tools v5.0
Introduction of alfcrypto library for speed Reorganisation of archive plugins,apps,other
This commit is contained in:
Apprentice Alf
@@ -4,28 +4,62 @@ from __future__ import with_statement
|
||||
|
||||
from calibre.customize import FileTypePlugin
|
||||
from calibre.gui2 import is_ok_to_use_qt
|
||||
from calibre.utils.config import config_dir
|
||||
from calibre.constants import iswindows, isosx
|
||||
# from calibre.ptempfile import PersistentTemporaryDirectory
|
||||
|
||||
from calibre_plugins.k4mobidedrm import kgenpids
|
||||
from calibre_plugins.k4mobidedrm import topazextract
|
||||
from calibre_plugins.k4mobidedrm import mobidedrm
|
||||
|
||||
import sys
|
||||
import os
|
||||
import re
|
||||
from zipfile import ZipFile
|
||||
|
||||
class K4DeDRM(FileTypePlugin):
|
||||
name = 'K4PC, K4Mac, Kindle Mobi and Topaz DeDRM' # Name of the plugin
|
||||
description = 'Removes DRM from Mobipocket, Kindle/Mobi, Kindle/Topaz and Kindle/Print Replica files. Provided by the work of many including DiapDealer, SomeUpdates, IHeartCabbages, CMBDTC, Skindle, DarkReverser, ApprenticeAlf, etc.'
|
||||
supported_platforms = ['osx', 'windows', 'linux'] # Platforms this plugin will run on
|
||||
author = 'DiapDealer, SomeUpdates' # The author of this plugin
|
||||
version = (0, 3, 8) # The version number of this plugin
|
||||
version = (0, 4, 1) # The version number of this plugin
|
||||
file_types = set(['prc','mobi','azw','azw1','azw4','tpz']) # The file types that this plugin will be applied to
|
||||
on_import = True # Run this plugin during the import
|
||||
priority = 210 # run this plugin before mobidedrm, k4pcdedrm, k4dedrm
|
||||
minimum_calibre_version = (0, 7, 55)
|
||||
|
||||
def initialize(self):
|
||||
"""
|
||||
Dynamic modules can't be imported/loaded from a zipfile... so this routine
|
||||
runs whenever the plugin gets initialized. This will extract the appropriate
|
||||
library for the target OS and copy it to the 'alfcrypto' subdirectory of
|
||||
calibre's configuration directory. That 'alfcrypto' directory is then
|
||||
inserted into the syspath (as the very first entry) in the run function
|
||||
so the CDLL stuff will work in the alfcrypto.py script.
|
||||
"""
|
||||
if iswindows:
|
||||
names = ['alfcrypto.dll','alfcrypto64.dll']
|
||||
elif isosx:
|
||||
names = ['libalfcrypto.dylib']
|
||||
else:
|
||||
names = ['libalfcrypto32.so','libalfcrypto64.so']
|
||||
lib_dict = self.load_resources(names)
|
||||
self.alfdir = os.path.join(config_dir, 'alfcrypto')
|
||||
if not os.path.exists(self.alfdir):
|
||||
os.mkdir(self.alfdir)
|
||||
for entry, data in lib_dict.items():
|
||||
file_path = os.path.join(self.alfdir, entry)
|
||||
with open(file_path,'wb') as f:
|
||||
f.write(data)
|
||||
|
||||
def run(self, path_to_ebook):
|
||||
# add the alfcrypto directory to sys.path so alfcrypto.py
|
||||
# will be able to locate the custom lib(s) for CDLL import.
|
||||
sys.path.insert(0, self.alfdir)
