etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 03:03:01 +00:00
Code Issues Projects Releases Wiki Activity

Merge pull request #147 from ZenulAbidin/master

Browse source 
Fix #93 YoutubePlaylistsIE
This commit is contained in:
Tom-Oliver Heidel 2020-11-10 22:58:42 +01:00 committed by GitHub
commit 0e0cffb8fe
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
youtube_dlc/extractor/youtube.py
View file

@ -300,11 +300,12 @@ class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
# Extract entries from page with "Load more" button # Extract entries from page with "Load more" button
def _entries(self, page, playlist_id): def _entries(self, page, playlist_id):
more_widget_html = content_html = page more_widget_html = content_html = page
mobj_reg = r'(?:(?:data-uix-load-more-href="[^"]+?;continuation=)|(?:"continuation":"))(?P<more>[^"]+)"'
for page_num in itertools.count(1): for page_num in itertools.count(1):
for entry in self._process_page(content_html): for entry in self._process_page(content_html):
yield entry yield entry
mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) mobj = re.search(mobj_reg, more_widget_html)
if not mobj: if not mobj:
break break
@ -315,7 +316,7 @@ def _entries(self, page, playlist_id):
# Downloading page may result in intermittent 5xx HTTP error # Downloading page may result in intermittent 5xx HTTP error
# that is usually worked around with a retry # that is usually worked around with a retry
more = self._download_json( more = self._download_json(
'https://www.youtube.com/%s' % mobj.group('more'), playlist_id, 'https://www.youtube.com/browse_ajax?ctoken=%s' % mobj.group('more'), playlist_id,
'Downloading page #%s%s' 'Downloading page #%s%s'
% (page_num, ' (retry #%d)' % count if count else ''), % (page_num, ' (retry #%d)' % count if count else ''),
transform_source=uppercase_escape, transform_source=uppercase_escape,
@ -372,7 +373,7 @@ def extract_videos_from_page(self, page):
class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
def _process_page(self, content): def _process_page(self, content):
for playlist_id in orderedSet(re.findall( for playlist_id in orderedSet(re.findall(
r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"', r'"/?playlist\?list=([0-9A-Za-z-_]{10,})"',
content)): content)):
yield self.url_result( yield self.url_result(
'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist') 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')