mirror of
https://github.com/ytdl-org/youtube-dl
synced 2025-07-21 02:44:14 +09:00
Compare commits
15 Commits
0c71fddace
...
fb251288ba
Author | SHA1 | Date | |
---|---|---|---|
![]() |
fb251288ba | ||
![]() |
2b4fbfce25 | ||
![]() |
1bc45b8b6c | ||
![]() |
b982d77d0b | ||
![]() |
c55dbf4838 | ||
![]() |
087d865230 | ||
![]() |
a4fc1151f1 | ||
![]() |
a464c159e6 | ||
![]() |
7dca08eff0 | ||
![]() |
2239ee7965 | ||
![]() |
44f73880fe | ||
![]() |
81d6b10f48 | ||
![]() |
1cd4bb0d82 | ||
![]() |
2fe0d70b6e | ||
![]() |
76f2b63a26 |
@ -84,6 +84,21 @@ _SIG_TESTS = [
|
|||||||
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
|
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
|
||||||
'0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xxAj7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJ2OySqa0q',
|
'0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xxAj7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJ2OySqa0q',
|
||||||
),
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
|
||||||
|
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
|
||||||
|
'AAOAOq0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xx8j7vgpDL0QwbdV06sCIEzpWqMGkFR20CFOS21Tp-7vj_EMu-m37KtXJoOy1',
|
||||||
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/363db69b/player_ias.vflset/en_US/base.js',
|
||||||
|
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
|
||||||
|
'0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpz2ICs6EVdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
|
||||||
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/4fcd6e4a/player_ias.vflset/en_US/base.js',
|
||||||
|
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
|
||||||
|
'wAOAOq0QJ8ARAIgXmPlOPSBkkUs1bYFYlJCfe29xx8q7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0',
|
||||||
|
),
|
||||||
]
|
]
|
||||||
|
|
||||||
_NSIG_TESTS = [
|
_NSIG_TESTS = [
|
||||||
@ -153,7 +168,7 @@ _NSIG_TESTS = [
|
|||||||
),
|
),
|
||||||
(
|
(
|
||||||
'https://www.youtube.com/s/player/c57c113c/player_ias.vflset/en_US/base.js',
|
'https://www.youtube.com/s/player/c57c113c/player_ias.vflset/en_US/base.js',
|
||||||
'-Txvy6bT5R6LqgnQNx', 'dcklJCnRUHbgSg',
|
'M92UUMHa8PdvPd3wyM', '3hPqLJsiNZx7yA',
|
||||||
),
|
),
|
||||||
(
|
(
|
||||||
'https://www.youtube.com/s/player/5a3b6271/player_ias.vflset/en_US/base.js',
|
'https://www.youtube.com/s/player/5a3b6271/player_ias.vflset/en_US/base.js',
|
||||||
@ -173,7 +188,7 @@ _NSIG_TESTS = [
|
|||||||
),
|
),
|
||||||
(
|
(
|
||||||
'https://www.youtube.com/s/player/cfa9e7cb/player_ias.vflset/en_US/base.js',
|
'https://www.youtube.com/s/player/cfa9e7cb/player_ias.vflset/en_US/base.js',
|
||||||
'qO0NiMtYQ7TeJnfFG2', 'k9cuJDHNS5O7kQ',
|
'aCi3iElgd2kq0bxVbQ', 'QX1y8jGb2IbZ0w',
|
||||||
),
|
),
|
||||||
(
|
(
|
||||||
'https://www.youtube.com/s/player/8c7583ff/player_ias.vflset/en_US/base.js',
|
'https://www.youtube.com/s/player/8c7583ff/player_ias.vflset/en_US/base.js',
|
||||||
@ -231,10 +246,6 @@ _NSIG_TESTS = [
|
|||||||
'https://www.youtube.com/s/player/f6e09c70/player_ias_tce.vflset/en_US/base.js',
|
'https://www.youtube.com/s/player/f6e09c70/player_ias_tce.vflset/en_US/base.js',
|
||||||
'W9HJZKktxuYoDTqW', 'jHbbkcaxm54',
|
'W9HJZKktxuYoDTqW', 'jHbbkcaxm54',
|
||||||
),
|
),
|
||||||
(
|
|
||||||
'https://www.youtube.com/s/player/643afba4/player_ias.vflset/en_US/base.js',
|
|
||||||
'W9HJZKktxuYoDTqW', 'larxUlagTRAcSw',
|
|
||||||
),
|
|
||||||
(
|
(
|
||||||
'https://www.youtube.com/s/player/e7567ecf/player_ias_tce.vflset/en_US/base.js',
|
'https://www.youtube.com/s/player/e7567ecf/player_ias_tce.vflset/en_US/base.js',
|
||||||
