Pastebin launched a little side project called HostCabi.net, check it out ;-)Don't like ads? PRO users don't see any ads ;-)
Guest

MobiDeDrm v0.13

By: a guest on Mar 8th, 2010  |  syntax: Python  |  size: 11.21 KB  |  hits: 23,790  |  expires: Never
download  |  raw  |  embed  |  report abuse  |  print
Text below is selected. Please press Ctrl+C to copy to your clipboard. (⌘+C on Mac)
  1. #!/usr/bin/python
  2. #
  3. # This is a python script. You need a Python interpreter to run it.
  4. # For example, ActiveState Python, which exists for windows.
  5. #
  6. # It can run standalone to convert files, or it can be installed as a
  7. # plugin for Calibre (http://calibre-ebook.com/about) so that
  8. # importing files with DRM 'Just Works'.
  9. #
  10. # To create a Calibre plugin, rename this file so that the filename
  11. # ends in '_plugin.py', put it into a ZIP file and import that Calibre
  12. # using its plugin configuration GUI.
  13. #
  14. # Changelog
  15. #  0.01 - Initial version
  16. #  0.02 - Huffdic compressed books were not properly decrypted
  17. #  0.03 - Wasn't checking MOBI header length
  18. #  0.04 - Wasn't sanity checking size of data record
  19. #  0.05 - It seems that the extra data flags take two bytes not four
  20. #  0.06 - And that low bit does mean something after all :-)
  21. #  0.07 - The extra data flags aren't present in MOBI header < 0xE8 in size
  22. #  0.08 - ...and also not in Mobi header version < 6
  23. #  0.09 - ...but they are there with Mobi header version 6, header size 0xE4!
  24. #  0.10 - Outputs unencrypted files as-is, so that when run as a Calibre
  25. #         import filter it works when importing unencrypted files.
  26. #         Also now handles encrypted files that don't need a specific PID.
  27. #  0.11 - use autoflushed stdout and proper return values
  28. #  0.12 - Fix for problems with metadata import as Calibre plugin, report errors
  29. #  0.13 - Formatting fixes: retabbed file, removed trailing whitespace
  30. #         and extra blank lines, converted CR/LF pairs at ends of each line,
  31. #         and other cosmetic fixes.
  32.  
  33. __version__ = '0.13'
  34.  
  35. import sys
  36. import struct
  37. import binascii
  38.  
  39. class Unbuffered:
  40.     def __init__(self, stream):
  41.         self.stream = stream
  42.     def write(self, data):
  43.         self.stream.write(data)
  44.         self.stream.flush()
  45.     def __getattr__(self, attr):
  46.         return getattr(self.stream, attr)
  47.  
  48. class DrmException(Exception):
  49.     pass
  50.  
  51. # Implementation of Pukall Cipher 1
  52. def PC1(key, src, decryption=True):
  53.     sum1 = 0;
  54.     sum2 = 0;
  55.     keyXorVal = 0;
  56.     if len(key)!=16:
  57.         print "Bad key length!"
  58.         return None
  59.     wkey = []
  60.     for i in xrange(8):
  61.         wkey.append(ord(key[i*2])<<8 | ord(key[i*2+1]))
  62.  
  63.     dst = ""
  64.     for i in xrange(len(src)):
  65.         temp1 = 0;
  66.         byteXorVal = 0;
  67.         for j in xrange(8):
  68.             temp1 ^= wkey[j]
  69.             sum2  = (sum2+j)*20021 + sum1
  70.             sum1  = (temp1*346)&0xFFFF
  71.             sum2  = (sum2+sum1)&0xFFFF
  72.             temp1 = (temp1*20021+1)&0xFFFF
  73.             byteXorVal ^= temp1 ^ sum2
  74.         curByte = ord(src[i])
  75.         if not decryption:
  76.             keyXorVal = curByte * 257;
  77.         curByte = ((curByte ^ (byteXorVal >> 8)) ^ byteXorVal) & 0xFF
  78.         if decryption:
  79.             keyXorVal = curByte * 257;
  80.         for j in xrange(8):
  81.             wkey[j] ^= keyXorVal;
  82.         dst+=chr(curByte)
  83.     return dst
  84.  
  85. def checksumPid(s):
  86.     letters = "ABCDEFGHIJKLMNPQRSTUVWXYZ123456789"
  87.     crc = (~binascii.crc32(s,-1))&0xFFFFFFFF
  88.     crc = crc ^ (crc >> 16)
  89.     res = s
  90.     l = len(letters)
  91.     for i in (0,1):
  92.         b = crc & 0xff
  93.         pos = (b // l) ^ (b % l)
  94.         res += letters[pos%l]
  95.         crc >>= 8
  96.     return res
  97.  
