From d67cc9fa7c1c38fa72ed8990965ef0aeebbdb43a Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Jaime=20Marqui=CC=81nez=20Ferra=CC=81ndiz?= Date: Thu, 6 Feb 2014 19:46:26 +0100 Subject: [PATCH] =?UTF-8?q?[youtube:playlist]=20Recognize=20=E2=80=98top?= =?UTF-8?q?=20tracks=E2=80=99=20urls=20(closes=20#2332)?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The list parameter starts with ‘MC’ and can have more characters after it, including dots --- test/test_all_urls.py | 2 ++ test/test_youtube_lists.py | 7 +++++++ youtube_dl/extractor/youtube.py | 15 +++++++-------- 3 files changed, 16 insertions(+), 8 deletions(-) diff --git a/test/test_all_urls.py b/test/test_all_urls.py index 94cbce6e8..dcce9ddb8 100644 --- a/test/test_all_urls.py +++ b/test/test_all_urls.py @@ -37,6 +37,8 @@ class TestAllURLsMatching(unittest.TestCase): assertPlaylist(u'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC') assertPlaylist(u'https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668 self.assertFalse('youtube:playlist' in self.matching_ies(u'PLtS2H6bU1M')) + # Top tracks + assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101') def test_youtube_matching(self): self.assertTrue(YoutubeIE.suitable(u'PLtS2H6bU1M')) diff --git a/test/test_youtube_lists.py b/test/test_youtube_lists.py index de157f657..c9632ddf6 100644 --- a/test/test_youtube_lists.py +++ b/test/test_youtube_lists.py @@ -117,6 +117,13 @@ class TestYoutubeLists(unittest.TestCase): original_video = entries[0] self.assertEqual(original_video['id'], 'rjFaenf1T-Y') + def test_youtube_toptracks(self): + dl = FakeYDL() + ie = YoutubePlaylistIE(dl) + result = ie.extract('https://www.youtube.com/playlist?list=MCUS') + entries = result['entries'] + self.assertEqual(len(entries), 100) + def test_youtube_toplist(self): dl = FakeYDL() ie = YoutubeTopListIE(dl) diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py index 5dd2de5ee..765c690f1 100644 --- a/youtube_dl/extractor/youtube.py +++ b/youtube_dl/extractor/youtube.py @@ -1422,7 +1422,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor): class YoutubePlaylistIE(YoutubeBaseInfoExtractor): IE_DESC = u'YouTube.com playlists' - _VALID_URL = r"""(?: + _VALID_URL = r"""(?x)(?: (?:https?://)? (?:\w+\.)? youtube\.com/ @@ -1431,7 +1431,11 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): \? (?:.*?&)*? (?:p|a|list)= | p/ ) - ((?:PL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,}) + ( + (?:PL|EC|UU|FL|RD)?[0-9A-Za-z-_]{10,} + # Top tracks, they can also include dots + |(?:MC)[\w\.]* + ) .* | ((?:PL|EC|UU|FL|RD)[0-9A-Za-z-_]{10,}) @@ -1441,11 +1445,6 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): _VIDEO_RE = r'href="/watch\?v=(?P[0-9A-Za-z_-]{11})&[^"]*?index=(?P\d+)' IE_NAME = u'youtube:playlist' - @classmethod - def suitable(cls, url): - """Receives a URL and returns True if suitable for this IE.""" - return re.match(cls._VALID_URL, url, re.VERBOSE) is not None - def _real_initialize(self): self._login() @@ -1469,7 +1468,7 @@ class YoutubePlaylistIE(YoutubeBaseInfoExtractor): def _real_extract(self, url): # Extract playlist id - mobj = re.match(self._VALID_URL, url, re.VERBOSE) + mobj = re.match(self._VALID_URL, url) if mobj is None: raise ExtractorError(u'Invalid URL: %s' % url) playlist_id = mobj.group(1) or mobj.group(2)