'Sy4aDGc0VpYRR9ew_', '5UPOT1VhoZxNLQ',
|
'Sy4aDGc0VpYRR9ew_', '5UPOT1VhoZxNLQ',
|
||||||
@ -259,6 +270,22 @@ _NSIG_TESTS = [
|
|||||||
'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
|
'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
|
||||||
'ir9-V6cdbCiyKxhr', '2PL7ZDYAALMfmA',
|
'ir9-V6cdbCiyKxhr', '2PL7ZDYAALMfmA',
|
||||||
),
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/643afba4/player_ias.vflset/en_US/base.js',
|
||||||
|
'W9HJZKktxuYoDTqW', 'larxUlagTRAcSw',
|
||||||
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/363db69b/player_ias.vflset/en_US/base.js',
|
||||||
|
'eWYu5d5YeY_4LyEDc', 'XJQqf-N7Xra3gg',
|
||||||
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/4fcd6e4a/player_ias.vflset/en_US/base.js',
|
||||||
|
'o_L251jm8yhZkWtBW', 'lXoxI3XvToqn6A',
|
||||||
|
),
|
||||||
|
(
|
||||||
|
'https://www.youtube.com/s/player/4fcd6e4a/tv-player-ias.vflset/tv-player-ias.js',
|
||||||
|
'o_L251jm8yhZkWtBW', 'lXoxI3XvToqn6A',
|
||||||
|
),
|
||||||
]
|
]
|
||||||
|
|
||||||
|
|
||||||
@ -271,6 +298,8 @@ class TestPlayerInfo(unittest.TestCase):
|
|||||||
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-en_US.vflset/base.js', '64dddad9'),
|
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-en_US.vflset/base.js', '64dddad9'),
|
||||||
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-de_DE.vflset/base.js', '64dddad9'),
|
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-de_DE.vflset/base.js', '64dddad9'),
|
||||||
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-tablet-en_US.vflset/base.js', '64dddad9'),
|
('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-tablet-en_US.vflset/base.js', '64dddad9'),
|
||||||
|
('https://www.youtube.com/s/player/e7567ecf/player_ias_tce.vflset/en_US/base.js', 'e7567ecf'),
|
||||||
|
('https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js', '643afba4'),
|
||||||
# obsolete
|
# obsolete
|
||||||
('https://www.youtube.com/yts/jsbin/player_ias-vfle4-e03/en_US/base.js', 'vfle4-e03'),
|
('https://www.youtube.com/yts/jsbin/player_ias-vfle4-e03/en_US/base.js', 'vfle4-e03'),
|
||||||
('https://www.youtube.com/yts/jsbin/player_ias-vfl49f_g4/en_US/base.js', 'vfl49f_g4'),
|
('https://www.youtube.com/yts/jsbin/player_ias-vfl49f_g4/en_US/base.js', 'vfl49f_g4'),
|
||||||
@ -280,8 +309,9 @@ class TestPlayerInfo(unittest.TestCase):
|
|||||||
('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js', 'vflXGBaUN'),
|
('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflXGBaUN.js', 'vflXGBaUN'),
|
||||||
('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js', 'vflKjOTVq'),
|
('https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js', 'vflKjOTVq'),
|
||||||
)
|
)
|
||||||
|
ie = YoutubeIE(FakeYDL({'cachedir': False}))
|
||||||
for player_url, expected_player_id in PLAYER_URLS:
|
for player_url, expected_player_id in PLAYER_URLS:
|
||||||
player_id = YoutubeIE._extract_player_info(player_url)
|
player_id = ie._extract_player_info(player_url)
|
||||||
self.assertEqual(player_id, expected_player_id)
|
self.assertEqual(player_id, expected_player_id)
|
||||||
|
|
||||||
|
|
||||||
@ -301,8 +331,8 @@ class TestSignature(unittest.TestCase):
|
|||||||
def t_factory(name, sig_func, url_pattern):
|
def t_factory(name, sig_func, url_pattern):
|
||||||
def make_tfunc(url, sig_input, expected_sig):
|
def make_tfunc(url, sig_input, expected_sig):
|
||||||
m = url_pattern.match(url)
|
m = url_pattern.match(url)
|
||||||
assert m, '%r should follow URL format' % url
|
assert m, '{0!r} should follow URL format'.format(url)
|
||||||
test_id = m.group('id')
|