|
||||
# Had to move these imports here so the custom libs can be
|
||||
# extracted to the appropriate places beforehand these routines
|
||||
# look for them.
|
||||
from calibre_plugins.k4mobidedrm import kgenpids
|
||||
from calibre_plugins.k4mobidedrm import topazextract
|
||||
from calibre_plugins.k4mobidedrm import mobidedrm
|
||||
|
||||
plug_ver = '.'.join(str(self.version).strip('()').replace(' ', '').split(','))
|
||||
k4 = True
|
||||
if sys.platform.startswith('linux'):
|
||||
@@ -45,7 +79,7 @@ class K4DeDRM(FileTypePlugin):
|
||||
serials.append(customvalue)
|
||||
else:
|
||||
print "%s is not a valid Kindle serial number or PID." % str(customvalue)
|
||||
|
||||
|
||||
# Load any kindle info files (*.info) included Calibre's config directory.
|
||||
try:
|
||||
# Find Calibre's configuration directory.
|
||||
@@ -77,7 +111,7 @@ class K4DeDRM(FileTypePlugin):
|
||||
|
||||
title = mb.getBookTitle()
|
||||
md1, md2 = mb.getPIDMetaInfo()
|
||||
pidlst = kgenpids.getPidList(md1, md2, k4, pids, serials, kInfoFiles)
|
||||
pidlst = kgenpids.getPidList(md1, md2, k4, pids, serials, kInfoFiles)
|
||||
|
||||
try:
|
||||
mb.processBook(pidlst)
|
||||
@@ -94,11 +128,11 @@ class K4DeDRM(FileTypePlugin):
|
||||
except topazextract.TpzDRMError, e:
|
||||
#if you reached here then no luck raise and exception
|
||||
if is_ok_to_use_qt():
|
||||
from PyQt4.Qt import QMessageBox
|
||||
d = QMessageBox(QMessageBox.Warning, "K4MobiDeDRM v%s Plugin" % plug_ver, "Error: " + str(e) + "... %s\n" % path_to_ebook)
|
||||
d.show()
|
||||
d.raise_()
|
||||
d.exec_()
|
||||
from PyQt4.Qt import QMessageBox
|
||||
d = QMessageBox(QMessageBox.Warning, "K4MobiDeDRM v%s Plugin" % plug_ver, "Error: " + str(e) + "... %s\n" % path_to_ebook)
|
||||
d.show()
|
||||
d.raise_()
|
||||
d.exec_()
|
||||
raise Exception("K4MobiDeDRM plugin v%s Error: %s" % (plug_ver, str(e)))
|
||||
|
||||
print "Success!"
|
||||
@@ -117,3 +151,11 @@ class K4DeDRM(FileTypePlugin):
|
||||
|
||||
def customization_help(self, gui=False):
|
||||
return 'Enter 10 character PIDs and/or Kindle serial numbers, use a comma (no spaces) to separate each PID or SerialNumber from the next.'
|
||||
|
||||
def load_resources(self, names):
|
||||
ans = {}
|
||||
with ZipFile(self.plugin_path, 'r') as zf:
|
||||
for candidate in zf.namelist():
|
||||
if candidate in names:
|
||||
ans[candidate] = zf.read(candidate)
|
||||
return ans
|
||||
File diff suppressed because it is too large
Load Diff
Binary file not shown.
@@ -1,250 +1,290 @@
|
||||
#! /usr/bin/python
|
||||
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
|
||||
#! /usr/bin/env python
|
||||
|
||||
import sys
|
||||
import csv
|
||||
import os
|
||||
import getopt
|
||||
import sys, os
|
||||
import hmac
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
import hashlib
|
||||
|
||||
|
||||
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'))
|
||||
# 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
|
||||
|
||||
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
|
||||
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:
|
||||
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):
|
||||
ml = ''
|
||||
pp = PParser(gdict, flat_xml, meta_array)
