self.p2.wait('nowait') == None):
self.p2.terminate()
self.root.destroy()
# actually ready to run the subprocess and get its output
def convertit(self):
# now disable the button to prevent multiple launches
self.sbotton.configure(state='disabled')
serial = self.serialinfo.get()
if not serial or serial == '':
self.status['text'] = 'No Kindle Serial Number or iPhone UDID specified'
self.sbotton.configure(state='normal')
return
log = 'Command = "python kindlepid.py"\n'
log += 'Serial = "' + serial + '"\n'
log += '\n\n'
log += 'Please Wait ...\n\n'
self.stext.insert(Tkconstants.END,log)
self.p2 = self.pidrdr(serial)
# python does not seem to allow you to create
# your own eventloop which every other gui does - strange
# so need to use the widget "after" command to force
# event loop to run non-gui events every interval
self.stext.after(self.interval,self.processPipe)
return
def main(argv=None):
root = Tkinter.Tk()
root.title('Kindle and iPhone PID Calculator')
root.resizable(True, False)
root.minsize(300, 0)
MainDialog(root).pack(fill=Tkconstants.X, expand=1)
root.mainloop()
return 0
if __name__ == "__main__":
sys.exit(main())

170
Other_Tools/Additional_Tools/Kindleizer.pyw
View File

@@ -1,170 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import sys
sys.path.append('lib')
import os, os.path, urllib
import subprocess
from subprocess import Popen, PIPE, STDOUT
import subasyncio
from subasyncio import Process
import Tkinter
import Tkconstants
import tkFileDialog
import tkMessageBox
from scrolltextwidget import ScrolledText
class MainDialog(Tkinter.Frame):
def __init__(self, root):
Tkinter.Frame.__init__(self, root, border=5)
self.root = root
self.interval = 2000
self.p2 = None
self.status = Tkinter.Label(self, text='Fix Encrypted Mobi eBooks so the Kindle can read them')
self.status.pack(fill=Tkconstants.X, expand=1)
body = Tkinter.Frame(self)
body.pack(fill=Tkconstants.X, expand=1)
sticky = Tkconstants.E + Tkconstants.W
body.grid_columnconfigure(1, weight=2)
Tkinter.Label(body, text='Mobi eBook input file').grid(row=0, sticky=Tkconstants.E)
self.mobipath = Tkinter.Entry(body, width=50)
self.mobipath.grid(row=0, column=1, sticky=sticky)
cwd = os.getcwdu()
cwd = cwd.encode('utf-8')
self.mobipath.insert(0, cwd)
button = Tkinter.Button(body, text="...", command=self.get_mobipath)
button.grid(row=0, column=2)
Tkinter.Label(body, text='10 Character PID').grid(row=1, sticky=Tkconstants.E)
self.pidnum = Tkinter.StringVar()
self.pidinfo = Tkinter.Entry(body, width=12, textvariable=self.pidnum)
self.pidinfo.grid(row=1, column=1, sticky=sticky)
msg1 = 'Conversion Log \n\n'
self.stext = ScrolledText(body, bd=5, relief=Tkconstants.RIDGE, height=15, width=60, wrap=Tkconstants.WORD)
self.stext.grid(row=2, column=0, columnspan=2,sticky=sticky)
self.stext.insert(Tkconstants.END,msg1)
buttons = Tkinter.Frame(self)
buttons.pack()
self.sbotton = Tkinter.Button(
buttons, text="Start", width=10, command=self.convertit)
self.sbotton.pack(side=Tkconstants.LEFT)
Tkinter.Frame(buttons, width=10).pack(side=Tkconstants.LEFT)
self.qbutton = Tkinter.Button(
buttons, text="Quit", width=10, command=self.quitting)
self.qbutton.pack(side=Tkconstants.RIGHT)
# read from subprocess pipe without blocking
# invoked every interval via the widget "after"
# option being used, so need to reset it for the next time
def processPipe(self):
poll = self.p2.wait('nowait')
if poll != None:
text = self.p2.readerr()
text += self.p2.read()
msg = text + '\n\n' + 'Fix for Kindle successful\n'
if poll != 0:
msg = text + '\n\n' + 'Error: Fix for Kindle Failed\n'
self.showCmdOutput(msg)
self.p2 = None
self.sbotton.configure(state='normal')
return
text = self.p2.readerr()
text += self.p2.read()
self.showCmdOutput(text)
# make sure we get invoked again by event loop after interval
self.stext.after(self.interval,self.processPipe)
return
# post output from subprocess in scrolled text widget
def showCmdOutput(self, msg):
if msg and msg !='':
msg = msg.encode('utf-8')
if sys.platform.startswith('win'):
msg = msg.replace('\r\n','\n')
self.stext.insert(Tkconstants.END,msg)
self.stext.yview_pickplace(Tkconstants.END)
return
# run as a subprocess via pipes and collect stdout
def krdr(self, infile, pidnum):
# os.putenv('PYTHONUNBUFFERED', '1')
cmdline = 'python ./lib/kindlefix.py "' + infile + '" "' + pidnum + '"'
if sys.platform[0:3] == 'win':
search_path = os.environ['PATH']
search_path = search_path.lower()
if search_path.find('python') >= 0:
cmdline = 'python lib\kindlefix.py "' + infile + '" "' + pidnum + '"'
else :
cmdline = 'lib\kindlefix.py "' + infile + '" "' + pidnum + '"'
cmdline = cmdline.encode(sys.getfilesystemencoding())
p2 = Process(cmdline, shell=True, bufsize=1, stdin=None, stdout=PIPE, stderr=PIPE, close_fds=False)
return p2
def get_mobipath(self):
mobipath = tkFileDialog.askopenfilename(
parent=None, title='Select Mobi eBook File',
defaultextension='.prc', filetypes=[('Mobi eBook File', '.prc'), ('Mobi eBook File', '.mobi'),
('All Files', '.*')])
if mobipath:
mobipath = os.path.normpath(mobipath)
self.mobipath.delete(0, Tkconstants.END)
self.mobipath.insert(0, mobipath)
return
def quitting(self):
# kill any still running subprocess
if self.p2 != None:
if (self.p2.wait('nowait') == None):
self.p2.terminate()
self.root.destroy()
# actually ready to run the subprocess and get its output
def convertit(self):
# now disable the button to prevent multiple launches
self.sbotton.configure(state='disabled')
mobipath = self.mobipath.get()
pidnum = self.pidinfo.get()
if not mobipath or not os.path.exists(mobipath):
self.status['text'] = 'Specified Mobi eBook file does not exist'
self.sbotton.configure(state='normal')
return
if not pidnum or pidnum == '':
self.status['text'] = 'No PID specified'
self.sbotton.configure(state='normal')
return
log = 'Command = "python kindlefix.py"\n'
log += 'Mobi Path = "'+ mobipath + '"\n'
log += 'PID = "' + pidnum + '"\n'
log += '\n\n'
log += 'Please Wait ...\n\n'
log = log.encode('utf-8')
self.stext.insert(Tkconstants.END,log)
self.p2 = self.krdr(mobipath, pidnum)
# python does not seem to allow you to create
# your own eventloop which every other gui does - strange
# so need to use the widget "after" command to force
# event loop to run non-gui events every interval
self.stext.after(self.interval,self.processPipe)
return
def main(argv=None):
root = Tkinter.Tk()
root.title('Fix Encrypted Mobi eBooks to work with the Kindle')
root.resizable(True, False)
root.minsize(300, 0)
MainDialog(root).pack(fill=Tkconstants.X, expand=1)
root.mainloop()
return 0
if __name__ == "__main__":
sys.exit(main())

203
Other_Tools/Additional_Tools/MobiDeDRM.pyw
View File

@@ -1,203 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import sys
sys.path.append('lib')
import os, os.path, urllib
os.environ['PYTHONIOENCODING'] = "utf-8"
import subprocess
from subprocess import Popen, PIPE, STDOUT
import subasyncio
from subasyncio import Process
import Tkinter
import Tkconstants
import tkFileDialog
import tkMessageBox
from scrolltextwidget import ScrolledText
class MainDialog(Tkinter.Frame):
def __init__(self, root):
Tkinter.Frame.__init__(self, root, border=5)
self.root = root
self.interval = 2000
self.p2 = None
self.status = Tkinter.Label(self, text='Remove Encryption from a Mobi eBook')
self.status.pack(fill=Tkconstants.X, expand=1)
body = Tkinter.Frame(self)
body.pack(fill=Tkconstants.X, expand=1)
sticky = Tkconstants.E + Tkconstants.W
body.grid_columnconfigure(1, weight=2)
Tkinter.Label(body, text='Mobi eBook input file').grid(row=0, sticky=Tkconstants.E)
self.mobipath = Tkinter.Entry(body, width=50)
self.mobipath.grid(row=0, column=1, sticky=sticky)
cwd = os.getcwdu()
cwd = cwd.encode('utf-8')
self.mobipath.insert(0, cwd)
button = Tkinter.Button(body, text="...", command=self.get_mobipath)
button.grid(row=0, column=2)
Tkinter.Label(body, text='Name for Unencrypted Output File').grid(row=1, sticky=Tkconstants.E)
self.outpath = Tkinter.Entry(body, width=50)
self.outpath.grid(row=1, column=1, sticky=sticky)
self.outpath.insert(0, '')
button = Tkinter.Button(body, text="...", command=self.get_outpath)
button.grid(row=1, column=2)
Tkinter.Label(body, text='10 Character PID').grid(row=2, sticky=Tkconstants.E)
self.pidnum = Tkinter.StringVar()
self.pidinfo = Tkinter.Entry(body, width=12, textvariable=self.pidnum)
self.pidinfo.grid(row=2, column=1, sticky=sticky)
msg1 = 'Conversion Log \n\n'
self.stext = ScrolledText(body, bd=5, relief=Tkconstants.RIDGE, height=15, width=60, wrap=Tkconstants.WORD)
self.stext.grid(row=3, column=0, columnspan=2,sticky=sticky)
self.stext.insert(Tkconstants.END,msg1)
buttons = Tkinter.Frame(self)
buttons.pack()
self.sbotton = Tkinter.Button(
buttons, text="Start", width=10, command=self.convertit)
self.sbotton.pack(side=Tkconstants.LEFT)
Tkinter.Frame(buttons, width=10).pack(side=Tkconstants.LEFT)
self.qbutton = Tkinter.Button(
buttons, text="Quit", width=10, command=self.quitting)
self.qbutton.pack(side=Tkconstants.RIGHT)
# read from subprocess pipe without blocking
# invoked every interval via the widget "after"
# option being used, so need to reset it for the next time
def processPipe(self):
poll = self.p2.wait('nowait')
if poll != None:
text = self.p2.readerr()
text += self.p2.read()
msg = text + '\n\n' + 'Encryption successfully removed\n'
if poll != 0:
msg = text + '\n\n' + 'Error: Encryption Removal Failed\n'
self.showCmdOutput(msg)
self.p2 = None
self.sbotton.configure(state='normal')
return
text = self.p2.readerr()
text += self.p2.read()
self.showCmdOutput(text)
# make sure we get invoked again by event loop after interval
self.stext.after(self.interval,self.processPipe)
return
# post output from subprocess in scrolled text widget
def showCmdOutput(self, msg):
if msg and msg !='':
if sys.platform.startswith('win'):
msg = msg.replace('\r\n','\n')
self.stext.insert(Tkconstants.END,msg)
self.stext.yview_pickplace(Tkconstants.END)
return
# run as a subprocess via pipes and collect stdout
def mobirdr(self, infile, outfile, pidnum):
pengine = sys.executable
if pengine is None or pengine == '':
pengine = "python"
pengine = os.path.normpath(pengine)
# os.putenv('PYTHONUNBUFFERED', '1')
cmdline = pengine + ' ./lib/mobidedrm.py "' + infile + '" "' + outfile + '" "' + pidnum + '"'
if sys.platform[0:3] == 'win':
# search_path = os.environ['PATH']
# search_path = search_path.lower()
# if search_path.find('python') >= 0:
# cmdline = 'python lib\mobidedrm.py "' + infile + '" "' + outfile + '" "' + pidnum + '"'
# else :
# cmdline = 'lib\mobidedrm.py "' + infile + '" "' + outfile + '" "' + pidnum + '"'
cmdline = pengine + ' lib\\mobidedrm.py "' + infile + '" "' + outfile + '" "' + pidnum + '"'
cmdline = cmdline.encode(sys.getfilesystemencoding())
p2 = Process(cmdline, shell=True, bufsize=1, stdin=None, stdout=PIPE, stderr=PIPE, close_fds=False)
return p2
def get_mobipath(self):
mobipath = tkFileDialog.askopenfilename(
parent=None, title='Select Mobi eBook File',
defaultextension='.prc', filetypes=[('Mobi eBook File', '.prc'), ('Mobi eBook File', '.azw'),('Mobi eBook File', '.mobi'),
('All Files', '.*')])
if mobipath:
mobipath = os.path.normpath(mobipath)
self.mobipath.delete(0, Tkconstants.END)
self.mobipath.insert(0, mobipath)
return
def get_outpath(self):
mobipath = self.mobipath.get()
initname = os.path.basename(mobipath)
p = initname.find('.')
if p >= 0: initname = initname[0:p]
initname += '_nodrm.mobi'
outpath = tkFileDialog.asksaveasfilename(
parent=None, title='Select Unencrypted Mobi File to produce',
defaultextension='.mobi', initialfile=initname,
filetypes=[('Mobi files', '.mobi'), ('All files', '.*')])
if outpath:
outpath = os.path.normpath(outpath)
self.outpath.delete(0, Tkconstants.END)
self.outpath.insert(0, outpath)
return
def quitting(self):
# kill any still running subprocess
if self.p2 != None:
if (self.p2.wait('nowait') == None):
self.p2.terminate()
self.root.destroy()
# actually ready to run the subprocess and get its output
def convertit(self):
# now disable the button to prevent multiple launches
self.sbotton.configure(state='disabled')
mobipath = self.mobipath.get()
outpath = self.outpath.get()
pidnum = self.pidinfo.get()
if not mobipath or not os.path.exists(mobipath):
self.status['text'] = 'Specified Mobi eBook file does not exist'
self.sbotton.configure(state='normal')
return
if not outpath:
self.status['text'] = 'No output file specified'
self.sbotton.configure(state='normal')
return
if not pidnum or pidnum == '':
self.status['text'] = 'No PID specified'
self.sbotton.configure(state='normal')
return
log = 'Command = "python mobidedrm.py"\n'
log += 'Mobi Path = "'+ mobipath + '"\n'
log += 'Output File = "' + outpath + '"\n'
log += 'PID = "' + pidnum + '"\n'
log += '\n\n'
log += 'Please Wait ...\n\n'
self.stext.insert(Tkconstants.END,log)
self.p2 = self.mobirdr(mobipath, outpath, pidnum)
# python does not seem to allow you to create
# your own eventloop which every other gui does - strange
# so need to use the widget "after" command to force
# event loop to run non-gui events every interval
self.stext.after(self.interval,self.processPipe)
return
def main(argv=None):
root = Tkinter.Tk()
root.title('Mobi eBook Encryption Removal')
root.resizable(True, False)
root.minsize(300, 0)
MainDialog(root).pack(fill=Tkconstants.X, expand=1)
root.mainloop()
return 0
if __name__ == "__main__":
sys.exit(main())

172
Other_Tools/Additional_Tools/lib/kindlefix.py
View File

@@ -1,172 +0,0 @@
class Unbuffered:
def __init__(self, stream):
self.stream = stream
def write(self, data):
self.stream.write(data)
self.stream.flush()
def __getattr__(self, attr):
return getattr(self.stream, attr)
import sys
sys.stdout=Unbuffered(sys.stdout)
import prc, struct
from binascii import hexlify
def strByte(s,off=0):
return struct.unpack(">B",s[off])[0];
def strSWord(s,off=0):
return struct.unpack(">h",s[off:off+2])[0];
def strWord(s,off=0):
return struct.unpack(">H",s[off:off+2])[0];
def strDWord(s,off=0):
return struct.unpack(">L",s[off:off+4])[0];
def strPutDWord(s,off,i):
return s[:off]+struct.pack(">L",i)+s[off+4:];
keyvec1 = "\x72\x38\x33\xB0\xB4\xF2\xE3\xCA\xDF\x09\x01\xD6\xE2\xE0\x3F\x96"
#implementation of Pukall Cipher 1
def PC1(key, src, decryption=True):
sum1 = 0;
sum2 = 0;
keyXorVal = 0;
if len(key)!=16:
print "Bad key length!"
return None
wkey = []
for i in xrange(8):
wkey.append(ord(key[i*2])<<8 | ord(key[i*2+1]))
dst = ""
for i in xrange(len(src)):
temp1 = 0;
byteXorVal = 0;
for j in xrange(8):
temp1 ^= wkey[j]
sum2 = (sum2+j)*20021 + sum1
sum1 = (temp1*346)&0xFFFF
sum2 = (sum2+sum1)&0xFFFF
temp1 = (temp1*20021+1)&0xFFFF
byteXorVal ^= temp1 ^ sum2
curByte = ord(src[i])
if not decryption:
keyXorVal = curByte * 257;
curByte = ((curByte ^ (byteXorVal >> 8)) ^ byteXorVal) & 0xFF
if decryption:
keyXorVal = curByte * 257;
for j in xrange(8):
wkey[j] ^= keyXorVal;
dst+=chr(curByte)
return dst
def find_key(rec0, pid):
off1 = strDWord(rec0, 0xA8)
if off1==0xFFFFFFFF or off1==0:
print "No DRM"
return None
size1 = strDWord(rec0, 0xB0)
cnt = strDWord(rec0, 0xAC)
flag = strDWord(rec0, 0xB4)
temp_key = PC1(keyvec1, pid.ljust(16,'\0'), False)
cksum = 0
#print pid, "->", hexlify(temp_key)
for i in xrange(len(temp_key)):
cksum += ord(temp_key[i])
cksum &= 0xFF
temp_key = temp_key.ljust(16,'\0')
#print "pid cksum: %02X"%cksum
#print "Key records: %02X-%02X, count: %d, flag: %02X"%(off1, off1+size1, cnt, flag)
iOff = off1
drm_key = None
for i in xrange(cnt):
dwCheck = strDWord(rec0, iOff)
dwSize = strDWord(rec0, iOff+4)
dwType = strDWord(rec0, iOff+8)
nCksum = strByte(rec0, iOff+0xC)
#print "Key record %d: check=%08X, size=%d, type=%d, cksum=%02X"%(i, dwCheck, dwSize, dwType, nCksum)
if nCksum==cksum:
drmInfo = PC1(temp_key, rec0[iOff+0x10:iOff+0x30])
dw0, dw4, dw18, dw1c = struct.unpack(">II16xII", drmInfo)
#print "Decrypted drmInfo:", "%08X, %08X, %s, %08X, %08X"%(dw0, dw4, hexlify(drmInfo[0x8:0x18]), dw18, dw1c)
#print "Decrypted drmInfo:", hexlify(drmInfo)
if dw0==dwCheck:
print "Found the matching record; setting the CustomDRM flag for Kindle"
drmInfo = strPutDWord(drmInfo,4,(dw4|0x800))
dw0, dw4, dw18, dw1c = struct.unpack(">II16xII", drmInfo)
#print "Updated drmInfo:", "%08X, %08X, %s, %08X, %08X"%(dw0, dw4, hexlify(drmInfo[0x8:0x18]), dw18, dw1c)
return rec0[:iOff+0x10] + PC1(temp_key, drmInfo, False) + rec0[:iOff+0x30]
iOff += dwSize
return None
def replaceext(filename, newext):
nameparts = filename.split(".")
if len(nameparts)>1:
return (".".join(nameparts[:-1]))+newext
else:
return nameparts[0]+newext
def main(argv=sys.argv):
print "The Kindleizer v0.2. Copyright (c) 2007 Igor Skochinsky"
if len(sys.argv) != 3:
print "Fixes encrypted Mobipocket books to be readable by Kindle"
print "Usage: kindlefix.py file.mobi PID"
return 1
fname = sys.argv[1]
pid = sys.argv[2]
if len(pid)==10 and pid[-3]=='*':
pid = pid[:-2]
if len(pid)!=8 or pid[-1]!='*':
print "PID is not valid! (should be in format AAAAAAA*DD)"
return 3
db = prc.File(fname)
#print dir(db)
if db.getDBInfo()["creator"]!='MOBI':
print "Not a Mobi file!"
return 1
rec0 = db.getRecord(0)[0]
enc = strSWord(rec0, 0xC)
print "Encryption:", enc
if enc!=2:
print "Unknown encryption type"
return 1
if len(rec0)<0x28 or rec0[0x10:0x14] != 'MOBI':
print "bad file format"
return 1
print "Mobi publication type:", strDWord(rec0, 0x18)
formatVer = strDWord(rec0, 0x24)
print "Mobi format version:", formatVer
last_rec = strWord(rec0, 8)
dwE0 = 0
if formatVer>=4:
new_rec0 = find_key(rec0, pid)
if new_rec0:
db.setRecordIdx(0,new_rec0)
else:
print "PID doesn't match this file"
return 2
else:
print "Wrong Mobi format version"
return 1
outfname = replaceext(fname, ".azw")
if outfname==fname:
outfname = replaceext(fname, "_fixed.azw")
db.save(outfname)
print "Output written to "+outfname
return 0
if __name__ == "__main__":
sys.exit(main())

91
Other_Tools/Additional_Tools/lib/kindlepid.py
View File

@@ -1,91 +0,0 @@
#!/usr/bin/python
# Mobipocket PID calculator v0.2 for Amazon Kindle.
# Copyright (c) 2007, 2009 Igor Skochinsky <skochinsky@mail.ru>
# History:
# 0.1 Initial release
# 0.2 Added support for generating PID for iPhone (thanks to mbp)
# 0.3 changed to autoflush stdout, fixed return code usage
class Unbuffered:
def __init__(self, stream):
self.stream = stream
def write(self, data):
self.stream.write(data)
self.stream.flush()
def __getattr__(self, attr):
return getattr(self.stream, attr)
import sys
sys.stdout=Unbuffered(sys.stdout)
import binascii
if sys.hexversion >= 0x3000000:
print "This script is incompatible with Python 3.x. Please install Python 2.6.x from python.org"
sys.exit(2)
letters = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
def crc32(s):
return (~binascii.crc32(s,-1))&0xFFFFFFFF
def checksumPid(s):
crc = crc32(s)
crc = crc ^ (crc >> 16)
res = s
l = len(letters)
for i in (0,1):
b = crc & 0xff
pos = (b // l) ^ (b % l)
res += letters[pos%l]
crc >>= 8
return res
def pidFromSerial(s, l):
crc = crc32(s)
arr1 = [0]*l
for i in xrange(len(s)):
arr1[i%l] ^= ord(s[i])
crc_bytes = [crc >> 24 & 0xff, crc >> 16 & 0xff, crc >> 8 & 0xff, crc & 0xff]
for i in xrange(l):
arr1[i] ^= crc_bytes[i&3]
pid = ""
for i in xrange(l):
b = arr1[i] & 0xff
pid+=letters[(b >> 7) + ((b >> 5 & 3) ^ (b & 0x1f))]
return pid
def main(argv=sys.argv):
print "Mobipocket PID calculator for Amazon Kindle. Copyright (c) 2007, 2009 Igor Skochinsky"
if len(sys.argv)==2:
serial = sys.argv[1]
else:
print "Usage: kindlepid.py <Kindle Serial Number>/<iPhone/iPod Touch UDID>"
return 1
if len(serial)==16:
if serial.startswith("B"):
print "Kindle serial number detected"
else:
print "Warning: unrecognized serial number. Please recheck input."
return 1
pid = pidFromSerial(serial,7)+"*"
print "Mobipocked PID for Kindle serial# "+serial+" is "+checksumPid(pid)
return 0
elif len(serial)==40:
print "iPhone serial number (UDID) detected"
pid = pidFromSerial(serial,8)
print "Mobipocked PID for iPhone serial# "+serial+" is "+checksumPid(pid)
return 0
else:
print "Warning: unrecognized serial number. Please recheck input."
return 1
return 0
if __name__ == "__main__":
sys.exit(main())

460
Other_Tools/Additional_Tools/lib/mobidedrm.py
View File

@@ -1,460 +0,0 @@
#!/usr/bin/python
#
# This is a python script. You need a Python interpreter to run it.
# For example, ActiveState Python, which exists for windows.
#
# Changelog
# 0.01 - Initial version
# 0.02 - Huffdic compressed books were not properly decrypted
# 0.03 - Wasn't checking MOBI header length
# 0.04 - Wasn't sanity checking size of data record
# 0.05 - It seems that the extra data flags take two bytes not four
# 0.06 - And that low bit does mean something after all :-)
# 0.07 - The extra data flags aren't present in MOBI header < 0xE8 in size
# 0.08 - ...and also not in Mobi header version < 6
# 0.09 - ...but they are there with Mobi header version 6, header size 0xE4!
# 0.10 - Outputs unencrypted files as-is, so that when run as a Calibre
# import filter it works when importing unencrypted files.
# Also now handles encrypted files that don't need a specific PID.
# 0.11 - use autoflushed stdout and proper return values
# 0.12 - Fix for problems with metadata import as Calibre plugin, report errors
# 0.13 - Formatting fixes: retabbed file, removed trailing whitespace
# and extra blank lines, converted CR/LF pairs at ends of each line,
# and other cosmetic fixes.
# 0.14 - Working out when the extra data flags are present has been problematic
# Versions 7 through 9 have tried to tweak the conditions, but have been
# only partially successful. Closer examination of lots of sample
# files reveals that a confusion has arisen because trailing data entries
# are not encrypted, but it turns out that the multibyte entries
# in utf8 file are encrypted. (Although neither kind gets compressed.)
# This knowledge leads to a simplification of the test for the
# trailing data byte flags - version 5 and higher AND header size >= 0xE4.
# 0.15 - Now outputs 'heartbeat', and is also quicker for long files.
# 0.16 - And reverts to 'done' not 'done.' at the end for unswindle compatibility.
# 0.17 - added modifications to support its use as an imported python module
# both inside calibre and also in other places (ie K4DeDRM tools)
# 0.17a- disabled the standalone plugin feature since a plugin can not import
# a plugin
# 0.18 - It seems that multibyte entries aren't encrypted in a v7 file...
# Removed the disabled Calibre plug-in code
# Permit use of 8-digit PIDs
# 0.19 - It seems that multibyte entries aren't encrypted in a v6 file either.
# 0.20 - Correction: It seems that multibyte entries are encrypted in a v6 file.
# 0.21 - Added support for multiple pids
# 0.22 - revised structure to hold MobiBook as a class to allow an extended interface
# 0.23 - fixed problem with older files with no EXTH section
# 0.24 - add support for type 1 encryption and 'TEXtREAd' books as well
# 0.25 - Fixed support for 'BOOKMOBI' type 1 encryption
# 0.26 - Now enables Text-To-Speech flag and sets clipping limit to 100%
# 0.27 - Correct pid metadata token generation to match that used by skindle (Thank You Bart!)
# 0.28 - slight additional changes to metadata token generation (None -> '')
# 0.29 - It seems that the ideas about when multibyte trailing characters were
# included in the encryption were wrong. They are for DOC compressed
# files, but they are not for HUFF/CDIC compress files!
# 0.30 - Modified interface slightly to work better with new calibre plugin style
# 0.31 - The multibyte encrytion info is true for version 7 files too.
# 0.32 - Added support for "Print Replica" Kindle ebooks
# 0.33 - Performance improvements for large files (concatenation)
# 0.34 - Performance improvements in decryption (libalfcrypto)
# 0.35 - add interface to get mobi_version
# 0.36 - fixed problem with TEXtREAd and getBookTitle interface
# 0.37 - Fixed double announcement for stand-alone operation
__version__ = '0.37'
import sys
class Unbuffered:
def __init__(self, stream):
self.stream = stream
def write(self, data):
self.stream.write(data)
self.stream.flush()
def __getattr__(self, attr):
return getattr(self.stream, attr)
sys.stdout=Unbuffered(sys.stdout)
import os
import struct
import binascii
from alfcrypto import Pukall_Cipher
class DrmException(Exception):
pass
#
# MobiBook Utility Routines
#
# Implementation of Pukall Cipher 1
def PC1(key, src, decryption=True):
return Pukall_Cipher().PC1(key,src,decryption)
# sum1 = 0;
# sum2 = 0;
# keyXorVal = 0;
# if len(key)!=16:
# print "Bad key length!"
# return None
# wkey = []
# for i in xrange(8):
# wkey.append(ord(key[i*2])<<8 | ord(key[i*2+1]))
# dst = ""
# for i in xrange(len(src)):
# temp1 = 0;
# byteXorVal = 0;
# for j in xrange(8):
# temp1 ^= wkey[j]
# sum2 = (sum2+j)*20021 + sum1
# sum1 = (temp1*346)&0xFFFF
# sum2 = (sum2+sum1)&0xFFFF
# temp1 = (temp1*20021+1)&0xFFFF
# byteXorVal ^= temp1 ^ sum2
# curByte = ord(src[i])
# if not decryption:
# keyXorVal = curByte * 257;
# curByte = ((curByte ^ (byteXorVal >> 8)) ^ byteXorVal) & 0xFF
# if decryption:
# keyXorVal = curByte * 257;
# for j in xrange(8):
# wkey[j] ^= keyXorVal;
# dst+=chr(curByte)
# return dst
def checksumPid(s):
letters = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
crc = (~binascii.crc32(s,-1))&0xFFFFFFFF
crc = crc ^ (crc >> 16)
res = s
l = len(letters)
for i in (0,1):
b = crc & 0xff
pos = (b // l) ^ (b % l)
res += letters[pos%l]
crc >>= 8
return res
def getSizeOfTrailingDataEntries(ptr, size, flags):
def getSizeOfTrailingDataEntry(ptr, size):
bitpos, result = 0, 0
if size <= 0:
return result
while True:
v = ord(ptr[size-1])
result |= (v & 0x7F) << bitpos
bitpos += 7
size -= 1
if (v & 0x80) != 0 or (bitpos >= 28) or (size == 0):
return result
num = 0
testflags = flags >> 1
while testflags:
if testflags & 1:
num += getSizeOfTrailingDataEntry(ptr, size - num)
testflags >>= 1
# Check the low bit to see if there's multibyte data present.
# if multibyte data is included in the encryped data, we'll
# have already cleared this flag.
if flags & 1:
num += (ord(ptr[size - num - 1]) & 0x3) + 1
return num
class MobiBook:
def loadSection(self, section):
if (section + 1 == self.num_sections):
endoff = len(self.data_file)
else:
endoff = self.sections[section + 1][0]
off = self.sections[section][0]
return self.data_file[off:endoff]
def __init__(self, infile, announce = True):
if announce:
print ('MobiDeDrm v%(__version__)s. '
'Copyright 2008-2012 The Dark Reverser et al.' % globals())
# initial sanity check on file
self.data_file = file(infile, 'rb').read()
self.mobi_data = ''
self.header = self.data_file[0:78]
if self.header[0x3C:0x3C+8] != 'BOOKMOBI' and self.header[0x3C:0x3C+8] != 'TEXtREAd':
raise DrmException("invalid file format")
self.magic = self.header[0x3C:0x3C+8]
self.crypto_type = -1
# build up section offset and flag info
self.num_sections, = struct.unpack('>H', self.header[76:78])
self.sections = []
for i in xrange(self.num_sections):
offset, a1,a2,a3,a4 = struct.unpack('>LBBBB', self.data_file[78+i*8:78+i*8+8])
flags, val = a1, a2<<16|a3<<8|a4
self.sections.append( (offset, flags, val) )
# parse information from section 0
self.sect = self.loadSection(0)
self.records, = struct.unpack('>H', self.sect[0x8:0x8+2])
self.compression, = struct.unpack('>H', self.sect[0x0:0x0+2])
if self.magic == 'TEXtREAd':
print "Book has format: ", self.magic
self.extra_data_flags = 0
self.mobi_length = 0
self.mobi_codepage = 1252
self.mobi_version = -1
self.meta_array = {}
return
self.mobi_length, = struct.unpack('>L',self.sect[0x14:0x18])
self.mobi_codepage, = struct.unpack('>L',self.sect[0x1c:0x20])
self.mobi_version, = struct.unpack('>L',self.sect[0x68:0x6C])
print "MOBI header version = %d, length = %d" %(self.mobi_version, self.mobi_length)
self.extra_data_flags = 0
if (self.mobi_length >= 0xE4) and (self.mobi_version >= 5):
self.extra_data_flags, = struct.unpack('>H', self.sect[0xF2:0xF4])
print "Extra Data Flags = %d" % self.extra_data_flags
if (self.compression != 17480):
# multibyte utf8 data is included in the encryption for PalmDoc compression
# so clear that byte so that we leave it to be decrypted.
self.extra_data_flags &= 0xFFFE
# if exth region exists parse it for metadata array
self.meta_array = {}
try:
exth_flag, = struct.unpack('>L', self.sect[0x80:0x84])
exth = 'NONE'
if exth_flag & 0x40:
exth = self.sect[16 + self.mobi_length:]
if (len(exth) >= 4) and (exth[:4] == 'EXTH'):
nitems, = struct.unpack('>I', exth[8:12])
pos = 12
for i in xrange(nitems):
type, size = struct.unpack('>II', exth[pos: pos + 8])
content = exth[pos + 8: pos + size]
self.meta_array[type] = content
# reset the text to speech flag and clipping limit, if present
if type == 401 and size == 9:
# set clipping limit to 100%
self.patchSection(0, "\144", 16 + self.mobi_length + pos + 8)
elif type == 404 and size == 9:
# make sure text to speech is enabled
self.patchSection(0, "\0", 16 + self.mobi_length + pos + 8)
# print type, size, content, content.encode('hex')
pos += size
except:
self.meta_array = {}
pass
self.print_replica = False
def getBookTitle(self):
codec_map = {
1252 : 'windows-1252',
65001 : 'utf-8',
}
title = ''
codec = 'windows-1252'
if self.magic == 'BOOKMOBI':
if 503 in self.meta_array:
title = self.meta_array[503]
else:
toff, tlen = struct.unpack('>II', self.sect[0x54:0x5c])
tend = toff + tlen
title = self.sect[toff:tend]
if self.mobi_codepage in codec_map.keys():
codec = codec_map[self.mobi_codepage]
if title == '':
title = self.header[:32]
title = title.split("\0")[0]
return unicode(title, codec).encode('utf-8')
def getPIDMetaInfo(self):
rec209 = ''
token = ''
if 209 in self.meta_array:
rec209 = self.meta_array[209]
data = rec209
# The 209 data comes in five byte groups. Interpret the last four bytes
# of each group as a big endian unsigned integer to get a key value
# if that key exists in the meta_array, append its contents to the token
for i in xrange(0,len(data),5):
val, = struct.unpack('>I',data[i+1:i+5])
sval = self.meta_array.get(val,'')
token += sval
return rec209, token
def patch(self, off, new):
self.data_file = self.data_file[:off] + new + self.data_file[off+len(new):]
def patchSection(self, section, new, in_off = 0):
if (section + 1 == self.num_sections):
endoff = len(self.data_file)
else:
endoff = self.sections[section + 1][0]
off = self.sections[section][0]
assert off + in_off + len(new) <= endoff
self.patch(off + in_off, new)
def parseDRM(self, data, count, pidlist):
found_key = None
keyvec1 = "\x72\x38\x33\xB0\xB4\xF2\xE3\xCA\xDF\x09\x01\xD6\xE2\xE0\x3F\x96"
for pid in pidlist:
bigpid = pid.ljust(16,'\0')
temp_key = PC1(keyvec1, bigpid, False)
temp_key_sum = sum(map(ord,temp_key)) & 0xff
found_key = None
for i in xrange(count):
verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
if cksum == temp_key_sum:
cookie = PC1(temp_key, cookie)
ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
if verification == ver and (flags & 0x1F) == 1:
found_key = finalkey
break
if found_key != None:
break
if not found_key:
# Then try the default encoding that doesn't require a PID
pid = "00000000"
temp_key = keyvec1
temp_key_sum = sum(map(ord,temp_key)) & 0xff
for i in xrange(count):
verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
if cksum == temp_key_sum:
cookie = PC1(temp_key, cookie)
ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
if verification == ver:
found_key = finalkey
break
return [found_key,pid]
def getMobiFile(self, outpath):
file(outpath,'wb').write(self.mobi_data)
def getMobiVersion(self):
return self.mobi_version
def getPrintReplica(self):
return self.print_replica
def processBook(self, pidlist):
crypto_type, = struct.unpack('>H', self.sect[0xC:0xC+2])
print 'Crypto Type is: ', crypto_type
self.crypto_type = crypto_type
if crypto_type == 0:
print "This book is not encrypted."
# we must still check for Print Replica
self.print_replica = (self.loadSection(1)[0:4] == '%MOP')
self.mobi_data = self.data_file
return
if crypto_type != 2 and crypto_type != 1:
raise DrmException("Cannot decode unknown Mobipocket encryption type %d" % crypto_type)
if 406 in self.meta_array:
data406 = self.meta_array[406]
val406, = struct.unpack('>Q',data406)
if val406 != 0:
raise DrmException("Cannot decode library or rented ebooks.")
goodpids = []
for pid in pidlist:
if len(pid)==10:
if checksumPid(pid[0:-2]) != pid:
print "Warning: PID " + pid + " has incorrect checksum, should have been "+checksumPid(pid[0:-2])
goodpids.append(pid[0:-2])
elif len(pid)==8:
goodpids.append(pid)
if self.crypto_type == 1:
t1_keyvec = "QDCVEPMU675RUBSZ"
if self.magic == 'TEXtREAd':
bookkey_data = self.sect[0x0E:0x0E+16]
elif self.mobi_version < 0:
bookkey_data = self.sect[0x90:0x90+16]
else:
bookkey_data = self.sect[self.mobi_length+16:self.mobi_length+32]
pid = "00000000"
found_key = PC1(t1_keyvec, bookkey_data)
else :
# calculate the keys
drm_ptr, drm_count, drm_size, drm_flags = struct.unpack('>LLLL', self.sect[0xA8:0xA8+16])
if drm_count == 0:
raise DrmException("Not yet initialised with PID. Must be opened with Mobipocket Reader first.")
found_key, pid = self.parseDRM(self.sect[drm_ptr:drm_ptr+drm_size], drm_count, goodpids)
if not found_key:
raise DrmException("No key found in " + str(len(goodpids)) + " keys tried. Please report this failure for help.")
# kill the drm keys
self.patchSection(0, "\0" * drm_size, drm_ptr)
# kill the drm pointers
self.patchSection(0, "\xff" * 4 + "\0" * 12, 0xA8)
if pid=="00000000":
print "File has default encryption, no specific PID."
else:
print "File is encoded with PID "+checksumPid(pid)+"."
# clear the crypto type
self.patchSection(0, "\0" * 2, 0xC)
# decrypt sections
print "Decrypting. Please wait . . .",
mobidataList = []
mobidataList.append(self.data_file[:self.sections[1][0]])
for i in xrange(1, self.records+1):
data = self.loadSection(i)
extra_size = getSizeOfTrailingDataEntries(data, len(data), self.extra_data_flags)
if i%100 == 0:
print ".",
# print "record %d, extra_size %d" %(i,extra_size)
decoded_data = PC1(found_key, data[0:len(data) - extra_size])
if i==1:
self.print_replica = (decoded_data[0:4] == '%MOP')
mobidataList.append(decoded_data)
if extra_size > 0:
mobidataList.append(data[-extra_size:])
if self.num_sections > self.records+1:
mobidataList.append(self.data_file[self.sections[self.records+1][0]:])
self.mobi_data = "".join(mobidataList)
print "done"
return
def getUnencryptedBook(infile,pid,announce=True):
if not os.path.isfile(infile):
raise DrmException('Input File Not Found')
book = MobiBook(infile,announce)
book.processBook([pid])
return book.mobi_data
def getUnencryptedBookWithList(infile,pidlist,announce=True):
if not os.path.isfile(infile):
raise DrmException('Input File Not Found')
book = MobiBook(infile, announce)
book.processBook(pidlist)
return book.mobi_data
def main(argv=sys.argv):
print ('MobiDeDrm v%(__version__)s. '
'Copyright 2008-2012 The Dark Reverser et al.' % globals())
if len(argv)<3 or len(argv)>4:
print "Removes protection from Kindle/Mobipocket, Kindle/KF8 and Kindle/Print Replica ebooks"
print "Usage:"
print " %s <infile> <outfile> [<Comma separated list of PIDs to try>]" % sys.argv[0]
return 1
else:
infile = argv[1]
outfile = argv[2]
if len(argv) is 4:
pidlist = argv[3].split(',')
else:
pidlist = {}
try:
stripped_file = getUnencryptedBookWithList(infile, pidlist, False)
file(outfile, 'wb').write(stripped_file)
except DrmException, e:
print "Error: %s" % e
return 1
return 0
if __name__ == "__main__":
sys.exit(main())

189
Other_Tools/Additional_Tools/lib/mobihuff.py
View File

@@ -1,189 +0,0 @@
# This is a python script. You need a Python interpreter to run it.
# For example, ActiveState Python, which exists for windows.
#
# Big Thanks to Igor SKOCHINSKY for providing me with all his information
# and source code relating to the inner workings of this compression scheme.
# Without it, I wouldn't be able to solve this as easily.
#
# Changelog
# 0.01 - Initial version
# 0.02 - Fix issue with size computing
# 0.03 - Fix issue with some files
# 0.04 - make stdout self flushing and fix return values
class Unbuffered:
def __init__(self, stream):
self.stream = stream
def write(self, data):
self.stream.write(data)
self.stream.flush()
def __getattr__(self, attr):
return getattr(self.stream, attr)
import sys
sys.stdout=Unbuffered(sys.stdout)
import struct
class BitReader:
def __init__(self, data):
self.data, self.pos, self.nbits = data + "\x00\x00\x00\x00", 0, len(data) * 8
def peek(self, n):
r, g = 0, 0
while g < n:
r, g = (r << 8) | ord(self.data[(self.pos+g)>>3]), g + 8 - ((self.pos+g) & 7)
return (r >> (g - n)) & ((1 << n) - 1)
def eat(self, n):
self.pos += n
return self.pos <= self.nbits
def left(self):
return self.nbits - self.pos
class HuffReader:
def __init__(self, huffs):
self.huffs = huffs
h = huffs[0]
if huffs[0][0:4] != 'HUFF' or huffs[0][4:8] != '\x00\x00\x00\x18':
raise ValueError('invalid huff1 header')
if huffs[1][0:4] != 'CDIC' or huffs[1][4:8] != '\x00\x00\x00\x10':
raise ValueError('invalid huff2 header')
self.entry_bits, = struct.unpack('>L', huffs[1][12:16])
off1,off2 = struct.unpack('>LL', huffs[0][16:24])
self.dict1 = struct.unpack('<256L', huffs[0][off1:off1+256*4])
self.dict2 = struct.unpack('<64L', huffs[0][off2:off2+64*4])
self.dicts = huffs[1:]
self.r = ''
def _unpack(self, bits, depth = 0):
if depth > 32:
raise ValueError('corrupt file')
while bits.left():
dw = bits.peek(32)
v = self.dict1[dw >> 24]
codelen = v & 0x1F
assert codelen != 0
code = dw >> (32 - codelen)
r = (v >> 8)
if not (v & 0x80):
while code < self.dict2[(codelen-1)*2]:
codelen += 1
code = dw >> (32 - codelen)
r = self.dict2[(codelen-1)*2+1]
r -= code
assert codelen != 0
if not bits.eat(codelen):
return
dicno = r >> self.entry_bits
off1 = 16 + (r - (dicno << self.entry_bits)) * 2
dic = self.dicts[dicno]
off2 = 16 + ord(dic[off1]) * 256 + ord(dic[off1+1])
blen = ord(dic[off2]) * 256 + ord(dic[off2+1])
slice = dic[off2+2:off2+2+(blen&0x7fff)]
if blen & 0x8000:
self.r += slice
else:
self._unpack(BitReader(slice), depth + 1)
def unpack(self, data):
self.r = ''
self._unpack(BitReader(data))
return self.r
class Sectionizer:
def __init__(self, filename, ident):
self.contents = file(filename, 'rb').read()
self.header = self.contents[0:72]
self.num_sections, = struct.unpack('>H', self.contents[76:78])
if self.header[0x3C:0x3C+8] != ident:
raise ValueError('Invalid file format')
self.sections = []
for i in xrange(self.num_sections):
offset, a1,a2,a3,a4 = struct.unpack('>LBBBB', self.contents[78+i*8:78+i*8+8])
flags, val = a1, a2<<16|a3<<8|a4
self.sections.append( (offset, flags, val) )
def loadSection(self, section):
if section + 1 == self.num_sections:
end_off = len(self.contents)
else:
end_off = self.sections[section + 1][0]
off = self.sections[section][0]
return self.contents[off:end_off]
def getSizeOfTrailingDataEntry(ptr, size):
bitpos, result = 0, 0
while True:
v = ord(ptr[size-1])
result |= (v & 0x7F) << bitpos
bitpos += 7
size -= 1
if (v & 0x80) != 0 or (bitpos >= 28) or (size == 0):
return result
def getSizeOfTrailingDataEntries(ptr, size, flags):
num = 0
flags >>= 1
while flags:
if flags & 1:
num += getSizeOfTrailingDataEntry(ptr, size - num)
flags >>= 1
return num
def unpackBook(input_file):
sect = Sectionizer(input_file, 'BOOKMOBI')
header = sect.loadSection(0)
crypto_type, = struct.unpack('>H', header[0xC:0xC+2])
if crypto_type != 0:
raise ValueError('The book is encrypted. Run mobidedrm first')
if header[0:2] != 'DH':
raise ValueError('invalid compression type')
extra_flags, = struct.unpack('>L', header[0xF0:0xF4])
records, = struct.unpack('>H', header[0x8:0x8+2])
huffoff,huffnum = struct.unpack('>LL', header[0x70:0x78])
huffs = [sect.loadSection(i) for i in xrange(huffoff, huffoff+huffnum)]
huff = HuffReader(huffs)
def decompressSection(nr):
data = sect.loadSection(nr)
trail_size = getSizeOfTrailingDataEntries(data, len(data), extra_flags)
return huff.unpack(data[0:len(data)-trail_size])
r = ''
for i in xrange(1, records+1):
r += decompressSection(i)
return r
def main(argv=sys.argv):
print "MobiHuff v0.03"
print " Copyright (c) 2008 The Dark Reverser <dark.reverser@googlemail.com>"
if len(sys.argv)!=3:
print ""
print "Description:"
print " Unpacks the new mobipocket huffdic compression."
print " This program works with unencrypted files only."
print "Usage:"
print " mobihuff.py infile.mobi outfile.html"
return 1
else:
infile = sys.argv[1]
outfile = sys.argv[2]
try:
print "Decompressing...",
result = unpackBook(infile)
file(outfile, 'wb').write(result)
print "done"
except ValueError, e:
print
print "Error: %s" % e
return 1
return 0
if __name__ == "__main__":
sys.exit(main())

529
Other_Tools/Additional_Tools/lib/prc.py
View File

@@ -1,529 +0,0 @@
#
# $Id: prc.py,v 1.3 2001/12/27 08:48:02 rob Exp $
#
# Copyright 1998-2001 Rob Tillotson <rob@pyrite.org>
# All Rights Reserved
#
# Permission to use, copy, modify, and distribute this software and
# its documentation for any purpose and without fee or royalty is
# hereby granted, provided that the above copyright notice appear in
# all copies and that both the copyright notice and this permission
# notice appear in supporting documentation or portions thereof,
# including modifications, that you you make.
#
# THE AUTHOR ROB TILLOTSON DISCLAIMS ALL WARRANTIES WITH REGARD TO
# THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY
# AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
# SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER
# RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF
# CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
# CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE!
#
"""PRC/PDB file I/O in pure Python.
This module serves two purposes: one, it allows access to Palm OS(tm)
database files on the desktop in pure Python without requiring
pilot-link (hence, it may be useful for import/export utilities),
and two, it caches the contents of the file in memory so it can
be freely modified using an identical API to databases over a
DLP connection.
"""
__version__ = '$Id: prc.py,v 1.3 2001/12/27 08:48:02 rob Exp $'
__copyright__ = 'Copyright 1998-2001 Rob Tillotson <robt@debian.org>'
# temporary hack until we get gettext support again
def _(s): return s
#
# DBInfo structure:
#
# int more
# unsigned int flags
# unsigned int miscflags
# unsigned long type
# unsigned long creator
# unsigned int version
# unsigned long modnum
# time_t createDate, modifydate, backupdate
# unsigned int index
# char name[34]
#
#
# DB Header:
# 32 name
# 2 flags
# 2 version
# 4 creation time
# 4 modification time
# 4 backup time
# 4 modification number
# 4 appinfo offset
# 4 sortinfo offset
# 4 type
# 4 creator
# 4 unique id seed (garbage?)
# 4 next record list id (normally 0)
# 2 num of records for this header
# (maybe 2 more bytes)
#
# Resource entry header: (if low bit of attr = 1)
# 4 type
# 2 id
# 4 offset
#
# record entry header: (if low bit of attr = 0)
# 4 offset
# 1 attributes
# 3 unique id
#
# then 2 bytes of 0
#
# then appinfo then sortinfo
#
import sys, os, stat, struct
PI_HDR_SIZE = 78
PI_RESOURCE_ENT_SIZE = 10
PI_RECORD_ENT_SIZE = 8
PILOT_TIME_DELTA = 2082844800L
flagResource = 0x0001
flagReadOnly = 0x0002
flagAppInfoDirty = 0x0004
flagBackup = 0x0008
flagOpen = 0x8000
# 2.x
flagNewer = 0x0010
flagReset = 0x0020
#
flagExcludeFromSync = 0x0080
attrDeleted = 0x80
attrDirty = 0x40
attrBusy = 0x20
attrSecret = 0x10
attrArchived = 0x08
default_info = {
'name': '',
'type': 'DATA',
'creator': ' ',
'createDate': 0,
'modifyDate': 0,
'backupDate': 0,
'modnum': 0,
'version': 0,
'flagReset': 0,
'flagResource': 0,
'flagNewer': 0,
'flagExcludeFromSync': 0,
'flagAppInfoDirty': 0,
'flagReadOnly': 0,
'flagBackup': 0,
'flagOpen': 0,
'more': 0,
'index': 0
}
def null_terminated(s):
for x in range(0, len(s)):
if s[x] == '\000': return s[:x]
return s
def trim_null(s):
return string.split(s, '\0')[0]
def pad_null(s, l):
if len(s) > l - 1:
s = s[:l-1]
s = s + '\0'
if len(s) < l: s = s + '\0' * (l - len(s))
return s
#
# new stuff
# Record object to be put in tree...
class PRecord:
def __init__(self, attr=0, id=0, category=0, raw=''):
self.raw = raw
self.id = id
self.attr = attr
self.category = category
# comparison and hashing are done by ID;
# thus, the id value *may not be changed* once
# the object is created.
def __cmp__(self, obj):
if type(obj) == type(0):
return cmp(self.id, obj)
else:
return cmp(self.id, obj.id)
def __hash__(self):
return self.id
class PResource:
def __init__(self, typ=' ', id=0, raw=''):
self.raw = raw
self.id = id
self.type = typ
def __cmp__(self, obj):
if type(obj) == type(()):
return cmp( (self.type, self.id), obj)
else:
return cmp( (self.type, self.id), (obj.type, obj.id) )
def __hash__(self):
return hash((self.type, self.id))
class PCache:
def __init__(self):
self.data = []
self.appblock = ''
self.sortblock = ''
self.dirty = 0
self.next = 0
self.info = {}
self.info.update(default_info)
# if allow_zero_ids is 1, then this prc behaves appropriately
# for a desktop database. That is, it never attempts to assign
# an ID, and lets new records be inserted with an ID of zero.
self.allow_zero_ids = 0
# pi-file API
def getRecords(self): return len(self.data)
def getAppBlock(self): return self.appblock and self.appblock or None
def setAppBlock(self, raw):
self.dirty = 1
self.appblock = raw
def getSortBlock(self): return self.sortblock and self.sortblock or None
def setSortBlock(self, raw):
self.dirty = 1
self.appblock = raw
def checkID(self, id): return id in self.data
def getRecord(self, i):
try: r = self.data[i]
except: return None
return r.raw, i, r.id, r.attr, r.category
def getRecordByID(self, id):
try:
i = self.data.index(id)
r = self.data[i]
except: return None
return r.raw, i, r.id, r.attr, r.category
def getResource(self, i):
try: r = self.data[i]
except: return None
return r.raw, r.type, r.id
def getDBInfo(self): return self.info
def setDBInfo(self, info):
self.dirty = 1
self.info = {}
self.info.update(info)
def updateDBInfo(self, info):
self.dirty = 1
self.info.update(info)
def setRecord(self, attr, id, cat, data):
if not self.allow_zero_ids and not id:
if not len(self.data): id = 1
else:
xid = self.data[0].id + 1
while xid in self.data: xid = xid + 1
id = xid
r = PRecord(attr, id, cat, data)
if id and id in self.data:
self.data.remove(id)
self.data.append(r)
self.dirty = 1
return id
def setRecordIdx(self, i, data):
self.data[i].raw = data
self.dirty = 1
def setResource(self, typ, id, data):
if (typ, id) in self.data:
self.data.remove((typ,id))
r = PResource(typ, id, data)
self.data.append(r)
self.dirty = 1
return id
def getNextRecord(self, cat):
while self.next < len(self.data):
r = self.data[self.next]
i = self.next
self.next = self.next + 1
if r.category == cat:
return r.raw, i, r.id, r.attr, r.category
return ''
def getNextModRecord(self, cat=-1):
while self.next < len(self.data):
r = self.data[self.next]
i = self.next
self.next = self.next + 1
if (r.attr & attrModified) and (cat < 0 or r.category == cat):
return r.raw, i, r.id, r.attr, r.category
def getResourceByID(self, type, id):
try: r = self.data[self.data.index((type,id))]
except: return None
return r.raw, r.type, r.id
def deleteRecord(self, id):
if not id in self.data: return None
self.data.remove(id)
self.dirty = 1
def deleteRecords(self):
self.data = []
self.dirty = 1
def deleteResource(self, type, id):
if not (type,id) in self.data: return None
self.data.remove((type,id))
self.dirty = 1
def deleteResources(self):
self.data = []
self.dirty = 1
def getRecordIDs(self, sort=0):
m = map(lambda x: x.id, self.data)
if sort: m.sort()
return m
def moveCategory(self, frm, to):
for r in self.data:
if r.category == frm:
r.category = to
self.dirty = 1
def deleteCategory(self, cat):
raise RuntimeError, _("unimplemented")
def purge(self):
ndata = []
# change to filter later
for r in self.data:
if (r.attr & attrDeleted):
continue
ndata.append(r)
self.data = ndata
self.dirty = 1
def resetNext(self):
self.next = 0
def resetFlags(self):
# special behavior for resources
if not self.info.get('flagResource',0):
# use map()
for r in self.data:
r.attr = r.attr & ~attrDirty
self.dirty = 1
import pprint
class File(PCache):
def __init__(self, name=None, read=1, write=0, info={}):
PCache.__init__(self)
self.filename = name
self.info.update(info)
self.writeback = write
self.isopen = 0
if read:
self.load(name)
self.isopen = 1
def close(self):
if self.writeback and self.dirty:
self.save(self.filename)
self.isopen = 0
def __del__(self):
if self.isopen: self.close()
def load(self, f):
if type(f) == type(''): f = open(f, 'rb')
data = f.read()
self.unpack(data)
def unpack(self, data):
if len(data) < PI_HDR_SIZE: raise IOError, _("file too short")
(name, flags, ver, ctime, mtime, btime, mnum, appinfo, sortinfo,
typ, creator, uid, nextrec, numrec) \
= struct.unpack('>32shhLLLlll4s4sllh', data[:PI_HDR_SIZE])
if nextrec or appinfo < 0 or sortinfo < 0 or numrec < 0:
raise IOError, _("invalid database header")
self.info = {
'name': null_terminated(name),
'type': typ,
'creator': creator,
'createDate': ctime - PILOT_TIME_DELTA,
'modifyDate': mtime - PILOT_TIME_DELTA,
'backupDate': btime - PILOT_TIME_DELTA,
'modnum': mnum,
'version': ver,
'flagReset': flags & flagReset,
'flagResource': flags & flagResource,
'flagNewer': flags & flagNewer,
'flagExcludeFromSync': flags & flagExcludeFromSync,
'flagAppInfoDirty': flags & flagAppInfoDirty,
'flagReadOnly': flags & flagReadOnly,
'flagBackup': flags & flagBackup,
'flagOpen': flags & flagOpen,
'more': 0,
'index': 0
}
rsrc = flags & flagResource
if rsrc: s = PI_RESOURCE_ENT_SIZE
else: s = PI_RECORD_ENT_SIZE
entries = []
pos = PI_HDR_SIZE
for x in range(0,numrec):
hstr = data[pos:pos+s]
pos = pos + s
if not hstr or len(hstr) < s:
raise IOError, _("bad database header")
if rsrc:
(typ, id, offset) = struct.unpack('>4shl', hstr)
entries.append((offset, typ, id))
else:
(offset, auid) = struct.unpack('>ll', hstr)
attr = (auid & 0xff000000) >> 24
uid = auid & 0x00ffffff
entries.append((offset, attr, uid))
offset = len(data)
entries.reverse()
for of, q, id in entries:
size = offset - of
if size < 0: raise IOError, _("bad pdb/prc record entry (size < 0)")
d = data[of:offset]
offset = of
if len(d) != size: raise IOError, _("failed to read record")
if rsrc:
r = PResource(q, id, d)
self.data.append(r)
else:
r = PRecord(q & 0xf0, id, q & 0x0f, d)
self.data.append(r)
self.data.reverse()
if sortinfo:
sortinfo_size = offset - sortinfo
offset = sortinfo
else:
sortinfo_size = 0
if appinfo:
appinfo_size = offset - appinfo
offset = appinfo
else:
appinfo_size = 0
if appinfo_size < 0 or sortinfo_size < 0:
raise IOError, _("bad database header (appinfo or sortinfo size < 0)")
if appinfo_size:
self.appblock = data[appinfo:appinfo+appinfo_size]
if len(self.appblock) != appinfo_size:
raise IOError, _("failed to read appinfo block")
if sortinfo_size:
self.sortblock = data[sortinfo:sortinfo+sortinfo_size]
if len(self.sortblock) != sortinfo_size:
raise IOError, _("failed to read sortinfo block")
def save(self, f):
"""Dump the cache to a file.
"""
if type(f) == type(''): f = open(f, 'wb')
# first, we need to precalculate the offsets.
if self.info.get('flagResource'):
entries_len = 10 * len(self.data)
else: entries_len = 8 * len(self.data)
off = PI_HDR_SIZE + entries_len + 2
if self.appblock:
appinfo_offset = off
off = off + len(self.appblock)
else:
appinfo_offset = 0
if self.sortblock:
sortinfo_offset = off
off = off + len(self.sortblock)
else:
sortinfo_offset = 0
rec_offsets = []
for x in self.data:
rec_offsets.append(off)
off = off + len(x.raw)
info = self.info
flg = 0
if info.get('flagResource',0): flg = flg | flagResource
if info.get('flagReadOnly',0): flg = flg | flagReadOnly
if info.get('flagAppInfoDirty',0): flg = flg | flagAppInfoDirty
if info.get('flagBackup',0): flg = flg | flagBackup
if info.get('flagOpen',0): flg = flg | flagOpen
if info.get('flagNewer',0): flg = flg | flagNewer
if info.get('flagReset',0): flg = flg | flagReset
# excludefromsync doesn't actually get stored?
hdr = struct.pack('>32shhLLLlll4s4sllh',
pad_null(info.get('name',''), 32),
flg,
info.get('version',0),
info.get('createDate',0L)+PILOT_TIME_DELTA,
info.get('modifyDate',0L)+PILOT_TIME_DELTA,
info.get('backupDate',0L)+PILOT_TIME_DELTA,
info.get('modnum',0),
appinfo_offset, # appinfo
sortinfo_offset, # sortinfo
info.get('type',' '),
info.get('creator',' '),
0, # uid???
0, # nextrec???
len(self.data))
f.write(hdr)
entries = []
record_data = []
rsrc = self.info.get('flagResource')
for x, off in map(None, self.data, rec_offsets):
if rsrc:
record_data.append(x.raw)
entries.append(struct.pack('>4shl', x.type, x.id, off))
else:
record_data.append(x.raw)
a = ((x.attr | x.category) << 24) | x.id
entries.append(struct.pack('>ll', off, a))
for x in entries: f.write(x)
f.write('\0\0') # padding? dunno, it's always there.
if self.appblock: f.write(self.appblock)
if self.sortblock: f.write(self.sortblock)
for x in record_data: f.write(x)

27
Other_Tools/Additional_Tools/lib/scrolltextwidget.py
View File

@@ -1,27 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import Tkinter
import Tkconstants
# basic scrolled text widget
class ScrolledText(Tkinter.Text):
def __init__(self, master=None, **kw):
self.frame = Tkinter.Frame(master)
self.vbar = Tkinter.Scrollbar(self.frame)
self.vbar.pack(side=Tkconstants.RIGHT, fill=Tkconstants.Y)
kw.update({'yscrollcommand': self.vbar.set})
Tkinter.Text.__init__(self, self.frame, **kw)
self.pack(side=Tkconstants.LEFT, fill=Tkconstants.BOTH, expand=True)
self.vbar['command'] = self.yview
# Copy geometry methods of self.frame without overriding Text
# methods = hack!
text_meths = vars(Tkinter.Text).keys()
methods = vars(Tkinter.Pack).keys() + vars(Tkinter.Grid).keys() + vars(Tkinter.Place).keys()
methods = set(methods).difference(text_meths)
for m in methods:
if m[0] != '_' and m != 'config' and m != 'configure':
setattr(self, m, getattr(self.frame, m))
def __str__(self):
return str(self.frame)

149
Other_Tools/Additional_Tools/lib/subasyncio.py
View File

@@ -1,149 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import os, sys
import signal
import threading
import subprocess
from subprocess import Popen, PIPE, STDOUT
# **heavily** chopped up and modfied version of asyncproc.py
# to make it actually work on Windows as well as Mac/Linux
# For the original see:
# "http://www.lysator.liu.se/~bellman/download/"
# author is "Thomas Bellman <bellman@lysator.liu.se>"
# available under GPL version 3 or Later
# create an asynchronous subprocess whose output can be collected in
# a non-blocking manner
# What a mess! Have to use threads just to get non-blocking io
# in a cross-platform manner
# luckily all thread use is hidden within this class
class Process(object):
def __init__(self, *params, **kwparams):
if len(params) <= 3:
kwparams.setdefault('stdin', subprocess.PIPE)
if len(params) <= 4:
kwparams.setdefault('stdout', subprocess.PIPE)
if len(params) <= 5:
kwparams.setdefault('stderr', subprocess.PIPE)
self.__pending_input = []
self.__collected_outdata = []
self.__collected_errdata = []
self.__exitstatus = None
self.__lock = threading.Lock()
self.__inputsem = threading.Semaphore(0)
self.__quit = False
self.__process = subprocess.Popen(*params, **kwparams)
if self.__process.stdin:
self.__stdin_thread = threading.Thread(
name="stdin-thread",
target=self.__feeder, args=(self.__pending_input,
self.__process.stdin))
self.__stdin_thread.setDaemon(True)
self.__stdin_thread.start()
if self.__process.stdout:
self.__stdout_thread = threading.Thread(
name="stdout-thread",
target=self.__reader, args=(self.__collected_outdata,
self.__process.stdout))
self.__stdout_thread.setDaemon(True)
self.__stdout_thread.start()
if self.__process.stderr:
self.__stderr_thread = threading.Thread(
name="stderr-thread",
target=self.__reader, args=(self.__collected_errdata,
self.__process.stderr))
self.__stderr_thread.setDaemon(True)
self.__stderr_thread.start()
def pid(self):
return self.__process.pid
def kill(self, signal):
self.__process.send_signal(signal)
# check on subprocess (pass in 'nowait') to act like poll
def wait(self, flag):
if flag.lower() == 'nowait':
rc = self.__process.poll()
else:
rc = self.__process.wait()
if rc != None:
if self.__process.stdin:
self.closeinput()
if self.__process.stdout:
self.__stdout_thread.join()
if self.__process.stderr:
self.__stderr_thread.join()
return self.__process.returncode
def terminate(self):
if self.__process.stdin:
self.closeinput()
self.__process.terminate()
# thread gets data from subprocess stdout
def __reader(self, collector, source):
while True:
data = os.read(source.fileno(), 65536)
self.__lock.acquire()
collector.append(data)
self.__lock.release()
if data == "":
source.close()
break
return
# thread feeds data to subprocess stdin
def __feeder(self, pending, drain):
while True:
self.__inputsem.acquire()
self.__lock.acquire()
if not pending and self.__quit:
drain.close()
self.__lock.release()
break
data = pending.pop(0)
self.__lock.release()
drain.write(data)
# non-blocking read of data from subprocess stdout
def read(self):
self.__lock.acquire()
outdata = "".join(self.__collected_outdata)
del self.__collected_outdata[:]
self.__lock.release()
return outdata
# non-blocking read of data from subprocess stderr
def readerr(self):
self.__lock.acquire()
errdata = "".join(self.__collected_errdata)
del self.__collected_errdata[:]
self.__lock.release()
return errdata
# non-blocking write to stdin of subprocess
def write(self, data):
if self.__process.stdin is None:
raise ValueError("Writing to process with stdin not a pipe")
self.__lock.acquire()
self.__pending_input.append(data)
self.__inputsem.release()
self.__lock.release()
# close stdinput of subprocess
def closeinput(self):
self.__lock.acquire()
self.__quit = True
self.__inputsem.release()
self.__lock.release()

18
Other_Tools/Adobe_PDF_Tools/README_ineptpdf.txt
View File

@@ -1,18 +0,0 @@
From Apprentice Alf's Blog
Adobe Adept PDF, .pdf
This directory includes modified versions of the I♥CABBAGES Adobe Adept inept scripts for pdfs. These scripts have been modified to work with OpenSSL on Windows as well as Linux and Mac OS X. If a Windows User has OpenSSL installed, these scripts will make use of it in place of PyCrypto.
The wonderful I♥CABBAGES has produced scripts that will remove the DRM from ePubs and PDFs encryped with Adobe’s DRM. These scripts require installation of the PyCrypto python package *or* the OpenSSL library on Windows. For Mac OS X and Linux boxes, these scripts use the already installed OpenSSL libcrypto so there is no additional requirements for these platforms.
For more info, see the author's blog:
http://i-u2665-cabbages.blogspot.com/2009_02_01_archive.html
There are two scripts:
The first is called ineptkey_vX.X.pyw. Simply double-click to launch it and it will create a key file that is needed later to actually remove the DRM. This script need only be run once unless you change your ADE account information.
The second is called in ineptpdf_vX.X.pyw. Simply double-click to launch it. It will ask for your previously generated key file and the path to the book you want to remove the DRM from.
Both of these scripts are gui python programs. Python 2.X (32 bit) is already installed in Mac OSX. We recommend ActiveState's Active Python Version 2.X (32 bit) for Windows users.

