-
Notifications
You must be signed in to change notification settings - Fork 10.2k
/
Copy pathyoutube.py
3678 lines (3436 loc) · 159 KB
/
youtube.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# coding: utf-8
from __future__ import unicode_literals
import itertools
import json
import os.path
import random
import re
import traceback
from .common import InfoExtractor, SearchInfoExtractor
from ..compat import (
compat_chr,
compat_HTTPError,
compat_map as map,
compat_str,
compat_urllib_parse,
compat_urllib_parse_parse_qs as compat_parse_qs,
compat_urllib_parse_unquote_plus,
compat_urllib_parse_urlparse,
compat_zip as zip,
)
from ..jsinterp import JSInterpreter
from ..utils import (
ExtractorError,
clean_html,
dict_get,
error_to_compat_str,
float_or_none,
extract_attributes,
get_element_by_attribute,
int_or_none,
js_to_json,
LazyList,
merge_dicts,
mimetype2ext,
parse_codecs,
parse_duration,
parse_qs,
qualities,
remove_start,
smuggle_url,
str_or_none,
str_to_int,
traverse_obj,
try_get,
unescapeHTML,
unified_strdate,
unsmuggle_url,
update_url,
update_url_query,
url_or_none,
urlencode_postdata,
urljoin,
)
class YoutubeBaseInfoExtractor(InfoExtractor):
"""Provide base functions for Youtube extractors"""
_LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
_TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
_LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup'
_CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge'
_TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
_NETRC_MACHINE = 'youtube'
# If True it will raise an error if no login info is provided
_LOGIN_REQUIRED = False
_PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM)'
def _login(self):
"""
Attempt to log in to YouTube.
True is returned if successful or skipped.
False is returned if login failed.
If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
"""
username, password = self._get_login_info()
# No authentication to be performed
if username is None:
if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None:
raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
return True
login_page = self._download_webpage(
self._LOGIN_URL, None,
note='Downloading login page',
errnote='unable to fetch login page', fatal=False)
if login_page is False:
return
login_form = self._hidden_inputs(login_page)
def req(url, f_req, note, errnote):
data = login_form.copy()
data.update({
'pstMsg': 1,
'checkConnection': 'youtube',
'checkedDomains': 'youtube',
'hl': 'en',
'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
'f.req': json.dumps(f_req),
'flowName': 'GlifWebSignIn',
'flowEntry': 'ServiceLogin',
# TODO: reverse actual botguard identifier generation algo
'bgRequest': '["identifier",""]',
})
return self._download_json(
url, None, note=note, errnote=errnote,
transform_source=lambda s: re.sub(r'^[^[]*', '', s),
fatal=False,
data=urlencode_postdata(data), headers={
'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
'Google-Accounts-XSRF': 1,
})
def warn(message):
self._downloader.report_warning(message)
lookup_req = [
username,
None, [], None, 'US', None, None, 2, False, True,
[
None, None,
[2, 1, None, 1,
'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn',
None, [], 4],
1, [None, None, []], None, None, None, True
],
username,
]
lookup_results = req(
self._LOOKUP_URL, lookup_req,
'Looking up account info', 'Unable to look up account info')
if lookup_results is False:
return False
user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
if not user_hash:
warn('Unable to extract user hash')
return False
challenge_req = [
user_hash,
None, 1, None, [1, None, None, None, [password, None, True]],
[
None, None, [2, 1, None, 1, 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn', None, [], 4],
1, [None, None, []], None, None, None, True
]]
challenge_results = req(
self._CHALLENGE_URL, challenge_req,
'Logging in', 'Unable to log in')
if challenge_results is False:
return
login_res = try_get(challenge_results, lambda x: x[0][5], list)
if login_res:
login_msg = try_get(login_res, lambda x: x[5], compat_str)
warn(
'Unable to login: %s' % 'Invalid password'
if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
return False
res = try_get(challenge_results, lambda x: x[0][-1], list)
if not res:
warn('Unable to extract result entry')
return False
login_challenge = try_get(res, lambda x: x[0][0], list)
if login_challenge:
challenge_str = try_get(login_challenge, lambda x: x[2], compat_str)
if challenge_str == 'TWO_STEP_VERIFICATION':
# SEND_SUCCESS - TFA code has been successfully sent to phone
# QUOTA_EXCEEDED - reached the limit of TFA codes
status = try_get(login_challenge, lambda x: x[5], compat_str)
if status == 'QUOTA_EXCEEDED':
warn('Exceeded the limit of TFA codes, try later')
return False
tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
if not tl:
warn('Unable to extract TL')
return False
tfa_code = self._get_tfa_info('2-step verification code')
if not tfa_code:
warn(
'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
'(Note that only TOTP (Google Authenticator App) codes work at this time.)')