|
||||
ml += '<?xml version="1.0" standalone="no"?>\n'
|
||||
if (raw):
|
||||
ml += '<!DOCTYPE svg PUBLIC "-//W3C/DTD SVG 1.1//EN" "http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd">\n'
|
||||
ml += '<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)
|
||||
ml += '<title>Page %d - %s by %s</title>\n' % (pageid, meta_array['Title'],meta_array['Authors'])
|
||||
name_of_lib = 'alfcrypto64.dll'
|
||||
else:
|
||||
ml += '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">\n'
|
||||
ml += '<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" ><head>\n'
|
||||
ml += '<title>Page %d - %s by %s</title>\n' % (pageid, meta_array['Title'],meta_array['Authors'])
|
||||
ml += '<script><![CDATA[\n'
|
||||
ml += 'function gd(){var p=window.location.href.replace(/^.*\?dpi=(\d+).*$/i,"$1");return p;}\n'
|
||||
ml += 'var dpi=%d;\n' % scaledpi
|
||||
if (previd) :
|
||||
ml += 'var prevpage="page%04d.xhtml";\n' % (previd)
|
||||
if (nextid) :
|
||||
ml += 'var nextpage="page%04d.xhtml";\n' % (nextid)
|
||||
ml += 'var pw=%d;var ph=%d;' % (pp.pw, pp.ph)
|
||||
ml += 'function zoomin(){dpi=dpi*(0.8);setsize();}\n'
|
||||
ml += 'function zoomout(){dpi=dpi*1.25;setsize();}\n'
|
||||
ml += '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'
|
||||
ml += 'function ppage(){window.location.href=prevpage+"?dpi="+Math.round(dpi);}\n'
|
||||
ml += 'function npage(){window.location.href=nextpage+"?dpi="+Math.round(dpi);}\n'
|
||||
ml += 'var gt=gd();if(gt>0){dpi=gt;}\n'
|
||||
ml += 'window.onload=setsize;\n'
|
||||
ml += ']]></script>\n'
|
||||
ml += '</head>\n'
|
||||
ml += '<body onLoad="setsize();" style="background-color:#777;text-align:center;">\n'
|
||||
ml += '<div style="white-space:nowrap;">\n'
|
||||
if previd == None:
|
||||
ml += '<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'
|
||||
if pointer_size == 4:
|
||||
name_of_lib = 'libalfcrypto32.so'
|
||||
else:
|
||||
ml += '<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'
|
||||
|
||||
ml += '<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):
|
||||
ml += '<defs>\n'
|
||||
gdefs = pp.getGlyphs()
|
||||
for j in xrange(0,len(gdefs)):
|
||||
ml += gdefs[j]
|
||||
ml += '</defs>\n'
|
||||
img = pp.getImages()
|
||||
if (img != None):
|
||||
for j in xrange(0,len(img)):
|
||||
ml += img[j]
|
||||
if (pp.gid != None):
|
||||
for j in xrange(0,len(pp.gid)):
|
||||
ml += '<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)
|
||||
ml += '<text x="' + xpos + '" y="' + ypos + '" font-size="' + meta_array['fontSize'] + '" font-family="Helvetica" stroke="black">This page intentionally left blank.</text>\n'
|
||||
if (raw) :
|
||||
ml += '</svg>'
|
||||
else :
|
||||
ml += '</svg></a>\n'
|
||||
if nextid == None:
|
||||
ml += '<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 :
|
||||
ml += '<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'
|
||||
ml += '</div>\n'
|
||||
ml += '<div><a href="javascript:zoomin();">zoom in</a> - <a href="javascript:zoomout();">zoom out</a></div>\n'
|
||||
ml += '</body>\n'
|
||||
ml += '</html>\n'
|
||||
return ml
|
||||
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]
|
||||
|
||||
|
||||
|
||||
Binary file not shown.
Binary file not shown.
