]>
jfr.im git - yt-dlp.git/blob - test/test_all_urls.py
3 from __future__
import unicode_literals
5 # Allow direct execution
9 sys
.path
.insert(0, os
.path
.dirname(os
.path
.dirname(os
.path
.abspath(__file__
))))
12 from test
.helper
import gettestcases
14 from youtube_dl
.extractor
import (
22 class TestAllURLsMatching(unittest
.TestCase
):
24 self
.ies
= gen_extractors()
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']
29 def assertMatch(self
, url
, ie_list
):
30 self
.assertEqual(self
.matching_ies(url
), ie_list
)
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'))
43 assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
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'])
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')
59 def test_youtube_user_matching(self
):
60 self
.assertMatch('www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
62 def test_youtube_feeds(self
):
63 self
.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watch_later'])
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'])
68 def test_youtube_show_matching(self
):
69 self
.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show'])
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'])
75 def test_justin_tv_channelid_matching(self
):
76 self
.assertTrue(JustinTVIE
.suitable('justin.tv/vanillatv'))
77 self
.assertTrue(JustinTVIE
.suitable('twitch.tv/vanillatv'))
78 self
.assertTrue(JustinTVIE
.suitable('www.justin.tv/vanillatv'))
79 self
.assertTrue(JustinTVIE
.suitable('www.twitch.tv/vanillatv'))
80 self
.assertTrue(JustinTVIE
.suitable('http://www.justin.tv/vanillatv'))
81 self
.assertTrue(JustinTVIE
.suitable('http://www.twitch.tv/vanillatv'))
82 self
.assertTrue(JustinTVIE
.suitable('http://www.justin.tv/vanillatv/'))
83 self
.assertTrue(JustinTVIE
.suitable('http://www.twitch.tv/vanillatv/'))
85 def test_justintv_videoid_matching(self
):
86 self
.assertTrue(JustinTVIE
.suitable('http://www.twitch.tv/vanillatv/b/328087483'))
88 def test_justin_tv_chapterid_matching(self
):
89 self
.assertTrue(JustinTVIE
.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361'))
91 def test_youtube_extract(self
):
92 assertExtractId
= lambda url
, id: self
.assertEqual(YoutubeIE
.extract_id(url
), id)
93 assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
94 assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
95 assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
96 assertExtractId('https://www.youtube.com/watch_popup?v=BaW_jenozKc', 'BaW_jenozKc')
97 assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
98 assertExtractId('BaW_jenozKc', 'BaW_jenozKc')
100 def test_facebook_matching(self
):
101 self
.assertTrue(FacebookIE
.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
102 self
.assertTrue(FacebookIE
.suitable('https://www.facebook.com/cindyweather?fref=ts#!/photo.php?v=10152183998945793'))
104 def test_no_duplicates(self
):
105 ies
= gen_extractors()
106 for tc
in gettestcases(include_onlymatching
=True):
109 if type(ie
).__name
__ in ('GenericIE', tc
['name'] + 'IE'):
110 self
.assertTrue(ie
.suitable(url
), '%s should match URL %r' % (type(ie
).__name
__, url
))
112 self
.assertFalse(ie
.suitable(url
), '%s should not match URL %r' % (type(ie
).__name
__, url
))
114 def test_keywords(self
):
115 self
.assertMatch(':ytsubs', ['youtube:subscriptions'])
116 self
.assertMatch(':ytsubscriptions', ['youtube:subscriptions'])
117 self
.assertMatch(':ythistory', ['youtube:history'])
118 self
.assertMatch(':thedailyshow', ['ComedyCentralShows'])
119 self
.assertMatch(':tds', ['ComedyCentralShows'])
120 self
.assertMatch(':colbertreport', ['ComedyCentralShows'])
121 self
.assertMatch(':cr', ['ComedyCentralShows'])
123 def test_vimeo_matching(self
):
124 self
.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])
125 self
.assertMatch('http://vimeo.com/channels/31259', ['vimeo:channel'])
126 self
.assertMatch('http://vimeo.com/channels/31259/53576664', ['vimeo'])
127 self
.assertMatch('http://vimeo.com/user7108434', ['vimeo:user'])
128 self
.assertMatch('http://vimeo.com/user7108434/videos', ['vimeo:user'])
129 self
.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
131 # https://github.com/rg3/youtube-dl/issues/1930
132 def test_soundcloud_not_matching_sets(self
):
133 self
.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set'])
135 def test_tumblr(self
):
136 self
.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', ['Tumblr'])
137 self
.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430', ['Tumblr'])
140 # https://github.com/rg3/youtube-dl/issues/2350
141 self
.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS'])
142 self
.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS'])
144 def test_ComedyCentralShows(self
):
146 'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
147 ['ComedyCentralShows'])
149 'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
150 ['ComedyCentralShows'])
152 'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
153 ['ComedyCentralShows'])
155 'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
156 ['ComedyCentralShows'])
158 'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
159 ['ComedyCentralShows'])
161 'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
162 ['ComedyCentralShows'])
164 'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
165 ['ComedyCentralShows'])
167 'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
168 ['ComedyCentralShows'])
170 def test_yahoo_https(self
):
171 # https://github.com/rg3/youtube-dl/issues/2701
173 'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
177 if __name__
== '__main__':