return False
tfa_code = remove_start(tfa_code, 'G-')
tfa_req = [
user_hash, None, 2, None,
[
9, None, None, None, None, None, None, None,
[None, tfa_code, True, 2]
]]
tfa_results = req(
self._TFA_URL.format(tl), tfa_req,
'Submitting TFA code', 'Unable to submit TFA code')
if tfa_results is False:
return False
tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
if tfa_res:
tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
warn(
'Unable to finish TFA: %s' % 'Invalid TFA code'
if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
return False
check_cookie_url = try_get(
tfa_results, lambda x: x[0][-1][2], compat_str)
else:
CHALLENGES = {
'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
}
challenge = CHALLENGES.get(
challenge_str,
'%s returned error %s.' % (self.IE_NAME, challenge_str))
warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge)
return False
else:
check_cookie_url = try_get(res, lambda x: x[2], compat_str)
if not check_cookie_url:
warn('Unable to extract CheckCookie URL')
return False
check_cookie_results = self._download_webpage(
check_cookie_url, None, 'Checking cookie', fatal=False)
if check_cookie_results is False:
return False
if 'https://myaccount.google.com/' not in check_cookie_results:
warn('Unable to log in')
return False
return True
def _initialize_consent(self):
cookies = self._get_cookies('https://www.youtube.com/')
if cookies.get('__Secure-3PSID'):
return
consent_id = None
consent = cookies.get('CONSENT')
if consent:
if 'YES' in consent.value:
return
consent_id = self._search_regex(
r'PENDING\+(\d+)', consent.value, 'consent', default=None)
if not consent_id:
consent_id = random.randint(100, 999)
self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
def _real_initialize(self):
self._initialize_consent()
if self._downloader is None:
return
if not self._login():
return
_DEFAULT_API_DATA = {
'context': {
'client': {
'clientName': 'WEB',
'clientVersion': '2.20201021.03.00',
}
},
}
_YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
_YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
_YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
def _call_api(self, ep, query, video_id, fatal=True, headers=None):
data = self._DEFAULT_API_DATA.copy()
data.update(query)
real_headers = {'content-type': 'application/json'}
if headers:
real_headers.update(headers)
return self._download_json(
'https://www.youtube.com/youtubei/v1/%s' % ep, video_id=video_id,
note='Downloading API JSON', errnote='Unable to download API page',
data=json.dumps(data).encode('utf8'), fatal=fatal,
headers=real_headers,
query={'key': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'})
def _extract_yt_initial_data(self, video_id, webpage):
return self._parse_json(
self._search_regex(
(r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
self._YT_INITIAL_DATA_RE), webpage, 'yt initial data'),
video_id)
def _extract_ytcfg(self, video_id, webpage):
return self._parse_json(
self._search_regex(
r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
default='{}'), video_id, fatal=False) or {}
def _extract_video(self, renderer):
video_id = renderer['videoId']
title = try_get(
renderer,
(lambda x: x['title']['runs'][0]['text'],
lambda x: x['title']['simpleText'],
lambda x: x['headline']['simpleText']), compat_str)
description = try_get(
renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'],
compat_str)
duration = parse_duration(try_get(
renderer, lambda x: x['lengthText']['simpleText'], compat_str))
view_count_text = try_get(
renderer, lambda x: x['viewCountText']['simpleText'], compat_str) or ''
view_count = str_to_int(self._search_regex(
r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
'view count', default=None))
uploader = try_get(
renderer,
(lambda x: x['ownerText']['runs'][0]['text'],
lambda x: x['shortBylineText']['runs'][0]['text']), compat_str)
return {
'_type': 'url',
'ie_key': YoutubeIE.ie_key(),
'id': video_id,
'url': video_id,
'title': title,
'description': description,
'duration': duration,
'view_count': view_count,
'uploader': uploader,
}
def _search_results(self, query, params):
data = {
'context': {
'client': {
'clientName': 'WEB',
'clientVersion': '2.20201021.03.00',
}
},
'query': query,
}
if params:
data['params'] = params
for page_num in itertools.count(1):
search = self._download_json(
