]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[extractor] Better error message for DRM (#729)
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
c5e8d7af 1# coding: utf-8
c5e8d7af 2
78caa52a
PH
3from __future__ import unicode_literals
4
2d6659b9 5import base64
d92f5d5a 6import calendar
109dd3b2 7import copy
fe93e2c4 8import datetime
a5c56234 9import hashlib
0ca96d48 10import itertools
c5e8d7af 11import json
c4417ddb 12import os.path
d77ab8e2 13import random
c5e8d7af 14import re
8a784c74 15import time
e0df6211 16import traceback
c5e8d7af 17
b05654f0 18from .common import InfoExtractor, SearchInfoExtractor
4bb4a188 19from ..compat import (
edf3e38e 20 compat_chr,
29f7c58a 21 compat_HTTPError,
c5e8d7af 22 compat_parse_qs,
545cc85d 23 compat_str,
7fd002c0 24 compat_urllib_parse_unquote_plus,
15707c7e 25 compat_urllib_parse_urlencode,
7c80519c 26 compat_urllib_parse_urlparse,
7c61bd36 27 compat_urlparse,
4bb4a188 28)
545cc85d 29from ..jsinterp import JSInterpreter
4bb4a188 30from ..utils import (
2d6659b9 31 bytes_to_intlist,
c5e8d7af 32 clean_html,
d92f5d5a 33 datetime_from_str,
11f9be09 34 dict_get,
358de58c 35 error_to_compat_str,
c5e8d7af 36 ExtractorError,
2d30521a 37 float_or_none,
11f9be09 38 format_field,
dd27fd17 39 int_or_none,
2d6659b9 40 intlist_to_bytes,
641ad5d8 41 is_html,
94278f72 42 mimetype2ext,
9c0d7f49 43 network_exceptions,
11f9be09 44 orderedSet,
6310acf5 45 parse_codecs,
49bd8c66 46 parse_count,
7c80519c 47 parse_duration,
7ea65411 48 parse_iso8601,
4dfbf869 49 parse_qs,
dca3ff4a 50 qualities,
3995d37d 51 remove_start,
cf7e015f 52 smuggle_url,
dbdaaa23 53 str_or_none,
c93d53f5 54 str_to_int,
7c365c21 55 traverse_obj,
556dbe7f 56 try_get,
c5e8d7af
PH
57 unescapeHTML,
58 unified_strdate,
cf7e015f 59 unsmuggle_url,
8bdd16b4 60 update_url_query,
21c340b8 61 url_or_none,
6e6bc8da 62 urlencode_postdata,
fe93e2c4 63 urljoin,
7c365c21 64 variadic,
c5e8d7af
PH
65)
66
5f6a1245 67
000c15a4 68# any clients starting with _ cannot be explicity requested by the user
69INNERTUBE_CLIENTS = {
70 'web': {
71 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
72 'INNERTUBE_CONTEXT': {
73 'client': {
74 'clientName': 'WEB',
75 'clientVersion': '2.20210622.10.00',
76 }
77 },
78 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
79 },
80 'web_embedded': {
81 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
82 'INNERTUBE_CONTEXT': {
83 'client': {
84 'clientName': 'WEB_EMBEDDED_PLAYER',
85 'clientVersion': '1.20210620.0.1',
86 },
87 },
88 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
89 },
90 'web_music': {
91 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
92 'INNERTUBE_HOST': 'music.youtube.com',
93 'INNERTUBE_CONTEXT': {
94 'client': {
95 'clientName': 'WEB_REMIX',
96 'clientVersion': '1.20210621.00.00',
97 }
98 },
99 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
100 },
e7e94f2a
D
101 'web_creator': {
102 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
103 'INNERTUBE_CONTEXT': {
104 'client': {
105 'clientName': 'WEB_CREATOR',
106 'clientVersion': '1.20210621.00.00',
107 }
108 },
109 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
110 },
000c15a4 111 'android': {
112 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
113 'INNERTUBE_CONTEXT': {
114 'client': {
115 'clientName': 'ANDROID',
116 'clientVersion': '16.20',
117 }
118 },
119 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
120 },
121 'android_embedded': {
122 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
123 'INNERTUBE_CONTEXT': {
124 'client': {
125 'clientName': 'ANDROID_EMBEDDED_PLAYER',
126 'clientVersion': '16.20',
127 },
128 },
129 'INNERTUBE_CONTEXT_CLIENT_NAME': 55
130 },
131 'android_music': {
132 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
133 'INNERTUBE_HOST': 'music.youtube.com',
134 'INNERTUBE_CONTEXT': {
135 'client': {
136 'clientName': 'ANDROID_MUSIC',
137 'clientVersion': '4.32',
138 }
139 },
140 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
141 },
e7e94f2a
D
142 'android_creator': {
143 'INNERTUBE_CONTEXT': {
144 'client': {
145 'clientName': 'ANDROID_CREATOR',
146 'clientVersion': '21.24.100',
147 },
148 },
149 'INNERTUBE_CONTEXT_CLIENT_NAME': 14
150 },
3619f78d 151 # ios has HLS live streams
152 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680
000c15a4 153 'ios': {
154 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
155 'INNERTUBE_CONTEXT': {
156 'client': {
157 'clientName': 'IOS',
158 'clientVersion': '16.20',
159 }
160 },
161 'INNERTUBE_CONTEXT_CLIENT_NAME': 5
162 },
163 'ios_embedded': {
164 'INNERTUBE_API_KEY': 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8',
165 'INNERTUBE_CONTEXT': {
166 'client': {
167 'clientName': 'IOS_MESSAGES_EXTENSION',
168 'clientVersion': '16.20',
169 },
170 },
171 'INNERTUBE_CONTEXT_CLIENT_NAME': 66
172 },
173 'ios_music': {
174 'INNERTUBE_API_KEY': 'AIzaSyDK3iBpDP9nHVTk2qL73FLJICfOC3c51Og',
175 'INNERTUBE_HOST': 'music.youtube.com',
176 'INNERTUBE_CONTEXT': {
177 'client': {
178 'clientName': 'IOS_MUSIC',
179 'clientVersion': '4.32',
180 },
181 },
182 'INNERTUBE_CONTEXT_CLIENT_NAME': 26
183 },
e7e94f2a
D
184 'ios_creator': {
185 'INNERTUBE_CONTEXT': {
186 'client': {
187 'clientName': 'IOS_CREATOR',
188 'clientVersion': '21.24.100',
189 },
190 },
191 'INNERTUBE_CONTEXT_CLIENT_NAME': 15
192 },
3619f78d 193 # mweb has 'ultralow' formats
194 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 195 'mweb': {
196 'INNERTUBE_API_KEY': 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8',
197 'INNERTUBE_CONTEXT': {
198 'client': {
199 'clientName': 'MWEB',
200 'clientVersion': '2.20210721.07.00',
201 }
202 },
203 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
204 },
205}
206
207
208def build_innertube_clients():
65c2fde2 209 third_party = {
210 'embedUrl': 'https://google.com', # Can be any valid URL
211 }
000c15a4 212 base_clients = ('android', 'web', 'ios', 'mweb')
213 priority = qualities(base_clients[::-1])
214
215 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 216 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 217 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
218 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
219 ytcfg['priority'] = 10 * priority(client.split('_', 1)[0])
220
221 if client in base_clients:
222 INNERTUBE_CLIENTS[f'{client}_agegate'] = agegate_ytcfg = copy.deepcopy(ytcfg)
223 agegate_ytcfg['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
65c2fde2 224 agegate_ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party
000c15a4 225 agegate_ytcfg['priority'] -= 1
226 elif client.endswith('_embedded'):
65c2fde2 227 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party
000c15a4 228 ytcfg['priority'] -= 2
229 else:
230 ytcfg['priority'] -= 3
231
232
233build_innertube_clients()
234
235
de7f3446 236class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 237 """Provide base functions for Youtube extractors"""
e00eb564 238
3462ffa8 239 _RESERVED_NAMES = (
3619f78d 240 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|'
241 r'shorts|movies|results|shared|hashtag|trending|feed|feeds|'
242 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 243 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 244
3619f78d 245 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
246
b2e8bc1b 247 _NETRC_MACHINE = 'youtube'
3619f78d 248
b2e8bc1b
JMF
249 # If True it will raise an error if no login info is provided
250 _LOGIN_REQUIRED = False
251
3619f78d 252 r''' # Unused since login is broken
253 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
254 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
255
256 _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup'
257 _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge'
258 _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
259 '''
d0ba5587 260
b2e8bc1b 261 def _login(self):
83317f69 262 """
263 Attempt to log in to YouTube.
264 True is returned if successful or skipped.
265 False is returned if login failed.
266
267 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
268 """
9d5d4d64 269
270 def warn(message):
271 self.report_warning(message)
272
273 # username+password login is broken
982ee69a
MB
274 if (self._LOGIN_REQUIRED
275 and self.get_param('cookiefile') is None
276 and self.get_param('cookiesfrombrowser') is None):
9d5d4d64 277 self.raise_login_required(
278 'Login details are needed to download this content', method='cookies')
68217024 279 username, password = self._get_login_info()
9d5d4d64 280 if username:
281 warn('Logging in using username and password is broken. %s' % self._LOGIN_HINTS['cookies'])
282 return
9d5d4d64 283
2d6659b9 284 # Everything below this is broken!
285 r'''
b2e8bc1b
JMF
286 # No authentication to be performed
287 if username is None:
a06916d9 288 if self._LOGIN_REQUIRED and self.get_param('cookiefile') is None:
69ea8ca4 289 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
a06916d9 290 # if self.get_param('cookiefile'): # TODO remove 'and False' later - too many people using outdated cookies and open issues, remind them.
545cc85d 291 # self.to_screen('[Cookies] Reminder - Make sure to always use up to date cookies!')