468
Other_Tools/Adobe_PDF_Tools/ineptkey.pyw
View File

@@ -1,468 +0,0 @@
#! /usr/bin/python
# -*- coding: utf-8 -*-
from __future__ import with_statement
# ineptkey.pyw, version 5.5
# Copyright © 2009-2010 i♥cabbages
# Released under the terms of the GNU General Public Licence, version 3 or
# later. <http://www.gnu.org/licenses/>
# Windows users: Before running this program, you must first install Python 2.6
# from <http://www.python.org/download/> and PyCrypto from
# <http://www.voidspace.org.uk/python/modules.shtml#pycrypto> (make certain
# to install the version for Python 2.6). Then save this script file as
# ineptkey.pyw and double-click on it to run it. It will create a file named
# adeptkey.der in the same directory. This is your ADEPT user key.
#
# Mac OS X users: Save this script file as ineptkey.pyw. You can run this
# program from the command line (pythonw ineptkey.pyw) or by double-clicking
# it when it has been associated with PythonLauncher. It will create a file
# named adeptkey.der in the same directory. This is your ADEPT user key.
# Revision history:
# 1 - Initial release, for Adobe Digital Editions 1.7
# 2 - Better algorithm for finding pLK; improved error handling
# 3 - Rename to INEPT
# 4 - Series of changes by joblack (and others?) --
# 4.1 - quick beta fix for ADE 1.7.2 (anon)
# 4.2 - added old 1.7.1 processing
# 4.3 - better key search
# 4.4 - Make it working on 64-bit Python
# 5 - Clean up and improve 4.x changes;
# Clean up and merge OS X support by unknown
# 5.1 - add support for using OpenSSL on Windows in place of PyCrypto
# 5.2 - added support for output of key to a particular file
# 5.3 - On Windows try PyCrypto first, OpenSSL next
# 5.4 - Modify interface to allow use of import
# 5.5 - Fix for potential problem with PyCrypto
"""
Retrieve Adobe ADEPT user key.
"""
__license__ = 'GPL v3'
import sys
import os
import struct
import Tkinter
import Tkconstants
import tkMessageBox
import traceback
class ADEPTError(Exception):
pass
if sys.platform.startswith('win'):
from ctypes import windll, c_char_p, c_wchar_p, c_uint, POINTER, byref, \
create_unicode_buffer, create_string_buffer, CFUNCTYPE, addressof, \
string_at, Structure, c_void_p, cast, c_size_t, memmove, CDLL, c_int, \
c_long, c_ulong
from ctypes.wintypes import LPVOID, DWORD, BOOL
import _winreg as winreg
def _load_crypto_libcrypto():
from ctypes.util import find_library
libcrypto = find_library('libeay32')
if libcrypto is None:
raise ADEPTError('libcrypto not found')
libcrypto = CDLL(libcrypto)
AES_MAXNR = 14
c_char_pp = POINTER(c_char_p)
c_int_p = POINTER(c_int)
class AES_KEY(Structure):
_fields_ = [('rd_key', c_long * (4 * (AES_MAXNR + 1))),
('rounds', c_int)]
AES_KEY_p = POINTER(AES_KEY)
def F(restype, name, argtypes):
func = getattr(libcrypto, name)
func.restype = restype
func.argtypes = argtypes
return func
AES_set_decrypt_key = F(c_int, 'AES_set_decrypt_key',
[c_char_p, c_int, AES_KEY_p])
AES_cbc_encrypt = F(None, 'AES_cbc_encrypt',
[c_char_p, c_char_p, c_ulong, AES_KEY_p, c_char_p,
c_int])
class AES(object):
def __init__(self, userkey):
self._blocksize = len(userkey)
if (self._blocksize != 16) and (self._blocksize != 24) and (self._blocksize != 32) :
raise ADEPTError('AES improper key used')
key = self._key = AES_KEY()
rv = AES_set_decrypt_key(userkey, len(userkey) * 8, key)
if rv < 0:
raise ADEPTError('Failed to initialize AES key')
def decrypt(self, data):
out = create_string_buffer(len(data))
iv = ("\x00" * self._blocksize)
rv = AES_cbc_encrypt(data, out, len(data), self._key, iv, 0)
if rv == 0:
raise ADEPTError('AES decryption failed')
return out.raw
return AES
def _load_crypto_pycrypto():
from Crypto.Cipher import AES as _AES
class AES(object):
def __init__(self, key):
self._aes = _AES.new(key, _AES.MODE_CBC, '\x00'*16)
def decrypt(self, data):
return self._aes.decrypt(data)
return AES
def _load_crypto():
AES = None
for loader in (_load_crypto_pycrypto, _load_crypto_libcrypto):
try:
AES = loader()
break
except (ImportError, ADEPTError):
pass
return AES
AES = _load_crypto()
DEVICE_KEY_PATH = r'Software\Adobe\Adept\Device'
PRIVATE_LICENCE_KEY_PATH = r'Software\Adobe\Adept\Activation'
MAX_PATH = 255
kernel32 = windll.kernel32
advapi32 = windll.advapi32
crypt32 = windll.crypt32
def GetSystemDirectory():
GetSystemDirectoryW = kernel32.GetSystemDirectoryW
GetSystemDirectoryW.argtypes = [c_wchar_p, c_uint]
GetSystemDirectoryW.restype = c_uint
def GetSystemDirectory():
buffer = create_unicode_buffer(MAX_PATH + 1)
GetSystemDirectoryW(buffer, len(buffer))
return buffer.value
return GetSystemDirectory
GetSystemDirectory = GetSystemDirectory()
def GetVolumeSerialNumber():
GetVolumeInformationW = kernel32.GetVolumeInformationW
GetVolumeInformationW.argtypes = [c_wchar_p, c_wchar_p, c_uint,
POINTER(c_uint), POINTER(c_uint),
POINTER(c_uint), c_wchar_p, c_uint]
GetVolumeInformationW.restype = c_uint
def GetVolumeSerialNumber(path):
vsn = c_uint(0)
GetVolumeInformationW(
path, None, 0, byref(vsn), None, None, None, 0)
return vsn.value
return GetVolumeSerialNumber
GetVolumeSerialNumber = GetVolumeSerialNumber()
def GetUserName():
GetUserNameW = advapi32.GetUserNameW
GetUserNameW.argtypes = [c_wchar_p, POINTER(c_uint)]
GetUserNameW.restype = c_uint
def GetUserName():
buffer = create_unicode_buffer(32)
size = c_uint(len(buffer))
while not GetUserNameW(buffer, byref(size)):
buffer = create_unicode_buffer(len(buffer) * 2)
size.value = len(buffer)
return buffer.value.encode('utf-16-le')[::2]
return GetUserName
GetUserName = GetUserName()
PAGE_EXECUTE_READWRITE = 0x40
MEM_COMMIT = 0x1000
MEM_RESERVE = 0x2000
def VirtualAlloc():
_VirtualAlloc = kernel32.VirtualAlloc
_VirtualAlloc.argtypes = [LPVOID, c_size_t, DWORD, DWORD]
_VirtualAlloc.restype = LPVOID
def VirtualAlloc(addr, size, alloctype=(MEM_COMMIT | MEM_RESERVE),
protect=PAGE_EXECUTE_READWRITE):
return _VirtualAlloc(addr, size, alloctype, protect)
return VirtualAlloc
VirtualAlloc = VirtualAlloc()
MEM_RELEASE = 0x8000
def VirtualFree():
_VirtualFree = kernel32.VirtualFree
_VirtualFree.argtypes = [LPVOID, c_size_t, DWORD]
_VirtualFree.restype = BOOL
def VirtualFree(addr, size=0, freetype=MEM_RELEASE):
return _VirtualFree(addr, size, freetype)
return VirtualFree
VirtualFree = VirtualFree()
class NativeFunction(object):
def __init__(self, restype, argtypes, insns):
self._buf = buf = VirtualAlloc(None, len(insns))
memmove(buf, insns, len(insns))
ftype = CFUNCTYPE(restype, *argtypes)
self._native = ftype(buf)
def __call__(self, *args):
return self._native(*args)
def __del__(self):
if self._buf is not None:
VirtualFree(self._buf)
self._buf = None
if struct.calcsize("P") == 4:
CPUID0_INSNS = (
"\x53" # push %ebx
"\x31\xc0" # xor %eax,%eax
"\x0f\xa2" # cpuid
"\x8b\x44\x24\x08" # mov 0x8(%esp),%eax
"\x89\x18" # mov %ebx,0x0(%eax)
"\x89\x50\x04" # mov %edx,0x4(%eax)
"\x89\x48\x08" # mov %ecx,0x8(%eax)
"\x5b" # pop %ebx
"\xc3" # ret
)
CPUID1_INSNS = (
"\x53" # push %ebx
"\x31\xc0" # xor %eax,%eax
"\x40" # inc %eax
"\x0f\xa2" # cpuid
"\x5b" # pop %ebx
"\xc3" # ret
)
else:
CPUID0_INSNS = (
"\x49\x89\xd8" # mov %rbx,%r8
"\x49\x89\xc9" # mov %rcx,%r9
"\x48\x31\xc0" # xor %rax,%rax
"\x0f\xa2" # cpuid
"\x4c\x89\xc8" # mov %r9,%rax
"\x89\x18" # mov %ebx,0x0(%rax)
"\x89\x50\x04" # mov %edx,0x4(%rax)
"\x89\x48\x08" # mov %ecx,0x8(%rax)
"\x4c\x89\xc3" # mov %r8,%rbx
"\xc3" # retq
)
CPUID1_INSNS = (
"\x53" # push %rbx
"\x48\x31\xc0" # xor %rax,%rax
"\x48\xff\xc0" # inc %rax
"\x0f\xa2" # cpuid
"\x5b" # pop %rbx
"\xc3" # retq
)
def cpuid0():
_cpuid0 = NativeFunction(None, [c_char_p], CPUID0_INSNS)
buf = create_string_buffer(12)
def cpuid0():
_cpuid0(buf)
return buf.raw
return cpuid0
cpuid0 = cpuid0()
cpuid1 = NativeFunction(c_uint, [], CPUID1_INSNS)
class DataBlob(Structure):
_fields_ = [('cbData', c_uint),
('pbData', c_void_p)]
DataBlob_p = POINTER(DataBlob)
def CryptUnprotectData():
_CryptUnprotectData = crypt32.CryptUnprotectData
_CryptUnprotectData.argtypes = [DataBlob_p, c_wchar_p, DataBlob_p,
c_void_p, c_void_p, c_uint, DataBlob_p]
_CryptUnprotectData.restype = c_uint
def CryptUnprotectData(indata, entropy):
indatab = create_string_buffer(indata)
indata = DataBlob(len(indata), cast(indatab, c_void_p))
entropyb = create_string_buffer(entropy)
entropy = DataBlob(len(entropy), cast(entropyb, c_void_p))
outdata = DataBlob()
if not _CryptUnprotectData(byref(indata), None, byref(entropy),
None, None, 0, byref(outdata)):
raise ADEPTError("Failed to decrypt user key key (sic)")
return string_at(outdata.pbData, outdata.cbData)
return CryptUnprotectData
CryptUnprotectData = CryptUnprotectData()
def retrieve_key(keypath):
if AES is None:
tkMessageBox.showerror(
"ADEPT Key",
"This script requires PyCrypto or OpenSSL which must be installed "
"separately. Read the top-of-script comment for details.")
return False
root = GetSystemDirectory().split('\\')[0] + '\\'
serial = GetVolumeSerialNumber(root)
vendor = cpuid0()
signature = struct.pack('>I', cpuid1())[1:]
user = GetUserName()
entropy = struct.pack('>I12s3s13s', serial, vendor, signature, user)
cuser = winreg.HKEY_CURRENT_USER
try:
regkey = winreg.OpenKey(cuser, DEVICE_KEY_PATH)
except WindowsError:
raise ADEPTError("Adobe Digital Editions not activated")
device = winreg.QueryValueEx(regkey, 'key')[0]
keykey = CryptUnprotectData(device, entropy)
userkey = None
try:
plkroot = winreg.OpenKey(cuser, PRIVATE_LICENCE_KEY_PATH)
except WindowsError:
raise ADEPTError("Could not locate ADE activation")
for i in xrange(0, 16):
try:
plkparent = winreg.OpenKey(plkroot, "%04d" % (i,))
except WindowsError:
break
ktype = winreg.QueryValueEx(plkparent, None)[0]
if ktype != 'credentials':
continue
for j in xrange(0, 16):
try:
plkkey = winreg.OpenKey(plkparent, "%04d" % (j,))
except WindowsError:
break
ktype = winreg.QueryValueEx(plkkey, None)[0]
if ktype != 'privateLicenseKey':
continue
userkey = winreg.QueryValueEx(plkkey, 'value')[0]
break
if userkey is not None:
break
if userkey is None:
raise ADEPTError('Could not locate privateLicenseKey')
userkey = userkey.decode('base64')
aes = AES(keykey)
userkey = aes.decrypt(userkey)
userkey = userkey[26:-ord(userkey[-1])]
with open(keypath, 'wb') as f:
f.write(userkey)
return True
elif sys.platform.startswith('darwin'):
import xml.etree.ElementTree as etree
import Carbon.File
import Carbon.Folder
import Carbon.Folders
import MacOS
ACTIVATION_PATH = 'Adobe/Digital Editions/activation.dat'
NSMAP = {'adept': 'http://ns.adobe.com/adept',
'enc': 'http://www.w3.org/2001/04/xmlenc#'}
def find_folder(domain, dtype):
try:
fsref = Carbon.Folder.FSFindFolder(domain, dtype, False)
return Carbon.File.pathname(fsref)
except MacOS.Error:
return None
def find_app_support_file(subpath):
dtype = Carbon.Folders.kApplicationSupportFolderType
for domain in Carbon.Folders.kUserDomain, Carbon.Folders.kLocalDomain:
path = find_folder(domain, dtype)
if path is None:
continue
path = os.path.join(path, subpath)
if os.path.isfile(path):
return path
return None
def retrieve_key(keypath):
actpath = find_app_support_file(ACTIVATION_PATH)
if actpath is None:
raise ADEPTError("Could not locate ADE activation")
tree = etree.parse(actpath)
adept = lambda tag: '{%s}%s' % (NSMAP['adept'], tag)
expr = '//%s/%s' % (adept('credentials'), adept('privateLicenseKey'))
userkey = tree.findtext(expr)
userkey = userkey.decode('base64')
userkey = userkey[26:]
with open(keypath, 'wb') as f:
f.write(userkey)
return True
elif sys.platform.startswith('cygwin'):
def retrieve_key(keypath):
tkMessageBox.showerror(
"ADEPT Key",
"This script requires a Windows-native Python, and cannot be run "
"under Cygwin. Please install a Windows-native Python and/or "
"check your file associations.")
return False
else:
def retrieve_key(keypath):
tkMessageBox.showerror(
"ADEPT Key",
"This script only supports Windows and Mac OS X. For Linux "
"you should be able to run ADE and this script under Wine (with "
"an appropriate version of Windows Python installed).")
return False
class ExceptionDialog(Tkinter.Frame):
def __init__(self, root, text):
Tkinter.Frame.__init__(self, root, border=5)
label = Tkinter.Label(self, text="Unexpected error:",
anchor=Tkconstants.W, justify=Tkconstants.LEFT)
label.pack(fill=Tkconstants.X, expand=0)
self.text = Tkinter.Text(self)
self.text.pack(fill=Tkconstants.BOTH, expand=1)
self.text.insert(Tkconstants.END, text)
def extractKeyfile(keypath):
try:
success = retrieve_key(keypath)
except ADEPTError, e:
print "Key generation Error: " + str(e)
return 1
except Exception, e:
print "General Error: " + str(e)
return 1
if not success:
return 1
return 0
def cli_main(argv=sys.argv):
keypath = argv[1]
return extractKeyfile(keypath)
def main(argv=sys.argv):
root = Tkinter.Tk()
root.withdraw()
progname = os.path.basename(argv[0])
keypath = 'adeptkey.der'
success = False
try:
success = retrieve_key(keypath)
except ADEPTError, e:
tkMessageBox.showerror("ADEPT Key", "Error: " + str(e))
except Exception:
root.wm_state('normal')
root.title('ADEPT Key')
text = traceback.format_exc()
ExceptionDialog(root, text).pack(fill=Tkconstants.BOTH, expand=1)
root.mainloop()
if not success:
return 1
tkMessageBox.showinfo(
"ADEPT Key", "Key successfully retrieved to %s" % (keypath))
return 0
if __name__ == '__main__':
if len(sys.argv) > 1:
sys.exit(cli_main())
sys.exit(main())

2255
Other_Tools/Adobe_PDF_Tools/ineptpdf.pyw
View File

File diff suppressed because it is too large Load Diff

3160
Other_Tools/Adobe_PDF_Tools/ineptpdf8.pyw
View File

File diff suppressed because it is too large Load Diff

18
Other_Tools/Adobe_ePub_Tools/README_ineptepub.txt
View File

@@ -1,18 +0,0 @@
From Apprentice Alf's Blog
Adobe Adept ePub, .epub
This directory includes modified versions of the I♥CABBAGES Adobe Adept inept scripts for epubs. These scripts have been modified to work with OpenSSL on Windows as well as Linux and Mac OS X. His original scripts can be found in the clearly labelled folder. If a Windows User has OpenSSL installed, these scripts will make use of it in place of PyCrypto.
The wonderful I♥CABBAGES has produced scripts that will remove the DRM from ePubs and PDFs encryped with Adobe’s DRM. These scripts require installation of the PyCrypto python package *or* the OpenSSL library on Windows. For Mac OS X and Linux boxes, these scripts use the already installed OpenSSL libcrypto so there is no additional requirements for these platforms.
For more info, see the author's blog:
http://i-u2665-cabbages.blogspot.com/2009_02_01_archive.html
There are two scripts:
The first is called ineptkey_vX.X.pyw. Simply double-click to launch it and it will create a key file that is needed later to actually remove the DRM. This script need only be run once unless you change your ADE account information.
The second is called in ineptepub_vX.X.pyw. Simply double-click to launch it. It will ask for your previously generated key file and the path to the book you want to remove the DRM from.
Both of these scripts are gui python programs. Python 2.X (32 bit) is already installed in Mac OSX. We recommend ActiveState's Active Python Version 2.X (32 bit) for Windows users.

478
Other_Tools/Adobe_ePub_Tools/ineptepub.pyw
View File

@@ -1,478 +0,0 @@
#! /usr/bin/python
# -*- coding: utf-8 -*-
from __future__ import with_statement
# ineptepub.pyw, version 5.7
# Copyright © 2009-2010 i♥cabbages
# Released under the terms of the GNU General Public Licence, version 3 or
# later. <http://www.gnu.org/licenses/>
# Windows users: Before running this program, you must first install Python 2.6
# from <http://www.python.org/download/> and PyCrypto from
# <http://www.voidspace.org.uk/python/modules.shtml#pycrypto> (make sure to
# install the version for Python 2.6). Save this script file as
# ineptepub.pyw and double-click on it to run it.
#
# Mac OS X users: Save this script file as ineptepub.pyw. You can run this
# program from the command line (pythonw ineptepub.pyw) or by double-clicking
# it when it has been associated with PythonLauncher.
# Revision history:
# 1 - Initial release
# 2 - Rename to INEPT, fix exit code
# 5 - Version bump to avoid (?) confusion;
# Improve OS X support by using OpenSSL when available
# 5.1 - Improve OpenSSL error checking
# 5.2 - Fix ctypes error causing segfaults on some systems
# 5.3 - add support for OpenSSL on Windows, fix bug with some versions of libcrypto 0.9.8 prior to path level o
# 5.4 - add support for encoding to 'utf-8' when building up list of files to decrypt from encryption.xml
# 5.5 - On Windows try PyCrypto first, OpenSSL next
# 5.6 - Modify interface to allow use with import
# 5.7 - Fix for potential problem with PyCrypto
"""
Decrypt Adobe ADEPT-encrypted EPUB books.
"""
__license__ = 'GPL v3'
import sys
import os
import zlib
import zipfile
from zipfile import ZipFile, ZIP_STORED, ZIP_DEFLATED
from contextlib import closing
import xml.etree.ElementTree as etree
import Tkinter
import Tkconstants
import tkFileDialog
import tkMessageBox
class ADEPTError(Exception):
pass
def _load_crypto_libcrypto():
from ctypes import CDLL, POINTER, c_void_p, c_char_p, c_int, c_long, \
Structure, c_ulong, create_string_buffer, cast
from ctypes.util import find_library
if sys.platform.startswith('win'):
libcrypto = find_library('libeay32')
else:
libcrypto = find_library('crypto')
if libcrypto is None:
raise ADEPTError('libcrypto not found')
libcrypto = CDLL(libcrypto)
RSA_NO_PADDING = 3
AES_MAXNR = 14
c_char_pp = POINTER(c_char_p)
c_int_p = POINTER(c_int)
class RSA(Structure):
pass
RSA_p = POINTER(RSA)
class AES_KEY(Structure):
_fields_ = [('rd_key', c_long * (4 * (AES_MAXNR + 1))),
('rounds', c_int)]
AES_KEY_p = POINTER(AES_KEY)
def F(restype, name, argtypes):
func = getattr(libcrypto, name)
func.restype = restype
func.argtypes = argtypes
return func
d2i_RSAPrivateKey = F(RSA_p, 'd2i_RSAPrivateKey',
[RSA_p, c_char_pp, c_long])
RSA_size = F(c_int, 'RSA_size', [RSA_p])
RSA_private_decrypt = F(c_int, 'RSA_private_decrypt',
[c_int, c_char_p, c_char_p, RSA_p, c_int])
RSA_free = F(None, 'RSA_free', [RSA_p])
AES_set_decrypt_key = F(c_int, 'AES_set_decrypt_key',
[c_char_p, c_int, AES_KEY_p])
AES_cbc_encrypt = F(None, 'AES_cbc_encrypt',
[c_char_p, c_char_p, c_ulong, AES_KEY_p, c_char_p,
c_int])
class RSA(object):
def __init__(self, der):
buf = create_string_buffer(der)
pp = c_char_pp(cast(buf, c_char_p))
rsa = self._rsa = d2i_RSAPrivateKey(None, pp, len(der))
if rsa is None:
raise ADEPTError('Error parsing ADEPT user key DER')
def decrypt(self, from_):
rsa = self._rsa
to = create_string_buffer(RSA_size(rsa))
dlen = RSA_private_decrypt(len(from_), from_, to, rsa,
RSA_NO_PADDING)
if dlen < 0:
raise ADEPTError('RSA decryption failed')
return to[:dlen]
def __del__(self):
if self._rsa is not None:
RSA_free(self._rsa)
self._rsa = None
class AES(object):
def __init__(self, userkey):
self._blocksize = len(userkey)
if (self._blocksize != 16) and (self._blocksize != 24) and (self._blocksize != 32) :
raise ADEPTError('AES improper key used')
return
key = self._key = AES_KEY()
rv = AES_set_decrypt_key(userkey, len(userkey) * 8, key)
if rv < 0:
raise ADEPTError('Failed to initialize AES key')
def decrypt(self, data):
out = create_string_buffer(len(data))
iv = ("\x00" * self._blocksize)
rv = AES_cbc_encrypt(data, out, len(data), self._key, iv, 0)
if rv == 0:
raise ADEPTError('AES decryption failed')
return out.raw
return (AES, RSA)
def _load_crypto_pycrypto():
from Crypto.Cipher import AES as _AES
from Crypto.PublicKey import RSA as _RSA
# ASN.1 parsing code from tlslite
class ASN1Error(Exception):
pass
class ASN1Parser(object):
class Parser(object):
def __init__(self, bytes):
self.bytes = bytes
self.index = 0
def get(self, length):
if self.index + length > len(self.bytes):
raise ASN1Error("Error decoding ASN.1")
x = 0
for count in range(length):
x <<= 8
x |= self.bytes[self.index]
self.index += 1
return x
def getFixBytes(self, lengthBytes):
bytes = self.bytes[self.index : self.index+lengthBytes]
self.index += lengthBytes
return bytes
def getVarBytes(self, lengthLength):
lengthBytes = self.get(lengthLength)
return self.getFixBytes(lengthBytes)
def getFixList(self, length, lengthList):
l = [0] * lengthList
for x in range(lengthList):
l[x] = self.get(length)
return l
def getVarList(self, length, lengthLength):
lengthList = self.get(lengthLength)
if lengthList % length != 0:
raise ASN1Error("Error decoding ASN.1")
lengthList = int(lengthList/length)
l = [0] * lengthList
for x in range(lengthList):
l[x] = self.get(length)
return l
def startLengthCheck(self, lengthLength):
self.lengthCheck = self.get(lengthLength)
self.indexCheck = self.index
def setLengthCheck(self, length):
self.lengthCheck = length
self.indexCheck = self.index
def stopLengthCheck(self):
if (self.index - self.indexCheck) != self.lengthCheck:
raise ASN1Error("Error decoding ASN.1")
def atLengthCheck(self):
if (self.index - self.indexCheck) < self.lengthCheck:
return False
elif (self.index - self.indexCheck) == self.lengthCheck:
return True
else:
raise ASN1Error("Error decoding ASN.1")
def __init__(self, bytes):
p = self.Parser(bytes)
p.get(1)
self.length = self._getASN1Length(p)
self.value = p.getFixBytes(self.length)
def getChild(self, which):
p = self.Parser(self.value)
for x in range(which+1):
markIndex = p.index
p.get(1)
length = self._getASN1Length(p)
p.getFixBytes(length)
return ASN1Parser(p.bytes[markIndex:p.index])
def _getASN1Length(self, p):
firstLength = p.get(1)
if firstLength<=127:
return firstLength
else:
lengthLength = firstLength & 0x7F
return p.get(lengthLength)
class AES(object):
def __init__(self, key):
self._aes = _AES.new(key, _AES.MODE_CBC, '\x00'*16)
def decrypt(self, data):
return self._aes.decrypt(data)
class RSA(object):
def __init__(self, der):
key = ASN1Parser([ord(x) for x in der])
key = [key.getChild(x).value for x in xrange(1, 4)]
key = [self.bytesToNumber(v) for v in key]
self._rsa = _RSA.construct(key)
def bytesToNumber(self, bytes):
total = 0L
for byte in bytes:
total = (total << 8) + byte
return total
def decrypt(self, data):
return self._rsa.decrypt(data)
return (AES, RSA)
def _load_crypto():
AES = RSA = None
cryptolist = (_load_crypto_libcrypto, _load_crypto_pycrypto)
if sys.platform.startswith('win'):
cryptolist = (_load_crypto_pycrypto, _load_crypto_libcrypto)
for loader in cryptolist:
try:
AES, RSA = loader()
break
except (ImportError, ADEPTError):
pass
return (AES, RSA)
AES, RSA = _load_crypto()
META_NAMES = ('mimetype', 'META-INF/rights.xml', 'META-INF/encryption.xml')
NSMAP = {'adept': 'http://ns.adobe.com/adept',
'enc': 'http://www.w3.org/2001/04/xmlenc#'}
class ZipInfo(zipfile.ZipInfo):
def __init__(self, *args, **kwargs):
if 'compress_type' in kwargs:
compress_type = kwargs.pop('compress_type')
super(ZipInfo, self).__init__(*args, **kwargs)
self.compress_type = compress_type
class Decryptor(object):
def __init__(self, bookkey, encryption):
enc = lambda tag: '{%s}%s' % (NSMAP['enc'], tag)
self._aes = AES(bookkey)
encryption = etree.fromstring(encryption)
self._encrypted = encrypted = set()
expr = './%s/%s/%s' % (enc('EncryptedData'), enc('CipherData'),
enc('CipherReference'))
for elem in encryption.findall(expr):
path = elem.get('URI', None)
if path is not None:
path = path.encode('utf-8')
encrypted.add(path)
def decompress(self, bytes):
dc = zlib.decompressobj(-15)
bytes = dc.decompress(bytes)
ex = dc.decompress('Z') + dc.flush()
if ex:
bytes = bytes + ex
return bytes
def decrypt(self, path, data):
if path in self._encrypted:
data = self._aes.decrypt(data)[16:]
data = data[:-ord(data[-1])]
data = self.decompress(data)
return data
class DecryptionDialog(Tkinter.Frame):
def __init__(self, root):
Tkinter.Frame.__init__(self, root, border=5)
self.status = Tkinter.Label(self, text='Select files for decryption')
self.status.pack(fill=Tkconstants.X, expand=1)
body = Tkinter.Frame(self)
body.pack(fill=Tkconstants.X, expand=1)
sticky = Tkconstants.E + Tkconstants.W
body.grid_columnconfigure(1, weight=2)
Tkinter.Label(body, text='Key file').grid(row=0)
self.keypath = Tkinter.Entry(body, width=30)
self.keypath.grid(row=0, column=1, sticky=sticky)
if os.path.exists('adeptkey.der'):
self.keypath.insert(0, 'adeptkey.der')
button = Tkinter.Button(body, text="...", command=self.get_keypath)
button.grid(row=0, column=2)
Tkinter.Label(body, text='Input file').grid(row=1)
self.inpath = Tkinter.Entry(body, width=30)
self.inpath.grid(row=1, column=1, sticky=sticky)
button = Tkinter.Button(body, text="...", command=self.get_inpath)
button.grid(row=1, column=2)
Tkinter.Label(body, text='Output file').grid(row=2)
self.outpath = Tkinter.Entry(body, width=30)
self.outpath.grid(row=2, column=1, sticky=sticky)
button = Tkinter.Button(body, text="...", command=self.get_outpath)
button.grid(row=2, column=2)
buttons = Tkinter.Frame(self)
buttons.pack()
botton = Tkinter.Button(
buttons, text="Decrypt", width=10, command=self.decrypt)
botton.pack(side=Tkconstants.LEFT)
Tkinter.Frame(buttons, width=10).pack(side=Tkconstants.LEFT)
button = Tkinter.Button(
buttons, text="Quit", width=10, command=self.quit)
button.pack(side=Tkconstants.RIGHT)
def get_keypath(self):
keypath = tkFileDialog.askopenfilename(
parent=None, title='Select ADEPT key file',
defaultextension='.der', filetypes=[('DER-encoded files', '.der'),
('All Files', '.*')])
if keypath:
keypath = os.path.normpath(keypath)
self.keypath.delete(0, Tkconstants.END)
self.keypath.insert(0, keypath)
return
def get_inpath(self):
inpath = tkFileDialog.askopenfilename(
parent=None, title='Select ADEPT-encrypted EPUB file to decrypt',
defaultextension='.epub', filetypes=[('EPUB files', '.epub'),
('All files', '.*')])
if inpath:
inpath = os.path.normpath(inpath)
self.inpath.delete(0, Tkconstants.END)
self.inpath.insert(0, inpath)
return
def get_outpath(self):
outpath = tkFileDialog.asksaveasfilename(
parent=None, title='Select unencrypted EPUB file to produce',
defaultextension='.epub', filetypes=[('EPUB files', '.epub'),
('All files', '.*')])
if outpath:
outpath = os.path.normpath(outpath)
self.outpath.delete(0, Tkconstants.END)
self.outpath.insert(0, outpath)
return
def decrypt(self):
keypath = self.keypath.get()
inpath = self.inpath.get()
outpath = self.outpath.get()
if not keypath or not os.path.exists(keypath):
self.status['text'] = 'Specified key file does not exist'
return
if not inpath or not os.path.exists(inpath):
self.status['text'] = 'Specified input file does not exist'
return
if not outpath:
self.status['text'] = 'Output file not specified'
return
if inpath == outpath:
self.status['text'] = 'Must have different input and output files'
return
argv = [sys.argv[0], keypath, inpath, outpath]
self.status['text'] = 'Decrypting...'
try:
cli_main(argv)
except Exception, e:
self.status['text'] = 'Error: ' + str(e)
return
self.status['text'] = 'File successfully decrypted'
def decryptBook(keypath, inpath, outpath):
with open(keypath, 'rb') as f:
keyder = f.read()
rsa = RSA(keyder)
with closing(ZipFile(open(inpath, 'rb'))) as inf:
namelist = set(inf.namelist())
if 'META-INF/rights.xml' not in namelist or \
'META-INF/encryption.xml' not in namelist:
raise ADEPTError('%s: not an ADEPT EPUB' % (inpath,))
for name in META_NAMES:
namelist.remove(name)
rights = etree.fromstring(inf.read('META-INF/rights.xml'))
adept = lambda tag: '{%s}%s' % (NSMAP['adept'], tag)
expr = './/%s' % (adept('encryptedKey'),)
bookkey = ''.join(rights.findtext(expr))
bookkey = rsa.decrypt(bookkey.decode('base64'))
# Padded as per RSAES-PKCS1-v1_5
if bookkey[-17] != '\x00':
raise ADEPTError('problem decrypting session key')
encryption = inf.read('META-INF/encryption.xml')
decryptor = Decryptor(bookkey[-16:], encryption)
kwds = dict(compression=ZIP_DEFLATED, allowZip64=False)
with closing(ZipFile(open(outpath, 'wb'), 'w', **kwds)) as outf:
zi = ZipInfo('mimetype', compress_type=ZIP_STORED)
outf.writestr(zi, inf.read('mimetype'))
for path in namelist:
data = inf.read(path)
outf.writestr(path, decryptor.decrypt(path, data))
return 0
def cli_main(argv=sys.argv):
progname = os.path.basename(argv[0])
if AES is None:
print "%s: This script requires OpenSSL or PyCrypto, which must be" \
" installed separately. Read the top-of-script comment for" \
" details." % (progname,)
return 1
if len(argv) != 4:
print "usage: %s KEYFILE INBOOK OUTBOOK" % (progname,)
return 1
keypath, inpath, outpath = argv[1:]
return decryptBook(keypath, inpath, outpath)
def gui_main():
root = Tkinter.Tk()
if AES is None:
root.withdraw()
tkMessageBox.showerror(
"INEPT EPUB Decrypter",
"This script requires OpenSSL or PyCrypto, which must be"
" installed separately. Read the top-of-script comment for"
" details.")
return 1
root.title('INEPT EPUB Decrypter')
root.resizable(True, False)
root.minsize(300, 0)
DecryptionDialog(root).pack(fill=Tkconstants.X, expand=1)
root.mainloop()
return 0
if __name__ == '__main__':
if len(sys.argv) > 1:
sys.exit(cli_main())
sys.exit(gui_main())

457
Other_Tools/Adobe_ePub_Tools/ineptkey.pyw
View File

@@ -1,457 +0,0 @@
#! /usr/bin/python
# -*- coding: utf-8 -*-
from __future__ import with_statement
# ineptkey.pyw, version 5.6
# Copyright © 2009-2010 i♥cabbages
# Released under the terms of the GNU General Public Licence, version 3 or
# later. <http://www.gnu.org/licenses/>
# Windows users: Before running this program, you must first install Python 2.6
# from <http://www.python.org/download/> and PyCrypto from
# <http://www.voidspace.org.uk/python/modules.shtml#pycrypto> (make certain
# to install the version for Python 2.6). Then save this script file as
# ineptkey.pyw and double-click on it to run it. It will create a file named
# adeptkey.der in the same directory. This is your ADEPT user key.
#
# Mac OS X users: Save this script file as ineptkey.pyw. You can run this
# program from the command line (pythonw ineptkey.pyw) or by double-clicking
# it when it has been associated with PythonLauncher. It will create a file
# named adeptkey.der in the same directory. This is your ADEPT user key.
# Revision history:
# 1 - Initial release, for Adobe Digital Editions 1.7
# 2 - Better algorithm for finding pLK; improved error handling
# 3 - Rename to INEPT
# 4 - Series of changes by joblack (and others?) --
# 4.1 - quick beta fix for ADE 1.7.2 (anon)
# 4.2 - added old 1.7.1 processing
# 4.3 - better key search
# 4.4 - Make it working on 64-bit Python
# 5 - Clean up and improve 4.x changes;
# Clean up and merge OS X support by unknown
# 5.1 - add support for using OpenSSL on Windows in place of PyCrypto
# 5.2 - added support for output of key to a particular file
# 5.3 - On Windows try PyCrypto first, OpenSSL next
# 5.4 - Modify interface to allow use of import
# 5.5 - Fix for potential problem with PyCrypto
# 5.6 - Revise to allow use in Plugins to eliminate need for duplicate code
"""
Retrieve Adobe ADEPT user key.
"""
__license__ = 'GPL v3'
import sys
import os
import struct
try:
from calibre.constants import iswindows, isosx
except:
iswindows = sys.platform.startswith('win')
isosx = sys.platform.startswith('darwin')
class ADEPTError(Exception):
pass
if iswindows:
from ctypes import windll, c_char_p, c_wchar_p, c_uint, POINTER, byref, \
create_unicode_buffer, create_string_buffer, CFUNCTYPE, addressof, \
string_at, Structure, c_void_p, cast, c_size_t, memmove, CDLL, c_int, \
c_long, c_ulong
from ctypes.wintypes import LPVOID, DWORD, BOOL
import _winreg as winreg
def _load_crypto_libcrypto():
from ctypes.util import find_library
libcrypto = find_library('libeay32')
if libcrypto is None:
raise ADEPTError('libcrypto not found')
libcrypto = CDLL(libcrypto)
AES_MAXNR = 14
c_char_pp = POINTER(c_char_p)
c_int_p = POINTER(c_int)
class AES_KEY(Structure):
_fields_ = [('rd_key', c_long * (4 * (AES_MAXNR + 1))),
('rounds', c_int)]
AES_KEY_p = POINTER(AES_KEY)
def F(restype, name, argtypes):
func = getattr(libcrypto, name)
func.restype = restype
func.argtypes = argtypes
return func
AES_set_decrypt_key = F(c_int, 'AES_set_decrypt_key',
[c_char_p, c_int, AES_KEY_p])
AES_cbc_encrypt = F(None, 'AES_cbc_encrypt',
[c_char_p, c_char_p, c_ulong, AES_KEY_p, c_char_p,
c_int])
class AES(object):
def __init__(self, userkey):
self._blocksize = len(userkey)
if (self._blocksize != 16) and (self._blocksize != 24) and (self._blocksize != 32) :
raise ADEPTError('AES improper key used')
key = self._key = AES_KEY()
rv = AES_set_decrypt_key(userkey, len(userkey) * 8, key)
if rv < 0:
raise ADEPTError('Failed to initialize AES key')
def decrypt(self, data):
out = create_string_buffer(len(data))
iv = ("\x00" * self._blocksize)
rv = AES_cbc_encrypt(data, out, len(data), self._key, iv, 0)
if rv == 0:
raise ADEPTError('AES decryption failed')
return out.raw
return AES
def _load_crypto_pycrypto():
from Crypto.Cipher import AES as _AES
class AES(object):
def __init__(self, key):
self._aes = _AES.new(key, _AES.MODE_CBC, '\x00'*16)
def decrypt(self, data):
return self._aes.decrypt(data)
return AES
def _load_crypto():
AES = None
for loader in (_load_crypto_pycrypto, _load_crypto_libcrypto):
try:
AES = loader()
break
except (ImportError, ADEPTError):
pass
return AES
AES = _load_crypto()
DEVICE_KEY_PATH = r'Software\Adobe\Adept\Device'
PRIVATE_LICENCE_KEY_PATH = r'Software\Adobe\Adept\Activation'
MAX_PATH = 255
kernel32 = windll.kernel32
advapi32 = windll.advapi32
crypt32 = windll.crypt32
def GetSystemDirectory():
GetSystemDirectoryW = kernel32.GetSystemDirectoryW
GetSystemDirectoryW.argtypes = [c_wchar_p, c_uint]
GetSystemDirectoryW.restype = c_uint
def GetSystemDirectory():
buffer = create_unicode_buffer(MAX_PATH + 1)
GetSystemDirectoryW(buffer, len(buffer))
return buffer.value
return GetSystemDirectory
GetSystemDirectory = GetSystemDirectory()
def GetVolumeSerialNumber():
GetVolumeInformationW = kernel32.GetVolumeInformationW
GetVolumeInformationW.argtypes = [c_wchar_p, c_wchar_p, c_uint,
POINTER(c_uint), POINTER(c_uint),
POINTER(c_uint), c_wchar_p, c_uint]
GetVolumeInformationW.restype = c_uint
def GetVolumeSerialNumber(path):
vsn = c_uint(0)
GetVolumeInformationW(
path, None, 0, byref(vsn), None, None, None, 0)
return vsn.value
return GetVolumeSerialNumber
GetVolumeSerialNumber = GetVolumeSerialNumber()
def GetUserName():
GetUserNameW = advapi32.GetUserNameW
GetUserNameW.argtypes = [c_wchar_p, POINTER(c_uint)]
GetUserNameW.restype = c_uint
def GetUserName():
buffer = create_unicode_buffer(32)
size = c_uint(len(buffer))
while not GetUserNameW(buffer, byref(size)):
buffer = create_unicode_buffer(len(buffer) * 2)
size.value = len(buffer)
return buffer.value.encode('utf-16-le')[::2]
return GetUserName
GetUserName = GetUserName()
PAGE_EXECUTE_READWRITE = 0x40
MEM_COMMIT = 0x1000
MEM_RESERVE = 0x2000
def VirtualAlloc():
_VirtualAlloc = kernel32.VirtualAlloc
_VirtualAlloc.argtypes = [LPVOID, c_size_t, DWORD, DWORD]
_VirtualAlloc.restype = LPVOID
def VirtualAlloc(addr, size, alloctype=(MEM_COMMIT | MEM_RESERVE),
protect=PAGE_EXECUTE_READWRITE):
return _VirtualAlloc(addr, size, alloctype, protect)
return VirtualAlloc
VirtualAlloc = VirtualAlloc()
MEM_RELEASE = 0x8000
def VirtualFree():
_VirtualFree = kernel32.VirtualFree
_VirtualFree.argtypes = [LPVOID, c_size_t, DWORD]
_VirtualFree.restype = BOOL
def VirtualFree(addr, size=0, freetype=MEM_RELEASE):
return _VirtualFree(addr, size, freetype)
return VirtualFree
VirtualFree = VirtualFree()
class NativeFunction(object):
def __init__(self, restype, argtypes, insns):
self._buf = buf = VirtualAlloc(None, len(insns))
memmove(buf, insns, len(insns))
ftype = CFUNCTYPE(restype, *argtypes)
self._native = ftype(buf)
def __call__(self, *args):
return self._native(*args)
def __del__(self):
if self._buf is not None:
VirtualFree(self._buf)
self._buf = None
if struct.calcsize("P") == 4:
CPUID0_INSNS = (
"\x53" # push %ebx
"\x31\xc0" # xor %eax,%eax
"\x0f\xa2" # cpuid
"\x8b\x44\x24\x08" # mov 0x8(%esp),%eax
"\x89\x18" # mov %ebx,0x0(%eax)
"\x89\x50\x04" # mov %edx,0x4(%eax)
"\x89\x48\x08" # mov %ecx,0x8(%eax)
"\x5b" # pop %ebx
"\xc3" # ret
)
CPUID1_INSNS = (
"\x53" # push %ebx
"\x31\xc0" # xor %eax,%eax
"\x40" # inc %eax
"\x0f\xa2" # cpuid
"\x5b" # pop %ebx
"\xc3" # ret
)
else:
CPUID0_INSNS = (
"\x49\x89\xd8" # mov %rbx,%r8
"\x49\x89\xc9" # mov %rcx,%r9
"\x48\x31\xc0" # xor %rax,%rax
"\x0f\xa2" # cpuid
"\x4c\x89\xc8" # mov %r9,%rax
"\x89\x18" # mov %ebx,0x0(%rax)
"\x89\x50\x04" # mov %edx,0x4(%rax)
"\x89\x48\x08" # mov %ecx,0x8(%rax)
"\x4c\x89\xc3" # mov %r8,%rbx
"\xc3" # retq
)
CPUID1_INSNS = (
"\x53" # push %rbx
"\x48\x31\xc0" # xor %rax,%rax
"\x48\xff\xc0" # inc %rax
"\x0f\xa2" # cpuid
"\x5b" # pop %rbx
"\xc3" # retq
)
def cpuid0():
_cpuid0 = NativeFunction(None, [c_char_p], CPUID0_INSNS)
buf = create_string_buffer(12)
def cpuid0():
_cpuid0(buf)
return buf.raw
return cpuid0
cpuid0 = cpuid0()
cpuid1 = NativeFunction(c_uint, [], CPUID1_INSNS)
class DataBlob(Structure):
_fields_ = [('cbData', c_uint),
('pbData', c_void_p)]
DataBlob_p = POINTER(DataBlob)
def CryptUnprotectData():
_CryptUnprotectData = crypt32.CryptUnprotectData
_CryptUnprotectData.argtypes = [DataBlob_p, c_wchar_p, DataBlob_p,
c_void_p, c_void_p, c_uint, DataBlob_p]
_CryptUnprotectData.restype = c_uint
def CryptUnprotectData(indata, entropy):
indatab = create_string_buffer(indata)
indata = DataBlob(len(indata), cast(indatab, c_void_p))
entropyb = create_string_buffer(entropy)
entropy = DataBlob(len(entropy), cast(entropyb, c_void_p))
outdata = DataBlob()
if not _CryptUnprotectData(byref(indata), None, byref(entropy),
None, None, 0, byref(outdata)):
raise ADEPTError("Failed to decrypt user key key (sic)")
return string_at(outdata.pbData, outdata.cbData)
return CryptUnprotectData
CryptUnprotectData = CryptUnprotectData()
def retrieve_keys():
if AES is None:
raise ADEPTError("PyCrypto or OpenSSL must be installed")
root = GetSystemDirectory().split('\\')[0] + '\\'
serial = GetVolumeSerialNumber(root)
vendor = cpuid0()
signature = struct.pack('>I', cpuid1())[1:]
user = GetUserName()
entropy = struct.pack('>I12s3s13s', serial, vendor, signature, user)
cuser = winreg.HKEY_CURRENT_USER
try:
regkey = winreg.OpenKey(cuser, DEVICE_KEY_PATH)
except WindowsError:
raise ADEPTError("Adobe Digital Editions not activated")
device = winreg.QueryValueEx(regkey, 'key')[0]
keykey = CryptUnprotectData(device, entropy)
userkey = None
keys = []
try:
plkroot = winreg.OpenKey(cuser, PRIVATE_LICENCE_KEY_PATH)
except WindowsError:
raise ADEPTError("Could not locate ADE activation")
for i in xrange(0, 16):
try:
plkparent = winreg.OpenKey(plkroot, "%04d" % (i,))
except WindowsError:
break
ktype = winreg.QueryValueEx(plkparent, None)[0]
if ktype != 'credentials':
continue
for j in xrange(0, 16):
try:
plkkey = winreg.OpenKey(plkparent, "%04d" % (j,))
except WindowsError:
break
ktype = winreg.QueryValueEx(plkkey, None)[0]
if ktype != 'privateLicenseKey':
continue
userkey = winreg.QueryValueEx(plkkey, 'value')[0]
userkey = userkey.decode('base64')
aes = AES(keykey)
userkey = aes.decrypt(userkey)
userkey = userkey[26:-ord(userkey[-1])]
keys.append(userkey)
if len(keys) == 0:
raise ADEPTError('Could not locate privateLicenseKey')
return keys
elif isosx:
import xml.etree.ElementTree as etree
import subprocess
NSMAP = {'adept': 'http://ns.adobe.com/adept',
'enc': 'http://www.w3.org/2001/04/xmlenc#'}
def findActivationDat():
home = os.getenv('HOME')
cmdline = 'find "' + home + '/Library/Application Support/Adobe/Digital Editions" -name "activation.dat"'
cmdline = cmdline.encode(sys.getfilesystemencoding())
p2 = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
out1, out2 = p2.communicate()
reslst = out1.split('\n')
cnt = len(reslst)
for j in xrange(cnt):
resline = reslst[j]
pp = resline.find('activation.dat')
if pp >= 0:
ActDatPath = resline
break
if os.path.exists(ActDatPath):
return ActDatPath
return None
def retrieve_keys():
actpath = findActivationDat()
if actpath is None:
raise ADEPTError("Could not locate ADE activation")
tree = etree.parse(actpath)
adept = lambda tag: '{%s}%s' % (NSMAP['adept'], tag)
expr = '//%s/%s' % (adept('credentials'), adept('privateLicenseKey'))
userkey = tree.findtext(expr)
userkey = userkey.decode('base64')
userkey = userkey[26:]
return [userkey]
else:
def retrieve_keys(keypath):
raise ADEPTError("This script only supports Windows and Mac OS X.")
return []
def retrieve_key(keypath):
keys = retrieve_keys()
with open(keypath, 'wb') as f:
f.write(keys[0])
return True
def extractKeyfile(keypath):
try:
success = retrieve_key(keypath)
except ADEPTError, e:
print "Key generation Error: " + str(e)
return 1
except Exception, e:
print "General Error: " + str(e)
return 1
if not success:
return 1
return 0
def cli_main(argv=sys.argv):
keypath = argv[1]
return extractKeyfile(keypath)
def main(argv=sys.argv):
import Tkinter
import Tkconstants
import tkMessageBox
import traceback
class ExceptionDialog(Tkinter.Frame):
def __init__(self, root, text):
Tkinter.Frame.__init__(self, root, border=5)
label = Tkinter.Label(self, text="Unexpected error:",
anchor=Tkconstants.W, justify=Tkconstants.LEFT)
label.pack(fill=Tkconstants.X, expand=0)
self.text = Tkinter.Text(self)
self.text.pack(fill=Tkconstants.BOTH, expand=1)
self.text.insert(Tkconstants.END, text)
root = Tkinter.Tk()
root.withdraw()
progname = os.path.basename(argv[0])
keypath = os.path.abspath("adeptkey.der")
success = False
try:
success = retrieve_key(keypath)
except ADEPTError, e:
tkMessageBox.showerror("ADEPT Key", "Error: " + str(e))
except Exception:
root.wm_state('normal')
root.title('ADEPT Key')
text = traceback.format_exc()
ExceptionDialog(root, text).pack(fill=Tkconstants.BOTH, expand=1)
root.mainloop()
if not success:
return 1
tkMessageBox.showinfo(
"ADEPT Key", "Key successfully retrieved to %s" % (keypath))
return 0
if __name__ == '__main__':
if len(sys.argv) > 1:
sys.exit(cli_main())
sys.exit(main())

22
Other_Tools/B&N_Download_Helper/BN-Dload.user_ReadMe.txt
View File

@@ -1,22 +1,32 @@
INTRODUCTION
============
To obtain unencrypted content from the B&N, you have to download it directly from the website. Unrooted Nook devices will not let you save your content to your PC.
If the downloaded file is encrypted, install and configure the ignoble plugin in Calibre to decrypt that.
Some content is not downloadable from the website, for instance magazines. The Greasemonkey script included in the tools modifies the myNook page of the Barnes and Noble website to show a download button for non-downloadable content. This will work until Barnes & Noble changes their website.
DOWNLOAD HIDDEN FILES FROM B&N
------------------------------
Some content is not downloadable from the B&N website, notably magazines. The Greasemonkey script included in the tools modifies the myNook page of the Barnes and Noble website to show a download button for normally non-downloadable content. This will work until Barnes & Noble changes their website.
Prerequisites
1) Firefox: http://getfirefox.com
-------------
1) Firefox: http://www.getfirefox.com
2) Greasemokey extension: https://addons.mozilla.org/nl/firefox/addon/greasemonkey/
One time installation
1) Install Firefox if not already done so;
---------------------
1) Install Firefox if not already done so
2) Follow the above link to GreaseMonkey and click Add to Firefox
3) Restart Firefox
4) Go to (link to the script, best hosted somewhere, as .js usually opens in an editor)
5) A pop up should appear, stating you are about to install a GreaseMonkey user script.
4) Go to http://userscripts.org/scripts/source/152985.user.js
5) A popup should appear, stating you are about to install a GreaseMonkey user script.
6) Click on install
Use
---
1) Log in into your B&N account
2) Go to MyNook
3) An “Alternative download” should apppear next to normally non-downloadable content.
3) An “Alternative download” should appear next to normally non-downloadable content. Note that this will not work for content such as Nook applications, and some children books.

24
Other_Tools/Barnes_and_Noble_EPUB_Tools/README_ignoble_epub.txt
View File

@@ -1,24 +0,0 @@
Readme.txt
Barnes and Noble EPUB ebooks use a form of Social DRM which requires information on your Credit Card Number and the Name on the Credit card used to purchase the book to actually unencrypt the book.
For more info, see the author's blog:
http://i-u2665-cabbages.blogspot.com/2009_12_01_archive.html
The original scripts by IHeartCabbages are available here as well. These scripts have been modified to allow the use of OpenSSL in place of PyCrypto to make them easier to run on Linux and Mac OS X, as well as to fix some minor bugs.
There are 2 scripts:
The first is ignoblekeygen_v2.4.pyw. Double-click to launch it and provide the required information, and this program will generate a key file needed to remove the DRM from the books. The require information is
* Your Name: Your name as set in your Barnes & Noble account, My Account page, directly under PERSONAL INFORMATION. It is usually just your first name and last name separated by a space.
* Credit Card number: This is the credit card number that was on file with Barnes & Noble at the time of download of the ebooks.
This key file need only be generated once unless either you change the default credit card number or your name on your B&N account.
The second is ignobleepub_vX.X.pyw. Double-click it and it will ask for your key file and the path to the book to remove the DRM from.
All of these scripts are gui python programs. Python 2.X (32 bit) is already installed in Mac OSX. We recommend ActiveState's Active Python Version 2.X (32 bit) for Windows users.
These scripts are based on the IHeartCabbages original scripts that allow the replacement of the requirement for PyCrypto with OpenSSL's libcrypto which is already installed on all Mac OS X machines and Linux Boxes. Window's Users will still have to install PyCrypto or OpenSSL to get these scripts to work properly.

336
Other_Tools/Barnes_and_Noble_EPUB_Tools/ignobleepub.pyw
View File

@@ -1,336 +0,0 @@
#! /usr/bin/python
from __future__ import with_statement
# ignobleepub.pyw, version 3.5
# To run this program install Python 2.6 from <http://www.python.org/download/>
# and OpenSSL or PyCrypto from http://www.voidspace.org.uk/python/modules.shtml#pycrypto
# (make sure to install the version for Python 2.6). Save this script file as
# ignobleepub.pyw and double-click on it to run it.
# Revision history:
# 1 - Initial release
# 2 - Added OS X support by using OpenSSL when available
# 3 - screen out improper key lengths to prevent segfaults on Linux
# 3.1 - Allow Windows versions of libcrypto to be found
# 3.2 - add support for encoding to 'utf-8' when building up list of files to cecrypt from encryption.xml
# 3.3 - On Windows try PyCrypto first and OpenSSL next
# 3.4 - Modify interace to allow use with import
# 3.5 - Fix for potential problem with PyCrypto
__license__ = 'GPL v3'
import sys
import os
import zlib
import zipfile
from zipfile import ZipFile, ZIP_STORED, ZIP_DEFLATED
from contextlib import closing
import xml.etree.ElementTree as etree
import Tkinter
import Tkconstants
import tkFileDialog
import tkMessageBox
class IGNOBLEError(Exception):
pass
def _load_crypto_libcrypto():
from ctypes import CDLL, POINTER, c_void_p, c_char_p, c_int, c_long, \
Structure, c_ulong, create_string_buffer, cast
from ctypes.util import find_library
if sys.platform.startswith('win'):
libcrypto = find_library('libeay32')
else:
libcrypto = find_library('crypto')
if libcrypto is None:
raise IGNOBLEError('libcrypto not found')
libcrypto = CDLL(libcrypto)
AES_MAXNR = 14
c_char_pp = POINTER(c_char_p)
c_int_p = POINTER(c_int)
class AES_KEY(Structure):
_fields_ = [('rd_key', c_long * (4 * (AES_MAXNR + 1))),
('rounds', c_int)]
AES_KEY_p = POINTER(AES_KEY)
def F(restype, name, argtypes):
func = getattr(libcrypto, name)
func.restype = restype
func.argtypes = argtypes
return func
AES_cbc_encrypt = F(None, 'AES_cbc_encrypt',
[c_char_p, c_char_p, c_ulong, AES_KEY_p, c_char_p,
c_int])
AES_set_decrypt_key = F(c_int, 'AES_set_decrypt_key',
[c_char_p, c_int, AES_KEY_p])
AES_cbc_encrypt = F(None, 'AES_cbc_encrypt',
[c_char_p, c_char_p, c_ulong, AES_KEY_p, c_char_p,
c_int])
class AES(object):
def __init__(self, userkey):
self._blocksize = len(userkey)
if (self._blocksize != 16) and (self._blocksize != 24) and (self._blocksize != 32) :
raise IGNOBLEError('AES improper key used')
return
key = self._key = AES_KEY()
rv = AES_set_decrypt_key(userkey, len(userkey) * 8, key)
if rv < 0:
raise IGNOBLEError('Failed to initialize AES key')
def decrypt(self, data):
out = create_string_buffer(len(data))
iv = ("\x00" * self._blocksize)
rv = AES_cbc_encrypt(data, out, len(data), self._key, iv, 0)
if rv == 0:
raise IGNOBLEError('AES decryption failed')
return out.raw
return AES
def _load_crypto_pycrypto():
from Crypto.Cipher import AES as _AES
class AES(object):
def __init__(self, key):
self._aes = _AES.new(key, _AES.MODE_CBC, '\x00'*16)
def decrypt(self, data):
return self._aes.decrypt(data)
return AES
def _load_crypto():
AES = None
cryptolist = (_load_crypto_libcrypto, _load_crypto_pycrypto)
if sys.platform.startswith('win'):
cryptolist = (_load_crypto_pycrypto, _load_crypto_libcrypto)
for loader in cryptolist:
try:
AES = loader()
break
except (ImportError, IGNOBLEError):
pass
return AES
AES = _load_crypto()
"""
Decrypt Barnes & Noble ADEPT encrypted EPUB books.
"""
META_NAMES = ('mimetype', 'META-INF/rights.xml', 'META-INF/encryption.xml')
NSMAP = {'adept': 'http://ns.adobe.com/adept',
'enc': 'http://www.w3.org/2001/04/xmlenc#'}
class ZipInfo(zipfile.ZipInfo):
def __init__(self, *args, **kwargs):
if 'compress_type' in kwargs:
compress_type = kwargs.pop('compress_type')
super(ZipInfo, self).__init__(*args, **kwargs)
self.compress_type = compress_type
class Decryptor(object):
def __init__(self, bookkey, encryption):
enc = lambda tag: '{%s}%s' % (NSMAP['enc'], tag)
# self._aes = AES.new(bookkey, AES.MODE_CBC, '\x00'*16)
self._aes = AES(bookkey)
encryption = etree.fromstring(encryption)
self._encrypted = encrypted = set()
expr = './%s/%s/%s' % (enc('EncryptedData'), enc('CipherData'),
enc('CipherReference'))
for elem in encryption.findall(expr):
path = elem.get('URI', None)
path = path.encode('utf-8')
if path is not None:
encrypted.add(path)
def decompress(self, bytes):
dc = zlib.decompressobj(-15)
bytes = dc.decompress(bytes)
ex = dc.decompress('Z') + dc.flush()
if ex:
bytes = bytes + ex
return bytes
def decrypt(self, path, data):
if path in self._encrypted:
data = self._aes.decrypt(data)[16:]
data = data[:-ord(data[-1])]
data = self.decompress(data)
return data
class DecryptionDialog(Tkinter.Frame):
def __init__(self, root):
Tkinter.Frame.__init__(self, root, border=5)
self.status = Tkinter.Label(self, text='Select files for decryption')
self.status.pack(fill=Tkconstants.X, expand=1)
body = Tkinter.Frame(self)
body.pack(fill=Tkconstants.X, expand=1)
sticky = Tkconstants.E + Tkconstants.W
body.grid_columnconfigure(1, weight=2)
Tkinter.Label(body, text='Key file').grid(row=0)
self.keypath = Tkinter.Entry(body, width=30)
self.keypath.grid(row=0, column=1, sticky=sticky)
if os.path.exists('bnepubkey.b64'):
self.keypath.insert(0, 'bnepubkey.b64')
button = Tkinter.Button(body, text="...", command=self.get_keypath)
button.grid(row=0, column=2)
Tkinter.Label(body, text='Input file').grid(row=1)
self.inpath = Tkinter.Entry(body, width=30)
self.inpath.grid(row=1, column=1, sticky=sticky)
button = Tkinter.Button(body, text="...", command=self.get_inpath)
button.grid(row=1, column=2)
Tkinter.Label(body, text='Output file').grid(row=2)
self.outpath = Tkinter.Entry(body, width=30)
self.outpath.grid(row=2, column=1, sticky=sticky)
button = Tkinter.Button(body, text="...", command=self.get_outpath)
button.grid(row=2, column=2)
buttons = Tkinter.Frame(self)
buttons.pack()
botton = Tkinter.Button(
buttons, text="Decrypt", width=10, command=self.decrypt)
botton.pack(side=Tkconstants.LEFT)
Tkinter.Frame(buttons, width=10).pack(side=Tkconstants.LEFT)
button = Tkinter.Button(
buttons, text="Quit", width=10, command=self.quit)
button.pack(side=Tkconstants.RIGHT)
def get_keypath(self):
keypath = tkFileDialog.askopenfilename(
parent=None, title='Select B&N EPUB key file',
defaultextension='.b64',
filetypes=[('base64-encoded files', '.b64'),
('All Files', '.*')])
if keypath:
keypath = os.path.normpath(keypath)
self.keypath.delete(0, Tkconstants.END)
self.keypath.insert(0, keypath)
return
def get_inpath(self):
inpath = tkFileDialog.askopenfilename(
parent=None, title='Select B&N-encrypted EPUB file to decrypt',
defaultextension='.epub', filetypes=[('EPUB files', '.epub'),
('All files', '.*')])
if inpath:
inpath = os.path.normpath(inpath)
self.inpath.delete(0, Tkconstants.END)
self.inpath.insert(0, inpath)
return
def get_outpath(self):
outpath = tkFileDialog.asksaveasfilename(
parent=None, title='Select unencrypted EPUB file to produce',
defaultextension='.epub', filetypes=[('EPUB files', '.epub'),
('All files', '.*')])
if outpath:
outpath = os.path.normpath(outpath)
self.outpath.delete(0, Tkconstants.END)
self.outpath.insert(0, outpath)
return
def decrypt(self):
keypath = self.keypath.get()
inpath = self.inpath.get()
outpath = self.outpath.get()
if not keypath or not os.path.exists(keypath):
self.status['text'] = 'Specified key file does not exist'
return
if not inpath or not os.path.exists(inpath):
self.status['text'] = 'Specified input file does not exist'
return
if not outpath:
self.status['text'] = 'Output file not specified'
return
if inpath == outpath:
self.status['text'] = 'Must have different input and output files'
return
argv = [sys.argv[0], keypath, inpath, outpath]
self.status['text'] = 'Decrypting...'
try:
cli_main(argv)
except Exception, e:
self.status['text'] = 'Error: ' + str(e)
return
self.status['text'] = 'File successfully decrypted'
def decryptBook(keypath, inpath, outpath):
with open(keypath, 'rb') as f:
keyb64 = f.read()
key = keyb64.decode('base64')[:16]
# aes = AES.new(key, AES.MODE_CBC, '\x00'*16)
aes = AES(key)
with closing(ZipFile(open(inpath, 'rb'))) as inf:
namelist = set(inf.namelist())
if 'META-INF/rights.xml' not in namelist or \
'META-INF/encryption.xml' not in namelist:
raise IGNOBLEError('%s: not an B&N ADEPT EPUB' % (inpath,))
for name in META_NAMES:
namelist.remove(name)
rights = etree.fromstring(inf.read('META-INF/rights.xml'))
adept = lambda tag: '{%s}%s' % (NSMAP['adept'], tag)
expr = './/%s' % (adept('encryptedKey'),)
bookkey = ''.join(rights.findtext(expr))
bookkey = aes.decrypt(bookkey.decode('base64'))
bookkey = bookkey[:-ord(bookkey[-1])]
encryption = inf.read('META-INF/encryption.xml')
decryptor = Decryptor(bookkey[-16:], encryption)
kwds = dict(compression=ZIP_DEFLATED, allowZip64=False)
with closing(ZipFile(open(outpath, 'wb'), 'w', **kwds)) as outf:
zi = ZipInfo('mimetype', compress_type=ZIP_STORED)
outf.writestr(zi, inf.read('mimetype'))
for path in namelist:
data = inf.read(path)
outf.writestr(path, decryptor.decrypt(path, data))
return 0
def cli_main(argv=sys.argv):
progname = os.path.basename(argv[0])
if AES is None:
print "%s: This script requires OpenSSL or PyCrypto, which must be installed " \
"separately. Read the top-of-script comment for details." % \
(progname,)
return 1
if len(argv) != 4:
print "usage: %s KEYFILE INBOOK OUTBOOK" % (progname,)
return 1
keypath, inpath, outpath = argv[1:]
return decryptBook(keypath, inpath, outpath)
def gui_main():
root = Tkinter.Tk()
if AES is None:
root.withdraw()
tkMessageBox.showerror(
"Ignoble EPUB Decrypter",
"This script requires OpenSSL or PyCrypto, which must be installed "
"separately. Read the top-of-script comment for details.")
return 1
root.title('Ignoble EPUB Decrypter')
root.resizable(True, False)
root.minsize(300, 0)
DecryptionDialog(root).pack(fill=Tkconstants.X, expand=1)
root.mainloop()
return 0
if __name__ == '__main__':
if len(sys.argv) > 1:
sys.exit(cli_main())
sys.exit(gui_main())