'https://www.youtube.com/youtubei/v1/search?key=AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
video_id='query "%s"' % query,
note='Downloading page %s' % page_num,
errnote='Unable to download API page', fatal=False,
data=json.dumps(data).encode('utf8'),
headers={'content-type': 'application/json'})
if not search:
break
slr_contents = try_get(
search,
(lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
list)
if not slr_contents:
break
for slr_content in slr_contents:
isr_contents = try_get(
slr_content,
lambda x: x['itemSectionRenderer']['contents'],
list)
if not isr_contents:
continue
for content in isr_contents:
if not isinstance(content, dict):
continue
video = content.get('videoRenderer')
if not isinstance(video, dict):
continue
video_id = video.get('videoId')
if not video_id:
continue
yield self._extract_video(video)
token = try_get(
slr_contents,
lambda x: x[-1]['continuationItemRenderer']['continuationEndpoint']['continuationCommand']['token'],
compat_str)
if not token:
break
data['continuation'] = token
@staticmethod
def _owner_endpoints_path():
return [
Ellipsis,
lambda k, _: k.endswith('SecondaryInfoRenderer'),
('owner', 'videoOwner'), 'videoOwnerRenderer', 'title',
'runs', Ellipsis]
def _extract_channel_id(self, webpage, videodetails={}, metadata={}, renderers=[]):
channel_id = None
if any((videodetails, metadata, renderers)):
channel_id = (
traverse_obj(videodetails, 'channelId')
or traverse_obj(metadata, 'externalChannelId', 'externalId')
or traverse_obj(renderers,
self._owner_endpoints_path() + [
'navigationEndpoint', 'browseEndpoint', 'browseId'],
get_all=False)
)
return channel_id or self._html_search_meta(
'channelId', webpage, 'channel id', default=None)
def _extract_author_var(self, webpage, var_name,
videodetails={}, metadata={}, renderers=[]):
result = None
paths = {
# (HTML, videodetails, metadata, renderers)
'name': ('content', 'author', (('ownerChannelName', None), 'title'), ['text']),
'url': ('href', 'ownerProfileUrl', 'vanityChannelUrl',
['navigationEndpoint', 'browseEndpoint', 'canonicalBaseUrl'])
}
if any((videodetails, metadata, renderers)):
result = (
traverse_obj(videodetails, paths[var_name][1], get_all=False)
or traverse_obj(metadata, paths[var_name][2], get_all=False)
or traverse_obj(renderers,
self._owner_endpoints_path() + paths[var_name][3],
get_all=False)
)
return result or traverse_obj(
extract_attributes(self._search_regex(
r'''(?s)(<link\b[^>]+\bitemprop\s*=\s*("|')%s\2[^>]*>)'''
% re.escape(var_name),
get_element_by_attribute('itemprop', 'author', webpage) or '',
'author link', default='')),
paths[var_name][0])
@staticmethod
def _yt_urljoin(url_or_path):
return urljoin('https://www.youtube.com', url_or_path)
def _extract_uploader_id(self, uploader_url):
return self._search_regex(
r'/(?:(?:channel|user)/|(?=@))([^/?&#]+)', uploader_url or '',
'uploader id', default=None)
class YoutubeIE(YoutubeBaseInfoExtractor):
IE_DESC = 'YouTube.com'
_INVIDIOUS_SITES = (
# invidious-redirect websites
r'(?:www\.)?redirect\.invidious\.io',
r'(?:(?:www|dev)\.)?invidio\.us',
# Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
r'(?:(?:www|no)\.)?invidiou\.sh',
r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
r'(?:www\.)?invidious\.kabi\.tk',
r'(?:www\.)?invidious\.13ad\.de',
r'(?:www\.)?invidious\.mastodon\.host',
r'(?:www\.)?invidious\.zapashcanon\.fr',
r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
r'(?:www\.)?invidious\.tinfoil-hat\.net',
r'(?:www\.)?invidious\.himiko\.cloud',
r'(?:www\.)?invidious\.reallyancient\.tech',
r'(?:www\.)?invidious\.tube',
r'(?:www\.)?invidiou\.site',
r'(?:www\.)?invidious\.site',
r'(?:www\.)?invidious\.xyz',
r'(?:www\.)?invidious\.nixnet\.xyz',
r'(?:www\.)?invidious\.048596\.xyz',
r'(?:www\.)?invidious\.drycat\.fr',
r'(?:www\.)?inv\.skyn3t\.in',
r'(?:www\.)?tube\.poal\.co',
r'(?:www\.)?tube\.connect\.cafe',
r'(?:www\.)?vid\.wxzm\.sx',
r'(?:www\.)?vid\.mint\.lgbt',
r'(?:www\.)?vid\.puffyan\.us',
r'(?:www\.)?yewtu\.be',
r'(?:www\.)?yt\.elukerio\.org',
r'(?:www\.)?yt\.lelux\.fi',
r'(?:www\.)?invidious\.ggc-project\.de',
r'(?:www\.)?yt\.maisputain\.ovh',
r'(?:www\.)?ytprivate\.com',
r'(?:www\.)?invidious\.13ad\.de',
r'(?:www\.)?invidious\.toot\.koeln',
r'(?:www\.)?invidious\.fdn\.fr',
r'(?:www\.)?watch\.nettohikari\.com',
r'(?:www\.)?invidious\.namazso\.eu',
r'(?:www\.)?invidious\.silkky\.cloud',
r'(?:www\.)?invidious\.exonip\.de',