83317f69 292 return True
b2e8bc1b 293
7cc3570e
PH
294 login_page = self._download_webpage(
295 self._LOGIN_URL, None,
69ea8ca4
PH
296 note='Downloading login page',
297 errnote='unable to fetch login page', fatal=False)
7cc3570e
PH
298 if login_page is False:
299 return
b2e8bc1b 300
1212e997 301 login_form = self._hidden_inputs(login_page)
c5e8d7af 302
e00eb564
S
303 def req(url, f_req, note, errnote):
304 data = login_form.copy()
305 data.update({
306 'pstMsg': 1,
307 'checkConnection': 'youtube',
308 'checkedDomains': 'youtube',
309 'hl': 'en',
310 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
3995d37d 311 'f.req': json.dumps(f_req),
e00eb564
S
312 'flowName': 'GlifWebSignIn',
313 'flowEntry': 'ServiceLogin',
baf67a60
S
314 # TODO: reverse actual botguard identifier generation algo
315 'bgRequest': '["identifier",""]',
041bc3ad 316 })
e00eb564
S
317 return self._download_json(
318 url, None, note=note, errnote=errnote,
319 transform_source=lambda s: re.sub(r'^[^[]*', '', s),
320 fatal=False,
321 data=urlencode_postdata(data), headers={
322 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
323 'Google-Accounts-XSRF': 1,
324 })
325
3995d37d
S
326 lookup_req = [
327 username,
328 None, [], None, 'US', None, None, 2, False, True,
329 [
330 None, None,
331 [2, 1, None, 1,
332 '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',
333 None, [], 4],
334 1, [None, None, []], None, None, None, True
335 ],
336 username,
337 ]
338
e00eb564 339 lookup_results = req(
3995d37d 340 self._LOOKUP_URL, lookup_req,
e00eb564
S
341 'Looking up account info', 'Unable to look up account info')
342
343 if lookup_results is False:
344 return False
041bc3ad 345
3995d37d
S
346 user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
347 if not user_hash:
348 warn('Unable to extract user hash')
349 return False
350
351 challenge_req = [
352 user_hash,
353 None, 1, None, [1, None, None, None, [password, None, True]],
354 [
355 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],
356 1, [None, None, []], None, None, None, True
357 ]]
83317f69 358
3995d37d
S
359 challenge_results = req(
360 self._CHALLENGE_URL, challenge_req,
361 'Logging in', 'Unable to log in')
83317f69 362
3995d37d 363 if challenge_results is False:
e00eb564 364 return
83317f69 365
3995d37d
S
366 login_res = try_get(challenge_results, lambda x: x[0][5], list)
367 if login_res:
368 login_msg = try_get(login_res, lambda x: x[5], compat_str)
369 warn(
370 'Unable to login: %s' % 'Invalid password'
371 if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
372 return False
373
374 res = try_get(challenge_results, lambda x: x[0][-1], list)
375 if not res:
376 warn('Unable to extract result entry')
377 return False
378
9a6628aa
S
379 login_challenge = try_get(res, lambda x: x[0][0], list)
380 if login_challenge:
381 challenge_str = try_get(login_challenge, lambda x: x[2], compat_str)
382 if challenge_str == 'TWO_STEP_VERIFICATION':
3995d37d
S
383 # SEND_SUCCESS - TFA code has been successfully sent to phone
384 # QUOTA_EXCEEDED - reached the limit of TFA codes
9a6628aa 385 status = try_get(login_challenge, lambda x: x[5], compat_str)
3995d37d
S
386 if status == 'QUOTA_EXCEEDED':
387 warn('Exceeded the limit of TFA codes, try later')
388 return False
389
390 tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
391 if not tl:
392 warn('Unable to extract TL')
393 return False
394
395 tfa_code = self._get_tfa_info('2-step verification code')
396
397 if not tfa_code:
398 warn(
399 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
400 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
401 return False
402
403 tfa_code = remove_start(tfa_code, 'G-')
404
405 tfa_req = [
406 user_hash, None, 2, None,
407 [
408 9, None, None, None, None, None, None, None,
409 [None, tfa_code, True, 2]
410 ]]
411
412 tfa_results = req(
413 self._TFA_URL.format(tl), tfa_req,
414 'Submitting TFA code', 'Unable to submit TFA code')
415
416 if tfa_results is False:
417 return False
418
419 tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
420 if tfa_res:
421 tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
422 warn(
423 'Unable to finish TFA: %s' % 'Invalid TFA code'
424 if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
425 return False
426
427 check_cookie_url = try_get(
428 tfa_results, lambda x: x[0][-1][2], compat_str)
9a6628aa
S
429 else:
430 CHALLENGES = {
431 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
432 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
433 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
434 }
435 challenge = CHALLENGES.get(
436 challenge_str,
437 '%s returned error %s.' % (self.IE_NAME, challenge_str))
438 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge)
439 return False
3995d37d
S
440 else:
441 check_cookie_url = try_get(res, lambda x: x[2], compat_str)
442
443 if not check_cookie_url:
444 warn('Unable to extract CheckCookie URL')
445 return False
e00eb564
S
446
447 check_cookie_results = self._download_webpage(
3995d37d
S
448 check_cookie_url, None, 'Checking cookie', fatal=False)
449
450 if check_cookie_results is False:
451 return False
e00eb564 452
3995d37d
S
453 if 'https://myaccount.google.com/' not in check_cookie_results:
454 warn('Unable to log in')
b2e8bc1b 455 return False
e00eb564 456
b2e8bc1b 457 return True
2d6659b9 458 '''
b2e8bc1b 459
cce889b9 460 def _initialize_consent(self):
461 cookies = self._get_cookies('https://www.youtube.com/')
462 if cookies.get('__Secure-3PSID'):
463 return
464 consent_id = None
465 consent = cookies.get('CONSENT')
466 if consent:
467 if 'YES' in consent.value:
468 return
469 consent_id = self._search_regex(
470 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
471 if not consent_id:
472 consent_id = random.randint(100, 999)
473 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 474
b2e8bc1b 475 def _real_initialize(self):
cce889b9 476 self._initialize_consent()
b2e8bc1b
JMF
477 if self._downloader is None:
478 return
b2e8bc1b
JMF
479 if not self._login():
480 return
c5e8d7af 481
a0566bbf 482 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
29f7c58a 483 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
484 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
a0566bbf 485
000c15a4 486 def _get_default_ytcfg(self, client='web'):
487 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 488
000c15a4 489 def _get_innertube_host(self, client='web'):
490 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 491
000c15a4 492 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 493 # try_get but with fallback to default ytcfg client values when present
494 _func = lambda y: try_get(y, getter, expected_type)
495 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
496
000c15a4 497 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 498 return self._ytcfg_get_safe(
499 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
500 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
109dd3b2 501
314ee305 502 @staticmethod
11f9be09 503 def _extract_session_index(*data):
504 for ytcfg in data:
505 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
506 if session_index is not None:
507 return session_index
314ee305 508
000c15a4 509 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 510 return self._ytcfg_get_safe(
511 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
512 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
109dd3b2 513
000c15a4 514 def _extract_api_key(self, ytcfg=None, default_client='web'):
109dd3b2 515 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
516
000c15a4 517 def _extract_context(self, ytcfg=None, default_client='web'):
109dd3b2 518 _get_context = lambda y: try_get(y, lambda x: x['INNERTUBE_CONTEXT'], dict)
519 context = _get_context(ytcfg)
520 if context:
521 return context
522
523 context = _get_context(self._get_default_ytcfg(default_client))
524 if not ytcfg:
525 return context
526
527 # Recreate the client context (required)
528 context['client'].update({
529 'clientVersion': self._extract_client_version(ytcfg, default_client),
530 'clientName': self._extract_client_name(ytcfg, default_client),
531 })
532 visitor_data = try_get(ytcfg, lambda x: x['VISITOR_DATA'], compat_str)
533 if visitor_data:
534 context['client']['visitorData'] = visitor_data
535 return context
536
cf87314d 537 _SAPISID = None
538
109dd3b2 539 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 540 time_now = round(time.time())
cf87314d 541 if self._SAPISID is None:
542 yt_cookies = self._get_cookies('https://www.youtube.com')
543 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
544 # See: https://github.com/yt-dlp/yt-dlp/issues/393
545 sapisid_cookie = dict_get(
546 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
547 if sapisid_cookie and sapisid_cookie.value:
548 self._SAPISID = sapisid_cookie.value
549 self.write_debug('Extracted SAPISID cookie')
550 # SAPISID cookie is required if not already present
551 if not yt_cookies.get('SAPISID'):
552 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
553 self._set_cookie(
554 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
555 else:
556 self._SAPISID = False
557 if not self._SAPISID:
558 return None
1974e99f 559 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
560 sapisidhash = hashlib.sha1(
cf87314d 561 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
1974e99f 562 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
563
564 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 565 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 566 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 567
109dd3b2 568 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 569 data.update(query)
11f9be09 570 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 571 real_headers.update({'content-type': 'application/json'})
572 if headers:
573 real_headers.update(headers)
545cc85d 574 return self._download_json(
109dd3b2 575 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
a5c56234 576 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 577 data=json.dumps(data).encode('utf8'), headers=real_headers,
578 query={'key': api_key or self._extract_api_key()})
579
11f9be09 580 def extract_yt_initial_data(self, video_id, webpage):
8bdd16b4 581 return self._parse_json(
582 self._search_regex(
29f7c58a 583 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
a0566bbf 584 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data'),
8bdd16b4 585 video_id)
0c148415 586
a1c5d2ca 587 def _extract_identity_token(self, webpage, item_id):
11f9be09 588 if not webpage:
589 return None
590 ytcfg = self.extract_ytcfg(item_id, webpage)
a1c5d2ca
M
591 if ytcfg:
592 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
593 if token:
594 return token
595 return self._search_regex(
596 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
597 'identity token', default=None)
598
599 @staticmethod
fe93e2c4 600 def _extract_account_syncid(*args):
8ea3f7b9 601 """
602 Extract syncId required to download private playlists of secondary channels
fe93e2c4 603 @params response and/or ytcfg
8ea3f7b9 604 """
fe93e2c4 605 for data in args:
606 # ytcfg includes channel_syncid if on secondary channel
607 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
608 if delegated_sid:
609 return delegated_sid
610 sync_ids = (try_get(
611 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
612 lambda x: x['DATASYNC_ID']), compat_str) or '').split("||")
613 if len(sync_ids) >= 2 and sync_ids[1]:
614 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
615 # and just "user_syncid||" for primary channel. We only want the channel_syncid
616 return sync_ids[0]
a1c5d2ca 617
11f9be09 618 def extract_ytcfg(self, video_id, webpage):
8c54a305 619 if not webpage:
620 return {}
29f7c58a 621 return self._parse_json(
622 self._search_regex(
623 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 624 default='{}'), video_id, fatal=False) or {}
625
11f9be09 626 def generate_api_headers(
627 self, ytcfg=None, identity_token=None, account_syncid=None,
000c15a4 628 visitor_data=None, api_hostname=None, default_client='web', session_index=None):
11f9be09 629 origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client))
f4f751af 630 headers = {
109dd3b2 631 'X-YouTube-Client-Name': compat_str(
11f9be09 632 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
633 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
109dd3b2 634 'Origin': origin
f4f751af 635 }
2d6659b9 636 if not visitor_data and ytcfg:
637 visitor_data = try_get(
11f9be09 638 self._extract_context(ytcfg, default_client), lambda x: x['client']['visitorData'], compat_str)
f4f751af 639 if identity_token:
109dd3b2 640 headers['X-Youtube-Identity-Token'] = identity_token
f4f751af 641 if account_syncid:
642 headers['X-Goog-PageId'] = account_syncid
314ee305 643 if session_index is None and ytcfg:
644 session_index = self._extract_session_index(ytcfg)
645 if account_syncid or session_index is not None:
646 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
f4f751af 647 if visitor_data:
109dd3b2 648 headers['X-Goog-Visitor-Id'] = visitor_data
649 auth = self._generate_sapisidhash_header(origin)
f4f751af 650 if auth is not None:
651 headers['Authorization'] = auth
109dd3b2 652 headers['X-Origin'] = origin
f4f751af 653 return headers
29f7c58a 654
2d6659b9 655 @staticmethod
656 def _build_api_continuation_query(continuation, ctp=None):
657 query = {
658 'continuation': continuation
659 }
660 # TODO: Inconsistency with clickTrackingParams.
661 # Currently we have a fixed ctp contained within context (from ytcfg)
662 # and a ctp in root query for continuation.