112
Other_Tools/Barnes_and_Noble_EPUB_Tools/ignoblekey.pyw
View File

@@ -1,112 +0,0 @@
#! /usr/bin/python
# ignoblekey.pyw, version 2
# To run this program install Python 2.6 from <http://www.python.org/download/>
# Save this script file as ignoblekey.pyw and double-click on it to run it.
# Revision history:
# 1 - Initial release
# 2 - Add some missing code
"""
Retrieve B&N DesktopReader EPUB user AES key.
"""
from __future__ import with_statement
__license__ = 'GPL v3'
import sys
import os
import binascii
import glob
import Tkinter
import Tkconstants
import tkMessageBox
import traceback
BN_KEY_KEY = 'uhk00000000'
BN_APPDATA_DIR = r'Barnes & Noble\DesktopReader'
class IgnobleError(Exception):
pass
def retrieve_key(inpath, outpath):
# The B&N DesktopReader 'ClientAPI' file is just a sqlite3 DB. Requiring
# users to install sqlite3 and bindings seems like overkill for retrieving
# one value, so we go in hot and dirty.
with open(inpath, 'rb') as f:
data = f.read()
if BN_KEY_KEY not in data:
raise IgnobleError('B&N user key not found; unexpected DB format?')
index = data.rindex(BN_KEY_KEY) + len(BN_KEY_KEY) + 1
data = data[index:index + 40]
for i in xrange(20, len(data)):
try:
keyb64 = data[:i]
if len(keyb64.decode('base64')) == 20:
break
except binascii.Error:
pass
else:
raise IgnobleError('Problem decoding key; unexpected DB format?')
with open(outpath, 'wb') as f:
f.write(keyb64 + '\n')
def cli_main(argv=sys.argv):
progname = os.path.basename(argv[0])
args = argv[1:]
if len(args) != 2:
sys.stderr.write("USAGE: %s CLIENTDB KEYFILE" % (progname,))
return 1
inpath, outpath = args
retrieve_key(inpath, outpath)
return 0
def find_bnclientdb_path():
appdata = os.environ['APPDATA']
bndir = os.path.join(appdata, BN_APPDATA_DIR)
if not os.path.isdir(bndir):
raise IgnobleError('Could not locate B&N Reader installation')
dbpath = glob.glob(os.path.join(bndir, 'ClientAPI_*.db'))
if len(dbpath) == 0:
raise IgnobleError('Problem locating B&N Reader DB')
return sorted(dbpath)[-1]
class ExceptionDialog(Tkinter.Frame):
def __init__(self, root, text):
Tkinter.Frame.__init__(self, root, border=5)
label = Tkinter.Label(self, text="Unexpected error:",
anchor=Tkconstants.W, justify=Tkconstants.LEFT)
label.pack(fill=Tkconstants.X, expand=0)
self.text = Tkinter.Text(self)
self.text.pack(fill=Tkconstants.BOTH, expand=1)
self.text.insert(Tkconstants.END, text)
def gui_main(argv=sys.argv):
root = Tkinter.Tk()
root.withdraw()
progname = os.path.basename(argv[0])
keypath = 'bnepubkey.b64'
try:
dbpath = find_bnclientdb_path()
retrieve_key(dbpath, keypath)
except IgnobleError, e:
tkMessageBox.showerror("Ignoble Key", "Error: " + str(e))
return 1
except Exception:
root.wm_state('normal')
root.title('Ignoble Key')
text = traceback.format_exc()
ExceptionDialog(root, text).pack(fill=Tkconstants.BOTH, expand=1)
root.mainloop()
return 1
tkMessageBox.showinfo(
"Ignoble Key", "Key successfully retrieved to %s" % (keypath))
return 0
if __name__ == '__main__':
if len(sys.argv) > 1:
sys.exit(cli_main())
sys.exit(gui_main())

244
Other_Tools/Barnes_and_Noble_EPUB_Tools/ignoblekeygen.pyw
View File

@@ -1,244 +0,0 @@
#! /usr/bin/python
from __future__ import with_statement
# ignoblekeygen.pyw, version 2.4
# To run this program install Python 2.6 from <http://www.python.org/download/>
# and OpenSSL or PyCrypto from http://www.voidspace.org.uk/python/modules.shtml#pycrypto
# (make sure to install the version for Python 2.6). Save this script file as
# ignoblekeygen.pyw and double-click on it to run it.
# Revision history:
# 1 - Initial release
# 2 - Add OS X support by using OpenSSL when available (taken/modified from ineptepub v5)
# 2.1 - Allow Windows versions of libcrypto to be found
# 2.2 - On Windows try PyCrypto first and then OpenSSL next
# 2.3 - Modify interface to allow use of import
# 2.4 - Improvements to UI and now works in plugins
"""
Generate Barnes & Noble EPUB user key from name and credit card number.
"""
__license__ = 'GPL v3'
import sys
import os
import hashlib
# use openssl's libcrypt if it exists in place of pycrypto
# code extracted from the Adobe Adept DRM removal code also by I HeartCabbages
class IGNOBLEError(Exception):
pass
def _load_crypto_libcrypto():
from ctypes import CDLL, POINTER, c_void_p, c_char_p, c_int, c_long, \
Structure, c_ulong, create_string_buffer, cast
from ctypes.util import find_library
if sys.platform.startswith('win'):
libcrypto = find_library('libeay32')
else:
libcrypto = find_library('crypto')
if libcrypto is None:
print 'libcrypto not found'
raise IGNOBLEError('libcrypto not found')
libcrypto = CDLL(libcrypto)
AES_MAXNR = 14
c_char_pp = POINTER(c_char_p)
c_int_p = POINTER(c_int)
class AES_KEY(Structure):
_fields_ = [('rd_key', c_long * (4 * (AES_MAXNR + 1))),
('rounds', c_int)]
AES_KEY_p = POINTER(AES_KEY)
def F(restype, name, argtypes):
func = getattr(libcrypto, name)
func.restype = restype
func.argtypes = argtypes
return func
AES_set_encrypt_key = F(c_int, 'AES_set_encrypt_key',
[c_char_p, c_int, AES_KEY_p])
AES_cbc_encrypt = F(None, 'AES_cbc_encrypt',
[c_char_p, c_char_p, c_ulong, AES_KEY_p, c_char_p,
c_int])
class AES(object):
def __init__(self, userkey, iv):
self._blocksize = len(userkey)
self._iv = iv
key = self._key = AES_KEY()
rv = AES_set_encrypt_key(userkey, len(userkey) * 8, key)
if rv < 0:
raise IGNOBLEError('Failed to initialize AES Encrypt key')
def encrypt(self, data):
out = create_string_buffer(len(data))
rv = AES_cbc_encrypt(data, out, len(data), self._key, self._iv, 1)
if rv == 0:
raise IGNOBLEError('AES encryption failed')
return out.raw
return AES
def _load_crypto_pycrypto():
from Crypto.Cipher import AES as _AES
class AES(object):
def __init__(self, key, iv):
self._aes = _AES.new(key, _AES.MODE_CBC, iv)
def encrypt(self, data):
return self._aes.encrypt(data)
return AES
def _load_crypto():
AES = None
cryptolist = (_load_crypto_libcrypto, _load_crypto_pycrypto)
if sys.platform.startswith('win'):
cryptolist = (_load_crypto_pycrypto, _load_crypto_libcrypto)
for loader in cryptolist:
try:
AES = loader()
break
except (ImportError, IGNOBLEError):
pass
return AES
AES = _load_crypto()
def normalize_name(name):
return ''.join(x for x in name.lower() if x != ' ')
def generate_keyfile(name, ccn, outpath):
# remove spaces and case from name and CC numbers.
name = normalize_name(name) + '\x00'
ccn = normalize_name(ccn) + '\x00'
name_sha = hashlib.sha1(name).digest()[:16]
ccn_sha = hashlib.sha1(ccn).digest()[:16]
both_sha = hashlib.sha1(name + ccn).digest()
aes = AES(ccn_sha, name_sha)
crypt = aes.encrypt(both_sha + ('\x0c' * 0x0c))
userkey = hashlib.sha1(crypt).digest()
with open(outpath, 'wb') as f:
f.write(userkey.encode('base64'))
return userkey
def cli_main(argv=sys.argv):
progname = os.path.basename(argv[0])
if AES is None:
print "%s: This script requires OpenSSL or PyCrypto, which must be installed " \
"separately. Read the top-of-script comment for details." % \
(progname,)
return 1
if len(argv) != 4:
print "usage: %s NAME CC# OUTFILE" % (progname,)
return 1
name, ccn, outpath = argv[1:]
generate_keyfile(name, ccn, outpath)
return 0
def gui_main():
import Tkinter
import Tkconstants
import tkFileDialog
import tkMessageBox
class DecryptionDialog(Tkinter.Frame):
def __init__(self, root):
Tkinter.Frame.__init__(self, root, border=5)
self.status = Tkinter.Label(self, text='Enter parameters')
self.status.pack(fill=Tkconstants.X, expand=1)
body = Tkinter.Frame(self)
body.pack(fill=Tkconstants.X, expand=1)
sticky = Tkconstants.E + Tkconstants.W
body.grid_columnconfigure(1, weight=2)
Tkinter.Label(body, text='Account Name').grid(row=0)
self.name = Tkinter.Entry(body, width=40)
self.name.grid(row=0, column=1, sticky=sticky)
Tkinter.Label(body, text='CC#').grid(row=1)
self.ccn = Tkinter.Entry(body, width=40)
self.ccn.grid(row=1, column=1, sticky=sticky)
Tkinter.Label(body, text='Output file').grid(row=2)
self.keypath = Tkinter.Entry(body, width=40)
self.keypath.grid(row=2, column=1, sticky=sticky)
self.keypath.insert(2, 'bnepubkey.b64')
button = Tkinter.Button(body, text="...", command=self.get_keypath)
button.grid(row=2, column=2)
buttons = Tkinter.Frame(self)
buttons.pack()
botton = Tkinter.Button(
buttons, text="Generate", width=10, command=self.generate)
botton.pack(side=Tkconstants.LEFT)
Tkinter.Frame(buttons, width=10).pack(side=Tkconstants.LEFT)
button = Tkinter.Button(
buttons, text="Quit", width=10, command=self.quit)
button.pack(side=Tkconstants.RIGHT)
def get_keypath(self):
keypath = tkFileDialog.asksaveasfilename(
parent=None, title='Select B&N EPUB key file to produce',
defaultextension='.b64',
filetypes=[('base64-encoded files', '.b64'),
('All Files', '.*')])
if keypath:
keypath = os.path.normpath(keypath)
self.keypath.delete(0, Tkconstants.END)
self.keypath.insert(0, keypath)
return
def generate(self):
name = self.name.get()
ccn = self.ccn.get()
keypath = self.keypath.get()
if not name:
self.status['text'] = 'Name not specified'
return
if not ccn:
self.status['text'] = 'Credit card number not specified'
return
if not keypath:
self.status['text'] = 'Output keyfile path not specified'
return
self.status['text'] = 'Generating...'
try:
generate_keyfile(name, ccn, keypath)
except Exception, e:
self.status['text'] = 'Error: ' + str(e)
return
self.status['text'] = 'Keyfile successfully generated'
root = Tkinter.Tk()
if AES is None:
root.withdraw()
tkMessageBox.showerror(
"Ignoble EPUB Keyfile Generator",
"This script requires OpenSSL or PyCrypto, which must be installed "
"separately. Read the top-of-script comment for details.")
return 1
root.title('Ignoble EPUB Keyfile Generator')
root.resizable(True, False)
root.minsize(300, 0)
DecryptionDialog(root).pack(fill=Tkconstants.X, expand=1)
root.mainloop()
return 0
if __name__ == '__main__':
if len(sys.argv) > 1:
sys.exit(cli_main())
sys.exit(gui_main())

261
Other_Tools/KindleBooks/KindleBooks.pyw
View File

@@ -1,261 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import sys
sys.path.append('lib')
import os, os.path, urllib
os.environ['PYTHONIOENCODING'] = "utf-8"
import Tkinter
import Tkconstants
import tkFileDialog
import tkMessageBox
from scrolltextwidget import ScrolledText
import subprocess
from subprocess import Popen, PIPE, STDOUT
import subasyncio
from subasyncio import Process
class MainDialog(Tkinter.Frame):
def __init__(self, root):
Tkinter.Frame.__init__(self, root, border=5)
self.root = root
self.interval = 1000
self.p2 = None
self.status = Tkinter.Label(self, text='Remove Encryption from a Kindle/Mobi/Topaz eBook')
self.status.pack(fill=Tkconstants.X, expand=1)
body = Tkinter.Frame(self)
body.pack(fill=Tkconstants.X, expand=1)
sticky = Tkconstants.E + Tkconstants.W
body.grid_columnconfigure(1, weight=2)
Tkinter.Label(body, text='Kindle/Mobi/Topaz eBook input file').grid(row=0, sticky=Tkconstants.E)
self.mobipath = Tkinter.Entry(body, width=50)
self.mobipath.grid(row=0, column=1, sticky=sticky)
cwd = os.getcwdu()
cwd = cwd.encode('utf-8')
self.mobipath.insert(0, cwd)
button = Tkinter.Button(body, text="...", command=self.get_mobipath)
button.grid(row=0, column=2)
Tkinter.Label(body, text='Directory for the Unencrypted Output File(s)').grid(row=1, sticky=Tkconstants.E)
self.outpath = Tkinter.Entry(body, width=50)
self.outpath.grid(row=1, column=1, sticky=sticky)
cwd = os.getcwdu()
cwd = cwd.encode('utf-8')
outname = cwd
self.outpath.insert(0, outname)
button = Tkinter.Button(body, text="...", command=self.get_outpath)
button.grid(row=1, column=2)
Tkinter.Label(body, text='Optional Alternative Kindle.info file').grid(row=2, sticky=Tkconstants.E)
self.altinfopath = Tkinter.Entry(body, width=50)
self.altinfopath.grid(row=2, column=1, sticky=sticky)
#cwd = os.getcwdu()
#cwd = cwd.encode('utf-8')
#self.altinfopath.insert(0, cwd)
button = Tkinter.Button(body, text="...", command=self.get_altinfopath)
button.grid(row=2, column=2)
Tkinter.Label(body, text='Optional Comma Separated List of 10 Character PIDs (no spaces)').grid(row=3, sticky=Tkconstants.E)
self.pidnums = Tkinter.StringVar()
self.pidinfo = Tkinter.Entry(body, width=50, textvariable=self.pidnums)
self.pidinfo.grid(row=3, column=1, sticky=sticky)
Tkinter.Label(body, text='Optional Comma Separated List of 16 Character Kindle Serial Numbers (no spaces)').grid(row=4, sticky=Tkconstants.E)
self.sernums = Tkinter.StringVar()
self.serinfo = Tkinter.Entry(body, width=50, textvariable=self.sernums)
self.serinfo.grid(row=4, column=1, sticky=sticky)
msg1 = 'Conversion Log \n\n'
self.stext = ScrolledText(body, bd=5, relief=Tkconstants.RIDGE, height=15, width=60, wrap=Tkconstants.WORD)
self.stext.grid(row=6, column=0, columnspan=2,sticky=sticky)
self.stext.insert(Tkconstants.END,msg1)
buttons = Tkinter.Frame(self)
buttons.pack()
self.sbotton = Tkinter.Button(
buttons, text="Start", width=10, command=self.convertit)
self.sbotton.pack(side=Tkconstants.LEFT)
Tkinter.Frame(buttons, width=10).pack(side=Tkconstants.LEFT)
self.qbutton = Tkinter.Button(
buttons, text="Quit", width=10, command=self.quitting)
self.qbutton.pack(side=Tkconstants.RIGHT)
# read from subprocess pipe without blocking
# invoked every interval via the widget "after"
# option being used, so need to reset it for the next time
def processPipe(self):
poll = self.p2.wait('nowait')
if poll != None:
text = self.p2.readerr()
text += self.p2.read()
msg = text + '\n\n' + 'Encryption successfully removed\n'
if poll == 1:
msg = text + '\n\n' + 'Error: Encryption Removal Failed\n'
if poll == 2:
msg = text + '\n\n' + 'Input File was Not Encrypted - No Output File Needed\n'
self.showCmdOutput(msg)
self.p2 = None
self.sbotton.configure(state='normal')
return
text = self.p2.readerr()
text += self.p2.read()
self.showCmdOutput(text)
# make sure we get invoked again by event loop after interval
self.stext.after(self.interval,self.processPipe)
return
# post output from subprocess in scrolled text widget
def showCmdOutput(self, msg):
if msg and msg !='':
if sys.platform.startswith('win'):
msg = msg.replace('\r\n','\n')
self.stext.insert(Tkconstants.END,msg)
self.stext.yview_pickplace(Tkconstants.END)
return
# run as a subprocess via pipes and collect stdout
def mobirdr(self, infile, outfile, altinfopath, pidnums, sernums):
# os.putenv('PYTHONUNBUFFERED', '1')
tool = 'k4mobidedrm.py'
pidoption = ''
if pidnums and pidnums != '':
pidoption = ' -p "' + pidnums + '" '
seroption = ''
if sernums and sernums != '':
seroption = ' -s "' + sernums + '" '
infooption = ''
if altinfopath and altinfopath != '':
infooption = ' -k "' + altinfopath + '" '
pengine = sys.executable
if pengine is None or pengine == '':
pengine = "python"
pengine = os.path.normpath(pengine)
cmdline = pengine + ' ./lib/' + tool + ' ' + pidoption + seroption + infooption + '"' + infile + '" "' + outfile + '"'
if sys.platform.startswith('win'):
cmdline = pengine + ' lib\\' + tool + ' ' + pidoption + seroption + infooption + '"' + infile + '" "' + outfile + '"'
print cmdline
cmdline = cmdline.encode(sys.getfilesystemencoding())
p2 = Process(cmdline, shell=True, bufsize=1, stdin=None, stdout=PIPE, stderr=PIPE, close_fds=False)
return p2
def get_mobipath(self):
cpath = self.mobipath.get()
mobipath = tkFileDialog.askopenfilename(
initialdir = cpath,
parent=None, title='Select Kindle/Mobi/Topaz eBook File',
defaultextension='.prc', filetypes=[('Mobi eBook File', '.prc'), ('Mobi eBook File', '.azw'),('Mobi eBook File', '.mobi'),('Mobi eBook File', '.tpz'),('Mobi eBook File', '.azw1'),('Mobi azw4 eBook File', '.azw4'),('All Files', '.*')])
if mobipath:
mobipath = os.path.normpath(mobipath)
self.mobipath.delete(0, Tkconstants.END)
self.mobipath.insert(0, mobipath)
return
def get_outpath(self):
cwd = os.getcwdu()
cwd = cwd.encode('utf-8')
outpath = tkFileDialog.askdirectory(
parent=None, title='Directory to Store Unencrypted file(s) into',
initialdir=cwd, initialfile=None)
if outpath:
outpath = os.path.normpath(outpath)
self.outpath.delete(0, Tkconstants.END)
self.outpath.insert(0, outpath)
return
def get_altinfopath(self):
cwd = os.getcwdu()
cwd = cwd.encode('utf-8')
altinfopath = tkFileDialog.askopenfilename(
parent=None, title='Select Alternative kindle.info File',
defaultextension='.prc', filetypes=[('Kindle Info', '.info'),
('All Files', '.*')],
initialdir=cwd)
if altinfopath:
altinfopath = os.path.normpath(altinfopath)
self.altinfopath.delete(0, Tkconstants.END)
self.altinfopath.insert(0, altinfopath)
return
def quitting(self):
# kill any still running subprocess
if self.p2 != None:
if (self.p2.wait('nowait') == None):
self.p2.terminate()
self.root.destroy()
# actually ready to run the subprocess and get its output
def convertit(self):
self.status['text'] = ''
# now disable the button to prevent multiple launches
self.sbotton.configure(state='disabled')
mobipath = self.mobipath.get()
outpath = self.outpath.get()
altinfopath = self.altinfopath.get()
pidnums = self.pidinfo.get()
sernums = self.serinfo.get()
if not mobipath or not os.path.exists(mobipath) or not os.path.isfile(mobipath):
self.status['text'] = 'Specified Kindle Mobi eBook file does not exist'
self.sbotton.configure(state='normal')
return
tpz = False
# Identify any Topaz Files
f = file(mobipath, 'rb')
raw = f.read(3)
if raw.startswith('TPZ'):
tpz = True
f.close()
if not outpath:
self.status['text'] = 'No output directory specified'
self.sbotton.configure(state='normal')
return
if not os.path.isdir(outpath):
self.status['text'] = 'Error specified output directory does not exist'
self.sbotton.configure(state='normal')
return
if altinfopath and not os.path.exists(altinfopath):
self.status['text'] = 'Specified kindle.info file does not exist'
self.sbotton.configure(state='normal')
return
log = 'Command = "python k4mobidedrm.py"\n'
if not tpz:
log += 'Kindle/Mobi Path = "'+ mobipath + '"\n'
else:
log += 'Topaz Path = "'+ mobipath + '"\n'
log += 'Output Directory = "' + outpath + '"\n'
log += 'Kindle.info file = "' + altinfopath + '"\n'
log += 'PID list = "' + pidnums + '"\n'
log += 'Serial Number list = "' + sernums + '"\n'
log += '\n\n'
log += 'Please Wait ...\n\n'
log = log.encode('utf-8')
self.stext.insert(Tkconstants.END,log)
self.p2 = self.mobirdr(mobipath, outpath, altinfopath, pidnums, sernums)
# python does not seem to allow you to create
# your own eventloop which every other gui does - strange
# so need to use the widget "after" command to force
# event loop to run non-gui events every interval
self.stext.after(self.interval,self.processPipe)
return
def main(argv=None):
root = Tkinter.Tk()
root.title('Kindle/Mobi/Topaz eBook Encryption Removal')
root.resizable(True, False)
root.minsize(300, 0)
MainDialog(root).pack(fill=Tkconstants.X, expand=1)
root.mainloop()
return 0
if __name__ == "__main__":
sys.exit(main())

58
Other_Tools/KindleBooks/README_KindleBooks.txt
View File

@@ -1,58 +0,0 @@
KindleBooks (Originally called K4MobiDeDRM and Topaz_Tools)
Most users will be better off using the DeDRM applications or the calibre plugin. This script is provided more for historical interest than anything else.
This tools combines functionality of MobiDeDRM with that of K4PCDeDRM, K4MDeDRM, and K4DeDRM. Effectively, it provides one-stop shopping for all your Mobipocket, Kindle for iPhone/iPad/iPodTouch, Kindle for PC, and Kindle for Mac needs and should work for both Mobi and Topaz ebooks.
Preliminary Steps:
1. Make sure you have Python 2.5, 2.6 or 2.7 installed (32 bit) and properly set as part of your SYSTEM PATH environment variable (On Windows I recommend ActiveState's ActivePython. See their web pages for instructions on how to install and how to properly set your PATH). On Mac OSX 10.5 and later everything you need is already installed.
Instructions:
1. double-click on KindleBooks.pyw
2. In the window that opens:
hit the first '...' button to locate your DRM Kindle-style ebook
3. Then hit the second '...' button to select an output directory for the unlocked file
4. If you have multiple Kindle.Info files and would like to use one specific one, please hit the third "...' button to select it. Note, if you only have one Kindle.Info file (like most users) this can and should be left blank.
5. Then add in any PIDs you need from KindleV1, Kindle for iPhone/iPad/iPodTouch, or other single PID devices to the provided box as a comma separated list of 10 digit PID numbers. If this is a Kindle for Mac or a Kindle for PC book then you can leave this box blank
6. If you have standalone Kindles, add in any 16 digit Serial Numbers as a comma separated list. If this is a Kindle for Mac or a Kindle for PC book then you can leave this box blank
7. hit the 'Start' button
After a short delay, you should see progress in the Conversion Log window indicating is the unlocking was a success or failure.
If your book was a normal Mobi style ebook:
If successful, you should see a "_nodrm" named version Mobi ebook.
If not please examine the Conversion Log window for any errors.
If your book was actually a Topaz book:
Please note that Topaz is most similar to a poor man's image only PDF in style. It has glyphs and x,y positions, ocrText used just for searching, that describe the image each page all encoded into a binary xml-like set of files.
If successful, you will have 3 zip archives created.
1. The first is BOOKNAME_nodrm.zip.
You can import this into calibre as is or unzip it and edit the book.html file you find inside. To create the book.html, Amazon's ocrText is combined with other information to recreate as closely as possible what the original book looked like. Unfortunately most bolding, italics is lost. Also, Amazon's ocrText can be absolutely horrible at times. Much work will be needed to clean up and correct Topaz books.
2. The second is BOOKNAME_SVG.zip
You can also import this into calibre or unzip it and open the indexsvg.xhtml file in any good Browser (Safari, Firefox, etc). This zip contains a set of svg images (one for each pages is created) and it shows the page exactly how it appeared. This zip can be used to create an image only pdf file via post conversion.
3. The third is BOOKNAME_XML.zip
This is a zip archive of the decrypted and translated xml-like descriptions of each page and can be archived/saved in case later code can do a better job converting these files. These are exactly what a Topaz books guts are. You should take a look at them in any text editor to see what they look like.
If the Topaz book conversion is not successful, a large _DEBUG.zip archive of all of the pieces is created and this can examined along with the Conversion Log window contents to determine the cause of the error and hopefully get it fixed in the next release.

568
Other_Tools/KindleBooks/lib/aescbc.py
View File

@@ -1,568 +0,0 @@
#! /usr/bin/env python
"""
Routines for doing AES CBC in one file
Modified by some_updates to extract
and combine only those parts needed for AES CBC
into one simple to add python file
Original Version
Copyright (c) 2002 by Paul A. Lambert
Under:
CryptoPy Artisitic License Version 1.0
See the wonderful pure python package cryptopy-1.2.5
and read its LICENSE.txt for complete license details.
"""
class CryptoError(Exception):
""" Base class for crypto exceptions """
def __init__(self,errorMessage='Error!'):
self.message = errorMessage
def __str__(self):
return self.message
class InitCryptoError(CryptoError):
""" Crypto errors during algorithm initialization """
class BadKeySizeError(InitCryptoError):
""" Bad key size error """
class EncryptError(CryptoError):
""" Error in encryption processing """
class DecryptError(CryptoError):
""" Error in decryption processing """
class DecryptNotBlockAlignedError(DecryptError):
""" Error in decryption processing """
def xorS(a,b):
""" XOR two strings """
assert len(a)==len(b)
x = []
for i in range(len(a)):
x.append( chr(ord(a[i])^ord(b[i])))
return ''.join(x)
def xor(a,b):
""" XOR two strings """
x = []
for i in range(min(len(a),len(b))):
x.append( chr(ord(a[i])^ord(b[i])))
return ''.join(x)
"""
Base 'BlockCipher' and Pad classes for cipher instances.
BlockCipher supports automatic padding and type conversion. The BlockCipher
class was written to make the actual algorithm code more readable and
not for performance.
"""
class BlockCipher:
""" Block ciphers """
def __init__(self):
self.reset()
def reset(self):
self.resetEncrypt()
self.resetDecrypt()
def resetEncrypt(self):
self.encryptBlockCount = 0
self.bytesToEncrypt = ''
def resetDecrypt(self):
self.decryptBlockCount = 0
self.bytesToDecrypt = ''
def encrypt(self, plainText, more = None):
""" Encrypt a string and return a binary string """
self.bytesToEncrypt += plainText # append plainText to any bytes from prior encrypt
numBlocks, numExtraBytes = divmod(len(self.bytesToEncrypt), self.blockSize)
cipherText = ''
for i in range(numBlocks):
bStart = i*self.blockSize
ctBlock = self.encryptBlock(self.bytesToEncrypt[bStart:bStart+self.blockSize])
self.encryptBlockCount += 1
cipherText += ctBlock
if numExtraBytes > 0: # save any bytes that are not block aligned
self.bytesToEncrypt = self.bytesToEncrypt[-numExtraBytes:]
else:
self.bytesToEncrypt = ''
if more == None: # no more data expected from caller
finalBytes = self.padding.addPad(self.bytesToEncrypt,self.blockSize)
if len(finalBytes) > 0:
ctBlock = self.encryptBlock(finalBytes)
self.encryptBlockCount += 1
cipherText += ctBlock
self.resetEncrypt()
return cipherText
def decrypt(self, cipherText, more = None):
""" Decrypt a string and return a string """
self.bytesToDecrypt += cipherText # append to any bytes from prior decrypt
numBlocks, numExtraBytes = divmod(len(self.bytesToDecrypt), self.blockSize)
if more == None: # no more calls to decrypt, should have all the data
if numExtraBytes != 0:
raise DecryptNotBlockAlignedError, 'Data not block aligned on decrypt'
# hold back some bytes in case last decrypt has zero len
if (more != None) and (numExtraBytes == 0) and (numBlocks >0) :
numBlocks -= 1
numExtraBytes = self.blockSize
plainText = ''
for i in range(numBlocks):
bStart = i*self.blockSize
ptBlock = self.decryptBlock(self.bytesToDecrypt[bStart : bStart+self.blockSize])
self.decryptBlockCount += 1
plainText += ptBlock
if numExtraBytes > 0: # save any bytes that are not block aligned
self.bytesToEncrypt = self.bytesToEncrypt[-numExtraBytes:]
else:
self.bytesToEncrypt = ''
if more == None: # last decrypt remove padding
plainText = self.padding.removePad(plainText, self.blockSize)
self.resetDecrypt()
return plainText
class Pad:
def __init__(self):
pass # eventually could put in calculation of min and max size extension
class padWithPadLen(Pad):
""" Pad a binary string with the length of the padding """
def addPad(self, extraBytes, blockSize):
""" Add padding to a binary string to make it an even multiple
of the block size """
blocks, numExtraBytes = divmod(len(extraBytes), blockSize)
padLength = blockSize - numExtraBytes
return extraBytes + padLength*chr(padLength)
def removePad(self, paddedBinaryString, blockSize):
""" Remove padding from a binary string """
if not(0<len(paddedBinaryString)):
raise DecryptNotBlockAlignedError, 'Expected More Data'
return paddedBinaryString[:-ord(paddedBinaryString[-1])]
class noPadding(Pad):
""" No padding. Use this to get ECB behavior from encrypt/decrypt """
def addPad(self, extraBytes, blockSize):
""" Add no padding """
return extraBytes
def removePad(self, paddedBinaryString, blockSize):
""" Remove no padding """
return paddedBinaryString
"""
Rijndael encryption algorithm
This byte oriented implementation is intended to closely
match FIPS specification for readability. It is not implemented
for performance.
"""
class Rijndael(BlockCipher):
""" Rijndael encryption algorithm """
def __init__(self, key = None, padding = padWithPadLen(), keySize=16, blockSize=16 ):
self.name = 'RIJNDAEL'
self.keySize = keySize
self.strength = keySize*8
self.blockSize = blockSize # blockSize is in bytes
self.padding = padding # change default to noPadding() to get normal ECB behavior
assert( keySize%4==0 and NrTable[4].has_key(keySize/4)),'key size must be 16,20,24,29 or 32 bytes'
assert( blockSize%4==0 and NrTable.has_key(blockSize/4)), 'block size must be 16,20,24,29 or 32 bytes'
self.Nb = self.blockSize/4 # Nb is number of columns of 32 bit words
self.Nk = keySize/4 # Nk is the key length in 32-bit words
self.Nr = NrTable[self.Nb][self.Nk] # The number of rounds (Nr) is a function of
# the block (Nb) and key (Nk) sizes.
if key != None:
self.setKey(key)
def setKey(self, key):
""" Set a key and generate the expanded key """
assert( len(key) == (self.Nk*4) ), 'Key length must be same as keySize parameter'
self.__expandedKey = keyExpansion(self, key)
self.reset() # BlockCipher.reset()
def encryptBlock(self, plainTextBlock):
""" Encrypt a block, plainTextBlock must be a array of bytes [Nb by 4] """
self.state = self._toBlock(plainTextBlock)
AddRoundKey(self, self.__expandedKey[0:self.Nb])
for round in range(1,self.Nr): #for round = 1 step 1 to Nr
SubBytes(self)
ShiftRows(self)
MixColumns(self)
AddRoundKey(self, self.__expandedKey[round*self.Nb:(round+1)*self.Nb])
SubBytes(self)
ShiftRows(self)
AddRoundKey(self, self.__expandedKey[self.Nr*self.Nb:(self.Nr+1)*self.Nb])
return self._toBString(self.state)
def decryptBlock(self, encryptedBlock):
""" decrypt a block (array of bytes) """
self.state = self._toBlock(encryptedBlock)
AddRoundKey(self, self.__expandedKey[self.Nr*self.Nb:(self.Nr+1)*self.Nb])
for round in range(self.Nr-1,0,-1):
InvShiftRows(self)
InvSubBytes(self)
AddRoundKey(self, self.__expandedKey[round*self.Nb:(round+1)*self.Nb])
InvMixColumns(self)
InvShiftRows(self)
InvSubBytes(self)
AddRoundKey(self, self.__expandedKey[0:self.Nb])
return self._toBString(self.state)
def _toBlock(self, bs):
""" Convert binary string to array of bytes, state[col][row]"""
assert ( len(bs) == 4*self.Nb ), 'Rijndarl blocks must be of size blockSize'
return [[ord(bs[4*i]),ord(bs[4*i+1]),ord(bs[4*i+2]),ord(bs[4*i+3])] for i in range(self.Nb)]
def _toBString(self, block):
""" Convert block (array of bytes) to binary string """
l = []
for col in block:
for rowElement in col:
l.append(chr(rowElement))
return ''.join(l)
#-------------------------------------
""" Number of rounds Nr = NrTable[Nb][Nk]
Nb Nk=4 Nk=5 Nk=6 Nk=7 Nk=8
------------------------------------- """
NrTable = {4: {4:10, 5:11, 6:12, 7:13, 8:14},
5: {4:11, 5:11, 6:12, 7:13, 8:14},
6: {4:12, 5:12, 6:12, 7:13, 8:14},
7: {4:13, 5:13, 6:13, 7:13, 8:14},
8: {4:14, 5:14, 6:14, 7:14, 8:14}}
#-------------------------------------
def keyExpansion(algInstance, keyString):
""" Expand a string of size keySize into a larger array """
Nk, Nb, Nr = algInstance.Nk, algInstance.Nb, algInstance.Nr # for readability
key = [ord(byte) for byte in keyString] # convert string to list
w = [[key[4*i],key[4*i+1],key[4*i+2],key[4*i+3]] for i in range(Nk)]
for i in range(Nk,Nb*(Nr+1)):
temp = w[i-1] # a four byte column
if (i%Nk) == 0 :
temp = temp[1:]+[temp[0]] # RotWord(temp)
temp = [ Sbox[byte] for byte in temp ]
temp[0] ^= Rcon[i/Nk]
elif Nk > 6 and i%Nk == 4 :
temp = [ Sbox[byte] for byte in temp ] # SubWord(temp)
w.append( [ w[i-Nk][byte]^temp[byte] for byte in range(4) ] )
return w
Rcon = (0,0x01,0x02,0x04,0x08,0x10,0x20,0x40,0x80,0x1b,0x36, # note extra '0' !!!
0x6c,0xd8,0xab,0x4d,0x9a,0x2f,0x5e,0xbc,0x63,0xc6,
0x97,0x35,0x6a,0xd4,0xb3,0x7d,0xfa,0xef,0xc5,0x91)
#-------------------------------------
def AddRoundKey(algInstance, keyBlock):
""" XOR the algorithm state with a block of key material """
for column in range(algInstance.Nb):
for row in range(4):
algInstance.state[column][row] ^= keyBlock[column][row]
#-------------------------------------
def SubBytes(algInstance):
for column in range(algInstance.Nb):
for row in range(4):
algInstance.state[column][row] = Sbox[algInstance.state[column][row]]
def InvSubBytes(algInstance):
for column in range(algInstance.Nb):
for row in range(4):
algInstance.state[column][row] = InvSbox[algInstance.state[column][row]]
Sbox = (0x63,0x7c,0x77,0x7b,0xf2,0x6b,0x6f,0xc5,
0x30,0x01,0x67,0x2b,0xfe,0xd7,0xab,0x76,
0xca,0x82,0xc9,0x7d,0xfa,0x59,0x47,0xf0,
0xad,0xd4,0xa2,0xaf,0x9c,0xa4,0x72,0xc0,
0xb7,0xfd,0x93,0x26,0x36,0x3f,0xf7,0xcc,
0x34,0xa5,0xe5,0xf1,0x71,0xd8,0x31,0x15,
0x04,0xc7,0x23,0xc3,0x18,0x96,0x05,0x9a,
0x07,0x12,0x80,0xe2,0xeb,0x27,0xb2,0x75,
0x09,0x83,0x2c,0x1a,0x1b,0x6e,0x5a,0xa0,
0x52,0x3b,0xd6,0xb3,0x29,0xe3,0x2f,0x84,
0x53,0xd1,0x00,0xed,0x20,0xfc,0xb1,0x5b,
0x6a,0xcb,0xbe,0x39,0x4a,0x4c,0x58,0xcf,
0xd0,0xef,0xaa,0xfb,0x43,0x4d,0x33,0x85,
0x45,0xf9,0x02,0x7f,0x50,0x3c,0x9f,0xa8,
0x51,0xa3,0x40,0x8f,0x92,0x9d,0x38,0xf5,
0xbc,0xb6,0xda,0x21,0x10,0xff,0xf3,0xd2,
0xcd,0x0c,0x13,0xec,0x5f,0x97,0x44,0x17,
0xc4,0xa7,0x7e,0x3d,0x64,0x5d,0x19,0x73,
0x60,0x81,0x4f,0xdc,0x22,0x2a,0x90,0x88,
0x46,0xee,0xb8,0x14,0xde,0x5e,0x0b,0xdb,
0xe0,0x32,0x3a,0x0a,0x49,0x06,0x24,0x5c,
0xc2,0xd3,0xac,0x62,0x91,0x95,0xe4,0x79,
0xe7,0xc8,0x37,0x6d,0x8d,0xd5,0x4e,0xa9,
0x6c,0x56,0xf4,0xea,0x65,0x7a,0xae,0x08,
0xba,0x78,0x25,0x2e,0x1c,0xa6,0xb4,0xc6,
0xe8,0xdd,0x74,0x1f,0x4b,0xbd,0x8b,0x8a,
0x70,0x3e,0xb5,0x66,0x48,0x03,0xf6,0x0e,
0x61,0x35,0x57,0xb9,0x86,0xc1,0x1d,0x9e,
0xe1,0xf8,0x98,0x11,0x69,0xd9,0x8e,0x94,
0x9b,0x1e,0x87,0xe9,0xce,0x55,0x28,0xdf,
0x8c,0xa1,0x89,0x0d,0xbf,0xe6,0x42,0x68,
0x41,0x99,0x2d,0x0f,0xb0,0x54,0xbb,0x16)
InvSbox = (0x52,0x09,0x6a,0xd5,0x30,0x36,0xa5,0x38,
0xbf,0x40,0xa3,0x9e,0x81,0xf3,0xd7,0xfb,
0x7c,0xe3,0x39,0x82,0x9b,0x2f,0xff,0x87,
0x34,0x8e,0x43,0x44,0xc4,0xde,0xe9,0xcb,
0x54,0x7b,0x94,0x32,0xa6,0xc2,0x23,0x3d,
0xee,0x4c,0x95,0x0b,0x42,0xfa,0xc3,0x4e,
0x08,0x2e,0xa1,0x66,0x28,0xd9,0x24,0xb2,
0x76,0x5b,0xa2,0x49,0x6d,0x8b,0xd1,0x25,
0x72,0xf8,0xf6,0x64,0x86,0x68,0x98,0x16,
0xd4,0xa4,0x5c,0xcc,0x5d,0x65,0xb6,0x92,
0x6c,0x70,0x48,0x50,0xfd,0xed,0xb9,0xda,
0x5e,0x15,0x46,0x57,0xa7,0x8d,0x9d,0x84,
0x90,0xd8,0xab,0x00,0x8c,0xbc,0xd3,0x0a,
0xf7,0xe4,0x58,0x05,0xb8,0xb3,0x45,0x06,
0xd0,0x2c,0x1e,0x8f,0xca,0x3f,0x0f,0x02,
0xc1,0xaf,0xbd,0x03,0x01,0x13,0x8a,0x6b,
0x3a,0x91,0x11,0x41,0x4f,0x67,0xdc,0xea,
0x97,0xf2,0xcf,0xce,0xf0,0xb4,0xe6,0x73,
0x96,0xac,0x74,0x22,0xe7,0xad,0x35,0x85,
0xe2,0xf9,0x37,0xe8,0x1c,0x75,0xdf,0x6e,
0x47,0xf1,0x1a,0x71,0x1d,0x29,0xc5,0x89,
0x6f,0xb7,0x62,0x0e,0xaa,0x18,0xbe,0x1b,
0xfc,0x56,0x3e,0x4b,0xc6,0xd2,0x79,0x20,
0x9a,0xdb,0xc0,0xfe,0x78,0xcd,0x5a,0xf4,
0x1f,0xdd,0xa8,0x33,0x88,0x07,0xc7,0x31,
0xb1,0x12,0x10,0x59,0x27,0x80,0xec,0x5f,
0x60,0x51,0x7f,0xa9,0x19,0xb5,0x4a,0x0d,
0x2d,0xe5,0x7a,0x9f,0x93,0xc9,0x9c,0xef,
0xa0,0xe0,0x3b,0x4d,0xae,0x2a,0xf5,0xb0,
0xc8,0xeb,0xbb,0x3c,0x83,0x53,0x99,0x61,
0x17,0x2b,0x04,0x7e,0xba,0x77,0xd6,0x26,
0xe1,0x69,0x14,0x63,0x55,0x21,0x0c,0x7d)
#-------------------------------------
""" For each block size (Nb), the ShiftRow operation shifts row i
by the amount Ci. Note that row 0 is not shifted.
Nb C1 C2 C3
------------------- """
shiftOffset = { 4 : ( 0, 1, 2, 3),
5 : ( 0, 1, 2, 3),
6 : ( 0, 1, 2, 3),
7 : ( 0, 1, 2, 4),
8 : ( 0, 1, 3, 4) }
def ShiftRows(algInstance):
tmp = [0]*algInstance.Nb # list of size Nb
for r in range(1,4): # row 0 reamains unchanged and can be skipped
for c in range(algInstance.Nb):
tmp[c] = algInstance.state[(c+shiftOffset[algInstance.Nb][r]) % algInstance.Nb][r]
for c in range(algInstance.Nb):
algInstance.state[c][r] = tmp[c]
def InvShiftRows(algInstance):
tmp = [0]*algInstance.Nb # list of size Nb
for r in range(1,4): # row 0 reamains unchanged and can be skipped
for c in range(algInstance.Nb):
tmp[c] = algInstance.state[(c+algInstance.Nb-shiftOffset[algInstance.Nb][r]) % algInstance.Nb][r]
for c in range(algInstance.Nb):
algInstance.state[c][r] = tmp[c]
#-------------------------------------
def MixColumns(a):
Sprime = [0,0,0,0]
for j in range(a.Nb): # for each column
Sprime[0] = mul(2,a.state[j][0])^mul(3,a.state[j][1])^mul(1,a.state[j][2])^mul(1,a.state[j][3])
Sprime[1] = mul(1,a.state[j][0])^mul(2,a.state[j][1])^mul(3,a.state[j][2])^mul(1,a.state[j][3])
Sprime[2] = mul(1,a.state[j][0])^mul(1,a.state[j][1])^mul(2,a.state[j][2])^mul(3,a.state[j][3])
Sprime[3] = mul(3,a.state[j][0])^mul(1,a.state[j][1])^mul(1,a.state[j][2])^mul(2,a.state[j][3])
for i in range(4):
a.state[j][i] = Sprime[i]
def InvMixColumns(a):
""" Mix the four bytes of every column in a linear way
This is the opposite operation of Mixcolumn """
Sprime = [0,0,0,0]
for j in range(a.Nb): # for each column
Sprime[0] = mul(0x0E,a.state[j][0])^mul(0x0B,a.state[j][1])^mul(0x0D,a.state[j][2])^mul(0x09,a.state[j][3])
Sprime[1] = mul(0x09,a.state[j][0])^mul(0x0E,a.state[j][1])^mul(0x0B,a.state[j][2])^mul(0x0D,a.state[j][3])
Sprime[2] = mul(0x0D,a.state[j][0])^mul(0x09,a.state[j][1])^mul(0x0E,a.state[j][2])^mul(0x0B,a.state[j][3])
Sprime[3] = mul(0x0B,a.state[j][0])^mul(0x0D,a.state[j][1])^mul(0x09,a.state[j][2])^mul(0x0E,a.state[j][3])
for i in range(4):
a.state[j][i] = Sprime[i]
#-------------------------------------
def mul(a, b):
""" Multiply two elements of GF(2^m)
needed for MixColumn and InvMixColumn """
if (a !=0 and b!=0):
return Alogtable[(Logtable[a] + Logtable[b])%255]
else:
return 0
Logtable = ( 0, 0, 25, 1, 50, 2, 26, 198, 75, 199, 27, 104, 51, 238, 223, 3,
100, 4, 224, 14, 52, 141, 129, 239, 76, 113, 8, 200, 248, 105, 28, 193,
125, 194, 29, 181, 249, 185, 39, 106, 77, 228, 166, 114, 154, 201, 9, 120,
101, 47, 138, 5, 33, 15, 225, 36, 18, 240, 130, 69, 53, 147, 218, 142,
150, 143, 219, 189, 54, 208, 206, 148, 19, 92, 210, 241, 64, 70, 131, 56,
102, 221, 253, 48, 191, 6, 139, 98, 179, 37, 226, 152, 34, 136, 145, 16,
126, 110, 72, 195, 163, 182, 30, 66, 58, 107, 40, 84, 250, 133, 61, 186,
43, 121, 10, 21, 155, 159, 94, 202, 78, 212, 172, 229, 243, 115, 167, 87,
175, 88, 168, 80, 244, 234, 214, 116, 79, 174, 233, 213, 231, 230, 173, 232,
44, 215, 117, 122, 235, 22, 11, 245, 89, 203, 95, 176, 156, 169, 81, 160,
127, 12, 246, 111, 23, 196, 73, 236, 216, 67, 31, 45, 164, 118, 123, 183,
204, 187, 62, 90, 251, 96, 177, 134, 59, 82, 161, 108, 170, 85, 41, 157,
151, 178, 135, 144, 97, 190, 220, 252, 188, 149, 207, 205, 55, 63, 91, 209,
83, 57, 132, 60, 65, 162, 109, 71, 20, 42, 158, 93, 86, 242, 211, 171,
68, 17, 146, 217, 35, 32, 46, 137, 180, 124, 184, 38, 119, 153, 227, 165,
103, 74, 237, 222, 197, 49, 254, 24, 13, 99, 140, 128, 192, 247, 112, 7)
Alogtable= ( 1, 3, 5, 15, 17, 51, 85, 255, 26, 46, 114, 150, 161, 248, 19, 53,
95, 225, 56, 72, 216, 115, 149, 164, 247, 2, 6, 10, 30, 34, 102, 170,
229, 52, 92, 228, 55, 89, 235, 38, 106, 190, 217, 112, 144, 171, 230, 49,
83, 245, 4, 12, 20, 60, 68, 204, 79, 209, 104, 184, 211, 110, 178, 205,
76, 212, 103, 169, 224, 59, 77, 215, 98, 166, 241, 8, 24, 40, 120, 136,
131, 158, 185, 208, 107, 189, 220, 127, 129, 152, 179, 206, 73, 219, 118, 154,
181, 196, 87, 249, 16, 48, 80, 240, 11, 29, 39, 105, 187, 214, 97, 163,
254, 25, 43, 125, 135, 146, 173, 236, 47, 113, 147, 174, 233, 32, 96, 160,
251, 22, 58, 78, 210, 109, 183, 194, 93, 231, 50, 86, 250, 21, 63, 65,
195, 94, 226, 61, 71, 201, 64, 192, 91, 237, 44, 116, 156, 191, 218, 117,
159, 186, 213, 100, 172, 239, 42, 126, 130, 157, 188, 223, 122, 142, 137, 128,
155, 182, 193, 88, 232, 35, 101, 175, 234, 37, 111, 177, 200, 67, 197, 84,
252, 31, 33, 99, 165, 244, 7, 9, 27, 45, 119, 153, 176, 203, 70, 202,
69, 207, 74, 222, 121, 139, 134, 145, 168, 227, 62, 66, 198, 81, 243, 14,
18, 54, 90, 238, 41, 123, 141, 140, 143, 138, 133, 148, 167, 242, 13, 23,
57, 75, 221, 124, 132, 151, 162, 253, 28, 36, 108, 180, 199, 82, 246, 1)
"""
AES Encryption Algorithm
The AES algorithm is just Rijndael algorithm restricted to the default
blockSize of 128 bits.
"""
class AES(Rijndael):
""" The AES algorithm is the Rijndael block cipher restricted to block
sizes of 128 bits and key sizes of 128, 192 or 256 bits
"""
def __init__(self, key = None, padding = padWithPadLen(), keySize=16):
""" Initialize AES, keySize is in bytes """
if not (keySize == 16 or keySize == 24 or keySize == 32) :
raise BadKeySizeError, 'Illegal AES key size, must be 16, 24, or 32 bytes'
Rijndael.__init__( self, key, padding=padding, keySize=keySize, blockSize=16 )
self.name = 'AES'
"""
CBC mode of encryption for block ciphers.
This algorithm mode wraps any BlockCipher to make a
Cipher Block Chaining mode.
"""
from random import Random # should change to crypto.random!!!
class CBC(BlockCipher):
""" The CBC class wraps block ciphers to make cipher block chaining (CBC) mode
algorithms. The initialization (IV) is automatic if set to None. Padding
is also automatic based on the Pad class used to initialize the algorithm
"""
def __init__(self, blockCipherInstance, padding = padWithPadLen()):
""" CBC algorithms are created by initializing with a BlockCipher instance """
self.baseCipher = blockCipherInstance
self.name = self.baseCipher.name + '_CBC'
self.blockSize = self.baseCipher.blockSize
self.keySize = self.baseCipher.keySize
self.padding = padding
self.baseCipher.padding = noPadding() # baseCipher should NOT pad!!
self.r = Random() # for IV generation, currently uses
# mediocre standard distro version <----------------
import time
newSeed = time.ctime()+str(self.r) # seed with instance location
self.r.seed(newSeed) # to make unique
self.reset()
def setKey(self, key):
self.baseCipher.setKey(key)
# Overload to reset both CBC state and the wrapped baseCipher
def resetEncrypt(self):
BlockCipher.resetEncrypt(self) # reset CBC encrypt state (super class)
self.baseCipher.resetEncrypt() # reset base cipher encrypt state
def resetDecrypt(self):
BlockCipher.resetDecrypt(self) # reset CBC state (super class)
self.baseCipher.resetDecrypt() # reset base cipher decrypt state
def encrypt(self, plainText, iv=None, more=None):
""" CBC encryption - overloads baseCipher to allow optional explicit IV
when iv=None, iv is auto generated!
"""
if self.encryptBlockCount == 0:
self.iv = iv
else:
assert(iv==None), 'IV used only on first call to encrypt'
return BlockCipher.encrypt(self,plainText, more=more)
def decrypt(self, cipherText, iv=None, more=None):
""" CBC decryption - overloads baseCipher to allow optional explicit IV
when iv=None, iv is auto generated!
"""
if self.decryptBlockCount == 0:
self.iv = iv
else:
assert(iv==None), 'IV used only on first call to decrypt'
return BlockCipher.decrypt(self, cipherText, more=more)
def encryptBlock(self, plainTextBlock):
""" CBC block encryption, IV is set with 'encrypt' """
auto_IV = ''
if self.encryptBlockCount == 0:
if self.iv == None:
# generate IV and use
self.iv = ''.join([chr(self.r.randrange(256)) for i in range(self.blockSize)])
self.prior_encr_CT_block = self.iv
auto_IV = self.prior_encr_CT_block # prepend IV if it's automatic
else: # application provided IV
assert(len(self.iv) == self.blockSize ),'IV must be same length as block'
self.prior_encr_CT_block = self.iv
""" encrypt the prior CT XORed with the PT """
ct = self.baseCipher.encryptBlock( xor(self.prior_encr_CT_block, plainTextBlock) )
self.prior_encr_CT_block = ct
return auto_IV+ct
def decryptBlock(self, encryptedBlock):
""" Decrypt a single block """
if self.decryptBlockCount == 0: # first call, process IV
if self.iv == None: # auto decrypt IV?
self.prior_CT_block = encryptedBlock
return ''
else:
assert(len(self.iv)==self.blockSize),"Bad IV size on CBC decryption"
self.prior_CT_block = self.iv
dct = self.baseCipher.decryptBlock(encryptedBlock)
""" XOR the prior decrypted CT with the prior CT """
dct_XOR_priorCT = xor( self.prior_CT_block, dct )
self.prior_CT_block = encryptedBlock
return dct_XOR_priorCT
"""
AES_CBC Encryption Algorithm
"""
class AES_CBC(CBC):
""" AES encryption in CBC feedback mode """
def __init__(self, key=None, padding=padWithPadLen(), keySize=16):
CBC.__init__( self, AES(key, noPadding(), keySize), padding)
self.name = 'AES_CBC'

BIN
Other_Tools/KindleBooks/lib/alfcrypto.dll
View File

Binary file not shown.

290
Other_Tools/KindleBooks/lib/alfcrypto.py
View File

@@ -1,290 +0,0 @@
#! /usr/bin/env python
import sys, os
import hmac
from struct import pack
import hashlib
# interface to needed routines libalfcrypto
def _load_libalfcrypto():
import ctypes
from ctypes import CDLL, byref, POINTER, c_void_p, c_char_p, c_int, c_long, \
Structure, c_ulong, create_string_buffer, addressof, string_at, cast, sizeof
pointer_size = ctypes.sizeof(ctypes.c_voidp)
name_of_lib = None
if sys.platform.startswith('darwin'):
name_of_lib = 'libalfcrypto.dylib'
elif sys.platform.startswith('win'):
if pointer_size == 4:
name_of_lib = 'alfcrypto.dll'
else:
name_of_lib = 'alfcrypto64.dll'
else:
if pointer_size == 4:
name_of_lib = 'libalfcrypto32.so'
else:
name_of_lib = 'libalfcrypto64.so'
libalfcrypto = sys.path[0] + os.sep + name_of_lib
if not os.path.isfile(libalfcrypto):
raise Exception('libalfcrypto not found')
libalfcrypto = CDLL(libalfcrypto)
c_char_pp = POINTER(c_char_p)
c_int_p = POINTER(c_int)
def F(restype, name, argtypes):
func = getattr(libalfcrypto, name)
func.restype = restype
func.argtypes = argtypes
return func
# aes cbc decryption
#
# struct aes_key_st {
# unsigned long rd_key[4 *(AES_MAXNR + 1)];
# int rounds;
# };
#
# typedef struct aes_key_st AES_KEY;
#
# int AES_set_decrypt_key(const unsigned char *userKey, const int bits, AES_KEY *key);
#
#
# void AES_cbc_encrypt(const unsigned char *in, unsigned char *out,
# const unsigned long length, const AES_KEY *key,
# unsigned char *ivec, const int enc);
AES_MAXNR = 14
class AES_KEY(Structure):
_fields_ = [('rd_key', c_long * (4 * (AES_MAXNR + 1))), ('rounds', c_int)]
AES_KEY_p = POINTER(AES_KEY)
AES_cbc_encrypt = F(None, 'AES_cbc_encrypt',[c_char_p, c_char_p, c_ulong, AES_KEY_p, c_char_p, c_int])
AES_set_decrypt_key = F(c_int, 'AES_set_decrypt_key',[c_char_p, c_int, AES_KEY_p])
# Pukall 1 Cipher
# unsigned char *PC1(const unsigned char *key, unsigned int klen, const unsigned char *src,
# unsigned char *dest, unsigned int len, int decryption);
PC1 = F(c_char_p, 'PC1', [c_char_p, c_ulong, c_char_p, c_char_p, c_ulong, c_ulong])
# Topaz Encryption
# typedef struct _TpzCtx {
# unsigned int v[2];
# } TpzCtx;
#
# void topazCryptoInit(TpzCtx *ctx, const unsigned char *key, int klen);
# void topazCryptoDecrypt(const TpzCtx *ctx, const unsigned char *in, unsigned char *out, int len);
class TPZ_CTX(Structure):
_fields_ = [('v', c_long * 2)]
TPZ_CTX_p = POINTER(TPZ_CTX)
topazCryptoInit = F(None, 'topazCryptoInit', [TPZ_CTX_p, c_char_p, c_ulong])
topazCryptoDecrypt = F(None, 'topazCryptoDecrypt', [TPZ_CTX_p, c_char_p, c_char_p, c_ulong])
class AES_CBC(object):
def __init__(self):
self._blocksize = 0
self._keyctx = None
self._iv = 0
def set_decrypt_key(self, userkey, iv):
self._blocksize = len(userkey)
if (self._blocksize != 16) and (self._blocksize != 24) and (self._blocksize != 32) :
raise Exception('AES CBC improper key used')
return
keyctx = self._keyctx = AES_KEY()
self._iv = iv
rv = AES_set_decrypt_key(userkey, len(userkey) * 8, keyctx)
if rv < 0:
raise Exception('Failed to initialize AES CBC key')
def decrypt(self, data):
out = create_string_buffer(len(data))
mutable_iv = create_string_buffer(self._iv, len(self._iv))
rv = AES_cbc_encrypt(data, out, len(data), self._keyctx, mutable_iv, 0)
if rv == 0:
raise Exception('AES CBC decryption failed')
return out.raw
class Pukall_Cipher(object):
def __init__(self):
self.key = None
def PC1(self, key, src, decryption=True):
self.key = key
out = create_string_buffer(len(src))
de = 0
if decryption:
de = 1
rv = PC1(key, len(key), src, out, len(src), de)
return out.raw
class Topaz_Cipher(object):
def __init__(self):
self._ctx = None
def ctx_init(self, key):
tpz_ctx = self._ctx = TPZ_CTX()
topazCryptoInit(tpz_ctx, key, len(key))
return tpz_ctx
def decrypt(self, data, ctx=None):
if ctx == None:
ctx = self._ctx
out = create_string_buffer(len(data))
topazCryptoDecrypt(ctx, data, out, len(data))
return out.raw
print "Using Library AlfCrypto DLL/DYLIB/SO"
return (AES_CBC, Pukall_Cipher, Topaz_Cipher)
def _load_python_alfcrypto():
import aescbc
class Pukall_Cipher(object):
def __init__(self):
self.key = None
def PC1(self, key, src, decryption=True):
sum1 = 0;
sum2 = 0;
keyXorVal = 0;
if len(key)!=16:
print "Bad key length!"
return None
wkey = []
for i in xrange(8):
wkey.append(ord(key[i*2])<<8 | ord(key[i*2+1]))
dst = ""
for i in xrange(len(src)):
temp1 = 0;
byteXorVal = 0;
for j in xrange(8):
temp1 ^= wkey[j]
sum2 = (sum2+j)*20021 + sum1
sum1 = (temp1*346)&0xFFFF
sum2 = (sum2+sum1)&0xFFFF
temp1 = (temp1*20021+1)&0xFFFF
byteXorVal ^= temp1 ^ sum2
curByte = ord(src[i])
if not decryption:
keyXorVal = curByte * 257;
curByte = ((curByte ^ (byteXorVal >> 8)) ^ byteXorVal) & 0xFF
if decryption:
keyXorVal = curByte * 257;
for j in xrange(8):
wkey[j] ^= keyXorVal;
dst+=chr(curByte)
return dst
class Topaz_Cipher(object):
def __init__(self):
self._ctx = None
def ctx_init(self, key):
ctx1 = 0x0CAFFE19E
for keyChar in key:
keyByte = ord(keyChar)
ctx2 = ctx1
ctx1 = ((((ctx1 >>2) * (ctx1 >>7))&0xFFFFFFFF) ^ (keyByte * keyByte * 0x0F902007)& 0xFFFFFFFF )
self._ctx = [ctx1, ctx2]
return [ctx1,ctx2]
def decrypt(self, data, ctx=None):
if ctx == None:
ctx = self._ctx
ctx1 = ctx[0]
ctx2 = ctx[1]
plainText = ""
for dataChar in data:
dataByte = ord(dataChar)
m = (dataByte ^ ((ctx1 >> 3) &0xFF) ^ ((ctx2<<3) & 0xFF)) &0xFF
ctx2 = ctx1
ctx1 = (((ctx1 >> 2) * (ctx1 >> 7)) &0xFFFFFFFF) ^((m * m * 0x0F902007) &0xFFFFFFFF)
plainText += chr(m)
return plainText
class AES_CBC(object):
def __init__(self):
self._key = None
self._iv = None
self.aes = None
def set_decrypt_key(self, userkey, iv):
self._key = userkey
self._iv = iv
self.aes = aescbc.AES_CBC(userkey, aescbc.noPadding(), len(userkey))
def decrypt(self, data):
iv = self._iv
cleartext = self.aes.decrypt(iv + data)
return cleartext
return (AES_CBC, Pukall_Cipher, Topaz_Cipher)
def _load_crypto():
AES_CBC = Pukall_Cipher = Topaz_Cipher = None
cryptolist = (_load_libalfcrypto, _load_python_alfcrypto)
for loader in cryptolist:
try:
AES_CBC, Pukall_Cipher, Topaz_Cipher = loader()
break
except (ImportError, Exception):
pass
return AES_CBC, Pukall_Cipher, Topaz_Cipher
AES_CBC, Pukall_Cipher, Topaz_Cipher = _load_crypto()
class KeyIVGen(object):
# this only exists in openssl so we will use pure python implementation instead
# PKCS5_PBKDF2_HMAC_SHA1 = F(c_int, 'PKCS5_PBKDF2_HMAC_SHA1',
# [c_char_p, c_ulong, c_char_p, c_ulong, c_ulong, c_ulong, c_char_p])
def pbkdf2(self, passwd, salt, iter, keylen):
def xorstr( a, b ):
if len(a) != len(b):
raise Exception("xorstr(): lengths differ")
return ''.join((chr(ord(x)^ord(y)) for x, y in zip(a, b)))
def prf( h, data ):
hm = h.copy()
hm.update( data )
return hm.digest()
def pbkdf2_F( h, salt, itercount, blocknum ):
U = prf( h, salt + pack('>i',blocknum ) )
T = U
for i in range(2, itercount+1):
U = prf( h, U )
T = xorstr( T, U )
return T
sha = hashlib.sha1
digest_size = sha().digest_size
# l - number of output blocks to produce
l = keylen / digest_size
if keylen % digest_size != 0:
l += 1
h = hmac.new( passwd, None, sha )
T = ""
for i in range(1, l+1):
T += pbkdf2_F( h, salt, iter, i )
return T[0: keylen]

BIN
Other_Tools/KindleBooks/lib/alfcrypto64.dll
View File

Binary file not shown.

BIN
Other_Tools/KindleBooks/lib/alfcrypto_src.zip
View File

Binary file not shown.

