From 9acd33094d36acde60a42837ed775c68ad3a327d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Sun, 31 Jan 2016 17:52:02 +0600 Subject: [PATCH] [youtube] Filter duplicates in playlists base extractor --- youtube_dl/extractor/youtube.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 2941da467..9a64c1d11 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -233,7 +233,7 @@ def extract_videos_from_page(self, page): class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): def _process_page(self, content): - for playlist_id in re.findall(r'href="/?playlist\?list=(.+?)"', content): + for playlist_id in set(re.findall(r'href="/?playlist\?list=([0-9A-Za-z-_]{10,})"', content)): yield self.url_result( 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')