test/test_all_urls.py

   1 #!/usr/bin/env python
   2
   3 from __future__ import unicode_literals
   4
   5 # Allow direct execution
   6 import os
   7 import sys
   8 import unittest
   9 import collections
  10 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
  11
  12
  13 from test.helper import gettestcases
  14
  15 from youtube_dl.extractor import (
  16     FacebookIE,
  17     gen_extractors,
  18     YoutubeIE,
  19 )
  20
  21
  22 class TestAllURLsMatching(unittest.TestCase):
  23     def setUp(self):
  24         self.ies = gen_extractors()
  25
  26     def matching_ies(self, url):
  27         return [ie.IE_NAME for ie in self.ies if ie.suitable(url) and ie.IE_NAME != 'generic']
  28
  29     def assertMatch(self, url, ie_list):
  30         self.assertEqual(self.matching_ies(url), ie_list)
  31
  32     def test_youtube_playlist_matching(self):
  33         assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
  34         assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
  35         assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q')  # 585
  36         assertPlaylist('PL63F0C78739B09958')
  37         assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
  38         assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
  39         assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
  40         assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')  # 668
  41         self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
  42         # Top tracks
  43         assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
  44
  45     def test_youtube_matching(self):
  46         self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))
  47         self.assertFalse(YoutubeIE.suitable('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012'))  # 668
  48         self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube'])
  49         self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])
  50         self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube'])
  51         self.assertMatch('http://www.cleanvideosearch.com/media/action/yt/watch?videoId=8v_4O44sfjM', ['youtube'])
  52
  53     def test_youtube_channel_matching(self):
  54         assertChannel = lambda url: self.assertMatch(url, ['youtube:channel'])
  55         assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM')
  56         assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec')
  57         assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
  58
  59     def test_youtube_user_matching(self):
  60         self.assertMatch('http://www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
  61
  62     def test_youtube_feeds(self):
  63         self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watchlater'])
  64         self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:subscriptions'])
  65         self.assertMatch('https://www.youtube.com/feed/recommended', ['youtube:recommended'])
  66         self.assertMatch('https://www.youtube.com/my_favorites', ['youtube:favorites'])
  67
  68     def test_youtube_show_matching(self):
  69         self.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show'])
  70
  71     def test_youtube_search_matching(self):
  72         self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
  73         self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
  74
  75     def test_youtube_extract(self):
  76         assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
  77         assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
  78         assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
  79         assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
  80         assertExtractId('https://www.youtube.com/watch_popup?v=BaW_jenozKc', 'BaW_jenozKc')
  81         assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
  82         assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
  83
  84     def test_facebook_matching(self):
  85         self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
  86         self.assertTrue(FacebookIE.suitable('https://www.facebook.com/cindyweather?fref=ts#!/photo.php?v=10152183998945793'))
  87
  88     def test_no_duplicates(self):
  89         ies = gen_extractors()
  90         for tc in gettestcases(include_onlymatching=True):
  91             url = tc['url']
  92             for ie in ies:
  93                 if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
  94                     self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url))
  95                 else:
  96                     self.assertFalse(
  97                         ie.suitable(url),
  98                         '%s should not match URL %r . That URL belongs to %s.' % (type(ie).__name__, url, tc['name']))
  99
 100     def test_keywords(self):
 101         self.assertMatch(':ytsubs', ['youtube:subscriptions'])
 102         self.assertMatch(':ytsubscriptions', ['youtube:subscriptions'])
 103         self.assertMatch(':ythistory', ['youtube:history'])
 104
 105     def test_vimeo_matching(self):
 106         self.assertMatch('https://vimeo.com/channels/tributes', ['vimeo:channel'])
 107         self.assertMatch('https://vimeo.com/channels/31259', ['vimeo:channel'])
 108         self.assertMatch('https://vimeo.com/channels/31259/53576664', ['vimeo'])
 109         self.assertMatch('https://vimeo.com/user7108434', ['vimeo:user'])
 110         self.assertMatch('https://vimeo.com/user7108434/videos', ['vimeo:user'])
 111         self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
 112
 113     # https://github.com/ytdl-org/youtube-dl/issues/1930
 114     def test_soundcloud_not_matching_sets(self):
 115         self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set'])
 116
 117     def test_tumblr(self):
 118         self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', ['Tumblr'])
 119         self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430', ['Tumblr'])
 120
 121     def test_pbs(self):
 122         # https://github.com/ytdl-org/youtube-dl/issues/2350
 123         self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs'])
 124         self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs'])
 125
 126     def test_yahoo_https(self):
 127         # https://github.com/ytdl-org/youtube-dl/issues/2701
 128         self.assertMatch(
 129             'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
 130             ['Yahoo'])
 131
 132     def test_no_duplicated_ie_names(self):
 133         name_accu = collections.defaultdict(list)
 134         for ie in self.ies:
 135             name_accu[ie.IE_NAME.lower()].append(type(ie).__name__)
 136         for (ie_name, ie_list) in name_accu.items():
 137             self.assertEqual(
 138                 len(ie_list), 1,
 139                 'Multiple extractors with the same IE_NAME "%s" (%s)' % (ie_name, ', '.join(ie_list)))
 140
 141
 142 if __name__ == '__main__':
 143     unittest.main()