test/test_all_urls.py

   1 #!/usr/bin/env python3
   2 # Allow direct execution
   3 import collections
   4 import os
   5 import sys
   6 import unittest
   7
   8 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
   9
  10
  11 from test.helper import gettestcases
  12
  13 from yt_dlp.extractor import FacebookIE, YoutubeIE, gen_extractors
  14
  15
  16 class TestAllURLsMatching(unittest.TestCase):
  17     def setUp(self):
  18         self.ies = gen_extractors()
  19
  20     def matching_ies(self, url):
  21         return [ie.IE_NAME for ie in self.ies if ie.suitable(url) and ie.IE_NAME != 'generic']
  22
  23     def assertMatch(self, url, ie_list):
  24         self.assertEqual(self.matching_ies(url), ie_list)
  25
  26     def test_youtube_playlist_matching(self):
  27         assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
  28         assertTab = lambda url: self.assertMatch(url, ['youtube:tab'])
  29         assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
  30         assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q')  # 585
  31         assertPlaylist('PL63F0C78739B09958')
  32         assertTab('https://www.youtube.com/AsapSCIENCE')
  33         assertTab('https://www.youtube.com/embedded')
  34         assertTab('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
  35         assertTab('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
  36         assertTab('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')  # 668
  37         self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
  38         # Top tracks
  39         assertTab('https://www.youtube.com/playlist?list=MCUS.20142101')
  40
  41     def test_youtube_matching(self):
  42         self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))
  43         self.assertFalse(YoutubeIE.suitable('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012'))  # 668
  44         self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube'])
  45         # self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])  # /v/ is no longer valid
  46         self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube'])
  47         self.assertMatch('http://www.cleanvideosearch.com/media/action/yt/watch?videoId=8v_4O44sfjM', ['youtube'])
  48
  49     def test_youtube_channel_matching(self):
  50         assertChannel = lambda url: self.assertMatch(url, ['youtube:tab'])
  51         assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM')
  52         assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec')
  53         assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
  54
  55     def test_youtube_user_matching(self):
  56         self.assertMatch('http://www.youtube.com/NASAgovVideo/videos', ['youtube:tab'])
  57
  58     def test_youtube_feeds(self):
  59         self.assertMatch('https://www.youtube.com/feed/library', ['youtube:tab'])
  60         self.assertMatch('https://www.youtube.com/feed/history', ['youtube:tab'])
  61         self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:tab'])
  62         self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:tab'])
  63
  64     def test_youtube_search_matching(self):
  65         self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
  66         self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
  67
  68     def test_facebook_matching(self):
  69         self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
  70         self.assertTrue(FacebookIE.suitable('https://www.facebook.com/cindyweather?fref=ts#!/photo.php?v=10152183998945793'))
  71
  72     def test_no_duplicates(self):
  73         ies = gen_extractors()
  74         for tc in gettestcases(include_onlymatching=True):
  75             url = tc['url']
  76             for ie in ies:
  77                 if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
  78                     self.assertTrue(ie.suitable(url), f'{type(ie).__name__} should match URL {url!r}')
  79                 else:
  80                     self.assertFalse(
  81                         ie.suitable(url),
  82                         f'{type(ie).__name__} should not match URL {url!r} . That URL belongs to {tc["name"]}.')
  83
  84     def test_keywords(self):
  85         self.assertMatch(':ytsubs', ['youtube:subscriptions'])
  86         self.assertMatch(':ytsubscriptions', ['youtube:subscriptions'])
  87         self.assertMatch(':ythistory', ['youtube:history'])
  88
  89     def test_vimeo_matching(self):
  90         self.assertMatch('https://vimeo.com/channels/tributes', ['vimeo:channel'])
  91         self.assertMatch('https://vimeo.com/channels/31259', ['vimeo:channel'])
  92         self.assertMatch('https://vimeo.com/channels/31259/53576664', ['vimeo'])
  93         self.assertMatch('https://vimeo.com/user7108434', ['vimeo:user'])
  94         self.assertMatch('https://vimeo.com/user7108434/videos', ['vimeo:user'])
  95         self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
  96
  97     # https://github.com/ytdl-org/youtube-dl/issues/1930
  98     def test_soundcloud_not_matching_sets(self):
  99         self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set'])
 100
 101     def test_tumblr(self):
 102         self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', ['Tumblr'])
 103         self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430', ['Tumblr'])
 104
 105     def test_pbs(self):
 106         # https://github.com/ytdl-org/youtube-dl/issues/2350
 107         self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs'])
 108         self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs'])
 109
 110     def test_no_duplicated_ie_names(self):
 111         name_accu = collections.defaultdict(list)
 112         for ie in self.ies:
 113             name_accu[ie.IE_NAME.lower()].append(type(ie).__name__)
 114         for (ie_name, ie_list) in name_accu.items():
 115             self.assertEqual(
 116                 len(ie_list), 1,
 117                 f'Multiple extractors with the same IE_NAME "{ie_name}" ({", ".join(ie_list)})')
 118
 119
 120 if __name__ == '__main__':
 121     unittest.main()