tools v2.2

This commit is contained in:
Apprentice Alf
2010-11-11 22:11:36 +00:00
parent 5f0671db7f
commit c386ac6e6d
100 changed files with 3157 additions and 4807 deletions

View File

@@ -0,0 +1,17 @@
ePub_Fixer
ePubs are specially crafted zip archives. Unfortunately, many of te 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.

189
ePub_Fixer/ePub_Fixer.pyw Normal file
View File

@@ -0,0 +1,189 @@
#!/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 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 !='':
msg = msg.encode('utf-8')
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')
cmdline = 'python ./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 = 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'
log = log.encode('utf-8')
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())

View File

@@ -0,0 +1,27 @@
#!/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)

View File

@@ -0,0 +1,149 @@
#!/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()

136
ePub_Fixer/lib/zipfix.py Normal file
View File

@@ -0,0 +1,136 @@
#!/usr/bin/env python
import sys
import zlib
import zipfile
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
class fixZip:
def __init__(self, zinput, zoutput):
self.inzip = zipfile.ZipFile(zinput,'r')
self.outzip = zipfile.ZipFile(zoutput,'w')
# open the input zip for reading only as a raw file
self.bzf = file(zinput,'rb')
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 == zipfile.ZIP_STORED:
data = self.bzf.read(zi.file_size)
# if compressed we must decompress it using zlib
if zi.compress_type == zipfile.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
for i, zinfo in enumerate(self.inzip.infolist()):
data = None
nzinfo = zinfo
try:
data = self.inzip.read(zinfo)
except zipfile.BadZipfile or zipfile.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 main(argv=sys.argv):
if len(argv)!=3:
usage()
return 1
infile = None
outfile = None
infile = argv[1]
outfile = argv[2]
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
if __name__ == '__main__' :
sys.exit(main())