[yt-dlp.git] / test / test_all_urls.py

#!/usr/bin/env python

from __future__ import unicode_literals

# Allow direct execution
import os
import sys
import unittest
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))


from test.helper import gettestcases

from youtube_dl.extractor import (
    FacebookIE,
    gen_extractors,
    JustinTVIE,
    YoutubeIE,
)


class TestAllURLsMatching(unittest.TestCase):
    def setUp(self):
        self.ies = gen_extractors()

    def matching_ies(self, url):
        return [ie.IE_NAME for ie in self.ies if ie.suitable(url) and ie.IE_NAME != 'generic']

    def assertMatch(self, url, ie_list):
        self.assertEqual(self.matching_ies(url), ie_list)

    def test_youtube_playlist_matching(self):
        assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
        assertPlaylist('ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
        assertPlaylist('UUBABnxM4Ar9ten8Mdjj1j0Q') #585
        assertPlaylist('PL63F0C78739B09958')
        assertPlaylist('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
        assertPlaylist('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
        assertPlaylist('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')
        assertPlaylist('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012') #668
        self.assertFalse('youtube:playlist' in self.matching_ies('PLtS2H6bU1M'))
        # Top tracks
        assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')

    def test_youtube_matching(self):
        self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))
        self.assertFalse(YoutubeIE.suitable('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
        self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube'])
        self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])
        self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube'])
        self.assertMatch('http://www.cleanvideosearch.com/media/action/yt/watch?videoId=8v_4O44sfjM', ['youtube'])

    def test_youtube_channel_matching(self):
        assertChannel = lambda url: self.assertMatch(url, ['youtube:channel'])
        assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM')
        assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM?feature=gb_ch_rec')
        assertChannel('https://www.youtube.com/channel/HCtnHdj3df7iM/videos')

    def test_youtube_user_matching(self):
        self.assertMatch('www.youtube.com/NASAgovVideo/videos', ['youtube:user'])

    def test_youtube_feeds(self):
        self.assertMatch('https://www.youtube.com/feed/watch_later', ['youtube:watch_later'])
        self.assertMatch('https://www.youtube.com/feed/subscriptions', ['youtube:subscriptions'])
        self.assertMatch('https://www.youtube.com/feed/recommended', ['youtube:recommended'])
        self.assertMatch('https://www.youtube.com/my_favorites', ['youtube:favorites'])

    def test_youtube_show_matching(self):
        self.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show'])

    def test_youtube_search_matching(self):
        self.assertMatch('http://www.youtube.com/results?search_query=making+mustard', ['youtube:search_url'])
        self.assertMatch('https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', ['youtube:search_url'])

    def test_justin_tv_channelid_matching(self):
        self.assertTrue(JustinTVIE.suitable('justin.tv/vanillatv'))
        self.assertTrue(JustinTVIE.suitable('twitch.tv/vanillatv'))
        self.assertTrue(JustinTVIE.suitable('www.justin.tv/vanillatv'))
        self.assertTrue(JustinTVIE.suitable('www.twitch.tv/vanillatv'))
        self.assertTrue(JustinTVIE.suitable('http://www.justin.tv/vanillatv'))
        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv'))
        self.assertTrue(JustinTVIE.suitable('http://www.justin.tv/vanillatv/'))
        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv/'))

    def test_justintv_videoid_matching(self):
        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv/b/328087483'))

    def test_justin_tv_chapterid_matching(self):
        self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361'))

    def test_youtube_extract(self):
        assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
        assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
        assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
        assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')
        assertExtractId('https://www.youtube.com/watch_popup?v=BaW_jenozKc', 'BaW_jenozKc')
        assertExtractId('http://www.youtube.com/watch?v=BaW_jenozKcsharePLED17F32AD9753930', 'BaW_jenozKc')
        assertExtractId('BaW_jenozKc', 'BaW_jenozKc')

    def test_facebook_matching(self):
        self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))

    def test_no_duplicates(self):
        ies = gen_extractors()
        for tc in gettestcases(include_onlymatching=True):
            url = tc['url']
            for ie in ies:
                if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
                    self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url))
                else:
                    self.assertFalse(ie.suitable(url), '%s should not match URL %r' % (type(ie).__name__, url))

    def test_keywords(self):
        self.assertMatch(':ytsubs', ['youtube:subscriptions'])
        self.assertMatch(':ytsubscriptions', ['youtube:subscriptions'])
        self.assertMatch(':ythistory', ['youtube:history'])
        self.assertMatch(':thedailyshow', ['ComedyCentralShows'])
        self.assertMatch(':tds', ['ComedyCentralShows'])
        self.assertMatch(':colbertreport', ['ComedyCentralShows'])
        self.assertMatch(':cr', ['ComedyCentralShows'])

    def test_vimeo_matching(self):
        self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])
        self.assertMatch('http://vimeo.com/channels/31259', ['vimeo:channel'])
        self.assertMatch('http://vimeo.com/channels/31259/53576664', ['vimeo'])
        self.assertMatch('http://vimeo.com/user7108434', ['vimeo:user'])
        self.assertMatch('http://vimeo.com/user7108434/videos', ['vimeo:user'])
        self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])