900
Other_Tools/KindleBooks/lib/cmbtc_v2.2.py
View File

@@ -1,900 +0,0 @@
#! /usr/bin/python
"""
Comprehensive Mazama Book DRM with Topaz Cryptography V2.2
-----BEGIN PUBLIC KEY-----
MIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQDdBHJ4CNc6DNFCw4MRCw4SWAK6
M8hYfnNEI0yQmn5Ti+W8biT7EatpauE/5jgQMPBmdNrDr1hbHyHBSP7xeC2qlRWC
B62UCxeu/fpfnvNHDN/wPWWH4jynZ2M6cdcnE5LQ+FfeKqZn7gnG2No1U9h7oOHx
y2/pHuYme7U1TsgSjwIDAQAB
-----END PUBLIC KEY-----
"""
from __future__ import with_statement
import csv
import sys
import os
import getopt
import zlib
from struct import pack
from struct import unpack
from ctypes import windll, c_char_p, c_wchar_p, c_uint, POINTER, byref, \
create_unicode_buffer, create_string_buffer, CFUNCTYPE, addressof, \
string_at, Structure, c_void_p, cast
import _winreg as winreg
import Tkinter
import Tkconstants
import tkMessageBox
import traceback
import hashlib
MAX_PATH = 255
kernel32 = windll.kernel32
advapi32 = windll.advapi32
crypt32 = windll.crypt32
global kindleDatabase
global bookFile
global bookPayloadOffset
global bookHeaderRecords
global bookMetadata
global bookKey
global command
#
# Various character maps used to decrypt books. Probably supposed to act as obfuscation
#
charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
charMap2 = "AaZzB0bYyCc1XxDdW2wEeVv3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_"
charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
charMap4 = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
#
# Exceptions for all the problems that might happen during the script
#
class CMBDTCError(Exception):
pass
class CMBDTCFatal(Exception):
pass
#
# Stolen stuff
#
class DataBlob(Structure):
_fields_ = [('cbData', c_uint),
('pbData', c_void_p)]
DataBlob_p = POINTER(DataBlob)
def GetSystemDirectory():
GetSystemDirectoryW = kernel32.GetSystemDirectoryW
GetSystemDirectoryW.argtypes = [c_wchar_p, c_uint]
GetSystemDirectoryW.restype = c_uint
def GetSystemDirectory():
buffer = create_unicode_buffer(MAX_PATH + 1)
GetSystemDirectoryW(buffer, len(buffer))
return buffer.value
return GetSystemDirectory
GetSystemDirectory = GetSystemDirectory()
def GetVolumeSerialNumber():
GetVolumeInformationW = kernel32.GetVolumeInformationW
GetVolumeInformationW.argtypes = [c_wchar_p, c_wchar_p, c_uint,
POINTER(c_uint), POINTER(c_uint),
POINTER(c_uint), c_wchar_p, c_uint]
GetVolumeInformationW.restype = c_uint
def GetVolumeSerialNumber(path):
vsn = c_uint(0)
GetVolumeInformationW(path, None, 0, byref(vsn), None, None, None, 0)
return vsn.value
return GetVolumeSerialNumber
GetVolumeSerialNumber = GetVolumeSerialNumber()
def GetUserName():
GetUserNameW = advapi32.GetUserNameW
GetUserNameW.argtypes = [c_wchar_p, POINTER(c_uint)]
GetUserNameW.restype = c_uint
def GetUserName():
buffer = create_unicode_buffer(32)
size = c_uint(len(buffer))
while not GetUserNameW(buffer, byref(size)):
buffer = create_unicode_buffer(len(buffer) * 2)
size.value = len(buffer)
return buffer.value.encode('utf-16-le')[::2]
return GetUserName
GetUserName = GetUserName()
def CryptUnprotectData():
_CryptUnprotectData = crypt32.CryptUnprotectData
_CryptUnprotectData.argtypes = [DataBlob_p, c_wchar_p, DataBlob_p,
c_void_p, c_void_p, c_uint, DataBlob_p]
_CryptUnprotectData.restype = c_uint
def CryptUnprotectData(indata, entropy):
indatab = create_string_buffer(indata)
indata = DataBlob(len(indata), cast(indatab, c_void_p))
entropyb = create_string_buffer(entropy)
entropy = DataBlob(len(entropy), cast(entropyb, c_void_p))
outdata = DataBlob()
if not _CryptUnprotectData(byref(indata), None, byref(entropy),
None, None, 0, byref(outdata)):
raise CMBDTCFatal("Failed to Unprotect Data")
return string_at(outdata.pbData, outdata.cbData)
return CryptUnprotectData
CryptUnprotectData = CryptUnprotectData()
#
# Returns the MD5 digest of "message"
#
def MD5(message):
ctx = hashlib.md5()
ctx.update(message)
return ctx.digest()
#
# Returns the MD5 digest of "message"
#
def SHA1(message):
ctx = hashlib.sha1()
ctx.update(message)
return ctx.digest()
#
# Open the book file at path
#
def openBook(path):
try:
return open(path,'rb')
except:
raise CMBDTCFatal("Could not open book file: " + path)
#
# Encode the bytes in data with the characters in map
#
def encode(data, map):
result = ""
for char in data:
value = ord(char)
Q = (value ^ 0x80) // len(map)
R = value % len(map)
result += map[Q]
result += map[R]
return result
#
# Hash the bytes in data and then encode the digest with the characters in map
#
def encodeHash(data,map):
return encode(MD5(data),map)
#
# Decode the string in data with the characters in map. Returns the decoded bytes
#
def decode(data,map):
result = ""
for i in range (0,len(data),2):
high = map.find(data[i])
low = map.find(data[i+1])
value = (((high * 0x40) ^ 0x80) & 0xFF) + low
result += pack("B",value)
return result
#
# Locate and open the Kindle.info file (Hopefully in the way it is done in the Kindle application)
#
def openKindleInfo():
regkey = winreg.OpenKey(winreg.HKEY_CURRENT_USER, "Software\\Microsoft\\Windows\\CurrentVersion\\Explorer\\Shell Folders\\")
path = winreg.QueryValueEx(regkey, 'Local AppData')[0]
return open(path+'\\Amazon\\Kindle For PC\\{AMAwzsaPaaZAzmZzZQzgZCAkZ3AjA_AY}\\kindle.info','r')
#
# Parse the Kindle.info file and return the records as a list of key-values
#
def parseKindleInfo():
DB = {}
infoReader = openKindleInfo()
infoReader.read(1)
data = infoReader.read()
items = data.split('{')
for item in items:
splito = item.split(':')
DB[splito[0]] =splito[1]
return DB
#
# Find if the original string for a hashed/encoded string is known. If so return the original string othwise return an empty string. (Totally not optimal)
#
def findNameForHash(hash):
names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber"]
result = ""
for name in names:
if hash == encodeHash(name, charMap2):
result = name
break
return name
#
# Print all the records from the kindle.info file (option -i)
#
def printKindleInfo():
for record in kindleDatabase:
name = findNameForHash(record)
if name != "" :
print (name)
print ("--------------------------\n")
else :
print ("Unknown Record")
print getKindleInfoValueForHash(record)
print "\n"
#
# Get a record from the Kindle.info file for the key "hashedKey" (already hashed and encoded). Return the decoded and decrypted record
#
def getKindleInfoValueForHash(hashedKey):
global kindleDatabase
encryptedValue = decode(kindleDatabase[hashedKey],charMap2)
return CryptUnprotectData(encryptedValue,"")
#
# Get a record from the Kindle.info file for the string in "key" (plaintext). Return the decoded and decrypted record
#
def getKindleInfoValueForKey(key):
return getKindleInfoValueForHash(encodeHash(key,charMap2))
#
# Get a 7 bit encoded number from the book file
#
def bookReadEncodedNumber():
flag = False
data = ord(bookFile.read(1))
if data == 0xFF:
flag = True
data = ord(bookFile.read(1))
if data >= 0x80:
datax = (data & 0x7F)
while data >= 0x80 :
data = ord(bookFile.read(1))
datax = (datax <<7) + (data & 0x7F)
data = datax
if flag:
data = -data
return data
#
# Encode a number in 7 bit format
#
def encodeNumber(number):
result = ""
negative = False
flag = 0
if number < 0 :
number = -number + 1
negative = True
while True:
byte = number & 0x7F
number = number >> 7
byte += flag
result += chr(byte)
flag = 0x80
if number == 0 :
if (byte == 0xFF and negative == False) :
result += chr(0x80)
break
if negative:
result += chr(0xFF)
return result[::-1]
#
# Get a length prefixed string from the file
#
def bookReadString():
stringLength = bookReadEncodedNumber()
return unpack(str(stringLength)+"s",bookFile.read(stringLength))[0]
#
# Returns a length prefixed string
#
def lengthPrefixString(data):
return encodeNumber(len(data))+data
#
# Read and return the data of one header record at the current book file position [[offset,compressedLength,decompressedLength],...]
#
def bookReadHeaderRecordData():
nbValues = bookReadEncodedNumber()
values = []
for i in range (0,nbValues):
values.append([bookReadEncodedNumber(),bookReadEncodedNumber(),bookReadEncodedNumber()])
return values
#
# Read and parse one header record at the current book file position and return the associated data [[offset,compressedLength,decompressedLength],...]
#
def parseTopazHeaderRecord():
if ord(bookFile.read(1)) != 0x63:
raise CMBDTCFatal("Parse Error : Invalid Header")
tag = bookReadString()
record = bookReadHeaderRecordData()
return [tag,record]
#
# Parse the header of a Topaz file, get all the header records and the offset for the payload
#
def parseTopazHeader():
global bookHeaderRecords
global bookPayloadOffset
magic = unpack("4s",bookFile.read(4))[0]
if magic != 'TPZ0':
raise CMBDTCFatal("Parse Error : Invalid Header, not a Topaz file")
nbRecords = bookReadEncodedNumber()
bookHeaderRecords = {}
for i in range (0,nbRecords):
result = parseTopazHeaderRecord()
bookHeaderRecords[result[0]] = result[1]
if ord(bookFile.read(1)) != 0x64 :
raise CMBDTCFatal("Parse Error : Invalid Header")
bookPayloadOffset = bookFile.tell()
#
# Get a record in the book payload, given its name and index. If necessary the record is decrypted. The record is not decompressed
#
def getBookPayloadRecord(name, index):
encrypted = False
try:
recordOffset = bookHeaderRecords[name][index][0]
except:
raise CMBDTCFatal("Parse Error : Invalid Record, record not found")
bookFile.seek(bookPayloadOffset + recordOffset)
tag = bookReadString()
if tag != name :
raise CMBDTCFatal("Parse Error : Invalid Record, record name doesn't match")
recordIndex = bookReadEncodedNumber()
if recordIndex < 0 :
encrypted = True
recordIndex = -recordIndex -1
if recordIndex != index :
raise CMBDTCFatal("Parse Error : Invalid Record, index doesn't match")
if bookHeaderRecords[name][index][2] != 0 :
record = bookFile.read(bookHeaderRecords[name][index][2])
else:
record = bookFile.read(bookHeaderRecords[name][index][1])
if encrypted:
ctx = topazCryptoInit(bookKey)
record = topazCryptoDecrypt(record,ctx)
return record
#
# Extract, decrypt and decompress a book record indicated by name and index and print it or save it in "filename"
#
def extractBookPayloadRecord(name, index, filename):
compressed = False
try:
compressed = bookHeaderRecords[name][index][2] != 0
record = getBookPayloadRecord(name,index)
except:
print("Could not find record")
if compressed:
try:
record = zlib.decompress(record)
except:
raise CMBDTCFatal("Could not decompress record")
if filename != "":
try:
file = open(filename,"wb")
file.write(record)
file.close()
except:
raise CMBDTCFatal("Could not write to destination file")
else:
print(record)
#
# return next record [key,value] from the book metadata from the current book position
#
def readMetadataRecord():
return [bookReadString(),bookReadString()]
#
# Parse the metadata record from the book payload and return a list of [key,values]
#
def parseMetadata():
global bookHeaderRecords
global bookPayloadAddress
global bookMetadata
bookMetadata = {}
bookFile.seek(bookPayloadOffset + bookHeaderRecords["metadata"][0][0])
tag = bookReadString()
if tag != "metadata" :
raise CMBDTCFatal("Parse Error : Record Names Don't Match")
flags = ord(bookFile.read(1))
nbRecords = ord(bookFile.read(1))
for i in range (0,nbRecords) :
record =readMetadataRecord()
bookMetadata[record[0]] = record[1]
#
# Returns two bit at offset from a bit field
#
def getTwoBitsFromBitField(bitField,offset):
byteNumber = offset // 4
bitPosition = 6 - 2*(offset % 4)
return ord(bitField[byteNumber]) >> bitPosition & 3
#
# Returns the six bits at offset from a bit field
#
def getSixBitsFromBitField(bitField,offset):
offset *= 3
value = (getTwoBitsFromBitField(bitField,offset) <<4) + (getTwoBitsFromBitField(bitField,offset+1) << 2) +getTwoBitsFromBitField(bitField,offset+2)
return value
#
# 8 bits to six bits encoding from hash to generate PID string
#
def encodePID(hash):
global charMap3
PID = ""
for position in range (0,8):
PID += charMap3[getSixBitsFromBitField(hash,position)]
return PID
#
# Context initialisation for the Topaz Crypto
#
def topazCryptoInit(key):
ctx1 = 0x0CAFFE19E
for keyChar in key:
keyByte = ord(keyChar)
ctx2 = ctx1
ctx1 = ((((ctx1 >>2) * (ctx1 >>7))&0xFFFFFFFF) ^ (keyByte * keyByte * 0x0F902007)& 0xFFFFFFFF )
return [ctx1,ctx2]
#
# decrypt data with the context prepared by topazCryptoInit()
#
def topazCryptoDecrypt(data, ctx):
ctx1 = ctx[0]
ctx2 = ctx[1]
plainText = ""
for dataChar in data:
dataByte = ord(dataChar)
m = (dataByte ^ ((ctx1 >> 3) &0xFF) ^ ((ctx2<<3) & 0xFF)) &0xFF
ctx2 = ctx1
ctx1 = (((ctx1 >> 2) * (ctx1 >> 7)) &0xFFFFFFFF) ^((m * m * 0x0F902007) &0xFFFFFFFF)
plainText += chr(m)
return plainText
#
# Decrypt a payload record with the PID
#
def decryptRecord(data,PID):
ctx = topazCryptoInit(PID)
return topazCryptoDecrypt(data, ctx)
#
# Try to decrypt a dkey record (contains the book PID)
#
def decryptDkeyRecord(data,PID):
record = decryptRecord(data,PID)
fields = unpack("3sB8sB8s3s",record)
if fields[0] != "PID" or fields[5] != "pid" :
raise CMBDTCError("Didn't find PID magic numbers in record")
elif fields[1] != 8 or fields[3] != 8 :
raise CMBDTCError("Record didn't contain correct length fields")
elif fields[2] != PID :
raise CMBDTCError("Record didn't contain PID")
return fields[4]
#
# Decrypt all the book's dkey records (contain the book PID)
#
def decryptDkeyRecords(data,PID):
nbKeyRecords = ord(data[0])
records = []
data = data[1:]
for i in range (0,nbKeyRecords):
length = ord(data[0])
try:
key = decryptDkeyRecord(data[1:length+1],PID)
records.append(key)
except CMBDTCError:
pass
data = data[1+length:]
return records
#
# Encryption table used to generate the device PID
#
def generatePidEncryptionTable() :
table = []
for counter1 in range (0,0x100):
value = counter1
for counter2 in range (0,8):
if (value & 1 == 0) :
value = value >> 1
else :
value = value >> 1
value = value ^ 0xEDB88320
table.append(value)
return table
#
# Seed value used to generate the device PID
#
def generatePidSeed(table,dsn) :
value = 0
for counter in range (0,4) :
index = (ord(dsn[counter]) ^ value) &0xFF
value = (value >> 8) ^ table[index]
return value
#
# Generate the device PID
#
def generateDevicePID(table,dsn,nbRoll):
seed = generatePidSeed(table,dsn)
pidAscii = ""
pid = [(seed >>24) &0xFF,(seed >> 16) &0xff,(seed >> 8) &0xFF,(seed) & 0xFF,(seed>>24) & 0xFF,(seed >> 16) &0xff,(seed >> 8) &0xFF,(seed) & 0xFF]
index = 0
for counter in range (0,nbRoll):
pid[index] = pid[index] ^ ord(dsn[counter])
index = (index+1) %8
for counter in range (0,8):
index = ((((pid[counter] >>5) & 3) ^ pid[counter]) & 0x1f) + (pid[counter] >> 7)
pidAscii += charMap4[index]
return pidAscii
#
# Create decrypted book payload
#
def createDecryptedPayload(payload):
# store data to be able to create the header later
headerData= []
currentOffset = 0
# Add social DRM to decrypted files
try:
data = getKindleInfoValueForKey("kindle.name.info")+":"+ getKindleInfoValueForKey("login")
if payload!= None:
payload.write(lengthPrefixString("sdrm"))
payload.write(encodeNumber(0))
payload.write(data)
else:
currentOffset += len(lengthPrefixString("sdrm"))
currentOffset += len(encodeNumber(0))
currentOffset += len(data)
except:
pass
for headerRecord in bookHeaderRecords:
name = headerRecord
newRecord = []
if name != "dkey" :
for index in range (0,len(bookHeaderRecords[name])) :
offset = currentOffset
if payload != None:
# write tag
payload.write(lengthPrefixString(name))
# write data
payload.write(encodeNumber(index))
payload.write(getBookPayloadRecord(name, index))
else :
currentOffset += len(lengthPrefixString(name))
currentOffset += len(encodeNumber(index))
currentOffset += len(getBookPayloadRecord(name, index))
newRecord.append([offset,bookHeaderRecords[name][index][1],bookHeaderRecords[name][index][2]])
headerData.append([name,newRecord])
return headerData
#
# Create decrypted book
#
def createDecryptedBook(outputFile):
outputFile = open(outputFile,"wb")
# Write the payload in a temporary file
headerData = createDecryptedPayload(None)
outputFile.write("TPZ0")
outputFile.write(encodeNumber(len(headerData)))
for header in headerData :
outputFile.write(chr(0x63))
outputFile.write(lengthPrefixString(header[0]))
outputFile.write(encodeNumber(len(header[1])))
for numbers in header[1] :
outputFile.write(encodeNumber(numbers[0]))
outputFile.write(encodeNumber(numbers[1]))
outputFile.write(encodeNumber(numbers[2]))
outputFile.write(chr(0x64))
createDecryptedPayload(outputFile)
outputFile.close()
#
# Set the command to execute by the programm according to cmdLine parameters
#
def setCommand(name) :
global command
if command != "" :
raise CMBDTCFatal("Invalid command line parameters")
else :
command = name
#
# Program usage
#
def usage():
print("\nUsage:")
print("\nCMBDTC.py [options] bookFileName\n")
print("-p Adds a PID to the list of PIDs that are tried to decrypt the book key (can be used several times)")
print("-d Saves a decrypted copy of the book")
print("-r Prints or writes to disk a record indicated in the form name:index (e.g \"img:0\")")
print("-o Output file name to write records and decrypted books")
print("-v Verbose (can be used several times)")
print("-i Prints kindle.info database")
#
# Main
#
def main(argv=sys.argv):
global kindleDatabase
global bookMetadata
global bookKey
global bookFile
global command
progname = os.path.basename(argv[0])
verbose = 0
recordName = ""
recordIndex = 0
outputFile = ""
PIDs = []
kindleDatabase = None
command = ""
try:
opts, args = getopt.getopt(sys.argv[1:], "vdir:o:p:")
except getopt.GetoptError, err:
# print help information and exit:
print str(err) # will print something like "option -a not recognized"
usage()
sys.exit(2)
if len(opts) == 0 and len(args) == 0 :
usage()
sys.exit(2)
for o, a in opts:
if o == "-v":
verbose+=1
if o == "-i":
setCommand("printInfo")
if o =="-o":
if a == None :
raise CMBDTCFatal("Invalid parameter for -o")
outputFile = a
if o =="-r":
setCommand("printRecord")
try:
recordName,recordIndex = a.split(':')
except:
raise CMBDTCFatal("Invalid parameter for -r")
if o =="-p":
PIDs.append(a)
if o =="-d":
setCommand("doit")
if command == "" :
raise CMBDTCFatal("No action supplied on command line")
#
# Read the encrypted database
#
try:
kindleDatabase = parseKindleInfo()
except Exception, message:
if verbose>0:
print(message)
if kindleDatabase != None :
if command == "printInfo" :
printKindleInfo()
#
# Compute the DSN
#
# Get the Mazama Random number
MazamaRandomNumber = getKindleInfoValueForKey("MazamaRandomNumber")
# Get the HDD serial
encodedSystemVolumeSerialNumber = encodeHash(str(GetVolumeSerialNumber(GetSystemDirectory().split('\\')[0] + '\\')),charMap1)
# Get the current user name
encodedUsername = encodeHash(GetUserName(),charMap1)
# concat, hash and encode
DSN = encode(SHA1(MazamaRandomNumber+encodedSystemVolumeSerialNumber+encodedUsername),charMap1)
if verbose >1:
print("DSN: " + DSN)
#
# Compute the device PID
#
table = generatePidEncryptionTable()
devicePID = generateDevicePID(table,DSN,4)
PIDs.append(devicePID)
if verbose > 0:
print("Device PID: " + devicePID)
#
# Open book and parse metadata
#
if len(args) == 1:
bookFile = openBook(args[0])
parseTopazHeader()
parseMetadata()
#
# Compute book PID
#
# Get the account token
if kindleDatabase != None:
kindleAccountToken = getKindleInfoValueForKey("kindle.account.tokens")
if verbose >1:
print("Account Token: " + kindleAccountToken)
keysRecord = bookMetadata["keys"]
keysRecordRecord = bookMetadata[keysRecord]
pidHash = SHA1(DSN+kindleAccountToken+keysRecord+keysRecordRecord)
bookPID = encodePID(pidHash)
PIDs.append(bookPID)
if verbose > 0:
print ("Book PID: " + bookPID )
#
# Decrypt book key
#
dkey = getBookPayloadRecord('dkey', 0)
bookKeys = []
for PID in PIDs :
bookKeys+=decryptDkeyRecords(dkey,PID)
if len(bookKeys) == 0 :
if verbose > 0 :
print ("Book key could not be found. Maybe this book is not registered with this device.")
else :
bookKey = bookKeys[0]
if verbose > 0:
print("Book key: " + bookKey.encode('hex'))
if command == "printRecord" :
extractBookPayloadRecord(recordName,int(recordIndex),outputFile)
if outputFile != "" and verbose>0 :
print("Wrote record to file: "+outputFile)
elif command == "doit" :
if outputFile!="" :
createDecryptedBook(outputFile)
if verbose >0 :
print ("Decrypted book saved. Don't pirate!")
elif verbose > 0:
print("Output file name was not supplied.")
return 0
if __name__ == '__main__':
sys.exit(main())

59
Other_Tools/KindleBooks/lib/config.py
View File

@@ -1,59 +0,0 @@
from PyQt4.Qt import QWidget, QVBoxLayout, QLabel, QLineEdit
from calibre.utils.config import JSONConfig
# This is where all preferences for this plugin will be stored
# You should always prefix your config file name with plugins/,
# so as to ensure you dont accidentally clobber a calibre config file
prefs = JSONConfig('plugins/K4MobiDeDRM')
# Set defaults
prefs.defaults['pids'] = ""
prefs.defaults['serials'] = ""
prefs.defaults['WINEPREFIX'] = None
class ConfigWidget(QWidget):
def __init__(self):
QWidget.__init__(self)
self.l = QVBoxLayout()
self.setLayout(self.l)
self.serialLabel = QLabel('eInk Kindle Serial numbers (First character B, 16 characters, use commas if more than one)')
self.l.addWidget(self.serialLabel)
self.serials = QLineEdit(self)
self.serials.setText(prefs['serials'])
self.l.addWidget(self.serials)
self.serialLabel.setBuddy(self.serials)
self.pidLabel = QLabel('Mobipocket PIDs (8 or 10 characters, use commas if more than one)')
self.l.addWidget(self.pidLabel)
self.pids = QLineEdit(self)
self.pids.setText(prefs['pids'])
self.l.addWidget(self.pids)
self.pidLabel.setBuddy(self.serials)
self.wpLabel = QLabel('For Linux only: WINEPREFIX (enter absolute path)')
self.l.addWidget(self.wpLabel)
self.wineprefix = QLineEdit(self)
wineprefix = prefs['WINEPREFIX']
if wineprefix is not None:
self.wineprefix.setText(wineprefix)
else:
self.wineprefix.setText('')
self.l.addWidget(self.wineprefix)
self.wpLabel.setBuddy(self.wineprefix)
def save_settings(self):
prefs['pids'] = str(self.pids.text()).replace(" ","")
prefs['serials'] = str(self.serials.text()).replace(" ","")
winepref=str(self.wineprefix.text())
if winepref.strip() != '':
prefs['WINEPREFIX'] = winepref
else:
prefs['WINEPREFIX'] = None

846
Other_Tools/KindleBooks/lib/convert2xml.py
View File

@@ -1,846 +0,0 @@
#! /usr/bin/python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
# For use with Topaz Scripts Version 2.6
class Unbuffered:
def __init__(self, stream):
self.stream = stream
def write(self, data):
self.stream.write(data)
self.stream.flush()
def __getattr__(self, attr):
return getattr(self.stream, attr)
import sys
sys.stdout=Unbuffered(sys.stdout)
import csv
import os
import getopt
from struct import pack
from struct import unpack
class TpzDRMError(Exception):
pass
# Get a 7 bit encoded number from string. The most
# significant byte comes first and has the high bit (8th) set
def readEncodedNumber(file):
flag = False
c = file.read(1)
if (len(c) == 0):
return None
data = ord(c)
if data == 0xFF:
flag = True
c = file.read(1)
if (len(c) == 0):
return None
data = ord(c)
if data >= 0x80:
datax = (data & 0x7F)
while data >= 0x80 :
c = file.read(1)
if (len(c) == 0):
return None
data = ord(c)
datax = (datax <<7) + (data & 0x7F)
data = datax
if flag:
data = -data
return data
# returns a binary string that encodes a number into 7 bits
# most significant byte first which has the high bit set
def encodeNumber(number):
result = ""
negative = False
flag = 0
if number < 0 :
number = -number + 1
negative = True
while True:
byte = number & 0x7F
number = number >> 7
byte += flag
result += chr(byte)
flag = 0x80
if number == 0 :
if (byte == 0xFF and negative == False) :
result += chr(0x80)
break
if negative:
result += chr(0xFF)
return result[::-1]
# create / read a length prefixed string from the file
def lengthPrefixString(data):
return encodeNumber(len(data))+data
def readString(file):
stringLength = readEncodedNumber(file)
if (stringLength == None):
return ""
sv = file.read(stringLength)
if (len(sv) != stringLength):
return ""
return unpack(str(stringLength)+"s",sv)[0]
# convert a binary string generated by encodeNumber (7 bit encoded number)
# to the value you would find inside the page*.dat files to be processed
def convert(i):
result = ''
val = encodeNumber(i)
for j in xrange(len(val)):
c = ord(val[j:j+1])
result += '%02x' % c
return result
# the complete string table used to store all book text content
# as well as the xml tokens and values that make sense out of it
class Dictionary(object):
def __init__(self, dictFile):
self.filename = dictFile
self.size = 0
self.fo = file(dictFile,'rb')
self.stable = []
self.size = readEncodedNumber(self.fo)
for i in xrange(self.size):
self.stable.append(self.escapestr(readString(self.fo)))
self.pos = 0
def escapestr(self, str):
str = str.replace('&','&amp;')
str = str.replace('<','&lt;')
str = str.replace('>','&gt;')
str = str.replace('=','&#61;')
return str
def lookup(self,val):
if ((val >= 0) and (val < self.size)) :
self.pos = val
return self.stable[self.pos]
else:
print "Error - %d outside of string table limits" % val
raise TpzDRMError('outside of string table limits')
# sys.exit(-1)
def getSize(self):
return self.size
def getPos(self):
return self.pos
def dumpDict(self):
for i in xrange(self.size):
print "%d %s %s" % (i, convert(i), self.stable[i])
return
# parses the xml snippets that are represented by each page*.dat file.
# also parses the other0.dat file - the main stylesheet
# and information used to inject the xml snippets into page*.dat files
class PageParser(object):
def __init__(self, filename, dict, debug, flat_xml):
self.fo = file(filename,'rb')
self.id = os.path.basename(filename).replace('.dat','')
self.dict = dict
self.debug = debug
self.flat_xml = flat_xml
self.tagpath = []
self.doc = []
self.snippetList = []
# hash table used to enable the decoding process
# This has all been developed by trial and error so it may still have omissions or
# contain errors
# Format:
# tag : (number of arguments, argument type, subtags present, special case of subtags presents when escaped)
token_tags = {
'x' : (1, 'scalar_number', 0, 0),
'y' : (1, 'scalar_number', 0, 0),
'h' : (1, 'scalar_number', 0, 0),
'w' : (1, 'scalar_number', 0, 0),
'firstWord' : (1, 'scalar_number', 0, 0),
'lastWord' : (1, 'scalar_number', 0, 0),
'rootID' : (1, 'scalar_number', 0, 0),
'stemID' : (1, 'scalar_number', 0, 0),
'type' : (1, 'scalar_text', 0, 0),
'info' : (0, 'number', 1, 0),
'info.word' : (0, 'number', 1, 1),
'info.word.ocrText' : (1, 'text', 0, 0),
'info.word.firstGlyph' : (1, 'raw', 0, 0),
'info.word.lastGlyph' : (1, 'raw', 0, 0),
'info.word.bl' : (1, 'raw', 0, 0),
'info.word.link_id' : (1, 'number', 0, 0),
'glyph' : (0, 'number', 1, 1),
'glyph.x' : (1, 'number', 0, 0),
'glyph.y' : (1, 'number', 0, 0),
'glyph.glyphID' : (1, 'number', 0, 0),
'dehyphen' : (0, 'number', 1, 1),
'dehyphen.rootID' : (1, 'number', 0, 0),
'dehyphen.stemID' : (1, 'number', 0, 0),
'dehyphen.stemPage' : (1, 'number', 0, 0),
'dehyphen.sh' : (1, 'number', 0, 0),
'links' : (0, 'number', 1, 1),
'links.page' : (1, 'number', 0, 0),
'links.rel' : (1, 'number', 0, 0),
'links.row' : (1, 'number', 0, 0),
'links.title' : (1, 'text', 0, 0),
'links.href' : (1, 'text', 0, 0),
'links.type' : (1, 'text', 0, 0),
'links.id' : (1, 'number', 0, 0),
'paraCont' : (0, 'number', 1, 1),
'paraCont.rootID' : (1, 'number', 0, 0),
'paraCont.stemID' : (1, 'number', 0, 0),
'paraCont.stemPage' : (1, 'number', 0, 0),
'paraStems' : (0, 'number', 1, 1),
'paraStems.stemID' : (1, 'number', 0, 0),
'wordStems' : (0, 'number', 1, 1),
'wordStems.stemID' : (1, 'number', 0, 0),
'empty' : (1, 'snippets', 1, 0),
'page' : (1, 'snippets', 1, 0),
'page.pageid' : (1, 'scalar_text', 0, 0),
'page.pagelabel' : (1, 'scalar_text', 0, 0),
'page.type' : (1, 'scalar_text', 0, 0),
'page.h' : (1, 'scalar_number', 0, 0),
'page.w' : (1, 'scalar_number', 0, 0),
'page.startID' : (1, 'scalar_number', 0, 0),
'group' : (1, 'snippets', 1, 0),
'group.type' : (1, 'scalar_text', 0, 0),
'group._tag' : (1, 'scalar_text', 0, 0),
'group.orientation': (1, 'scalar_text', 0, 0),
'region' : (1, 'snippets', 1, 0),
'region.type' : (1, 'scalar_text', 0, 0),
'region.x' : (1, 'scalar_number', 0, 0),
'region.y' : (1, 'scalar_number', 0, 0),
'region.h' : (1, 'scalar_number', 0, 0),
'region.w' : (1, 'scalar_number', 0, 0),
'region.orientation' : (1, 'scalar_text', 0, 0),
'empty_text_region' : (1, 'snippets', 1, 0),
'img' : (1, 'snippets', 1, 0),
'img.x' : (1, 'scalar_number', 0, 0),
'img.y' : (1, 'scalar_number', 0, 0),
'img.h' : (1, 'scalar_number', 0, 0),
'img.w' : (1, 'scalar_number', 0, 0),
'img.src' : (1, 'scalar_number', 0, 0),
'img.color_src' : (1, 'scalar_number', 0, 0),
'paragraph' : (1, 'snippets', 1, 0),
'paragraph.class' : (1, 'scalar_text', 0, 0),
'paragraph.firstWord' : (1, 'scalar_number', 0, 0),
'paragraph.lastWord' : (1, 'scalar_number', 0, 0),
'paragraph.lastWord' : (1, 'scalar_number', 0, 0),
'paragraph.gridSize' : (1, 'scalar_number', 0, 0),
'paragraph.gridBottomCenter' : (1, 'scalar_number', 0, 0),
'paragraph.gridTopCenter' : (1, 'scalar_number', 0, 0),
'paragraph.gridBeginCenter' : (1, 'scalar_number', 0, 0),
'paragraph.gridEndCenter' : (1, 'scalar_number', 0, 0),
'word_semantic' : (1, 'snippets', 1, 1),
'word_semantic.type' : (1, 'scalar_text', 0, 0),
'word_semantic.firstWord' : (1, 'scalar_number', 0, 0),
'word_semantic.lastWord' : (1, 'scalar_number', 0, 0),
'word' : (1, 'snippets', 1, 0),
'word.type' : (1, 'scalar_text', 0, 0),
'word.class' : (1, 'scalar_text', 0, 0),
'word.firstGlyph' : (1, 'scalar_number', 0, 0),
'word.lastGlyph' : (1, 'scalar_number', 0, 0),
'_span' : (1, 'snippets', 1, 0),
'_span.firstWord' : (1, 'scalar_number', 0, 0),
'_span.lastWord' : (1, 'scalar_number', 0, 0),
'_span.gridSize' : (1, 'scalar_number', 0, 0),
'_span.gridBottomCenter' : (1, 'scalar_number', 0, 0),
'_span.gridTopCenter' : (1, 'scalar_number', 0, 0),
'_span.gridBeginCenter' : (1, 'scalar_number', 0, 0),
'_span.gridEndCenter' : (1, 'scalar_number', 0, 0),
'span' : (1, 'snippets', 1, 0),
'span.firstWord' : (1, 'scalar_number', 0, 0),
'span.lastWord' : (1, 'scalar_number', 0, 0),
'span.gridSize' : (1, 'scalar_number', 0, 0),
'span.gridBottomCenter' : (1, 'scalar_number', 0, 0),
'span.gridTopCenter' : (1, 'scalar_number', 0, 0),
'span.gridBeginCenter' : (1, 'scalar_number', 0, 0),
'span.gridEndCenter' : (1, 'scalar_number', 0, 0),
'extratokens' : (1, 'snippets', 1, 0),
'extratokens.type' : (1, 'scalar_text', 0, 0),
'extratokens.firstGlyph' : (1, 'scalar_number', 0, 0),
'extratokens.lastGlyph' : (1, 'scalar_number', 0, 0),
'glyph.h' : (1, 'number', 0, 0),
'glyph.w' : (1, 'number', 0, 0),
'glyph.use' : (1, 'number', 0, 0),
'glyph.vtx' : (1, 'number', 0, 1),
'glyph.len' : (1, 'number', 0, 1),
'glyph.dpi' : (1, 'number', 0, 0),
'vtx' : (0, 'number', 1, 1),
'vtx.x' : (1, 'number', 0, 0),
'vtx.y' : (1, 'number', 0, 0),
'len' : (0, 'number', 1, 1),
'len.n' : (1, 'number', 0, 0),
'book' : (1, 'snippets', 1, 0),
'version' : (1, 'snippets', 1, 0),
'version.FlowEdit_1_id' : (1, 'scalar_text', 0, 0),
'version.FlowEdit_1_version' : (1, 'scalar_text', 0, 0),
'version.Schema_id' : (1, 'scalar_text', 0, 0),
'version.Schema_version' : (1, 'scalar_text', 0, 0),
'version.Topaz_version' : (1, 'scalar_text', 0, 0),
'version.WordDetailEdit_1_id' : (1, 'scalar_text', 0, 0),
'version.WordDetailEdit_1_version' : (1, 'scalar_text', 0, 0),
'version.ZoneEdit_1_id' : (1, 'scalar_text', 0, 0),
'version.ZoneEdit_1_version' : (1, 'scalar_text', 0, 0),
'version.chapterheaders' : (1, 'scalar_text', 0, 0),
'version.creation_date' : (1, 'scalar_text', 0, 0),
'version.header_footer' : (1, 'scalar_text', 0, 0),
'version.init_from_ocr' : (1, 'scalar_text', 0, 0),
'version.letter_insertion' : (1, 'scalar_text', 0, 0),
'version.xmlinj_convert' : (1, 'scalar_text', 0, 0),
'version.xmlinj_reflow' : (1, 'scalar_text', 0, 0),
'version.xmlinj_transform' : (1, 'scalar_text', 0, 0),
'version.findlists' : (1, 'scalar_text', 0, 0),
'version.page_num' : (1, 'scalar_text', 0, 0),
'version.page_type' : (1, 'scalar_text', 0, 0),
'version.bad_text' : (1, 'scalar_text', 0, 0),
'version.glyph_mismatch' : (1, 'scalar_text', 0, 0),
'version.margins' : (1, 'scalar_text', 0, 0),
'version.staggered_lines' : (1, 'scalar_text', 0, 0),
'version.paragraph_continuation' : (1, 'scalar_text', 0, 0),
'version.toc' : (1, 'scalar_text', 0, 0),
'stylesheet' : (1, 'snippets', 1, 0),
'style' : (1, 'snippets', 1, 0),
'style._tag' : (1, 'scalar_text', 0, 0),
'style.type' : (1, 'scalar_text', 0, 0),
'style._parent_type' : (1, 'scalar_text', 0, 0),
'style.class' : (1, 'scalar_text', 0, 0),
'style._after_class' : (1, 'scalar_text', 0, 0),
'rule' : (1, 'snippets', 1, 0),
'rule.attr' : (1, 'scalar_text', 0, 0),
'rule.value' : (1, 'scalar_text', 0, 0),
'original' : (0, 'number', 1, 1),
'original.pnum' : (1, 'number', 0, 0),
'original.pid' : (1, 'text', 0, 0),
'pages' : (0, 'number', 1, 1),
'pages.ref' : (1, 'number', 0, 0),
'pages.id' : (1, 'number', 0, 0),
'startID' : (0, 'number', 1, 1),
'startID.page' : (1, 'number', 0, 0),
'startID.id' : (1, 'number', 0, 0),
}
# full tag path record keeping routines
def tag_push(self, token):
self.tagpath.append(token)
def tag_pop(self):
if len(self.tagpath) > 0 :
self.tagpath.pop()
def tagpath_len(self):
return len(self.tagpath)
def get_tagpath(self, i):
cnt = len(self.tagpath)
if i < cnt : result = self.tagpath[i]
for j in xrange(i+1, cnt) :
result += '.' + self.tagpath[j]
return result
# list of absolute command byte values values that indicate
# various types of loop meachanisms typically used to generate vectors
cmd_list = (0x76, 0x76)
# peek at and return 1 byte that is ahead by i bytes
def peek(self, aheadi):
c = self.fo.read(aheadi)
if (len(c) == 0):
return None
self.fo.seek(-aheadi,1)
c = c[-1:]
return ord(c)
# get the next value from the file being processed
def getNext(self):
nbyte = self.peek(1);
if (nbyte == None):
return None
val = readEncodedNumber(self.fo)
return val
# format an arg by argtype
def formatArg(self, arg, argtype):
if (argtype == 'text') or (argtype == 'scalar_text') :
result = self.dict.lookup(arg)
elif (argtype == 'raw') or (argtype == 'number') or (argtype == 'scalar_number') :
result = arg
elif (argtype == 'snippets') :
result = arg
else :
print "Error Unknown argtype %s" % argtype
sys.exit(-2)
return result
# process the next tag token, recursively handling subtags,
# arguments, and commands
def procToken(self, token):
known_token = False
self.tag_push(token)
if self.debug : print 'Processing: ', self.get_tagpath(0)
cnt = self.tagpath_len()
for j in xrange(cnt):
tkn = self.get_tagpath(j)
if tkn in self.token_tags :
num_args = self.token_tags[tkn][0]
argtype = self.token_tags[tkn][1]
subtags = self.token_tags[tkn][2]
splcase = self.token_tags[tkn][3]
ntags = -1
known_token = True
break
if known_token :
# handle subtags if present
subtagres = []
if (splcase == 1):
# this type of tag uses of escape marker 0x74 indicate subtag count
if self.peek(1) == 0x74:
skip = readEncodedNumber(self.fo)
subtags = 1
num_args = 0
if (subtags == 1):
ntags = readEncodedNumber(self.fo)
if self.debug : print 'subtags: ' + token + ' has ' + str(ntags)
for j in xrange(ntags):
val = readEncodedNumber(self.fo)
subtagres.append(self.procToken(self.dict.lookup(val)))
# arguments can be scalars or vectors of text or numbers
argres = []
if num_args > 0 :
firstarg = self.peek(1)
if (firstarg in self.cmd_list) and (argtype != 'scalar_number') and (argtype != 'scalar_text'):
# single argument is a variable length vector of data
arg = readEncodedNumber(self.fo)
argres = self.decodeCMD(arg,argtype)
else :
# num_arg scalar arguments
for i in xrange(num_args):
argres.append(self.formatArg(readEncodedNumber(self.fo), argtype))
# build the return tag
result = []
tkn = self.get_tagpath(0)
result.append(tkn)
result.append(subtagres)
result.append(argtype)
result.append(argres)
self.tag_pop()
return result
# all tokens that need to be processed should be in the hash
# table if it may indicate a problem, either new token
# or an out of sync condition
else:
result = []
if (self.debug):
print 'Unknown Token:', token
self.tag_pop()
return result
# special loop used to process code snippets
# it is NEVER used to format arguments.
# builds the snippetList
def doLoop72(self, argtype):
cnt = readEncodedNumber(self.fo)
if self.debug :
result = 'Set of '+ str(cnt) + ' xml snippets. The overall structure \n'
result += 'of the document is indicated by snippet number sets at the\n'
result += 'end of each snippet. \n'
print result
for i in xrange(cnt):
if self.debug: print 'Snippet:',str(i)
snippet = []
snippet.append(i)
val = readEncodedNumber(self.fo)
snippet.append(self.procToken(self.dict.lookup(val)))
self.snippetList.append(snippet)
return
# general loop code gracisouly submitted by "skindle" - thank you!
def doLoop76Mode(self, argtype, cnt, mode):
result = []
adj = 0
if mode & 1:
adj = readEncodedNumber(self.fo)
mode = mode >> 1
x = []
for i in xrange(cnt):
x.append(readEncodedNumber(self.fo) - adj)
for i in xrange(mode):
for j in xrange(1, cnt):
x[j] = x[j] + x[j - 1]
for i in xrange(cnt):
result.append(self.formatArg(x[i],argtype))
return result
# dispatches loop commands bytes with various modes
# The 0x76 style loops are used to build vectors
# This was all derived by trial and error and
# new loop types may exist that are not handled here
# since they did not appear in the test cases
def decodeCMD(self, cmd, argtype):
if (cmd == 0x76):
# loop with cnt, and mode to control loop styles
cnt = readEncodedNumber(self.fo)
mode = readEncodedNumber(self.fo)
if self.debug : print 'Loop for', cnt, 'with mode', mode, ': '
return self.doLoop76Mode(argtype, cnt, mode)
if self.dbug: print "Unknown command", cmd
result = []
return result
# add full tag path to injected snippets
def updateName(self, tag, prefix):
name = tag[0]
subtagList = tag[1]
argtype = tag[2]
argList = tag[3]
nname = prefix + '.' + name
nsubtaglist = []
for j in subtagList:
nsubtaglist.append(self.updateName(j,prefix))
ntag = []
ntag.append(nname)
ntag.append(nsubtaglist)
ntag.append(argtype)
ntag.append(argList)
return ntag
# perform depth first injection of specified snippets into this one
def injectSnippets(self, snippet):
snipno, tag = snippet
name = tag[0]
subtagList = tag[1]
argtype = tag[2]
argList = tag[3]
nsubtagList = []
if len(argList) > 0 :
for j in argList:
asnip = self.snippetList[j]
aso, atag = self.injectSnippets(asnip)
atag = self.updateName(atag, name)
nsubtagList.append(atag)
argtype='number'
argList=[]
if len(nsubtagList) > 0 :
subtagList.extend(nsubtagList)
tag = []
tag.append(name)
tag.append(subtagList)
tag.append(argtype)
tag.append(argList)
snippet = []
snippet.append(snipno)
snippet.append(tag)
return snippet
# format the tag for output
def formatTag(self, node):
name = node[0]
subtagList = node[1]
argtype = node[2]
argList = node[3]
fullpathname = name.split('.')
nodename = fullpathname.pop()
ilvl = len(fullpathname)
indent = ' ' * (3 * ilvl)
rlst = []
rlst.append(indent + '<' + nodename + '>')
if len(argList) > 0:
alst = []
for j in argList:
if (argtype == 'text') or (argtype == 'scalar_text') :
alst.append(j + '|')
else :
alst.append(str(j) + ',')
argres = "".join(alst)
argres = argres[0:-1]
if argtype == 'snippets' :
rlst.append('snippets:' + argres)
else :
rlst.append(argres)
if len(subtagList) > 0 :
rlst.append('\n')
for j in subtagList:
if len(j) > 0 :
rlst.append(self.formatTag(j))
rlst.append(indent + '</' + nodename + '>\n')
else:
rlst.append('</' + nodename + '>\n')
return "".join(rlst)
# flatten tag
def flattenTag(self, node):
name = node[0]
subtagList = node[1]
argtype = node[2]
argList = node[3]
rlst = []
rlst.append(name)
if (len(argList) > 0):
alst = []
for j in argList:
if (argtype == 'text') or (argtype == 'scalar_text') :
alst.append(j + '|')
else :
alst.append(str(j) + '|')
argres = "".join(alst)
argres = argres[0:-1]
if argtype == 'snippets' :
rlst.append('.snippets=' + argres)
else :
rlst.append('=' + argres)
rlst.append('\n')
for j in subtagList:
if len(j) > 0 :
rlst.append(self.flattenTag(j))
return "".join(rlst)
# reduce create xml output
def formatDoc(self, flat_xml):
rlst = []
for j in self.doc :
if len(j) > 0:
if flat_xml:
rlst.append(self.flattenTag(j))
else:
rlst.append(self.formatTag(j))
result = "".join(rlst)
if self.debug : print result
return result
# main loop - parse the page.dat files
# to create structured document and snippets
# FIXME: value at end of magic appears to be a subtags count
# but for what? For now, inject an 'info" tag as it is in
# every dictionary and seems close to what is meant
# The alternative is to special case the last _ "0x5f" to mean something
def process(self):
# peek at the first bytes to see what type of file it is
magic = self.fo.read(9)
if (magic[0:1] == 'p') and (magic[2:9] == 'marker_'):
first_token = 'info'
elif (magic[0:1] == 'p') and (magic[2:9] == '__PAGE_'):
skip = self.fo.read(2)
first_token = 'info'
elif (magic[0:1] == 'p') and (magic[2:8] == '_PAGE_'):
first_token = 'info'
elif (magic[0:1] == 'g') and (magic[2:9] == '__GLYPH'):
skip = self.fo.read(3)
first_token = 'info'
else :
# other0.dat file
first_token = None
self.fo.seek(-9,1)
# main loop to read and build the document tree
while True:
if first_token != None :
# use "inserted" first token 'info' for page and glyph files
tag = self.procToken(first_token)
if len(tag) > 0 :
self.doc.append(tag)
first_token = None
v = self.getNext()
if (v == None):
break
if (v == 0x72):
self.doLoop72('number')
elif (v > 0) and (v < self.dict.getSize()) :
tag = self.procToken(self.dict.lookup(v))
if len(tag) > 0 :
self.doc.append(tag)
else:
if self.debug:
print "Main Loop: Unknown value: %x" % v
if (v == 0):
if (self.peek(1) == 0x5f):
skip = self.fo.read(1)
first_token = 'info'
# now do snippet injection
if len(self.snippetList) > 0 :
if self.debug : print 'Injecting Snippets:'
snippet = self.injectSnippets(self.snippetList[0])
snipno = snippet[0]
tag_add = snippet[1]
if self.debug : print self.formatTag(tag_add)
if len(tag_add) > 0:
self.doc.append(tag_add)
# handle generation of xml output
xmlpage = self.formatDoc(self.flat_xml)
return xmlpage
def fromData(dict, fname):
flat_xml = True
debug = False
pp = PageParser(fname, dict, debug, flat_xml)
xmlpage = pp.process()
return xmlpage
def getXML(dict, fname):
flat_xml = False
debug = False
pp = PageParser(fname, dict, debug, flat_xml)
xmlpage = pp.process()
return xmlpage
def usage():
print 'Usage: '
print ' convert2xml.py dict0000.dat infile.dat '
print ' '
print ' Options:'
print ' -h print this usage help message '
print ' -d turn on debug output to check for potential errors '
print ' --flat-xml output the flattened xml page description only '
print ' '
print ' This program will attempt to convert a page*.dat file or '
print ' glyphs*.dat file, using the dict0000.dat file, to its xml description. '
print ' '
print ' Use "cmbtc_dump.py" first to unencrypt, uncompress, and dump '
print ' the *.dat files from a Topaz format e-book.'
#
# Main
#
def main(argv):
dictFile = ""
pageFile = ""
debug = False
flat_xml = False
printOutput = False
if len(argv) == 0:
printOutput = True
argv = sys.argv
try:
opts, args = getopt.getopt(argv[1:], "hd", ["flat-xml"])
except getopt.GetoptError, err:
# print help information and exit:
print str(err) # will print something like "option -a not recognized"
usage()
sys.exit(2)
if len(opts) == 0 and len(args) == 0 :
usage()
sys.exit(2)
for o, a in opts:
if o =="-d":
debug=True
if o =="-h":
usage()
sys.exit(0)
if o =="--flat-xml":
flat_xml = True
dictFile, pageFile = args[0], args[1]
# read in the string table dictionary
dict = Dictionary(dictFile)
# dict.dumpDict()
# create a page parser
pp = PageParser(pageFile, dict, debug, flat_xml)
xmlpage = pp.process()
if printOutput:
print xmlpage
return 0
return xmlpage
if __name__ == '__main__':
sys.exit(main(''))

793
Other_Tools/KindleBooks/lib/flatxml2html.py
View File

@@ -1,793 +0,0 @@
#! /usr/bin/python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
# For use with Topaz Scripts Version 2.6
import sys
import csv
import os
import math
import getopt
from struct import pack
from struct import unpack
class DocParser(object):
def __init__(self, flatxml, classlst, fileid, bookDir, gdict, fixedimage):
self.id = os.path.basename(fileid).replace('.dat','')
self.svgcount = 0
self.docList = flatxml.split('\n')
self.docSize = len(self.docList)
self.classList = {}
self.bookDir = bookDir
self.gdict = gdict
tmpList = classlst.split('\n')
for pclass in tmpList:
if pclass != '':
# remove the leading period from the css name
cname = pclass[1:]
self.classList[cname] = True
self.fixedimage = fixedimage
self.ocrtext = []
self.link_id = []
self.link_title = []
self.link_page = []
self.link_href = []
self.link_type = []
self.dehyphen_rootid = []
self.paracont_stemid = []
self.parastems_stemid = []
def getGlyph(self, gid):
result = ''
id='id="gl%d"' % gid
return self.gdict.lookup(id)
def glyphs_to_image(self, glyphList):
def extract(path, key):
b = path.find(key) + len(key)
e = path.find(' ',b)
return int(path[b:e])
svgDir = os.path.join(self.bookDir,'svg')
imgDir = os.path.join(self.bookDir,'img')
imgname = self.id + '_%04d.svg' % self.svgcount
imgfile = os.path.join(imgDir,imgname)
# get glyph information
gxList = self.getData('info.glyph.x',0,-1)
gyList = self.getData('info.glyph.y',0,-1)
gidList = self.getData('info.glyph.glyphID',0,-1)
gids = []
maxws = []
maxhs = []
xs = []
ys = []
gdefs = []
# get path defintions, positions, dimensions for each glyph
# that makes up the image, and find min x and min y to reposition origin
minx = -1
miny = -1
for j in glyphList:
gid = gidList[j]
gids.append(gid)
xs.append(gxList[j])
if minx == -1: minx = gxList[j]
else : minx = min(minx, gxList[j])
ys.append(gyList[j])
if miny == -1: miny = gyList[j]
else : miny = min(miny, gyList[j])
path = self.getGlyph(gid)
gdefs.append(path)
maxws.append(extract(path,'width='))
maxhs.append(extract(path,'height='))
# change the origin to minx, miny and calc max height and width
maxw = maxws[0] + xs[0] - minx
maxh = maxhs[0] + ys[0] - miny
for j in xrange(0, len(xs)):
xs[j] = xs[j] - minx
ys[j] = ys[j] - miny
maxw = max( maxw, (maxws[j] + xs[j]) )
maxh = max( maxh, (maxhs[j] + ys[j]) )
# open the image file for output
ifile = open(imgfile,'w')
ifile.write('<?xml version="1.0" standalone="no"?>\n')
ifile.write('<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n')
ifile.write('<svg width="%dpx" height="%dpx" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1">\n' % (math.floor(maxw/10), math.floor(maxh/10), maxw, maxh))
ifile.write('<defs>\n')
for j in xrange(0,len(gdefs)):
ifile.write(gdefs[j])
ifile.write('</defs>\n')
for j in xrange(0,len(gids)):
ifile.write('<use xlink:href="#gl%d" x="%d" y="%d" />\n' % (gids[j], xs[j], ys[j]))
ifile.write('</svg>')
ifile.close()
return 0
# return tag at line pos in document
def lineinDoc(self, pos) :
if (pos >= 0) and (pos < self.docSize) :
item = self.docList[pos]
if item.find('=') >= 0:
(name, argres) = item.split('=',1)
else :
name = item
argres = ''
return name, argres
# find tag in doc if within pos to end inclusive
def findinDoc(self, tagpath, pos, end) :
result = None
if end == -1 :
end = self.docSize
else:
end = min(self.docSize, end)
foundat = -1
for j in xrange(pos, end):
item = self.docList[j]
if item.find('=') >= 0:
(name, argres) = item.split('=',1)
else :
name = item
argres = ''
if name.endswith(tagpath) :
result = argres
foundat = j
break
return foundat, result
# return list of start positions for the tagpath
def posinDoc(self, tagpath):
startpos = []
pos = 0
res = ""
while res != None :
(foundpos, res) = self.findinDoc(tagpath, pos, -1)
if res != None :
startpos.append(foundpos)
pos = foundpos + 1
return startpos
# returns a vector of integers for the tagpath
def getData(self, tagpath, pos, end):
argres=[]
(foundat, argt) = self.findinDoc(tagpath, pos, end)
if (argt != None) and (len(argt) > 0) :
argList = argt.split('|')
argres = [ int(strval) for strval in argList]
return argres
# get the class
def getClass(self, pclass):
nclass = pclass
# class names are an issue given topaz may start them with numerals (not allowed),
# use a mix of cases (which cause some browsers problems), and actually
# attach numbers after "_reclustered*" to the end to deal classeses that inherit
# from a base class (but then not actually provide all of these _reclustereed
# classes in the stylesheet!
# so we clean this up by lowercasing, prepend 'cl-', and getting any baseclass
# that exists in the stylesheet first, and then adding this specific class
# after
# also some class names have spaces in them so need to convert to dashes
if nclass != None :
nclass = nclass.replace(' ','-')
classres = ''
nclass = nclass.lower()
nclass = 'cl-' + nclass
baseclass = ''
# graphic is the base class for captions
if nclass.find('cl-cap-') >=0 :
classres = 'graphic' + ' '
else :
# strip to find baseclass
p = nclass.find('_')
if p > 0 :
baseclass = nclass[0:p]
if baseclass in self.classList:
classres += baseclass + ' '
classres += nclass
nclass = classres
return nclass
# develop a sorted description of the starting positions of
# groups and regions on the page, as well as the page type
def PageDescription(self):
def compare(x, y):
(xtype, xval) = x
(ytype, yval) = y
if xval > yval:
return 1
if xval == yval:
return 0
return -1
result = []
(pos, pagetype) = self.findinDoc('page.type',0,-1)
groupList = self.posinDoc('page.group')
groupregionList = self.posinDoc('page.group.region')
pageregionList = self.posinDoc('page.region')
# integrate into one list
for j in groupList:
result.append(('grpbeg',j))
for j in groupregionList:
result.append(('gregion',j))
for j in pageregionList:
result.append(('pregion',j))
result.sort(compare)
# insert group end and page end indicators
inGroup = False
j = 0
while True:
if j == len(result): break
rtype = result[j][0]
rval = result[j][1]
if not inGroup and (rtype == 'grpbeg') :
inGroup = True
j = j + 1
elif inGroup and (rtype in ('grpbeg', 'pregion')):
result.insert(j,('grpend',rval))
inGroup = False
else:
j = j + 1
if inGroup:
result.append(('grpend',-1))
result.append(('pageend', -1))
return pagetype, result
# build a description of the paragraph
def getParaDescription(self, start, end, regtype):
result = []
# paragraph
(pos, pclass) = self.findinDoc('paragraph.class',start,end)
pclass = self.getClass(pclass)
# if paragraph uses extratokens (extra glyphs) then make it fixed
(pos, extraglyphs) = self.findinDoc('paragraph.extratokens',start,end)
# build up a description of the paragraph in result and return it
# first check for the basic - all words paragraph
(pos, sfirst) = self.findinDoc('paragraph.firstWord',start,end)
(pos, slast) = self.findinDoc('paragraph.lastWord',start,end)
if (sfirst != None) and (slast != None) :
first = int(sfirst)
last = int(slast)
makeImage = (regtype == 'vertical') or (regtype == 'table')
makeImage = makeImage or (extraglyphs != None)
if self.fixedimage:
makeImage = makeImage or (regtype == 'fixed')
if (pclass != None):
makeImage = makeImage or (pclass.find('.inverted') >= 0)
if self.fixedimage :
makeImage = makeImage or (pclass.find('cl-f-') >= 0)
# before creating an image make sure glyph info exists
gidList = self.getData('info.glyph.glyphID',0,-1)
makeImage = makeImage & (len(gidList) > 0)
if not makeImage :
# standard all word paragraph
for wordnum in xrange(first, last):
result.append(('ocr', wordnum))
return pclass, result
# convert paragraph to svg image
# translate first and last word into first and last glyphs
# and generate inline image and include it
glyphList = []
firstglyphList = self.getData('word.firstGlyph',0,-1)
gidList = self.getData('info.glyph.glyphID',0,-1)
firstGlyph = firstglyphList[first]
if last < len(firstglyphList):
lastGlyph = firstglyphList[last]
else :
lastGlyph = len(gidList)
# handle case of white sapce paragraphs with no actual glyphs in them
# by reverting to text based paragraph
if firstGlyph >= lastGlyph:
# revert to standard text based paragraph
for wordnum in xrange(first, last):
result.append(('ocr', wordnum))
return pclass, result
for glyphnum in xrange(firstGlyph, lastGlyph):
glyphList.append(glyphnum)
# include any extratokens if they exist
(pos, sfg) = self.findinDoc('extratokens.firstGlyph',start,end)
(pos, slg) = self.findinDoc('extratokens.lastGlyph',start,end)
if (sfg != None) and (slg != None):
for glyphnum in xrange(int(sfg), int(slg)):
glyphList.append(glyphnum)
num = self.svgcount
self.glyphs_to_image(glyphList)
self.svgcount += 1
result.append(('svg', num))
return pclass, result
# this type of paragraph may be made up of multiple spans, inline
# word monograms (images), and words with semantic meaning,
# plus glyphs used to form starting letter of first word
# need to parse this type line by line
line = start + 1
word_class = ''
# if end is -1 then we must search to end of document
if end == -1 :
end = self.docSize
# seems some xml has last* coming before first* so we have to
# handle any order
sp_first = -1
sp_last = -1
gl_first = -1
gl_last = -1
ws_first = -1
ws_last = -1
word_class = ''
word_semantic_type = ''
while (line < end) :
(name, argres) = self.lineinDoc(line)
if name.endswith('span.firstWord') :
sp_first = int(argres)
elif name.endswith('span.lastWord') :
sp_last = int(argres)
elif name.endswith('word.firstGlyph') :
gl_first = int(argres)
elif name.endswith('word.lastGlyph') :
gl_last = int(argres)
elif name.endswith('word_semantic.firstWord'):
ws_first = int(argres)
elif name.endswith('word_semantic.lastWord'):
ws_last = int(argres)
elif name.endswith('word.class'):
(cname, space) = argres.split('-',1)
if space == '' : space = '0'
if (cname == 'spaceafter') and (int(space) > 0) :
word_class = 'sa'
elif name.endswith('word.img.src'):
result.append(('img' + word_class, int(argres)))
word_class = ''
elif name.endswith('region.img.src'):
result.append(('img' + word_class, int(argres)))
if (sp_first != -1) and (sp_last != -1):
for wordnum in xrange(sp_first, sp_last):
result.append(('ocr', wordnum))
sp_first = -1
sp_last = -1
if (gl_first != -1) and (gl_last != -1):
glyphList = []
for glyphnum in xrange(gl_first, gl_last):
glyphList.append(glyphnum)
num = self.svgcount
self.glyphs_to_image(glyphList)
self.svgcount += 1
result.append(('svg', num))
gl_first = -1
gl_last = -1
if (ws_first != -1) and (ws_last != -1):
for wordnum in xrange(ws_first, ws_last):
result.append(('ocr', wordnum))
ws_first = -1
ws_last = -1
line += 1
return pclass, result
def buildParagraph(self, pclass, pdesc, type, regtype) :
parares = ''
sep =''
classres = ''
if pclass :
classres = ' class="' + pclass + '"'
br_lb = (regtype == 'fixed') or (regtype == 'chapterheading') or (regtype == 'vertical')
handle_links = len(self.link_id) > 0
if (type == 'full') or (type == 'begin') :
parares += '<p' + classres + '>'
if (type == 'end'):
parares += ' '
lstart = len(parares)
cnt = len(pdesc)
for j in xrange( 0, cnt) :
(wtype, num) = pdesc[j]
if wtype == 'ocr' :
word = self.ocrtext[num]
sep = ' '
if handle_links:
link = self.link_id[num]
if (link > 0):
linktype = self.link_type[link-1]
title = self.link_title[link-1]
if (title == "") or (parares.rfind(title) < 0):
title=parares[lstart:]
if linktype == 'external' :
linkhref = self.link_href[link-1]
linkhtml = '<a href="%s">' % linkhref
else :
if len(self.link_page) >= link :
ptarget = self.link_page[link-1] - 1
linkhtml = '<a href="#page%04d">' % ptarget
else :
# just link to the current page
linkhtml = '<a href="#' + self.id + '">'
linkhtml += title + '</a>'
pos = parares.rfind(title)
if pos >= 0:
parares = parares[0:pos] + linkhtml + parares[pos+len(title):]
else :
parares += linkhtml
lstart = len(parares)
if word == '_link_' : word = ''
elif (link < 0) :
if word == '_link_' : word = ''
if word == '_lb_':
if ((num-1) in self.dehyphen_rootid ) or handle_links:
word = ''
sep = ''
elif br_lb :
word = '<br />\n'
sep = ''
else :
word = '\n'
sep = ''
if num in self.dehyphen_rootid :
word = word[0:-1]
sep = ''
parares += word + sep
elif wtype == 'img' :
sep = ''
parares += '<img src="img/img%04d.jpg" alt="" />' % num
parares += sep
elif wtype == 'imgsa' :
sep = ' '
parares += '<img src="img/img%04d.jpg" alt="" />' % num
parares += sep
elif wtype == 'svg' :
sep = ''
parares += '<img src="img/' + self.id + '_%04d.svg" alt="" />' % num
parares += sep
if len(sep) > 0 : parares = parares[0:-1]
if (type == 'full') or (type == 'end') :
parares += '</p>'
return parares
def buildTOCEntry(self, pdesc) :
parares = ''
sep =''
tocentry = ''
handle_links = len(self.link_id) > 0
lstart = 0
cnt = len(pdesc)
for j in xrange( 0, cnt) :
(wtype, num) = pdesc[j]
if wtype == 'ocr' :
word = self.ocrtext[num]
sep = ' '
if handle_links:
link = self.link_id[num]
if (link > 0):
linktype = self.link_type[link-1]
title = self.link_title[link-1]
title = title.rstrip('. ')
alt_title = parares[lstart:]
alt_title = alt_title.strip()
# now strip off the actual printed page number
alt_title = alt_title.rstrip('01234567890ivxldIVXLD-.')
alt_title = alt_title.rstrip('. ')
# skip over any external links - can't have them in a books toc
if linktype == 'external' :
title = ''
alt_title = ''
linkpage = ''
else :
if len(self.link_page) >= link :
ptarget = self.link_page[link-1] - 1
linkpage = '%04d' % ptarget
else :
# just link to the current page
linkpage = self.id[4:]
if len(alt_title) >= len(title):
title = alt_title
if title != '' and linkpage != '':
tocentry += title + '|' + linkpage + '\n'
lstart = len(parares)
if word == '_link_' : word = ''
elif (link < 0) :
if word == '_link_' : word = ''
if word == '_lb_':
word = ''
sep = ''
if num in self.dehyphen_rootid :
word = word[0:-1]
sep = ''
parares += word + sep
else :
continue
return tocentry
# walk the document tree collecting the information needed
# to build an html page using the ocrText
def process(self):
tocinfo = ''
hlst = []
# get the ocr text
(pos, argres) = self.findinDoc('info.word.ocrText',0,-1)
if argres : self.ocrtext = argres.split('|')
# get information to dehyphenate the text
self.dehyphen_rootid = self.getData('info.dehyphen.rootID',0,-1)
# determine if first paragraph is continued from previous page
(pos, self.parastems_stemid) = self.findinDoc('info.paraStems.stemID',0,-1)
first_para_continued = (self.parastems_stemid != None)
# determine if last paragraph is continued onto the next page
(pos, self.paracont_stemid) = self.findinDoc('info.paraCont.stemID',0,-1)
last_para_continued = (self.paracont_stemid != None)
# collect link ids
self.link_id = self.getData('info.word.link_id',0,-1)
# collect link destination page numbers
self.link_page = self.getData('info.links.page',0,-1)
# collect link types (container versus external)
(pos, argres) = self.findinDoc('info.links.type',0,-1)
if argres : self.link_type = argres.split('|')
# collect link destinations
(pos, argres) = self.findinDoc('info.links.href',0,-1)
if argres : self.link_href = argres.split('|')
# collect link titles
(pos, argres) = self.findinDoc('info.links.title',0,-1)
if argres :
self.link_title = argres.split('|')
else:
self.link_title.append('')
# get a descriptions of the starting points of the regions
# and groups on the page
(pagetype, pageDesc) = self.PageDescription()
regcnt = len(pageDesc) - 1
anchorSet = False
breakSet = False
inGroup = False
# process each region on the page and convert what you can to html
for j in xrange(regcnt):
(etype, start) = pageDesc[j]
(ntype, end) = pageDesc[j+1]
# set anchor for link target on this page
if not anchorSet and not first_para_continued:
hlst.append('<div style="visibility: hidden; height: 0; width: 0;" id="')
hlst.append(self.id + '" title="pagetype_' + pagetype + '"></div>\n')
anchorSet = True
# handle groups of graphics with text captions
if (etype == 'grpbeg'):
(pos, grptype) = self.findinDoc('group.type', start, end)
if grptype != None:
if grptype == 'graphic':
gcstr = ' class="' + grptype + '"'
hlst.append('<div' + gcstr + '>')
inGroup = True
elif (etype == 'grpend'):
if inGroup:
hlst.append('</div>\n')
inGroup = False
else:
(pos, regtype) = self.findinDoc('region.type',start,end)
if regtype == 'graphic' :
(pos, simgsrc) = self.findinDoc('img.src',start,end)
if simgsrc:
if inGroup:
hlst.append('<img src="img/img%04d.jpg" alt="" />' % int(simgsrc))
else:
hlst.append('<div class="graphic"><img src="img/img%04d.jpg" alt="" /></div>' % int(simgsrc))
elif regtype == 'chapterheading' :
(pclass, pdesc) = self.getParaDescription(start,end, regtype)
if not breakSet:
hlst.append('<div style="page-break-after: always;">&nbsp;</div>\n')
breakSet = True
tag = 'h1'
if pclass and (len(pclass) >= 7):
if pclass[3:7] == 'ch1-' : tag = 'h1'
if pclass[3:7] == 'ch2-' : tag = 'h2'
if pclass[3:7] == 'ch3-' : tag = 'h3'
hlst.append('<' + tag + ' class="' + pclass + '">')
else:
hlst.append('<' + tag + '>')
hlst.append(self.buildParagraph(pclass, pdesc, 'middle', regtype))
hlst.append('</' + tag + '>')
elif (regtype == 'text') or (regtype == 'fixed') or (regtype == 'insert') or (regtype == 'listitem'):
ptype = 'full'
# check to see if this is a continution from the previous page
if first_para_continued :
ptype = 'end'
first_para_continued = False
(pclass, pdesc) = self.getParaDescription(start,end, regtype)
if pclass and (len(pclass) >= 6) and (ptype == 'full'):
tag = 'p'
if pclass[3:6] == 'h1-' : tag = 'h4'
if pclass[3:6] == 'h2-' : tag = 'h5'
if pclass[3:6] == 'h3-' : tag = 'h6'
hlst.append('<' + tag + ' class="' + pclass + '">')
hlst.append(self.buildParagraph(pclass, pdesc, 'middle', regtype))
hlst.append('</' + tag + '>')
else :
hlst.append(self.buildParagraph(pclass, pdesc, ptype, regtype))
elif (regtype == 'tocentry') :
ptype = 'full'
if first_para_continued :
ptype = 'end'
first_para_continued = False
(pclass, pdesc) = self.getParaDescription(start,end, regtype)
tocinfo += self.buildTOCEntry(pdesc)
hlst.append(self.buildParagraph(pclass, pdesc, ptype, regtype))
elif (regtype == 'vertical') or (regtype == 'table') :
ptype = 'full'
if inGroup:
ptype = 'middle'
if first_para_continued :
ptype = 'end'
first_para_continued = False
(pclass, pdesc) = self.getParaDescription(start, end, regtype)
hlst.append(self.buildParagraph(pclass, pdesc, ptype, regtype))
elif (regtype == 'synth_fcvr.center'):
(pos, simgsrc) = self.findinDoc('img.src',start,end)
if simgsrc:
hlst.append('<div class="graphic"><img src="img/img%04d.jpg" alt="" /></div>' % int(simgsrc))
else :
print ' Making region type', regtype,
(pos, temp) = self.findinDoc('paragraph',start,end)
(pos2, temp) = self.findinDoc('span',start,end)
if pos != -1 or pos2 != -1:
print ' a "text" region'
orig_regtype = regtype
regtype = 'fixed'
ptype = 'full'
# check to see if this is a continution from the previous page
if first_para_continued :
ptype = 'end'
first_para_continued = False
(pclass, pdesc) = self.getParaDescription(start,end, regtype)
if not pclass:
if orig_regtype.endswith('.right') : pclass = 'cl-right'
elif orig_regtype.endswith('.center') : pclass = 'cl-center'
elif orig_regtype.endswith('.left') : pclass = 'cl-left'
elif orig_regtype.endswith('.justify') : pclass = 'cl-justify'
if pclass and (ptype == 'full') and (len(pclass) >= 6):
tag = 'p'
if pclass[3:6] == 'h1-' : tag = 'h4'
if pclass[3:6] == 'h2-' : tag = 'h5'
if pclass[3:6] == 'h3-' : tag = 'h6'
hlst.append('<' + tag + ' class="' + pclass + '">')
hlst.append(self.buildParagraph(pclass, pdesc, 'middle', regtype))
hlst.append('</' + tag + '>')
else :
hlst.append(self.buildParagraph(pclass, pdesc, ptype, regtype))
else :
print ' a "graphic" region'
(pos, simgsrc) = self.findinDoc('img.src',start,end)
if simgsrc:
hlst.append('<div class="graphic"><img src="img/img%04d.jpg" alt="" /></div>' % int(simgsrc))
htmlpage = "".join(hlst)
if last_para_continued :
if htmlpage[-4:] == '</p>':
htmlpage = htmlpage[0:-4]
last_para_continued = False
return htmlpage, tocinfo
def convert2HTML(flatxml, classlst, fileid, bookDir, gdict, fixedimage):
# create a document parser
dp = DocParser(flatxml, classlst, fileid, bookDir, gdict, fixedimage)
htmlpage, tocinfo = dp.process()
return htmlpage, tocinfo