r'(?:www\.)?invidious\.riverside\.rocks',
r'(?:www\.)?invidious\.blamefran\.net',
r'(?:www\.)?invidious\.moomoo\.de',
r'(?:www\.)?ytb\.trom\.tf',
r'(?:www\.)?yt\.cyberhost\.uk',
r'(?:www\.)?kgg2m7yk5aybusll\.onion',
r'(?:www\.)?qklhadlycap4cnod\.onion',
r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
)
_VALID_URL = r"""(?x)^
(
(?:https?://|//) # http(s):// or protocol-independent URL
(?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
(?:www\.)?deturl\.com/www\.youtube\.com|
(?:www\.)?pwnyoutube\.com|
(?:www\.)?hooktube\.com|
(?:www\.)?yourepeat\.com|
tube\.majestyc\.net|
%(invidious)s|
youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
(?:.*?\#/)? # handle anchor (#/) redirect urls
(?: # the various things that can precede the ID:
(?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
|shorts/
|(?: # or the v= param in all its forms
(?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
(?:\?|\#!?) # the params delimiter ? or # or #!
(?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
v=
)
))
|(?:
youtu\.be| # just youtu.be/xxxx
vid\.plus| # or vid.plus/xxxx
zwearz\.com/watch| # or zwearz.com/watch/xxxx
%(invidious)s
)/
|(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
)
)? # all until now is optional -> you can pass the naked ID
(?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
(?(1).+)? # if we found the ID, everything can follow
$""" % {
'invidious': '|'.join(_INVIDIOUS_SITES),
}
_PLAYER_INFO_RE = (
r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
)
_SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
_GEO_BYPASS = False
IE_NAME = 'youtube'
_TESTS = [
{
'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
'info_dict': {
'id': 'BaW_jenozKc',
'ext': 'mp4',
'title': 'youtube-dl test video "\'/\\ä↭𝕐',
'uploader': 'Philipp Hagemeister',
'uploader_id': '@PhilippHagemeister',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/@PhilippHagemeister',
'channel': 'Philipp Hagemeister',
'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
'upload_date': '20121002',
'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
'categories': ['Science & Technology'],
'tags': ['youtube-dl'],
'duration': 10,
'view_count': int,
'like_count': int,
'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
'start_time': 1,
'end_time': 9,
},
},
{
'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
'note': 'Embed-only video (#1746)',
'info_dict': {
'id': 'yZIXLfi8CZQ',
'ext': 'mp4',
'upload_date': '20120608',
'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
'uploader': 'SET India',
'uploader_id': 'setindia',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
'age_limit': 18,
},
'skip': 'Private video',
},
{
'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
'note': 'Use the first video ID in the URL',
'info_dict': {
'id': 'BaW_jenozKc',
'ext': 'mp4',
'title': 'youtube-dl test video "\'/\\ä↭𝕐',
'uploader': 'Philipp Hagemeister',
'uploader_id': '@PhilippHagemeister',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/@PhilippHagemeister',
'upload_date': '20121002',
'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
'categories': ['Science & Technology'],
'tags': ['youtube-dl'],
'duration': 10,
'view_count': int,
'like_count': int,
},
'params': {
'skip_download': True,
},
},
{
'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
'note': '256k DASH audio (format 141) via DASH manifest',
'info_dict': {
'id': 'a9LDPn-MO4I',
'ext': 'm4a',
'upload_date': '20121002',
'uploader_id': '8KVIDEO',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
'description': '',
'uploader': '8KVIDEO',
'title': 'UHDTV TEST 8K VIDEO.mp4'
},
'params': {
'youtube_include_dash_manifest': True,
'format': '141',
},
'skip': 'format 141 not served any more',
},
# DASH manifest with encrypted signature
{
'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
'info_dict': {
'id': 'IB3lcPjvWLA',
'ext': 'm4a',
'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
'duration': 244,
'uploader': 'AfrojackVEVO',
'uploader_id': '@AfrojackVEVO',
'upload_date': '20131011',
'abr': 129.495,
},
'params': {
'youtube_include_dash_manifest': True,
'format': '141/bestaudio[ext=m4a]',
},
},
# Controversy video
{
'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
'info_dict': {
'id': 'T4XJQO3qol8',
'ext': 'mp4',
'duration': 219,
'upload_date': '20100909',
