test/test_all_urls.py

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  46         # self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])  # /v/ is no longer valid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