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

More strenuous cleaning for title/summary of feeds

Browse Source
This commit is contained in:
Kovid Goyal 2016-09-26 23:19:06 +05:30
parent 68df59c633
commit a3eee6a22a
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
src/calibre/web/feeds/__init__.py
View File

@ -8,9 +8,9 @@ Contains the logic for parsing feeds.
import time, traceback, copy, re import time, traceback, copy, re
from calibre.utils.logging import default_log from calibre.utils.logging import default_log
from calibre import entity_to_unicode, strftime from calibre import entity_to_unicode, strftime, force_unicode
from calibre.utils.date import dt_factory, utcnow, local_tz from calibre.utils.date import dt_factory, utcnow, local_tz
from calibre.utils.cleantext import clean_ascii_chars from calibre.utils.cleantext import clean_ascii_chars, clean_xml_chars
class Article(object): class Article(object):
@ -18,23 +18,23 @@ class Article(object):
from lxml import html from lxml import html
self.downloaded = False self.downloaded = False
self.id = id self.id = id
self._title = (title or _('Unknown')).strip() title = force_unicode(title or _('Unknown'), 'utf-8')
self._title = clean_xml_chars(title).strip()
try: try:
self._title = re.sub(r'&(\S+?);', self._title = re.sub(r'&(\S+?);',
entity_to_unicode, self._title) entity_to_unicode, self._title)
except: except:
pass pass
if not isinstance(self._title, unicode):
self._title = self._title.decode('utf-8', 'replace')
self._title = clean_ascii_chars(self._title) self._title = clean_ascii_chars(self._title)
self.url = url self.url = url
self.author = author self.author = author
self.toc_thumbnail = None self.toc_thumbnail = None
if author and not isinstance(author, unicode): if author and not isinstance(author, unicode):
author = author.decode('utf-8', 'replace') author = author.decode('utf-8', 'replace')
self.summary = summary
if summary and not isinstance(summary, unicode): if summary and not isinstance(summary, unicode):
summary = summary.decode('utf-8', 'replace') summary = summary.decode('utf-8', 'replace')
summary = clean_xml_chars(summary) if summary else summary
self.summary = summary
if summary and '<' in summary: if summary and '<' in summary:
try: try:
s = html.fragment_fromstring(summary, create_parent=True) s = html.fragment_fromstring(summary, create_parent=True)