  98. def getSizeOfTrailingDataEntries(ptr, size, flags):
  99.     def getSizeOfTrailingDataEntry(ptr, size):
  100.         bitpos, result = 0, 0
  101.         if size <= 0:
  102.             return result
  103.         while True:
  104.             v = ord(ptr[size-1])
  105.             result |= (v & 0x7F) << bitpos
  106.             bitpos += 7
  107.             size -= 1
  108.             if (v & 0x80) != 0 or (bitpos >= 28) or (size == 0):
  109.                 return result
  110.     num = 0
  111.     testflags = flags >> 1
  112.     while testflags:
  113.         if testflags & 1:
  114.             num += getSizeOfTrailingDataEntry(ptr, size - num)
  115.         testflags >>= 1
  116.     if flags & 1:
  117.         num += (ord(ptr[size - num - 1]) & 0x3) + 1
  118.     return num
  119.  
  120. class DrmStripper:
  121.     def loadSection(self, section):
  122.         if (section + 1 == self.num_sections):
  123.             endoff = len(self.data_file)
  124.         else:
  125.             endoff = self.sections[section + 1][0]
  126.         off = self.sections[section][0]
  127.         return self.data_file[off:endoff]
  128.  
  129.     def patch(self, off, new):
  130.         self.data_file = self.data_file[:off] + new + self.data_file[off+len(new):]
  131.  
  132.     def patchSection(self, section, new, in_off = 0):
  133.         if (section + 1 == self.num_sections):
  134.             endoff = len(self.data_file)
  135.         else:
  136.             endoff = self.sections[section + 1][0]
  137.         off = self.sections[section][0]
  138.         assert off + in_off + len(new) <= endoff
  139.         self.patch(off + in_off, new)
  140.  
  141.     def parseDRM(self, data, count, pid):
  142.         pid = pid.ljust(16,'\0')
  143.         keyvec1 = "\x72\x38\x33\xB0\xB4\xF2\xE3\xCA\xDF\x09\x01\xD6\xE2\xE0\x3F\x96"
  144.         temp_key = PC1(keyvec1, pid, False)
  145.         temp_key_sum = sum(map(ord,temp_key)) & 0xff
  146.         found_key = None
  147.         for i in xrange(count):
  148.             verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
  149.             cookie = PC1(temp_key, cookie)
  150.             ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
  151.             if verification == ver and cksum == temp_key_sum and (flags & 0x1F) == 1:
  152.                 found_key = finalkey
  153.                 break
  154.         if not found_key:
  155.             # Then try the default encoding that doesn't require a PID
  156.             temp_key = keyvec1
  157.             temp_key_sum = sum(map(ord,temp_key)) & 0xff
  158.             for i in xrange(count):
  159.                 verification, size, type, cksum, cookie = struct.unpack('>LLLBxxx32s', data[i*0x30:i*0x30+0x30])
  160.                 cookie = PC1(temp_key, cookie)
  161.                 ver,flags,finalkey,expiry,expiry2 = struct.unpack('>LL16sLL', cookie)
  162.                 if verification == ver and cksum == temp_key_sum:
  163.                     found_key = finalkey
  164.                     break
  165.         return found_key
  166.  
  167.     def __init__(self, data_file, pid):
  168.         if checksumPid(pid[0:-2]) != pid:
  169.             raise DrmException("invalid PID checksum")
  170.         pid = pid[0:-2]
  171.  
  172.         self.data_file = data_file
  173.         header = data_file[0:72]
  174.         if header[0x3C:0x3C+8] != 'BOOKMOBI':
  175.             raise DrmException("invalid file format")
  176.         self.num_sections, = struct.unpack('>H', data_file[76:78])
  177.  
  178.         self.sections = []
  179.         for i in xrange(self.num_sections):
  180.             offset, a1,a2,a3,a4 = struct.unpack('>LBBBB', data_file[78+i*8:78+i*8+8])
  181.             flags, val = a1, a2<<16|a3<<8|a4
  182.             self.sections.append( (offset, flags, val) )
  183.  
  184.         sect = self.loadSection(0)
  185.         records, = struct.unpack('>H', sect[0x8:0x8+2])
  186.         mobi_length, = struct.unpack('>L',sect[0x14:0x18])
  187.         mobi_version, = struct.unpack('>L',sect[0x68:0x6C])
  188.         extra_data_flags = 0
  189.         print "MOBI header length = %d" %mobi_length
  190.         print "MOBI header version = %d" %mobi_version
  191.         if (mobi_length >= 0xE4) and (mobi_version > 5):
  192.             extra_data_flags, = struct.unpack('>H', sect[0xF2:0xF4])
  193.             print "Extra Data Flags = %d" %extra_data_flags
  194.  
