[youtube:playlist] Recognize ‘top tracks’ urls (closes #2332)

The list parameter starts with ‘MC’ and can have more characters after it, including dots
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-02-06 19:46:26 +01:00
parent bf3a2fe923
commit d67cc9fa7c
3 changed files with 16 additions and 8 deletions

View File

@ -37,6 +37,8 @@ def test_youtube_playlist_matching(self):
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'))

View File

@ -117,6 +117,13 @@ def test_youtube_mix(self):
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)

View File

@ -1422,7 +1422,7 @@ def _map_to_format_list(urlmap):
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<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\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 @@ def _extract_mix(self, playlist_id):
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)