test_id = re.sub(r'[/.-]', '_', m.group('id') or m.group('compat_id'))
|
||||||
|
|
||||||
def test_func(self):
|
def test_func(self):
|
||||||
basename = 'player-{0}-{1}.js'.format(name, test_id)
|
basename = 'player-{0}-{1}.js'.format(name, test_id)
|
||||||
@ -335,12 +365,16 @@ def n_sig(jscode, sig_input):
|
|||||||
|
|
||||||
|
|
||||||
make_sig_test = t_factory(
|
make_sig_test = t_factory(
|
||||||
'signature', signature, re.compile(r'.*(?:-|/player/)(?P<id>[a-zA-Z0-9_-]+)(?:/.+\.js|(?:/watch_as3|/html5player)?\.[a-z]+)$'))
|
'signature', signature,
|
||||||
|
re.compile(r'''(?x)
|
||||||
|
.+/(?P<h5>html5)?player(?(h5)(?:-en_US)?-|/)(?P<id>[a-zA-Z0-9/._-]+)
|
||||||
|
(?(h5)/(?:watch_as3|html5player))?\.js$
|
||||||
|
'''))
|
||||||
for test_spec in _SIG_TESTS:
|
for test_spec in _SIG_TESTS:
|
||||||
make_sig_test(*test_spec)
|
make_sig_test(*test_spec)
|
||||||
|
|
||||||
make_nsig_test = t_factory(
|
make_nsig_test = t_factory(
|
||||||
'nsig', n_sig, re.compile(r'.+/player/(?P<id>[a-zA-Z0-9_-]+)/.+.js$'))
|
'nsig', n_sig, re.compile(r'.+/player/(?P<id>[a-zA-Z0-9_/.-]+)\.js$'))
|
||||||
for test_spec in _NSIG_TESTS:
|
for test_spec in _NSIG_TESTS:
|
||||||
make_nsig_test(*test_spec)
|
make_nsig_test(*test_spec)
|
||||||
|
|
||||||
|
@ -157,7 +157,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
|
|||||||
|
|
||||||
description = strip_or_none(xpath_text(itemdoc, 'description'))
|
description = strip_or_none(xpath_text(itemdoc, 'description'))
|
||||||
|
|
||||||
timestamp = timeconvert(xpath_text(itemdoc, 'pubDate'))
|
timestamp = timeconvert(xpath_text(itemdoc, 'pubDate') or xpath_text(itemdoc, 'airDate'))
|
||||||
|
|
||||||
title_el = None
|
title_el = None
|
||||||
if title_el is None:
|
if title_el is None:
|
||||||
@ -290,7 +290,17 @@ class MTVServicesInfoExtractor(InfoExtractor):
|
|||||||
main_container = self._extract_child_with_type(data, 'MainContainer')
|
main_container = self._extract_child_with_type(data, 'MainContainer')
|
||||||
ab_testing = self._extract_child_with_type(main_container, 'ABTesting')
|
ab_testing = self._extract_child_with_type(main_container, 'ABTesting')
|
||||||
video_player = self._extract_child_with_type(ab_testing or main_container, 'VideoPlayer')
|
video_player = self._extract_child_with_type(ab_testing or main_container, 'VideoPlayer')
|
||||||
mgid = video_player['props']['media']['video']['config']['uri']
|
if video_player:
|
||||||
|
mgid = video_player['props']['media']['video']['config']['uri']
|
||||||
|
else:
|
||||||
|
flex_wrapper = self._extract_child_with_type(ab_testing or main_container, 'FlexWrapper')
|
||||||
|
auth_suite_wrapper = self._extract_child_with_type(flex_wrapper, 'AuthSuiteWrapper')
|
||||||
|
player = self._extract_child_with_type(auth_suite_wrapper or flex_wrapper, 'Player')
|
||||||
|
if player:
|
||||||
|
mgid = player['props']['videoDetail']['mgid']
|
||||||
|
|
||||||
|
if not mgid:
|
||||||
|
raise ExtractorError('Could not extract mgid')
|
||||||
|
|
||||||
return mgid
|
return mgid
|
||||||
|
|
||||||
|
@ -6,19 +6,19 @@ from .mtv import MTVServicesInfoExtractor
|
|||||||
|
|
||||||
class SouthParkIE(MTVServicesInfoExtractor):
|
class SouthParkIE(MTVServicesInfoExtractor):
|
||||||
IE_NAME = 'southpark.cc.com'
|
IE_NAME = 'southpark.cc.com'
|
||||||
_VALID_URL = r'https?://(?:www\.)?(?P<url>southpark(?:\.cc|studios)\.com/(?:clips|(?:full-)?episodes|collections)/(?P<id>.+?)(\?|#|$))'
|
_VALID_URL = r'https?://(?:www\.)?(?P<url>southpark(?:\.cc|studios)\.com/((?:video-)?clips|(?:full-)?episodes|collections)/(?P<id>.+?)(\?|#|$))'
|
||||||
|
|
||||||
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
|
_FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
|
||||||
|
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://southpark.cc.com/clips/104437/bat-daded#tab=featured',
|
'url': 'https://southpark.cc.com/video-clips/d7wr06/south-park-you-all-agreed-to-counseling',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'id': 'a7bff6c2-ed00-11e0-aca6-0026b9414f30',
|
'id': '31929ad5-8269-11eb-8774-70df2f866ace',
|
||||||
'ext': 'mp4',
|
'ext': 'mp4',
|
||||||
'title': 'South Park|Bat Daded',
|
'title': 'You All Agreed to Counseling',
|
||||||
'description': 'Randy disqualifies South Park by getting into a fight with Bat Dad.',
|
'description': 'Kenny, Cartman, Stan, and Kyle visit Mr. Mackey and ask for his help getting Mrs. Nelson to come back. Mr. Mackey reveals the only way to get things back to normal is to get the teachers vaccinated.',
|
||||||
'timestamp': 1112760000,
|
'timestamp': 1615377600,
|
||||||
'upload_date': '20050406',
|
'upload_date': '20210310',
|
||||||
},
|
},
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://southpark.cc.com/collections/7758/fan-favorites/1',
|
'url': 'http://southpark.cc.com/collections/7758/fan-favorites/1',
|
||||||
@ -40,11 +40,11 @@ class SouthParkIE(MTVServicesInfoExtractor):
|
|||||||
|
|
||||||
class SouthParkEsIE(SouthParkIE):
|
class SouthParkEsIE(SouthParkIE):
|
||||||
IE_NAME = 'southpark.cc.com:español'
|
IE_NAME = 'southpark.cc.com:español'
|
||||||
_VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/episodios-en-espanol/(?P<id>.+?)(\?|#|$))'
|
_VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/es/episodios/(?P<id>.+?)(\?|#|$))'
|
||||||
_LANG = 'es'
|
_LANG = 'es'
|
||||||
|
|
||||||
_TESTS = [{
|
_TESTS = [{
|
||||||
'url': 'http://southpark.cc.com/episodios-en-espanol/s01e01-cartman-consigue-una-sonda-anal#source=351c1323-0b96-402d-a8b9-40d01b2e9bde&position=1&sort=!airdate',
|
'url': 'http://southpark.cc.com/es/episodios/s01e01-cartman-consigue-una-sonda-anal#source=351c1323-0b96-402d-a8b9-40d01b2e9bde&position=1&sort=!airdate',
|
||||||
'info_dict': {
|
'info_dict': {
|
||||||
'title': 'Cartman Consigue Una Sonda Anal',
|
'title': 'Cartman Consigue Una Sonda Anal',
|
||||||
'description': 'Cartman Consigue Una Sonda Anal',
|
'description': 'Cartman Consigue Una Sonda Anal',
|
||||||
@ -69,6 +69,7 @@ class SouthParkDeIE(SouthParkIE):
|
|||||||
'timestamp': 1380160800,
|
'timestamp': 1380160800,
|
||||||
'upload_date': '20130926',
|
'upload_date': '20130926',
|
||||||
},
|
},
|
||||||
|
'skip': 'Geo-restricted',
|
||||||
}, {
|
}, {
|
||||||
# non-ASCII characters in initial URL
|
# non-ASCII characters in initial URL
|
||||||
'url': 'http://www.southpark.de/alle-episoden/s18e09-hashtag-aufwärmen',
|
'url': 'http://www.southpark.de/alle-episoden/s18e09-hashtag-aufwärmen',
|
||||||
@ -77,6 +78,7 @@ class SouthParkDeIE(SouthParkIE):
|
|||||||
'description': 'Kyle will mit seinem kleinen Bruder Ike Videospiele spielen. Als der nicht mehr mit ihm spielen will, hat Kyle Angst, dass er die Kids von heute nicht mehr versteht.',
|
'description': 'Kyle will mit seinem kleinen Bruder Ike Videospiele spielen. Als der nicht mehr mit ihm spielen will, hat Kyle Angst, dass er die Kids von heute nicht mehr versteht.',
|
||||||
},
|
},
|
||||||
'playlist_count': 3,
|
'playlist_count': 3,
|
||||||
|
'skip': 'Geo-restricted',
|
||||||
}, {
|
}, {
|
||||||
# non-ASCII characters in redirect URL
|
# non-ASCII characters in redirect URL
|
||||||
'url': 'http://www.southpark.de/alle-episoden/s18e09',
|
'url': 'http://www.southpark.de/alle-episoden/s18e09',
|
||||||
@ -85,6 +87,7 @@ class SouthParkDeIE(SouthParkIE):