663 if ctp:
664 query['clickTracking'] = {'clickTrackingParams': ctp}
665 return query
666
2d6659b9 667 @classmethod
668 def _extract_next_continuation_data(cls, renderer):
669 next_continuation = try_get(
670 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
671 lambda x: x['continuation']['reloadContinuationData']), dict)
672 if not next_continuation:
673 return
674 continuation = next_continuation.get('continuation')
675 if not continuation:
676 return
677 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 678 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 679
680 @classmethod
681 def _extract_continuation_ep_data(cls, continuation_ep: dict):
682 if isinstance(continuation_ep, dict):
683 continuation = try_get(
684 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
685 if not continuation:
686 return
687 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 688 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 689
690 @classmethod
691 def _extract_continuation(cls, renderer):
692 next_continuation = cls._extract_next_continuation_data(renderer)
693 if next_continuation:
694 return next_continuation
fe93e2c4 695
2d6659b9 696 contents = []
697 for key in ('contents', 'items'):
698 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 699
2d6659b9 700 for content in contents:
701 if not isinstance(content, dict):
702 continue
703 continuation_ep = try_get(
704 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
705 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
706 dict)
707 continuation = cls._extract_continuation_ep_data(continuation_ep)
708 if continuation:
709 return continuation
710
fe93e2c4 711 @classmethod
712 def _extract_alerts(cls, data):
109dd3b2 713 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
714 if not isinstance(alert_dict, dict):
715 continue
716 for alert in alert_dict.values():
717 alert_type = alert.get('type')
718 if not alert_type:
719 continue
052e1350 720 message = cls._get_text(alert, 'text')
109dd3b2 721 if message:
722 yield alert_type, message
723
641ad5d8 724 def _report_alerts(self, alerts, expected=True, fatal=True):
109dd3b2 725 errors = []
726 warnings = []
727 for alert_type, alert_message in alerts:
641ad5d8 728 if alert_type.lower() == 'error' and fatal:
109dd3b2 729 errors.append([alert_type, alert_message])
730 else:
731 warnings.append([alert_type, alert_message])
732
733 for alert_type, alert_message in (warnings + errors[:-1]):
734 self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message))
735 if errors:
736 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
737
738 def _extract_and_report_alerts(self, data, *args, **kwargs):
739 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
740
47193e02 741 def _extract_badges(self, renderer: dict):
742 badges = set()
743 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
744 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
745 if label:
746 badges.add(label.lower())
747 return badges
748
749 @staticmethod
052e1350 750 def _get_text(data, *path_list, max_runs=None):
751 for path in path_list or [None]:
752 if path is None:
753 obj = [data]
754 else:
755 obj = traverse_obj(data, path, default=[])
756 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
757 obj = [obj]
758 for item in obj:
759 text = try_get(item, lambda x: x['simpleText'], compat_str)
760 if text:
761 return text
762 runs = try_get(item, lambda x: x['runs'], list) or []
763 if not runs and isinstance(item, list):
764 runs = item
765
766 runs = runs[:min(len(runs), max_runs or len(runs))]
767 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
768 if text:
769 return text
47193e02 770
109dd3b2 771 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
772 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 773 default_client='web'):
109dd3b2 774 response = None
775 last_error = None
776 count = -1
777 retries = self.get_param('extractor_retries', 3)
778 if check_get_keys is None:
779 check_get_keys = []
780 while count < retries:
781 count += 1
782 if last_error:
783 self.report_warning('%s. Retrying ...' % last_error)
784 try:
785 response = self._call_api(
786 ep=ep, fatal=True, headers=headers,
787 video_id=item_id, query=query,
788 context=self._extract_context(ytcfg, default_client),
789 api_key=self._extract_api_key(ytcfg, default_client),
790 api_hostname=api_hostname, default_client=default_client,
791 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
792 except ExtractorError as e:
9c0d7f49 793 if isinstance(e.cause, network_exceptions):
641ad5d8 794 if isinstance(e.cause, compat_HTTPError) and not is_html(e.cause.read(512)):
795 e.cause.seek(0)
796 yt_error = try_get(
797 self._parse_json(e.cause.read().decode(), item_id, fatal=False),
798 lambda x: x['error']['message'], compat_str)
799 if yt_error:
800 self._report_alerts([('ERROR', yt_error)], fatal=False)
109dd3b2 801 # Downloading page may result in intermittent 5xx HTTP error
802 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 803 # We also want to catch all other network exceptions since errors in later pages can be troublesome
804 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
805 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
806 last_error = error_to_compat_str(e.cause or e)
807 if count < retries:
808 continue
109dd3b2 809 if fatal:
810 raise
811 else:
812 self.report_warning(error_to_compat_str(e))
813 return
814
815 else:
816 # Youtube may send alerts if there was an issue with the continuation page
817 try:
818 self._extract_and_report_alerts(response, expected=False)
819 except ExtractorError as e:
820 if fatal:
821 raise
822 self.report_warning(error_to_compat_str(e))
823 return
824 if not check_get_keys or dict_get(response, check_get_keys):
825 break
826 # Youtube sometimes sends incomplete data
827 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
828 last_error = 'Incomplete data received'
829 if count >= retries:
830 if fatal:
831 raise ExtractorError(last_error)
832 else:
833 self.report_warning(last_error)
834 return
835 return response
836
9297939e 837 @staticmethod
838 def is_music_url(url):
839 return re.match(r'https?://music\.youtube\.com/', url) is not None
840
30a074c2 841 def _extract_video(self, renderer):
842 video_id = renderer.get('videoId')
052e1350 843 title = self._get_text(renderer, 'title')
844 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 845 duration = parse_duration(self._get_text(
846 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
052e1350 847 view_count_text = self._get_text(renderer, 'viewCountText') or ''
30a074c2 848 view_count = str_to_int(self._search_regex(
849 r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
850 'view count', default=None))
fe93e2c4 851
052e1350 852 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
fe93e2c4 853
30a074c2 854 return {
39ed931e 855 '_type': 'url',
30a074c2 856 'ie_key': YoutubeIE.ie_key(),
857 'id': video_id,
858 'url': video_id,
859 'title': title,
860 'description': description,
861 'duration': duration,
862 'view_count': view_count,
863 'uploader': uploader,
864 }
865
0c148415 866
360e1ca5 867class YoutubeIE(YoutubeBaseInfoExtractor):
78caa52a 868 IE_DESC = 'YouTube.com'
bc2ca1bb 869 _INVIDIOUS_SITES = (
870 # invidious-redirect websites
871 r'(?:www\.)?redirect\.invidious\.io',
872 r'(?:(?:www|dev)\.)?invidio\.us',
873 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
874 r'(?:www\.)?invidious\.pussthecat\.org',
bc2ca1bb 875 r'(?:www\.)?invidious\.zee\.li',
bc2ca1bb 876 r'(?:www\.)?invidious\.ethibox\.fr',
bc2ca1bb 877 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
bc2ca1bb 878 # youtube-dl invidious instances list
879 r'(?:(?:www|no)\.)?invidiou\.sh',
880 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
881 r'(?:www\.)?invidious\.kabi\.tk',
bc2ca1bb 882 r'(?:www\.)?invidious\.mastodon\.host',
883 r'(?:www\.)?invidious\.zapashcanon\.fr',
ed807c18 884 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
201c1459 885 r'(?:www\.)?invidious\.tinfoil-hat\.net',
886 r'(?:www\.)?invidious\.himiko\.cloud',
887 r'(?:www\.)?invidious\.reallyancient\.tech',
bc2ca1bb 888 r'(?:www\.)?invidious\.tube',
889 r'(?:www\.)?invidiou\.site',
890 r'(?:www\.)?invidious\.site',
891 r'(?:www\.)?invidious\.xyz',
892 r'(?:www\.)?invidious\.nixnet\.xyz',
201c1459 893 r'(?:www\.)?invidious\.048596\.xyz',
bc2ca1bb 894 r'(?:www\.)?invidious\.drycat\.fr',
201c1459 895 r'(?:www\.)?inv\.skyn3t\.in',
bc2ca1bb 896 r'(?:www\.)?tube\.poal\.co',
897 r'(?:www\.)?tube\.connect\.cafe',
898 r'(?:www\.)?vid\.wxzm\.sx',
899 r'(?:www\.)?vid\.mint\.lgbt',
201c1459 900 r'(?:www\.)?vid\.puffyan\.us',
bc2ca1bb 901 r'(?:www\.)?yewtu\.be',
902 r'(?:www\.)?yt\.elukerio\.org',
903 r'(?:www\.)?yt\.lelux\.fi',
904 r'(?:www\.)?invidious\.ggc-project\.de',
905 r'(?:www\.)?yt\.maisputain\.ovh',
201c1459 906 r'(?:www\.)?ytprivate\.com',
907 r'(?:www\.)?invidious\.13ad\.de',
bc2ca1bb 908 r'(?:www\.)?invidious\.toot\.koeln',
909 r'(?:www\.)?invidious\.fdn\.fr',
910 r'(?:www\.)?watch\.nettohikari\.com',
ed807c18 911 r'(?:www\.)?invidious\.namazso\.eu',
912 r'(?:www\.)?invidious\.silkky\.cloud',
913 r'(?:www\.)?invidious\.exonip\.de',
914 r'(?:www\.)?invidious\.riverside\.rocks',
915 r'(?:www\.)?invidious\.blamefran\.net',
916 r'(?:www\.)?invidious\.moomoo\.de',
917 r'(?:www\.)?ytb\.trom\.tf',
918 r'(?:www\.)?yt\.cyberhost\.uk',
bc2ca1bb 919 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
920 r'(?:www\.)?qklhadlycap4cnod\.onion',
921 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
922 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
923 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
924 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
925 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
926 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
ed807c18 927 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
928 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
929 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
930 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
bc2ca1bb 931 )
cb7dfeea 932 _VALID_URL = r"""(?x)^
c5e8d7af 933 (
edb53e2d 934 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 935 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
936 (?:www\.)?deturl\.com/www\.youtube\.com|
937 (?:www\.)?pwnyoutube\.com|
938 (?:www\.)?hooktube\.com|
939 (?:www\.)?yourepeat\.com|
940 tube\.majestyc\.net|
941 %(invidious)s|
942 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
943 (?:.*?\#/)? # handle anchor (#/) redirect urls
944 (?: # the various things that can precede the ID:
8fc54b12 945 (?:(?:v|embed|e|shorts)/(?!videoseries)) # v/ or embed/ or e/ or shorts/
c5e8d7af 946 |(?: # or the v= param in all its forms
f7000f3a 947 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 948 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 949 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
950 v=
951 )
f4b05232 952 ))
cbaed4bb
S
953 |(?:
954 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
955 vid\.plus| # or vid.plus/xxxx
956 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 957 %(invidious)s
cbaed4bb 958 )/
edb53e2d 959 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 960 )
c5e8d7af 961 )? # all until now is optional -> you can pass the naked ID
201c1459 962 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 963 (?(1).+)? # if we found the ID, everything can follow
9297939e 964 (?:\#|$)""" % {
bc2ca1bb 965 'invidious': '|'.join(_INVIDIOUS_SITES),
966 }
e40c758c 967 _PLAYER_INFO_RE = (
cc2db878 968 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
969 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
545cc85d 970 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 971 )
2c62dc26 972 _formats = {
c2d3cb4c 973 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
974 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
975 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
976 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
977 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
978 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
979 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
980 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 981 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 982 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
983 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
984 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
985 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
986 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
987 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 988 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 989 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
