From 2bf0634d16b5732548652093d77dbd1aa76e8189 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 7 Dec 2020 01:48:10 +0700 Subject: [PATCH] [youtube] Improve youtu.be extraction in non-existing playlists (closes #27324) --- youtube_dl/extractor/extractors.py | 1 + youtube_dl/extractor/youtube.py | 55 +++++++++++++++++++----------- 2 files changed, 36 insertions(+), 20 deletions(-) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 03aff1d52..575b4b36f 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1520,6 +1520,7 @@ from .youtube import ( YoutubeSubscriptionsIE, YoutubeTruncatedIDIE, YoutubeTruncatedURLIE, + YoutubeYtBeIE, YoutubeYtUserIE, YoutubeWatchLaterIE, ) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index b796f58b2..b8219a0ad 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -3139,8 +3139,7 @@ class YoutubePlaylistIE(InfoExtractor): (?: (?: youtube(?:kids)?\.com| - invidio\.us| - youtu\.be + invidio\.us ) /.*?\?.*?\blist= )? @@ -3185,6 +3184,32 @@ class YoutubePlaylistIE(InfoExtractor): 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA', } }, { + 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', + 'only_matching': True, + }, { + # music album playlist + 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', + 'only_matching': True, + }] + + @classmethod + def suitable(cls, url): + return False if YoutubeTabIE.suitable(url) else super( + YoutubePlaylistIE, cls).suitable(url) + + def _real_extract(self, url): + playlist_id = self._match_id(url) + qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) + if not qs: + qs = {'list': playlist_id} + return self.url_result( + update_url_query('https://www.youtube.com/playlist', qs), + ie=YoutubeTabIE.ie_key(), video_id=playlist_id) + + +class YoutubeYtBeIE(InfoExtractor): + _VALID_URL = r'https?://youtu\.be/(?P[0-9A-Za-z_-]{11})/*?.*?\blist=(?P%(playlist_id)s)' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} + _TESTS = [{ 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', 'info_dict': { 'id': 'yeWKywCrFtk', @@ -3207,28 +3232,18 @@ class YoutubePlaylistIE(InfoExtractor): }, { 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', 'only_matching': True, - }, { - 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', - 'only_matching': True, - }, { - # music album playlist - 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', - 'only_matching': True, }] - @classmethod - def suitable(cls, url): - return False if YoutubeTabIE.suitable(url) else super( - YoutubePlaylistIE, cls).suitable(url) - def _real_extract(self, url): - playlist_id = self._match_id(url) - qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) - if not qs: - qs = {'list': playlist_id} + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + playlist_id = mobj.group('playlist_id') return self.url_result( - update_url_query('https://www.youtube.com/playlist', qs), - ie=YoutubeTabIE.ie_key(), video_id=playlist_id) + update_url_query('https://www.youtube.com/watch', { + 'v': video_id, + 'list': playlist_id, + 'feature': 'youtu.be', + }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id) class YoutubeYtUserIE(InfoExtractor):