|
|||||||
'description': 'Kyle will mit seinem kleinen Bruder Ike Videospiele spielen. Als der nicht mehr mit ihm spielen will, hat Kyle Angst, dass er die Kids von heute nicht mehr versteht.',
|
'description': 'Kyle will mit seinem kleinen Bruder Ike Videospiele spielen. Als der nicht mehr mit ihm spielen will, hat Kyle Angst, dass er die Kids von heute nicht mehr versteht.',
|
||||||
},
|
},
|
||||||
'playlist_count': 3,
|
'playlist_count': 3,
|
||||||
|
'skip': 'Geo-restricted',
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://www.southpark.de/collections/2476/superhero-showdown/1',
|
'url': 'http://www.southpark.de/collections/2476/superhero-showdown/1',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
@ -103,6 +106,7 @@ class SouthParkNlIE(SouthParkIE):
|
|||||||
'description': 'Stan is addicted to the new Terrance and Phillip mobile game.',
|
'description': 'Stan is addicted to the new Terrance and Phillip mobile game.',
|
||||||
},
|
},
|
||||||
'playlist_mincount': 3,
|
'playlist_mincount': 3,
|
||||||
|
'skip': 'Geo-restricted',
|
||||||
}]
|
}]
|
||||||
|
|
||||||
|
|
||||||
@ -118,6 +122,7 @@ class SouthParkDkIE(SouthParkIE):
|
|||||||
'description': 'Butters is convinced he\'s living in a virtual reality.',
|
'description': 'Butters is convinced he\'s living in a virtual reality.',
|
||||||
},
|
},
|
||||||
'playlist_mincount': 3,
|
'playlist_mincount': 3,
|
||||||
|
'skip': 'Geo-restricted',
|
||||||
}, {
|
}, {
|
||||||
'url': 'http://www.southparkstudios.dk/collections/2476/superhero-showdown/1',
|
'url': 'http://www.southparkstudios.dk/collections/2476/superhero-showdown/1',
|
||||||
'only_matching': True,
|
'only_matching': True,
|
||||||
|
@ -692,9 +692,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
'invidious': '|'.join(_INVIDIOUS_SITES),
|
'invidious': '|'.join(_INVIDIOUS_SITES),
|
||||||
}
|
}
|
||||||
_PLAYER_INFO_RE = (
|
_PLAYER_INFO_RE = (
|
||||||
r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})//(?:tv-)?player',
|
r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/(?:tv-)?player',
|
||||||
r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
|
r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias(?:_tce)?\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
|
||||||
r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
|
r'\b(?P<id>vfl[a-zA-Z0-9_-]{6,})\b.*?\.js$',
|
||||||
)
|
)
|
||||||
_SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
|
_SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
|
||||||
|
|
||||||
@ -1626,15 +1626,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
""" Return a string representation of a signature """
|
""" Return a string representation of a signature """
|
||||||
return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
|
return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
|
||||||
|
|
||||||
@classmethod
|
def _extract_player_info(self, player_url):
|
||||||
def _extract_player_info(cls, player_url):
|
try:
|
||||||
for player_re in cls._PLAYER_INFO_RE:
|
return self._search_regex(
|
||||||
id_m = re.search(player_re, player_url)
|
self._PLAYER_INFO_RE, player_url, 'player info', group='id')
|
||||||
if id_m:
|
except ExtractorError as e:
|
||||||
break
|
raise ExtractorError(
|
||||||
else:
|
'Cannot identify player %r' % (player_url,), cause=e)
|
||||||
raise ExtractorError('Cannot identify player %r' % player_url)
|
|
||||||
return id_m.group('id')
|
|
||||||
|
|
||||||
def _load_player(self, video_id, player_url, fatal=True, player_id=None):
|
def _load_player(self, video_id, player_url, fatal=True, player_id=None):
|
||||||