249
Other_Tools/KindleBooks/lib/flatxml2svg.py
View File

@@ -1,249 +0,0 @@
#! /usr/bin/python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import sys
import csv
import os
import getopt
from struct import pack
from struct import unpack
class PParser(object):
def __init__(self, gd, flatxml, meta_array):
self.gd = gd
self.flatdoc = flatxml.split('\n')
self.docSize = len(self.flatdoc)
self.temp = []
self.ph = -1
self.pw = -1
startpos = self.posinDoc('page.h') or self.posinDoc('book.h')
for p in startpos:
(name, argres) = self.lineinDoc(p)
self.ph = max(self.ph, int(argres))
startpos = self.posinDoc('page.w') or self.posinDoc('book.w')
for p in startpos:
(name, argres) = self.lineinDoc(p)
self.pw = max(self.pw, int(argres))
if self.ph <= 0:
self.ph = int(meta_array.get('pageHeight', '11000'))
if self.pw <= 0:
self.pw = int(meta_array.get('pageWidth', '8500'))
res = []
startpos = self.posinDoc('info.glyph.x')
for p in startpos:
argres = self.getDataatPos('info.glyph.x', p)
res.extend(argres)
self.gx = res
res = []
startpos = self.posinDoc('info.glyph.y')
for p in startpos:
argres = self.getDataatPos('info.glyph.y', p)
res.extend(argres)
self.gy = res
res = []
startpos = self.posinDoc('info.glyph.glyphID')
for p in startpos:
argres = self.getDataatPos('info.glyph.glyphID', p)
res.extend(argres)
self.gid = res
# return tag at line pos in document
def lineinDoc(self, pos) :
if (pos >= 0) and (pos < self.docSize) :
item = self.flatdoc[pos]
if item.find('=') >= 0:
(name, argres) = item.split('=',1)
else :
name = item
argres = ''
return name, argres
# find tag in doc if within pos to end inclusive
def findinDoc(self, tagpath, pos, end) :
result = None
if end == -1 :
end = self.docSize
else:
end = min(self.docSize, end)
foundat = -1
for j in xrange(pos, end):
item = self.flatdoc[j]
if item.find('=') >= 0:
(name, argres) = item.split('=',1)
else :
name = item
argres = ''
if name.endswith(tagpath) :
result = argres
foundat = j
break
return foundat, result
# return list of start positions for the tagpath
def posinDoc(self, tagpath):
startpos = []
pos = 0
res = ""
while res != None :
(foundpos, res) = self.findinDoc(tagpath, pos, -1)
if res != None :
startpos.append(foundpos)
pos = foundpos + 1
return startpos
def getData(self, path):
result = None
cnt = len(self.flatdoc)
for j in xrange(cnt):
item = self.flatdoc[j]
if item.find('=') >= 0:
(name, argt) = item.split('=')
argres = argt.split('|')
else:
name = item
argres = []
if (name.endswith(path)):
result = argres
break
if (len(argres) > 0) :
for j in xrange(0,len(argres)):
argres[j] = int(argres[j])
return result
def getDataatPos(self, path, pos):
result = None
item = self.flatdoc[pos]
if item.find('=') >= 0:
(name, argt) = item.split('=')
argres = argt.split('|')
else:
name = item
argres = []
if (len(argres) > 0) :
for j in xrange(0,len(argres)):
argres[j] = int(argres[j])
if (name.endswith(path)):
result = argres
return result
def getDataTemp(self, path):
result = None
cnt = len(self.temp)
for j in xrange(cnt):
item = self.temp[j]
if item.find('=') >= 0:
(name, argt) = item.split('=')
argres = argt.split('|')
else:
name = item
argres = []
if (name.endswith(path)):
result = argres
self.temp.pop(j)
break
if (len(argres) > 0) :
for j in xrange(0,len(argres)):
argres[j] = int(argres[j])
return result
def getImages(self):
result = []
self.temp = self.flatdoc
while (self.getDataTemp('img') != None):
h = self.getDataTemp('img.h')[0]
w = self.getDataTemp('img.w')[0]
x = self.getDataTemp('img.x')[0]
y = self.getDataTemp('img.y')[0]
src = self.getDataTemp('img.src')[0]
result.append('<image xlink:href="../img/img%04d.jpg" x="%d" y="%d" width="%d" height="%d" />\n' % (src, x, y, w, h))
return result
def getGlyphs(self):
result = []
if (self.gid != None) and (len(self.gid) > 0):
glyphs = []
for j in set(self.gid):
glyphs.append(j)
glyphs.sort()
for gid in glyphs:
id='id="gl%d"' % gid
path = self.gd.lookup(id)
if path:
result.append(id + ' ' + path)
return result
def convert2SVG(gdict, flat_xml, pageid, previd, nextid, svgDir, raw, meta_array, scaledpi):
mlst = []
pp = PParser(gdict, flat_xml, meta_array)
mlst.append('<?xml version="1.0" standalone="no"?>\n')
if (raw):
mlst.append('<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n')
mlst.append('<svg width="%fin" height="%fin" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1">\n' % (pp.pw / scaledpi, pp.ph / scaledpi, pp.pw -1, pp.ph -1))
mlst.append('<title>Page %d - %s by %s</title>\n' % (pageid, meta_array['Title'],meta_array['Authors']))
else:
mlst.append('<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n')
mlst.append('<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" ><head>\n')
mlst.append('<title>Page %d - %s by %s</title>\n' % (pageid, meta_array['Title'],meta_array['Authors']))
mlst.append('<script><![CDATA[\n')
mlst.append('function gd(){var p=window.location.href.replace(/^.*\?dpi=(\d+).*$/i,"$1");return p;}\n')
mlst.append('var dpi=%d;\n' % scaledpi)
if (previd) :
mlst.append('var prevpage="page%04d.xhtml";\n' % (previd))
if (nextid) :
mlst.append('var nextpage="page%04d.xhtml";\n' % (nextid))
mlst.append('var pw=%d;var ph=%d;' % (pp.pw, pp.ph))
mlst.append('function zoomin(){dpi=dpi*(0.8);setsize();}\n')
mlst.append('function zoomout(){dpi=dpi*1.25;setsize();}\n')
mlst.append('function setsize(){var svg=document.getElementById("svgimg");var prev=document.getElementById("prevsvg");var next=document.getElementById("nextsvg");var width=(pw/dpi)+"in";var height=(ph/dpi)+"in";svg.setAttribute("width",width);svg.setAttribute("height",height);prev.setAttribute("height",height);prev.setAttribute("width","50px");next.setAttribute("height",height);next.setAttribute("width","50px");}\n')
mlst.append('function ppage(){window.location.href=prevpage+"?dpi="+Math.round(dpi);}\n')
mlst.append('function npage(){window.location.href=nextpage+"?dpi="+Math.round(dpi);}\n')
mlst.append('var gt=gd();if(gt>0){dpi=gt;}\n')
mlst.append('window.onload=setsize;\n')
mlst.append(']]></script>\n')
mlst.append('</head>\n')
mlst.append('<body onLoad="setsize();" style="background-color:#777;text-align:center;">\n')
mlst.append('<div style="white-space:nowrap;">\n')
if previd == None:
mlst.append('<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n')
else:
mlst.append('<a href="javascript:ppage();"><svg id="prevsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,150,95,5,95,295" fill="#AAAAAA" /></svg></a>\n')
mlst.append('<a href="javascript:npage();"><svg id="svgimg" viewBox="0 0 %d %d" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" version="1.1" style="background-color:#FFF;border:1px solid black;">' % (pp.pw, pp.ph))
if (pp.gid != None):
mlst.append('<defs>\n')
gdefs = pp.getGlyphs()
for j in xrange(0,len(gdefs)):
mlst.append(gdefs[j])
mlst.append('</defs>\n')
img = pp.getImages()
if (img != None):
for j in xrange(0,len(img)):
mlst.append(img[j])
if (pp.gid != None):
for j in xrange(0,len(pp.gid)):
mlst.append('<use xlink:href="#gl%d" x="%d" y="%d" />\n' % (pp.gid[j], pp.gx[j], pp.gy[j]))
if (img == None or len(img) == 0) and (pp.gid == None or len(pp.gid) == 0):
xpos = "%d" % (pp.pw // 3)
ypos = "%d" % (pp.ph // 3)
mlst.append('<text x="' + xpos + '" y="' + ypos + '" font-size="' + meta_array['fontSize'] + '" font-family="Helvetica" stroke="black">This page intentionally left blank.</text>\n')
if (raw) :
mlst.append('</svg>')
else :
mlst.append('</svg></a>\n')
if nextid == None:
mlst.append('<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"></svg></a>\n')
else :
mlst.append('<a href="javascript:npage();"><svg id="nextsvg" viewBox="0 0 100 300" xmlns="http://www.w3.org/2000/svg" version="1.1" style="background-color:#777"><polygon points="5,5,5,295,95,150" fill="#AAAAAA" /></svg></a>\n')
mlst.append('</div>\n')
mlst.append('<div><a href="javascript:zoomin();">zoom in</a> - <a href="javascript:zoomout();">zoom out</a></div>\n')
mlst.append('</body>\n')
mlst.append('</html>\n')
return "".join(mlst)

721
Other_Tools/KindleBooks/lib/genbook.py
View File

@@ -1,721 +0,0 @@
#! /usr/bin/python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
class Unbuffered:
def __init__(self, stream):
self.stream = stream
def write(self, data):
self.stream.write(data)
self.stream.flush()
def __getattr__(self, attr):
return getattr(self.stream, attr)
import sys
sys.stdout=Unbuffered(sys.stdout)
import csv
import os
import getopt
from struct import pack
from struct import unpack
class TpzDRMError(Exception):
pass
# local support routines
if 'calibre' in sys.modules:
inCalibre = True
else:
inCalibre = False
if inCalibre :
from calibre_plugins.k4mobidedrm import convert2xml
from calibre_plugins.k4mobidedrm import flatxml2html
from calibre_plugins.k4mobidedrm import flatxml2svg
from calibre_plugins.k4mobidedrm import stylexml2css
else :
import convert2xml
import flatxml2html
import flatxml2svg
import stylexml2css
# global switch
buildXML = False
# Get a 7 bit encoded number from a file
def readEncodedNumber(file):
flag = False
c = file.read(1)
if (len(c) == 0):
return None
data = ord(c)
if data == 0xFF:
flag = True
c = file.read(1)
if (len(c) == 0):
return None
data = ord(c)
if data >= 0x80:
datax = (data & 0x7F)
while data >= 0x80 :
c = file.read(1)
if (len(c) == 0):
return None
data = ord(c)
datax = (datax <<7) + (data & 0x7F)
data = datax
if flag:
data = -data
return data
# Get a length prefixed string from the file
def lengthPrefixString(data):
return encodeNumber(len(data))+data
def readString(file):
stringLength = readEncodedNumber(file)
if (stringLength == None):
return None
sv = file.read(stringLength)
if (len(sv) != stringLength):
return ""
return unpack(str(stringLength)+"s",sv)[0]
def getMetaArray(metaFile):
# parse the meta file
result = {}
fo = file(metaFile,'rb')
size = readEncodedNumber(fo)
for i in xrange(size):
tag = readString(fo)
value = readString(fo)
result[tag] = value
# print tag, value
fo.close()
return result
# dictionary of all text strings by index value
class Dictionary(object):
def __init__(self, dictFile):
self.filename = dictFile
self.size = 0
self.fo = file(dictFile,'rb')
self.stable = []
self.size = readEncodedNumber(self.fo)
for i in xrange(self.size):
self.stable.append(self.escapestr(readString(self.fo)))
self.pos = 0
def escapestr(self, str):
str = str.replace('&','&amp;')
str = str.replace('<','&lt;')
str = str.replace('>','&gt;')
str = str.replace('=','&#61;')
return str
def lookup(self,val):
if ((val >= 0) and (val < self.size)) :
self.pos = val
return self.stable[self.pos]
else:
print "Error - %d outside of string table limits" % val
raise TpzDRMError('outside or string table limits')
# sys.exit(-1)
def getSize(self):
return self.size
def getPos(self):
return self.pos
class PageDimParser(object):
def __init__(self, flatxml):
self.flatdoc = flatxml.split('\n')
# find tag if within pos to end inclusive
def findinDoc(self, tagpath, pos, end) :
result = None
docList = self.flatdoc
cnt = len(docList)
if end == -1 :
end = cnt
else:
end = min(cnt,end)
foundat = -1
for j in xrange(pos, end):
item = docList[j]
if item.find('=') >= 0:
(name, argres) = item.split('=')
else :
name = item
argres = ''
if name.endswith(tagpath) :
result = argres
foundat = j
break
return foundat, result
def process(self):
(pos, sph) = self.findinDoc('page.h',0,-1)
(pos, spw) = self.findinDoc('page.w',0,-1)
if (sph == None): sph = '-1'
if (spw == None): spw = '-1'
return sph, spw
def getPageDim(flatxml):
# create a document parser
dp = PageDimParser(flatxml)
(ph, pw) = dp.process()
return ph, pw
class GParser(object):
def __init__(self, flatxml):
self.flatdoc = flatxml.split('\n')
self.dpi = 1440
self.gh = self.getData('info.glyph.h')
self.gw = self.getData('info.glyph.w')
self.guse = self.getData('info.glyph.use')
if self.guse :
self.count = len(self.guse)
else :
self.count = 0
self.gvtx = self.getData('info.glyph.vtx')
self.glen = self.getData('info.glyph.len')
self.gdpi = self.getData('info.glyph.dpi')
self.vx = self.getData('info.vtx.x')
self.vy = self.getData('info.vtx.y')
self.vlen = self.getData('info.len.n')
if self.vlen :
self.glen.append(len(self.vlen))
elif self.glen:
self.glen.append(0)
if self.vx :
self.gvtx.append(len(self.vx))
elif self.gvtx :
self.gvtx.append(0)
def getData(self, path):
result = None
cnt = len(self.flatdoc)
for j in xrange(cnt):
item = self.flatdoc[j]
if item.find('=') >= 0:
(name, argt) = item.split('=')
argres = argt.split('|')
else:
name = item
argres = []
if (name == path):
result = argres
break
if (len(argres) > 0) :
for j in xrange(0,len(argres)):
argres[j] = int(argres[j])
return result
def getGlyphDim(self, gly):
if self.gdpi[gly] == 0:
return 0, 0
maxh = (self.gh[gly] * self.dpi) / self.gdpi[gly]
maxw = (self.gw[gly] * self.dpi) / self.gdpi[gly]
return maxh, maxw
def getPath(self, gly):
path = ''
if (gly < 0) or (gly >= self.count):
return path
tx = self.vx[self.gvtx[gly]:self.gvtx[gly+1]]
ty = self.vy[self.gvtx[gly]:self.gvtx[gly+1]]
p = 0
for k in xrange(self.glen[gly], self.glen[gly+1]):
if (p == 0):
zx = tx[0:self.vlen[k]+1]
zy = ty[0:self.vlen[k]+1]
else:
zx = tx[self.vlen[k-1]+1:self.vlen[k]+1]
zy = ty[self.vlen[k-1]+1:self.vlen[k]+1]
p += 1
j = 0
while ( j < len(zx) ):
if (j == 0):
# Start Position.
path += 'M %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly])
elif (j <= len(zx)-3):
# Cubic Bezier Curve
path += 'C %d %d %d %d %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly], zx[j+1] * self.dpi / self.gdpi[gly], zy[j+1] * self.dpi / self.gdpi[gly], zx[j+2] * self.dpi / self.gdpi[gly], zy[j+2] * self.dpi / self.gdpi[gly])
j += 2
elif (j == len(zx)-2):
# Cubic Bezier Curve to Start Position
path += 'C %d %d %d %d %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly], zx[j+1] * self.dpi / self.gdpi[gly], zy[j+1] * self.dpi / self.gdpi[gly], zx[0] * self.dpi / self.gdpi[gly], zy[0] * self.dpi / self.gdpi[gly])
j += 1
elif (j == len(zx)-1):
# Quadratic Bezier Curve to Start Position
path += 'Q %d %d %d %d ' % (zx[j] * self.dpi / self.gdpi[gly], zy[j] * self.dpi / self.gdpi[gly], zx[0] * self.dpi / self.gdpi[gly], zy[0] * self.dpi / self.gdpi[gly])
j += 1
path += 'z'
return path
# dictionary of all text strings by index value
class GlyphDict(object):
def __init__(self):
self.gdict = {}
def lookup(self, id):
# id='id="gl%d"' % val
if id in self.gdict:
return self.gdict[id]
return None
def addGlyph(self, val, path):
id='id="gl%d"' % val
self.gdict[id] = path
def generateBook(bookDir, raw, fixedimage):
# sanity check Topaz file extraction
if not os.path.exists(bookDir) :
print "Can not find directory with unencrypted book"
return 1
dictFile = os.path.join(bookDir,'dict0000.dat')
if not os.path.exists(dictFile) :
print "Can not find dict0000.dat file"
return 1
pageDir = os.path.join(bookDir,'page')
if not os.path.exists(pageDir) :
print "Can not find page directory in unencrypted book"
return 1
imgDir = os.path.join(bookDir,'img')
if not os.path.exists(imgDir) :
print "Can not find image directory in unencrypted book"
return 1
glyphsDir = os.path.join(bookDir,'glyphs')
if not os.path.exists(glyphsDir) :
print "Can not find glyphs directory in unencrypted book"
return 1
metaFile = os.path.join(bookDir,'metadata0000.dat')
if not os.path.exists(metaFile) :
print "Can not find metadata0000.dat in unencrypted book"
return 1
svgDir = os.path.join(bookDir,'svg')
if not os.path.exists(svgDir) :
os.makedirs(svgDir)
if buildXML:
xmlDir = os.path.join(bookDir,'xml')
if not os.path.exists(xmlDir) :
os.makedirs(xmlDir)
otherFile = os.path.join(bookDir,'other0000.dat')
if not os.path.exists(otherFile) :
print "Can not find other0000.dat in unencrypted book"
return 1
print "Updating to color images if available"
spath = os.path.join(bookDir,'color_img')
dpath = os.path.join(bookDir,'img')
filenames = os.listdir(spath)
filenames = sorted(filenames)
for filename in filenames:
imgname = filename.replace('color','img')
sfile = os.path.join(spath,filename)
dfile = os.path.join(dpath,imgname)
imgdata = file(sfile,'rb').read()
file(dfile,'wb').write(imgdata)
print "Creating cover.jpg"
isCover = False
cpath = os.path.join(bookDir,'img')
cpath = os.path.join(cpath,'img0000.jpg')
if os.path.isfile(cpath):
cover = file(cpath, 'rb').read()
cpath = os.path.join(bookDir,'cover.jpg')
file(cpath, 'wb').write(cover)
isCover = True
print 'Processing Dictionary'
dict = Dictionary(dictFile)
print 'Processing Meta Data and creating OPF'
meta_array = getMetaArray(metaFile)
# replace special chars in title and authors like & < >
title = meta_array.get('Title','No Title Provided')
title = title.replace('&','&amp;')
title = title.replace('<','&lt;')
title = title.replace('>','&gt;')
meta_array['Title'] = title
authors = meta_array.get('Authors','No Authors Provided')
authors = authors.replace('&','&amp;')
authors = authors.replace('<','&lt;')
authors = authors.replace('>','&gt;')
meta_array['Authors'] = authors
if buildXML:
xname = os.path.join(xmlDir, 'metadata.xml')
mlst = []
for key in meta_array:
mlst.append('<meta name="' + key + '" content="' + meta_array[key] + '" />\n')
metastr = "".join(mlst)
mlst = None
file(xname, 'wb').write(metastr)
print 'Processing StyleSheet'
# get some scaling info from metadata to use while processing styles
# and first page info
fontsize = '135'
if 'fontSize' in meta_array:
fontsize = meta_array['fontSize']
# also get the size of a normal text page
# get the total number of pages unpacked as a safety check
filenames = os.listdir(pageDir)
numfiles = len(filenames)
spage = '1'
if 'firstTextPage' in meta_array:
spage = meta_array['firstTextPage']
pnum = int(spage)
if pnum >= numfiles or pnum < 0:
# metadata is wrong so just select a page near the front
# 10% of the book to get a normal text page
pnum = int(0.10 * numfiles)
# print "first normal text page is", spage
# get page height and width from first text page for use in stylesheet scaling
pname = 'page%04d.dat' % (pnum + 1)
fname = os.path.join(pageDir,pname)
flat_xml = convert2xml.fromData(dict, fname)
(ph, pw) = getPageDim(flat_xml)
if (ph == '-1') or (ph == '0') : ph = '11000'
if (pw == '-1') or (pw == '0') : pw = '8500'
meta_array['pageHeight'] = ph
meta_array['pageWidth'] = pw
if 'fontSize' not in meta_array.keys():
meta_array['fontSize'] = fontsize
# process other.dat for css info and for map of page files to svg images
# this map is needed because some pages actually are made up of multiple
# pageXXXX.xml files
xname = os.path.join(bookDir, 'style.css')
flat_xml = convert2xml.fromData(dict, otherFile)
# extract info.original.pid to get original page information
pageIDMap = {}
pageidnums = stylexml2css.getpageIDMap(flat_xml)
if len(pageidnums) == 0:
filenames = os.listdir(pageDir)
numfiles = len(filenames)
for k in range(numfiles):
pageidnums.append(k)
# create a map from page ids to list of page file nums to process for that page
for i in range(len(pageidnums)):
id = pageidnums[i]
if id in pageIDMap.keys():
pageIDMap[id].append(i)
else:
pageIDMap[id] = [i]
# now get the css info
cssstr , classlst = stylexml2css.convert2CSS(flat_xml, fontsize, ph, pw)
file(xname, 'wb').write(cssstr)
if buildXML:
xname = os.path.join(xmlDir, 'other0000.xml')
file(xname, 'wb').write(convert2xml.getXML(dict, otherFile))
print 'Processing Glyphs'
gd = GlyphDict()
filenames = os.listdir(glyphsDir)
filenames = sorted(filenames)
glyfname = os.path.join(svgDir,'glyphs.svg')
glyfile = open(glyfname, 'w')
glyfile.write('<?xml version="1.0" standalone="no"?>\n')
glyfile.write('<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n')
glyfile.write('<svg width="512" height="512" viewBox="0 0 511 511" xmlns="http://www.w3.org/2000/svg" version="1.1">\n')
glyfile.write('<title>Glyphs for %s</title>\n' % meta_array['Title'])
glyfile.write('<defs>\n')
counter = 0
for filename in filenames:
# print ' ', filename
print '.',
fname = os.path.join(glyphsDir,filename)
flat_xml = convert2xml.fromData(dict, fname)
if buildXML:
xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
file(xname, 'wb').write(convert2xml.getXML(dict, fname))
gp = GParser(flat_xml)
for i in xrange(0, gp.count):
path = gp.getPath(i)
maxh, maxw = gp.getGlyphDim(i)
fullpath = '<path id="gl%d" d="%s" fill="black" /><!-- width=%d height=%d -->\n' % (counter * 256 + i, path, maxw, maxh)
glyfile.write(fullpath)
gd.addGlyph(counter * 256 + i, fullpath)
counter += 1
glyfile.write('</defs>\n')
glyfile.write('</svg>\n')
glyfile.close()
print " "
# start up the html
# also build up tocentries while processing html
htmlFileName = "book.html"
hlst = []
hlst.append('<?xml version="1.0" encoding="utf-8"?>\n')
hlst.append('<!DOCTYPE HTML PUBLIC "-//W3C//DTD XHTML 1.1 Strict//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11-strict.dtd">\n')
hlst.append('<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en">\n')
hlst.append('<head>\n')
hlst.append('<meta http-equiv="content-type" content="text/html; charset=utf-8"/>\n')
hlst.append('<title>' + meta_array['Title'] + ' by ' + meta_array['Authors'] + '</title>\n')
hlst.append('<meta name="Author" content="' + meta_array['Authors'] + '" />\n')
hlst.append('<meta name="Title" content="' + meta_array['Title'] + '" />\n')
if 'ASIN' in meta_array:
hlst.append('<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n')
if 'GUID' in meta_array:
hlst.append('<meta name="GUID" content="' + meta_array['GUID'] + '" />\n')
hlst.append('<link href="style.css" rel="stylesheet" type="text/css" />\n')
hlst.append('</head>\n<body>\n')
print 'Processing Pages'
# Books are at 1440 DPI. This is rendering at twice that size for
# readability when rendering to the screen.
scaledpi = 1440.0
filenames = os.listdir(pageDir)
filenames = sorted(filenames)
numfiles = len(filenames)
xmllst = []
elst = []
for filename in filenames:
# print ' ', filename
print ".",
fname = os.path.join(pageDir,filename)
flat_xml = convert2xml.fromData(dict, fname)
# keep flat_xml for later svg processing
xmllst.append(flat_xml)
if buildXML:
xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
file(xname, 'wb').write(convert2xml.getXML(dict, fname))
# first get the html
pagehtml, tocinfo = flatxml2html.convert2HTML(flat_xml, classlst, fname, bookDir, gd, fixedimage)
elst.append(tocinfo)
hlst.append(pagehtml)
# finish up the html string and output it
hlst.append('</body>\n</html>\n')
htmlstr = "".join(hlst)
hlst = None
file(os.path.join(bookDir, htmlFileName), 'wb').write(htmlstr)
print " "
print 'Extracting Table of Contents from Amazon OCR'
# first create a table of contents file for the svg images
tlst = []
tlst.append('<?xml version="1.0" encoding="utf-8"?>\n')
tlst.append('<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n')
tlst.append('<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >')
tlst.append('<head>\n')
tlst.append('<title>' + meta_array['Title'] + '</title>\n')
tlst.append('<meta name="Author" content="' + meta_array['Authors'] + '" />\n')
tlst.append('<meta name="Title" content="' + meta_array['Title'] + '" />\n')
if 'ASIN' in meta_array:
tlst.append('<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n')
if 'GUID' in meta_array:
tlst.append('<meta name="GUID" content="' + meta_array['GUID'] + '" />\n')
tlst.append('</head>\n')
tlst.append('<body>\n')
tlst.append('<h2>Table of Contents</h2>\n')
start = pageidnums[0]
if (raw):
startname = 'page%04d.svg' % start
else:
startname = 'page%04d.xhtml' % start
tlst.append('<h3><a href="' + startname + '">Start of Book</a></h3>\n')
# build up a table of contents for the svg xhtml output
tocentries = "".join(elst)
elst = None
toclst = tocentries.split('\n')
toclst.pop()
for entry in toclst:
print entry
title, pagenum = entry.split('|')
id = pageidnums[int(pagenum)]
if (raw):
fname = 'page%04d.svg' % id
else:
fname = 'page%04d.xhtml' % id
tlst.append('<h3><a href="'+ fname + '">' + title + '</a></h3>\n')
tlst.append('</body>\n')
tlst.append('</html>\n')
tochtml = "".join(tlst)
file(os.path.join(svgDir, 'toc.xhtml'), 'wb').write(tochtml)
# now create index_svg.xhtml that points to all required files
slst = []
slst.append('<?xml version="1.0" encoding="utf-8"?>\n')
slst.append('<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n')
slst.append('<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" >')
slst.append('<head>\n')
slst.append('<title>' + meta_array['Title'] + '</title>\n')
slst.append('<meta name="Author" content="' + meta_array['Authors'] + '" />\n')
slst.append('<meta name="Title" content="' + meta_array['Title'] + '" />\n')
if 'ASIN' in meta_array:
slst.append('<meta name="ASIN" content="' + meta_array['ASIN'] + '" />\n')
if 'GUID' in meta_array:
slst.append('<meta name="GUID" content="' + meta_array['GUID'] + '" />\n')
slst.append('</head>\n')
slst.append('<body>\n')
print "Building svg images of each book page"
slst.append('<h2>List of Pages</h2>\n')
slst.append('<div>\n')
idlst = sorted(pageIDMap.keys())
numids = len(idlst)
cnt = len(idlst)
previd = None
for j in range(cnt):
pageid = idlst[j]
if j < cnt - 1:
nextid = idlst[j+1]
else:
nextid = None
print '.',
pagelst = pageIDMap[pageid]
flst = []
for page in pagelst:
flst.append(xmllst[page])
flat_svg = "".join(flst)
flst=None
svgxml = flatxml2svg.convert2SVG(gd, flat_svg, pageid, previd, nextid, svgDir, raw, meta_array, scaledpi)
if (raw) :
pfile = open(os.path.join(svgDir,'page%04d.svg' % pageid),'w')
slst.append('<a href="svg/page%04d.svg">Page %d</a>\n' % (pageid, pageid))
else :
pfile = open(os.path.join(svgDir,'page%04d.xhtml' % pageid), 'w')
slst.append('<a href="svg/page%04d.xhtml">Page %d</a>\n' % (pageid, pageid))
previd = pageid
pfile.write(svgxml)
pfile.close()
counter += 1
slst.append('</div>\n')
slst.append('<h2><a href="svg/toc.xhtml">Table of Contents</a></h2>\n')
slst.append('</body>\n</html>\n')
svgindex = "".join(slst)
slst = None
file(os.path.join(bookDir, 'index_svg.xhtml'), 'wb').write(svgindex)
print " "
# build the opf file
opfname = os.path.join(bookDir, 'book.opf')
olst = []
olst.append('<?xml version="1.0" encoding="utf-8"?>\n')
olst.append('<package xmlns="http://www.idpf.org/2007/opf" unique-identifier="guid_id">\n')
# adding metadata
olst.append(' <metadata xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:opf="http://www.idpf.org/2007/opf">\n')
if 'GUID' in meta_array:
olst.append(' <dc:identifier opf:scheme="GUID" id="guid_id">' + meta_array['GUID'] + '</dc:identifier>\n')
if 'ASIN' in meta_array:
olst.append(' <dc:identifier opf:scheme="ASIN">' + meta_array['ASIN'] + '</dc:identifier>\n')
if 'oASIN' in meta_array:
olst.append(' <dc:identifier opf:scheme="oASIN">' + meta_array['oASIN'] + '</dc:identifier>\n')
olst.append(' <dc:title>' + meta_array['Title'] + '</dc:title>\n')
olst.append(' <dc:creator opf:role="aut">' + meta_array['Authors'] + '</dc:creator>\n')
olst.append(' <dc:language>en</dc:language>\n')
olst.append(' <dc:date>' + meta_array['UpdateTime'] + '</dc:date>\n')
if isCover:
olst.append(' <meta name="cover" content="bookcover"/>\n')
olst.append(' </metadata>\n')
olst.append('<manifest>\n')
olst.append(' <item id="book" href="book.html" media-type="application/xhtml+xml"/>\n')
olst.append(' <item id="stylesheet" href="style.css" media-type="text/css"/>\n')
# adding image files to manifest
filenames = os.listdir(imgDir)
filenames = sorted(filenames)
for filename in filenames:
imgname, imgext = os.path.splitext(filename)
if imgext == '.jpg':
imgext = 'jpeg'
if imgext == '.svg':
imgext = 'svg+xml'
olst.append(' <item id="' + imgname + '" href="img/' + filename + '" media-type="image/' + imgext + '"/>\n')
if isCover:
olst.append(' <item id="bookcover" href="cover.jpg" media-type="image/jpeg" />\n')
olst.append('</manifest>\n')
# adding spine
olst.append('<spine>\n <itemref idref="book" />\n</spine>\n')
if isCover:
olst.append(' <guide>\n')
olst.append(' <reference href="cover.jpg" type="cover" title="Cover"/>\n')
olst.append(' </guide>\n')
olst.append('</package>\n')
opfstr = "".join(olst)
olst = None
file(opfname, 'wb').write(opfstr)
print 'Processing Complete'
return 0
def usage():
print "genbook.py generates a book from the extract Topaz Files"
print "Usage:"
print " genbook.py [-r] [-h [--fixed-image] <bookDir> "
print " "
print "Options:"
print " -h : help - print this usage message"
print " -r : generate raw svg files (not wrapped in xhtml)"
print " --fixed-image : genearate any Fixed Area as an svg image in the html"
print " "
def main(argv):
bookDir = ''
if len(argv) == 0:
argv = sys.argv
try:
opts, args = getopt.getopt(argv[1:], "rh:",["fixed-image"])
except getopt.GetoptError, err:
print str(err)
usage()
return 1
if len(opts) == 0 and len(args) == 0 :
usage()
return 1
raw = 0
fixedimage = True
for o, a in opts:
if o =="-h":
usage()
return 0
if o =="-r":
raw = 1
if o =="--fixed-image":
fixedimage = True
bookDir = args[0]
rv = generateBook(bookDir, raw, fixedimage)
return rv
if __name__ == '__main__':
sys.exit(main(''))

145
Other_Tools/KindleBooks/lib/genxml.py
View File

@@ -1,145 +0,0 @@
#! /usr/bin/python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
# For use with Topaz Scripts Version 2.6
class Unbuffered:
def __init__(self, stream):
self.stream = stream
def write(self, data):
self.stream.write(data)
self.stream.flush()
def __getattr__(self, attr):
return getattr(self.stream, attr)
import sys
sys.stdout=Unbuffered(sys.stdout)
import os, getopt
# local routines
import convert2xml
import flatxml2html
import decode_meta
def usage():
print 'Usage: '
print ' '
print ' genxml.py dict0000.dat unencryptedBookDir'
print ' '
def main(argv):
bookDir = ''
if len(argv) == 0:
argv = sys.argv
try:
opts, args = getopt.getopt(argv[1:], "h:")
except getopt.GetoptError, err:
print str(err)
usage()
sys.exit(1)
if len(opts) == 0 and len(args) == 0 :
usage()
sys.exit(1)
for o, a in opts:
if o =="-h":
usage()
sys.exit(0)
bookDir = args[0]
if not os.path.exists(bookDir) :
print "Can not find directory with unencrypted book"
sys.exit(1)
dictFile = os.path.join(bookDir,'dict0000.dat')
if not os.path.exists(dictFile) :
print "Can not find dict0000.dat file"
sys.exit(1)
pageDir = os.path.join(bookDir,'page')
if not os.path.exists(pageDir) :
print "Can not find page directory in unencrypted book"
sys.exit(1)
glyphsDir = os.path.join(bookDir,'glyphs')
if not os.path.exists(glyphsDir) :
print "Can not find glyphs directory in unencrypted book"
sys.exit(1)
otherFile = os.path.join(bookDir,'other0000.dat')
if not os.path.exists(otherFile) :
print "Can not find other0000.dat in unencrypted book"
sys.exit(1)
metaFile = os.path.join(bookDir,'metadata0000.dat')
if not os.path.exists(metaFile) :
print "Can not find metadata0000.dat in unencrypted book"
sys.exit(1)
xmlDir = os.path.join(bookDir,'xml')
if not os.path.exists(xmlDir):
os.makedirs(xmlDir)
print 'Processing ... '
print ' ', 'metadata0000.dat'
fname = os.path.join(bookDir,'metadata0000.dat')
xname = os.path.join(xmlDir, 'metadata.txt')
metastr = decode_meta.getMetaData(fname)
file(xname, 'wb').write(metastr)
print ' ', 'other0000.dat'
fname = os.path.join(bookDir,'other0000.dat')
xname = os.path.join(xmlDir, 'stylesheet.xml')
pargv=[]
pargv.append('convert2xml.py')
pargv.append(dictFile)
pargv.append(fname)
xmlstr = convert2xml.main(pargv)
file(xname, 'wb').write(xmlstr)
filenames = os.listdir(pageDir)
filenames = sorted(filenames)
for filename in filenames:
print ' ', filename
fname = os.path.join(pageDir,filename)
xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
pargv=[]
pargv.append('convert2xml.py')
pargv.append(dictFile)
pargv.append(fname)
xmlstr = convert2xml.main(pargv)
file(xname, 'wb').write(xmlstr)
filenames = os.listdir(glyphsDir)
filenames = sorted(filenames)
for filename in filenames:
print ' ', filename
fname = os.path.join(glyphsDir,filename)
xname = os.path.join(xmlDir, filename.replace('.dat','.xml'))
pargv=[]
pargv.append('convert2xml.py')
pargv.append(dictFile)
pargv.append(fname)
xmlstr = convert2xml.main(pargv)
file(xname, 'wb').write(xmlstr)
print 'Processing Complete'
return 0
if __name__ == '__main__':
sys.exit(main(''))

78
Other_Tools/KindleBooks/lib/getk4pcpids.py
View File

@@ -1,78 +0,0 @@
#!/usr/bin/python
#
# This is a python script. You need a Python interpreter to run it.
# For example, ActiveState Python, which exists for windows.
#
# Changelog
# 1.00 - Initial version
# 1.01 - getPidList interface change
__version__ = '1.01'
import sys
class Unbuffered:
def __init__(self, stream):
self.stream = stream
def write(self, data):
self.stream.write(data)
self.stream.flush()
def __getattr__(self, attr):
return getattr(self.stream, attr)
sys.stdout=Unbuffered(sys.stdout)
import os
import struct
import binascii
import kgenpids
import topazextract
import mobidedrm
from alfcrypto import Pukall_Cipher
class DrmException(Exception):
pass
def getK4PCpids(path_to_ebook):
# Return Kindle4PC PIDs. Assumes that the caller checked that we are not on Linux, which will raise an exception
mobi = True
magic3 = file(path_to_ebook,'rb').read(3)
if magic3 == 'TPZ':
mobi = False
if mobi:
mb = mobidedrm.MobiBook(path_to_ebook,False)
else:
mb = topazextract.TopazBook(path_to_ebook)
md1, md2 = mb.getPIDMetaInfo()
return kgenpids.getPidList(md1, md2)
def main(argv=sys.argv):
print ('getk4pcpids.py v%(__version__)s. '
'Copyright 2012 Apprentice Alf' % globals())
if len(argv)<2 or len(argv)>3:
print "Gets the possible book-specific PIDs from K4PC for a particular book"
print "Usage:"
print " %s <bookfile> [<outfile>]" % sys.argv[0]
return 1
else:
infile = argv[1]
try:
pidlist = getK4PCpids(infile)
except DrmException, e:
print "Error: %s" % e
return 1
pidstring = ','.join(pidlist)
print "Possible PIDs are: ", pidstring
if len(argv) is 3:
outfile = argv[2]
file(outfile, 'w').write(pidstring)
return 0
if __name__ == "__main__":
sys.exit(main())

333
Other_Tools/KindleBooks/lib/k4mdumpkinfo.py
View File

@@ -1,333 +0,0 @@
# engine to remove drm from Kindle for Mac books
# for personal use for archiving and converting your ebooks
# PLEASE DO NOT PIRATE!
# We want all authors and Publishers, and eBook stores to live long and prosperous lives
#
# it borrows heavily from works by CMBDTC, IHeartCabbages, skindle,
# unswindle, DiapDealer, some_updates and many many others
from __future__ import with_statement
class Unbuffered:
def __init__(self, stream):
self.stream = stream
def write(self, data):
self.stream.write(data)
self.stream.flush()
def __getattr__(self, attr):
return getattr(self.stream, attr)
import sys
sys.stdout=Unbuffered(sys.stdout)
import os, csv, getopt
from struct import pack
from struct import unpack
import zlib
# for handling sub processes
import subprocess
from subprocess import Popen, PIPE, STDOUT
import subasyncio
from subasyncio import Process
#Exception Handling
class K4MDEDRMError(Exception):
pass
class K4MDEDRMFatal(Exception):
pass
#
# crypto routines
#
import hashlib
def MD5(message):
ctx = hashlib.md5()
ctx.update(message)
return ctx.digest()
def SHA1(message):
ctx = hashlib.sha1()
ctx.update(message)
return ctx.digest()
def SHA256(message):
ctx = hashlib.sha256()
ctx.update(message)
return ctx.digest()
# interface to needed routines in openssl's libcrypto
def _load_crypto_libcrypto():
from ctypes import CDLL, byref, POINTER, c_void_p, c_char_p, c_int, c_long, \
Structure, c_ulong, create_string_buffer, addressof, string_at, cast
from ctypes.util import find_library
libcrypto = find_library('crypto')
if libcrypto is None:
raise K4MDEDRMError('libcrypto not found')
libcrypto = CDLL(libcrypto)
AES_MAXNR = 14
c_char_pp = POINTER(c_char_p)
c_int_p = POINTER(c_int)
class AES_KEY(Structure):
_fields_ = [('rd_key', c_long * (4 * (AES_MAXNR + 1))), ('rounds', c_int)]
AES_KEY_p = POINTER(AES_KEY)
def F(restype, name, argtypes):
func = getattr(libcrypto, name)
func.restype = restype
func.argtypes = argtypes
return func
AES_cbc_encrypt = F(None, 'AES_cbc_encrypt',[c_char_p, c_char_p, c_ulong, AES_KEY_p, c_char_p,c_int])
AES_set_decrypt_key = F(c_int, 'AES_set_decrypt_key',[c_char_p, c_int, AES_KEY_p])
PKCS5_PBKDF2_HMAC_SHA1 = F(c_int, 'PKCS5_PBKDF2_HMAC_SHA1',
[c_char_p, c_ulong, c_char_p, c_ulong, c_ulong, c_ulong, c_char_p])
class LibCrypto(object):
def __init__(self):
self._blocksize = 0
self._keyctx = None
self.iv = 0
def set_decrypt_key(self, userkey, iv):
self._blocksize = len(userkey)
if (self._blocksize != 16) and (self._blocksize != 24) and (self._blocksize != 32) :
raise K4MDEDRMError('AES improper key used')
return
keyctx = self._keyctx = AES_KEY()
self.iv = iv
rv = AES_set_decrypt_key(userkey, len(userkey) * 8, keyctx)
if rv < 0:
raise K4MDEDRMError('Failed to initialize AES key')
def decrypt(self, data):
out = create_string_buffer(len(data))
rv = AES_cbc_encrypt(data, out, len(data), self._keyctx, self.iv, 0)
if rv == 0:
raise K4MDEDRMError('AES decryption failed')
return out.raw
def keyivgen(self, passwd):
salt = '16743'
saltlen = 5
passlen = len(passwd)
iter = 0x3e8
keylen = 80
out = create_string_buffer(keylen)
rv = PKCS5_PBKDF2_HMAC_SHA1(passwd, passlen, salt, saltlen, iter, keylen, out)
return out.raw
return LibCrypto
def _load_crypto():
LibCrypto = None
try:
LibCrypto = _load_crypto_libcrypto()
except (ImportError, K4MDEDRMError):
pass
return LibCrypto
LibCrypto = _load_crypto()
#
# Utility Routines
#
# uses a sub process to get the Hard Drive Serial Number using ioreg
# returns with the first found serial number in that class
def GetVolumeSerialNumber():
sernum = os.getenv('MYSERIALNUMBER')
if sernum != None:
return sernum
cmdline = '/usr/sbin/ioreg -l -S -w 0 -r -c AppleAHCIDiskDriver'
cmdline = cmdline.encode(sys.getfilesystemencoding())
p = Process(cmdline, shell=True, bufsize=1, stdin=None, stdout=PIPE, stderr=PIPE, close_fds=False)
poll = p.wait('wait')
results = p.read()
reslst = results.split('\n')
cnt = len(reslst)
bsdname = None
sernum = None
foundIt = False
for j in xrange(cnt):
resline = reslst[j]
pp = resline.find('"Serial Number" = "')
if pp >= 0:
sernum = resline[pp+19:-1]
sernum = sernum.strip()
bb = resline.find('"BSD Name" = "')
if bb >= 0:
bsdname = resline[bb+14:-1]
bsdname = bsdname.strip()
if (bsdname == 'disk0') and (sernum != None):
foundIt = True
break
if not foundIt:
sernum = '9999999999'
return sernum
# uses unix env to get username instead of using sysctlbyname
def GetUserName():
username = os.getenv('USER')
return username
MAX_PATH = 255
#
# start of Kindle specific routines
#
global kindleDatabase
# Various character maps used to decrypt books. Probably supposed to act as obfuscation
charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
charMap2 = "ZB0bYyc1xDdW2wEV3Ff7KkPpL8UuGA4gz-Tme9Nn_tHh5SvXCsIiR6rJjQaqlOoM"
charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
charMap4 = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
# Encode the bytes in data with the characters in map
def encode(data, map):
result = ""
for char in data:
value = ord(char)
Q = (value ^ 0x80) // len(map)
R = value % len(map)
result += map[Q]
result += map[R]
return result
# Hash the bytes in data and then encode the digest with the characters in map
def encodeHash(data,map):
return encode(MD5(data),map)
# Decode the string in data with the characters in map. Returns the decoded bytes
def decode(data,map):
result = ""
for i in range (0,len(data)-1,2):
high = map.find(data[i])
low = map.find(data[i+1])
if (high == -1) or (low == -1) :
break
value = (((high * len(map)) ^ 0x80) & 0xFF) + low
result += pack("B",value)
return result
# implements an Pseudo Mac Version of Windows built-in Crypto routine
def CryptUnprotectData(encryptedData):
sp = GetVolumeSerialNumber() + '!@#' + GetUserName()
passwdData = encode(SHA256(sp),charMap1)
crp = LibCrypto()
key_iv = crp.keyivgen(passwdData)
key = key_iv[0:32]
iv = key_iv[32:48]
crp.set_decrypt_key(key,iv)
cleartext = crp.decrypt(encryptedData)
return cleartext
# Locate and open the .kindle-info file
def openKindleInfo():
home = os.getenv('HOME')
kinfopath = home + '/Library/Application Support/Amazon/Kindle/storage/.kindle-info'
if not os.path.exists(kinfopath):
kinfopath = home + '/Library/Application Support/Amazon/Kindle for Mac/storage/.kindle-info'
if not os.path.exists(kinfopath):
raise K4MDEDRMError('Error: .kindle-info file can not be found')
return open(kinfopath,'r')
# Parse the Kindle.info file and return the records as a list of key-values
def parseKindleInfo():
DB = {}
infoReader = openKindleInfo()
infoReader.read(1)
data = infoReader.read()
items = data.split('[')
for item in items:
splito = item.split(':')
DB[splito[0]] =splito[1]
return DB
# Get a record from the Kindle.info file for the key "hashedKey" (already hashed and encoded). Return the decoded and decrypted record
def getKindleInfoValueForHash(hashedKey):
global kindleDatabase
encryptedValue = decode(kindleDatabase[hashedKey],charMap2)
cleartext = CryptUnprotectData(encryptedValue)
return decode(cleartext, charMap1)
# Get a record from the Kindle.info file for the string in "key" (plaintext). Return the decoded and decrypted record
def getKindleInfoValueForKey(key):
return getKindleInfoValueForHash(encodeHash(key,charMap2))
# Find if the original string for a hashed/encoded string is known. If so return the original string othwise return an empty string.
def findNameForHash(hash):
names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber"]
result = ""
for name in names:
if hash == encodeHash(name, charMap2):
result = name
break
return result
# Print all the records from the kindle.info file (option -i)
def printKindleInfo():
for record in kindleDatabase:
name = findNameForHash(record)
if name != "" :
print (name)
print ("--------------------------")
else :
print ("Unknown Record")
print getKindleInfoValueForHash(record)
print "\n"
#
# PID generation routines
#
# Returns two bit at offset from a bit field
def getTwoBitsFromBitField(bitField,offset):
byteNumber = offset // 4
bitPosition = 6 - 2*(offset % 4)
return ord(bitField[byteNumber]) >> bitPosition & 3
# Returns the six bits at offset from a bit field
def getSixBitsFromBitField(bitField,offset):
offset *= 3
value = (getTwoBitsFromBitField(bitField,offset) <<4) + (getTwoBitsFromBitField(bitField,offset+1) << 2) +getTwoBitsFromBitField(bitField,offset+2)
return value
# 8 bits to six bits encoding from hash to generate PID string
def encodePID(hash):
global charMap3
PID = ""
for position in range (0,8):
PID += charMap3[getSixBitsFromBitField(hash,position)]
return PID
#
# Main
#
def main(argv=sys.argv):
global kindleDatabase
kindleDatabase = None
#
# Read the encrypted database
#
try:
kindleDatabase = parseKindleInfo()
except Exception, message:
print(message)
if kindleDatabase != None :
printKindleInfo()
return 0
if __name__ == '__main__':
sys.exit(main())

238
Other_Tools/KindleBooks/lib/k4mobidedrm.py
View File

@@ -1,238 +0,0 @@
#!/usr/bin/env python
from __future__ import with_statement
# engine to remove drm from Kindle for Mac and Kindle for PC books
# for personal use for archiving and converting your ebooks
# PLEASE DO NOT PIRATE EBOOKS!
# We want all authors and publishers, and eBook stores to live
# long and prosperous lives but at the same time we just want to
# be able to read OUR books on whatever device we want and to keep
# readable for a long, long time
# This borrows very heavily from works by CMBDTC, IHeartCabbages, skindle,
# unswindle, DarkReverser, ApprenticeAlf, DiapDealer, some_updates
# and many many others
__version__ = '4.4'
class Unbuffered:
def __init__(self, stream):
self.stream = stream
def write(self, data):
self.stream.write(data)
self.stream.flush()
def __getattr__(self, attr):
return getattr(self.stream, attr)
import sys
import os, csv, getopt
import string
import re
import traceback
import time
buildXML = False
class DrmException(Exception):
pass
if 'calibre' in sys.modules:
inCalibre = True
else:
inCalibre = False
if inCalibre:
from calibre_plugins.k4mobidedrm import mobidedrm
from calibre_plugins.k4mobidedrm import topazextract
from calibre_plugins.k4mobidedrm import kgenpids
else:
import mobidedrm
import topazextract
import kgenpids
# cleanup bytestring filenames
# borrowed from calibre from calibre/src/calibre/__init__.py
# added in removal of non-printing chars
# and removal of . at start
# convert underscores to spaces (we're OK with spaces in file names)
def cleanup_name(name):
_filename_sanitize = re.compile(r'[\xae\0\\|\?\*<":>\+/]')
substitute='_'
one = ''.join(char for char in name if char in string.printable)
one = _filename_sanitize.sub(substitute, one)
one = re.sub(r'\s', ' ', one).strip()
one = re.sub(r'^\.+$', '_', one)
one = one.replace('..', substitute)
# Windows doesn't like path components that end with a period
if one.endswith('.'):
one = one[:-1]+substitute
# Mac and Unix don't like file names that begin with a full stop
if len(one) > 0 and one[0] == '.':
one = substitute+one[1:]
one = one.replace('_',' ')
return one
def decryptBook(infile, outdir, k4, kInfoFiles, serials, pids):
global buildXML
# handle the obvious cases at the beginning
if not os.path.isfile(infile):
print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: Input file does not exist"
return 1
starttime = time.time()
print "Starting decryptBook routine."
mobi = True
magic3 = file(infile,'rb').read(3)
if magic3 == 'TPZ':
mobi = False
bookname = os.path.splitext(os.path.basename(infile))[0]
if mobi:
mb = mobidedrm.MobiBook(infile)
else:
mb = topazextract.TopazBook(infile)
title = mb.getBookTitle()
print "Processing Book: ", title
filenametitle = cleanup_name(title)
outfilename = cleanup_name(bookname)
# generate 'sensible' filename, that will sort with the original name,
# but is close to the name from the file.
outlength = len(outfilename)
comparelength = min(8,min(outlength,len(filenametitle)))
copylength = min(max(outfilename.find(' '),8),len(outfilename))
if outlength==0:
outfilename = filenametitle
elif comparelength > 0:
if outfilename[:comparelength] == filenametitle[:comparelength]:
outfilename = filenametitle
else:
outfilename = outfilename[:copylength] + " " + filenametitle
# avoid excessively long file names
if len(outfilename)>150:
outfilename = outfilename[:150]
# build pid list
md1, md2 = mb.getPIDMetaInfo()
pids.extend(kgenpids.getPidList(md1, md2, k4, serials, kInfoFiles))
print "Found {1:d} keys to try after {0:.1f} seconds".format(time.time()-starttime, len(pids))
try:
mb.processBook(pids)
except mobidedrm.DrmException, e:
print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
print "Failed to decrypted book after {0:.1f} seconds".format(time.time()-starttime)
return 1
except topazextract.TpzDRMError, e:
print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
print "Failed to decrypted book after {0:.1f} seconds".format(time.time()-starttime)
return 1
except Exception, e:
print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
print "Failed to decrypted book after {0:.1f} seconds".format(time.time()-starttime)
return 1
print "Successfully decrypted book after {0:.1f} seconds".format(time.time()-starttime)
if mobi:
if mb.getPrintReplica():
outfile = os.path.join(outdir, outfilename + '_nodrm' + '.azw4')
elif mb.getMobiVersion() >= 8:
outfile = os.path.join(outdir, outfilename + '_nodrm' + '.azw3')
else:
outfile = os.path.join(outdir, outfilename + '_nodrm' + '.mobi')
mb.getMobiFile(outfile)
print "Saved decrypted book {1:s} after {0:.1f} seconds".format(time.time()-starttime, outfilename + '_nodrm')
return 0
# topaz:
print " Creating NoDRM HTMLZ Archive"
zipname = os.path.join(outdir, outfilename + '_nodrm' + '.htmlz')
mb.getHTMLZip(zipname)
print " Creating SVG ZIP Archive"
zipname = os.path.join(outdir, outfilename + '_SVG' + '.zip')
mb.getSVGZip(zipname)
if buildXML:
print " Creating XML ZIP Archive"
zipname = os.path.join(outdir, outfilename + '_XML' + '.zip')
mb.getXMLZip(zipname)
# remove internal temporary directory of Topaz pieces
mb.cleanup()
print "Saved decrypted Topaz book parts after {0:.1f} seconds".format(time.time()-starttime)
return 0
def usage(progname):
print "Removes DRM protection from K4PC/M, Kindle, Mobi and Topaz ebooks"
print "Usage:"
print " %s [-k <kindle.info>] [-p <pidnums>] [-s <kindleSerialNumbers>] <infile> <outdir> " % progname
#
# Main
#
def main(argv=sys.argv):
progname = os.path.basename(argv[0])
k4 = False
kInfoFiles = []
serials = []
pids = []
print ('K4MobiDeDrm v%(__version__)s '
'provided by the work of many including DiapDealer, SomeUpdates, IHeartCabbages, CMBDTC, Skindle, DarkReverser, ApprenticeAlf, etc .' % globals())
try:
opts, args = getopt.getopt(sys.argv[1:], "k:p:s:")
except getopt.GetoptError, err:
print str(err)
usage(progname)
sys.exit(2)
if len(args)<2:
usage(progname)
sys.exit(2)
for o, a in opts:
if o == "-k":
if a == None :
raise DrmException("Invalid parameter for -k")
kInfoFiles.append(a)
if o == "-p":
if a == None :
raise DrmException("Invalid parameter for -p")
pids = a.split(',')
if o == "-s":
if a == None :
raise DrmException("Invalid parameter for -s")
serials = a.split(',')
# try with built in Kindle Info files
k4 = True
if sys.platform.startswith('linux'):
k4 = False
kInfoFiles = None
infile = args[0]
outdir = args[1]
return decryptBook(infile, outdir, k4, kInfoFiles, serials, pids)
if __name__ == '__main__':
sys.stdout=Unbuffered(sys.stdout)
sys.exit(main())