990 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 991
992
993 # 3D videos
c2d3cb4c 994 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
995 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
996 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
997 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 998 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
999 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1000 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 1001
96fb5605 1002 # Apple HTTP Live Streaming
11f12195 1003 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 1004 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1005 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1006 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1007 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1008 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 1009 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1010 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
1011
1012 # DASH mp4 video
d23028a8
S
1013 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1014 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1015 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1016 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1017 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 1018 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
1019 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1020 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1021 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1022 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1023 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1024 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 1025
f6f1fc92 1026 # Dash mp4 audio
d23028a8
S
1027 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1028 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1029 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1030 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1031 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1032 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1033 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1034
1035 # Dash webm
d23028a8
S
1036 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1037 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1038 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1039 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1040 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1041 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1042 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1043 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1044 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1045 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1046 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1047 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1048 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1049 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1050 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1051 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1052 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1053 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1054 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1055 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1056 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1057 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1058
1059 # Dash webm audio
d23028a8
S
1060 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1061 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1062
0857baad 1063 # Dash webm audio with opus inside
d23028a8
S
1064 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1065 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1066 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1067
ce6b9a2d
PH
1068 # RTMP (unnamed)
1069 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1070
1071 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1072 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1073 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1074 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1075 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1076 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1077 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1078 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1079 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1080 }
29f7c58a 1081 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1082
fd5c4aab
S
1083 _GEO_BYPASS = False
1084
78caa52a 1085 IE_NAME = 'youtube'
2eb88d95
PH
1086 _TESTS = [
1087 {
2d3d2997 1088 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1089 'info_dict': {
1090 'id': 'BaW_jenozKc',
1091 'ext': 'mp4',
3867038a 1092 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1093 'uploader': 'Philipp Hagemeister',
1094 'uploader_id': 'phihag',
ec85ded8 1095 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
dd4c4492
S
1096 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1097 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1098 'upload_date': '20121002',
3867038a 1099 '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 .',
4bc3a23e 1100 'categories': ['Science & Technology'],
3867038a 1101 'tags': ['youtube-dl'],
556dbe7f 1102 'duration': 10,
dbdaaa23 1103 'view_count': int,
3e7c1224
PH
1104 'like_count': int,
1105 'dislike_count': int,
7c80519c 1106 'start_time': 1,
297a564b 1107 'end_time': 9,
2eb88d95 1108 }
0e853ca4 1109 },
fccd3771 1110 {
4bc3a23e
PH
1111 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1112 'note': 'Embed-only video (#1746)',
1113 'info_dict': {
1114 'id': 'yZIXLfi8CZQ',
1115 'ext': 'mp4',
1116 'upload_date': '20120608',
1117 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1118 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1119 'uploader': 'SET India',
94bfcd23 1120 'uploader_id': 'setindia',
ec85ded8 1121 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1122 'age_limit': 18,
545cc85d 1123 },
1124 'skip': 'Private video',
fccd3771 1125 },
11b56058 1126 {
8bdd16b4 1127 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1128 'note': 'Use the first video ID in the URL',
1129 'info_dict': {
1130 'id': 'BaW_jenozKc',
1131 'ext': 'mp4',
3867038a 1132 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1133 'uploader': 'Philipp Hagemeister',
1134 'uploader_id': 'phihag',
ec85ded8 1135 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
11b56058 1136 'upload_date': '20121002',
3867038a 1137 '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 .',
11b56058 1138 'categories': ['Science & Technology'],
3867038a 1139 'tags': ['youtube-dl'],
556dbe7f 1140 'duration': 10,
dbdaaa23 1141 'view_count': int,
11b56058
PM
1142 'like_count': int,
1143 'dislike_count': int,
34a7de29
S
1144 },
1145 'params': {
1146 'skip_download': True,
1147 },
11b56058 1148 },
dd27fd17 1149 {
2d3d2997 1150 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1151 'note': '256k DASH audio (format 141) via DASH manifest',
1152 'info_dict': {
1153 'id': 'a9LDPn-MO4I',
1154 'ext': 'm4a',
1155 'upload_date': '20121002',
1156 'uploader_id': '8KVIDEO',
ec85ded8 1157 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1158 'description': '',
1159 'uploader': '8KVIDEO',
1160 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1161 },
4bc3a23e
PH
1162 'params': {
1163 'youtube_include_dash_manifest': True,
1164 'format': '141',
4919603f 1165 },
de3c7fe0 1166 'skip': 'format 141 not served anymore',
dd27fd17 1167 },
8bdd16b4 1168 # DASH manifest with encrypted signature
1169 {
1170 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1171 'info_dict': {
1172 'id': 'IB3lcPjvWLA',
1173 'ext': 'm4a',
1174 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1175 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1176 'duration': 244,
1177 'uploader': 'AfrojackVEVO',
1178 'uploader_id': 'AfrojackVEVO',
1179 'upload_date': '20131011',
cc2db878 1180 'abr': 129.495,
8bdd16b4 1181 },
1182 'params': {
1183 'youtube_include_dash_manifest': True,
1184 'format': '141/bestaudio[ext=m4a]',
1185 },
1186 },
65c2fde2 1187 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1188 {
65c2fde2 1189 'note': 'Embed allowed age-gate video',
2d3d2997 1190 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1191 'info_dict': {
1192 'id': 'HtVdAasjOgU',
1193 'ext': 'mp4',
1194 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1195 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1196 'duration': 142,
c522adb1
JMF
1197 'uploader': 'The Witcher',
1198 'uploader_id': 'WitcherGame',
ec85ded8 1199 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1200 'upload_date': '20140605',
34952f09 1201 'age_limit': 18,
c522adb1
JMF
1202 },
1203 },
65c2fde2 1204 {
1205 'note': 'Age-gate video with embed allowed in public site',
1206 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1207 'info_dict': {
1208 'id': 'HsUATh_Nc2U',
1209 'ext': 'mp4',
1210 'title': 'Godzilla 2 (Official Video)',
1211 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1212 'upload_date': '20200408',
1213 'uploader_id': 'FlyingKitty900',
1214 'uploader': 'FlyingKitty',
1215 'age_limit': 18,
1216 },
1217 },
1218 {
1219 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1220 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1221 'info_dict': {
1222 'id': 'Tq92D6wQ1mg',
1223 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1224 'ext': 'mp4',
1225 'upload_date': '20191227',
65c2fde2 1226 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1227 'uploader': 'Projekt Melody',
1228 'description': 'md5:17eccca93a786d51bc67646756894066',
1229 'age_limit': 18,
1230 },
1231 },
1232 {
1233 'note': 'Non-Agegated non-embeddable video',
1234 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1235 'info_dict': {
1236 'id': 'MeJVWBSsPAY',
1237 'ext': 'mp4',
1238 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1239 'uploader': 'Herr Lurik',
1240 'uploader_id': 'st3in234',
1241 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1242 'upload_date': '20130730',
1243 },
1244 },
1245 {
1246 'note': 'Non-bypassable age-gated video',
1247 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1248 'only_matching': True,
1249 },
8bdd16b4 1250 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1251 # YouTube Red ad is not captured for creator
1252 {
1253 'url': '__2ABJjxzNo',
1254 'info_dict': {
1255 'id': '__2ABJjxzNo',
1256 'ext': 'mp4',
1257 'duration': 266,
1258 'upload_date': '20100430',
1259 'uploader_id': 'deadmau5',
1260 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1261 'creator': 'deadmau5',
1262 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1263 'uploader': 'deadmau5',
1264 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1265 'alt_title': 'Some Chords',
8bdd16b4 1266 },
1267 'expected_warnings': [
1268 'DASH manifest missing',
1269 ]
1270 },
067aa17e 1271 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1272 {
1273 'url': 'lqQg6PlCWgI',
1274 'info_dict': {
1275 'id': 'lqQg6PlCWgI',
1276 'ext': 'mp4',
556dbe7f 1277 'duration': 6085,
90227264 1278 'upload_date': '20150827',
cbe2bd91 1279 'uploader_id': 'olympic',
ec85ded8 1280 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1281 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1282 'uploader': 'Olympics',
cbe2bd91
PH
1283 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1284 },
1285 'params': {
1286 'skip_download': 'requires avconv',
e52a40ab 1287 }
cbe2bd91 1288 },
6271f1ca
PH
1289 # Non-square pixels
1290 {
1291 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1292 'info_dict': {
1293 'id': '_b-2C3KPAM0',
1294 'ext': 'mp4',
1295 'stretched_ratio': 16 / 9.,
556dbe7f 1296 'duration': 85,
6271f1ca
PH
1297 'upload_date': '20110310',
1298 'uploader_id': 'AllenMeow',
ec85ded8 1299 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1300 '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',
eb6793ba 1301 'uploader': '孫ᄋᄅ',
6271f1ca
PH
1302 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1303 },
06b491eb
S
1304 },
1305 # url_encoded_fmt_stream_map is empty string
1306 {
1307 'url': 'qEJwOuvDf7I',
1308 'info_dict': {
1309 'id': 'qEJwOuvDf7I',
f57b7835 1310 'ext': 'webm',
06b491eb
S
1311 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1312 'description': '',
1313 'upload_date': '20150404',
1314 'uploader_id': 'spbelect',
1315 'uploader': 'Наблюдатели Петербурга',
1316 },
1317 'params': {
1318 'skip_download': 'requires avconv',
e323cf3f
S
1319 },
1320 'skip': 'This live event has ended.',
06b491eb 1321 },
