test_all_urls.py 6.8 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137
  1. #!/usr/bin/env python
  2. from __future__ import unicode_literals
  3. # Allow direct execution
  4. import os
  5. import sys
  6. import unittest
  7. import collections
  8. sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
  9. from test.helper import gettestcases
  10. from youtube_dl.extractor import (
  11. FacebookIE,
  12. gen_extractors,
  13. YoutubeIE,
  14. )
  15. class TestAllURLsMatching(unittest.TestCase):
  16. def setUp(self):
  17. self.ies = gen_extractors()
  18. def matching_ies(self, url):
  19. return [ie.IE_NAME for ie in self.ies if ie.suitable(url) and ie.IE_NAME != 'generic']
  20. def assertMatch(self, url, ie_list):
  21. self.assertEqual(self.matching_ies(url), ie_list)
  22. def test_youtube_playlist_matching(self):
  23. assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
  24. assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
  25. assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') # 585
  26. assertPlaylist('PL63F0C78739B09958')
  27. assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
  28. assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
  29. assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
  30. assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') # 668
  31. self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
  32. # Top tracks
  33. assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
  34. def test_youtube_matching(self):
  35. self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))
  36. self.assertFalse(YoutubeIE.suitable('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) # 668
  37. self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube'])
  38. self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])
  39. self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube'])
  40. self.assertMatch('http://www.cleanvideosearch.com/media/action/yt/watch?videoId=8v_4O44sfjM', ['youtube'])
  41. def test_youtube_channel_matching(self):
  42. assertChannel = lambda url: self.assertMatch(url, ['youtube:channel'])
  43. assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM')
  44. assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec')
  45. assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
  46. def test_youtube_user_matching(self):
  47. self.assertMatch('http://www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
  48. def test_youtube_feeds(self):
  49. self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watchlater'])
  50. self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:subscriptions'])
  51. self.assertMatch('https://www.youtube.com/feed/recommended', ['youtube:recommended'])
  52. self.assertMatch('https://www.youtube.com/my_favorites', ['youtube:favorites'])
  53. def test_youtube_show_matching(self):
  54. self.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show'])
  55. def test_youtube_search_matching(self):
  56. self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
  57. self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
  58. def test_youtube_extract(self):
  59. assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
  60. assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
  61. assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
  62. assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
  63. assertExtractId('https://www.youtube.com/watch_popup?v=BaW_jenozKc', 'BaW_jenozKc')
  64. assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
  65. assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
  66. def test_facebook_matching(self):
  67. self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
  68. self.assertTrue(FacebookIE.suitable('https://www.facebook.com/cindyweather?fref=ts#!/photo.php?v=10152183998945793'))
  69. def test_no_duplicates(self):
  70. ies = gen_extractors()
  71. for tc in gettestcases(include_onlymatching=True):
  72. url = tc['url']
  73. for ie in ies:
  74. if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
  75. self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url))
  76. else:
  77. self.assertFalse(
  78. ie.suitable(url),
  79. '%s should not match URL %r . That URL belongs to %s.' % (type(ie).__name__, url, tc['name']))
  80. def test_keywords(self):
  81. self.assertMatch(':ytsubs', ['youtube:subscriptions'])
  82. self.assertMatch(':ytsubscriptions', ['youtube:subscriptions'])
  83. self.assertMatch(':ythistory', ['youtube:history'])
  84. def test_vimeo_matching(self):
  85. self.assertMatch('https://vimeo.com/channels/tributes', ['vimeo:channel'])
  86. self.assertMatch('https://vimeo.com/channels/31259', ['vimeo:channel'])
  87. self.assertMatch('https://vimeo.com/channels/31259/53576664', ['vimeo'])
  88. self.assertMatch('https://vimeo.com/user7108434', ['vimeo:user'])
  89. self.assertMatch('https://vimeo.com/user7108434/videos', ['vimeo:user'])
  90. self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
  91. # https://github.com/ytdl-org/youtube-dl/issues/1930
  92. def test_soundcloud_not_matching_sets(self):
  93. self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set'])
  94. def test_tumblr(self):
  95. self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', ['Tumblr'])
  96. self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430', ['Tumblr'])
  97. def test_pbs(self):
  98. # https://github.com/ytdl-org/youtube-dl/issues/2350
  99. self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs'])
  100. self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs'])
  101. def test_no_duplicated_ie_names(self):
  102. name_accu = collections.defaultdict(list)
  103. for ie in self.ies:
  104. name_accu[ie.IE_NAME.lower()].append(type(ie).__name__)
  105. for (ie_name, ie_list) in name_accu.items():
  106. self.assertEqual(
  107. len(ie_list), 1,
  108. 'Multiple extractors with the same IE_NAME "%s" (%s)' % (ie_name, ', '.join(ie_list)))
  109. if __name__ == '__main__':
  110. unittest.main()