    # https://github.com/rg3/youtube-dl/issues/1930
    def test_soundcloud_not_matching_sets(self):
        self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set'])

    def test_tumblr(self):
        self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', ['Tumblr'])
        self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430', ['Tumblr'])

    def test_pbs(self):
        # https://github.com/rg3/youtube-dl/issues/2350
        self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS'])
        self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS'])

    def test_ComedyCentralShows(self):
        self.assertMatch(
            'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
            ['ComedyCentralShows'])
        self.assertMatch(
            'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
            ['ComedyCentralShows'])
        self.assertMatch(
            'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
            ['ComedyCentralShows'])
        self.assertMatch(
            'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
            ['ComedyCentralShows'])
        self.assertMatch(
            'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
            ['ComedyCentralShows'])
        self.assertMatch(
            'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
            ['ComedyCentralShows'])
        self.assertMatch(
            'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
            ['ComedyCentralShows'])
        self.assertMatch(
            'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
            ['ComedyCentralShows'])

    def test_yahoo_https(self):
        # https://github.com/rg3/youtube-dl/issues/2701
        self.assertMatch(
            'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
            ['Yahoo'])


if __name__ == '__main__':
    unittest.main()
Commit	Line	Data
e387eb5a PH	1	#!/usr/bin/env python
e387eb5a PH	2
bf5f6100 PH	3	from __future__ import unicode_literals
bf5f6100 PH	4
44a5f171 PH	5	# Allow direct execution
44a5f171 PH	6	import os
e387eb5a PH	7	import sys
e387eb5a PH	8	import unittest
44a5f171	9	sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
e387eb5a	10
e387eb5a	11
ff14fc49	12	from test.helper import gettestcases
44a5f171 PH	13
44a5f171 PH	14	from youtube_dl.extractor import (
8c8e3eec	15	FacebookIE,
44a5f171 PH	16	gen_extractors,
	17	JustinTVIE,
	18	YoutubeIE,
	19	)
	20
e387eb5a	21
3bb61659	22	class TestAllURLsMatching(unittest.TestCase):
f4b05232 JMF	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
3bb61659	32	def test_youtube_playlist_matching(self):
e3ea4790	33	assertPlaylist = lambda url: self.assertMatch(url, ['youtube:playlist'])
bf5f6100 PH	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'))
d67cc9fa JMF	42	# Top tracks
d67cc9fa JMF	43	assertPlaylist('https://www.youtube.com/playlist?list=MCUS.20142101')
e387eb5a PH	44
e387eb5a PH	45	def test_youtube_matching(self):
bf5f6100 PH	46	self.assertTrue(YoutubeIE.suitable('PLtS2H6bU1M'))
bf5f6100 PH	47	self.assertFalse(YoutubeIE.suitable('https://www.youtube.com/watch?v=AV6J6_AeFEQ&playnext=1&list=PL4023E734DA416012')) #668
f4b05232 JMF	48	self.assertMatch('http://youtu.be/BaW_jenozKc', ['youtube'])
f4b05232 JMF	49	self.assertMatch('http://www.youtube.com/v/BaW_jenozKc', ['youtube'])
e69ae5b9	50	self.assertMatch('https://youtube.googleapis.com/v/BaW_jenozKc', ['youtube'])
b9c76aa1	51	self.assertMatch('http://www.cleanvideosearch.com/media/action/yt/watch?videoId=8v_4O44sfjM', ['youtube'])
e387eb5a	52
fb6c3199	53	def test_youtube_channel_matching(self):
e3ea4790 JMF	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')
fb6c3199	58
f4b05232 JMF	59	def test_youtube_user_matching(self):
	60	self.assertMatch('www.youtube.com/NASAgovVideo/videos', ['youtube:user'])
	61
faab1d38 JMF	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'])
	67
e3ea4790 JMF	68	def test_youtube_show_matching(self):
	69	self.assertMatch('http://www.youtube.com/show/airdisasters', ['youtube:show'])
	70
c9ae7b95 PH	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
50b4d259	75	def test_justin_tv_channelid_matching(self):
5367fe7f PH	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/'))
50b4d259 CD	84
50b4d259 CD	85	def test_justintv_videoid_matching(self):
5367fe7f	86	self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/vanillatv/b/328087483'))
50b4d259 CD	87
50b4d259 CD	88	def test_justin_tv_chapterid_matching(self):