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,726 @@
|
||||
# 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/Application Support/Kindle'
|
||||
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
|
||||
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:
|
||||
return mungedmac
|
||||
sernum = GetVolumeSerialNumber()
|
||||
if len(sernum) > 7:
|
||||
return sernum
|
||||
diskpart = GetUserHomeAppSupKindleDirParitionName()
|
||||
uuidnum = GetDiskPartitionUUID(diskpart)
|
||||
if len(uuidnum) > 7:
|
||||
return uuidnum
|
||||
mungedmac = GetMACAddressMunged()
|
||||
if len(mungedmac) > 7:
|
||||
return mungedmac
|
||||
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(kInfoFiles):
|
||||
# first search for current .kindle-info files
|
||||
home = os.getenv('HOME')
|
||||
cmdline = 'find "' + home + '/Library/Application Support" -name ".kindle-info"'
|
||||
cmdline = cmdline.encode(sys.getfilesystemencoding())
|
||||
p1 = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
|
||||
out1, out2 = p1.communicate()
|
||||
reslst = out1.split('\n')
|
||||
kinfopath = 'NONE'
|
||||
found = False
|
||||
for resline in reslst:
|
||||
if os.path.isfile(resline):
|
||||
kInfoFiles.append(resline)
|
||||
found = True
|
||||
# add any .rainier*-kinf files
|
||||
cmdline = 'find "' + home + '/Library/Application Support" -name ".rainier*-kinf"'
|
||||
cmdline = cmdline.encode(sys.getfilesystemencoding())
|
||||
p1 = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
|
||||
out1, out2 = p1.communicate()
|
||||
reslst = out1.split('\n')
|
||||
for resline in reslst:
|
||||
if os.path.isfile(resline):
|
||||
kInfoFiles.append(resline)
|
||||
found = True
|
||||
# add any .kinf2011 files
|
||||
cmdline = 'find "' + home + '/Library/Application Support" -name ".kinf2011"'
|
||||
cmdline = cmdline.encode(sys.getfilesystemencoding())
|
||||
p1 = subprocess.Popen(cmdline, shell=True, stdin=None, stdout=subprocess.PIPE, stderr=subprocess.PIPE, close_fds=False)
|
||||
out1, out2 = p1.communicate()
|
||||
reslst = out1.split('\n')
|
||||
for resline in reslst:
|
||||
if os.path.isfile(resline):
|
||||
kInfoFiles.append(resline)
|
||||
found = True
|
||||
if not found:
|
||||
print('No kindle-info 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
|
||||
|
||||
@@ -1,50 +1,134 @@
|
||||
#! /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 sys
|
||||
import os
|
||||
import getopt
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
|
||||
class TpzDRMError(Exception):
|
||||
pass
|
||||
|
||||
class DocParser(object):
|
||||
def __init__(self, flatxml, fontsize, ph, pw):
|
||||
# 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('&','&')
|
||||
str = str.replace('<','<')
|
||||
str = str.replace('>','>')
|
||||
str = str.replace('=','=')
|
||||
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')
|
||||
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
|
||||
@@ -58,198 +142,568 @@ class DocParser(object):
|
||||
for j in xrange(pos, end):
|
||||
item = docList[j]
|
||||
if item.find('=') >= 0:
|
||||
(name, argres) = item.split('=',1)
|
||||
else :
|
||||
(name, argres) = item.split('=')
|
||||
else :
|
||||
name = item
|
||||
argres = ''
|
||||
if name.endswith(tagpath) :
|
||||
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
|
||||
|
||||
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
|
||||
|
||||
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 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
|
||||
|
||||
def getPageDim(flatxml):
|
||||
# create a document parser
|
||||
dp = DocParser(flatxml, fontsize, ph, pw)
|
||||
csspage = dp.process()
|
||||
return csspage
|
||||
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
|
||||
|
||||
|
||||
def getpageIDMap(flatxml):
|
||||
dp = DocParser(flatxml, 0, 0, 0)
|
||||
