]> jfr.im git - yt-dlp.git/blob - test/test_all_urls.py
Merge 'ytdl-org/youtube-dl/master' release 2020.11.19
[yt-dlp.git] / 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_dlc.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 assertTab = lambda url: self.assertMatch(url, ['youtube:tab'])
35 assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
36 assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') # 585
37 assertPlaylist('PL63F0C78739B09958')
38 assertTab('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
39 assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
40 assertTab('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
41 assertTab('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') # 668
42 self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
43 # Top tracks
44 assertTab('https://www.youtube.com/playlist?list=MCUS.20142101')
45
46 def test_youtube_matching(self):
47 self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))
48 self.assertFalse(YoutubeIE.suitable('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) # 668
49 self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube'])
50 self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])
51 self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube'])
52 self.assertMatch('http://www.cleanvideosearch.com/media/action/yt/watch?videoId=8v_4O44sfjM', ['youtube'])
53
54 def test_youtube_channel_matching(self):
55 assertChannel = lambda url: self.assertMatch(url, ['youtube:tab'])
56 assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM')
57 assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec')
58 assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')
59
60 # def test_youtube_user_matching(self):
61 # self.assertMatch('http://www.youtube.com/NASAgovVideo/videos', ['youtube:tab'])
62
63 def test_youtube_feeds(self):
64 self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watchlater'])
65 self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:subscriptions'])
66 self.assertMatch('https://www.youtube.com/feed/recommended', ['youtube:recommended'])
67
68 # def test_youtube_search_matching(self):
69 # self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
70 # self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])
71
72 def test_youtube_extract(self):
73 assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
74 assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
75 assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
76 assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
77 assertExtractId('https://www.youtube.com/watch_popup?v=BaW_jenozKc', 'BaW_jenozKc')
78 assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
79 assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
80
81 def test_facebook_matching(self):
82 self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
83 self.assertTrue(FacebookIE.suitable('https://www.facebook.com/cindyweather?fref=ts#!/photo.php?v=10152183998945793'))
84
85 def test_no_duplicates(self):
86 ies = gen_extractors()
87 for tc in gettestcases(include_onlymatching=True):
88 url = tc['url']
89 for ie in ies:
90 if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
91 self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url))
92 else:
93 self.assertFalse(
94 ie.suitable(url),
95 '%s should not match URL %r . That URL belongs to %s.' % (type(ie).__name__, url, tc['name']))
96
97 def test_keywords(self):
98 self.assertMatch(':ytsubs', ['youtube:subscriptions'])
99 self.assertMatch(':ytsubscriptions', ['youtube:subscriptions'])
100 self.assertMatch(':ythistory', ['youtube:history'])
101
102 def test_vimeo_matching(self):
103 self.assertMatch('https://vimeo.com/channels/tributes', ['vimeo:channel'])
104 self.assertMatch('https://vimeo.com/channels/31259', ['vimeo:channel'])
105 self.assertMatch('https://vimeo.com/channels/31259/53576664', ['vimeo'])
106 self.assertMatch('https://vimeo.com/user7108434', ['vimeo:user'])
107 self.assertMatch('https://vimeo.com/user7108434/videos', ['vimeo:user'])
108 self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
109
110 # https://github.com/ytdl-org/youtube-dl/issues/1930
111 def test_soundcloud_not_matching_sets(self):
112 self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set'])
113
114 def test_tumblr(self):
115 self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', ['Tumblr'])
116 self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430', ['Tumblr'])
117
118 def test_pbs(self):
119 # https://github.com/ytdl-org/youtube-dl/issues/2350
120 self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['pbs'])
121 self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['pbs'])
122
123 def test_no_duplicated_ie_names(self):
124 name_accu = collections.defaultdict(list)
125 for ie in self.ies:
126 name_accu[ie.IE_NAME.lower()].append(type(ie).__name__)
127 for (ie_name, ie_list) in name_accu.items():
128 self.assertEqual(
129 len(ie_list), 1,
130 'Multiple extractors with the same IE_NAME "%s" (%s)' % (ie_name, ', '.join(ie_list)))
131
132
133 if __name__ == '__main__':
134 unittest.main()