730
Other_Tools/KindleBooks/lib/k4mutils.py
View File

@@ -1,730 +0,0 @@
# standlone set of Mac OSX specific routines needed for KindleBooks
from __future__ import with_statement
import sys
import os
import os.path
import re
import copy
import subprocess
from struct import pack, unpack, unpack_from
class DrmException(Exception):
pass
# interface to needed routines in openssl's libcrypto
def _load_crypto_libcrypto():
from ctypes import CDLL, byref, POINTER, c_void_p, c_char_p, c_int, c_long, \
Structure, c_ulong, create_string_buffer, addressof, string_at, cast
from ctypes.util import find_library
libcrypto = find_library('crypto')
if libcrypto is None:
raise DrmException('libcrypto not found')
libcrypto = CDLL(libcrypto)
# From OpenSSL's crypto aes header
#
# AES_ENCRYPT 1
# AES_DECRYPT 0
# AES_MAXNR 14 (in bytes)
# AES_BLOCK_SIZE 16 (in bytes)
#
# struct aes_key_st {
# unsigned long rd_key[4 *(AES_MAXNR + 1)];
# int rounds;
# };
# typedef struct aes_key_st AES_KEY;
#
# int AES_set_decrypt_key(const unsigned char *userKey, const int bits, AES_KEY *key);
#
# note: the ivec string, and output buffer are both mutable
# void AES_cbc_encrypt(const unsigned char *in, unsigned char *out,
# const unsigned long length, const AES_KEY *key, unsigned char *ivec, const int enc);
AES_MAXNR = 14
c_char_pp = POINTER(c_char_p)
c_int_p = POINTER(c_int)
class AES_KEY(Structure):
_fields_ = [('rd_key', c_long * (4 * (AES_MAXNR + 1))), ('rounds', c_int)]
AES_KEY_p = POINTER(AES_KEY)
def F(restype, name, argtypes):
func = getattr(libcrypto, name)
func.restype = restype
func.argtypes = argtypes
return func
AES_cbc_encrypt = F(None, 'AES_cbc_encrypt',[c_char_p, c_char_p, c_ulong, AES_KEY_p, c_char_p,c_int])
AES_set_decrypt_key = F(c_int, 'AES_set_decrypt_key',[c_char_p, c_int, AES_KEY_p])
# From OpenSSL's Crypto evp/p5_crpt2.c
#
# int PKCS5_PBKDF2_HMAC_SHA1(const char *pass, int passlen,
# const unsigned char *salt, int saltlen, int iter,
# int keylen, unsigned char *out);
PKCS5_PBKDF2_HMAC_SHA1 = F(c_int, 'PKCS5_PBKDF2_HMAC_SHA1',
[c_char_p, c_ulong, c_char_p, c_ulong, c_ulong, c_ulong, c_char_p])
class LibCrypto(object):
def __init__(self):
self._blocksize = 0
self._keyctx = None
self._iv = 0
def set_decrypt_key(self, userkey, iv):
self._blocksize = len(userkey)
if (self._blocksize != 16) and (self._blocksize != 24) and (self._blocksize != 32) :
raise DrmException('AES improper key used')
return
keyctx = self._keyctx = AES_KEY()
self._iv = iv
self._userkey = userkey
rv = AES_set_decrypt_key(userkey, len(userkey) * 8, keyctx)
if rv < 0:
raise DrmException('Failed to initialize AES key')
def decrypt(self, data):
out = create_string_buffer(len(data))
mutable_iv = create_string_buffer(self._iv, len(self._iv))
keyctx = self._keyctx
rv = AES_cbc_encrypt(data, out, len(data), keyctx, mutable_iv, 0)
if rv == 0:
raise DrmException('AES decryption failed')
return out.raw
def keyivgen(self, passwd, salt, iter, keylen):
saltlen = len(salt)
passlen = len(passwd)
out = create_string_buffer(keylen)
rv = PKCS5_PBKDF2_HMAC_SHA1(passwd, passlen, salt, saltlen, iter, keylen, out)
return out.raw
return LibCrypto
def _load_crypto():
LibCrypto = None
try:
LibCrypto = _load_crypto_libcrypto()
except (ImportError, DrmException):
pass
return LibCrypto
LibCrypto = _load_crypto()
#
# Utility Routines
#
# crypto digestroutines
import hashlib
def MD5(message):
ctx = hashlib.md5()
ctx.update(message)
return ctx.digest()
def SHA1(message):
ctx = hashlib.sha1()
ctx.update(message)
return ctx.digest()
def SHA256(message):
ctx = hashlib.sha256()
ctx.update(message)
return ctx.digest()
# Various character maps used to decrypt books. Probably supposed to act as obfuscation
charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
charMap2 = "ZB0bYyc1xDdW2wEV3Ff7KkPpL8UuGA4gz-Tme9Nn_tHh5SvXCsIiR6rJjQaqlOoM"
# For kinf approach of K4Mac 1.6.X or later
# On K4PC charMap5 = "AzB0bYyCeVvaZ3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_c1XxDdW2wE"
# For Mac they seem to re-use charMap2 here
charMap5 = charMap2
# new in K4M 1.9.X
testMap8 = "YvaZ3FfUm9Nn_c1XuG4yCAzB0beVg-TtHh5SsIiR6rJjQdW2wEq7KkPpL8lOoMxD"
def encode(data, map):
result = ""
for char in data:
value = ord(char)
Q = (value ^ 0x80) // len(map)
R = value % len(map)
result += map[Q]
result += map[R]
return result
# Hash the bytes in data and then encode the digest with the characters in map
def encodeHash(data,map):
return encode(MD5(data),map)
# Decode the string in data with the characters in map. Returns the decoded bytes
def decode(data,map):
result = ""
for i in range (0,len(data)-1,2):
high = map.find(data[i])
low = map.find(data[i+1])
if (high == -1) or (low == -1) :
break
value = (((high * len(map)) ^ 0x80) & 0xFF) + low
result += pack("B",value)
return result
# For K4M 1.6.X and later
# generate table of prime number less than or equal to int n
def primes(n):
if n==2: return [2]
elif n<2: return []
s=range(3,n+1,2)
mroot = n ** 0.5
half=(n+1)/2-1
i=0
m=3
while m <= mroot:
if s[i]:
j=(m*m-3)/2
s[j]=0
while j<half:
s[j]=0
j+=m
i=i+1
m=2*i+3
return [2]+[x for x in s if x]
# uses a sub process to get the Hard Drive Serial Number using ioreg
# returns with the serial number of drive whose BSD Name is "disk0"
def GetVolumeSerialNumber():
sernum = os.getenv('MYSERIALNUMBER')
if sernum != None:
return sernum
cmdline = '/usr/sbin/ioreg -l -S -w 0 -r -c AppleAHCIDiskDriver'
cmdline = cmdline.encode(sys.getfilesystemencoding())
p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
out1, out2 = p.communicate()
reslst = out1.split('\n')
cnt = len(reslst)
bsdname = None
sernum = None
foundIt = False
for j in xrange(cnt):
resline = reslst[j]
pp = resline.find('"Serial Number" = "')
if pp >= 0:
sernum = resline[pp+19:-1]
sernum = sernum.strip()
bb = resline.find('"BSD Name" = "')
if bb >= 0:
bsdname = resline[bb+14:-1]
bsdname = bsdname.strip()
if (bsdname == 'disk0') and (sernum != None):
foundIt = True
break
if not foundIt:
sernum = ''
return sernum
def GetUserHomeAppSupKindleDirParitionName():
home = os.getenv('HOME')
dpath = home + '/Library'
cmdline = '/sbin/mount'
cmdline = cmdline.encode(sys.getfilesystemencoding())
p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
out1, out2 = p.communicate()
reslst = out1.split('\n')
cnt = len(reslst)
disk = ''
foundIt = False
for j in xrange(cnt):
resline = reslst[j]
if resline.startswith('/dev'):
(devpart, mpath) = resline.split(' on ')
dpart = devpart[5:]
pp = mpath.find('(')
if pp >= 0:
mpath = mpath[:pp-1]
if dpath.startswith(mpath):
disk = dpart
return disk
# uses a sub process to get the UUID of the specified disk partition using ioreg
def GetDiskPartitionUUID(diskpart):
uuidnum = os.getenv('MYUUIDNUMBER')
if uuidnum != None:
return uuidnum
cmdline = '/usr/sbin/ioreg -l -S -w 0 -r -c AppleAHCIDiskDriver'
cmdline = cmdline.encode(sys.getfilesystemencoding())
p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
out1, out2 = p.communicate()
reslst = out1.split('\n')
cnt = len(reslst)
bsdname = None
uuidnum = None
foundIt = False
nest = 0
uuidnest = -1
partnest = -2
for j in xrange(cnt):
resline = reslst[j]
if resline.find('{') >= 0:
nest += 1
if resline.find('}') >= 0:
nest -= 1
pp = resline.find('"UUID" = "')
if pp >= 0:
uuidnum = resline[pp+10:-1]
uuidnum = uuidnum.strip()
uuidnest = nest
if partnest == uuidnest and uuidnest > 0:
foundIt = True
break
bb = resline.find('"BSD Name" = "')
if bb >= 0:
bsdname = resline[bb+14:-1]
bsdname = bsdname.strip()
if (bsdname == diskpart):
partnest = nest
else :
partnest = -2
if partnest == uuidnest and partnest > 0:
foundIt = True
break
if nest == 0:
partnest = -2
uuidnest = -1
uuidnum = None
bsdname = None
if not foundIt:
uuidnum = ''
return uuidnum
def GetMACAddressMunged():
macnum = os.getenv('MYMACNUM')
if macnum != None:
return macnum
cmdline = '/sbin/ifconfig en0'
cmdline = cmdline.encode(sys.getfilesystemencoding())
p = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
out1, out2 = p.communicate()
reslst = out1.split('\n')
cnt = len(reslst)
macnum = None
foundIt = False
for j in xrange(cnt):
resline = reslst[j]
pp = resline.find('ether ')
if pp >= 0:
macnum = resline[pp+6:-1]
macnum = macnum.strip()
# print "original mac", macnum
# now munge it up the way Kindle app does
# by xoring it with 0xa5 and swapping elements 3 and 4
maclst = macnum.split(':')
n = len(maclst)
if n != 6:
fountIt = False
break
for i in range(6):
maclst[i] = int('0x' + maclst[i], 0)
mlst = [0x00, 0x00, 0x00, 0x00, 0x00, 0x00]
mlst[5] = maclst[5] ^ 0xa5
mlst[4] = maclst[3] ^ 0xa5
mlst[3] = maclst[4] ^ 0xa5
mlst[2] = maclst[2] ^ 0xa5
mlst[1] = maclst[1] ^ 0xa5
mlst[0] = maclst[0] ^ 0xa5
macnum = "%0.2x%0.2x%0.2x%0.2x%0.2x%0.2x" % (mlst[0], mlst[1], mlst[2], mlst[3], mlst[4], mlst[5])
foundIt = True
break
if not foundIt:
macnum = ''
return macnum
# uses unix env to get username instead of using sysctlbyname
def GetUserName():
username = os.getenv('USER')
return username
def isNewInstall():
home = os.getenv('HOME')
# soccer game fan anyone
dpath = home + '/Library/Application Support/Kindle/storage/.pes2011'
# print dpath, os.path.exists(dpath)
if os.path.exists(dpath):
return True
dpath = home + '/Library/Containers/com.amazon.Kindle/Data/Library/Application Support/Kindle/storage/.pes2011'
# print dpath, os.path.exists(dpath)
if os.path.exists(dpath):
return True
return False
def GetIDString():
# K4Mac now has an extensive set of ids strings it uses
# in encoding pids and in creating unique passwords
# for use in its own version of CryptUnprotectDataV2
# BUT Amazon has now become nasty enough to detect when its app
# is being run under a debugger and actually changes code paths
# including which one of these strings is chosen, all to try
# to prevent reverse engineering
# Sad really ... they will only hurt their own sales ...
# true book lovers really want to keep their books forever
# and move them to their devices and DRM prevents that so they
# will just buy from someplace else that they can remove
# the DRM from
# Amazon should know by now that true book lover's are not like
# penniless kids that pirate music, we do not pirate books
if isNewInstall():
mungedmac = GetMACAddressMunged()
if len(mungedmac) > 7:
print('Using Munged MAC Address for ID: '+mungedmac)
return mungedmac
sernum = GetVolumeSerialNumber()
if len(sernum) > 7:
print('Using Volume Serial Number for ID: '+sernum)
return sernum
diskpart = GetUserHomeAppSupKindleDirParitionName()
uuidnum = GetDiskPartitionUUID(diskpart)
if len(uuidnum) > 7:
print('Using Disk Partition UUID for ID: '+uuidnum)
return uuidnum
mungedmac = GetMACAddressMunged()
if len(mungedmac) > 7:
print('Using Munged MAC Address for ID: '+mungedmac)
return mungedmac
print('Using Fixed constant 9999999999 for ID.')
return '9999999999'
# implements an Pseudo Mac Version of Windows built-in Crypto routine
# used by Kindle for Mac versions < 1.6.0
class CryptUnprotectData(object):
def __init__(self):
sernum = GetVolumeSerialNumber()
if sernum == '':
sernum = '9999999999'
sp = sernum + '!@#' + GetUserName()
passwdData = encode(SHA256(sp),charMap1)
salt = '16743'
self.crp = LibCrypto()
iter = 0x3e8
keylen = 0x80
key_iv = self.crp.keyivgen(passwdData, salt, iter, keylen)
self.key = key_iv[0:32]
self.iv = key_iv[32:48]
self.crp.set_decrypt_key(self.key, self.iv)
def decrypt(self, encryptedData):
cleartext = self.crp.decrypt(encryptedData)
cleartext = decode(cleartext,charMap1)
return cleartext
# implements an Pseudo Mac Version of Windows built-in Crypto routine
# used for Kindle for Mac Versions >= 1.6.0
class CryptUnprotectDataV2(object):
def __init__(self):
sp = GetUserName() + ':&%:' + GetIDString()
passwdData = encode(SHA256(sp),charMap5)
# salt generation as per the code
salt = 0x0512981d * 2 * 1 * 1
salt = str(salt) + GetUserName()
salt = encode(salt,charMap5)
self.crp = LibCrypto()
iter = 0x800
keylen = 0x400
key_iv = self.crp.keyivgen(passwdData, salt, iter, keylen)
self.key = key_iv[0:32]
self.iv = key_iv[32:48]
self.crp.set_decrypt_key(self.key, self.iv)
def decrypt(self, encryptedData):
cleartext = self.crp.decrypt(encryptedData)
cleartext = decode(cleartext, charMap5)
return cleartext
# unprotect the new header blob in .kinf2011
# used in Kindle for Mac Version >= 1.9.0
def UnprotectHeaderData(encryptedData):
passwdData = 'header_key_data'
salt = 'HEADER.2011'
iter = 0x80
keylen = 0x100
crp = LibCrypto()
key_iv = crp.keyivgen(passwdData, salt, iter, keylen)
key = key_iv[0:32]
iv = key_iv[32:48]
crp.set_decrypt_key(key,iv)
cleartext = crp.decrypt(encryptedData)
return cleartext
# implements an Pseudo Mac Version of Windows built-in Crypto routine
# used for Kindle for Mac Versions >= 1.9.0
class CryptUnprotectDataV3(object):
def __init__(self, entropy):
sp = GetUserName() + '+@#$%+' + GetIDString()
passwdData = encode(SHA256(sp),charMap2)
salt = entropy
self.crp = LibCrypto()
iter = 0x800
keylen = 0x400
key_iv = self.crp.keyivgen(passwdData, salt, iter, keylen)
self.key = key_iv[0:32]
self.iv = key_iv[32:48]
self.crp.set_decrypt_key(self.key, self.iv)
def decrypt(self, encryptedData):
cleartext = self.crp.decrypt(encryptedData)
cleartext = decode(cleartext, charMap2)
return cleartext
# Locate the .kindle-info files
def getKindleInfoFiles():
# file searches can take a long time on some systems, so just look in known specific places.
kInfoFiles=[]
found = False
home = os.getenv('HOME')
# check for .kinf2011 file in new location (App Store Kindle for Mac)
testpath = home + '/Library/Containers/com.amazon.Kindle/Data/Library/Application Support/Kindle/storage/.kinf2011'
if os.path.isfile(testpath):
kInfoFiles.append(testpath)
print('Found k4Mac kinf2011 file: ' + testpath)
found = True
# check for .kinf2011 files
testpath = home + '/Library/Application Support/Kindle/storage/.kinf2011'
if os.path.isfile(testpath):
kInfoFiles.append(testpath)
print('Found k4Mac kinf2011 file: ' + testpath)
found = True
# check for .rainier-2.1.1-kinf files
testpath = home + '/Library/Application Support/Kindle/storage/.rainier-2.1.1-kinf'
if os.path.isfile(testpath):
kInfoFiles.append(testpath)
print('Found k4Mac rainier file: ' + testpath)
found = True
# check for .rainier-2.1.1-kinf files
testpath = home + '/Library/Application Support/Kindle/storage/.kindle-info'
if os.path.isfile(testpath):
kInfoFiles.append(testpath)
print('Found k4Mac kindle-info file: ' + testpath)
found = True
if not found:
print('No k4Mac kindle-info/rainier/kinf2011 files have been found.')
return kInfoFiles
# determine type of kindle info provided and return a
# database of keynames and values
def getDBfromFile(kInfoFile):
names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber", "max_date", "SIGVERIF"]
DB = {}
cnt = 0
infoReader = open(kInfoFile, 'r')
hdr = infoReader.read(1)
data = infoReader.read()
if data.find('[') != -1 :
# older style kindle-info file
cud = CryptUnprotectData()
items = data.split('[')
for item in items:
if item != '':
keyhash, rawdata = item.split(':')
keyname = "unknown"
for name in names:
if encodeHash(name,charMap2) == keyhash:
keyname = name
break
if keyname == "unknown":
keyname = keyhash
encryptedValue = decode(rawdata,charMap2)
cleartext = cud.decrypt(encryptedValue)
DB[keyname] = cleartext
cnt = cnt + 1
if cnt == 0:
DB = None
return DB
if hdr == '/':
# else newer style .kinf file used by K4Mac >= 1.6.0
# the .kinf file uses "/" to separate it into records
# so remove the trailing "/" to make it easy to use split
data = data[:-1]
items = data.split('/')
cud = CryptUnprotectDataV2()
# loop through the item records until all are processed
while len(items) > 0:
# get the first item record
item = items.pop(0)
# the first 32 chars of the first record of a group
# is the MD5 hash of the key name encoded by charMap5
keyhash = item[0:32]
keyname = "unknown"
# the raw keyhash string is also used to create entropy for the actual
# CryptProtectData Blob that represents that keys contents
# "entropy" not used for K4Mac only K4PC
# entropy = SHA1(keyhash)
# the remainder of the first record when decoded with charMap5
# has the ':' split char followed by the string representation
# of the number of records that follow
# and make up the contents
srcnt = decode(item[34:],charMap5)
rcnt = int(srcnt)
# read and store in rcnt records of data
# that make up the contents value
edlst = []
for i in xrange(rcnt):
item = items.pop(0)
edlst.append(item)
keyname = "unknown"
for name in names:
if encodeHash(name,charMap5) == keyhash:
keyname = name
break
if keyname == "unknown":
keyname = keyhash
# the charMap5 encoded contents data has had a length
# of chars (always odd) cut off of the front and moved
# to the end to prevent decoding using charMap5 from
# working properly, and thereby preventing the ensuing
# CryptUnprotectData call from succeeding.
# The offset into the charMap5 encoded contents seems to be:
# len(contents) - largest prime number less than or equal to int(len(content)/3)
# (in other words split "about" 2/3rds of the way through)
# move first offsets chars to end to align for decode by charMap5
encdata = "".join(edlst)
contlen = len(encdata)
# now properly split and recombine
# by moving noffset chars from the start of the
# string to the end of the string
noffset = contlen - primes(int(contlen/3))[-1]
pfx = encdata[0:noffset]
encdata = encdata[noffset:]
encdata = encdata + pfx
# decode using charMap5 to get the CryptProtect Data
encryptedValue = decode(encdata,charMap5)
cleartext = cud.decrypt(encryptedValue)
DB[keyname] = cleartext
cnt = cnt + 1
if cnt == 0:
DB = None
return DB
# the latest .kinf2011 version for K4M 1.9.1
# put back the hdr char, it is needed
data = hdr + data
data = data[:-1]
items = data.split('/')
# the headerblob is the encrypted information needed to build the entropy string
headerblob = items.pop(0)
encryptedValue = decode(headerblob, charMap1)
cleartext = UnprotectHeaderData(encryptedValue)
# now extract the pieces in the same way
# this version is different from K4PC it scales the build number by multipying by 735
pattern = re.compile(r'''\[Version:(\d+)\]\[Build:(\d+)\]\[Cksum:([^\]]+)\]\[Guid:([\{\}a-z0-9\-]+)\]''', re.IGNORECASE)
for m in re.finditer(pattern, cleartext):
entropy = str(int(m.group(2)) * 0x2df) + m.group(4)
cud = CryptUnprotectDataV3(entropy)
# loop through the item records until all are processed
while len(items) > 0:
# get the first item record
item = items.pop(0)
# the first 32 chars of the first record of a group
# is the MD5 hash of the key name encoded by charMap5
keyhash = item[0:32]
keyname = "unknown"
# unlike K4PC the keyhash is not used in generating entropy
# entropy = SHA1(keyhash) + added_entropy
# entropy = added_entropy
# the remainder of the first record when decoded with charMap5
# has the ':' split char followed by the string representation
# of the number of records that follow
# and make up the contents
srcnt = decode(item[34:],charMap5)
rcnt = int(srcnt)
# read and store in rcnt records of data
# that make up the contents value
edlst = []
for i in xrange(rcnt):
item = items.pop(0)
edlst.append(item)
keyname = "unknown"
for name in names:
if encodeHash(name,testMap8) == keyhash:
keyname = name
break
if keyname == "unknown":
keyname = keyhash
# the testMap8 encoded contents data has had a length
# of chars (always odd) cut off of the front and moved
# to the end to prevent decoding using testMap8 from
# working properly, and thereby preventing the ensuing
# CryptUnprotectData call from succeeding.
# The offset into the testMap8 encoded contents seems to be:
# len(contents) - largest prime number less than or equal to int(len(content)/3)
# (in other words split "about" 2/3rds of the way through)
# move first offsets chars to end to align for decode by testMap8
encdata = "".join(edlst)
contlen = len(encdata)
# now properly split and recombine
# by moving noffset chars from the start of the
# string to the end of the string
noffset = contlen - primes(int(contlen/3))[-1]
pfx = encdata[0:noffset]
encdata = encdata[noffset:]
encdata = encdata + pfx
# decode using testMap8 to get the CryptProtect Data
encryptedValue = decode(encdata,testMap8)
cleartext = cud.decrypt(encryptedValue)
# print keyname
# print cleartext
DB[keyname] = cleartext
cnt = cnt + 1
if cnt == 0:
DB = None
return DB

455
Other_Tools/KindleBooks/lib/k4pcutils.py
View File

@@ -1,455 +0,0 @@
#!/usr/bin/env python
# K4PC Windows specific routines
from __future__ import with_statement
import sys, os, re
from struct import pack, unpack, unpack_from
from ctypes import windll, c_char_p, c_wchar_p, c_uint, POINTER, byref, \
create_unicode_buffer, create_string_buffer, CFUNCTYPE, addressof, \
string_at, Structure, c_void_p, cast
import _winreg as winreg
MAX_PATH = 255
kernel32 = windll.kernel32
advapi32 = windll.advapi32
crypt32 = windll.crypt32
import traceback
# crypto digestroutines
import hashlib
def MD5(message):
ctx = hashlib.md5()
ctx.update(message)
return ctx.digest()
def SHA1(message):
ctx = hashlib.sha1()
ctx.update(message)
return ctx.digest()
def SHA256(message):
ctx = hashlib.sha256()
ctx.update(message)
return ctx.digest()
# For K4PC 1.9.X
# use routines in alfcrypto:
# AES_cbc_encrypt
# AES_set_decrypt_key
# PKCS5_PBKDF2_HMAC_SHA1
from alfcrypto import AES_CBC, KeyIVGen
def UnprotectHeaderData(encryptedData):
passwdData = 'header_key_data'
salt = 'HEADER.2011'
iter = 0x80
keylen = 0x100
key_iv = KeyIVGen().pbkdf2(passwdData, salt, iter, keylen)
key = key_iv[0:32]
iv = key_iv[32:48]
aes=AES_CBC()
aes.set_decrypt_key(key, iv)
cleartext = aes.decrypt(encryptedData)
return cleartext
# simple primes table (<= n) calculator
def primes(n):
if n==2: return [2]
elif n<2: return []
s=range(3,n+1,2)
mroot = n ** 0.5
half=(n+1)/2-1
i=0
m=3
while m <= mroot:
if s[i]:
j=(m*m-3)/2
s[j]=0
while j<half:
s[j]=0
j+=m
i=i+1
m=2*i+3
return [2]+[x for x in s if x]
# Various character maps used to decrypt kindle info values.
# Probably supposed to act as obfuscation
charMap2 = "AaZzB0bYyCc1XxDdW2wEeVv3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_"
charMap5 = "AzB0bYyCeVvaZ3FfUuG4g-TtHh5SsIiR6rJjQq7KkPpL8lOoMm9Nn_c1XxDdW2wE"
# New maps in K4PC 1.9.0
testMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
testMap6 = "9YzAb0Cd1Ef2n5Pr6St7Uvh3Jk4M8WxG"
testMap8 = "YvaZ3FfUm9Nn_c1XuG4yCAzB0beVg-TtHh5SsIiR6rJjQdW2wEq7KkPpL8lOoMxD"
class DrmException(Exception):
pass
# Encode the bytes in data with the characters in map
def encode(data, map):
result = ""
for char in data:
value = ord(char)
Q = (value ^ 0x80) // len(map)
R = value % len(map)
result += map[Q]
result += map[R]
return result
# Hash the bytes in data and then encode the digest with the characters in map
def encodeHash(data,map):
return encode(MD5(data),map)
# Decode the string in data with the characters in map. Returns the decoded bytes
def decode(data,map):
result = ""
for i in range (0,len(data)-1,2):
high = map.find(data[i])
low = map.find(data[i+1])
if (high == -1) or (low == -1) :
break
value = (((high * len(map)) ^ 0x80) & 0xFF) + low
result += pack("B",value)
return result
# interface with Windows OS Routines
class DataBlob(Structure):
_fields_ = [('cbData', c_uint),
('pbData', c_void_p)]
DataBlob_p = POINTER(DataBlob)
def GetSystemDirectory():
GetSystemDirectoryW = kernel32.GetSystemDirectoryW
GetSystemDirectoryW.argtypes = [c_wchar_p, c_uint]
GetSystemDirectoryW.restype = c_uint
def GetSystemDirectory():
buffer = create_unicode_buffer(MAX_PATH + 1)
GetSystemDirectoryW(buffer, len(buffer))
return buffer.value
return GetSystemDirectory
GetSystemDirectory = GetSystemDirectory()
def GetVolumeSerialNumber():
GetVolumeInformationW = kernel32.GetVolumeInformationW
GetVolumeInformationW.argtypes = [c_wchar_p, c_wchar_p, c_uint,
POINTER(c_uint), POINTER(c_uint),
POINTER(c_uint), c_wchar_p, c_uint]
GetVolumeInformationW.restype = c_uint
def GetVolumeSerialNumber(path = GetSystemDirectory().split('\\')[0] + '\\'):
vsn = c_uint(0)
GetVolumeInformationW(path, None, 0, byref(vsn), None, None, None, 0)
return str(vsn.value)
return GetVolumeSerialNumber
GetVolumeSerialNumber = GetVolumeSerialNumber()
def GetIDString():
vsn = GetVolumeSerialNumber()
print('Using Volume Serial Number for ID: '+vsn)
return vsn
def getLastError():
GetLastError = kernel32.GetLastError
GetLastError.argtypes = None
GetLastError.restype = c_uint
def getLastError():
return GetLastError()
return getLastError
getLastError = getLastError()
def GetUserName():
GetUserNameW = advapi32.GetUserNameW
GetUserNameW.argtypes = [c_wchar_p, POINTER(c_uint)]
GetUserNameW.restype = c_uint
def GetUserName():
buffer = create_unicode_buffer(2)
size = c_uint(len(buffer))
while not GetUserNameW(buffer, byref(size)):
errcd = getLastError()
if errcd == 234:
# bad wine implementation up through wine 1.3.21
return "AlternateUserName"
buffer = create_unicode_buffer(len(buffer) * 2)
size.value = len(buffer)
return buffer.value.encode('utf-16-le')[::2]
return GetUserName
GetUserName = GetUserName()
def CryptUnprotectData():
_CryptUnprotectData = crypt32.CryptUnprotectData
_CryptUnprotectData.argtypes = [DataBlob_p, c_wchar_p, DataBlob_p,
c_void_p, c_void_p, c_uint, DataBlob_p]
_CryptUnprotectData.restype = c_uint
def CryptUnprotectData(indata, entropy, flags):
indatab = create_string_buffer(indata)
indata = DataBlob(len(indata), cast(indatab, c_void_p))
entropyb = create_string_buffer(entropy)
entropy = DataBlob(len(entropy), cast(entropyb, c_void_p))
outdata = DataBlob()
if not _CryptUnprotectData(byref(indata), None, byref(entropy),
None, None, flags, byref(outdata)):
# raise DrmException("Failed to Unprotect Data")
return 'failed'
return string_at(outdata.pbData, outdata.cbData)
return CryptUnprotectData
CryptUnprotectData = CryptUnprotectData()
# Locate all of the kindle-info style files and return as list
def getKindleInfoFiles():
kInfoFiles = []
# some 64 bit machines do not have the proper registry key for some reason
# or the pythonn interface to the 32 vs 64 bit registry is broken
path = ""
if 'LOCALAPPDATA' in os.environ.keys():
path = os.environ['LOCALAPPDATA']
else:
# User Shell Folders show take precedent over Shell Folders if present
try:
regkey = winreg.OpenKey(winreg.HKEY_CURRENT_USER, "Software\\Microsoft\\Windows\\CurrentVersion\\Explorer\\User Shell Folders\\")
path = winreg.QueryValueEx(regkey, 'Local AppData')[0]
if not os.path.isdir(path):
path = ""
try:
regkey = winreg.OpenKey(winreg.HKEY_CURRENT_USER, "Software\\Microsoft\\Windows\\CurrentVersion\\Explorer\\Shell Folders\\")
path = winreg.QueryValueEx(regkey, 'Local AppData')[0]
if not os.path.isdir(path):
path = ""
except RegError:
pass
except RegError:
pass
found = False
if path == "":
print ('Could not find the folder in which to look for kinfoFiles.')
else:
print('searching for kinfoFiles in ' + path)
# first look for older kindle-info files
kinfopath = path +'\\Amazon\\Kindle For PC\\{AMAwzsaPaaZAzmZzZQzgZCAkZ3AjA_AY}\\kindle.info'
if os.path.isfile(kinfopath):
found = True
print('Found K4PC kindle.info file: ' + kinfopath)
kInfoFiles.append(kinfopath)
# now look for newer (K4PC 1.5.0 and later rainier.2.1.1.kinf file
kinfopath = path +'\\Amazon\\Kindle For PC\\storage\\rainier.2.1.1.kinf'
if os.path.isfile(kinfopath):
found = True
print('Found K4PC 1.5.X kinf file: ' + kinfopath)
kInfoFiles.append(kinfopath)
# now look for even newer (K4PC 1.6.0 and later) rainier.2.1.1.kinf file
kinfopath = path +'\\Amazon\\Kindle\\storage\\rainier.2.1.1.kinf'
if os.path.isfile(kinfopath):
found = True
print('Found K4PC 1.6.X kinf file: ' + kinfopath)
kInfoFiles.append(kinfopath)
# now look for even newer (K4PC 1.9.0 and later) .kinf2011 file
kinfopath = path +'\\Amazon\\Kindle\\storage\\.kinf2011'
if os.path.isfile(kinfopath):
found = True
print('Found K4PC kinf2011 file: ' + kinfopath)
kInfoFiles.append(kinfopath)
if not found:
print('No K4PC kindle.info/kinf/kinf2011 files have been found.')
return kInfoFiles
# determine type of kindle info provided and return a
# database of keynames and values
def getDBfromFile(kInfoFile):
names = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber", "max_date", "SIGVERIF"]
DB = {}
cnt = 0
infoReader = open(kInfoFile, 'r')
hdr = infoReader.read(1)
data = infoReader.read()
if data.find('{') != -1 :
# older style kindle-info file
items = data.split('{')
for item in items:
if item != '':
keyhash, rawdata = item.split(':')
keyname = "unknown"
for name in names:
if encodeHash(name,charMap2) == keyhash:
keyname = name
break
if keyname == "unknown":
keyname = keyhash
encryptedValue = decode(rawdata,charMap2)
DB[keyname] = CryptUnprotectData(encryptedValue, "", 0)
cnt = cnt + 1
if cnt == 0:
DB = None
return DB
if hdr == '/':
# else rainier-2-1-1 .kinf file
# the .kinf file uses "/" to separate it into records
# so remove the trailing "/" to make it easy to use split
data = data[:-1]
items = data.split('/')
# loop through the item records until all are processed
while len(items) > 0:
# get the first item record
item = items.pop(0)
# the first 32 chars of the first record of a group
# is the MD5 hash of the key name encoded by charMap5
keyhash = item[0:32]
# the raw keyhash string is used to create entropy for the actual
# CryptProtectData Blob that represents that keys contents
entropy = SHA1(keyhash)
# the remainder of the first record when decoded with charMap5
# has the ':' split char followed by the string representation
# of the number of records that follow
# and make up the contents
srcnt = decode(item[34:],charMap5)
rcnt = int(srcnt)
# read and store in rcnt records of data
# that make up the contents value
edlst = []
for i in xrange(rcnt):
item = items.pop(0)
edlst.append(item)
keyname = "unknown"
for name in names:
if encodeHash(name,charMap5) == keyhash:
keyname = name
break
if keyname == "unknown":
keyname = keyhash
# the charMap5 encoded contents data has had a length
# of chars (always odd) cut off of the front and moved
# to the end to prevent decoding using charMap5 from
# working properly, and thereby preventing the ensuing
# CryptUnprotectData call from succeeding.
# The offset into the charMap5 encoded contents seems to be:
# len(contents)-largest prime number <= int(len(content)/3)
# (in other words split "about" 2/3rds of the way through)
# move first offsets chars to end to align for decode by charMap5
encdata = "".join(edlst)
contlen = len(encdata)
noffset = contlen - primes(int(contlen/3))[-1]
# now properly split and recombine
# by moving noffset chars from the start of the
# string to the end of the string
pfx = encdata[0:noffset]
encdata = encdata[noffset:]
encdata = encdata + pfx
# decode using Map5 to get the CryptProtect Data
encryptedValue = decode(encdata,charMap5)
DB[keyname] = CryptUnprotectData(encryptedValue, entropy, 1)
cnt = cnt + 1
if cnt == 0:
DB = None
return DB
# else newest .kinf2011 style .kinf file
# the .kinf file uses "/" to separate it into records
# so remove the trailing "/" to make it easy to use split
# need to put back the first char read because it it part
# of the added entropy blob
data = hdr + data[:-1]
items = data.split('/')
# starts with and encoded and encrypted header blob
headerblob = items.pop(0)
encryptedValue = decode(headerblob, testMap1)
cleartext = UnprotectHeaderData(encryptedValue)
# now extract the pieces that form the added entropy
pattern = re.compile(r'''\[Version:(\d+)\]\[Build:(\d+)\]\[Cksum:([^\]]+)\]\[Guid:([\{\}a-z0-9\-]+)\]''', re.IGNORECASE)
for m in re.finditer(pattern, cleartext):
added_entropy = m.group(2) + m.group(4)
# loop through the item records until all are processed
while len(items) > 0:
# get the first item record
item = items.pop(0)
# the first 32 chars of the first record of a group
# is the MD5 hash of the key name encoded by charMap5
keyhash = item[0:32]
# the sha1 of raw keyhash string is used to create entropy along
# with the added entropy provided above from the headerblob
entropy = SHA1(keyhash) + added_entropy
# the remainder of the first record when decoded with charMap5
# has the ':' split char followed by the string representation
# of the number of records that follow
# and make up the contents
srcnt = decode(item[34:],charMap5)
rcnt = int(srcnt)
# read and store in rcnt records of data
# that make up the contents value
edlst = []
for i in xrange(rcnt):
item = items.pop(0)
edlst.append(item)
# key names now use the new testMap8 encoding
keyname = "unknown"
for name in names:
if encodeHash(name,testMap8) == keyhash:
keyname = name
break
# the testMap8 encoded contents data has had a length
# of chars (always odd) cut off of the front and moved
# to the end to prevent decoding using testMap8 from
# working properly, and thereby preventing the ensuing
# CryptUnprotectData call from succeeding.
# The offset into the testMap8 encoded contents seems to be:
# len(contents)-largest prime number <= int(len(content)/3)
# (in other words split "about" 2/3rds of the way through)
# move first offsets chars to end to align for decode by testMap8
# by moving noffset chars from the start of the
# string to the end of the string
encdata = "".join(edlst)
contlen = len(encdata)
noffset = contlen - primes(int(contlen/3))[-1]
pfx = encdata[0:noffset]
encdata = encdata[noffset:]
encdata = encdata + pfx
# decode using new testMap8 to get the original CryptProtect Data
encryptedValue = decode(encdata,testMap8)
cleartext = CryptUnprotectData(encryptedValue, entropy, 1)
DB[keyname] = cleartext
cnt = cnt + 1
if cnt == 0:
DB = None
return DB

274
Other_Tools/KindleBooks/lib/kgenpids.py
View File

@@ -1,274 +0,0 @@
#!/usr/bin/env python
from __future__ import with_statement
import sys
import os, csv
import binascii
import zlib
import re
from struct import pack, unpack, unpack_from
class DrmException(Exception):
pass
global charMap1
global charMap3
global charMap4
if 'calibre' in sys.modules:
inCalibre = True
else:
inCalibre = False
if inCalibre:
if sys.platform.startswith('win'):
from calibre_plugins.k4mobidedrm.k4pcutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
if sys.platform.startswith('darwin'):
from calibre_plugins.k4mobidedrm.k4mutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
else:
if sys.platform.startswith('win'):
from k4pcutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
if sys.platform.startswith('darwin'):
from k4mutils import getKindleInfoFiles, getDBfromFile, GetUserName, GetIDString
charMap1 = "n5Pr6St7Uv8Wx9YzAb0Cd1Ef2Gh3Jk4M"
charMap3 = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
charMap4 = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
# crypto digestroutines
import hashlib
def MD5(message):
ctx = hashlib.md5()
ctx.update(message)
return ctx.digest()
def SHA1(message):
ctx = hashlib.sha1()
ctx.update(message)
return ctx.digest()
# Encode the bytes in data with the characters in map
def encode(data, map):
result = ""
for char in data:
value = ord(char)
Q = (value ^ 0x80) // len(map)
R = value % len(map)
result += map[Q]
result += map[R]
return result
# Hash the bytes in data and then encode the digest with the characters in map
def encodeHash(data,map):
return encode(MD5(data),map)
# Decode the string in data with the characters in map. Returns the decoded bytes
def decode(data,map):
result = ""
for i in range (0,len(data)-1,2):
high = map.find(data[i])
low = map.find(data[i+1])
if (high == -1) or (low == -1) :
break
value = (((high * len(map)) ^ 0x80) & 0xFF) + low
result += pack("B",value)
return result
#
# PID generation routines
#
# Returns two bit at offset from a bit field
def getTwoBitsFromBitField(bitField,offset):
byteNumber = offset // 4
bitPosition = 6 - 2*(offset % 4)
return ord(bitField[byteNumber]) >> bitPosition & 3
# Returns the six bits at offset from a bit field
def getSixBitsFromBitField(bitField,offset):
offset *= 3
value = (getTwoBitsFromBitField(bitField,offset) <<4) + (getTwoBitsFromBitField(bitField,offset+1) << 2) +getTwoBitsFromBitField(bitField,offset+2)
return value
# 8 bits to six bits encoding from hash to generate PID string
def encodePID(hash):
global charMap3
PID = ""
for position in range (0,8):
PID += charMap3[getSixBitsFromBitField(hash,position)]
return PID
# Encryption table used to generate the device PID
def generatePidEncryptionTable() :
table = []
for counter1 in range (0,0x100):
value = counter1
for counter2 in range (0,8):
if (value & 1 == 0) :
value = value >> 1
else :
value = value >> 1
value = value ^ 0xEDB88320
table.append(value)
return table
# Seed value used to generate the device PID
def generatePidSeed(table,dsn) :
value = 0
for counter in range (0,4) :
index = (ord(dsn[counter]) ^ value) &0xFF
value = (value >> 8) ^ table[index]
return value
# Generate the device PID
def generateDevicePID(table,dsn,nbRoll):
global charMap4
seed = generatePidSeed(table,dsn)
pidAscii = ""
pid = [(seed >>24) &0xFF,(seed >> 16) &0xff,(seed >> 8) &0xFF,(seed) & 0xFF,(seed>>24) & 0xFF,(seed >> 16) &0xff,(seed >> 8) &0xFF,(seed) & 0xFF]
index = 0
for counter in range (0,nbRoll):
pid[index] = pid[index] ^ ord(dsn[counter])
index = (index+1) %8
for counter in range (0,8):
index = ((((pid[counter] >>5) & 3) ^ pid[counter]) & 0x1f) + (pid[counter] >> 7)
pidAscii += charMap4[index]
return pidAscii
def crc32(s):
return (~binascii.crc32(s,-1))&0xFFFFFFFF
# convert from 8 digit PID to 10 digit PID with checksum
def checksumPid(s):
global charMap4
crc = crc32(s)
crc = crc ^ (crc >> 16)
res = s
l = len(charMap4)
for i in (0,1):
b = crc & 0xff
pos = (b // l) ^ (b % l)
res += charMap4[pos%l]
crc >>= 8
return res
# old kindle serial number to fixed pid
def pidFromSerial(s, l):
global charMap4
crc = crc32(s)
arr1 = [0]*l
for i in xrange(len(s)):
arr1[i%l] ^= ord(s[i])
crc_bytes = [crc >> 24 & 0xff, crc >> 16 & 0xff, crc >> 8 & 0xff, crc & 0xff]
for i in xrange(l):
arr1[i] ^= crc_bytes[i&3]
pid = ""
for i in xrange(l):
b = arr1[i] & 0xff
pid+=charMap4[(b >> 7) + ((b >> 5 & 3) ^ (b & 0x1f))]
return pid
# Parse the EXTH header records and use the Kindle serial number to calculate the book pid.
def getKindlePid(pidlst, rec209, token, serialnum):
# Compute book PID
pidHash = SHA1(serialnum+rec209+token)
bookPID = encodePID(pidHash)
bookPID = checksumPid(bookPID)
pidlst.append(bookPID)
# compute fixed pid for old pre 2.5 firmware update pid as well
bookPID = pidFromSerial(serialnum, 7) + "*"
bookPID = checksumPid(bookPID)
pidlst.append(bookPID)
return pidlst
# parse the Kindleinfo file to calculate the book pid.
keynames = ["kindle.account.tokens","kindle.cookie.item","eulaVersionAccepted","login_date","kindle.token.item","login","kindle.key.item","kindle.name.info","kindle.device.info", "MazamaRandomNumber"]
def getK4Pids(pidlst, rec209, token, kInfoFile):
global charMap1
kindleDatabase = None
try:
kindleDatabase = getDBfromFile(kInfoFile)
except Exception, message:
print(message)
kindleDatabase = None
pass
if kindleDatabase == None :
return pidlst
try:
# Get the Mazama Random number
MazamaRandomNumber = kindleDatabase["MazamaRandomNumber"]
# Get the kindle account token
kindleAccountToken = kindleDatabase["kindle.account.tokens"]
except KeyError:
print "Keys not found in " + kInfoFile
return pidlst
# Get the ID string used
encodedIDString = encodeHash(GetIDString(),charMap1)
# Get the current user name
encodedUsername = encodeHash(GetUserName(),charMap1)
# concat, hash and encode to calculate the DSN
DSN = encode(SHA1(MazamaRandomNumber+encodedIDString+encodedUsername),charMap1)
# Compute the device PID (for which I can tell, is used for nothing).
table = generatePidEncryptionTable()
devicePID = generateDevicePID(table,DSN,4)
devicePID = checksumPid(devicePID)
pidlst.append(devicePID)
# Compute book PIDs
# book pid
pidHash = SHA1(DSN+kindleAccountToken+rec209+token)
bookPID = encodePID(pidHash)
bookPID = checksumPid(bookPID)
pidlst.append(bookPID)
# variant 1
pidHash = SHA1(kindleAccountToken+rec209+token)
bookPID = encodePID(pidHash)
bookPID = checksumPid(bookPID)
pidlst.append(bookPID)
# variant 2
pidHash = SHA1(DSN+rec209+token)
bookPID = encodePID(pidHash)
bookPID = checksumPid(bookPID)
pidlst.append(bookPID)
return pidlst
def getPidList(md1, md2, k4 = True, serials=[], kInfoFiles=[]):
pidlst = []
if kInfoFiles is None:
kInfoFiles = []
if k4:
kInfoFiles.extend(getKindleInfoFiles())
for infoFile in kInfoFiles:
try:
pidlst = getK4Pids(pidlst, md1, md2, infoFile)
except Exception, message:
print("Error getting PIDs from " + infoFile + ": " + message)
for serialnum in serials:
try:
pidlst = getKindlePid(pidlst, md1, md2, serialnum)
except Exception, message:
print("Error getting PIDs from " + serialnum + ": " + message)
return pidlst

BIN
Other_Tools/KindleBooks/lib/libalfcrypto.dylib
View File

Binary file not shown.

BIN
Other_Tools/KindleBooks/lib/libalfcrypto32.so
View File

Binary file not shown.

BIN
Other_Tools/KindleBooks/lib/libalfcrypto64.so
View File

Binary file not shown.

460
Other_Tools/KindleBooks/lib/mobidedrm.py
View File

@@ -1,460 +0,0 @@
#!/usr/bin/python
#
# This is a python script. You need a Python interpreter to run it.
# For example, ActiveState Python, which exists for windows.
#
# Changelog
# 0.01 - Initial version
# 0.02 - Huffdic compressed books were not properly decrypted
# 0.03 - Wasn't checking MOBI header length
# 0.04 - Wasn't sanity checking size of data record
# 0.05 - It seems that the extra data flags take two bytes not four
# 0.06 - And that low bit does mean something after all :-)
# 0.07 - The extra data flags aren't present in MOBI header < 0xE8 in size
# 0.08 - ...and also not in Mobi header version < 6
# 0.09 - ...but they are there with Mobi header version 6, header size 0xE4!
# 0.10 - Outputs unencrypted files as-is, so that when run as a Calibre
# import filter it works when importing unencrypted files.
# Also now handles encrypted files that don't need a specific PID.
# 0.11 - use autoflushed stdout and proper return values
# 0.12 - Fix for problems with metadata import as Calibre plugin, report errors
# 0.13 - Formatting fixes: retabbed file, removed trailing whitespace
# and extra blank lines, converted CR/LF pairs at ends of each line,
# and other cosmetic fixes.
# 0.14 - Working out when the extra data flags are present has been problematic
# Versions 7 through 9 have tried to tweak the conditions, but have been
# only partially successful. Closer examination of lots of sample
# files reveals that a confusion has arisen because trailing data entries
# are not encrypted, but it turns out that the multibyte entries
# in utf8 file are encrypted. (Although neither kind gets compressed.)
# This knowledge leads to a simplification of the test for the
# trailing data byte flags - version 5 and higher AND header size >= 0xE4.
# 0.15 - Now outputs 'heartbeat', and is also quicker for long files.
# 0.16 - And reverts to 'done' not 'done.' at the end for unswindle compatibility.
# 0.17 - added modifications to support its use as an imported python module
# both inside calibre and also in other places (ie K4DeDRM tools)
# 0.17a- disabled the standalone plugin feature since a plugin can not import
# a plugin
# 0.18 - It seems that multibyte entries aren't encrypted in a v7 file...
# Removed the disabled Calibre plug-in code
# Permit use of 8-digit PIDs
# 0.19 - It seems that multibyte entries aren't encrypted in a v6 file either.
# 0.20 - Correction: It seems that multibyte entries are encrypted in a v6 file.
# 0.21 - Added support for multiple pids
# 0.22 - revised structure to hold MobiBook as a class to allow an extended interface
# 0.23 - fixed problem with older files with no EXTH section
# 0.24 - add support for type 1 encryption and 'TEXtREAd' books as well
# 0.25 - Fixed support for 'BOOKMOBI' type 1 encryption
# 0.26 - Now enables Text-To-Speech flag and sets clipping limit to 100%
# 0.27 - Correct pid metadata token generation to match that used by skindle (Thank You Bart!)
# 0.28 - slight additional changes to metadata token generation (None -> '')
# 0.29 - It seems that the ideas about when multibyte trailing characters were
# included in the encryption were wrong. They are for DOC compressed
# files, but they are not for HUFF/CDIC compress files!
# 0.30 - Modified interface slightly to work better with new calibre plugin style
# 0.31 - The multibyte encrytion info is true for version 7 files too.
# 0.32 - Added support for "Print Replica" Kindle ebooks
# 0.33 - Performance improvements for large files (concatenation)
# 0.34 - Performance improvements in decryption (libalfcrypto)
# 0.35 - add interface to get mobi_version
# 0.36 - fixed problem with TEXtREAd and getBookTitle interface
# 0.37 - Fixed double announcement for stand-alone operation
__version__ = '0.37'
import sys
class Unbuffered:
def __init__(self, stream):
self.stream = stream
def write(self, data):
self.stream.write(data)
self.stream.flush()
def __getattr__(self, attr):
return getattr(self.stream, attr)
sys.stdout=Unbuffered(sys.stdout)
import os
import struct
import binascii
from alfcrypto import Pukall_Cipher
class DrmException(Exception):
pass
#
# MobiBook Utility Routines
#
# Implementation of Pukall Cipher 1
def PC1(key, src, decryption=True):
return Pukall_Cipher().PC1(key,src,decryption)
# sum1 = 0;
# sum2 = 0;
# keyXorVal = 0;
# if len(key)!=16:
# print "Bad key length!"
# return None
# wkey = []
# for i in xrange(8):
# wkey.append(ord(key[i*2])<<8 | ord(key[i*2+1]))
# dst = ""
# for i in xrange(len(src)):
# temp1 = 0;
# byteXorVal = 0;
# for j in xrange(8):
# temp1 ^= wkey[j]
# sum2 = (sum2+j)*20021 + sum1
# sum1 = (temp1*346)&0xFFFF
# sum2 = (sum2+sum1)&0xFFFF
# temp1 = (temp1*20021+1)&0xFFFF
# byteXorVal ^= temp1 ^ sum2
# curByte = ord(src[i])
# if not decryption:
# keyXorVal = curByte * 257;
# curByte = ((curByte ^ (byteXorVal >> 8)) ^ byteXorVal) & 0xFF
# if decryption:
# keyXorVal = curByte * 257;
# for j in xrange(8):
# wkey[j] ^= keyXorVal;
# dst+=chr(curByte)
# return dst
def checksumPid(s):
letters = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
crc = (~binascii.crc32(s,-1))&0xFFFFFFFF
crc = crc ^ (crc >> 16)
res = s
l = len(letters)
for i in (0,1):
b = crc & 0xff
pos = (b // l) ^ (b % l)
res += letters[pos%l]
crc >>= 8
return res
def getSizeOfTrailingDataEntries(ptr, size, flags):
def getSizeOfTrailingDataEntry(ptr, size):
bitpos, result = 0, 0
if size <= 0:
return result
while True:
v = ord(ptr[size-1])
result |= (v & 0x7F) << bitpos
bitpos += 7
size -= 1
if (v & 0x80) != 0 or (bitpos >= 28) or (size == 0):
return result
num = 0
testflags = flags >> 1
while testflags:
if testflags & 1:
num += getSizeOfTrailingDataEntry(ptr, size - num)
testflags >>= 1
# Check the low bit to see if there's multibyte data present.
# if multibyte data is included in the encryped data, we'll
# have already cleared this flag.
if flags & 1:
num += (ord(ptr[size - num - 1]) & 0x3) + 1
return num
class MobiBook:
def loadSection(self, section):
if (section + 1 == self.num_sections):
endoff = len(self.data_file)
else:
endoff = self.sections[section + 1][0]
off = self.sections[section][0]
return self.data_file[off:endoff]
def __init__(self, infile, announce = True):
if announce:
print ('MobiDeDrm v%(__version__)s. '
'Copyright 2008-2012 The Dark Reverser et al.' % globals())
# initial sanity check on file
self.data_file = file(infile, 'rb').read()
self.mobi_data = ''
self.header = self.data_file[0:78]
if self.header[0x3C:0x3C+8] != 'BOOKMOBI' and self.header[0x3C:0x3C+8] != 'TEXtREAd':
raise DrmException("invalid file format")
self.magic = self.header[0x3C:0x3C+8]
self.crypto_type = -1
# build up section offset and flag info
self.num_sections, = struct.unpack('>H', self.header[76:78])
self.sections = []
for i in xrange(self.num_sections):
offset, a1,a2,a3,a4 = struct.unpack('>LBBBB', self.data_file[78+i*8:78+i*8+8])
flags, val = a1, a2<<16|a3<<8|a4
self.sections.append( (offset, flags, val) )
# parse information from section 0
self.sect = self.loadSection(0)
self.records, = struct.unpack('>H', self.sect[0x8:0x8+2])
self.compression, = struct.unpack('>H', self.sect[0x0:0x0+2])
if self.magic == 'TEXtREAd':
print "Book has format: ", self.magic
self.extra_data_flags = 0
self.mobi_length = 0
self.mobi_codepage = 1252
self.mobi_version = -1
self.meta_array = {}
return
self.mobi_length, = struct.unpack('>L',self.sect[0x14:0x18])
self.mobi_codepage, = struct.unpack('>L',self.sect[0x1c:0x20])
self.mobi_version, = struct.unpack('>L',self.sect[0x68:0x6C])
print "MOBI header version = %d, length = %d" %(self.mobi_version, self.mobi_length)
self.extra_data_flags = 0
if (self.mobi_length >= 0xE4) and (self.mobi_version >= 5):
self.extra_data_flags, = struct.unpack('>H', self.sect[0xF2:0xF4])
print "Extra Data Flags = %d" % self.extra_data_flags
if (self.compression != 17480):
# multibyte utf8 data is included in the encryption for PalmDoc compression
# so clear that byte so that we leave it to be decrypted.
self.extra_data_flags &= 0xFFFE
# if exth region exists parse it for metadata array
self.meta_array = {}
try:
exth_flag, = struct.unpack('>L', self.sect[0x80:0x84])
exth = 'NONE'
if exth_flag & 0x40:
exth = self.sect[16 + self.mobi_length:]
if (len(exth) >= 4) and (exth[:4] == 'EXTH'):
nitems, = struct.unpack('>I', exth[8:12])
pos = 12
for i in xrange(nitems):
type, size = struct.unpack('>II', exth[pos: pos + 8])
content = exth[pos + 8: pos + size]
self.meta_array[type] = content
# reset the text to speech flag and clipping limit, if present
if type == 401 and size == 9:
# set clipping limit to 100%
self.patchSection(0, "\144", 16 + self.mobi_length + pos + 8)
elif type == 404 and size == 9:
# make sure text to speech is enabled
self.patchSection(0, "\0", 16 + self.mobi_length + pos + 8)
# print type, size, content, content.encode('hex')
pos += size
except:
self.meta_array = {}
pass
self.print_replica = False
def getBookTitle(self):
codec_map = {
1252 : 'windows-1252',
65001 : 'utf-8',
}
title = ''
codec = 'windows-1252'
if self.magic == 'BOOKMOBI':
if 503 in self.meta_array:
title = self.meta_array[503]
else:
toff, tlen = struct.unpack('>II', self.sect[0x54:0x5c])
tend = toff + tlen
title = self.sect[toff:tend]
if self.mobi_codepage in codec_map.keys():
codec = codec_map[self.mobi_codepage]
if title == '':
title = self.header[:32]
title = title.split("\0")[0]
return unicode(title, codec).encode('utf-8')
def getPIDMetaInfo(self):
rec209 = ''
token = ''
if 209 in self.meta_array:
rec209 = self.meta_array[209]
data = rec209
# The 209 data comes in five byte groups. Interpret the last four bytes
# of each group as a big endian unsigned integer to get a key value
# if that key exists in the meta_array, append its contents to the token
for i in xrange(0,len(data),5):
val, = struct.unpack('>I',data[i+1:i+5])
sval = self.meta_array.get(val,'')
token += sval
return rec209, token
def patch(self, off, new):
self.data_file = self.data_file[:off] + new + self.data_file[off+len(new):]
def patchSection(self, section, new, in_off = 0):
if (section + 1 == self.num_sections):
endoff = len(self.data_file)
else:
endoff = self.sections[section + 1][0]
off = self.sections[section][0]
assert off + in_off + len(new) <= endoff
self.patch(off + in_off, new)
def parseDRM(self, data, count, pidlist):
found_key = None
keyvec1 = "\x72\x38\x33\xB0\xB4\xF2\xE3\xCA\xDF\x09\x01\xD6\xE2\xE0\x3F\x96"
for pid in pidlist:
bigpid = pid.ljust(16,'\0')
temp_key = PC1(keyvec1, bigpid, False)
temp_key_sum = sum(map(ord,temp_key)) & 0xff
found_key = None
for i in xrange(count):
verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
if cksum == temp_key_sum:
cookie = PC1(temp_key, cookie)
ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
if verification == ver and (flags & 0x1F) == 1:
found_key = finalkey
break
if found_key != None:
break
if not found_key:
# Then try the default encoding that doesn't require a PID
pid = "00000000"
temp_key = keyvec1
temp_key_sum = sum(map(ord,temp_key)) & 0xff
for i in xrange(count):
verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
if cksum == temp_key_sum:
cookie = PC1(temp_key, cookie)
ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
if verification == ver:
found_key = finalkey
break
return [found_key,pid]
def getMobiFile(self, outpath):
file(outpath,'wb').write(self.mobi_data)
def getMobiVersion(self):
return self.mobi_version
def getPrintReplica(self):
return self.print_replica
def processBook(self, pidlist):
crypto_type, = struct.unpack('>H', self.sect[0xC:0xC+2])
print 'Crypto Type is: ', crypto_type
self.crypto_type = crypto_type
if crypto_type == 0:
print "This book is not encrypted."
# we must still check for Print Replica
self.print_replica = (self.loadSection(1)[0:4] == '%MOP')
self.mobi_data = self.data_file
return
if crypto_type != 2 and crypto_type != 1:
raise DrmException("Cannot decode unknown Mobipocket encryption type %d" % crypto_type)
if 406 in self.meta_array:
data406 = self.meta_array[406]
val406, = struct.unpack('>Q',data406)
if val406 != 0:
raise DrmException("Cannot decode library or rented ebooks.")
goodpids = []
for pid in pidlist:
if len(pid)==10:
if checksumPid(pid[0:-2]) != pid:
print "Warning: PID " + pid + " has incorrect checksum, should have been "+checksumPid(pid[0:-2])
goodpids.append(pid[0:-2])
elif len(pid)==8:
goodpids.append(pid)
if self.crypto_type == 1:
t1_keyvec = "QDCVEPMU675RUBSZ"
if self.magic == 'TEXtREAd':
bookkey_data = self.sect[0x0E:0x0E+16]
elif self.mobi_version < 0:
bookkey_data = self.sect[0x90:0x90+16]
else:
bookkey_data = self.sect[self.mobi_length+16:self.mobi_length+32]
pid = "00000000"
found_key = PC1(t1_keyvec, bookkey_data)
else :
# calculate the keys
drm_ptr, drm_count, drm_size, drm_flags = struct.unpack('>LLLL', self.sect[0xA8:0xA8+16])
if drm_count == 0:
raise DrmException("Not yet initialised with PID. Must be opened with Mobipocket Reader first.")
found_key, pid = self.parseDRM(self.sect[drm_ptr:drm_ptr+drm_size], drm_count, goodpids)
if not found_key:
raise DrmException("No key found in " + str(len(goodpids)) + " keys tried. Read the FAQs at Alf's blog. Only if none apply, report this failure for help.")
# kill the drm keys
self.patchSection(0, "\0" * drm_size, drm_ptr)
# kill the drm pointers
self.patchSection(0, "\xff" * 4 + "\0" * 12, 0xA8)
if pid=="00000000":
print "File has default encryption, no specific PID."
else:
print "File is encoded with PID "+checksumPid(pid)+"."
# clear the crypto type
self.patchSection(0, "\0" * 2, 0xC)
# decrypt sections
print "Decrypting. Please wait . . .",
mobidataList = []
mobidataList.append(self.data_file[:self.sections[1][0]])
for i in xrange(1, self.records+1):
data = self.loadSection(i)
extra_size = getSizeOfTrailingDataEntries(data, len(data), self.extra_data_flags)
if i%100 == 0:
print ".",
# print "record %d, extra_size %d" %(i,extra_size)
decoded_data = PC1(found_key, data[0:len(data) - extra_size])
if i==1:
self.print_replica = (decoded_data[0:4] == '%MOP')
mobidataList.append(decoded_data)
if extra_size > 0:
mobidataList.append(data[-extra_size:])
if self.num_sections > self.records+1:
mobidataList.append(self.data_file[self.sections[self.records+1][0]:])
self.mobi_data = "".join(mobidataList)
print "done"
return
def getUnencryptedBook(infile,pid,announce=True):
if not os.path.isfile(infile):
raise DrmException('Input File Not Found')
book = MobiBook(infile,announce)
book.processBook([pid])
return book.mobi_data
def getUnencryptedBookWithList(infile,pidlist,announce=True):
if not os.path.isfile(infile):
raise DrmException('Input File Not Found')
book = MobiBook(infile, announce)
book.processBook(pidlist)
return book.mobi_data
def main(argv=sys.argv):
print ('MobiDeDrm v%(__version__)s. '
'Copyright 2008-2012 The Dark Reverser et al.' % globals())
if len(argv)<3 or len(argv)>4:
print "Removes protection from Kindle/Mobipocket, Kindle/KF8 and Kindle/Print Replica ebooks"
print "Usage:"
print " %s <infile> <outfile> [<Comma separated list of PIDs to try>]" % sys.argv[0]
return 1
else:
infile = argv[1]
outfile = argv[2]
if len(argv) is 4:
pidlist = argv[3].split(',')
else:
pidlist = {}
try:
stripped_file = getUnencryptedBookWithList(infile, pidlist, False)
file(outfile, 'wb').write(stripped_file)
except DrmException, e:
print "Error: %s" % e
return 1
return 0
if __name__ == "__main__":
sys.exit(main())

27
Other_Tools/KindleBooks/lib/scrolltextwidget.py
View File

@@ -1,27 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import Tkinter
import Tkconstants
# basic scrolled text widget
class ScrolledText(Tkinter.Text):
def __init__(self, master=None, **kw):
self.frame = Tkinter.Frame(master)
self.vbar = Tkinter.Scrollbar(self.frame)
self.vbar.pack(side=Tkconstants.RIGHT, fill=Tkconstants.Y)
kw.update({'yscrollcommand': self.vbar.set})
Tkinter.Text.__init__(self, self.frame, **kw)
self.pack(side=Tkconstants.LEFT, fill=Tkconstants.BOTH, expand=True)
self.vbar['command'] = self.yview
# Copy geometry methods of self.frame without overriding Text
# methods = hack!
text_meths = vars(Tkinter.Text).keys()
methods = vars(Tkinter.Pack).keys() + vars(Tkinter.Grid).keys() + vars(Tkinter.Place).keys()
methods = set(methods).difference(text_meths)
for m in methods:
if m[0] != '_' and m != 'config' and m != 'configure':
setattr(self, m, getattr(self.frame, m))
def __str__(self):
return str(self.frame)

266
Other_Tools/KindleBooks/lib/stylexml2css.py
View File

@@ -1,266 +0,0 @@
#! /usr/bin/python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
# For use with Topaz Scripts Version 2.6
import csv
import sys
import os
import getopt
import re
from struct import pack
from struct import unpack
class DocParser(object):
def __init__(self, flatxml, fontsize, ph, pw):
self.flatdoc = flatxml.split('\n')
self.fontsize = int(fontsize)
self.ph = int(ph) * 1.0
self.pw = int(pw) * 1.0
stags = {
'paragraph' : 'p',
'graphic' : '.graphic'
}
attr_val_map = {
'hang' : 'text-indent: ',
'indent' : 'text-indent: ',
'line-space' : 'line-height: ',
'margin-bottom' : 'margin-bottom: ',
'margin-left' : 'margin-left: ',
'margin-right' : 'margin-right: ',
'margin-top' : 'margin-top: ',
'space-after' : 'padding-bottom: ',
}
attr_str_map = {
'align-center' : 'text-align: center; margin-left: auto; margin-right: auto;',
'align-left' : 'text-align: left;',
'align-right' : 'text-align: right;',
'align-justify' : 'text-align: justify;',
'display-inline' : 'display: inline;',
'pos-left' : 'text-align: left;',
'pos-right' : 'text-align: right;',
'pos-center' : 'text-align: center; margin-left: auto; margin-right: auto;',
}
# find tag if within pos to end inclusive
def findinDoc(self, tagpath, pos, end) :
result = None
docList = self.flatdoc
cnt = len(docList)
if end == -1 :
end = cnt
else:
end = min(cnt,end)
foundat = -1
for j in xrange(pos, end):
item = docList[j]
if item.find('=') >= 0:
(name, argres) = item.split('=',1)
else :
name = item
argres = ''
if name.endswith(tagpath) :
result = argres
foundat = j
break
return foundat, result
# return list of start positions for the tagpath
def posinDoc(self, tagpath):
startpos = []
pos = 0
res = ""
while res != None :
(foundpos, res) = self.findinDoc(tagpath, pos, -1)
if res != None :
startpos.append(foundpos)
pos = foundpos + 1
return startpos
# returns a vector of integers for the tagpath
def getData(self, tagpath, pos, end, clean=False):
if clean:
digits_only = re.compile(r'''([0-9]+)''')
argres=[]
(foundat, argt) = self.findinDoc(tagpath, pos, end)
if (argt != None) and (len(argt) > 0) :
argList = argt.split('|')
for strval in argList:
if clean:
m = re.search(digits_only, strval)
if m != None:
strval = m.group()
argres.append(int(strval))
return argres
def process(self):
classlst = ''
csspage = '.cl-center { text-align: center; margin-left: auto; margin-right: auto; }\n'
csspage += '.cl-right { text-align: right; }\n'
csspage += '.cl-left { text-align: left; }\n'
csspage += '.cl-justify { text-align: justify; }\n'
# generate a list of each <style> starting point in the stylesheet
styleList= self.posinDoc('book.stylesheet.style')
stylecnt = len(styleList)
styleList.append(-1)
# process each style converting what you can
for j in xrange(stylecnt):
start = styleList[j]
end = styleList[j+1]
(pos, tag) = self.findinDoc('style._tag',start,end)
if tag == None :
(pos, tag) = self.findinDoc('style.type',start,end)
# Is this something we know how to convert to css
if tag in self.stags :
# get the style class
(pos, sclass) = self.findinDoc('style.class',start,end)
if sclass != None:
sclass = sclass.replace(' ','-')
sclass = '.cl-' + sclass.lower()
else :
sclass = ''
# check for any "after class" specifiers
(pos, aftclass) = self.findinDoc('style._after_class',start,end)
if aftclass != None:
aftclass = aftclass.replace(' ','-')
aftclass = '.cl-' + aftclass.lower()
else :
aftclass = ''
cssargs = {}
while True :
(pos1, attr) = self.findinDoc('style.rule.attr', start, end)
(pos2, val) = self.findinDoc('style.rule.value', start, end)
if attr == None : break
if (attr == 'display') or (attr == 'pos') or (attr == 'align'):
# handle text based attributess
attr = attr + '-' + val
if attr in self.attr_str_map :
cssargs[attr] = (self.attr_str_map[attr], '')
else :
# handle value based attributes
if attr in self.attr_val_map :
name = self.attr_val_map[attr]
if attr in ('margin-bottom', 'margin-top', 'space-after') :
scale = self.ph
elif attr in ('margin-right', 'indent', 'margin-left', 'hang') :
scale = self.pw
elif attr == 'line-space':
scale = self.fontsize * 2.0
if val == "":
val = 0
if not ((attr == 'hang') and (int(val) == 0)) :
pv = float(val)/scale
cssargs[attr] = (self.attr_val_map[attr], pv)
keep = True
start = max(pos1, pos2) + 1
# disable all of the after class tags until I figure out how to handle them
if aftclass != "" : keep = False
if keep :
# make sure line-space does not go below 100% or above 300% since
# it can be wacky in some styles
if 'line-space' in cssargs:
seg = cssargs['line-space'][0]
val = cssargs['line-space'][1]
if val < 1.0: val = 1.0
if val > 3.0: val = 3.0
del cssargs['line-space']
cssargs['line-space'] = (self.attr_val_map['line-space'], val)
# handle modifications for css style hanging indents
if 'hang' in cssargs:
hseg = cssargs['hang'][0]
hval = cssargs['hang'][1]
del cssargs['hang']
cssargs['hang'] = (self.attr_val_map['hang'], -hval)
mval = 0
mseg = 'margin-left: '
mval = hval
if 'margin-left' in cssargs:
mseg = cssargs['margin-left'][0]
mval = cssargs['margin-left'][1]
if mval < 0: mval = 0
mval = hval + mval
cssargs['margin-left'] = (mseg, mval)
if 'indent' in cssargs:
del cssargs['indent']
cssline = sclass + ' { '
for key in iter(cssargs):
mseg = cssargs[key][0]
mval = cssargs[key][1]
if mval == '':
cssline += mseg + ' '
else :
aseg = mseg + '%.1f%%;' % (mval * 100.0)
cssline += aseg + ' '
cssline += '}'
if sclass != '' :
classlst += sclass + '\n'
# handle special case of paragraph class used inside chapter heading
# and non-chapter headings
if sclass != '' :
ctype = sclass[4:7]
if ctype == 'ch1' :
csspage += 'h1' + cssline + '\n'
if ctype == 'ch2' :
csspage += 'h2' + cssline + '\n'
if ctype == 'ch3' :
csspage += 'h3' + cssline + '\n'
if ctype == 'h1-' :
csspage += 'h4' + cssline + '\n'
if ctype == 'h2-' :
csspage += 'h5' + cssline + '\n'
if ctype == 'h3_' :
csspage += 'h6' + cssline + '\n'
if cssline != ' { }':
csspage += self.stags[tag] + cssline + '\n'
return csspage, classlst
def convert2CSS(flatxml, fontsize, ph, pw):
print ' ', 'Using font size:',fontsize
print ' ', 'Using page height:', ph
print ' ', 'Using page width:', pw
# create a document parser
dp = DocParser(flatxml, fontsize, ph, pw)
csspage = dp.process()
return csspage
def getpageIDMap(flatxml):
dp = DocParser(flatxml, 0, 0, 0)
pageidnumbers = dp.getData('info.original.pid', 0, -1, True)
return pageidnumbers

148
Other_Tools/KindleBooks/lib/subasyncio.py
View File

@@ -1,148 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import os, sys
import signal
import threading
import subprocess
from subprocess import Popen, PIPE, STDOUT
# **heavily** chopped up and modfied version of asyncproc.py
# to make it actually work on Windows as well as Mac/Linux
# For the original see:
# "http://www.lysator.liu.se/~bellman/download/"
# author is "Thomas Bellman <bellman@lysator.liu.se>"
# available under GPL version 3 or Later
# create an asynchronous subprocess whose output can be collected in
# a non-blocking manner
# What a mess! Have to use threads just to get non-blocking io
# in a cross-platform manner
# luckily all thread use is hidden within this class
class Process(object):
def __init__(self, *params, **kwparams):
if len(params) <= 3:
kwparams.setdefault('stdin', subprocess.PIPE)
if len(params) <= 4:
kwparams.setdefault('stdout', subprocess.PIPE)
if len(params) <= 5:
kwparams.setdefault('stderr', subprocess.PIPE)
self.__pending_input = []
self.__collected_outdata = []
self.__collected_errdata = []
self.__exitstatus = None
self.__lock = threading.Lock()
self.__inputsem = threading.Semaphore(0)
self.__quit = False
self.__process = subprocess.Popen(*params, **kwparams)
if self.__process.stdin:
self.__stdin_thread = threading.Thread(
name="stdin-thread",
target=self.__feeder, args=(self.__pending_input,
self.__process.stdin))
self.__stdin_thread.setDaemon(True)
self.__stdin_thread.start()
if self.__process.stdout:
self.__stdout_thread = threading.Thread(
name="stdout-thread",
target=self.__reader, args=(self.__collected_outdata,
self.__process.stdout))
self.__stdout_thread.setDaemon(True)
self.__stdout_thread.start()
if self.__process.stderr:
self.__stderr_thread = threading.Thread(
name="stderr-thread",
target=self.__reader, args=(self.__collected_errdata,
self.__process.stderr))
self.__stderr_thread.setDaemon(True)
self.__stderr_thread.start()
def pid(self):
return self.__process.pid
def kill(self, signal):
self.__process.send_signal(signal)
# check on subprocess (pass in 'nowait') to act like poll
def wait(self, flag):
if flag.lower() == 'nowait':
rc = self.__process.poll()
else:
rc = self.__process.wait()
if rc != None:
if self.__process.stdin:
self.closeinput()
if self.__process.stdout:
self.__stdout_thread.join()
if self.__process.stderr:
self.__stderr_thread.join()
return self.__process.returncode
def terminate(self):
if self.__process.stdin:
self.closeinput()
self.__process.terminate()
# thread gets data from subprocess stdout
def __reader(self, collector, source):
while True:
data = os.read(source.fileno(), 65536)
self.__lock.acquire()
collector.append(data)
self.__lock.release()
if data == "":
source.close()
break
return
# thread feeds data to subprocess stdin
def __feeder(self, pending, drain):
while True:
self.__inputsem.acquire()
self.__lock.acquire()
if not pending and self.__quit:
drain.close()
self.__lock.release()
break
data = pending.pop(0)
self.__lock.release()
drain.write(data)
# non-blocking read of data from subprocess stdout
def read(self):
self.__lock.acquire()
outdata = "".join(self.__collected_outdata)
del self.__collected_outdata[:]
self.__lock.release()
return outdata
# non-blocking read of data from subprocess stderr
def readerr(self):
self.__lock.acquire()
errdata = "".join(self.__collected_errdata)
del self.__collected_errdata[:]
self.__lock.release()
return errdata
# non-blocking write to stdin of subprocess
def write(self, data):
if self.__process.stdin is None:
raise ValueError("Writing to process with stdin not a pipe")
self.__lock.acquire()
self.__pending_input.append(data)
self.__inputsem.release()
self.__lock.release()
# close stdinput of subprocess
def closeinput(self):
self.__lock.acquire()
self.__quit = True
self.__inputsem.release()
self.__lock.release()