if not player_id:
|
if not player_id:
|
||||||
@ -1711,6 +1709,23 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
' return %s\n') % (signature_id_tuple, expr_code)
|
' return %s\n') % (signature_id_tuple, expr_code)
|
||||||
self.to_screen('Extracted signature function:\n' + code)
|
self.to_screen('Extracted signature function:\n' + code)
|
||||||
|
|
||||||
|
def _extract_sig_fn(self, jsi, funcname):
|
||||||
|
var_ay = self._search_regex(
|
||||||
|
r'''(?x)
|
||||||
|
(?:\*/|\{|\n|^)\s*(?:'[^']+'\s*;\s*)
|
||||||
|
(var\s*[\w$]+\s*=\s*(?:
|
||||||
|
('|")(?:\\\2|(?!\2).)+\2\s*\.\s*split\(\s*('|")\W+\3\s*\)|
|
||||||
|
\[\s*(?:('|")(?:\\\4|(?!\4).)*\4\s*(?:(?=\])|,\s*))+\]
|
||||||
|
))(?=\s*[,;])
|
||||||
|
''', jsi.code, 'useful values', default='')
|
||||||
|
|
||||||
|
sig_fn = jsi.extract_function_code(funcname)
|
||||||
|
|
||||||
|
if var_ay:
|
||||||
|
sig_fn = (sig_fn[0], ';\n'.join((var_ay, sig_fn[1])))
|
||||||
|
|
||||||
|
return sig_fn
|
||||||
|
|
||||||
def _parse_sig_js(self, jscode):
|
def _parse_sig_js(self, jscode):
|
||||||
# Examples where `sig` is funcname:
|
# Examples where `sig` is funcname:
|
||||||
# sig=function(a){a=a.split(""); ... ;return a.join("")};
|
# sig=function(a){a=a.split(""); ... ;return a.join("")};
|
||||||
@ -1736,8 +1751,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
jscode, 'Initial JS player signature function name', group='sig')
|
jscode, 'Initial JS player signature function name', group='sig')
|
||||||
|
|
||||||
jsi = JSInterpreter(jscode)
|
jsi = JSInterpreter(jscode)
|
||||||
initial_function = jsi.extract_function(funcname)
|
|
||||||
return lambda s: initial_function([s])
|
initial_function = self._extract_sig_fn(jsi, funcname)
|
||||||
|
|
||||||
|
func = jsi.extract_function_from_code(*initial_function)
|
||||||
|
|
||||||
|
return lambda s: func([s])
|
||||||
|
|
||||||
def _cached(self, func, *cache_id):
|
def _cached(self, func, *cache_id):
|
||||||
def inner(*args, **kwargs):
|
def inner(*args, **kwargs):
|
||||||
@ -1856,15 +1875,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
|
|
||||||
def _extract_n_function_code_jsi(self, video_id, jsi, player_id=None):
|
def _extract_n_function_code_jsi(self, video_id, jsi, player_id=None):
|
||||||
|
|
||||||
var_ay = self._search_regex(
|
|
||||||
r'(?:[;\s]|^)\s*(var\s*[\w$]+\s*=\s*"(?:\\"|[^"])+"\s*\.\s*split\("\W+"\))(?=\s*[,;])',
|
|
||||||
jsi.code, 'useful values', default='')
|
|
||||||
|
|
||||||
func_name = self._extract_n_function_name(jsi.code)
|
func_name = self._extract_n_function_name(jsi.code)
|
||||||
|
|
||||||
func_code = jsi.extract_function_code(func_name)
|
func_code = self._extract_sig_fn(jsi, func_name)
|
||||||
if var_ay:
|
|
||||||
func_code = (func_code[0], ';\n'.join((var_ay, func_code[1])))
|
|
||||||
|
|
||||||
if player_id:
|
if player_id:
|
||||||
self.cache.store('youtube-nsig', player_id, func_code)
|
self.cache.store('youtube-nsig', player_id, func_code)
|
||||||
@ -2136,7 +2149,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
video_details = merge_dicts(*traverse_obj(
|
video_details = merge_dicts(*traverse_obj(
|
||||||
(player_response, api_player_response),
|
(player_response, api_player_response),
|
||||||
(Ellipsis, 'videoDetails', T(dict))))
|
(Ellipsis, 'videoDetails', T(dict))))
|
||||||
player_response.update(api_player_response or {})
|
player_response.update(filter_dict(
|
||||||
|
api_player_response or {}, cndn=lambda k, _: k != 'captions'))
|
||||||
player_response['videoDetails'] = video_details
|
player_response['videoDetails'] = video_details
|
||||||
|
|
||||||
def is_agegated(playability):