  195.         crypto_type, = struct.unpack('>H', sect[0xC:0xC+2])
  196.         if crypto_type == 0:
  197.             print "This book is not encrypted."
  198.         else:
  199.             if crypto_type == 1:
  200.                 raise DrmException("cannot decode Mobipocket encryption type 1")
  201.             if crypto_type != 2:
  202.                 raise DrmException("unknown encryption type: %d" % crypto_type)
  203.  
  204.             # calculate the keys
  205.             drm_ptr, drm_count, drm_size, drm_flags = struct.unpack('>LLLL', sect[0xA8:0xA8+16])
  206.             if drm_count == 0:
  207.                 raise DrmException("no PIDs found in this file")
  208.             found_key = self.parseDRM(sect[drm_ptr:drm_ptr+drm_size], drm_count, pid)
  209.             if not found_key:
  210.                 raise DrmException("no key found. maybe the PID is incorrect")
  211.  
  212.             # kill the drm keys
  213.             self.patchSection(0, "\0" * drm_size, drm_ptr)
  214.             # kill the drm pointers
  215.             self.patchSection(0, "\xff" * 4 + "\0" * 12, 0xA8)
  216.             # clear the crypto type
  217.             self.patchSection(0, "\0" * 2, 0xC)
  218.  
  219.             # decrypt sections
  220.             print "Decrypting. Please wait...",
  221.             for i in xrange(1, records+1):
  222.                 data = self.loadSection(i)
  223.                 extra_size = getSizeOfTrailingDataEntries(data, len(data), extra_data_flags)
  224.                 # print "record %d, extra_size %d" %(i,extra_size)
  225.                 self.patchSection(i, PC1(found_key, data[0:len(data) - extra_size]))
  226.         print "done"
  227.  
  228.     def getResult(self):
  229.         return self.data_file
  230.  
  231. if not __name__ == "__main__":
  232.     from calibre.customize import FileTypePlugin
  233.  
  234.     class MobiDeDRM(FileTypePlugin):
  235.         name                = 'MobiDeDRM' # Name of the plugin
  236.         description         = 'Removes DRM from secure Mobi files'
  237.         supported_platforms = ['linux', 'osx', 'windows'] # Platforms this plugin will run on
  238.         author              = 'The Dark Reverser' # The author of this plugin
  239.         version             = (0, 1, 2)   # The version number of this plugin
  240.         file_types          = set(['prc','mobi','azw']) # The file types that this plugin will be applied to
  241.         on_import           = True # Run this plugin during the import
  242.  
  243.         def run(self, path_to_ebook):
  244.             from calibre.gui2 import is_ok_to_use_qt
  245.             from PyQt4.Qt import QMessageBox
  246.             PID = self.site_customization
  247.             data_file = file(path_to_ebook, 'rb').read()
  248.             ar = PID.split(',')
  249.             for i in ar:
  250.                 try:
  251.                     unlocked_file = DrmStripper(data_file, i).getResult()
  252.                 except DrmException:
  253.                     # ignore the error
  254.                     pass
  255.                 else:
  256.                     of = self.temporary_file('.mobi')
  257.                     of.write(unlocked_file)
  258.                     of.close()
  259.                     return of.name
  260.             if is_ok_to_use_qt():
  261.                 d = QMessageBox(QMessageBox.Warning, "MobiDeDRM Plugin", "Couldn't decode: %s\n\nImporting encrypted version." % path_to_ebook)
  262.                 d.show()
  263.                 d.raise_()
  264.                 d.exec_()
  265.             return path_to_ebook
  266.  
  267.         def customization_help(self, gui=False):
  268.             return 'Enter PID (separate multiple PIDs with comma)'
  269.  
  270. if __name__ == "__main__":
  271.     sys.stdout=Unbuffered(sys.stdout)
  272.     print ('MobiDeDrm v%(__version__)s. '
  273.            'Copyright 2008-2010 The Dark Reverser.' % globals())
  274.     if len(sys.argv)<4:
  275.         print "Removes protection from Mobipocket books"
  276.         print "Usage:"
  277.         print "    %s <infile> <outfile> <PID>" % sys.argv[0]
  278.         sys.exit(1)
  279.     else:
  280.         infile = sys.argv[1]
  281.         outfile = sys.argv[2]
  282.         pid = sys.argv[3]
  283.         data_file = file(infile, 'rb').read()
  284.         try:
  285.             strippedFile = DrmStripper(data_file, pid)
  286.             file(outfile, 'wb').write(strippedFile.getResult())
  287.         except DrmException, e:
  288.             print "Error: %s" % e
  289.             sys.exit(1)
  290.     sys.exit(0)