etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 02:25:11 +00:00
Code Issues Projects Releases Wiki Activity

[youtube] feeds: Also look for the html in the 'content_html' field (fixes #2671)

Browse source
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-04-02 14:13:08 +02:00
parent 9ddaf4ef8c
commit f6177462db
1 changed files with 2 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
youtube_dl/extractor/youtube.py
View file

@ -1738,11 +1738,10 @@ def _real_extract(self, url):
feed_entries = [] feed_entries = []
paging = 0 paging = 0
for i in itertools.count(1): for i in itertools.count(1):
info = self._download_webpage(self._FEED_TEMPLATE % paging, info = self._download_json(self._FEED_TEMPLATE % paging,
u'%s feed' % self._FEED_NAME, u'%s feed' % self._FEED_NAME,
u'Downloading page %s' % i) u'Downloading page %s' % i)
info = json.loads(info) feed_html = info.get('feed_html') or info.get('content_html')
feed_html = info['feed_html']
m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html) m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html)
ids = orderedSet(m.group(1) for m in m_ids) ids = orderedSet(m.group(1) for m in m_ids)
feed_entries.extend( feed_entries.extend(