482
Other_Tools/KindleBooks/lib/topazextract.py
View File

@@ -1,482 +0,0 @@
#!/usr/bin/env python
class Unbuffered:
def __init__(self, stream):
self.stream = stream
def write(self, data):
self.stream.write(data)
self.stream.flush()
def __getattr__(self, attr):
return getattr(self.stream, attr)
import sys
if 'calibre' in sys.modules:
inCalibre = True
else:
inCalibre = False
buildXML = False
import os, csv, getopt
import zlib, zipfile, tempfile, shutil
from struct import pack
from struct import unpack
from alfcrypto import Topaz_Cipher
class TpzDRMError(Exception):
pass
# local support routines
if inCalibre:
from calibre_plugins.k4mobidedrm import kgenpids
else:
import kgenpids
# recursive zip creation support routine
def zipUpDir(myzip, tdir, localname):
currentdir = tdir
if localname != "":
currentdir = os.path.join(currentdir,localname)
list = os.listdir(currentdir)
for file in list:
afilename = file
localfilePath = os.path.join(localname, afilename)
realfilePath = os.path.join(currentdir,file)
if os.path.isfile(realfilePath):
myzip.write(realfilePath, localfilePath)
elif os.path.isdir(realfilePath):
zipUpDir(myzip, tdir, localfilePath)
#
# Utility routines
#
# Get a 7 bit encoded number from file
def bookReadEncodedNumber(fo):
flag = False
data = ord(fo.read(1))
if data == 0xFF:
flag = True
data = ord(fo.read(1))
if data >= 0x80:
datax = (data & 0x7F)
while data >= 0x80 :
data = ord(fo.read(1))
datax = (datax <<7) + (data & 0x7F)
data = datax
if flag:
data = -data
return data
# Get a length prefixed string from file
def bookReadString(fo):
stringLength = bookReadEncodedNumber(fo)
return unpack(str(stringLength)+"s",fo.read(stringLength))[0]
#
# crypto routines
#
# Context initialisation for the Topaz Crypto
def topazCryptoInit(key):
return Topaz_Cipher().ctx_init(key)
# ctx1 = 0x0CAFFE19E
# for keyChar in key:
# keyByte = ord(keyChar)
# ctx2 = ctx1
# ctx1 = ((((ctx1 >>2) * (ctx1 >>7))&0xFFFFFFFF) ^ (keyByte * keyByte * 0x0F902007)& 0xFFFFFFFF )
# return [ctx1,ctx2]
# decrypt data with the context prepared by topazCryptoInit()
def topazCryptoDecrypt(data, ctx):
return Topaz_Cipher().decrypt(data, ctx)
# ctx1 = ctx[0]
# ctx2 = ctx[1]
# plainText = ""
# for dataChar in data:
# dataByte = ord(dataChar)
# m = (dataByte ^ ((ctx1 >> 3) &0xFF) ^ ((ctx2<<3) & 0xFF)) &0xFF
# ctx2 = ctx1
# ctx1 = (((ctx1 >> 2) * (ctx1 >> 7)) &0xFFFFFFFF) ^((m * m * 0x0F902007) &0xFFFFFFFF)
# plainText += chr(m)
# return plainText
# Decrypt data with the PID
def decryptRecord(data,PID):
ctx = topazCryptoInit(PID)
return topazCryptoDecrypt(data, ctx)
# Try to decrypt a dkey record (contains the bookPID)
def decryptDkeyRecord(data,PID):
record = decryptRecord(data,PID)
fields = unpack("3sB8sB8s3s",record)
if fields[0] != "PID" or fields[5] != "pid" :
raise TpzDRMError("Didn't find PID magic numbers in record")
elif fields[1] != 8 or fields[3] != 8 :
raise TpzDRMError("Record didn't contain correct length fields")
elif fields[2] != PID :
raise TpzDRMError("Record didn't contain PID")
return fields[4]
# Decrypt all dkey records (contain the book PID)
def decryptDkeyRecords(data,PID):
nbKeyRecords = ord(data[0])
records = []
data = data[1:]
for i in range (0,nbKeyRecords):
length = ord(data[0])
try:
key = decryptDkeyRecord(data[1:length+1],PID)
records.append(key)
except TpzDRMError:
pass
data = data[1+length:]
if len(records) == 0:
raise TpzDRMError("BookKey Not Found")
return records
class TopazBook:
def __init__(self, filename):
self.fo = file(filename, 'rb')
self.outdir = tempfile.mkdtemp()
# self.outdir = 'rawdat'
self.bookPayloadOffset = 0
self.bookHeaderRecords = {}
self.bookMetadata = {}
self.bookKey = None
magic = unpack("4s",self.fo.read(4))[0]
if magic != 'TPZ0':
raise TpzDRMError("Parse Error : Invalid Header, not a Topaz file")
self.parseTopazHeaders()
self.parseMetadata()
def parseTopazHeaders(self):
def bookReadHeaderRecordData():
# Read and return the data of one header record at the current book file position
# [[offset,decompressedLength,compressedLength],...]
nbValues = bookReadEncodedNumber(self.fo)
values = []
for i in range (0,nbValues):
values.append([bookReadEncodedNumber(self.fo),bookReadEncodedNumber(self.fo),bookReadEncodedNumber(self.fo)])
return values
def parseTopazHeaderRecord():
# Read and parse one header record at the current book file position and return the associated data
# [[offset,decompressedLength,compressedLength],...]
if ord(self.fo.read(1)) != 0x63:
raise TpzDRMError("Parse Error : Invalid Header")
tag = bookReadString(self.fo)
record = bookReadHeaderRecordData()
return [tag,record]
nbRecords = bookReadEncodedNumber(self.fo)
for i in range (0,nbRecords):
result = parseTopazHeaderRecord()
# print result[0], result[1]
self.bookHeaderRecords[result[0]] = result[1]
if ord(self.fo.read(1)) != 0x64 :
raise TpzDRMError("Parse Error : Invalid Header")
self.bookPayloadOffset = self.fo.tell()
def parseMetadata(self):
# Parse the metadata record from the book payload and return a list of [key,values]
self.fo.seek(self.bookPayloadOffset + self.bookHeaderRecords["metadata"][0][0])
tag = bookReadString(self.fo)
if tag != "metadata" :
raise TpzDRMError("Parse Error : Record Names Don't Match")
flags = ord(self.fo.read(1))
nbRecords = ord(self.fo.read(1))
# print nbRecords
for i in range (0,nbRecords) :
keyval = bookReadString(self.fo)
content = bookReadString(self.fo)
# print keyval
# print content
self.bookMetadata[keyval] = content
return self.bookMetadata
def getPIDMetaInfo(self):
keysRecord = self.bookMetadata.get('keys','')
keysRecordRecord = ''
if keysRecord != '':
keylst = keysRecord.split(',')
for keyval in keylst:
keysRecordRecord += self.bookMetadata.get(keyval,'')
return keysRecord, keysRecordRecord
def getBookTitle(self):
title = ''
if 'Title' in self.bookMetadata:
title = self.bookMetadata['Title']
return title
def setBookKey(self, key):
self.bookKey = key
def getBookPayloadRecord(self, name, index):
# Get a record in the book payload, given its name and index.
# decrypted and decompressed if necessary
encrypted = False
compressed = False
try:
recordOffset = self.bookHeaderRecords[name][index][0]
except:
raise TpzDRMError("Parse Error : Invalid Record, record not found")
self.fo.seek(self.bookPayloadOffset + recordOffset)
tag = bookReadString(self.fo)
if tag != name :
raise TpzDRMError("Parse Error : Invalid Record, record name doesn't match")
recordIndex = bookReadEncodedNumber(self.fo)
if recordIndex < 0 :
encrypted = True
recordIndex = -recordIndex -1
if recordIndex != index :
raise TpzDRMError("Parse Error : Invalid Record, index doesn't match")
if (self.bookHeaderRecords[name][index][2] > 0):
compressed = True
record = self.fo.read(self.bookHeaderRecords[name][index][2])
else:
record = self.fo.read(self.bookHeaderRecords[name][index][1])
if encrypted:
if self.bookKey:
ctx = topazCryptoInit(self.bookKey)
record = topazCryptoDecrypt(record,ctx)
else :
raise TpzDRMError("Error: Attempt to decrypt without bookKey")
if compressed:
record = zlib.decompress(record)
return record
def processBook(self, pidlst):
raw = 0
fixedimage=True
try:
keydata = self.getBookPayloadRecord('dkey', 0)
except TpzDRMError, e:
print "no dkey record found, book may not be encrypted"
print "attempting to extrct files without a book key"
self.createBookDirectory()
self.extractFiles()
print "Successfully Extracted Topaz contents"
if inCalibre:
from calibre_plugins.k4mobidedrm import genbook
else:
import genbook
rv = genbook.generateBook(self.outdir, raw, fixedimage)
if rv == 0:
print "\nBook Successfully generated"
return rv
# try each pid to decode the file
bookKey = None
for pid in pidlst:
# use 8 digit pids here
pid = pid[0:8]
print "\nTrying: ", pid
bookKeys = []
data = keydata
try:
bookKeys+=decryptDkeyRecords(data,pid)
except TpzDRMError, e:
pass
else:
bookKey = bookKeys[0]
print "Book Key Found!"
break
if not bookKey:
raise TpzDRMError("Topaz Book. No key found in " + str(len(pidlst)) + " keys tried. Read the FAQs at Alf's blog. Only if none apply, report this failure for help.")
self.setBookKey(bookKey)
self.createBookDirectory()
self.extractFiles()
print "Successfully Extracted Topaz contents"
if inCalibre:
from calibre_plugins.k4mobidedrm import genbook
else:
import genbook
rv = genbook.generateBook(self.outdir, raw, fixedimage)
if rv == 0:
print "\nBook Successfully generated"
return rv
def createBookDirectory(self):
outdir = self.outdir
# create output directory structure
if not os.path.exists(outdir):
os.makedirs(outdir)
destdir = os.path.join(outdir,'img')
if not os.path.exists(destdir):
os.makedirs(destdir)
destdir = os.path.join(outdir,'color_img')
if not os.path.exists(destdir):
os.makedirs(destdir)
destdir = os.path.join(outdir,'page')
if not os.path.exists(destdir):
os.makedirs(destdir)
destdir = os.path.join(outdir,'glyphs')
if not os.path.exists(destdir):
os.makedirs(destdir)
def extractFiles(self):
outdir = self.outdir
for headerRecord in self.bookHeaderRecords:
name = headerRecord
if name != "dkey" :
ext = '.dat'
if name == 'img' : ext = '.jpg'
if name == 'color' : ext = '.jpg'
print "\nProcessing Section: %s " % name
for index in range (0,len(self.bookHeaderRecords[name])) :
fnum = "%04d" % index
fname = name + fnum + ext
destdir = outdir
if name == 'img':
destdir = os.path.join(outdir,'img')
if name == 'color':
destdir = os.path.join(outdir,'color_img')
if name == 'page':
destdir = os.path.join(outdir,'page')
if name == 'glyphs':
destdir = os.path.join(outdir,'glyphs')
outputFile = os.path.join(destdir,fname)
print ".",
record = self.getBookPayloadRecord(name,index)
if record != '':
file(outputFile, 'wb').write(record)
print " "
def getHTMLZip(self, zipname):
htmlzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
htmlzip.write(os.path.join(self.outdir,'book.html'),'book.html')
htmlzip.write(os.path.join(self.outdir,'book.opf'),'book.opf')
if os.path.isfile(os.path.join(self.outdir,'cover.jpg')):
htmlzip.write(os.path.join(self.outdir,'cover.jpg'),'cover.jpg')
htmlzip.write(os.path.join(self.outdir,'style.css'),'style.css')
zipUpDir(htmlzip, self.outdir, 'img')
htmlzip.close()
def getSVGZip(self, zipname):
svgzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
svgzip.write(os.path.join(self.outdir,'index_svg.xhtml'),'index_svg.xhtml')
zipUpDir(svgzip, self.outdir, 'svg')
zipUpDir(svgzip, self.outdir, 'img')
svgzip.close()
def getXMLZip(self, zipname):
xmlzip = zipfile.ZipFile(zipname,'w',zipfile.ZIP_DEFLATED, False)
targetdir = os.path.join(self.outdir,'xml')
zipUpDir(xmlzip, targetdir, '')
zipUpDir(xmlzip, self.outdir, 'img')
xmlzip.close()
def cleanup(self):
if os.path.isdir(self.outdir):
shutil.rmtree(self.outdir, True)
def usage(progname):
print "Removes DRM protection from Topaz ebooks and extract the contents"
print "Usage:"
print " %s [-k <kindle.info>] [-p <pidnums>] [-s <kindleSerialNumbers>] <infile> <outdir> " % progname
# Main
def main(argv=sys.argv):
global buildXML
progname = os.path.basename(argv[0])
k4 = False
pids = []
serials = []
kInfoFiles = []
try:
opts, args = getopt.getopt(sys.argv[1:], "k:p:s:")
except getopt.GetoptError, err:
print str(err)
usage(progname)
return 1
if len(args)<2:
usage(progname)
return 1
for o, a in opts:
if o == "-k":
if a == None :
print "Invalid parameter for -k"
return 1
kInfoFiles.append(a)
if o == "-p":
if a == None :
print "Invalid parameter for -p"
return 1
pids = a.split(',')
if o == "-s":
if a == None :
print "Invalid parameter for -s"
return 1
serials = a.split(',')
k4 = True
infile = args[0]
outdir = args[1]
if not os.path.isfile(infile):
print "Input File Does Not Exist"
return 1
bookname = os.path.splitext(os.path.basename(infile))[0]
tb = TopazBook(infile)
title = tb.getBookTitle()
print "Processing Book: ", title
keysRecord, keysRecordRecord = tb.getPIDMetaInfo()
pids.extend(kgenpids.getPidList(keysRecord, keysRecordRecord, k4, serials, kInfoFiles))
try:
print "Decrypting Book"
tb.processBook(pids)
print " Creating HTML ZIP Archive"
zipname = os.path.join(outdir, bookname + '_nodrm' + '.htmlz')
tb.getHTMLZip(zipname)
print " Creating SVG ZIP Archive"
zipname = os.path.join(outdir, bookname + '_SVG' + '.zip')
tb.getSVGZip(zipname)
if buildXML:
print " Creating XML ZIP Archive"
zipname = os.path.join(outdir, bookname + '_XML' + '.zip')
tb.getXMLZip(zipname)
# removing internal temporary directory of pieces
tb.cleanup()
except TpzDRMError, e:
print str(e)
# tb.cleanup()
return 1
except Exception, e:
print str(e)
# tb.cleanup
return 1
return 0
if __name__ == '__main__':
sys.stdout=Unbuffered(sys.stdout)
sys.exit(main())

37
Other_Tools/README_Kindle_for_iPad_iPhone_iPodTouch.txt
View File

@@ -1,37 +0,0 @@
Kindle for iPhone, iPod Touch, iPad
------------------------------------
The Kindle application for iOS (iPhone/iPod Touch/iPad) uses a PID derived from the UDID number of the iPhone/iPod Touch/iPad. Kindlepid.pyw (see Other_Tools/Additional_Tools) is a python script that turns the serial number into the equivalent PID, which can then be used with the Calibre Plugins and DeDRM Applications.
So, to remove the DRM from (Mobipocket) Kindle books downloaded to your iPhone/iPodTouch/iPad, you’ll need the latest tools_vX.X.zip archive and
some way to extract the book files from the backup of your device on your computer. There are several free tools around to do this.
Your first step is to download and install one of the free apps onto your iPod Touch/iPhone/iPad that will find your devices's UUID. Alternatively, you can find your device's UDID in iTunes when your device is connected in the Summary page – click on the serial number and it changes to the (40 digit!) UDID.
Once you have the UUID, double-click on KindlePID.pyw to get your device’s PID.
You should get back a response something like:
Mobipocket PID calculator for Amazon Kindle. Copyright (c) 2007, 2009 Igor Skochinsky
iPhone serial number (UDID) detected
Mobipocked PID for iPhone serial# FOURTYDIGITUDIDNUMBERGIVENHERE is TENDIGITPID
You can then add this fixed PID to the DeDRM Applications or Calibre_Plugins or KindleBooks tools and be ready to go.
You next need to find an "iPhone Extractor" or "iPhone Explorer" program for your OS that will allow you to mount your iPhone/iPad/iPod Touch as a usb device on your machine and copy your Kindle ebooks from the device back to your home machine.
IMPORTANT UPDATE
----------------
Apple has recently (2012) restricted access to a device's UDID. This means that recent (2012+) versions of Kindle for iOS no longer use this method of generating an encryption key. If you had already installed and registered Kindle for iOS before this change, the key based on your device's UDID will continue to be used. Otherwise, it is not currently (2012) possible to remove the DRM of Kindle eBooks from a newly installed and registered copy of Kindle for iOS.
---
Kindlefix gives you another way to use the PID generated by kindlepid. Some ebook stores and libraries will accept the PIDs generated by kindlepid (some won’t), and you can then download ebooks from the store or library encrypted to work with your Kindle. Except they don’t. There’s a flag byte set in encrypted Kindle ebooks, and Kindles and the Kindle app won’t read encrypted mobipocket ebooks unless that flag is set. Kindlefix will set that flag for you. If your library have Mobipocket ebooks to lend and will accept your Kindle’s PID, you can now check out library ebooks, run kindlefix on them, and then read them on your Kindle, and when your loan period ends, they’ll automatically become unreadable.
(2012 note: Few, if any, libraries now use this method of loaning ebooks.)

BIN
Other_Tools/Scuolabook_DRM/Scuolabook+DRM+Remover+1.0.zip Normal file
View File

Binary file not shown.

BIN
Other_Tools/Scuolabook_DRM/Scuolabook_DRM_Remover_source_19_11_2012.zip Normal file
View File

Binary file not shown.

10
Other_Tools/Scuolabook_DRM/Scuolabook_ReadMe.txt Normal file
View File

@@ -0,0 +1,10 @@
How-to:
1) Make sure you can read all PDF files on Scuolabook Reader.
2) Run Scuolabook DRM Remover.
3) Get your free books from the directory where you started the program.
Note:
It is recommended to use Scuolabook version 2.0.1 and refuse all updates
because the encryption algorithm may change making this tool useless.
Hex

17
Other_Tools/ePub_Fixer/README_ePub_Fixer.txt
View File

@@ -1,17 +0,0 @@
ePub_Fixer
ePubs are specially crafted zip archives. Unfortunately, many of the DRM encoded Adobe Adept and Barnes & Noble ePubs are not "proper" zip archives in that the names of some files in the zip central directory do NOT match the local name given in archive itself. This type of zip archive is technically incorrect/corrupted and can not be read by many other programs.
ePub_Fixer was designed to fix improperly created zip archives of this type.
1. Simply double-click to launch ePub_Fixer.pyw.
2. use the first "..." button to select the ePub (with DRM) that needs to be fixed
3. use the second "..." button to select where you want the fixed ePub (still with DRM!) to be placed.
4. Hit the start button.
Once the program has successfully completed, you can now feed the fixed ePubs into other programs such as DRM removal programs like ignobleepub.pyw and ineptepub.pyw.

196
Other_Tools/ePub_Fixer/ePub_Fixer.pyw
View File

@@ -1,196 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import sys
sys.path.append('lib')
import os, os.path, urllib
os.environ['PYTHONIOENCODING'] = "utf-8"
import subprocess
from subprocess import Popen, PIPE, STDOUT
import subasyncio
from subasyncio import Process
import Tkinter
import Tkconstants
import tkFileDialog
import tkMessageBox
from scrolltextwidget import ScrolledText
class MainDialog(Tkinter.Frame):
def __init__(self, root):
Tkinter.Frame.__init__(self, root, border=5)
self.root = root
self.interval = 2000
self.p2 = None
self.status = Tkinter.Label(self, text='Fix Improper ePubs')
self.status.pack(fill=Tkconstants.X, expand=1)
body = Tkinter.Frame(self)
body.pack(fill=Tkconstants.X, expand=1)
sticky = Tkconstants.E + Tkconstants.W
body.grid_columnconfigure(1, weight=2)
Tkinter.Label(body, text='ePub input file').grid(row=0, sticky=Tkconstants.E)
self.epubpath = Tkinter.Entry(body, width=50)
self.epubpath.grid(row=0, column=1, sticky=sticky)
cwd = os.getcwdu()
cwd = cwd.encode('utf-8')
self.epubpath.insert(0, cwd)
button = Tkinter.Button(body, text="...", command=self.get_epubpath)
button.grid(row=0, column=2)
Tkinter.Label(body, text='Directory to store fixed ePub in').grid(row=1, sticky=Tkconstants.E)
self.outpath = Tkinter.Entry(body, width=50)
self.outpath.grid(row=1, column=1, sticky=sticky)
cwd = os.getcwdu()
cwd = cwd.encode('utf-8')
outname = cwd
self.outpath.insert(0, outname)
button = Tkinter.Button(body, text="...", command=self.get_outpath)
button.grid(row=1, column=2)
msg1 = 'Log \n\n'
self.stext = ScrolledText(body, bd=5, relief=Tkconstants.RIDGE, height=15, width=60, wrap=Tkconstants.WORD)
self.stext.grid(row=2, column=0, columnspan=2,sticky=sticky)
self.stext.insert(Tkconstants.END,msg1)
buttons = Tkinter.Frame(self)
buttons.pack()
self.sbotton = Tkinter.Button(
buttons, text="Start", width=10, command=self.fixit)
self.sbotton.pack(side=Tkconstants.LEFT)
Tkinter.Frame(buttons, width=10).pack(side=Tkconstants.LEFT)
self.qbutton = Tkinter.Button(
buttons, text="Quit", width=10, command=self.quitting)
self.qbutton.pack(side=Tkconstants.RIGHT)
# read from subprocess pipe without blocking
# invoked every interval via the widget "after"
# option being used, so need to reset it for the next time
def processPipe(self):
poll = self.p2.wait('nowait')
if poll != None:
text = self.p2.readerr()
text += self.p2.read()
msg = text + '\n\n' + 'ePub successfully fixed\n'
if poll != 0:
msg = text + '\n\n' + 'Error: ePub Fixing Failed\n'
self.showCmdOutput(msg)
self.p2 = None
self.sbotton.configure(state='normal')
return
text = self.p2.readerr()
text += self.p2.read()
self.showCmdOutput(text)
# make sure we get invoked again by event loop after interval
self.stext.after(self.interval,self.processPipe)
return
# post output from subprocess in scrolled text widget
def showCmdOutput(self, msg):
if msg and msg !='':
if sys.platform.startswith('win'):
msg = msg.replace('\r\n','\n')
self.stext.insert(Tkconstants.END,msg)
self.stext.yview_pickplace(Tkconstants.END)
return
# run as a subprocess via pipes and collect stdout
def zipfixrdr(self, infile, outfile):
# os.putenv('PYTHONUNBUFFERED', '1')
pengine = sys.executable
if pengine is None or pengine == '':
pengine = "python"
pengine = os.path.normpath(pengine)
cmdline = pengine + ' ./lib/zipfix.py "' + infile + '" "' + outfile + '"'
if sys.platform[0:3] == 'win':
# search_path = os.environ['PATH']
# search_path = search_path.lower()
# if search_path.find('python') >= 0:
# cmdline = 'python lib\zipfix.py "' + infile + '" "' + outfile + '"'
# else :
# cmdline = 'lib\zipfix.py "' + infile + '" "' + outfile + '"'
cmdline = pengine + ' lib\\zipfix.py "' + infile + '" "' + outfile + '"'
cmdline = cmdline.encode(sys.getfilesystemencoding())
p2 = Process(cmdline, shell=True, bufsize=1, stdin=None, stdout=PIPE, stderr=PIPE, close_fds=False)
return p2
def get_epubpath(self):
epubpath = tkFileDialog.askopenfilename(
parent=None, title='Select ePub to be Fixed',
defaultextension='.epub', filetypes=[('ePub eBook File', '.epub'), ('Zip File', '.zip'),('All Files', '.*')])
if epubpath:
epubpath = os.path.normpath(epubpath)
self.epubpath.delete(0, Tkconstants.END)
self.epubpath.insert(0, epubpath)
return
def get_outpath(self):
cwd = os.getcwdu()
cwd = cwd.encode('utf-8')
outpath = tkFileDialog.askdirectory(
parent=None, title='Directory to Store Fixed ePub into',
initialdir=cwd, initialfile=None)
if outpath:
outpath = os.path.normpath(outpath)
self.outpath.delete(0, Tkconstants.END)
self.outpath.insert(0, outpath)
return
def quitting(self):
# kill any still running subprocess
if self.p2 != None:
if (self.p2.wait('nowait') == None):
self.p2.terminate()
self.root.destroy()
# actually ready to run the subprocess and get its output
def fixit(self):
# now disable the button to prevent multiple launches
self.sbotton.configure(state='disabled')
epubpath = self.epubpath.get()
outpath = self.outpath.get()
if not epubpath or not os.path.exists(epubpath):
self.status['text'] = 'Specified ePub eBook file does not exist'
self.sbotton.configure(state='normal')
return
if not outpath:
self.status['text'] = 'Error specified output directory does not exist'
self.sbotton.configure(state='normal')
return
# default output file name to be input file name + '_fixed.epub'
initname = os.path.splitext(os.path.basename(epubpath))[0]
initname += '_fixed.epub'
outpath += os.sep + initname
log = 'Command = "python zipfix.py"\n'
log += 'ePub Path = "'+ epubpath + '"\n'
log += 'Output File = "' + outpath + '"\n'
log += '\n\n'
log += 'Please Wait ...\n\n'
self.stext.insert(Tkconstants.END,log)
self.p2 = self.zipfixrdr(epubpath, outpath)
# python does not seem to allow you to create
# your own eventloop which every other gui does - strange
# so need to use the widget "after" command to force
# event loop to run non-gui events every interval
self.stext.after(self.interval,self.processPipe)
return
def main(argv=None):
root = Tkinter.Tk()
root.title('Fix Incorrect ePubs')
root.resizable(True, False)
root.minsize(300, 0)
MainDialog(root).pack(fill=Tkconstants.X, expand=1)
root.mainloop()
return 0
if __name__ == "__main__":
sys.exit(main())

27
Other_Tools/ePub_Fixer/lib/scrolltextwidget.py
View File

@@ -1,27 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import Tkinter
import Tkconstants
# basic scrolled text widget
class ScrolledText(Tkinter.Text):
def __init__(self, master=None, **kw):
self.frame = Tkinter.Frame(master)
self.vbar = Tkinter.Scrollbar(self.frame)
self.vbar.pack(side=Tkconstants.RIGHT, fill=Tkconstants.Y)
kw.update({'yscrollcommand': self.vbar.set})
Tkinter.Text.__init__(self, self.frame, **kw)
self.pack(side=Tkconstants.LEFT, fill=Tkconstants.BOTH, expand=True)
self.vbar['command'] = self.yview
# Copy geometry methods of self.frame without overriding Text
# methods = hack!
text_meths = vars(Tkinter.Text).keys()
methods = vars(Tkinter.Pack).keys() + vars(Tkinter.Grid).keys() + vars(Tkinter.Place).keys()
methods = set(methods).difference(text_meths)
for m in methods:
if m[0] != '_' and m != 'config' and m != 'configure':
setattr(self, m, getattr(self.frame, m))
def __str__(self):
return str(self.frame)

149
Other_Tools/ePub_Fixer/lib/subasyncio.py
View File

@@ -1,149 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import os, sys
import signal
import threading
import subprocess
from subprocess import Popen, PIPE, STDOUT
# **heavily** chopped up and modfied version of asyncproc.py
# to make it actually work on Windows as well as Mac/Linux
# For the original see:
# "http://www.lysator.liu.se/~bellman/download/"
# author is "Thomas Bellman <bellman@lysator.liu.se>"
# available under GPL version 3 or Later
# create an asynchronous subprocess whose output can be collected in
# a non-blocking manner
# What a mess! Have to use threads just to get non-blocking io
# in a cross-platform manner
# luckily all thread use is hidden within this class
class Process(object):
def __init__(self, *params, **kwparams):
if len(params) <= 3:
kwparams.setdefault('stdin', subprocess.PIPE)
if len(params) <= 4:
kwparams.setdefault('stdout', subprocess.PIPE)
if len(params) <= 5:
kwparams.setdefault('stderr', subprocess.PIPE)
self.__pending_input = []
self.__collected_outdata = []
self.__collected_errdata = []
self.__exitstatus = None
self.__lock = threading.Lock()
self.__inputsem = threading.Semaphore(0)
self.__quit = False
self.__process = subprocess.Popen(*params, **kwparams)
if self.__process.stdin:
self.__stdin_thread = threading.Thread(
name="stdin-thread",
target=self.__feeder, args=(self.__pending_input,
self.__process.stdin))
self.__stdin_thread.setDaemon(True)
self.__stdin_thread.start()
if self.__process.stdout:
self.__stdout_thread = threading.Thread(
name="stdout-thread",
target=self.__reader, args=(self.__collected_outdata,
self.__process.stdout))
self.__stdout_thread.setDaemon(True)
self.__stdout_thread.start()
if self.__process.stderr:
self.__stderr_thread = threading.Thread(
name="stderr-thread",
target=self.__reader, args=(self.__collected_errdata,
self.__process.stderr))
self.__stderr_thread.setDaemon(True)
self.__stderr_thread.start()
def pid(self):
return self.__process.pid
def kill(self, signal):
self.__process.send_signal(signal)
# check on subprocess (pass in 'nowait') to act like poll
def wait(self, flag):
if flag.lower() == 'nowait':
rc = self.__process.poll()
else:
rc = self.__process.wait()
if rc != None:
if self.__process.stdin:
self.closeinput()
if self.__process.stdout:
self.__stdout_thread.join()
if self.__process.stderr:
self.__stderr_thread.join()
return self.__process.returncode
def terminate(self):
if self.__process.stdin:
self.closeinput()
self.__process.terminate()
# thread gets data from subprocess stdout
def __reader(self, collector, source):
while True:
data = os.read(source.fileno(), 65536)
self.__lock.acquire()
collector.append(data)
self.__lock.release()
if data == "":
source.close()
break
return
# thread feeds data to subprocess stdin
def __feeder(self, pending, drain):
while True:
self.__inputsem.acquire()
self.__lock.acquire()
if not pending and self.__quit:
drain.close()
self.__lock.release()
break
data = pending.pop(0)
self.__lock.release()
drain.write(data)
# non-blocking read of data from subprocess stdout
def read(self):
self.__lock.acquire()
outdata = "".join(self.__collected_outdata)
del self.__collected_outdata[:]
self.__lock.release()
return outdata
# non-blocking read of data from subprocess stderr
def readerr(self):
self.__lock.acquire()
errdata = "".join(self.__collected_errdata)
del self.__collected_errdata[:]
self.__lock.release()
return errdata
# non-blocking write to stdin of subprocess
def write(self, data):
if self.__process.stdin is None:
raise ValueError("Writing to process with stdin not a pipe")
self.__lock.acquire()
self.__pending_input.append(data)
self.__inputsem.release()
self.__lock.release()
# close stdinput of subprocess
def closeinput(self):
self.__lock.acquire()
self.__quit = True
self.__inputsem.release()
self.__lock.release()

1400
Other_Tools/ePub_Fixer/lib/zipfilerugged.py
View File

File diff suppressed because it is too large Load Diff

158
Other_Tools/ePub_Fixer/lib/zipfix.py
View File

@@ -1,158 +0,0 @@
#!/usr/bin/env python
import sys
import zlib
import zipfilerugged
import os
import os.path
import getopt
from struct import unpack
_FILENAME_LEN_OFFSET = 26
_EXTRA_LEN_OFFSET = 28
_FILENAME_OFFSET = 30
_MAX_SIZE = 64 * 1024
_MIMETYPE = 'application/epub+zip'
class ZipInfo(zipfilerugged.ZipInfo):
def __init__(self, *args, **kwargs):
if 'compress_type' in kwargs:
compress_type = kwargs.pop('compress_type')
super(ZipInfo, self).__init__(*args, **kwargs)
self.compress_type = compress_type
class fixZip:
def __init__(self, zinput, zoutput):
self.ztype = 'zip'
if zinput.lower().find('.epub') >= 0 :
self.ztype = 'epub'
print "opening input"
self.inzip = zipfilerugged.ZipFile(zinput,'r')
print "opening outout"
self.outzip = zipfilerugged.ZipFile(zoutput,'w')
print "opening input as raw file"
# open the input zip for reading only as a raw file
self.bzf = file(zinput,'rb')
print "finished initialising"
def getlocalname(self, zi):
local_header_offset = zi.header_offset
self.bzf.seek(local_header_offset + _FILENAME_LEN_OFFSET)
leninfo = self.bzf.read(2)
local_name_length, = unpack('<H', leninfo)
self.bzf.seek(local_header_offset + _FILENAME_OFFSET)
local_name = self.bzf.read(local_name_length)
return local_name
def uncompress(self, cmpdata):
dc = zlib.decompressobj(-15)
data = ''
while len(cmpdata) > 0:
if len(cmpdata) > _MAX_SIZE :
newdata = cmpdata[0:_MAX_SIZE]
cmpdata = cmpdata[_MAX_SIZE:]
else:
newdata = cmpdata
cmpdata = ''
newdata = dc.decompress(newdata)
unprocessed = dc.unconsumed_tail
if len(unprocessed) == 0:
newdata += dc.flush()
data += newdata
cmpdata += unprocessed
unprocessed = ''
return data
def getfiledata(self, zi):
# get file name length and exta data length to find start of file data
local_header_offset = zi.header_offset
self.bzf.seek(local_header_offset + _FILENAME_LEN_OFFSET)
leninfo = self.bzf.read(2)
local_name_length, = unpack('<H', leninfo)
self.bzf.seek(local_header_offset + _EXTRA_LEN_OFFSET)
exinfo = self.bzf.read(2)
extra_field_length, = unpack('<H', exinfo)
self.bzf.seek(local_header_offset + _FILENAME_OFFSET + local_name_length + extra_field_length)
data = None
# if not compressed we are good to go
if zi.compress_type == zipfilerugged.ZIP_STORED:
data = self.bzf.read(zi.file_size)
# if compressed we must decompress it using zlib
if zi.compress_type == zipfilerugged.ZIP_DEFLATED:
cmpdata = self.bzf.read(zi.compress_size)
data = self.uncompress(cmpdata)
return data
def fix(self):
# get the zipinfo for each member of the input archive
# and copy member over to output archive
# if problems exist with local vs central filename, fix them
# if epub write mimetype file first, with no compression
if self.ztype == 'epub':
nzinfo = ZipInfo('mimetype', compress_type=zipfilerugged.ZIP_STORED)
self.outzip.writestr(nzinfo, _MIMETYPE)
# write the rest of the files
for zinfo in self.inzip.infolist():
if zinfo.filename != "mimetype" or self.ztype == '.zip':
data = None
nzinfo = zinfo
try:
data = self.inzip.read(zinfo.filename)
except zipfilerugged.BadZipfile or zipfilerugged.error:
local_name = self.getlocalname(zinfo)
data = self.getfiledata(zinfo)
nzinfo.filename = local_name
nzinfo.date_time = zinfo.date_time
nzinfo.compress_type = zinfo.compress_type
nzinfo.flag_bits = 0
nzinfo.internal_attr = 0
self.outzip.writestr(nzinfo,data)
self.bzf.close()
self.inzip.close()
self.outzip.close()
def usage():
print """usage: zipfix.py inputzip outputzip
inputzip is the source zipfile to fix
outputzip is the fixed zip archive
"""
def repairBook(infile, outfile):
if not os.path.exists(infile):
print "Error: Input Zip File does not exist"
return 1
try:
fr = fixZip(infile, outfile)
fr.fix()
return 0
except Exception, e:
print "Error Occurred ", e
return 2
def main(argv=sys.argv):
if len(argv)!=3:
usage()
return 1
infile = argv[1]
outfile = argv[2]
return repairBook(infile, outfile)
if __name__ == '__main__' :
sys.exit(main())

192
Other_Tools/eReader_PDB_Tools/Pml2HTML.pyw
View File

@@ -1,192 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import sys
sys.path.append('lib')
import os, os.path, urllib
os.environ['PYTHONIOENCODING'] = "utf-8"
import subprocess
from subprocess import Popen, PIPE, STDOUT
import subasyncio
from subasyncio import Process
import Tkinter
import Tkconstants
import tkFileDialog
import tkMessageBox
from scrolltextwidget import ScrolledText
class MainDialog(Tkinter.Frame):
def __init__(self, root):
Tkinter.Frame.__init__(self, root, border=5)
self.root = root
self.interval = 2000
self.p2 = None
self.status = Tkinter.Label(self, text='Pml to HTML Conversion')
self.status.pack(fill=Tkconstants.X, expand=1)
body = Tkinter.Frame(self)
body.pack(fill=Tkconstants.X, expand=1)
sticky = Tkconstants.E + Tkconstants.W
body.grid_columnconfigure(1, weight=2)
Tkinter.Label(body, text='eBook Pml input file').grid(row=0, sticky=Tkconstants.E)
self.pmlpath = Tkinter.Entry(body, width=50)
self.pmlpath.grid(row=0, column=1, sticky=sticky)
cwd = os.getcwdu()
cwd = cwd.encode('utf-8')
self.pmlpath.insert(0, cwd)
button = Tkinter.Button(body, text="...", command=self.get_pmlpath)
button.grid(row=0, column=2)
Tkinter.Label(body, text='Name for HTML Output File').grid(row=1, sticky=Tkconstants.E)
self.outpath = Tkinter.Entry(body, width=50)
self.outpath.grid(row=1, column=1, sticky=sticky)
self.outpath.insert(0, '')
button = Tkinter.Button(body, text="...", command=self.get_outpath)
button.grid(row=1, column=2)
msg1 = 'Conversion Log \n\n'
self.stext = ScrolledText(body, bd=5, relief=Tkconstants.RIDGE, height=15, width=60, wrap=Tkconstants.WORD)
self.stext.grid(row=2, column=0, columnspan=2,sticky=sticky)
self.stext.insert(Tkconstants.END,msg1)
buttons = Tkinter.Frame(self)
buttons.pack()
self.sbotton = Tkinter.Button(
buttons, text="Start", width=10, command=self.convertit)
self.sbotton.pack(side=Tkconstants.LEFT)
Tkinter.Frame(buttons, width=10).pack(side=Tkconstants.LEFT)
self.qbutton = Tkinter.Button(
buttons, text="Quit", width=10, command=self.quitting)
self.qbutton.pack(side=Tkconstants.RIGHT)
# read from subprocess pipe without blocking
# invoked every interval via the widget "after"
# option being used, so need to reset it for the next time
def processPipe(self):
poll = self.p2.wait('nowait')
if poll != None:
text = self.p2.readerr()
text += self.p2.read()
msg = text + '\n\n' + 'File successfully converted\n'
if poll != 0:
msg = text + '\n\n' + 'Error: Conversion Failed\n'
self.showCmdOutput(msg)
self.p2 = None
self.sbotton.configure(state='normal')
return
text = self.p2.readerr()
text += self.p2.read()
self.showCmdOutput(text)
# make sure we get invoked again by event loop after interval
self.stext.after(self.interval,self.processPipe)
return
# post output from subprocess in scrolled text widget
def showCmdOutput(self, msg):
if msg and msg !='':
if sys.platform.startswith('win'):
msg = msg.replace('\r\n','\n')
self.stext.insert(Tkconstants.END,msg)
self.stext.yview_pickplace(Tkconstants.END)
return
# run xpml2hxtml.py as a subprocess via pipes and collect stdout
def pmlhtml(self, infile, outfile):
# os.putenv('PYTHONUNBUFFERED', '1')
pengine = sys.executable
if pengine is None or pengine == '':
pengine = "python"
pengine = os.path.normpath(pengine)
cmdline = pengine + ' ./lib/xpml2xhtml.py "' + infile + '" "' + outfile + '"'
if sys.platform[0:3] == 'win':
# search_path = os.environ['PATH']
# search_path = search_path.lower()
# if search_path.find('python') >= 0:
# cmdline = 'python lib\\xpml2xhtml.py "' + infile + '" "' + outfile + '"'
# else :
# cmdline = 'lib\\xpml2xhtml.py "' + infile + '" "' + outfile + '"'
cmdline = pengine + ' lib\\xpml2xhtml.py "' + infile + '" "' + outfile + '"'
cmdline = cmdline.encode(sys.getfilesystemencoding())
p2 = Process(cmdline, shell=True, bufsize=1, stdin=None, stdout=PIPE, stderr=PIPE, close_fds=False)
return p2
def get_pmlpath(self):
pmlpath = tkFileDialog.askopenfilename(
parent=None, title='Select eBook Pml File',
defaultextension='.pml', filetypes=[('eBook Pml File', '.pml'),
('All Files', '.*')])
if pmlpath:
pmlpath = os.path.normpath(pmlpath)
self.pmlpath.delete(0, Tkconstants.END)
self.pmlpath.insert(0, pmlpath)
return
def get_outpath(self):
pmlpath = self.pmlpath.get()
initname = os.path.basename(pmlpath)
p = initname.find('.')
if p >= 0: initname = initname[0:p]
initname += '.html'
outpath = tkFileDialog.asksaveasfilename(
parent=None, title='Select HTML file to produce',
defaultextension='.html', initialfile=initname,
filetypes=[('HTML files', '.html'), ('All files', '.*')])
if outpath:
outpath = os.path.normpath(outpath)
self.outpath.delete(0, Tkconstants.END)
self.outpath.insert(0, outpath)
return
def quitting(self):
# kill any still running subprocess
if self.p2 != None:
if (self.p2.wait('nowait') == None):
self.p2.terminate()
self.root.destroy()
# actually ready to run the subprocess and get its output
def convertit(self):
# now disable the button to prevent multiple launches
self.sbotton.configure(state='disabled')
pmlpath = self.pmlpath.get()
outpath = self.outpath.get()
if not pmlpath or not os.path.exists(pmlpath):
self.status['text'] = 'Specified eBook pml file does not exist'
self.sbotton.configure(state='normal')
return
if not outpath:
self.status['text'] = 'No output file specified'
self.sbotton.configure(state='normal')
return
log = 'Command = "python xpml2xhtml.py"\n'
log += 'PDB Path = "'+ pmlpath + '"\n'
log += 'HTML Output File = "' + outpath + '"\n'
log += '\n\n'
log += 'Please Wait ...\n\n'
self.stext.insert(Tkconstants.END,log)
self.p2 = self.pmlhtml(pmlpath, outpath)
# python does not seem to allow you to create
# your own eventloop which every other gui does - strange
# so need to use the widget "after" command to force
# event loop to run non-gui events every interval
self.stext.after(self.interval,self.processPipe)
return
def main(argv=None):
root = Tkinter.Tk()
root.title('eBook Pml to HTML Conversion')
root.resizable(True, False)
root.minsize(300, 0)
MainDialog(root).pack(fill=Tkconstants.X, expand=1)
root.mainloop()
return 0
if __name__ == "__main__":
sys.exit(main())

21
Other_Tools/eReader_PDB_Tools/README_eReaderPDB.txt
View File

@@ -1,21 +0,0 @@
From Apprentice Alf's Blog
Barnes & Noble/Fictionwise eReader, .pdb
Barnes & Noble’s .pdb eReader format is one of the survivors from the early days of ebooks. Internally, text is marked up in PML – Palm Markup Language. This makes conversion to other formats more difficult.
Barnes and Noble .pdb ebooks use a form of Social DRM which requires information on your Credit Card Number (last 8 digits only) and the Name on the Credit card to unencrypt the book that was purchased with that credit card.
There are three scripts used to decrypt and convert eReader ebooks.
The first, eReaderPDB2PML.pyw removes the DRM and extracts the PML and images from the ebook into a folder. It’s then possible to use the free DropBook (available for Mac or Windows) to compile the PML back into a DRM-free eReader file.
The second script, Pml2HTML.pyw, converts the PML file extracted by the first script into xhtml, which can then be converted into your preferred ebook format with a variety of tools.
The last script is eReaderPDB2PMLZ.pyw and it removes the DRM and extracts the PML and images from the ebook into a zip archive that can be directly imported into Calibre.
All of these scripts are gui python programs. Python 2.5 or later (32 bit) is already installed in Mac OSX 10.5 and later. We recommend ActiveState's Active Python Version 2.5 or later (32 bit) for Windows users.
Simply double-click to launch these applications and follow along.

215
Other_Tools/eReader_PDB_Tools/eReaderPDB2PML.pyw
View File

@@ -1,215 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import sys
sys.path.append('lib')
import os, os.path, urllib
os.environ['PYTHONIOENCODING'] = "utf-8"
import subprocess
from subprocess import Popen, PIPE, STDOUT
import Tkinter
import Tkconstants
import tkFileDialog
import tkMessageBox
import subasyncio
from subasyncio import Process
from scrolltextwidget import ScrolledText
class MainDialog(Tkinter.Frame):
def __init__(self, root):
Tkinter.Frame.__init__(self, root, border=5)
self.root = root
self.interval = 2000
self.p2 = None
self.status = Tkinter.Label(self, text='eReader eBook Conversion')
self.status.pack(fill=Tkconstants.X, expand=1)
body = Tkinter.Frame(self)
body.pack(fill=Tkconstants.X, expand=1)
sticky = Tkconstants.E + Tkconstants.W
body.grid_columnconfigure(1, weight=2)
Tkinter.Label(body, text='eBook PDB input file').grid(row=0, sticky=Tkconstants.E)
self.pdbpath = Tkinter.Entry(body, width=50)
self.pdbpath.grid(row=0, column=1, sticky=sticky)
cwd = os.getcwdu()
cwd = cwd.encode('utf-8')
self.pdbpath.insert(0, cwd)
button = Tkinter.Button(body, text="...", command=self.get_pdbpath)
button.grid(row=0, column=2)
Tkinter.Label(body, text='Output Directory').grid(row=1, sticky=Tkconstants.E)
self.outpath = Tkinter.Entry(body, width=50)
self.outpath.grid(row=1, column=1, sticky=sticky)
cwd = os.getcwdu()
cwd = cwd.encode('utf-8')
self.outpath.insert(0, cwd)
button = Tkinter.Button(body, text="...", command=self.get_outpath)
button.grid(row=1, column=2)
Tkinter.Label(body, text='Name on CC').grid(row=2, sticky=Tkconstants.E)
self.name = Tkinter.StringVar()
self.nameinfo = Tkinter.Entry(body, width=40, textvariable=self.name)
self.nameinfo.grid(row=2, column=1, sticky=sticky)
Tkinter.Label(body, text='Last 8 digits of CC Number').grid(row=3, sticky=Tkconstants.E)
self.ccnum = Tkinter.StringVar()
self.ccinfo = Tkinter.Entry(body, width=10, textvariable=self.ccnum)
self.ccinfo.grid(row=3, column=1, sticky=sticky)
msg1 = 'Conversion Log \n\n'
self.stext = ScrolledText(body, bd=5, relief=Tkconstants.RIDGE, height=15, width=60, wrap=Tkconstants.WORD)
self.stext.grid(row=4, column=0, columnspan=2,sticky=sticky)
self.stext.insert(Tkconstants.END,msg1)
buttons = Tkinter.Frame(self)
buttons.pack()
self.sbotton = Tkinter.Button(
buttons, text="Start", width=10, command=self.convertit)
self.sbotton.pack(side=Tkconstants.LEFT)
Tkinter.Frame(buttons, width=10).pack(side=Tkconstants.LEFT)
self.qbutton = Tkinter.Button(
buttons, text="Quit", width=10, command=self.quitting)
self.qbutton.pack(side=Tkconstants.RIGHT)
# read from subprocess pipe without blocking
# invoked every interval via the widget "after"
# option being used, so need to reset it for the next time
def processPipe(self):
poll = self.p2.wait('nowait')
if poll != None:
text = self.p2.readerr()
text += self.p2.read()
msg = text + '\n\n' + 'File successfully converted\n'
if poll != 0:
msg = text + '\n\n' + 'Error: Conversion Failed\n'
self.showCmdOutput(msg)
self.p2 = None
self.sbotton.configure(state='normal')
return
text = self.p2.readerr()
text += self.p2.read()
self.showCmdOutput(text)
# make sure we get invoked again by event loop after interval
self.stext.after(self.interval,self.processPipe)
return
# post output from subprocess in scrolled text widget
def showCmdOutput(self, msg):
if msg and msg !='':
if sys.platform.startswith('win'):
msg = msg.replace('\r\n','\n')
self.stext.insert(Tkconstants.END,msg)
self.stext.yview_pickplace(Tkconstants.END)
return
# run erdr2pml.py as a subprocess via pipes and collect stdout
def erdr(self, infile, outdir, name, ccnum):
# os.putenv('PYTHONUNBUFFERED', '1')
pengine = sys.executable
if pengine is None or pengine == '':
pengine = "python"
pengine = os.path/normpath(pengine)
cmdline = pengine + ' ./lib/erdr2pml.py "' + infile + '" "' + outdir + '" "' + name + '" ' + ccnum
if sys.platform[0:3] == 'win':
# search_path = os.environ['PATH']
# search_path = search_path.lower()
# if search_path.find('python') >= 0:
# cmdline = 'python lib\erdr2pml.py "' + infile + '" "' + outdir + '" "' + name + '" ' + ccnum
# else :
# cmdline = 'lib\erdr2pml.py "' + infile + '" "' + outdir + '" "' + name + '" ' + ccnum
cmdline = pengine + ' lib\\erdr2pml.py "' + infile + '" "' + outdir + '" "' + name + '" ' + ccnum
cmdline = cmdline.encode(sys.getfilesystemencoding())
p2 = Process(cmdline, shell=True, bufsize=1, stdin=None, stdout=PIPE, stderr=PIPE, close_fds=False)
return p2
def get_pdbpath(self):
pdbpath = tkFileDialog.askopenfilename(
parent=None, title='Select eReader PDB File',
defaultextension='.pdb', filetypes=[('eReader eBooks', '.pdb'),
('All Files', '.*')])
if pdbpath:
pdbpath = os.path.normpath(pdbpath)
self.pdbpath.delete(0, Tkconstants.END)
self.pdbpath.insert(0, pdbpath)
return
def get_outpath(self):
cwd = os.getcwdu()
cwd = cwd.encode('utf-8')
outpath = tkFileDialog.askdirectory(
parent=None, title='Directory to Store Output into',
initialdir=cwd, initialfile=None)
if outpath:
outpath = os.path.normpath(outpath)
self.outpath.delete(0, Tkconstants.END)
self.outpath.insert(0, outpath)
return
def quitting(self):
# kill any still running subprocess
if self.p2 != None:
if (self.p2.wait('nowait') == None):
self.p2.terminate()
self.root.destroy()
# actually ready to run the subprocess and get its output
def convertit(self):
# now disable the button to prevent multiple launches
self.sbotton.configure(state='disabled')
pdbpath = self.pdbpath.get()
outpath = self.outpath.get()
if not pdbpath or not os.path.exists(pdbpath):
self.status['text'] = 'Specified eBook file does not exist'
self.sbotton.configure(state='normal')
return
if not outpath:
self.status['text'] = 'No output directory specified'
self.sbotton.configure(state='normal')
return
if not os.path.exists(outpath):
os.makedirs(outpath)
name = self.name.get()
if not name or name == '':
self.status['text'] = 'Your forgot to enter the Name on the CC'
self.sbotton.configure(state='normal')
return
ccnum = self.ccnum.get()
if not ccnum or ccnum == '':
self.status['text'] = 'Your forgot to enter the last 8 digits on the CC'
self.sbotton.configure(state='normal')
return
log = 'Command = "python erdr2pml.py"\n'
log += 'PDB Path = "'+ pdbpath + '"\n'
log += 'Output Directory = "' + outpath + '"\n'
log += 'Name = "' + name + '"\n'
log += 'Last 8 of CC = "' + ccnum + '"\n'
log += '\n\n'
log += 'Please Wait ...\n'
self.stext.insert(Tkconstants.END,log)
self.p2 = self.erdr(pdbpath, outpath, name, ccnum)
# python does not seem to allow you to create
# your own eventloop which every other gui does - strange
# so need to use the widget "after" command to force
# event loop to run non-gui events every interval
self.stext.after(self.interval,self.processPipe)
return
def main(argv=None):
root = Tkinter.Tk()
root.title('eReader PDB to PML Conversion')
root.resizable(True, False)
root.minsize(300, 0)
MainDialog(root).pack(fill=Tkconstants.X, expand=1)
root.mainloop()
return 0
if __name__ == "__main__":
sys.exit(main())

185
Other_Tools/eReader_PDB_Tools/eReaderPDB2PMLZ.pyw
View File

@@ -1,185 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import sys
sys.path.append('lib')
import os, os.path, urllib
os.environ['PYTHONIOENCODING'] = "utf-8"
import subprocess
from subprocess import Popen, PIPE, STDOUT
import Tkinter
import Tkconstants
import tkFileDialog
import tkMessageBox
import subasyncio
from subasyncio import Process
from scrolltextwidget import ScrolledText
class MainDialog(Tkinter.Frame):
def __init__(self, root):
Tkinter.Frame.__init__(self, root, border=5)
self.root = root
self.interval = 2000
self.p2 = None
self.status = Tkinter.Label(self, text='eReader eBook Conversion to PMLZ')
self.status.pack(fill=Tkconstants.X, expand=1)
body = Tkinter.Frame(self)
body.pack(fill=Tkconstants.X, expand=1)
sticky = Tkconstants.E + Tkconstants.W
body.grid_columnconfigure(1, weight=2)
Tkinter.Label(body, text='eBook PDB input file').grid(row=0, sticky=Tkconstants.E)
self.pdbpath = Tkinter.Entry(body, width=50)
self.pdbpath.grid(row=0, column=1, sticky=sticky)
cwd = os.getcwdu()
cwd = cwd.encode('utf-8')
self.pdbpath.insert(0, cwd)
button = Tkinter.Button(body, text="...", command=self.get_pdbpath)
button.grid(row=0, column=2)
Tkinter.Label(body, text='Name on CC').grid(row=1, sticky=Tkconstants.E)
self.name = Tkinter.StringVar()
self.nameinfo = Tkinter.Entry(body, width=40, textvariable=self.name)
self.nameinfo.grid(row=1, column=1, sticky=sticky)
Tkinter.Label(body, text='Last 8 digits of CC Number').grid(row=2, sticky=Tkconstants.E)
self.ccnum = Tkinter.StringVar()
self.ccinfo = Tkinter.Entry(body, width=10, textvariable=self.ccnum)
self.ccinfo.grid(row=2, column=1, sticky=sticky)
msg1 = 'Conversion Log \n\n'
self.stext = ScrolledText(body, bd=5, relief=Tkconstants.RIDGE, height=15, width=60, wrap=Tkconstants.WORD)
self.stext.grid(row=3, column=0, columnspan=2,sticky=sticky)
self.stext.insert(Tkconstants.END,msg1)
buttons = Tkinter.Frame(self)
buttons.pack()
self.sbotton = Tkinter.Button(
buttons, text="Start", width=10, command=self.convertit)
self.sbotton.pack(side=Tkconstants.LEFT)
Tkinter.Frame(buttons, width=10).pack(side=Tkconstants.LEFT)
self.qbutton = Tkinter.Button(
buttons, text="Quit", width=10, command=self.quitting)
self.qbutton.pack(side=Tkconstants.RIGHT)
# read from subprocess pipe without blocking
# invoked every interval via the widget "after"
# option being used, so need to reset it for the next time
def processPipe(self):
poll = self.p2.wait('nowait')
if poll != None:
text = self.p2.readerr()
text += self.p2.read()
msg = text + '\n\n' + 'File successfully converted\n'
if poll != 0:
msg = text + '\n\n' + 'Error: Conversion Failed\n'
self.showCmdOutput(msg)
self.p2 = None
self.sbotton.configure(state='normal')
return
text = self.p2.readerr()
text += self.p2.read()
self.showCmdOutput(text)
# make sure we get invoked again by event loop after interval
self.stext.after(self.interval,self.processPipe)
return
# post output from subprocess in scrolled text widget
def showCmdOutput(self, msg):
if msg and msg !='':
if sys.platform.startswith('win'):
msg = msg.replace('\r\n','\n')
self.stext.insert(Tkconstants.END,msg)
self.stext.yview_pickplace(Tkconstants.END)
return
# run erdr2pml.py as a subprocess via pipes and collect stdout
def erdr(self, infile, name, ccnum):
# os.putenv('PYTHONUNBUFFERED', '1')
pengine = sys.executable
if pengine is None or pengine == '':
pengine = "python"
pengine = os.path.normpath(pengine)
cmdline = pengine + ' ./lib/erdr2pml.py --make-pmlz "' + infile + '" "' + name + '" ' + ccnum
if sys.platform[0:3] == 'win':
# search_path = os.environ['PATH']
# search_path = search_path.lower()
# if search_path.find('python') >= 0:
# cmdline = 'python lib\erdr2pml.py --make-pmlz "' + infile + '" "' + name + '" ' + ccnum
# else :
# cmdline = 'lib\erdr2pml.py --make-pmlz "' + infile + '" "' + name + '" ' + ccnum
cmdline = pengine + ' lib\\erdr2pml.py --make-pmlz "' + infile + '" "' + name + '" ' + ccnum
cmdline = cmdline.encode(sys.getfilesystemencoding())
p2 = Process(cmdline, shell=True, bufsize=1, stdin=None, stdout=PIPE, stderr=PIPE, close_fds=False)
return p2
def get_pdbpath(self):
pdbpath = tkFileDialog.askopenfilename(
parent=None, title='Select eReader PDB File',
defaultextension='.pdb', filetypes=[('eReader eBooks', '.pdb'),
('All Files', '.*')])
if pdbpath:
pdbpath = os.path.normpath(pdbpath)
self.pdbpath.delete(0, Tkconstants.END)
self.pdbpath.insert(0, pdbpath)
return
def quitting(self):
# kill any still running subprocess
if self.p2 != None:
if (self.p2.wait('nowait') == None):
self.p2.terminate()
self.root.destroy()
# actually ready to run the subprocess and get its output
def convertit(self):
# now disable the button to prevent multiple launches
self.sbotton.configure(state='disabled')
pdbpath = self.pdbpath.get()
if not pdbpath or not os.path.exists(pdbpath):
self.status['text'] = 'Specified eBook file does not exist'
self.sbotton.configure(state='normal')
return
name = self.name.get()
if not name or name == '':
self.status['text'] = 'Your forgot to enter the Name on the CC'
self.sbotton.configure(state='normal')
return
ccnum = self.ccnum.get()
if not ccnum or ccnum == '':
self.status['text'] = 'Your forgot to enter the last 8 digits on the CC'
self.sbotton.configure(state='normal')
return
log = 'Command = "python erdr2pml.py --make-pmlz "\n'
log += 'PDB Path = "'+ pdbpath + '"\n'
log += 'Name = "' + name + '"\n'
log += 'Last 8 of CC = "' + ccnum + '"\n'
log += '\n\n'
log += 'Please Wait ...\n'
self.stext.insert(Tkconstants.END,log)
self.p2 = self.erdr(pdbpath, name, ccnum)
# python does not seem to allow you to create
# your own eventloop which every other gui does - strange
# so need to use the widget "after" command to force
# event loop to run non-gui events every interval
self.stext.after(self.interval,self.processPipe)
return
def main(argv=None):
root = Tkinter.Tk()
root.title('eReader PDB to PMLZ Conversion')
root.resizable(True, False)
root.minsize(300, 0)
MainDialog(root).pack(fill=Tkconstants.X, expand=1)
root.mainloop()
return 0
if __name__ == "__main__":
sys.exit(main())

137
Other_Tools/eReader_PDB_Tools/lib/eReaderPDB2PML_plugin.py
View File

@@ -1,137 +0,0 @@
#!/usr/bin/env python
# eReaderPDB2PML_plugin.py
# Released under the terms of the GNU General Public Licence, version 3 or
# later. <http://www.gnu.org/licenses/>
#
# All credit given to The Dark Reverser for the original standalone script.
# I had the much easier job of converting it to Calibre a plugin.
#
# This plugin is meant to convert secure Ereader files (PDB) to unsecured PMLZ files.
# Calibre can then convert it to whatever format you desire.
# It is meant to function without having to install any dependencies...
# other than having Calibre installed, of course.
#
# Installation:
# Go to Calibre's Preferences page... click on the Plugins button. Use the file
# dialog button to select the plugin's zip file (eReaderPDB2PML_vXX_plugin.zip) and
# click the 'Add' button. You're done.
#
# Configuration:
# Highlight the plugin (eReader PDB 2 PML) and click the
# "Customize Plugin" button on Calibre's Preferences->Plugins page.
# Enter your name and the last 8 digits of the credit card number separated by
# a comma: Your Name,12341234
#
# If you've purchased books with more than one credit card, separate the info with
# a colon: Your Name,12341234:Other Name,23452345
# NOTE: Do NOT put quotes around your name like you do with the original script!!
#
# Revision history:
# 0.0.1 - Initial release
# 0.0.2 - updated to distinguish it from earlier non-openssl version
# 0.0.3 - removed added psyco code as it is not supported under Calibre's Python 2.7
import sys, os
from calibre.customize import FileTypePlugin
class eRdrDeDRM(FileTypePlugin):
name = 'eReader PDB 2 PML' # Name of the plugin
description = 'Removes DRM from secure pdb files. \
Credit given to The Dark Reverser for the original standalone script.'
supported_platforms = ['linux', 'osx', 'windows'] # Platforms this plugin will run on
author = 'DiapDealer' # The author of this plugin
version = (0, 0, 4) # The version number of this plugin
file_types = set(['pdb']) # The file types that this plugin will be applied to
on_import = True # Run this plugin during the import
def run(self, path_to_ebook):
from calibre.ptempfile import PersistentTemporaryDirectory
from calibre.constants import iswindows, isosx
global bookname, erdr2pml
import erdr2pml
infile = path_to_ebook
bookname = os.path.splitext(os.path.basename(infile))[0]
outdir = PersistentTemporaryDirectory()
pmlzfile = self.temporary_file(bookname + '.pmlz')
if self.site_customization:
keydata = self.site_customization
ar = keydata.split(':')
for i in ar:
try:
name, cc = i.split(',')
except ValueError:
print ' Error parsing user supplied data.'
return path_to_ebook
try:
print "Processing..."
import time
start_time = time.time()
pmlfilepath = self.convertEreaderToPml(infile, name, cc, outdir)
if pmlfilepath and pmlfilepath != 1:
import zipfile
print " Creating PMLZ file"
myZipFile = zipfile.ZipFile(pmlzfile.name,'w',zipfile.ZIP_STORED, False)
list = os.listdir(outdir)
for file in list:
localname = file
filePath = os.path.join(outdir,file)
if os.path.isfile(filePath):
myZipFile.write(filePath, localname)
elif os.path.isdir(filePath):
imageList = os.listdir(filePath)
localimgdir = os.path.basename(filePath)
for image in imageList:
localname = os.path.join(localimgdir,image)
imagePath = os.path.join(filePath,image)
if os.path.isfile(imagePath):
myZipFile.write(imagePath, localname)
myZipFile.close()
end_time = time.time()
search_time = end_time - start_time
print 'elapsed time: %.2f seconds' % (search_time, )
print "done"
return pmlzfile.name
else:
raise ValueError('Error Creating PML file.')
except ValueError, e:
print "Error: %s" % e
pass
raise Exception('Couldn\'t decrypt pdb file.')
else:
raise Exception('No name and CC# provided.')
def convertEreaderToPml(self, infile, name, cc, outdir):
print " Decoding File"
sect = erdr2pml.Sectionizer(infile, 'PNRdPPrs')
er = erdr2pml.EreaderProcessor(sect, name, cc)
if er.getNumImages() > 0:
print " Extracting images"
#imagedir = bookname + '_img/'
imagedir = 'images/'
imagedirpath = os.path.join(outdir,imagedir)
if not os.path.exists(imagedirpath):
os.makedirs(imagedirpath)
for i in xrange(er.getNumImages()):
name, contents = er.getImage(i)
file(os.path.join(imagedirpath, name), 'wb').write(contents)
print " Extracting pml"
pml_string = er.getText()
pmlfilename = bookname + ".pml"
try:
file(os.path.join(outdir, pmlfilename),'wb').write(erdr2pml.cleanPML(pml_string))
return os.path.join(outdir, pmlfilename)
except:
return 1
def customization_help(self, gui=False):
return 'Enter Account Name & Last 8 digits of Credit Card number (separate with a comma)'