'uploader': 'Amazing Atheist',
'uploader_id': '@theamazingatheist',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/@theamazingatheist',
'title': 'Burning Everyone\'s Koran',
'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms \r\n\r\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html',
}
},
# Age-gated videos
{
'note': 'Age-gated video (No vevo, embed allowed)',
'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
'info_dict': {
'id': 'HtVdAasjOgU',
'ext': 'mp4',
'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
'duration': 142,
'uploader': 'The Witcher',
'uploader_id': '@thewitcher',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/@thewitcher',
'upload_date': '20140605',
'thumbnail': 'https://i.ytimg.com/vi/HtVdAasjOgU/maxresdefault.jpg',
'age_limit': 18,
'categories': ['Gaming'],
'tags': 'count:17',
'channel': 'The Witcher',
'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
'view_count': int,
'like_count': int,
},
},
{
'note': 'Age-gated video with embed allowed in public site',
'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
'info_dict': {
'id': 'HsUATh_Nc2U',
'ext': 'mp4',
'title': 'Godzilla 2 (Official Video)',
'description': 'md5:bf77e03fcae5529475e500129b05668a',
'duration': 177,
'uploader': 'FlyingKitty',
'uploader_id': '@FlyingKitty900',
'upload_date': '20200408',
'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
'age_limit': 18,
'categories': ['Entertainment'],
'tags': ['Flyingkitty', 'godzilla 2'],
'channel': 'FlyingKitty',
'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
'view_count': int,
'like_count': int,
},
},
{
'note': 'Age-gated video embeddable only with clientScreen=EMBED',
'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
'info_dict': {
'id': 'Tq92D6wQ1mg',
'ext': 'mp4',
'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
'description': 'md5:17eccca93a786d51bc67646756894066',
'duration': 106,
'uploader': 'Projekt Melody',
'uploader_id': '@ProjektMelody',
'upload_date': '20191227',
'age_limit': 18,
'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
'categories': ['Entertainment'],
'channel': 'Projekt Melody',
'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
'view_count': int,
'like_count': int,
},
},
{
'note': 'Non-Age-gated non-embeddable video',
'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
'info_dict': {
'id': 'MeJVWBSsPAY',
'ext': 'mp4',
'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
'description': 'Fan Video. Music & Lyrics by OOMPH!.',
'duration': 210,
'upload_date': '20130730',
'uploader': 'Herr Lurik',
'uploader_id': '@HerrLurik',
'uploader_url': 'http://www.youtube.com/@HerrLurik',
'age_limit': 0,
'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/hqdefault.jpg',
'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
'categories': ['Music'],
'channel': 'Herr Lurik',
'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
'artist': 'OOMPH!',
'view_count': int,
'like_count': int,
},
},
{
'note': 'Non-bypassable age-gated video',
'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
'only_matching': True,
},
{
'note': 'Age-gated video only available with authentication (not via embed workaround)',
'url': 'XgnwCQzjau8',
'only_matching': True,
'skip': '''This video has been removed for violating YouTube's Community Guidelines''',
},
# video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
# YouTube Red ad is not captured for creator
{
'url': '__2ABJjxzNo',
'info_dict': {
'id': '__2ABJjxzNo',
'ext': 'mp4',
'duration': 266,
'upload_date': '20100430',
'uploader_id': '@deadmau5',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/@deadmau5',
'creator': 'deadmau5',
'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
'uploader': 'deadmau5',
'title': 'Deadmau5 - Some Chords (HD)',
'alt_title': 'Some Chords',
},
'expected_warnings': [
'DASH manifest missing',
]
},
# Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
{
'url': 'lqQg6PlCWgI',
'info_dict': {
'id': 'lqQg6PlCWgI',
'ext': 'mp4',
'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
'description': r're:(?s)(?:.+\s)?HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games\s*',
'duration': 6085,
'upload_date': '20150827',
'uploader_id': '@Olympics',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/@Olympics',
'uploader': r're:Olympics?',
'age_limit': 0,
'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