067aa17e 1322 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1323 {
1324 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1325 'info_dict': {
1326 'id': 'FIl7x6_3R5Y',
eb6793ba 1327 'ext': 'webm',
da77d856
S
1328 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1329 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1330 'duration': 220,
da77d856
S
1331 'upload_date': '20150625',
1332 'uploader_id': 'dorappi2000',
ec85ded8 1333 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1334 'uploader': 'dorappi2000',
eb6793ba 1335 'formats': 'mincount:31',
da77d856 1336 },
eb6793ba 1337 'skip': 'not actual anymore',
2ee8f5d8 1338 },
8a1a26ce
YCH
1339 # DASH manifest with segment_list
1340 {
1341 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1342 'md5': '8ce563a1d667b599d21064e982ab9e31',
1343 'info_dict': {
1344 'id': 'CsmdDsKjzN8',
1345 'ext': 'mp4',
17ee98e1 1346 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1347 'uploader': 'Airtek',
1348 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1349 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1350 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1351 },
1352 'params': {
1353 'youtube_include_dash_manifest': True,
1354 'format': '135', # bestvideo
be49068d
S
1355 },
1356 'skip': 'This live event has ended.',
2ee8f5d8 1357 },
cf7e015f
S
1358 {
1359 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1360 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1361 'info_dict': {
545cc85d 1362 'id': 'jvGDaLqkpTg',
1363 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1364 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1365 },
1366 'playlist': [{
1367 'info_dict': {
545cc85d 1368 'id': 'jvGDaLqkpTg',
cf7e015f 1369 'ext': 'mp4',
545cc85d 1370 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1371 'description': 'md5:e03b909557865076822aa169218d6a5d',
1372 'duration': 10643,
1373 'upload_date': '20161111',
1374 'uploader': 'Team PGP',
1375 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1376 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1377 },
1378 }, {
1379 'info_dict': {
545cc85d 1380 'id': '3AKt1R1aDnw',
cf7e015f 1381 'ext': 'mp4',
545cc85d 1382 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1383 'description': 'md5:e03b909557865076822aa169218d6a5d',
1384 'duration': 10991,
1385 'upload_date': '20161111',
1386 'uploader': 'Team PGP',
1387 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1388 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1389 },
1390 }, {
1391 'info_dict': {
545cc85d 1392 'id': 'RtAMM00gpVc',
cf7e015f 1393 'ext': 'mp4',
545cc85d 1394 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1395 'description': 'md5:e03b909557865076822aa169218d6a5d',
1396 'duration': 10995,
1397 'upload_date': '20161111',
1398 'uploader': 'Team PGP',
1399 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1400 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1401 },
1402 }, {
1403 'info_dict': {
545cc85d 1404 'id': '6N2fdlP3C5U',
cf7e015f 1405 'ext': 'mp4',
545cc85d 1406 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1407 'description': 'md5:e03b909557865076822aa169218d6a5d',
1408 'duration': 10990,
1409 'upload_date': '20161111',
1410 'uploader': 'Team PGP',
1411 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1412 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1413 },
1414 }],
1415 'params': {
1416 'skip_download': True,
1417 },
65c2fde2 1418 'skip': 'Not multifeed anymore',
cbaed4bb 1419 },
f9f49d87 1420 {
067aa17e 1421 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1422 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1423 'info_dict': {
1424 'id': 'gVfLd0zydlo',
1425 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1426 },
1427 'playlist_count': 2,
be49068d 1428 'skip': 'Not multifeed anymore',
f9f49d87 1429 },
cbaed4bb 1430 {
2d3d2997 1431 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1432 'only_matching': True,
0e49d9a6 1433 },
6d4fc66b 1434 {
2d3d2997 1435 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1436 'only_matching': True,
1437 },
0e49d9a6 1438 {
067aa17e 1439 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1440 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1441 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1442 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1443 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1444 'info_dict': {
1445 'id': 'lsguqyKfVQg',
1446 'ext': 'mp4',
1447 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1448 'alt_title': 'Dark Walk',
0e49d9a6 1449 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1450 'duration': 133,
0e49d9a6
LL
1451 'upload_date': '20151119',
1452 'uploader_id': 'IronSoulElf',
ec85ded8 1453 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1454 'uploader': 'IronSoulElf',
11f9be09 1455 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1456 'track': 'Dark Walk',
1457 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1458 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
0e49d9a6
LL
1459 },
1460 'params': {
1461 'skip_download': True,
1462 },
1463 },
61f92af1 1464 {
067aa17e 1465 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1466 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1467 'only_matching': True,
1468 },
313dfc45
LL
1469 {
1470 # Video with yt:stretch=17:0
1471 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1472 'info_dict': {
1473 'id': 'Q39EVAstoRM',
1474 'ext': 'mp4',
1475 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1476 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1477 'upload_date': '20151107',
1478 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1479 'uploader': 'CH GAMER DROID',
1480 },
1481 'params': {
1482 'skip_download': True,
1483 },
be49068d 1484 'skip': 'This video does not exist.',
313dfc45 1485 },
201c1459 1486 {
1487 # Video with incomplete 'yt:stretch=16:'
1488 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1489 'only_matching': True,
1490 },
7caf9830
S
1491 {
1492 # Video licensed under Creative Commons
1493 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1494 'info_dict': {
1495 'id': 'M4gD1WSo5mA',
1496 'ext': 'mp4',
1497 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1498 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1499 'duration': 721,
7caf9830
S
1500 'upload_date': '20150127',
1501 'uploader_id': 'BerkmanCenter',
ec85ded8 1502 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1503 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830
S
1504 'license': 'Creative Commons Attribution license (reuse allowed)',
1505 },
1506 'params': {
1507 'skip_download': True,
1508 },
1509 },
fd050249
S
1510 {
1511 # Channel-like uploader_url
1512 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1513 'info_dict': {
1514 'id': 'eQcmzGIKrzg',
1515 'ext': 'mp4',
1516 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1517 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1518 'duration': 4060,
fd050249 1519 'upload_date': '20151119',
eb6793ba 1520 'uploader': 'Bernie Sanders',
fd050249 1521 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1522 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249
S
1523 'license': 'Creative Commons Attribution license (reuse allowed)',
1524 },
1525 'params': {
1526 'skip_download': True,
1527 },
1528 },
040ac686
S
1529 {
1530 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1531 'only_matching': True,
7f29cf54
S
1532 },
1533 {
067aa17e 1534 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1535 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1536 'only_matching': True,
6496ccb4
S
1537 },
1538 {
1539 # Rental video preview
1540 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1541 'info_dict': {
1542 'id': 'uGpuVWrhIzE',
1543 'ext': 'mp4',
1544 'title': 'Piku - Trailer',
1545 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1546 'upload_date': '20150811',
1547 'uploader': 'FlixMatrix',
1548 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1549 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1550 'license': 'Standard YouTube License',
1551 },
1552 'params': {
1553 'skip_download': True,
1554 },
eb6793ba 1555 'skip': 'This video is not available.',
022a5d66 1556 },
12afdc2a
S
1557 {
1558 # YouTube Red video with episode data
1559 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1560 'info_dict': {
1561 'id': 'iqKdEhx-dD4',
1562 'ext': 'mp4',
1563 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1564 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1565 'duration': 2085,
12afdc2a
S
1566 'upload_date': '20170118',
1567 'uploader': 'Vsauce',
1568 'uploader_id': 'Vsauce',
1569 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1570 'series': 'Mind Field',
1571 'season_number': 1,
1572 'episode_number': 1,
1573 },
1574 'params': {
1575 'skip_download': True,
1576 },
1577 'expected_warnings': [
1578 'Skipping DASH manifest',
1579 ],
1580 },
c7121fa7
S
1581 {
1582 # The following content has been identified by the YouTube community
1583 # as inappropriate or offensive to some audiences.
1584 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1585 'info_dict': {
1586 'id': '6SJNVb0GnPI',
1587 'ext': 'mp4',
1588 'title': 'Race Differences in Intelligence',
1589 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1590 'duration': 965,
1591 'upload_date': '20140124',
1592 'uploader': 'New Century Foundation',
1593 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1594 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1595 },
1596 'params': {
1597 'skip_download': True,
1598 },
545cc85d 1599 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1600 },
022a5d66
S
1601 {
1602 # itag 212
1603 'url': '1t24XAntNCY',
1604 'only_matching': True,
fd5c4aab
S
1605 },
1606 {
1607 # geo restricted to JP
1608 'url': 'sJL6WA-aGkQ',
1609 'only_matching': True,
1610 },
cd5a74a2
S
1611 {
1612 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1613 'only_matching': True,
1614 },
bc2ca1bb 1615 {
1616 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1617 'only_matching': True,
1618 },
1619 {
1620 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1621 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1622 'only_matching': True,
1623 },
825cd268
RA
1624 {
1625 # DRM protected
1626 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1627 'only_matching': True,
4fe54c12
S
1628 },
1629 {
1630 # Video with unsupported adaptive stream type formats
1631 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1632 'info_dict': {
1633 'id': 'Z4Vy8R84T1U',
1634 'ext': 'mp4',
1635 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1636 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1637 'duration': 433,
1638 'upload_date': '20130923',
1639 'uploader': 'Amelia Putri Harwita',
1640 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1641 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1642 'formats': 'maxcount:10',
1643 },
1644 'params': {
1645 'skip_download': True,
1646 'youtube_include_dash_manifest': False,
1647 },
5429d6a9 1648 'skip': 'not actual anymore',
5caabd3c 1649 },
1650 {
822b9d9c 1651 # Youtube Music Auto-generated description
5caabd3c 1652 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1653 'info_dict': {
1654 'id': 'MgNrAu2pzNs',
1655 'ext': 'mp4',
1656 'title': 'Voyeur Girl',
1657 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1658 'upload_date': '20190312',
5429d6a9
S
1659 'uploader': 'Stephen - Topic',
1660 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1661 'artist': 'Stephen',
1662 'track': 'Voyeur Girl',
1663 'album': 'it\'s too much love to know my dear',
1664 'release_date': '20190313',
1665 'release_year': 2019,
1666 },
1667 'params': {
1668 'skip_download': True,
1669 },
1670 },
66b48727
RA
1671 {
1672 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1673 'only_matching': True,
1674 },
011e75e6
S
1675 {
1676 # invalid -> valid video id redirection
1677 'url': 'DJztXj2GPfl',
1678 'info_dict': {
1679 'id': 'DJztXj2GPfk',
1680 'ext': 'mp4',
1681 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1682 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1683 'upload_date': '20090125',
1684 'uploader': 'Prochorowka',
1685 'uploader_id': 'Prochorowka',
1686 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1687 'artist': 'Panjabi MC',
1688 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1689 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1690 },
1691 'params': {
1692 'skip_download': True,
1693 },
545cc85d 1694 'skip': 'Video unavailable',
ea74e00b
DP
1695 },
1696 {
1697 # empty description results in an empty string
1698 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1699 'info_dict': {
1700 'id': 'x41yOUIvK2k',