526
Other_Tools/eReader_PDB_Tools/lib/erdr2pml.py
View File

@@ -1,526 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
#
# erdr2pml.py
#
# This is a python script. You need a Python interpreter to run it.
# For example, ActiveState Python, which exists for windows.
# Changelog
#
# Based on ereader2html version 0.08 plus some later small fixes
#
# 0.01 - Initial version
# 0.02 - Support more eReader files. Support bold text and links. Fix PML decoder parsing bug.
# 0.03 - Fix incorrect variable usage at one place.
# 0.03b - enhancement by DeBockle (version 259 support)
# Custom version 0.03 - no change to eReader support, only usability changes
# - start of pep-8 indentation (spaces not tab), fix trailing blanks
# - version variable, only one place to change
# - added main routine, now callable as a library/module,
# means tools can add optional support for ereader2html
# - outdir is no longer a mandatory parameter (defaults based on input name if missing)
# - time taken output to stdout
# - Psyco support - reduces runtime by a factor of (over) 3!
# E.g. (~600Kb file) 90 secs down to 24 secs
# - newstyle classes
# - changed map call to list comprehension
# may not work with python 2.3
# without Psyco this reduces runtime to 90%
# E.g. 90 secs down to 77 secs
# Psyco with map calls takes longer, do not run with map in Psyco JIT!
# - izip calls used instead of zip (if available), further reduction
# in run time (factor of 4.5).
# E.g. (~600Kb file) 90 secs down to 20 secs
# - Python 2.6+ support, avoid DeprecationWarning with sha/sha1
# 0.04 - Footnote support, PML output, correct charset in html, support more PML tags
# - Feature change, dump out PML file
# - Added supprt for footnote tags. NOTE footnote ids appear to be bad (not usable)
# in some pdb files :-( due to the same id being used multiple times
# - Added correct charset encoding (pml is based on cp1252)
# - Added logging support.
# 0.05 - Improved type 272 support for sidebars, links, chapters, metainfo, etc
# 0.06 - Merge of 0.04 and 0.05. Improved HTML output
# Placed images in subfolder, so that it's possible to just
# drop the book.pml file onto DropBook to make an unencrypted
# copy of the eReader file.
# Using that with Calibre works a lot better than the HTML
# conversion in this code.
# 0.07 - Further Improved type 272 support for sidebars with all earlier fixes
# 0.08 - fixed typos, removed extraneous things
# 0.09 - fixed typos in first_pages to first_page to again support older formats
# 0.10 - minor cleanups
# 0.11 - fixups for using correct xml for footnotes and sidebars for use with Dropbook
# 0.12 - Fix added to prevent lowercasing of image names when the pml code itself uses a different case in the link name.
# 0.13 - change to unbuffered stdout for use with gui front ends
# 0.14 - contributed enhancement to support --make-pmlz switch
# 0.15 - enabled high-ascii to pml character encoding. DropBook now works on Mac.
# 0.16 - convert to use openssl DES (very very fast) or pure python DES if openssl's libcrypto is not available
# 0.17 - added support for pycrypto's DES as well
# 0.18 - on Windows try PyCrypto first and OpenSSL next
# 0.19 - Modify the interface to allow use of import
# 0.20 - modify to allow use inside new interface for calibre plugins
# 0.21 - Support eReader (drm) version 11.
# - Don't reject dictionary format.
# - Ignore sidebars for dictionaries (different format?)
__version__='0.21'
class Unbuffered:
def __init__(self, stream):
self.stream = stream
def write(self, data):
self.stream.write(data)
self.stream.flush()
def __getattr__(self, attr):
return getattr(self.stream, attr)
import sys
import struct, binascii, getopt, zlib, os, os.path, urllib, tempfile
if 'calibre' in sys.modules:
inCalibre = True
else:
inCalibre = False
Des = None
if sys.platform.startswith('win'):
# first try with pycrypto
if inCalibre:
from calibre_plugins.erdrpdb2pml import pycrypto_des
else:
import pycrypto_des
Des = pycrypto_des.load_pycrypto()
if Des == None:
# they try with openssl
if inCalibre:
from calibre_plugins.erdrpdb2pml import openssl_des
else:
import openssl_des
Des = openssl_des.load_libcrypto()
else:
# first try with openssl
if inCalibre:
from calibre_plugins.erdrpdb2pml import openssl_des
else:
import openssl_des
Des = openssl_des.load_libcrypto()
if Des == None:
# then try with pycrypto
if inCalibre:
from calibre_plugins.erdrpdb2pml import pycrypto_des
else:
import pycrypto_des
Des = pycrypto_des.load_pycrypto()
# if that did not work then use pure python implementation
# of DES and try to speed it up with Psycho
if Des == None:
if inCalibre:
from calibre_plugins.erdrpdb2pml import python_des
else:
import python_des
Des = python_des.Des
# Import Psyco if available
try:
# http://psyco.sourceforge.net
import psyco
psyco.full()
except ImportError:
pass
try:
from hashlib import sha1
except ImportError:
# older Python release
import sha
sha1 = lambda s: sha.new(s)
import cgi
import logging
logging.basicConfig()
#logging.basicConfig(level=logging.DEBUG)
class Sectionizer(object):
bkType = "Book"
def __init__(self, filename, ident):
self.contents = file(filename, 'rb').read()
self.header = self.contents[0:72]
self.num_sections, = struct.unpack('>H', self.contents[76:78])
# Dictionary or normal content (TODO: Not hard-coded)
if self.header[0x3C:0x3C+8] != ident:
if self.header[0x3C:0x3C+8] == "PDctPPrs":
self.bkType = "Dict"
else:
raise ValueError('Invalid file format')
self.sections = []
for i in xrange(self.num_sections):
offset, a1,a2,a3,a4 = struct.unpack('>LBBBB', self.contents[78+i*8:78+i*8+8])
flags, val = a1, a2<<16|a3<<8|a4
self.sections.append( (offset, flags, val) )
def loadSection(self, section):
if section + 1 == self.num_sections:
end_off = len(self.contents)
else:
end_off = self.sections[section + 1][0]
off = self.sections[section][0]
return self.contents[off:end_off]
def sanitizeFileName(s):
r = ''
for c in s:
if c in "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_.-":
r += c
return r
def fixKey(key):
def fixByte(b):
return b ^ ((b ^ (b<<1) ^ (b<<2) ^ (b<<3) ^ (b<<4) ^ (b<<5) ^ (b<<6) ^ (b<<7) ^ 0x80) & 0x80)
return "".join([chr(fixByte(ord(a))) for a in key])
def deXOR(text, sp, table):
r=''
j = sp
for i in xrange(len(text)):
r += chr(ord(table[j]) ^ ord(text[i]))
j = j + 1
if j == len(table):
j = 0
return r
class EreaderProcessor(object):
def __init__(self, sect, username, creditcard):
self.section_reader = sect.loadSection
data = self.section_reader(0)
version, = struct.unpack('>H', data[0:2])
self.version = version
logging.info('eReader file format version %s', version)
if version != 272 and version != 260 and version != 259:
raise ValueError('incorrect eReader version %d (error 1)' % version)
data = self.section_reader(1)
self.data = data
des = Des(fixKey(data[0:8]))
cookie_shuf, cookie_size = struct.unpack('>LL', des.decrypt(data[-8:]))
if cookie_shuf < 3 or cookie_shuf > 0x14 or cookie_size < 0xf0 or cookie_size > 0x200:
raise ValueError('incorrect eReader version (error 2)')
input = des.decrypt(data[-cookie_size:])
def unshuff(data, shuf):
r = [''] * len(data)
j = 0
for i in xrange(len(data)):
j = (j + shuf) % len(data)
r[j] = data[i]
assert len("".join(r)) == len(data)
return "".join(r)
r = unshuff(input[0:-8], cookie_shuf)
def fixUsername(s):
r = ''
for c in s.lower():
if (c >= 'a' and c <= 'z' or c >= '0' and c <= '9'):
r += c
return r
user_key = struct.pack('>LL', binascii.crc32(fixUsername(username)) & 0xffffffff, binascii.crc32(creditcard[-8:])& 0xffffffff)
drm_sub_version = struct.unpack('>H', r[0:2])[0]
self.num_text_pages = struct.unpack('>H', r[2:4])[0] - 1
self.num_image_pages = struct.unpack('>H', r[26:26+2])[0]
self.first_image_page = struct.unpack('>H', r[24:24+2])[0]
# Default values
self.num_footnote_pages = 0
self.num_sidebar_pages = 0
self.first_footnote_page = -1
self.first_sidebar_page = -1
if self.version == 272:
self.num_footnote_pages = struct.unpack('>H', r[46:46+2])[0]
self.first_footnote_page = struct.unpack('>H', r[44:44+2])[0]
if (sect.bkType == "Book"):
self.num_sidebar_pages = struct.unpack('>H', r[38:38+2])[0]
self.first_sidebar_page = struct.unpack('>H', r[36:36+2])[0]
# self.num_bookinfo_pages = struct.unpack('>H', r[34:34+2])[0]
# self.first_bookinfo_page = struct.unpack('>H', r[32:32+2])[0]
# self.num_chapter_pages = struct.unpack('>H', r[22:22+2])[0]
# self.first_chapter_page = struct.unpack('>H', r[20:20+2])[0]
# self.num_link_pages = struct.unpack('>H', r[30:30+2])[0]
# self.first_link_page = struct.unpack('>H', r[28:28+2])[0]
# self.num_xtextsize_pages = struct.unpack('>H', r[54:54+2])[0]
# self.first_xtextsize_page = struct.unpack('>H', r[52:52+2])[0]
# **before** data record 1 was decrypted and unshuffled, it contained data
# to create an XOR table and which is used to fix footnote record 0, link records, chapter records, etc
self.xortable_offset = struct.unpack('>H', r[40:40+2])[0]
self.xortable_size = struct.unpack('>H', r[42:42+2])[0]
self.xortable = self.data[self.xortable_offset:self.xortable_offset + self.xortable_size]
else:
# Nothing needs to be done
pass
# self.num_bookinfo_pages = 0
# self.num_chapter_pages = 0
# self.num_link_pages = 0
# self.num_xtextsize_pages = 0
# self.first_bookinfo_page = -1
# self.first_chapter_page = -1
# self.first_link_page = -1
# self.first_xtextsize_page = -1
logging.debug('self.num_text_pages %d', self.num_text_pages)
logging.debug('self.num_footnote_pages %d, self.first_footnote_page %d', self.num_footnote_pages , self.first_footnote_page)
logging.debug('self.num_sidebar_pages %d, self.first_sidebar_page %d', self.num_sidebar_pages , self.first_sidebar_page)
self.flags = struct.unpack('>L', r[4:8])[0]
reqd_flags = (1<<9) | (1<<7) | (1<<10)
if (self.flags & reqd_flags) != reqd_flags:
print "Flags: 0x%X" % self.flags
raise ValueError('incompatible eReader file')
des = Des(fixKey(user_key))
if version == 259:
if drm_sub_version != 7:
raise ValueError('incorrect eReader version %d (error 3)' % drm_sub_version)
encrypted_key_sha = r[44:44+20]
encrypted_key = r[64:64+8]
elif version == 260:
if drm_sub_version != 13 and drm_sub_version != 11:
raise ValueError('incorrect eReader version %d (error 3)' % drm_sub_version)
if drm_sub_version == 13:
encrypted_key = r[44:44+8]
encrypted_key_sha = r[52:52+20]
else:
encrypted_key = r[64:64+8]
encrypted_key_sha = r[44:44+20]
elif version == 272:
encrypted_key = r[172:172+8]
encrypted_key_sha = r[56:56+20]
self.content_key = des.decrypt(encrypted_key)
if sha1(self.content_key).digest() != encrypted_key_sha:
raise ValueError('Incorrect Name and/or Credit Card')
def getNumImages(self):
return self.num_image_pages
def getImage(self, i):
sect = self.section_reader(self.first_image_page + i)
name = sect[4:4+32].strip('\0')
data = sect[62:]
return sanitizeFileName(name), data
# def getChapterNamePMLOffsetData(self):
# cv = ''
# if self.num_chapter_pages > 0:
# for i in xrange(self.num_chapter_pages):
# chaps = self.section_reader(self.first_chapter_page + i)
# j = i % self.xortable_size
# offname = deXOR(chaps, j, self.xortable)
# offset = struct.unpack('>L', offname[0:4])[0]
# name = offname[4:].strip('\0')
# cv += '%d|%s\n' % (offset, name)
# return cv
# def getLinkNamePMLOffsetData(self):
# lv = ''
# if self.num_link_pages > 0:
# for i in xrange(self.num_link_pages):
# links = self.section_reader(self.first_link_page + i)
# j = i % self.xortable_size
# offname = deXOR(links, j, self.xortable)
# offset = struct.unpack('>L', offname[0:4])[0]
# name = offname[4:].strip('\0')
# lv += '%d|%s\n' % (offset, name)
# return lv
# def getExpandedTextSizesData(self):
# ts = ''
# if self.num_xtextsize_pages > 0:
# tsize = deXOR(self.section_reader(self.first_xtextsize_page), 0, self.xortable)
# for i in xrange(self.num_text_pages):
# xsize = struct.unpack('>H', tsize[0:2])[0]
# ts += "%d\n" % xsize
# tsize = tsize[2:]
# return ts
# def getBookInfo(self):
# bkinfo = ''
# if self.num_bookinfo_pages > 0:
# info = self.section_reader(self.first_bookinfo_page)
# bkinfo = deXOR(info, 0, self.xortable)
# bkinfo = bkinfo.replace('\0','|')
# bkinfo += '\n'
# return bkinfo
def getText(self):
des = Des(fixKey(self.content_key))
r = ''
for i in xrange(self.num_text_pages):
logging.debug('get page %d', i)
r += zlib.decompress(des.decrypt(self.section_reader(1 + i)))
# now handle footnotes pages
if self.num_footnote_pages > 0:
r += '\n'
# the record 0 of the footnote section must pass through the Xor Table to make it useful
sect = self.section_reader(self.first_footnote_page)
fnote_ids = deXOR(sect, 0, self.xortable)
# the remaining records of the footnote sections need to be decoded with the content_key and zlib inflated
des = Des(fixKey(self.content_key))
for i in xrange(1,self.num_footnote_pages):
logging.debug('get footnotepage %d', i)
id_len = ord(fnote_ids[2])
id = fnote_ids[3:3+id_len]
fmarker = '<footnote id="%s">\n' % id
fmarker += zlib.decompress(des.decrypt(self.section_reader(self.first_footnote_page + i)))
fmarker += '\n</footnote>\n'
r += fmarker
fnote_ids = fnote_ids[id_len+4:]
# TODO: Handle dictionary index (?) pages - which are also marked as
# sidebar_pages (?). For now dictionary sidebars are ignored
# For dictionaries - record 0 is null terminated strings, followed by
# blocks of around 62000 bytes and a final block. Not sure of the
# encoding
# now handle sidebar pages
if self.num_sidebar_pages > 0:
r += '\n'
# the record 0 of the sidebar section must pass through the Xor Table to make it useful
sect = self.section_reader(self.first_sidebar_page)
sbar_ids = deXOR(sect, 0, self.xortable)
# the remaining records of the sidebar sections need to be decoded with the content_key and zlib inflated
des = Des(fixKey(self.content_key))
for i in xrange(1,self.num_sidebar_pages):
id_len = ord(sbar_ids[2])
id = sbar_ids[3:3+id_len]
smarker = '<sidebar id="%s">\n' % id
smarker += zlib.decompress(des.decrypt(self.section_reader(self.first_sidebar_page + i)))
smarker += '\n</sidebar>\n'
r += smarker
sbar_ids = sbar_ids[id_len+4:]
return r
def cleanPML(pml):
# Convert special characters to proper PML code. High ASCII start at (\x80, \a128) and go up to (\xff, \a255)
pml2 = pml
for k in xrange(128,256):
badChar = chr(k)
pml2 = pml2.replace(badChar, '\\a%03d' % k)
return pml2
def convertEreaderToPml(infile, name, cc, outdir):
if not os.path.exists(outdir):
os.makedirs(outdir)
bookname = os.path.splitext(os.path.basename(infile))[0]
print " Decoding File"
sect = Sectionizer(infile, 'PNRdPPrs')
er = EreaderProcessor(sect, name, cc)
if er.getNumImages() > 0:
print " Extracting images"
imagedir = bookname + '_img/'
imagedirpath = os.path.join(outdir,imagedir)
if not os.path.exists(imagedirpath):
os.makedirs(imagedirpath)
for i in xrange(er.getNumImages()):
name, contents = er.getImage(i)
file(os.path.join(imagedirpath, name), 'wb').write(contents)
print " Extracting pml"
pml_string = er.getText()
pmlfilename = bookname + ".pml"
file(os.path.join(outdir, pmlfilename),'wb').write(cleanPML(pml_string))
# bkinfo = er.getBookInfo()
# if bkinfo != '':
# print " Extracting book meta information"
# file(os.path.join(outdir, 'bookinfo.txt'),'wb').write(bkinfo)
def decryptBook(infile, outdir, name, cc, make_pmlz):
if make_pmlz :
# ignore specified outdir, use tempdir instead
outdir = tempfile.mkdtemp()
try:
print "Processing..."
convertEreaderToPml(infile, name, cc, outdir)
if make_pmlz :
import zipfile
import shutil
print " Creating PMLZ file"
zipname = infile[:-4] + '.pmlz'
myZipFile = zipfile.ZipFile(zipname,'w',zipfile.ZIP_STORED, False)
list = os.listdir(outdir)
for file in list:
localname = file
filePath = os.path.join(outdir,file)
if os.path.isfile(filePath):
myZipFile.write(filePath, localname)
elif os.path.isdir(filePath):
imageList = os.listdir(filePath)
localimgdir = os.path.basename(filePath)
for image in imageList:
localname = os.path.join(localimgdir,image)
imagePath = os.path.join(filePath,image)
if os.path.isfile(imagePath):
myZipFile.write(imagePath, localname)
myZipFile.close()
# remove temporary directory
shutil.rmtree(outdir, True)
print 'output is %s' % zipname
else :
print 'output in %s' % outdir
print "done"
except ValueError, e:
print "Error: %s" % e
return 1
return 0
def usage():
print "Converts DRMed eReader books to PML Source"
print "Usage:"
print " erdr2pml [options] infile.pdb [outdir] \"your name\" credit_card_number "
print " "
print "Options: "
print " -h prints this message"
print " --make-pmlz create PMLZ instead of using output directory"
print " "
print "Note:"
print " if ommitted, outdir defaults based on 'infile.pdb'"
print " It's enough to enter the last 8 digits of the credit card number"
return
def main(argv=None):
try:
opts, args = getopt.getopt(sys.argv[1:], "h", ["make-pmlz"])
except getopt.GetoptError, err:
print str(err)
usage()
return 1
make_pmlz = False
for o, a in opts:
if o == "-h":
usage()
return 0
elif o == "--make-pmlz":
make_pmlz = True
print "eRdr2Pml v%s. Copyright (c) 2009 The Dark Reverser" % __version__
if len(args)!=3 and len(args)!=4:
usage()
return 1
if len(args)==3:
infile, name, cc = args[0], args[1], args[2]
outdir = infile[:-4] + '_Source'
elif len(args)==4:
infile, outdir, name, cc = args[0], args[1], args[2], args[3]
return decryptBook(infile, outdir, name, cc, make_pmlz)
if __name__ == "__main__":
sys.stdout=Unbuffered(sys.stdout)
sys.exit(main())

89
Other_Tools/eReader_PDB_Tools/lib/openssl_des.py
View File

@@ -1,89 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
# implement just enough of des from openssl to make erdr2pml.py happy
def load_libcrypto():
from ctypes import CDLL, POINTER, c_void_p, c_char_p, c_char, c_int, c_long, \
Structure, c_ulong, create_string_buffer, cast
from ctypes.util import find_library
import sys
if sys.platform.startswith('win'):
libcrypto = find_library('libeay32')
else:
libcrypto = find_library('crypto')
if libcrypto is None:
return None
libcrypto = CDLL(libcrypto)
# typedef struct DES_ks
# {
# union
# {
# DES_cblock cblock;
# /* make sure things are correct size on machines with
# * 8 byte longs */
# DES_LONG deslong[2];
# } ks[16];
# } DES_key_schedule;
# just create a big enough place to hold everything
# it will have alignment of structure so we should be okay (16 byte aligned?)
class DES_KEY_SCHEDULE(Structure):
_fields_ = [('DES_cblock1', c_char * 16),
('DES_cblock2', c_char * 16),
('DES_cblock3', c_char * 16),
('DES_cblock4', c_char * 16),
('DES_cblock5', c_char * 16),
('DES_cblock6', c_char * 16),
('DES_cblock7', c_char * 16),
('DES_cblock8', c_char * 16),
('DES_cblock9', c_char * 16),
('DES_cblock10', c_char * 16),
('DES_cblock11', c_char * 16),
('DES_cblock12', c_char * 16),
('DES_cblock13', c_char * 16),
('DES_cblock14', c_char * 16),
('DES_cblock15', c_char * 16),
('DES_cblock16', c_char * 16)]
DES_KEY_SCHEDULE_p = POINTER(DES_KEY_SCHEDULE)
def F(restype, name, argtypes):
func = getattr(libcrypto, name)
func.restype = restype
func.argtypes = argtypes
return func
DES_set_key = F(None, 'DES_set_key',[c_char_p, DES_KEY_SCHEDULE_p])
DES_ecb_encrypt = F(None, 'DES_ecb_encrypt',[c_char_p, c_char_p, DES_KEY_SCHEDULE_p, c_int])
class DES(object):
def __init__(self, key):
if len(key) != 8 :
raise Error('DES improper key used')
return
self.key = key
self.keyschedule = DES_KEY_SCHEDULE()
DES_set_key(self.key, self.keyschedule)
def desdecrypt(self, data):
ob = create_string_buffer(len(data))
DES_ecb_encrypt(data, ob, self.keyschedule, 0)
return ob.raw
def decrypt(self, data):
if not data:
return ''
i = 0
result = []
while i < len(data):
block = data[i:i+8]
processed_block = self.desdecrypt(block)
result.append(processed_block)
i += 8
return ''.join(result)
return DES

30
Other_Tools/eReader_PDB_Tools/lib/pycrypto_des.py
View File

@@ -1,30 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
def load_pycrypto():
try :
from Crypto.Cipher import DES as _DES
except:
return None
class DES(object):
def __init__(self, key):
if len(key) != 8 :
raise Error('DES improper key used')
self.key = key
self._des = _DES.new(key,_DES.MODE_ECB)
def desdecrypt(self, data):
return self._des.decrypt(data)
def decrypt(self, data):
if not data:
return ''
i = 0
result = []
while i < len(data):
block = data[i:i+8]
processed_block = self.desdecrypt(block)
result.append(processed_block)
i += 8
return ''.join(result)
return DES

220
Other_Tools/eReader_PDB_Tools/lib/python_des.py
View File

@@ -1,220 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import sys
ECB = 0
CBC = 1
class Des(object):
__pc1 = [56, 48, 40, 32, 24, 16, 8, 0, 57, 49, 41, 33, 25, 17,
9, 1, 58, 50, 42, 34, 26, 18, 10, 2, 59, 51, 43, 35,
62, 54, 46, 38, 30, 22, 14, 6, 61, 53, 45, 37, 29, 21,
13, 5, 60, 52, 44, 36, 28, 20, 12, 4, 27, 19, 11, 3]
__left_rotations = [1, 1, 2, 2, 2, 2, 2, 2, 1, 2, 2, 2, 2, 2, 2, 1]
__pc2 = [13, 16, 10, 23, 0, 4,2, 27, 14, 5, 20, 9,
22, 18, 11, 3, 25, 7, 15, 6, 26, 19, 12, 1,
40, 51, 30, 36, 46, 54, 29, 39, 50, 44, 32, 47,
43, 48, 38, 55, 33, 52, 45, 41, 49, 35, 28, 31]
__ip = [57, 49, 41, 33, 25, 17, 9, 1, 59, 51, 43, 35, 27, 19, 11, 3,
61, 53, 45, 37, 29, 21, 13, 5, 63, 55, 47, 39, 31, 23, 15, 7,
56, 48, 40, 32, 24, 16, 8, 0, 58, 50, 42, 34, 26, 18, 10, 2,
60, 52, 44, 36, 28, 20, 12, 4, 62, 54, 46, 38, 30, 22, 14, 6]
__expansion_table = [31, 0, 1, 2, 3, 4, 3, 4, 5, 6, 7, 8,
7, 8, 9, 10, 11, 12,11, 12, 13, 14, 15, 16,
15, 16, 17, 18, 19, 20,19, 20, 21, 22, 23, 24,
23, 24, 25, 26, 27, 28,27, 28, 29, 30, 31, 0]
__sbox = [[14, 4, 13, 1, 2, 15, 11, 8, 3, 10, 6, 12, 5, 9, 0, 7,
0, 15, 7, 4, 14, 2, 13, 1, 10, 6, 12, 11, 9, 5, 3, 8,
4, 1, 14, 8, 13, 6, 2, 11, 15, 12, 9, 7, 3, 10, 5, 0,
15, 12, 8, 2, 4, 9, 1, 7, 5, 11, 3, 14, 10, 0, 6, 13],
[15, 1, 8, 14, 6, 11, 3, 4, 9, 7, 2, 13, 12, 0, 5, 10,
3, 13, 4, 7, 15, 2, 8, 14, 12, 0, 1, 10, 6, 9, 11, 5,
0, 14, 7, 11, 10, 4, 13, 1, 5, 8, 12, 6, 9, 3, 2, 15,
13, 8, 10, 1, 3, 15, 4, 2, 11, 6, 7, 12, 0, 5, 14, 9],
[10, 0, 9, 14, 6, 3, 15, 5, 1, 13, 12, 7, 11, 4, 2, 8,
13, 7, 0, 9, 3, 4, 6, 10, 2, 8, 5, 14, 12, 11, 15, 1,
13, 6, 4, 9, 8, 15, 3, 0, 11, 1, 2, 12, 5, 10, 14, 7,
1, 10, 13, 0, 6, 9, 8, 7, 4, 15, 14, 3, 11, 5, 2, 12],
[7, 13, 14, 3, 0, 6, 9, 10, 1, 2, 8, 5, 11, 12, 4, 15,
13, 8, 11, 5, 6, 15, 0, 3, 4, 7, 2, 12, 1, 10, 14, 9,
10, 6, 9, 0, 12, 11, 7, 13, 15, 1, 3, 14, 5, 2, 8, 4,
3, 15, 0, 6, 10, 1, 13, 8, 9, 4, 5, 11, 12, 7, 2, 14],
[2, 12, 4, 1, 7, 10, 11, 6, 8, 5, 3, 15, 13, 0, 14, 9,
14, 11, 2, 12, 4, 7, 13, 1, 5, 0, 15, 10, 3, 9, 8, 6,
4, 2, 1, 11, 10, 13, 7, 8, 15, 9, 12, 5, 6, 3, 0, 14,
11, 8, 12, 7, 1, 14, 2, 13, 6, 15, 0, 9, 10, 4, 5, 3],
[12, 1, 10, 15, 9, 2, 6, 8, 0, 13, 3, 4, 14, 7, 5, 11,
10, 15, 4, 2, 7, 12, 9, 5, 6, 1, 13, 14, 0, 11, 3, 8,
9, 14, 15, 5, 2, 8, 12, 3, 7, 0, 4, 10, 1, 13, 11, 6,
4, 3, 2, 12, 9, 5, 15, 10, 11, 14, 1, 7, 6, 0, 8, 13],
[4, 11, 2, 14, 15, 0, 8, 13, 3, 12, 9, 7, 5, 10, 6, 1,
13, 0, 11, 7, 4, 9, 1, 10, 14, 3, 5, 12, 2, 15, 8, 6,
1, 4, 11, 13, 12, 3, 7, 14, 10, 15, 6, 8, 0, 5, 9, 2,
6, 11, 13, 8, 1, 4, 10, 7, 9, 5, 0, 15, 14, 2, 3, 12],
[13, 2, 8, 4, 6, 15, 11, 1, 10, 9, 3, 14, 5, 0, 12, 7,
1, 15, 13, 8, 10, 3, 7, 4, 12, 5, 6, 11, 0, 14, 9, 2,
7, 11, 4, 1, 9, 12, 14, 2, 0, 6, 10, 13, 15, 3, 5, 8,
2, 1, 14, 7, 4, 10, 8, 13, 15, 12, 9, 0, 3, 5, 6, 11],]
__p = [15, 6, 19, 20, 28, 11,27, 16, 0, 14, 22, 25,
4, 17, 30, 9, 1, 7,23,13, 31, 26, 2, 8,18, 12, 29, 5, 21, 10,3, 24]
__fp = [39, 7, 47, 15, 55, 23, 63, 31,38, 6, 46, 14, 54, 22, 62, 30,
37, 5, 45, 13, 53, 21, 61, 29,36, 4, 44, 12, 52, 20, 60, 28,
35, 3, 43, 11, 51, 19, 59, 27,34, 2, 42, 10, 50, 18, 58, 26,
33, 1, 41, 9, 49, 17, 57, 25,32, 0, 40, 8, 48, 16, 56, 24]
# Type of crypting being done
ENCRYPT = 0x00
DECRYPT = 0x01
def __init__(self, key, mode=ECB, IV=None):
if len(key) != 8:
raise ValueError("Invalid DES key size. Key must be exactly 8 bytes long.")
self.block_size = 8
self.key_size = 8
self.__padding = ''
self.setMode(mode)
if IV:
self.setIV(IV)
self.L = []
self.R = []
self.Kn = [ [0] * 48 ] * 16 # 16 48-bit keys (K1 - K16)
self.final = []
self.setKey(key)
def getKey(self):
return self.__key
def setKey(self, key):
self.__key = key
self.__create_sub_keys()
def getMode(self):
return self.__mode
def setMode(self, mode):
self.__mode = mode
def getIV(self):
return self.__iv
def setIV(self, IV):
if not IV or len(IV) != self.block_size:
raise ValueError("Invalid Initial Value (IV), must be a multiple of " + str(self.block_size) + " bytes")
self.__iv = IV
def getPadding(self):
return self.__padding
def __String_to_BitList(self, data):
l = len(data) * 8
result = [0] * l
pos = 0
for c in data:
i = 7
ch = ord(c)
while i >= 0:
if ch & (1 << i) != 0:
result[pos] = 1
else:
result[pos] = 0
pos += 1
i -= 1
return result
def __BitList_to_String(self, data):
result = ''
pos = 0
c = 0
while pos < len(data):
c += data[pos] << (7 - (pos % 8))
if (pos % 8) == 7:
result += chr(c)
c = 0
pos += 1
return result
def __permutate(self, table, block):
return [block[x] for x in table]
def __create_sub_keys(self):
key = self.__permutate(Des.__pc1, self.__String_to_BitList(self.getKey()))
i = 0
self.L = key[:28]
self.R = key[28:]
while i < 16:
j = 0
while j < Des.__left_rotations[i]:
self.L.append(self.L[0])
del self.L[0]
self.R.append(self.R[0])
del self.R[0]
j += 1
self.Kn[i] = self.__permutate(Des.__pc2, self.L + self.R)
i += 1
def __des_crypt(self, block, crypt_type):
block = self.__permutate(Des.__ip, block)
self.L = block[:32]
self.R = block[32:]
if crypt_type == Des.ENCRYPT:
iteration = 0
iteration_adjustment = 1
else:
iteration = 15
iteration_adjustment = -1
i = 0
while i < 16:
tempR = self.R[:]
self.R = self.__permutate(Des.__expansion_table, self.R)
self.R = [x ^ y for x,y in zip(self.R, self.Kn[iteration])]
B = [self.R[:6], self.R[6:12], self.R[12:18], self.R[18:24], self.R[24:30], self.R[30:36], self.R[36:42], self.R[42:]]
j = 0
Bn = [0] * 32
pos = 0
while j < 8:
m = (B[j][0] << 1) + B[j][5]
n = (B[j][1] << 3) + (B[j][2] << 2) + (B[j][3] << 1) + B[j][4]
v = Des.__sbox[j][(m << 4) + n]
Bn[pos] = (v & 8) >> 3
Bn[pos + 1] = (v & 4) >> 2
Bn[pos + 2] = (v & 2) >> 1
Bn[pos + 3] = v & 1
pos += 4
j += 1
self.R = self.__permutate(Des.__p, Bn)
self.R = [x ^ y for x, y in zip(self.R, self.L)]
self.L = tempR
i += 1
iteration += iteration_adjustment
self.final = self.__permutate(Des.__fp, self.R + self.L)
return self.final
def crypt(self, data, crypt_type):
if not data:
return ''
if len(data) % self.block_size != 0:
if crypt_type == Des.DECRYPT: # Decryption must work on 8 byte blocks
raise ValueError("Invalid data length, data must be a multiple of " + str(self.block_size) + " bytes\n.")
if not self.getPadding():
raise ValueError("Invalid data length, data must be a multiple of " + str(self.block_size) + " bytes\n. Try setting the optional padding character")
else:
data += (self.block_size - (len(data) % self.block_size)) * self.getPadding()
if self.getMode() == CBC:
if self.getIV():
iv = self.__String_to_BitList(self.getIV())
else:
raise ValueError("For CBC mode, you must supply the Initial Value (IV) for ciphering")
i = 0
dict = {}
result = []
while i < len(data):
block = self.__String_to_BitList(data[i:i+8])
if self.getMode() == CBC:
if crypt_type == Des.ENCRYPT:
block = [x ^ y for x, y in zip(block, iv)]
processed_block = self.__des_crypt(block, crypt_type)
if crypt_type == Des.DECRYPT:
processed_block = [x ^ y for x, y in zip(processed_block, iv)]
iv = block
else:
iv = processed_block
else:
processed_block = self.__des_crypt(block, crypt_type)
result.append(self.__BitList_to_String(processed_block))
i += 8
if crypt_type == Des.DECRYPT and self.getPadding():
s = result[-1]
while s[-1] == self.getPadding():
s = s[:-1]
result[-1] = s
return ''.join(result)
def encrypt(self, data, pad=''):
self.__padding = pad
return self.crypt(data, Des.ENCRYPT)
def decrypt(self, data, pad=''):
self.__padding = pad
return self.crypt(data, Des.DECRYPT)

27
Other_Tools/eReader_PDB_Tools/lib/scrolltextwidget.py
View File

@@ -1,27 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import Tkinter
import Tkconstants
# basic scrolled text widget
class ScrolledText(Tkinter.Text):
def __init__(self, master=None, **kw):
self.frame = Tkinter.Frame(master)
self.vbar = Tkinter.Scrollbar(self.frame)
self.vbar.pack(side=Tkconstants.RIGHT, fill=Tkconstants.Y)
kw.update({'yscrollcommand': self.vbar.set})
Tkinter.Text.__init__(self, self.frame, **kw)
self.pack(side=Tkconstants.LEFT, fill=Tkconstants.BOTH, expand=True)
self.vbar['command'] = self.yview
# Copy geometry methods of self.frame without overriding Text
# methods = hack!
text_meths = vars(Tkinter.Text).keys()
methods = vars(Tkinter.Pack).keys() + vars(Tkinter.Grid).keys() + vars(Tkinter.Place).keys()
methods = set(methods).difference(text_meths)
for m in methods:
if m[0] != '_' and m != 'config' and m != 'configure':
setattr(self, m, getattr(self.frame, m))
def __str__(self):
return str(self.frame)

149
Other_Tools/eReader_PDB_Tools/lib/subasyncio.py
View File

@@ -1,149 +0,0 @@
#!/usr/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
import os, sys
import signal
import threading
import subprocess
from subprocess import Popen, PIPE, STDOUT
# **heavily** chopped up and modfied version of asyncproc.py
# to make it actually work on Windows as well as Mac/Linux
# For the original see:
# "http://www.lysator.liu.se/~bellman/download/"
# author is "Thomas Bellman <bellman@lysator.liu.se>"
# available under GPL version 3 or Later
# create an asynchronous subprocess whose output can be collected in
# a non-blocking manner
# What a mess! Have to use threads just to get non-blocking io
# in a cross-platform manner
# luckily all thread use is hidden within this class
class Process(object):
def __init__(self, *params, **kwparams):
if len(params) <= 3:
kwparams.setdefault('stdin', subprocess.PIPE)
if len(params) <= 4:
kwparams.setdefault('stdout', subprocess.PIPE)
if len(params) <= 5:
kwparams.setdefault('stderr', subprocess.PIPE)
self.__pending_input = []
self.__collected_outdata = []
self.__collected_errdata = []
self.__exitstatus = None
self.__lock = threading.Lock()
self.__inputsem = threading.Semaphore(0)
self.__quit = False
self.__process = subprocess.Popen(*params, **kwparams)
if self.__process.stdin:
self.__stdin_thread = threading.Thread(
name="stdin-thread",
target=self.__feeder, args=(self.__pending_input,
self.__process.stdin))
self.__stdin_thread.setDaemon(True)
self.__stdin_thread.start()
if self.__process.stdout:
self.__stdout_thread = threading.Thread(
name="stdout-thread",
target=self.__reader, args=(self.__collected_outdata,
self.__process.stdout))
self.__stdout_thread.setDaemon(True)
self.__stdout_thread.start()
if self.__process.stderr:
self.__stderr_thread = threading.Thread(
name="stderr-thread",
target=self.__reader, args=(self.__collected_errdata,
self.__process.stderr))
self.__stderr_thread.setDaemon(True)
self.__stderr_thread.start()
def pid(self):
return self.__process.pid
def kill(self, signal):
self.__process.send_signal(signal)
# check on subprocess (pass in 'nowait') to act like poll
def wait(self, flag):
if flag.lower() == 'nowait':
rc = self.__process.poll()
else:
rc = self.__process.wait()
if rc != None:
if self.__process.stdin:
self.closeinput()
if self.__process.stdout:
self.__stdout_thread.join()
if self.__process.stderr:
self.__stderr_thread.join()
return self.__process.returncode
def terminate(self):
if self.__process.stdin:
self.closeinput()
self.__process.terminate()
# thread gets data from subprocess stdout
def __reader(self, collector, source):
while True:
data = os.read(source.fileno(), 65536)
self.__lock.acquire()
collector.append(data)
self.__lock.release()
if data == "":
source.close()
break
return
# thread feeds data to subprocess stdin
def __feeder(self, pending, drain):
while True:
self.__inputsem.acquire()
self.__lock.acquire()
if not pending and self.__quit:
drain.close()
self.__lock.release()
break
data = pending.pop(0)
self.__lock.release()
drain.write(data)
# non-blocking read of data from subprocess stdout
def read(self):
self.__lock.acquire()
outdata = "".join(self.__collected_outdata)
del self.__collected_outdata[:]
self.__lock.release()
return outdata
# non-blocking read of data from subprocess stderr
def readerr(self):
self.__lock.acquire()
errdata = "".join(self.__collected_errdata)
del self.__collected_errdata[:]
self.__lock.release()
return errdata
# non-blocking write to stdin of subprocess
def write(self, data):
if self.__process.stdin is None:
raise ValueError("Writing to process with stdin not a pipe")
self.__lock.acquire()
self.__pending_input.append(data)
self.__inputsem.release()
self.__lock.release()
# close stdinput of subprocess
def closeinput(self):
self.__lock.acquire()
self.__quit = True
self.__inputsem.release()
self.__lock.release()

858
Other_Tools/eReader_PDB_Tools/lib/xpml2xhtml.py
View File

@@ -1,858 +0,0 @@
#!/bin/env python
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
#
# xPml2XHtml.py
#
# This is a python script. You need a Python interpreter to run it.
# For example, ActiveState Python, which exists for windows.
#
# Based on Code, Input and Ideas from:
# The Dark Reverser (original author)
# Kevin Hendricks
# Logan Kennelly
# John Schember (Calibre project)
# WayneD's (perl pml2html.pl)
# Changelog
# 0.02 - tried to greatly improve html conversion especially with \t tags
# 0.03 - more cleanup, a few fixes, and add in use of tidy to output xhtml
# 0.04 - incorporate more cleanups
# 0.05 - add check to fix block elements nested in inline elements which are not allowed
# 0.07 - handle clean up for remains left over from fixing nesting issues rampant in pml
# 0.08 - deal with inline style tags nesting issues in new way using a style tag list
# 0.09 - add in support for wrapping all text not in a block in <p></p> tags
# 0.10 - treat links effectively as block elements for style markup
# 0.11 - add in various paragraphs indentations to handle leading spaces that html would ignore or compress
# 0.12 - add in support for handling xml based pml footnotes and sidebars - using pseudo pml tags
# 0.14 - add in full header info parsing and remove need for bookinfo.txt
# 0.15 - cleanup high chars better handled, optional use of tidy with command line switch
# 0.16 - use proper and safe temporary file when passing things to tidy
# 0.17 - add support for tidy.exe under windows
# 0.18 - fix corner case of lines that start with \axxx or \Uxxxx tags
# 0.19 - change to use auto flushed stdout, and use proper return values
# 0.20 - properly handle T markup inside links
# 0.21 - properly handle new sigil Chapter Breaks for 0.2X series and up
__version__='0.21'
class Unbuffered:
def __init__(self, stream):
self.stream = stream
def write(self, data):
self.stream.write(data)
self.stream.flush()
def __getattr__(self, attr):
return getattr(self.stream, attr)
import sys
sys.stdout=Unbuffered(sys.stdout)
import struct, binascii, zlib, os, getopt, os.path, urllib, re, tempfile
import logging
from subprocess import Popen, PIPE, STDOUT
logging.basicConfig()
#logging.basicConfig(level=logging.DEBUG)
class PmlConverter(object):
def __init__(self, s):
def cleanupHighChars(src):
# special win1252 chars 0x80 - 0xa0 properly handled
src = re.sub('[\x80-\xff]', lambda x: '\\a%03d' % ord(x.group()), src)
src = re.sub('[^\x00-\xff]', lambda x: '\\U%04x' % ord(x.group()), src)
return src
def convertFootnoteXMLtoPseudoPML(src):
# creates pseudo tag \Ft="id"footnote text\Ft
p = re.compile(r'<footnote id="(?P<label>[^"]+)">\n')
m = p.search(src)
while m:
(b, e) = m.span()
fid = m.groups('label')[0]
src = src[0:b] + '\\p\\Ft="' + fid + '"' + src[e:]
src = re.sub('\n</footnote>\n','\\\\Ft\n\n',src,1)
m = p.search(src)
return src
def convertSidebarXMLtoPseudoPML(src):
# creates pseudo tag \St="id"sidebar text\St
p = re.compile(r'<sidebar id="(?P<label>[^"]+)">\n')
m = p.search(src)
while m:
(b, e) = m.span()
sid = m.groups('label')[0]
src = src[0:b] + '\\p\\St="' + sid + '"' + src[e:]
src = re.sub('\n</sidebar>\n','\\\\St\n\n',src,1)
m = p.search(src)
return src
def convert_x_to_pX0(src):
# converts all \x \x to \p\X0 \X0 make later code simpler
p = re.compile(r'\\x(.*?)\\x')
m = p.search(src)
while m:
(b, e) = m.span()
src = src[0:b] + '\\p\\X0' + src[b+2:e-2] + '\\X0' + src[e:]
m = p.search(src)
return src
def findPrevStartofLine(src,p,n):
# find last end of previous line in substring from p to n
b1 = src.rfind('\n',p,n)
b2 = src.rfind('\\c',p,n)
b3 = src.rfind('\\r',p,n)
b4 = src.rfind('\\x',p,n)
b5 = src.rfind('\\p',p,n)
b = max(b1, b2, b3, b4, b5)
if b == -1:
return n
if b == b1:
return b + 1
return b + 2
def markHangingIndents(src):
r = ''
p = 0
while True:
if p > len(src):
return r
n = src.find('\\t', p)
if n == -1:
r += src[p:]
return r
pc = findPrevStartofLine(src,p,n)
if pc == n :
# \t tag is at start of line so indent block will work
end = src.find('\\t',n+2)
if end == -1:
end = n
r += src[p:end+2]
p = end + 2
else :
# \t tag not at start of line so hanging indent case
# recode \t to pseudo \h tags and move it to start of this line
# and recode its close as well
r += src[p:pc] + '\\h' + src[pc:n]
end = src.find('\\t',n+2)
if end == -1:
end = n+2
r += src[n+2:end] + '\\h'
p = end + 2
return r
# recode double single slashes in pml to allow easier regular expression usage
s = s.replace('\\\\','_amp#92_')
s = cleanupHighChars(s)
s = markHangingIndents(s)
s = convertFootnoteXMLtoPseudoPML(s)
s = convertSidebarXMLtoPseudoPML(s)
s = convert_x_to_pX0(s)
# file('converted.pml','wb').write(s)
self.s = s
self.pos = 0
self.markChapters = (s.find('\\X') == -1)
def headerInfo(self):
title, author, copyright, publisher, eisbn = None, None, None, None, None
m = re.search(r'\\v.*TITLE="(?P<value>[^"]+)".*\\v', self.s, re.DOTALL)
if m:
title = m.groups('value')[0]
m = re.search(r'\\v.*AUTHOR="(?P<value>[^"]+)".*\\v', self.s, re.DOTALL)
if m:
author = m.groups('value')[0]
m = re.search(r'\\v.*PUBLISHER="(?P<value>[^"]+)".*\\v', self.s, re.DOTALL)
if m:
publisher = m.groups('value')[0]
m = re.search(r'\\v.*EISBN="(?P<value>[^"]+)".*\\v', self.s, re.DOTALL)
if m:
eisbn = m.groups('value')[0]
m = re.search(r'\\v.*COPYRIGHT="(?P<value>[^"]+)".*\\v', self.s, re.DOTALL)
if m:
copyright = m.groups('value')[0]
return title, author, copyright, publisher, eisbn
def nextOptAttr(self):
p = self.pos
if self.s[p:p+2] != '="':
return None
r = ''
p += 2
while self.s[p] != '"':
r += self.s[p]
p += 1
self.pos = p + 1
return r
def skipNewLine(self):
p = self.pos
if p >= len(self.s):
return
if self.s[p] == '\n':
self.pos = p + 1
return
def next(self):
p = self.pos
if p >= len(self.s):
return None
if self.s[p] != '\\':
res = self.s.find('\\', p)
if res == -1:
res = len(self.s)
self.pos = res
return self.s[p : res], None, None
c = self.s[p+1]
# add in support for new pseudo tag \\h
if c in 'pxcriuovthnsblBk-lI\\d':
self.pos = p + 2
return None, c, None
if c in 'TwmqQ':
self.pos = p + 2
return None, c, self.nextOptAttr()
if c == 'a':
self.pos = p + 5
return None, c, int(self.s[p+2:p+5])
if c == 'U':
self.pos = p + 6
return None, c, int(self.s[p+2:p+6], 16)
c = self.s[p+1:p+1+2]
if c in ('X0','X1','X2','X3','X4','Sp','Sb'):
self.pos = p + 3
return None, c, None
# add in support for new pseudo tags Ft and St
if c in ('C0','C1','C2','C3','C4','Fn','Sd', 'Ft', 'St'):
self.pos = p + 3
return None, c, self.nextOptAttr()
print "unknown escape code %s" % c
self.pos = p + 1
return None, None, None
def LinkPrinter(link):
return '<a href="%s">' % link
# for every footnote provide a unique id (built on footnote unique id)
# so that a hyperlink return is possibly
def FootnoteLinkPrinter(link):
rlink = 'return_' + link
footnote_ids[link] = rlink
return '<a id="%s" href="#%s">' % (rlink, link)
def Footnote(link):
return '<div title="footnote" id="%s">' % link
def EndFootnote(link):
return '&nbsp;&nbsp;<a href="#%s"><small>return</small></a></div>' % footnote_ids[link]
# for every sidebar provide a unique id (built from sidebar unique id)
# so that a hyperlink return is possibly
def SidebarLinkPrinter(link):
rlink = 'return_' + link
sidebar_ids[link] = rlink
return '<a id="%s" href="#%s">' % (rlink, link)
def Sidebar(link):
return '<div title="sidebar" id="%s">' % link
def EndSidebar(link):
return '&nbsp;&nbsp;<a href="#%s"><small>return</small></a></div>' % sidebar_ids[link]
# standard font switch is used mainly for special chars that may not be in user fonts
# but since these special chars are html encoded neither of these are needed
# def NormalFont(link):
# return '<!-- NormalFont -->%s' %link
# def EndNormalFont(link):
# return '<!-- EndNormalFont -->'
# def StdFont(link):
# return '<!-- StdFont -->%s' %link
# def EndStdFont(link):
# return '<!-- EndStdFont -->'
# See http://wiki.mobileread.com/wiki/PML#Palm_Markup_Language
# html non-style related beg and end tags
html_tags = {
'v' : ('<!-- ', ' -->'),
'c' : ('\n<div class="center">', '</div>\n'),
'r' : ('\n<div class="right">', '</div>\n'),
't' : ('<div class="indent">','</div>\n'),
'h' : ('<div class="hang">','</div>\n'), # pseudo-tag created to handle hanging indent cases
'X0' : ('<h1>', '</h1>\n'),
'X1' : ('<h2>', '</h2>\n'),
'X2' : ('<h3>', '</h3>\n'),
'X3' : ('<h4>', '</h4>\n'),
'X4' : ('<h5>', '</h5>\n'),
'q' : (LinkPrinter, '</a>'),
'Fn' : (FootnoteLinkPrinter, '</a>'),
'Sd' : (SidebarLinkPrinter, '</a>'),
'Ft' : (Footnote, EndFootnote),
'St' : (Sidebar, EndSidebar),
'I' : ('<i>', '</i>'),
'P' : ('<p>', '</p>\n'), # pseudo tag indicating a paragraph (imputed from pml file contents)
#'x' : ('<div class="breakafter"></div><h1>', '</h1>\n'), handled via recoding
}
# html style related beg and end tags
html_style_tags = {
'i' : ('<i>', '</i>'),
'u' : ('<span class="under">', '</span>'),
'b' : ('<b>', '</b>'),
'B' : ('<b>', '</b>'),
'o' : ('<del>', '</del>'),
'v' : ('<!-- ', ' -->'),
'Sb' : ('<sub>', '</sub>'),
'Sp' : ('<sup>', '</sup>'),
'l' : ('<span class="big">', '</span>'),
'k' : ('<span class="smallcaps">', '</span>'),
'I' : ('<i>', '</i>'), # according to calibre - all ereader does is italicize the index entries
'l' : ('<span class="big">', '</span>'),
'k' : ('<span class="smallcaps">', '</span>'),
#'n' : (NormalFont, EndNormalFont), handle as a single and strip out to prevent undesired mid word breaks
#'s' : (StdFont, EndStdFont), handle as a single and strip out to prevent undesired mid word breaks
}
# single tags (non-paired) that require no arguments
html_one_tags = {
#'p' : '<div class="breakafter"></div>\n', handle them in the if block to create at body level
#'\\': '\\', handled via recoding
'-' : '&shy;',
's' : '', # strip out see earlier note on standard and normla font use
'n' : '', # strip out see earlier note on standard and normla font use
}
# single tags that are not paired but that require attribute an argument
#'w' : handled in the if block,
#'m' : handled in if block,
#'Q' : handled in if block,
#'a' : handled in if block,
#'U' : handled in if block,
#'C0' : handled in if block,
#'C1' : handled in if block,
#'C2' : handled in if block,
#'C3' : handled in if block,
#'C4' : handled in if block,
#'T' : handled in if block,
html_block_tags = ('c','r','t','h','X0','X1','X2','X3','X4','x','P', 'Ft', 'St')
html_link_tags = ('q','Fn','Sd')
html_comment_tags = ('v')
pml_chars = {
128 : '&#8364;', 129 : '' , 130 : '&#8212;', 131 : '&#402;' , 132 : '&#8222;',
133 : '&#8230;', 134 : '&#8224;', 135 : '&#8225;', 136 : '&#710;' , 137 : '&#8240;',
138 : '&#352;' , 139 : '&#8249;', 140 : '&#338;' , 141 : '' , 142 : '&#381;' ,
143 : '' , 144 : '' , 145 : '&#8216;', 146 : '&#8217;', 147 : '&#8220;',
148 : '&#8221;', 149 : '&#8226;', 150 : '&#8211;', 151 : '&#8212;', 152 : '' ,
153 : '&#8482;', 154 : '&#353;' , 155 : '&#8250;', 156 : '&#339;' , 157 : '' ,
158 : '&#382;' , 159 : '&#376;' , 160 : '&nbsp;' ,
}
def process(self):
lastbreaksize = 0
final = '<!DOCTYPE HTML PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd">\n'
final += '<html>\n<head>\n'
final += '<meta http-equiv="content-type" content="text/html; charset=windows-1252"/>\n'
title, author, copyright, publisher, eisbn = self.headerInfo()
if not title: title = bookname
if not author: author = 'Unknown'
final += '<title>%s by %s</title>\n' % (title, author)
final += '<meta name="Title" content="%s"/>\n' % title
final += '<meta name="Author" content="%s"/>\n' % author
if copyright: final += '<meta name="Copyright" content="%s"/>\n' % copyright
if publisher: final += '<meta name="Publisher" content="%s"/>\n' % publisher
if eisbn: final += '<meta name="EISBN" content="%s"/>\n' % eisbn
final += '<style type="text/css">\n'
final += 'div.center { text-align:center; }\n'
final += 'div.right { text-align:right; }\n'
final += 'div.indent { margin-left: 5%; margin-right: 5%; }\n'
final += 'div.hang { text-indent: -5%; margin-left: 5%; margin-right: 5%; }\n'
final += 'span.big { font-size: 175%; }\n'
final += 'span.smallcaps { font-size: 80%; font-variant: small-caps; }\n'
final += 'span.under { text-decoration: underline; }\n'
final += '.breakafter { page-break-after: always; }\n'
final += 'p { text-indent: 0; margin-top: 0; margin-bottom: 0; }\n'
final += 'p.i0 { text-indent: 0; margin-top: 0; margin-bottom: 0; }\n'
final += 'p.i1 { text-indent: 1%; margin-top: 0; margin-bottom: 0; }\n'
final += 'p.i2 { text-indent: 2%; margin-top: 0; margin-bottom: 0; }\n'
final += 'p.i3 { text-indent: 3%; margin-top: 0; margin-bottom: 0; }\n'
final += 'p.i4 { text-indent: 4%; margin-top: 0; margin-bottom: 0; }\n'
final += 'p.i5 { text-indent: 5%; margin-top: 0; margin-bottom: 0; }\n'
final += '</style>\n'
final += '</head>\n<body>\n'
in_tags = []
st_tags = []
def inSet(slist):
rval = False
j = len(in_tags)
if j == 0:
return False
while True:
j = j - 1
if in_tags[j][0] in slist:
rval = True
break
if j == 0:
break
return rval
def inBlock():
return inSet(self.html_block_tags)
def inLink():
return inSet(self.html_link_tags)
def inComment():
return inSet(self.html_comment_tags)
def inParaNow():
j = len(in_tags)
if j == 0:
return False
if in_tags[j-1][0] == 'P':
return True
return False
def getTag(ti, end):
cmd, attr = ti
r = self.html_tags[cmd][end]
if type(r) != str:
r = r(attr)
return r
def getSTag(ti, end):
cmd, attr = ti
r = self.html_style_tags[cmd][end]
if type(r) != str:
r = r(attr)
return r
def applyStyles(ending):
s = ''
j = len(st_tags)
if j > 0:
if ending:
while True:
j = j - 1
s += getSTag(st_tags[j], True)
if j == 0:
break
else:
k = 0
while True:
s += getSTag(st_tags[k], False)
k = k + 1
if k == j:
break
return s
def indentLevel(line_start):
nb = 0
while line_start[nb:nb+1] == ' ':
nb = nb + 1
line_start = line_start[nb:]
if nb > 5:
nb = 5
return nb, line_start
def makeText(s):
# handle replacements required for html
s = s.replace('&', '&amp;')
s = s.replace('<', '&lt;')
s = s.replace('>', '&gt;')
return_s =''
# parse the text line by line
lp = s.find('\n')
while lp != -1:
line = s[0:lp]
s = s[lp+1:]
if not inBlock() and not inLink() and not inComment():
if len(line) > 0:
# text should not exist in the <body> tag level unless it is in a comment
nb, line = indentLevel(line)
return_s += '<p class="i%d">' % nb
return_s += applyStyles(False)
return_s += line
return_s += applyStyles(True)
return_s += '</p>\n'
else:
return_s += '<p>&nbsp;</p>\n'
elif inParaNow():
# text is a continuation of a previously started paragraph
return_s += line
return_s += applyStyles(True)
return_s += '</p>\n'
j = len(in_tags)
del in_tags[j-1]
else:
if len(line) > 0:
return_s += line + '<br />\n'
else:
return_s += '<br />\n'
lp = s.find('\n')
linefrag = s
if len(linefrag) > 0:
if not inBlock() and not inLink() and not inComment():
nb, linefrag = indentLevel(linefrag)
return_s += '<p class="i%d">' % nb
return_s += applyStyles(False)
return_s += linefrag
ppair = ('P', None)
in_tags.append(ppair)
else:
return_s += linefrag
return return_s
while True:
r = self.next()
if not r:
break
text, cmd, attr = r
if text:
final += makeText(text)
if cmd:
# handle pseudo paragraph P tags
# close if starting a new block element
if cmd in self.html_block_tags or cmd == 'w':
j = len(in_tags)
if j > 0:
if in_tags[j-1][0] == 'P':
final += applyStyles(True)
final += getTag(in_tags[j-1],True)
del in_tags[j-1]
if cmd in self.html_block_tags:
pair = (cmd, attr)
if cmd not in [a for (a,b) in in_tags]:
# starting a new block tag
final += getTag(pair, False)
final += applyStyles(False)
in_tags.append(pair)
else:
# process ending tag for a tag pair
# ending tag should be for the most recently added start tag
j = len(in_tags)
if cmd == in_tags[j-1][0]:
final += applyStyles(True)
final += getTag(in_tags[j-1], True)
del in_tags[j-1]
else:
# ow: things are not properly nested
# process ending tag for block
# ending tag **should** be for the most recently added block tag
# but in too many cases it is not so we must fix this by
# closing all open tags up to the current one and then
# reopen all of the tags we had to close due to improper nesting of styles
print 'Warning: Improperly Nested Block Tags: expected %s found %s' % (cmd, in_tags[j-1][0])
print 'after processing %s' % final[-40:]
j = len(in_tags)
while True:
j = j - 1
final += applyStyles(True)
final += getTag(in_tags[j], True)
if in_tags[j][0] == cmd:
break
del in_tags[j]
# now create new block start tags if they were previously open
while j < len(st_tags):
final += getTag(in_tags[j], False)
final += applyStyles(False)
j = j + 1
self.skipNewLine()
elif cmd in self.html_link_tags:
pair = (cmd, attr)
if cmd not in [a for (a,b) in in_tags]:
# starting a new link tag
# first close out any still open styles
if inBlock():
final += applyStyles(True)
# output start tag and styles needed
final += getTag(pair, False)
final += applyStyles(False)
in_tags.append(pair)
else:
# process ending tag for a tag pair
# ending tag should be for the most recently added start tag
j = len(in_tags)
if cmd == in_tags[j-1][0]:
j = len(in_tags)
# apply closing styles and tag
final += applyStyles(True)
final += getTag(in_tags[j-1], True)
# if needed reopen any style tags
if inBlock():
final += applyStyles(False)
del in_tags[j-1]
else:
# ow: things are not properly nested
print 'Error: Improperly Nested Link Tags: expected %s found %s' % (cmd, in_tags[j-1][0])
print 'after processing %s' % final[-40:]
elif cmd in self.html_style_tags:
spair = (cmd, attr)
if cmd not in [a for (a,b) in st_tags]:
# starting a new style
if inBlock() or inLink():
final += getSTag(spair,False)
st_tags.append(spair)
else:
# process ending tag for style
# ending tag **should** be for the most recently added style tag
# but in too many cases it is not so we must fix this by
# closing all open tags up to the current one and then
# reopen all of the tags we had to close due to improper nesting of styles
j = len(st_tags)
while True:
j = j - 1
if inBlock() or inLink():
final += getSTag(st_tags[j], True)
if st_tags[j][0] == cmd:
break
del st_tags[j]
# now create new style start tags if they were previously open
while j < len(st_tags):
if inBlock() or inLink():
final += getSTag(st_tags[j], False)
j = j + 1
elif cmd in self.html_one_tags:
final += self.html_one_tags[cmd]
elif cmd == 'p':
# create page breaks at the <body> level so
# they can be easily used for safe html file segmentation breakpoints
# first close any open tags
j = len(in_tags)
if j > 0:
while True:
j = j - 1
if in_tags[j][0] in self.html_block_tags:
final += applyStyles(True)
final += getTag(in_tags[j], True)
if j == 0:
break
# insert the page break tag
final += '\n<div class="breakafter"></div>\n'
if sigil_breaks:
if (len(final) - lastbreaksize) > 3000:
final += '<hr class="sigilChapterBreak" />\n'
lastbreaksize = len(final)
# now create new start tags for all tags that
# were previously open
while j < len(in_tags):
final += getTag(in_tags[j], False)
if in_tags[j][0] in self.html_block_tags:
final += applyStyles(False)
j = j + 1
self.skipNewLine()
elif cmd[0:1] == 'C':
if self.markChapters:
# create toc entries at the <body> level
# since they will be in an invisible block
# first close any open tags
j = len(in_tags)
if j > 0:
while True:
j = j - 1
if in_tags[j][0] in self.html_block_tags:
final += applyStyles(True)
final += getTag(in_tags[j], True)
if j == 0:
break
level = int(cmd[1:2]) + 1
final += '<h%d title="%s"></h%d>' % (level, attr, level)
# now create new start tags for all tags that
# were previously open
while j < len(in_tags):
final += getTag(in_tags[j], False)
if in_tags[j][0] in self.html_block_tags:
final += applyStyles(False)
j = j + 1
else:
final += '<!-- ToC%s: %s -->' % (cmd[1:2], attr)
# now handle single tags (non-paired) that have attributes
elif cmd == 'm':
unquotedimagepath = bookname + '_img/' + attr
imagepath = urllib.quote( unquotedimagepath )
final += '<img src="%s" alt="" />' % imagepath
elif cmd == 'Q':
final += '<span id="%s"> </span>' % attr
elif cmd == 'a':
if not inBlock() and not inLink() and not inComment():
final += '<p class="i0">'
final += applyStyles(False)
final += self.pml_chars.get(attr, '&#%d;' % attr)
ppair = ('P', None)
in_tags.append(ppair)
else:
final += self.pml_chars.get(attr, '&#%d;' % attr)
elif cmd == 'U':
if not inBlock() and not inLink() and not inComment():
final += '<p class="i0">'
final += applyStyles(False)
final += '&#%d;' % attr
ppair = ('P', None)
in_tags.append(ppair)
else:
final += makeText('&#%d;' % attr)
elif cmd == 'w':
# hr width and align parameters are not allowed in strict xhtml but style widths are possible
final += '\n<hr style="width: %s;" />' % attr
# final += '<div style="width: %s; margin-left: auto; margin-right: auto; \
# border-top-style: solid; border-top-color: grey; border-top-width: thin;">&nbsp;</div>' % attr
self.skipNewLine()
elif cmd == 'T':
if inBlock() or inLink() or inComment():
final += '<span style="margin-left: %s;">&nbsp;</span>' % attr
else:
final += '<p style="text-indent: %s;">' % attr
final += applyStyles(False)
ppair = ('P', None)
in_tags.append(ppair)
else:
logging.warning("Unknown tag: %s-%s", cmd, attr)
# handle file ending condition for imputed P tags
j = len(in_tags)
if (j > 0):
if in_tags[j-1][0] == 'P':
final += '</p>'
final += '</body>\n</html>\n'
# recode html back to a single slash
final = final.replace('_amp#92_', '\\')
# cleanup the html code for issues specifically generated by this translation process
# ending divs already break the line at the end so we don't need the <br /> we added
final = final.replace('</div><br />\n','</div>\n')
# clean up empty elements that can be created when fixing improperly nested pml tags
# and by moving page break tags to the body level so that they can be used as html file split points
while True:
s = final
final = final.replace('<b></b>','')
final = final.replace('<i></i>','')
final = final.replace('<del></del>','')
final = final.replace('<sup></sup>','')
final = final.replace('<sub></sub>','')
final = final.replace('<span class="under"></span>','')
final = final.replace('<span class="big"></span>','')
final = final.replace('<span class="smallcaps"></span>','')
final = final.replace('<span class="under"> </span>','')
final = final.replace('<span class="big"> </span>','')
final = final.replace('<span class="smallcaps"> </span>','')
final = final.replace('<p></p>','')
final = final.replace('<p> </p>','')
final = final.replace('<p class="i0"></p>','')
final = final.replace('<p class="i1"></p>','')
final = final.replace('<p class="i2"></p>','')
final = final.replace('<p class="i3"></p>','')
final = final.replace('<p class="i4"></p>','')
final = final.replace('<p class="i5"></p>','')
final = final.replace('<h1></h1>\n','')
final = final.replace('<h2></h2>\n','')
final = final.replace('<h3></h3>\n','')
final = final.replace('<h4></h4>\n','')
final = final.replace('<h5></h5>\n','')
final = final.replace('<div class="center"></div>\n','')
final = final.replace('<div class="hang"></div>\n','')
final = final.replace('<div class="indent"></div>\n','')
final = final.replace('<div class="right"></div>\n','')
if s == final:
break
return final
def tidy(rawhtmlfile):
# processes rawhtmlfile through command line tidy via pipes
rawfobj = file(rawhtmlfile,'rb')
# --doctype strict forces strict dtd checking
# --enclose-text yes - enclosees non-block electment text inside <body></body> into its own <p></p> block to meet xhtml spec
# -w 100 -i will wrap text at column 120 and indent it to indicate level of nesting to make structure clearer
# -win1252 sets the input encoding of pml files
# -asxhtml convert to xhtml
# -q (quiet)
cmdline = 'tidy -w 120 -i -q -asxhtml -win1252 --enclose-text yes --doctype strict '
if sys.platform[0:3] == 'win':
cmdline = 'tidy.exe -w 120 -i -q -asxhtml -win1252 --enclose-text yes --doctype strict '
p2 = Popen(cmdline, shell=True, stdin=rawfobj, stdout=PIPE, stderr=PIPE, close_fds=False)
stdout, stderr = p2.communicate()
# print "Tidy Original Conversion Warnings and Errors"
# print stderr
return stdout
def usage():
print "Converts PML file to XHTML"
print "Usage:"
print " xpml2xhtml [options] infile.pml outfile.html "
print " "
print "Options: "
print " -h prints this message"
print " --sigil-breaks insert Sigil Chapterbbreaks"
print " --use-tidy use tidy to further clean up the html "
print " "
return
def main(argv=None):
global bookname
global footnote_ids
global sidebar_ids
global sigil_breaks
try:
opts, args = getopt.getopt(sys.argv[1:], "h", ["sigil-breaks", "use-tidy"])
except getopt.GetoptError, err:
print str(err)
usage()
return 1
if len(args) != 2:
usage()
return 1
sigil_breaks = False
use_tidy = False
for o, a in opts:
if o == "-h":
usage()
return 0
elif o == "--sigil-breaks":
sigil_breaks = True
elif o == "--use-tidy":
use_tidy = True
infile, outfile = args[0], args[1]
bookname = os.path.splitext(os.path.basename(infile))[0]
footnote_ids = { }
sidebar_ids = { }
try:
print "Processing..."
import time
start_time = time.time()
print " Converting pml to raw html"
pml_string = file(infile,'rb').read()
pml = PmlConverter(pml_string)
html_src = pml.process()
if use_tidy:
print " Tidying html to xhtml"
fobj = tempfile.NamedTemporaryFile(mode='w+b',suffix=".html",delete=False)
tempname = fobj.name
fobj.write(html_src)
fobj.close()
html_src = tidy(tempname)
os.remove(tempname)
file(outfile,'wb').write(html_src)
end_time = time.time()
convert_time = end_time - start_time
print 'elapsed time: %.2f seconds' % (convert_time, )
print 'output is in file %s' % outfile
print "Finished Processing"
except ValueError, e:
print "Error: %s" % e
return 1
return 0
if __name__ == "__main__":
#import cProfile
#command = """sys.exit(main())"""
#cProfile.runctx( command, globals(), locals(), filename="cprofile.profile" )
sys.exit(main())