Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-06-23 15:30:45 -04:00
Code Issues Packages Projects Releases Wiki Activity

Fix #2565 (MOBI to Epub convertion creates a abreviated epub version)

Browse Source
This commit is contained in:
Kovid Goyal 2009-06-11 14:35:41 -07:00
parent af9e34b6d6
commit c317411f03
1 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
src/calibre/ebooks/mobi/reader.py
View File

@ -300,9 +300,9 @@ class MobiReader(object):
root = html.fromstring(self.processed_html) root = html.fromstring(self.processed_html)
if root.xpath('descendant::p/descendant::p'): if root.xpath('descendant::p/descendant::p'):
from lxml.html import soupparser from lxml.html import soupparser
self.log.warning('Markup contains unclosed <p> tags, parsing using', self.log.warning('Malformed markup, parsing using BeatifulSoup')
'BeatifulSoup')
root = soupparser.fromstring(self.processed_html) root = soupparser.fromstring(self.processed_html)
if root.tag != 'html': if root.tag != 'html':
self.log.warn('File does not have opening <html> tag') self.log.warn('File does not have opening <html> tag')
nroot = html.fromstring('<html><head></head><body></body></html>') nroot = html.fromstring('<html><head></head><body></body></html>')
@ -313,6 +313,7 @@ class MobiReader(object):
root = nroot root = nroot
htmls = list(root.xpath('//html')) htmls = list(root.xpath('//html'))
if len(htmls) > 1: if len(htmls) > 1:
self.log.warn('Markup contains multiple <html> tags') self.log.warn('Markup contains multiple <html> tags')
# Keep only the largest head and body # Keep only the largest head and body
@ -428,6 +429,7 @@ class MobiReader(object):
self.processed_html = '<html><p>' + self.processed_html.replace('\n\n', '<p>') + '</html>' self.processed_html = '<html><p>' + self.processed_html.replace('\n\n', '<p>') + '</html>'
self.processed_html = self.processed_html.replace('\r\n', '\n') self.processed_html = self.processed_html.replace('\r\n', '\n')
self.processed_html = self.processed_html.replace('> <', '>\n<') self.processed_html = self.processed_html.replace('> <', '>\n<')
self.processed_html = re.sub('\x14|\x15', '', self.processed_html)
def upshift_markup(self, root): def upshift_markup(self, root):
self.log.debug('Converting style information to CSS...') self.log.debug('Converting style information to CSS...')