pageidnumbers = dp.getData('info.original.pid', 0, -1)
|
||||
return pageidnumbers
|
||||
|
||||
# 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('&','&')
|
||||
title = title.replace('<','<')
|
||||
title = title.replace('>','>')
|
||||
meta_array['Title'] = title
|
||||
authors = meta_array.get('Authors','No Authors Provided')
|
||||
authors = authors.replace('&','&')
|
||||
authors = authors.replace('<','<')
|
||||
authors = authors.replace('>','>')
|
||||
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
|
||||
fontsize = '135'
|
||||
if 'fontSize' in meta_array:
|
||||
fontsize = meta_array['fontSize']
|
||||
|
||||
# also get the size of a normal text page
|
||||
spage = '1'
|
||||
if 'firstTextPage' in meta_array:
|
||||
spage = meta_array['firstTextPage']
|
||||
pnum = int(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(''))
|
||||
|
||||
@@ -1,5 +1,24 @@
|
||||
#!/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__ = '4.0'
|
||||
|
||||
class Unbuffered:
|
||||
def __init__(self, stream):
|
||||
self.stream = stream
|
||||
@@ -10,460 +29,184 @@ class Unbuffered:
|
||||
return getattr(self.stream, attr)
|
||||
|
||||
import sys
|
||||
import os, csv, getopt
|
||||
import string
|
||||
import re
|
||||
import traceback
|
||||
|
||||
buildXML = False
|
||||
|
||||
class DrmException(Exception):
|
||||
pass
|
||||
|
||||
if 'calibre' in sys.modules:
|
||||
inCalibre = True
|
||||
else:
|
||||
inCalibre = False
|
||||
|
||||
import os, csv, getopt
|
||||
import zlib, zipfile, tempfile, shutil
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
|
||||
class TpzDRMError(Exception):
|
||||
pass
|
||||
|
||||
|
||||
# local support routines
|
||||
if inCalibre:
|
||||
from calibre_plugins.k4mobidedrm import mobidedrm
|
||||
from calibre_plugins.k4mobidedrm import topazextract
|
||||
from calibre_plugins.k4mobidedrm import kgenpids
|
||||
from calibre_plugins.k4mobidedrm import genbook
|
||||
else:
|
||||
import mobidedrm
|
||||
import topazextract
|
||||
import kgenpids
|
||||
import genbook
|
||||
|
||||
|
||||
# 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)
|
||||
# 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 spaces to underscores
|
||||
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
|
||||
|
||||
#
|
||||
# Utility routines
|
||||
#
|
||||
def decryptBook(infile, outdir, k4, kInfoFiles, serials, pids):
|
||||
global buildXML
|
||||
|
||||
# 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]
|
||||
# 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
|
||||
|
||||
#
|
||||
# crypto routines
|
||||
#
|
||||
mobi = True
|
||||
magic3 = file(infile,'rb').read(3)
|
||||
if magic3 == 'TPZ':
|
||||
mobi = False
|
||||
|
||||
# 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
|
||||
bookname = os.path.splitext(os.path.basename(infile))[0]
|
||||
|
||||
# Decrypt data with the PID
|
||||
def decryptRecord(data,PID):
|
||||
ctx = topazCryptoInit(PID)
|
||||
return topazCryptoDecrypt(data, ctx)
|
||||
if mobi:
|
||||
mb = mobidedrm.MobiBook(infile)
|
||||
else:
|
||||
mb = topazextract.TopazBook(infile)
|
||||
|
||||
# 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]
|
||||
title = mb.getBookTitle()
|
||||
print "Processing Book: ", title
|
||||
filenametitle = cleanup_name(title)
|
||||
outfilename = bookname
|
||||
if len(outfilename)<=8 or len(filenametitle)<=8:
|
||||
outfilename = outfilename + "_" + filenametitle
|
||||
elif outfilename[:8] != filenametitle[:8]:
|
||||
outfilename = outfilename[:8] + "_" + filenametitle
|
||||
|
||||
# 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
|
||||
# avoid excessively long file names
|
||||
if len(outfilename)>150:
|
||||
outfilename = outfilename[:150]
|
||||
|
||||
# build pid list
|
||||
md1, md2 = mb.getPIDMetaInfo()
|
||||
pidlst = kgenpids.getPidList(md1, md2, k4, pids, serials, kInfoFiles)