1701 'ext': 'mp4',
1702 'title': 'IMG 3456',
1703 'description': '',
1704 'upload_date': '20170613',
1705 'uploader_id': 'ElevageOrVert',
1706 'uploader': 'ElevageOrVert',
1707 },
1708 'params': {
1709 'skip_download': True,
1710 },
1711 },
a0566bbf 1712 {
29f7c58a 1713 # with '};' inside yt initial data (see [1])
1714 # see [2] for an example with '};' inside ytInitialPlayerResponse
1715 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1716 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1717 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1718 'info_dict': {
1719 'id': 'CHqg6qOn4no',
1720 'ext': 'mp4',
1721 'title': 'Part 77 Sort a list of simple types in c#',
1722 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1723 'upload_date': '20130831',
1724 'uploader_id': 'kudvenkat',
1725 'uploader': 'kudvenkat',
1726 },
1727 'params': {
1728 'skip_download': True,
1729 },
1730 },
29f7c58a 1731 {
1732 # another example of '};' in ytInitialData
1733 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1734 'only_matching': True,
1735 },
1736 {
1737 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1738 'only_matching': True,
1739 },
545cc85d 1740 {
cc2db878 1741 # https://github.com/ytdl-org/youtube-dl/pull/28094
1742 'url': 'OtqTfy26tG0',
1743 'info_dict': {
1744 'id': 'OtqTfy26tG0',
1745 'ext': 'mp4',
1746 'title': 'Burn Out',
1747 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1748 'upload_date': '20141120',
1749 'uploader': 'The Cinematic Orchestra - Topic',
1750 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1751 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1752 'artist': 'The Cinematic Orchestra',
1753 'track': 'Burn Out',
1754 'album': 'Every Day',
1755 'release_data': None,
1756 'release_year': None,
1757 },
1758 'params': {
1759 'skip_download': True,
1760 },
545cc85d 1761 },
bc2ca1bb 1762 {
1763 # controversial video, only works with bpctr when authenticated with cookies
1764 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1765 'only_matching': True,
1766 },
a1a7907b 1767 {
1768 # controversial video, requires bpctr/contentCheckOk
1769 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1770 'info_dict': {
1771 'id': 'SZJvDhaSDnc',
1772 'ext': 'mp4',
1773 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1774 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1775 'uploader': 'CBS This Morning',
11f9be09 1776 'uploader_id': 'CBSThisMorning',
a1a7907b 1777 'upload_date': '20140716',
1778 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7'
1779 }
1780 },
f7ad7160 1781 {
1782 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1783 'url': 'cBvYw8_A0vQ',
1784 'info_dict': {
1785 'id': 'cBvYw8_A0vQ',
1786 'ext': 'mp4',
1787 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1788 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1789 'upload_date': '20201120',
1790 'uploader': 'Walk around Japan',
1791 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1792 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1793 },
1794 'params': {
1795 'skip_download': True,
1796 },
0fb983f6 1797 }, {
1798 # Has multiple audio streams
1799 'url': 'WaOKSUlf4TM',
1800 'only_matching': True
9297939e 1801 }, {
1802 # Requires Premium: has format 141 when requested using YTM url
1803 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
1804 'only_matching': True
1805 }, {
120916da 1806 # multiple subtitles with same lang_code
1807 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
1808 'only_matching': True,
109dd3b2 1809 }, {
1810 # Force use android client fallback
1811 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
1812 'info_dict': {
1813 'id': 'YOelRv7fMxY',
11f9be09 1814 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 1815 'ext': '3gp',
1816 'upload_date': '20210624',
1817 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
1818 'uploader': 'colinfurze',
11f9be09 1819 'uploader_id': 'colinfurze',
109dd3b2 1820 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
11f9be09 1821 'description': 'md5:b5096f56af7ccd7a555c84db81738b22'
109dd3b2 1822 },
1823 'params': {
1824 'format': '17', # 3gp format available on android
1825 'extractor_args': {'youtube': {'player_client': ['android']}},
1826 },
120916da 1827 },
109dd3b2 1828 {
1829 # Skip download of additional client configs (remix client config in this case)
1830 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1831 'only_matching': True,
1832 'params': {
1833 'extractor_args': {'youtube': {'player_skip': ['configs']}},
1834 },
8fc54b12 1835 }, {
1836 # shorts
1837 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
1838 'only_matching': True,
1839 },
2eb88d95
PH
1840 ]
1841
201c1459 1842 @classmethod
1843 def suitable(cls, url):
4dfbf869 1844 from ..utils import parse_qs
1845
201c1459 1846 qs = parse_qs(url)
1847 if qs.get('list', [None])[0]:
1848 return False
1849 return super(YoutubeIE, cls).suitable(url)
1850
e0df6211
PH
1851 def __init__(self, *args, **kwargs):
1852 super(YoutubeIE, self).__init__(*args, **kwargs)
545cc85d 1853 self._code_cache = {}
83799698 1854 self._player_cache = {}
e0df6211 1855
109dd3b2 1856 def _extract_player_url(self, ytcfg=None, webpage=None):
1857 player_url = try_get(ytcfg, (lambda x: x['PLAYER_JS_URL']), str)
11f9be09 1858 if not player_url and webpage:
109dd3b2 1859 player_url = self._search_regex(
1860 r'"(?:PLAYER_JS_URL|jsUrl)"\s*:\s*"([^"]+)"',
1861 webpage, 'player URL', fatal=False)
11f9be09 1862 if not player_url:
1863 return None
109dd3b2 1864 if player_url.startswith('//'):
1865 player_url = 'https:' + player_url
1866 elif not re.match(r'https?://', player_url):
1867 player_url = compat_urlparse.urljoin(
1868 'https://www.youtube.com', player_url)
1869 return player_url
1870
60064c53
PH
1871 def _signature_cache_id(self, example_sig):
1872 """ Return a string representation of a signature """
78caa52a 1873 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 1874
e40c758c
S
1875 @classmethod
1876 def _extract_player_info(cls, player_url):
1877 for player_re in cls._PLAYER_INFO_RE:
1878 id_m = re.search(player_re, player_url)
1879 if id_m:
1880 break
1881 else:
c081b35c 1882 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 1883 return id_m.group('id')
e40c758c 1884
109dd3b2 1885 def _load_player(self, video_id, player_url, fatal=True) -> bool:
1886 player_id = self._extract_player_info(player_url)
1887 if player_id not in self._code_cache:
1888 self._code_cache[player_id] = self._download_webpage(
1889 player_url, video_id, fatal=fatal,
1890 note='Downloading player ' + player_id,
1891 errnote='Download of %s failed' % player_url)
1892 return player_id in self._code_cache
1893
e40c758c 1894 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 1895 player_id = self._extract_player_info(player_url)
e0df6211 1896
c4417ddb 1897 # Read from filesystem cache
545cc85d 1898 func_id = 'js_%s_%s' % (
1899 player_id, self._signature_cache_id(example_sig))
c4417ddb 1900 assert os.path.basename(func_id) == func_id
a0e07d31 1901
69ea8ca4 1902 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 1903 if cache_spec is not None:
78caa52a 1904 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 1905
109dd3b2 1906 if self._load_player(video_id, player_url):
1907 code = self._code_cache[player_id]
1908 res = self._parse_sig_js(code)
e0df6211 1909
109dd3b2 1910 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1911 cache_res = res(test_string)
1912 cache_spec = [ord(c) for c in cache_res]
83799698 1913
109dd3b2 1914 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
1915 return res
83799698 1916
60064c53 1917 def _print_sig_code(self, func, example_sig):
edf3e38e
PH
1918 def gen_sig_code(idxs):
1919 def _genslice(start, end, step):
78caa52a 1920 starts = '' if start == 0 else str(start)
8bcc8756 1921 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 1922 steps = '' if step == 1 else (':%d' % step)
78caa52a 1923 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
1924
1925 step = None
7af808a5
PH
1926 # Quelch pyflakes warnings - start will be set when step is set
1927 start = '(Never used)'
edf3e38e
PH
1928 for i, prev in zip(idxs[1:], idxs[:-1]):
1929 if step is not None:
1930 if i - prev == step:
1931 continue
1932 yield _genslice(start, prev, step)
1933 step = None
1934 continue
1935 if i - prev in [-1, 1]:
1936 step = i - prev
1937 start = prev
1938 continue
1939 else:
78caa52a 1940 yield 's[%d]' % prev
edf3e38e 1941 if step is None:
78caa52a 1942 yield 's[%d]' % i
edf3e38e
PH
1943 else:
1944 yield _genslice(start, i, step)
1945
78caa52a 1946 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 1947 cache_res = func(test_string)
edf3e38e 1948 cache_spec = [ord(c) for c in cache_res]
78caa52a 1949 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
1950 signature_id_tuple = '(%s)' % (
1951 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 1952 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 1953 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 1954 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 1955
e0df6211
PH
1956 def _parse_sig_js(self, jscode):
1957 funcname = self._search_regex(
abefc03f
S
1958 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1959 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
858a65ec
P
1960 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
1961 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
1962 r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\);[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\)',
1963 r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
31ce6e99 1964 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
1965 # Obsolete patterns
1966 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 1967 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
1968 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1969 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1970 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1971 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1972 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1973 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 1974 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
1975
1976 jsi = JSInterpreter(jscode)
1977 initial_function = jsi.extract_function(funcname)
e0df6211
PH
1978 return lambda s: initial_function([s])
1979
545cc85d 1980 def _decrypt_signature(self, s, video_id, player_url):
257a2501 1981 """Turn the encrypted s field into a working signature"""
6b37f0be 1982
c8bf86d5 1983 if player_url is None:
69ea8ca4 1984 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 1985
c8bf86d5 1986 try:
62af3a0e 1987 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
1988 if player_id not in self._player_cache:
1989 func = self._extract_signature_function(
60064c53 1990 video_id, player_url, s
c8bf86d5
PH
1991 )
1992 self._player_cache[player_id] = func
1993 func = self._player_cache[player_id]
a06916d9 1994 if self.get_param('youtube_print_sig_code'):
60064c53 1995 self._print_sig_code(func, s)
c8bf86d5
PH
1996 return func(s)
1997 except Exception as e:
1998 tb = traceback.format_exc()
1999 raise ExtractorError(
78caa52a 2000 'Signature extraction failed: ' + tb, cause=e)
e0df6211 2001
109dd3b2 2002 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2003 """
2004 Extract signatureTimestamp (sts)
2005 Required to tell API what sig/player version is in use.
2006 """
2007 sts = None
2008 if isinstance(ytcfg, dict):
2009 sts = int_or_none(ytcfg.get('STS'))
2010
2011 if not sts:
2012 # Attempt to extract from player
2013 if player_url is None:
2014 error_msg = 'Cannot extract signature timestamp without player_url.'
2015 if fatal:
2016 raise ExtractorError(error_msg)
2017 self.report_warning(error_msg)
2018 return
2019 if self._load_player(video_id, player_url, fatal=fatal):
2020 player_id = self._extract_player_info(player_url)
2021 code = self._code_cache[player_id]
2022 sts = int_or_none(self._search_regex(
2023 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2024 'JS player signature timestamp', group='sts', fatal=fatal))
2025 return sts
2026
11f9be09 2027 def _mark_watched(self, video_id, player_responses):
352d63fd 2028 playback_url = traverse_obj(
2029 player_responses, (..., 'playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2030 expected_type=url_or_none, get_all=False)
d77ab8e2 2031 if not playback_url:
352d63fd 2032 self.report_warning('Unable to mark watched')
d77ab8e2
S
2033 return
2034 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2035 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2036
2037 # cpn generation algorithm is reverse engineered from base.js.
2038 # In fact it works even with dummy cpn.