|
def is_agegated(playability):
|
||||||
@ -2566,8 +2580,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
}
|
}
|
||||||
|
|
||||||
pctr = traverse_obj(
|
pctr = traverse_obj(
|
||||||
player_response,
|
(player_response, api_player_response),
|
||||||
('captions', 'playerCaptionsTracklistRenderer', T(dict)))
|
(Ellipsis, 'captions', 'playerCaptionsTracklistRenderer', T(dict)))
|
||||||
if pctr:
|
if pctr:
|
||||||
def process_language(container, base_url, lang_code, query):
|
def process_language(container, base_url, lang_code, query):
|
||||||
lang_subs = []
|
lang_subs = []
|
||||||
@ -2584,20 +2598,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
|||||||
def process_subtitles():
|
def process_subtitles():
|
||||||
subtitles = {}
|
subtitles = {}
|
||||||
for caption_track in traverse_obj(pctr, (
|
for caption_track in traverse_obj(pctr, (
|
||||||
'captionTracks', lambda _, v: v.get('baseUrl'))):
|
Ellipsis, 'captionTracks', lambda _, v: (
|
||||||
|
v.get('baseUrl') and v.get('languageCode')))):
|
||||||
base_url = self._yt_urljoin(caption_track['baseUrl'])
|
base_url = self._yt_urljoin(caption_track['baseUrl'])
|
||||||
if not base_url:
|
if not base_url:
|
||||||
continue
|
continue
|
||||||
|
lang_code = caption_track['languageCode']
|
||||||
if caption_track.get('kind') != 'asr':
|
if caption_track.get('kind') != 'asr':
|
||||||
lang_code = caption_track.get('languageCode')
|
|
||||||
if not lang_code:
|
|
||||||
continue
|
|
||||||
process_language(
|
process_language(
|
||||||
subtitles, base_url, lang_code, {})
|
subtitles, base_url, lang_code, {})
|
||||||
continue
|
continue
|
||||||
automatic_captions = {}
|
automatic_captions = {}
|
||||||
|
process_language(
|
||||||
|
automatic_captions, base_url, lang_code, {})
|
||||||
for translation_language in traverse_obj(pctr, (
|
for translation_language in traverse_obj(pctr, (
|
||||||
'translationLanguages', lambda _, v: v.get('languageCode'))):
|
Ellipsis, 'translationLanguages', lambda _, v: v.get('languageCode'))):
|
||||||
translation_language_code = translation_language['languageCode']
|
translation_language_code = translation_language['languageCode']
|
||||||
process_language(
|
process_language(
|
||||||
automatic_captions, base_url, translation_language_code,
|
automatic_captions, base_url, translation_language_code,
|
||||||
|
@ -678,7 +678,7 @@ class JSInterpreter(object):
|
|||||||
return len(obj)
|
return len(obj)
|
||||||
try:
|
try:
|
||||||
return obj[int(idx)] if isinstance(obj, list) else obj[compat_str(idx)]
|
return obj[int(idx)] if isinstance(obj, list) else obj[compat_str(idx)]
|
||||||
except (TypeError, KeyError, IndexError) as e:
|
except (TypeError, KeyError, IndexError, ValueError) as e:
|
||||||
# allow_undefined is None gives correct behaviour
|
# allow_undefined is None gives correct behaviour
|
||||||
if allow_undefined or (
|
if allow_undefined or (
|
||||||
allow_undefined is None and not isinstance(e, TypeError)):
|
allow_undefined is None and not isinstance(e, TypeError)):
|
||||||
@ -1038,6 +1038,10 @@ class JSInterpreter(object):
|
|||||||
left_val = self._index(left_val, idx)
|
left_val = self._index(left_val, idx)
|
||||||
if isinstance(idx, float):
|
if isinstance(idx, float):
|
||||||
idx = int(idx)
|
idx = int(idx)
|
||||||
|
if isinstance(left_val, list) and len(left_val) <= int_or_none(idx, default=-1):
|
||||||
|
# JS Array is a sparsely assignable list
|
||||||
|
# TODO: handle extreme sparsity without memory bloat, eg using auxiliary dict
|
||||||
|
left_val.extend((idx - len(left_val) + 1) * [JS_Undefined])
|
||||||
left_val[idx] = self._operator(