'categories': ['Sports'],
'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
'channel': 'Olympics',
'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
'view_count': int,
'like_count': int,
},
},
# Non-square pixels
{
'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
'info_dict': {
'id': '_b-2C3KPAM0',
'ext': 'mp4',
'stretched_ratio': 16 / 9.,
'duration': 85,
'upload_date': '20110310',
'uploader_id': '@AllenMeow',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/@AllenMeow',
'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
'uploader': '孫ᄋᄅ',
'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
},
},
# url_encoded_fmt_stream_map is empty string
{
'url': 'qEJwOuvDf7I',
'info_dict': {
'id': 'qEJwOuvDf7I',
'ext': 'webm',
'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
'description': '',
'upload_date': '20150404',
'uploader_id': 'spbelect',
'uploader': 'Наблюдатели Петербурга',
},
'params': {
'skip_download': 'requires avconv',
},
'skip': 'This live event has ended.',
},
# Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
{
'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
'info_dict': {
'id': 'FIl7x6_3R5Y',
'ext': 'webm',
'title': 'md5:7b81415841e02ecd4313668cde88737a',
'description': 'md5:116377fd2963b81ec4ce64b542173306',
'duration': 220,
'upload_date': '20150625',
'uploader_id': 'dorappi2000',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
'uploader': 'dorappi2000',
'formats': 'mincount:31',
},
'skip': 'not actual any more',
},
# DASH manifest with segment_list
{
'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
'md5': '8ce563a1d667b599d21064e982ab9e31',
'info_dict': {
'id': 'CsmdDsKjzN8',
'ext': 'mp4',
'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
'uploader': 'Airtek',
'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
},
'params': {
'youtube_include_dash_manifest': True,
'format': '135', # bestvideo
},
'skip': 'This live event has ended.',
},
{
# Multifeed videos (multiple cameras), URL is for Main Camera
'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
'info_dict': {
'id': 'jvGDaLqkpTg',
'title': 'Tom Clancy Free Weekend Rainbow Whatever',
'description': 'md5:e03b909557865076822aa169218d6a5d',
},
'playlist': [{
'info_dict': {
'id': 'jvGDaLqkpTg',
'ext': 'mp4',
'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
'description': 'md5:e03b909557865076822aa169218d6a5d',
'duration': 10643,
'upload_date': '20161111',
'uploader': 'Team PGP',
'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
},
}, {
'info_dict': {
'id': '3AKt1R1aDnw',
'ext': 'mp4',
'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
'description': 'md5:e03b909557865076822aa169218d6a5d',
'duration': 10991,
'upload_date': '20161111',
'uploader': 'Team PGP',
'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
},
}, {
'info_dict': {
'id': 'RtAMM00gpVc',
'ext': 'mp4',
'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
'description': 'md5:e03b909557865076822aa169218d6a5d',
'duration': 10995,
'upload_date': '20161111',
'uploader': 'Team PGP',
'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
},
}, {
'info_dict': {
'id': '6N2fdlP3C5U',
'ext': 'mp4',
'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
'description': 'md5:e03b909557865076822aa169218d6a5d',
'duration': 10990,
'upload_date': '20161111',
'uploader': 'Team PGP',
'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
},
}],
'params': {
'skip_download': True,
},
'skip': 'Not multifeed any more',
},
{
# Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
'info_dict': {
'id': 'gVfLd0zydlo',
'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
},
'playlist_count': 2,
'skip': 'Not multifeed any more',
},
{
'url': 'https://vid.plus/FlRa-iH7PGw',
'only_matching': True,
},
{
'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
'only_matching': True,
},
{
# Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
# Also tests cut-off URL expansion in video description (see
# https://github.com/ytdl-org/youtube-dl/issues/1892,
# https://github.com/ytdl-org/youtube-dl/issues/8164)
'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
'info_dict': {
'id': 'lsguqyKfVQg',
'ext': 'mp4',
'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
'alt_title': 'Dark Walk',
'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
'duration': 133,
'upload_date': '20151119',