def extract_text(self, offset=1):
self.log.debug('Extracting text...')
text_sections = [
self.text_section(i) for i in range(
offset,
min(self.book_header.records + offset, len(self.sections)))
]
processed_records = list(
range(offset - 1, self.book_header.records + offset))
self.mobi_html = b''
if self.book_header.compression_type == 'DH':
huffs = [
self.sections[i][0] for i in range(
self.book_header.huff_offset,
self.book_header.huff_offset +
self.book_header.huff_number)
]
processed_records += list(
range(
self.book_header.huff_offset,
self.book_header.huff_offset +
self.book_header.huff_number))
huff = HuffReader(huffs)
unpack = huff.unpack
elif self.book_header.compression_type == '\x00\x02':
unpack = decompress_doc
elif self.book_header.compression_type == '\x00\x01':
unpack = lambda x: x
else:
raise MobiError('Unknown compression algorithm: %s' %
repr(self.book_header.compression_type))
self.mobi_html = b''.join(map(unpack, text_sections))
if self.mobi_html.endswith(b'#'):
self.mobi_html = self.mobi_html[:-1]
if self.book_header.ancient and '<html' not in self.mobi_html[:
300].lower(
):
self.mobi_html = self.mobi_html.replace('\r ', '\n\n ')
self.mobi_html = self.mobi_html.replace('\0', '')
if self.book_header.codec == 'cp1252':
self.mobi_html = self.mobi_html.replace('\x1e',
'') # record separator
self.mobi_html = self.mobi_html.replace('\x02',
'') # start of text
return processed_records
def huffit(off, cnt):
huffman_record_nums = list(xrange(off, off + cnt))
huffrecs = [self.records[r].raw for r in huffman_record_nums]
huffs = HuffReader(huffrecs)
return huffman_record_nums, huffs.unpack
