public-mirrors/NewsBlur-viq
1
0
Fork 0
mirror of https://github.com/viq/NewsBlur.git synced 2025-09-18 21:43:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Sanitizing text/plain stories.

Browse source
This commit is contained in:
Samuel Clay 2016-05-11 12:01:20 -07:00
parent fb03d62610
commit c1d1534d67
2 changed files with 6 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
utils/feed_fetcher.py
View file

@ -462,7 +462,7 @@ class ProcessFeed:
story_hashes = []
stories = []
for entry in self.fpf.entries:
story = pre_process_story(entry)
story = pre_process_story(entry, self.fpf.encoding)
if story.get('published') < start_date:
start_date = story.get('published')
if replace_guids:

6
utils/story_functions.py
View file

@ -13,6 +13,7 @@ from django.utils.html import strip_tags as strip_tags_django
from utils.tornado_escape import linkify as linkify_tornado
from utils.tornado_escape import xhtml_unescape as xhtml_unescape_tornado
from vendor import reseekfile
from utils import feedparser
# COMMENTS_RE = re.compile('\<![ \r\n\t]*(--([^\-]|[\r\n]|-[^\-])*--[ \r\n\t]*)\>')
COMMENTS_RE = re.compile('\<!--.*?--\>')
@ -67,7 +68,7 @@ def _extract_date_tuples(date):
return parsed_date, date_tuple, today_tuple, yesterday_tuple
def pre_process_story(entry):
def pre_process_story(entry, encoding):
publish_date = entry.get('published_parsed') or entry.get('updated_parsed')
if publish_date:
publish_date = datetime.datetime(*publish_date[:6])
@ -110,6 +111,9 @@ def pre_process_story(entry):
else:
entry['story_content'] = summary.strip()
if 'summary_detail' in entry and entry['summary_detail'].get('type', None) == 'text/plain':
entry['story_content'] = feedparser._sanitizeHTML(entry['story_content'], encoding, 'text/plain')
# Add each media enclosure as a Download link
for media_content in chain(entry.get('media_content', [])[:5], entry.get('links', [])[:5]):
media_url = media_content.get('url', '')