2039 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2040 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2041
2042 qs.update({
2043 'ver': ['2'],
2044 'cpn': [cpn],
2045 })
2046 playback_url = compat_urlparse.urlunparse(
15707c7e 2047 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
2048
2049 self._download_webpage(
2050 playback_url, video_id, 'Marking watched',
2051 'Unable to mark watched', fatal=False)
2052
66c9fa36
S
2053 @staticmethod
2054 def _extract_urls(webpage):
2055 # Embedded YouTube player
2056 entries = [
2057 unescapeHTML(mobj.group('url'))
2058 for mobj in re.finditer(r'''(?x)
2059 (?:
2060 <iframe[^>]+?src=|
2061 data-video-url=|
2062 <embed[^>]+?src=|
2063 embedSWF\(?:\s*|
2064 <object[^>]+data=|
2065 new\s+SWFObject\(
2066 )
2067 (["\'])
2068 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2069 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2070 \1''', webpage)]
2071
2072 # lazyYT YouTube embed
2073 entries.extend(list(map(
2074 unescapeHTML,
2075 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2076
2077 # Wordpress "YouTube Video Importer" plugin
2078 matches = re.findall(r'''(?x)<div[^>]+
2079 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2080 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2081 entries.extend(m[-1] for m in matches)
2082
2083 return entries
2084
2085 @staticmethod
2086 def _extract_url(webpage):
2087 urls = YoutubeIE._extract_urls(webpage)
2088 return urls[0] if urls else None
2089
97665381
PH
2090 @classmethod
2091 def extract_id(cls, url):
2092 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 2093 if mobj is None:
69ea8ca4 2094 raise ExtractorError('Invalid URL: %s' % url)
5ad28e7f 2095 return mobj.group('id')
c5e8d7af 2096
7c365c21 2097 def _extract_chapters_from_json(self, data, duration):
2098 chapter_list = traverse_obj(
2099 data, (
2100 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2101 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2102 ), expected_type=list)
2103
2104 return self._extract_chapters(
2105 chapter_list,
2106 chapter_time=lambda chapter: float_or_none(
2107 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2108 chapter_title=lambda chapter: traverse_obj(
2109 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2110 duration=duration)
2111
2112 def _extract_chapters_from_engagement_panel(self, data, duration):
2113 content_list = traverse_obj(
8bdd16b4 2114 data,
7c365c21 2115 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2116 expected_type=list, default=[])
052e1350 2117 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2118 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2119
2120 return next((
2121 filter(None, (
2122 self._extract_chapters(
2123 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2124 chapter_time, chapter_title, duration)
2125 for contents in content_list
2126 ))), [])
2127
2128 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
84213ea8 2129 chapters = []
7c365c21 2130 last_chapter = {'start_time': 0}
2131 for idx, chapter in enumerate(chapter_list or []):
2132 title = chapter_title(chapter)
84213ea8
S
2133 start_time = chapter_time(chapter)
2134 if start_time is None:
2135 continue
7c365c21 2136 last_chapter['end_time'] = start_time
2137 if start_time < last_chapter['start_time']:
2138 if idx == 1:
2139 chapters.pop()
2140 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2141 else:
2142 self.report_warning(f'Invalid start time for chapter "{title}"')
2143 continue
2144 last_chapter = {'start_time': start_time, 'title': title}
2145 chapters.append(last_chapter)
2146 last_chapter['end_time'] = duration
84213ea8
S
2147 return chapters
2148
545cc85d 2149 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2150 return self._parse_json(self._search_regex(
2151 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2152 regex), webpage, name, default='{}'), video_id, fatal=False)
84213ea8 2153
d92f5d5a 2154 @staticmethod
2155 def parse_time_text(time_text):
2156 """
2157 Parse the comment time text
2158 time_text is in the format 'X units ago (edited)'
2159 """
2160 time_text_split = time_text.split(' ')
2161 if len(time_text_split) >= 3:
da503b7a 2162 try:
2163 return datetime_from_str('now-%s%s' % (time_text_split[0], time_text_split[1]), precision='auto')
2164 except ValueError:
2165 return None
d92f5d5a 2166
a1c5d2ca
M
2167 def _extract_comment(self, comment_renderer, parent=None):
2168 comment_id = comment_renderer.get('commentId')
2169 if not comment_id:
2170 return
fe93e2c4 2171
052e1350 2172 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2173
49bd8c66 2174 # note: timestamp is an estimate calculated from the current time and time_text
052e1350 2175 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
fe93e2c4 2176 time_text_dt = self.parse_time_text(time_text)
2177 if isinstance(time_text_dt, datetime.datetime):
2178 timestamp = calendar.timegm(time_text_dt.timetuple())
052e1350 2179 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2180 author_id = try_get(comment_renderer,
2181 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2182
49bd8c66 2183 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2184 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2185 author_thumbnail = try_get(comment_renderer,
2186 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2187
2188 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2189 is_favorited = 'creatorHeart' in (try_get(
2190 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2191 return {
2192 'id': comment_id,
2193 'text': text,
d92f5d5a 2194 'timestamp': timestamp,
a1c5d2ca
M
2195 'time_text': time_text,
2196 'like_count': votes,
97524332 2197 'is_favorited': is_favorited,
a1c5d2ca
M
2198 'author': author,
2199 'author_id': author_id,
2200 'author_thumbnail': author_thumbnail,
2201 'author_is_uploader': author_is_uploader,
2202 'parent': parent or 'root'
2203 }
2204
2205 def _comment_entries(self, root_continuation_data, identity_token, account_syncid,
2d6659b9 2206 ytcfg, video_id, parent=None, comment_counts=None):
2207
2208 def extract_header(contents):
2209 _total_comments = 0
2210 _continuation = None
2211 for content in contents:
2212 comments_header_renderer = try_get(content, lambda x: x['commentsHeaderRenderer'])
fe93e2c4 2213 expected_comment_count = parse_count(self._get_text(
052e1350 2214 comments_header_renderer, 'countText', 'commentsCount', max_runs=1))
fe93e2c4 2215
2d6659b9 2216 if expected_comment_count:
fe93e2c4 2217 comment_counts[1] = expected_comment_count
2218 self.to_screen('Downloading ~%d comments' % expected_comment_count)
2d6659b9 2219 _total_comments = comment_counts[1]
2220 sort_mode_str = self._configuration_arg('comment_sort', [''])[0]
2221 comment_sort_index = int(sort_mode_str != 'top') # 1 = new, 0 = top
2222
2223 sort_menu_item = try_get(
2224 comments_header_renderer,
2225 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2226 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2227
2228 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2229 if not _continuation:
2230 continue
2231
2232 sort_text = sort_menu_item.get('title')
2233 if isinstance(sort_text, compat_str):
2234 sort_text = sort_text.lower()
2235 else:
2236 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2237 self.to_screen('Sorting comments by %s' % sort_text)
2238 break
2239 return _total_comments, _continuation
a1c5d2ca 2240
2d6659b9 2241 def extract_thread(contents):
a1c5d2ca
M
2242 if not parent:
2243 comment_counts[2] = 0
2244 for content in contents:
2245 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2246 comment_renderer = try_get(
2247 comment_thread_renderer, (lambda x: x['comment']['commentRenderer'], dict)) or try_get(
2248 content, (lambda x: x['commentRenderer'], dict))
2249
2250 if not comment_renderer:
2251 continue
2252 comment = self._extract_comment(comment_renderer, parent)
2253 if not comment:
2254 continue
2255 comment_counts[0] += 1
2256 yield comment
2257 # Attempt to get the replies
2258 comment_replies_renderer = try_get(
2259 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2260
2261 if comment_replies_renderer:
2262 comment_counts[2] += 1
2263 comment_entries_iter = self._comment_entries(
f4f751af 2264 comment_replies_renderer, identity_token, account_syncid, ytcfg,
2d6659b9 2265 video_id, parent=comment.get('id'), comment_counts=comment_counts)
a1c5d2ca
M
2266
2267 for reply_comment in comment_entries_iter:
2268 yield reply_comment
2269
2d6659b9 2270 # YouTube comments have a max depth of 2
2271 max_depth = int_or_none(self._configuration_arg('max_comment_depth', [''])[0]) or float('inf')
2272 if max_depth == 1 and parent:
2273 return
a1c5d2ca
M
2274 if not comment_counts:
2275 # comment so far, est. total comments, current comment thread #
2276 comment_counts = [0, 0, 0]
a1c5d2ca 2277
2d6659b9 2278 continuation = self._extract_continuation(root_continuation_data)
fe93e2c4 2279 if continuation and len(continuation['continuation']) < 27:
2d6659b9 2280 self.write_debug('Detected old API continuation token. Generating new API compatible token.')
2281 continuation_token = self._generate_comment_continuation(video_id)
fe93e2c4 2282 continuation = self._build_api_continuation_query(continuation_token, None)
2d6659b9 2283
2284 visitor_data = None
2285 is_first_continuation = parent is None
a1c5d2ca
M
2286
2287 for page_num in itertools.count(0):
2288 if not continuation:
2289 break
11f9be09 2290 headers = self.generate_api_headers(ytcfg, identity_token, account_syncid, visitor_data)
2d6659b9 2291 comment_prog_str = '(%d/%d)' % (comment_counts[0], comment_counts[1])
2292 if page_num == 0:
2293 if is_first_continuation:
2294 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2295 else:
2d6659b9 2296 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2297 comment_counts[2], comment_prog_str)
2298 else:
2299 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2300 ' ' if parent else '', ' replies' if parent else '',
2301 page_num, comment_prog_str)
2302
2303 response = self._extract_response(
fe93e2c4 2304 item_id=None, query=continuation,
2d6659b9 2305 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2306 check_get_keys=('onResponseReceivedEndpoints', 'continuationContents'))
a1c5d2ca
M
2307 if not response:
2308 break
f4f751af 2309 visitor_data = try_get(
2310 response,
2311 lambda x: x['responseContext']['webResponseContextExtensionData']['ytConfigData']['visitorData'],
2312 compat_str) or visitor_data
a1c5d2ca 2313
2d6659b9 2314 continuation_contents = dict_get(response, ('onResponseReceivedEndpoints', 'continuationContents'))
a1c5d2ca 2315
2d6659b9 2316 continuation = None
2317 if isinstance(continuation_contents, list):
2318 for continuation_section in continuation_contents:
2319 if not isinstance(continuation_section, dict):
2320 continue
2321 continuation_items = try_get(
2322 continuation_section,
2323 (lambda x: x['reloadContinuationItemsCommand']['continuationItems'],
2324 lambda x: x['appendContinuationItemsAction']['continuationItems']),
2325 list) or []
2326 if is_first_continuation:
2327 total_comments, continuation = extract_header(continuation_items)
2328 if total_comments:
2329 yield total_comments
2330 is_first_continuation = False
2331 if continuation:
2332 break
2333 continue
2334 count = 0
2335 for count, entry in enumerate(extract_thread(continuation_items)):
2336 yield entry
2337 continuation = self._extract_continuation({'contents': continuation_items})
2338 if continuation:
2339 # Sometimes YouTube provides a continuation without any comments
2340 # In most cases we end up just downloading these with very little comments to come.
2341 if count == 0:
2342 if not parent:
2343 self.report_warning('No comments received - assuming end of comments')
2344 continuation = None
a1c5d2ca
M
2345 break
2346
2d6659b9 2347 # Deprecated response structure
2348 elif isinstance(continuation_contents, dict):
2349 known_continuation_renderers = ('itemSectionContinuation', 'commentRepliesContinuation')
2350 for key, continuation_renderer in continuation_contents.items():
2351 if key not in known_continuation_renderers:
2352 continue
2353 if not isinstance(continuation_renderer, dict):
2354 continue
2355 if is_first_continuation:
2356 header_continuation_items = [continuation_renderer.get('header') or {}]
2357 total_comments, continuation = extract_header(header_continuation_items)
2358 if total_comments:
2359 yield total_comments
2360 is_first_continuation = False
2361 if continuation:
2362 break
a1c5d2ca 2363
2d6659b9 2364 # Sometimes YouTube provides a continuation without any comments
2365 # In most cases we end up just downloading these with very little comments to come.