|
||||
|
||||
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()
|
||||
try:
|
||||
mb.processBook(pidlst)
|
||||
|
||||
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()
|
||||
except mobidedrm.DrmException, e:
|
||||
print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
|
||||
return 1
|
||||
except topazextract.TpzDRMError, e:
|
||||
print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
|
||||
return 1
|
||||
except Exception, e:
|
||||
print >>sys.stderr, ('K4MobiDeDrm v%(__version__)s\n' % globals()) + "Error: " + str(e) + "\nDRM Removal Failed.\n"
|
||||
return 1
|
||||
|
||||
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])
|
||||
if mobi:
|
||||
if mb.getPrintReplica():
|
||||
outfile = os.path.join(outdir, outfilename + '_nodrm' + '.azw4')
|
||||
else:
|
||||
record = self.fo.read(self.bookHeaderRecords[name][index][1])
|
||||
outfile = os.path.join(outdir, outfilename + '_nodrm' + '.mobi')
|
||||
mb.getMobiFile(outfile)
|
||||
return 0
|
||||
|
||||
if encrypted:
|
||||
if self.bookKey:
|
||||
ctx = topazCryptoInit(self.bookKey)
|
||||
record = topazCryptoDecrypt(record,ctx)
|
||||
else :
|
||||
raise TpzDRMError("Error: Attempt to decrypt without bookKey")
|
||||
# topaz:
|
||||
print " Creating NoDRM HTMLZ Archive"
|
||||
zipname = os.path.join(outdir, outfilename + '_nodrm' + '.htmlz')
|
||||
mb.getHTMLZip(zipname)
|
||||
|
||||
if compressed:
|
||||
record = zlib.decompress(record)
|
||||
print " Creating SVG ZIP Archive"
|
||||
zipname = os.path.join(outdir, outfilename + '_SVG' + '.zip')
|
||||
mb.getSVGZip(zipname)
|
||||
|
||||
return record
|
||||
if buildXML:
|
||||
print " Creating XML ZIP Archive"
|
||||
zipname = os.path.join(outdir, outfilename + '_XML' + '.zip')
|
||||
mb.getXMLZip(zipname)
|
||||
|
||||
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"
|
||||
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
|
||||
# remove internal temporary directory of Topaz pieces
|
||||
mb.cleanup()
|
||||
|
||||
if not bookKey:
|
||||
raise TpzDRMError('Decryption Unsucessful; No valid pid found')
|
||||
return 0
|
||||
|
||||
self.setBookKey(bookKey)
|
||||
self.createBookDirectory()
|
||||
self.extractFiles()
|
||||
print "Successfully Extracted Topaz contents"
|
||||
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):
|
||||
pass
|
||||
# shutil.rmtree(self.outdir, True)
|
||||
|
||||
def usage(progname):
|
||||
print "Removes DRM protection from Topaz ebooks and extract the contents"
|
||||
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
|
||||
pids = []
|
||||
serials = []
|
||||
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)
|
||||
return 1
|
||||
sys.exit(2)
|
||||
if len(args)<2:
|
||||
usage(progname)
|
||||
return 1
|
||||
|
||||
sys.exit(2)
|
||||
|
||||
for o, a in opts:
|
||||
if o == "-k":
|
||||
if a == None :
|
||||
print "Invalid parameter for -k"
|
||||
return 1
|
||||
raise DrmException("Invalid parameter for -k")
|
||||
kInfoFiles.append(a)
|
||||
if o == "-p":
|
||||
if a == None :
|
||||
print "Invalid parameter for -p"
|
||||
return 1
|
||||
raise DrmException("Invalid parameter for -p")
|
||||
pids = a.split(',')
|
||||
if o == "-s":
|
||||
if a == None :
|
||||
print "Invalid parameter for -s"
|
||||
return 1
|
||||
raise DrmException("Invalid parameter for -s")
|
||||
serials = a.split(',')
|
||||
k4 = True
|
||||
|
||||
# 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 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()
|
||||
pidlst = kgenpids.getPidList(keysRecord, keysRecordRecord, k4, pids, serials, kInfoFiles)
|
||||
|
||||
try:
|
||||
print "Decrypting Book"
|
||||
tb.processBook(pidlst)
|
||||
|
||||
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)
|
||||
|
||||
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())
|
||||
|
||||
|
||||
Binary file not shown.
