Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

MOBI Input: Ignore all ASCII control codes except CR, NL and Tab. Fixes #9219 (Instapaper magazine can't be shown in ebook-viewer)

Browse Source
This commit is contained in:
Kovid Goyal 2011-02-28 08:45:31 -07:00
parent 752d9f350d
commit c2d85e81b7
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/calibre/ebooks/mobi/reader.py
View File

@ -18,6 +18,7 @@ from calibre import xml_entity_to_unicode, CurrentDir, entity_to_unicode, \
replace_entities replace_entities
from calibre.utils.filenames import ascii_filename from calibre.utils.filenames import ascii_filename
from calibre.utils.date import parse_date from calibre.utils.date import parse_date
from calibre.utils.cleantext import clean_ascii_chars
from calibre.ptempfile import TemporaryDirectory from calibre.ptempfile import TemporaryDirectory
from calibre.ebooks import DRMError from calibre.ebooks import DRMError
from calibre.ebooks.chardet import ENCODING_PATS from calibre.ebooks.chardet import ENCODING_PATS
@ -323,6 +324,7 @@ class MobiReader(object):
self.cleanup_html() self.cleanup_html()
self.log.debug('Parsing HTML...') self.log.debug('Parsing HTML...')
self.processed_html = clean_ascii_chars(self.processed_html)
try: try:
root = html.fromstring(self.processed_html) root = html.fromstring(self.processed_html)
if len(root.xpath('//html')) > 5: if len(root.xpath('//html')) > 5: