def extract_content(self, output_dir):
from calibre.ebooks.pml.pmlconverter import pml_to_html
output_dir = os.path.abspath(output_dir)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
pml = ''
for i in range(1, self.header_record.num_text_pages + 1):
self.log.debug('Extracting text page %i' % i)
pml += self.get_text_page(i)
title = self.mi.title
if not isinstance(title, unicode_type):
title = title.decode('utf-8', 'replace')
html = '<html><head><title>%s</title></head><body>%s</body></html>' % \
(title, pml_to_html(pml))
with CurrentDir(output_dir):
with open('index.html', 'wb') as index:
self.log.debug('Writing text to index.html')
index.write(html.encode('utf-8'))
if not os.path.exists(os.path.join(output_dir, 'images/')):
os.makedirs(os.path.join(output_dir, 'images/'))
images = []
with CurrentDir(os.path.join(output_dir, 'images/')):
for i in range(self.header_record.non_text_offset,
len(self.sections)):
name, img = self.get_image(i)
if name:
name = as_unicode(name)
images.append(name)
with open(name, 'wb') as imgf:
self.log.debug('Writing image %s to images/' % name)
imgf.write(img)
opf_path = self.create_opf(output_dir, images)
return opf_path
def extract_content(self, output_dir):
from calibre.ebooks.pml.pmlconverter import pml_to_html
output_dir = os.path.abspath(output_dir)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
pml = u''
for i in range(1, self.header_record.num_text_pages + 1):
self.log.debug('Extracting text page %i' % i)
pml += self.get_text_page(i)
title = self.mi.title
if not isinstance(title, unicode):
title = title.decode('utf-8', 'replace')
html = u'<html><head><title>%s</title></head><body>%s</body></html>' % \
(title, pml_to_html(pml))
with CurrentDir(output_dir):
with open('index.html', 'wb') as index:
self.log.debug('Writing text to index.html')
index.write(html.encode('utf-8'))
if not os.path.exists(os.path.join(output_dir, 'images/')):
os.makedirs(os.path.join(output_dir, 'images/'))
images = []
with CurrentDir(os.path.join(output_dir, 'images/')):
for i in range(self.header_record.non_text_offset, len(self.sections)):
name, img = self.get_image(i)
if name:
images.append(name)
with open(name, 'wb') as imgf:
self.log.debug('Writing image %s to images/' % name)
imgf.write(img)
opf_path = self.create_opf(output_dir, images)
return opf_path