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,444 +1,249 @@
|
||||
#!/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
|
||||
|
||||
__version__ = '0.32'
|
||||
#! /usr/bin/python
|
||||
# vim:ts=4:sw=4:softtabstop=4:smarttab:expandtab
|
||||
|
||||
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 csv
|
||||
import os
|
||||
import struct
|
||||
import binascii
|
||||
|
||||
class DrmException(Exception):
|
||||
pass
|
||||
import getopt
|
||||
from struct import pack
|
||||
from struct import unpack
|
||||
|
||||
|
||||
#
|
||||
# MobiBook Utility Routines
|
||||
#
|
||||
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 = []
|
||||
|
||||
# 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
|
||||
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))
|
||||
|
||||
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
|
||||
if self.ph <= 0:
|
||||
self.ph = int(meta_array.get('pageHeight', '11000'))
|
||||
if self.pw <= 0:
|
||||
self.pw = int(meta_array.get('pageWidth', '8500'))
|
||||
|
||||
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
|
||||
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
|
||||
|
||||
class MobiBook:
|
||||
def loadSection(self, section):
|
||||
if (section + 1 == self.num_sections):
|
||||
endoff = len(self.data_file)
|
||||
# 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:
|
||||
endoff = self.sections[section + 1][0]
|
||||
off = self.sections[section][0]
|
||||
return self.data_file[off:endoff]
|
||||
|
||||
def __init__(self, infile):
|
||||
print ('MobiDeDrm v%(__version__)s. '
|
||||
'Copyright 2008-2011 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_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 = ''
|
||||
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 title == '':
|
||||
title = self.header[:32]
|
||||
title = title.split("\0")[0]
|
||||
codec = 'windows-1252'
|
||||
if self.mobi_codepage in codec_map.keys():
|
||||
codec = codec_map[self.mobi_codepage]
|
||||
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:
|
||||
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
|
||||
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]
|
||||
return foundat, result
|
||||
|
||||
def getMobiFile(self, outpath):
|
||||
file(outpath,'wb').write(self.mobi_data)
|
||||
|
||||
def getPrintReplica(self):
|
||||
return self.print_replica
|
||||
# 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 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]
|
||||
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:
|
||||
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. Most likely the correct PID has not been given.")
|
||||
# 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."
|
||||
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:
|
||||
print "File is encoded with PID "+checksumPid(pid)+"."
|
||||
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
|
||||
|
||||
# clear the crypto type
|
||||
self.patchSection(0, "\0" * 2, 0xC)
|
||||
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
|
||||
|
||||
# decrypt sections
|
||||
print "Decrypting. Please wait . . .",
|
||||
self.mobi_data = 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')
|
||||
self.mobi_data += decoded_data
|
||||
if extra_size > 0:
|
||||
self.mobi_data += data[-extra_size:]
|
||||
if self.num_sections > self.records+1:
|
||||
self.mobi_data += self.data_file[self.sections[self.records+1][0]:]
|
||||
print "done"
|
||||
return
|
||||
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 getUnencryptedBook(infile,pid):
|
||||
if not os.path.isfile(infile):
|
||||
raise DrmException('Input File Not Found')
|
||||
book = MobiBook(infile)
|
||||
book.processBook([pid])
|
||||
return book.mobi_data
|
||||
|
||||
def getUnencryptedBookWithList(infile,pidlist):
|
||||
if not os.path.isfile(infile):
|
||||
raise DrmException('Input File Not Found')
|
||||
book = MobiBook(infile)
|
||||
book.processBook(pidlist)
|
||||
return book.mobi_data
|
||||
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 main(argv=sys.argv):
|
||||
print ('MobiDeDrm v%(__version__)s. '
|
||||
'Copyright 2008-2011 The Dark Reverser et al.' % globals())
|
||||
if len(argv)<3 or len(argv)>4:
|
||||
print "Removes protection from Kindle/Mobipocket and Kindle/Print Replica ebooks"
|
||||
print "Usage:"
|
||||
print " %s <infile> <outfile> [<Comma separated list of PIDs to try>]" % sys.argv[0]
|
||||
return 1
|
||||
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:
|
||||
infile = argv[1]
|
||||
outfile = argv[2]
|
||||
if len(argv) is 4:
|
||||
pidlist = argv[3].split(',')
|
||||
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:
|
||||
pidlist = {}
|
||||
try:
|
||||
stripped_file = getUnencryptedBookWithList(infile, pidlist)
|
||||
file(outfile, 'wb').write(stripped_file)
|
||||
except DrmException, e:
|
||||
print "Error: %s" % e
|
||||
return 1
|
||||
return 0
|
||||
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')
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
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)
|
||||
|
||||
Reference in New Issue
Block a user