|
left_val[idx] = self._operator(
|
||||||
m.group('op'), self._index(left_val, idx) if m.group('op') else None,
|
m.group('op'), self._index(left_val, idx) if m.group('op') else None,
|
||||||
m.group('expr'), expr, local_vars, allow_recursion)
|
m.group('expr'), expr, local_vars, allow_recursion)
|
||||||
@ -1204,9 +1208,10 @@ class JSInterpreter(object):
|
|||||||
elif member == 'join':
|
elif member == 'join':
|
||||||
assertion(isinstance(obj, list), 'must be applied on a list')
|
assertion(isinstance(obj, list), 'must be applied on a list')
|
||||||
assertion(len(argvals) <= 1, 'takes at most one argument')
|
assertion(len(argvals) <= 1, 'takes at most one argument')
|
||||||
return (',' if len(argvals) == 0 else argvals[0]).join(
|
return (',' if len(argvals) == 0 or argvals[0] in (None, JS_Undefined)
|
||||||
('' if x in (None, JS_Undefined) else _js_toString(x))
|
else argvals[0]).join(
|
||||||
for x in obj)
|
('' if x in (None, JS_Undefined) else _js_toString(x))
|
||||||
|
for x in obj)
|
||||||
elif member == 'reverse':
|
elif member == 'reverse':
|
||||||
assertion(not argvals, 'does not take any arguments')
|
assertion(not argvals, 'does not take any arguments')
|
||||||
obj.reverse()
|
obj.reverse()
|
||||||
@ -1364,19 +1369,21 @@ class JSInterpreter(object):
|
|||||||
code, _ = self._separate_at_paren(func_m.group('code')) # refine the match
|
code, _ = self._separate_at_paren(func_m.group('code')) # refine the match
|
||||||
return self.build_arglist(func_m.group('args')), code
|
return self.build_arglist(func_m.group('args')), code
|
||||||
|
|
||||||
def extract_function(self, funcname):
|
def extract_function(self, funcname, *global_stack):
|
||||||
return function_with_repr(
|
return function_with_repr(
|
||||||
self.extract_function_from_code(*self.extract_function_code(funcname)),
|
self.extract_function_from_code(*itertools.chain(
|
||||||
|
self.extract_function_code(funcname), global_stack)),
|
||||||
'F<%s>' % (funcname,))
|
'F<%s>' % (funcname,))
|
||||||
|
|
||||||
def extract_function_from_code(self, argnames, code, *global_stack):
|
def extract_function_from_code(self, argnames, code, *global_stack):
|
||||||
local_vars = {}
|
local_vars = {}
|
||||||
|
|
||||||
|
start = None
|
||||||
while True:
|
while True:
|
||||||
mobj = re.search(r'function\((?P<args>[^)]*)\)\s*{', code)
|
mobj = re.search(r'function\((?P<args>[^)]*)\)\s*{', code[start:])
|
||||||
if mobj is None:
|
if mobj is None:
|
||||||
break
|
break
|
||||||
start, body_start = mobj.span()
|
start, body_start = ((start or 0) + x for x in mobj.span())
|
||||||
body, remaining = self._separate_at_paren(code[body_start - 1:])
|
body, remaining = self._separate_at_paren(code[body_start - 1:])
|
||||||
name = self._named_object(local_vars, self.extract_function_from_code(
|
name = self._named_object(local_vars, self.extract_function_from_code(
|
||||||
[x.strip() for x in mobj.group('args').split(',')],
|
[x.strip() for x in mobj.group('args').split(',')],
|
||||||
|
@ -2079,7 +2079,7 @@ def timeconvert(timestr):
|
|||||||
timetuple = email.utils.parsedate_tz(timestr)
|
timetuple = email.utils.parsedate_tz(timestr)
|
||||||
if timetuple is not None:
|
if timetuple is not None:
|
||||||
timestamp = email.utils.mktime_tz(timetuple)
|
timestamp = email.utils.mktime_tz(timetuple)
|
||||||
return timestamp
|
return int(timestamp) if timestamp is not None else timestamp
|
||||||
|
|
||||||
|
|
||||||
def sanitize_filename(s, restricted=False, is_id=False):
|
def sanitize_filename(s, restricted=False, is_id=False):
|
||||||
|
Loading…
x
Reference in New Issue
Block a user