5367fe7f	89	self.assertTrue(JustinTVIE.suitable('http://www.twitch.tv/tsm_theoddone/c/2349361'))
50b4d259	90
3bb61659	91	def test_youtube_extract(self):
97665381	92	assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
8963d9c2 JMF	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')
3bb61659	99
8c8e3eec	100	def test_facebook_matching(self):
bf5f6100	101	self.assertTrue(FacebookIE.suitable('https://www.facebook.com/Shiniknoh#!/photo.php?v=10153317450565268'))
8c8e3eec	102
a924876f PH	103	def test_no_duplicates(self):
a924876f PH	104	ies = gen_extractors()
52fadd5f	105	for tc in gettestcases(include_onlymatching=True):
a924876f PH	106	url = tc['url']
a924876f PH	107	for ie in ies:
8c8e3eec	108	if type(ie).__name__ in ('GenericIE', tc['name'] + 'IE'):
a924876f PH	109	self.assertTrue(ie.suitable(url), '%s should match URL %r' % (type(ie).__name__, url))
	110	else:
	111	self.assertFalse(ie.suitable(url), '%s should not match URL %r' % (type(ie).__name__, url))
	112
897f36d1	113	def test_keywords(self):
f4b05232 JMF	114	self.assertMatch(':ytsubs', ['youtube:subscriptions'])
f4b05232 JMF	115	self.assertMatch(':ytsubscriptions', ['youtube:subscriptions'])
f459d170	116	self.assertMatch(':ythistory', ['youtube:history'])
16e05584 JMF	117	self.assertMatch(':thedailyshow', ['ComedyCentralShows'])
	118	self.assertMatch(':tds', ['ComedyCentralShows'])
	119	self.assertMatch(':colbertreport', ['ComedyCentralShows'])
	120	self.assertMatch(':cr', ['ComedyCentralShows'])
897f36d1	121
55a10eab JMF	122	def test_vimeo_matching(self):
55a10eab JMF	123	self.assertMatch('http://vimeo.com/channels/tributes', ['vimeo:channel'])
b1ff8722 JMF	124	self.assertMatch('http://vimeo.com/channels/31259', ['vimeo:channel'])
b1ff8722 JMF	125	self.assertMatch('http://vimeo.com/channels/31259/53576664', ['vimeo'])
55a10eab	126	self.assertMatch('http://vimeo.com/user7108434', ['vimeo:user'])
48a20346 PH	127	self.assertMatch('http://vimeo.com/user7108434/videos', ['vimeo:user'])
48a20346 PH	128	self.assertMatch('https://vimeo.com/user21297594/review/75524534/3c257a1b5d', ['vimeo:review'])
55a10eab	129
4ff50ef8 PH	130	# https://github.com/rg3/youtube-dl/issues/1930
	131	def test_soundcloud_not_matching_sets(self):
	132	self.assertMatch('http://soundcloud.com/floex/sets/gone-ep', ['soundcloud:set'])
a924876f	133
456895d9 PH	134	def test_tumblr(self):
	135	self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430/orphan-black-dvd-extra-behind-the-scenes', ['Tumblr'])
	136	self.assertMatch('http://tatianamaslanydaily.tumblr.com/post/54196191430', ['Tumblr'])
	137
bf5f6100 PH	138	def test_pbs(self):
	139	# https://github.com/rg3/youtube-dl/issues/2350
	140	self.assertMatch('http://video.pbs.org/viralplayer/2365173446/', ['PBS'])
773c0b4b	141	self.assertMatch('http://video.pbs.org/widget/partnerplayer/980042464/', ['PBS'])
bf5f6100	142
69c01a9f	143	def test_ComedyCentralShows(self):
16f4eb72 PH	144	self.assertMatch(
	145	'http://thedailyshow.cc.com/extended-interviews/xm3fnq/andrew-napolitano-extended-interview',
	146	['ComedyCentralShows'])
	147	self.assertMatch(
	148	'http://thecolbertreport.cc.com/videos/29w6fx/-realhumanpraise-for-fox-news',
	149	['ComedyCentralShows'])
65148662 PH	150	self.assertMatch(
	151	'http://thecolbertreport.cc.com/videos/gh6urb/neil-degrasse-tyson-pt--1?xrs=eml_col_031114',
	152	['ComedyCentralShows'])
968ed2a7 PH	153	self.assertMatch(
	154	'http://thedailyshow.cc.com/guests/michael-lewis/3efna8/exclusive---michael-lewis-extended-interview-pt--3',
	155	['ComedyCentralShows'])
29e3e682 PH	156	self.assertMatch(
	157	'http://thedailyshow.cc.com/episodes/sy7yv0/april-8--2014---denis-leary',
	158	['ComedyCentralShows'])
	159	self.assertMatch(
	160	'http://thecolbertreport.cc.com/episodes/8ase07/april-8--2014---jane-goodall',
	161	['ComedyCentralShows'])
	162	self.assertMatch(
	163	'http://thedailyshow.cc.com/video-playlists/npde3s/the-daily-show-19088-highlights',
	164	['ComedyCentralShows'])
7753cadb PH	165	self.assertMatch(
	166	'http://thedailyshow.cc.com/special-editions/2l8fdb/special-edition---a-look-back-at-food',
	167	['ComedyCentralShows'])
69c01a9f	168
c8edf47b PH	169	def test_yahoo_https(self):
	170	# https://github.com/rg3/youtube-dl/issues/2701
	171	self.assertMatch(
	172	'https://screen.yahoo.com/smartwatches-latest-wearable-gadgets-163745379-cbs.html',
	173	['Yahoo'])
	174
52fadd5f	175
e387eb5a PH	176	if __name__ == '__main__':
e387eb5a PH	177	unittest.main()