def extract_content(self, output_dir):
txt = ''
self.log.info(u'Decompressing text...')
for i in range(1, self.header_record.num_records + 1):
self.log.debug(u'\tDecompressing text section %i' % i)
title = self.header_record.chapter_titles[i - 1]
lines = []
title_added = False
for line in self.decompress_text(i).splitlines():
line = fix_punct(line)
line = line.strip()
if not title_added and title in line:
line = '<h1 class="chapter">' + line + '</h1>\n'
title_added = True
else:
line = prepare_string_for_xml(line)
lines.append('<p>%s</p>' % line)
if not title_added:
lines.insert(0, '<h1 class="chapter">' + title + '</h1>\n')
txt += '\n'.join(lines)
self.log.info(u'Converting text to OEB...')
html = HTML_TEMPLATE % (self.header_record.title, txt)
with open(os.path.join(output_dir, 'index.html'), 'wb') as index:
index.write(html.encode('utf-8'))
mi = self.get_metadata()
manifest = [('index.html', None)]
spine = ['index.html']
opf_writer(output_dir, 'metadata.opf', manifest, spine, mi)
return os.path.join(output_dir, 'metadata.opf')
def extract_content(self, output_dir):
txt = ''
self.log.info('Decompressing text...')
for i in range(1, self.header_record.num_records + 1):
self.log.debug('\tDecompressing text section %i' % i)
title = self.header_record.chapter_titles[i-1]
lines = []
title_added = False
for line in self.decompress_text(i).splitlines():
line = fix_punct(line)
line = line.strip()
if not title_added and title in line:
line = u'<h1 class="chapter">' + line + u'</h1>\n'
title_added = True
else:
line = prepare_string_for_xml(line)
lines.append(u'<p>%s</p>' % line)
if not title_added:
lines.insert(0, u'<h1 class="chapter">' + title + u'</h1>\n')
txt += '\n'.join(lines)
self.log.info('Converting text to OEB...')
html = HTML_TEMPLATE % (self.header_record.title, txt)
with open(os.path.join(output_dir, 'index.html'), 'wb') as index:
index.write(html.encode('utf-8'))
mi = self.get_metadata()
manifest = [('index.html', None)]
spine = ['index.html']
opf_writer(output_dir, 'metadata.opf', manifest, spine, mi)
return os.path.join(output_dir, 'metadata.opf')