diff options
author | Sergey M․ <dstftw@gmail.com> | 2017-08-13 07:53:02 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2017-08-13 07:53:02 +0700 |
commit | 475bcb225f6046e38b47594c504da6ec15bac113 (patch) | |
tree | a0162464a094b37ba7f44990fae4dcd70e370066 /youtube_dl/extractor | |
parent | b3c6515365ed415bbf813c0c2e6c12585824b77a (diff) |
[pornhub:playlistbase] Skip videos from drop-down menu for all playlists (closes #12819, closes #13902)
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r-- | youtube_dl/extractor/pornhub.py | 18 |
1 files changed, 9 insertions, 9 deletions
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py index e032817f2..f6777cd26 100644 --- a/youtube_dl/extractor/pornhub.py +++ b/youtube_dl/extractor/pornhub.py @@ -227,13 +227,20 @@ class PornHubIE(InfoExtractor): class PornHubPlaylistBaseIE(InfoExtractor): def _extract_entries(self, webpage): + # Only process container div with main playlist content skipping + # drop-down menu that uses similar pattern for videos (see + # https://github.com/rg3/youtube-dl/issues/11594). + container = self._search_regex( + r'(?s)(<div[^>]+class=["\']container.+)', webpage, + 'container', default=webpage) + return [ self.url_result( 'http://www.pornhub.com/%s' % video_url, PornHubIE.ie_key(), video_title=title) for video_url, title in orderedSet(re.findall( r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"[^>]*\s+title="([^"]+)"', - webpage)) + container)) ] def _real_extract(self, url): @@ -241,14 +248,7 @@ class PornHubPlaylistBaseIE(InfoExtractor): webpage = self._download_webpage(url, playlist_id) - # Only process container div with main playlist content skipping - # drop-down menu that uses similar pattern for videos (see - # https://github.com/rg3/youtube-dl/issues/11594). - container = self._search_regex( - r'(?s)(<div[^>]+class=["\']container.+)', webpage, - 'container', default=webpage) - - entries = self._extract_entries(container) + entries = self._extract_entries(webpage) playlist = self._parse_json( self._search_regex( |