2366 count = 0
2367 for count, entry in enumerate(extract_thread(continuation_renderer.get('contents') or {})):
2368 yield entry
2369 continuation = self._extract_continuation(continuation_renderer)
2370 if count == 0:
2371 if not parent:
2372 self.report_warning('No comments received - assuming end of comments')
2373 continuation = None
2374 break
a1c5d2ca 2375
2d6659b9 2376 @staticmethod
2377 def _generate_comment_continuation(video_id):
2378 """
2379 Generates initial comment section continuation token from given video id
2380 """
2381 b64_vid_id = base64.b64encode(bytes(video_id.encode('utf-8')))
2382 parts = ('Eg0SCw==', b64_vid_id, 'GAYyJyIRIgs=', b64_vid_id, 'MAB4AjAAQhBjb21tZW50cy1zZWN0aW9u')
2383 new_continuation_intlist = list(itertools.chain.from_iterable(
2384 [bytes_to_intlist(base64.b64decode(part)) for part in parts]))
2385 return base64.b64encode(intlist_to_bytes(new_continuation_intlist)).decode('utf-8')
2386
2387 def _extract_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2388 """Entry for comment extraction"""
2d6659b9 2389 def _real_comment_extract(contents):
2390 if isinstance(contents, list):
2391 for entry in contents:
2392 for key, renderer in entry.items():
2393 if key not in known_entry_comment_renderers:
2394 continue
2395 yield from self._comment_entries(
2396 renderer, video_id=video_id, ytcfg=ytcfg,
2397 identity_token=self._extract_identity_token(webpage, item_id=video_id),
2398 account_syncid=self._extract_account_syncid(ytcfg))
2399 break
a1c5d2ca 2400 comments = []
2d6659b9 2401 known_entry_comment_renderers = ('itemSectionRenderer',)
a1c5d2ca 2402 estimated_total = 0
2d6659b9 2403 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0]) or float('inf')
65524694 2404 # Force English regardless of account setting to prevent parsing issues
2405 # See: https://github.com/yt-dlp/yt-dlp/issues/532
2406 ytcfg = copy.deepcopy(ytcfg)
2407 traverse_obj(
2408 ytcfg, ('INNERTUBE_CONTEXT', 'client'), expected_type=dict, default={})['hl'] = 'en'
2d6659b9 2409 try:
2410 for comment in _real_comment_extract(contents):
2411 if len(comments) >= max_comments:
2412 break
2413 if isinstance(comment, int):
2414 estimated_total = comment
2415 continue
2416 comments.append(comment)
2417 except KeyboardInterrupt:
2418 self.to_screen('Interrupted by user')
d92f5d5a 2419 self.to_screen('Downloaded %d/%d comments' % (len(comments), estimated_total))
a1c5d2ca
M
2420 return {
2421 'comments': comments,
2422 'comment_count': len(comments),
2423 }
2424
109dd3b2 2425 @staticmethod
2426 def _generate_player_context(sts=None):
2427 context = {
2428 'html5Preference': 'HTML5_PREF_WANTS',
2429 }
2430 if sts is not None:
2431 context['signatureTimestamp'] = sts
2432 return {
2433 'playbackContext': {
2434 'contentPlaybackContext': context
a1a7907b 2435 },
2fd226f6 2436 'contentCheckOk': True,
2437 'racyCheckOk': True
109dd3b2 2438 }
2439
e7e94f2a
D
2440 @staticmethod
2441 def _is_agegated(player_response):
2442 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 2443 return True
e7e94f2a
D
2444
2445 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2446 AGE_GATE_REASONS = (
2447 'confirm your age', 'age-restricted', 'inappropriate', # reason
2448 'age_verification_required', 'age_check_required', # status
2449 )
2450 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2451
2452 @staticmethod
2453 def _is_unplayable(player_response):
2454 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 2455
11f9be09 2456 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, identity_token, player_url, initial_pr):
109dd3b2 2457
11f9be09 2458 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2459 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
2460 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False)
2461 headers = self.generate_api_headers(
2462 player_ytcfg, identity_token, syncid,
000c15a4 2463 default_client=client, session_index=session_index)
9297939e 2464
11f9be09 2465 yt_query = {'videoId': video_id}
2466 yt_query.update(self._generate_player_context(sts))
2467 return self._extract_response(
2468 item_id=video_id, ep='player', query=yt_query,
379e44ed 2469 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 2470 default_client=client,
11f9be09 2471 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2472 ) or None
2473
11f9be09 2474 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 2475 requested_clients = []
000c15a4 2476 allowed_clients = sorted(
2477 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2478 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 2479 for client in self._configuration_arg('player_client'):
2480 if client in allowed_clients:
2481 requested_clients.append(client)
2482 elif client == 'all':
2483 requested_clients.extend(allowed_clients)
2484 else:
2485 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 2486 if not requested_clients:
2487 requested_clients = ['android', 'web']
cf7e015f 2488
11f9be09 2489 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2490 requested_clients.extend(
e7e94f2a 2491 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 2492
11f9be09 2493 return orderedSet(requested_clients)
cf7e015f 2494
c0bc527b
M
2495 def _extract_player_ytcfg(self, client, video_id):
2496 url = {
2497 'web_music': 'https://music.youtube.com',
2498 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2499 }.get(client)
2500 if not url:
2501 return {}
2502 webpage = self._download_webpage(url, video_id, fatal=False, note=f'Downloading {client} config')
2503 return self.extract_ytcfg(video_id, webpage) or {}
2504
11f9be09 2505 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, player_url, identity_token):
2506 initial_pr = None
2507 if webpage:
2508 initial_pr = self._extract_yt_initial_variable(
2509 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2510 video_id, 'initial player response')
6b09401b 2511
c0bc527b
M
2512 original_clients = clients
2513 clients = clients[::-1]
e7e94f2a
D
2514
2515 def append_client(client_name):
2516 if client_name in INNERTUBE_CLIENTS and client_name not in original_clients:
2517 clients.append(client_name)
2518
379e44ed 2519 # Android player_response does not have microFormats which are needed for
2520 # extraction of some data. So we return the initial_pr with formats
2521 # stripped out even if not requested by the user
2522 # See: https://github.com/yt-dlp/yt-dlp/issues/501
2523 yielded_pr = False
2524 if initial_pr:
2525 pr = dict(initial_pr)
2526 pr['streamingData'] = None
2527 yielded_pr = True
2528 yield pr
2529
2530 last_error = None
c0bc527b
M
2531 while clients:
2532 client = clients.pop()
11f9be09 2533 player_ytcfg = master_ytcfg if client == 'web' else {}
c0bc527b
M
2534 if 'configs' not in self._configuration_arg('player_skip'):
2535 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
c0bc527b 2536
379e44ed 2537 try:
2538 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
2539 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, identity_token, player_url, initial_pr)
2540 except ExtractorError as e:
2541 if last_error:
2542 self.report_warning(last_error)
2543 last_error = e
2544 continue
2545
11f9be09 2546 if pr:
379e44ed 2547 yielded_pr = True
11f9be09 2548 yield pr
c0bc527b 2549
e7e94f2a
D
2550 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
2551 if client.endswith('_agegate') and self._is_unplayable(pr) and self._generate_sapisidhash_header():
2552 append_client(client.replace('_agegate', '_creator'))
2553 elif self._is_agegated(pr):
2554 append_client(f'{client}_agegate')
c0bc527b 2555
379e44ed 2556 if last_error:
2557 if not yielded_pr:
2558 raise last_error
2559 self.report_warning(last_error)
11f9be09 2560
2561 def _extract_formats(self, streaming_data, video_id, player_url, is_live):
2562 itags, stream_ids = [], []
2a9c6dcd 2563 itag_qualities, res_qualities = {}, {}
d3fc8074 2564 q = qualities([
2a9c6dcd 2565 # Normally tiny is the smallest video-only formats. But
2566 # audio-only formats with unknown quality may get tagged as tiny
2567 'tiny',
2568 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 2569 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
2570 ])
11f9be09 2571 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 2572
545cc85d 2573 for fmt in streaming_formats:
2574 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
2575 continue
321bf820 2576
cc2db878 2577 itag = str_or_none(fmt.get('itag'))
9297939e 2578 audio_track = fmt.get('audioTrack') or {}
2579 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
2580 if stream_id in stream_ids:
2581 continue
2582
cc2db878 2583 quality = fmt.get('quality')
2a9c6dcd 2584 height = int_or_none(fmt.get('height'))
d3fc8074 2585 if quality == 'tiny' or not quality:
2586 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 2587 # The 3gp format (17) in android client has a quality of "small",
2588 # but is actually worse than other formats
2589 if itag == '17':
2590 quality = 'tiny'
2591 if quality:
2592 if itag:
2593 itag_qualities[itag] = quality
2594 if height:
2595 res_qualities[height] = quality
cc2db878 2596 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
2597 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
2598 # number of fragment that would subsequently requested with (`&sq=N`)
2599 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
2600 continue
2601
545cc85d 2602 fmt_url = fmt.get('url')
2603 if not fmt_url:
2604 sc = compat_parse_qs(fmt.get('signatureCipher'))
2605 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
2606 encrypted_sig = try_get(sc, lambda x: x['s'][0])
2607 if not (sc and fmt_url and encrypted_sig):
2608 continue
545cc85d 2609 if not player_url:
201e9eaa 2610 continue
545cc85d 2611 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2612 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2613 fmt_url += '&' + sp + '=' + signature
2614
545cc85d 2615 if itag:
2616 itags.append(itag)
9297939e 2617 stream_ids.append(stream_id)
2618
cc2db878 2619 tbr = float_or_none(
2620 fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
545cc85d 2621 dct = {
2622 'asr': int_or_none(fmt.get('audioSampleRate')),
2623 'filesize': int_or_none(fmt.get('contentLength')),
2624 'format_id': itag,
11f9be09 2625 'format_note': ', '.join(filter(None, (
2a9c6dcd 2626 audio_track.get('displayName'),
2627 fmt.get('qualityLabel') or quality.replace('audio_quality_', '')))),
545cc85d 2628 'fps': int_or_none(fmt.get('fps')),
2a9c6dcd 2629 'height': height,
dca3ff4a 2630 'quality': q(quality),
cc2db878 2631 'tbr': tbr,
545cc85d 2632 'url': fmt_url,
2a9c6dcd 2633 'width': int_or_none(fmt.get('width')),
0fb983f6 2634 'language': audio_track.get('id', '').split('.')[0],
545cc85d 2635 }
60bdb7bd 2636 mime_mobj = re.match(
2637 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
2638 if mime_mobj:
2639 dct['ext'] = mimetype2ext(mime_mobj.group(1))
2640 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 2641 no_audio = dct.get('acodec') == 'none'
2642 no_video = dct.get('vcodec') == 'none'
2643 if no_audio:
2644 dct['vbr'] = tbr
2645 if no_video:
2646 dct['abr'] = tbr
2647 if no_audio or no_video:
545cc85d 2648 dct['downloader_options'] = {
2649 # Youtube throttles chunks >~10M
2650 'http_chunk_size': 10485760,
bf1317d2 2651 }
7c60c33e 2652 if dct.get('ext'):
2653 dct['container'] = dct['ext'] + '_dash'
11f9be09 2654 yield dct
545cc85d 2655
4bb6b02f 2656 skip_manifests = self._configuration_arg('skip')
57015a4a 2657 get_dash = (
2658 (not is_live or self._configuration_arg('include_live_dash'))
2659 and 'dash' not in skip_manifests and self.get_param('youtube_include_dash_manifest', True))
5d3a0e79 2660 get_hls = 'hls' not in skip_manifests and self.get_param('youtube_include_hls_manifest', True)
2661
2a9c6dcd 2662 def guess_quality(f):
2663 for val, qdict in ((f.get('format_id'), itag_qualities), (f.get('height'), res_qualities)):
2664 if val in qdict:
2665 return q(qdict[val])
2666 return -1
2667
11f9be09 2668 for sd in streaming_data:
5d3a0e79 2669 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 2670 if hls_manifest_url:
2a9c6dcd 2671 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
9297939e 2672 itag = self._search_regex(
2673 r'/itag/(\d+)', f['url'], 'itag', default=None)
11f9be09 2674 if itag in itags:
2675 continue
9297939e 2676 if itag:
2677 f['format_id'] = itag
11f9be09 2678 itags.append(itag)
2a9c6dcd 2679 f['quality'] = guess_quality(f)
11f9be09 2680 yield f
545cc85d 2681
5d3a0e79 2682 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
2683 if dash_manifest_url:
2a9c6dcd 2684 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
5d3a0e79 2685 itag = f['format_id']
2686 if itag in itags:
2687 continue
11f9be09 2688 if itag:
2689 itags.append(itag)
2a9c6dcd 2690 f['quality'] = guess_quality(f)
5d3a0e79 2691 filesize = int_or_none(self._search_regex(
2692 r'/clen/(\d+)', f.get('fragment_base_url')
2693 or f['url'], 'file size', default=None))
2694 if filesize:
2695 f['filesize'] = filesize
11f9be09 2696 yield f
2697
2698 def _real_extract(self, url):
2699 url, smuggled_data = unsmuggle_url(url, {})
2700 video_id = self._match_id(url)
2701
2702 base_url = self.http_scheme() + '//www.youtube.com/'
2703 webpage_url = base_url + 'watch?v=' + video_id
2704 webpage = self._download_webpage(
2705 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
2706
2707 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
2708 player_url = self._extract_player_url(master_ytcfg, webpage)
2709 identity_token = self._extract_identity_token(webpage, video_id)
2710
2711 player_responses = list(self._extract_player_responses(
2712 self._get_requested_clients(url, smuggled_data),
2713 video_id, webpage, master_ytcfg, player_url, identity_token))
2714
352d63fd 2715 get_first = lambda obj, keys, **kwargs: traverse_obj(obj, (..., *variadic(keys)), **kwargs, get_all=False)
11f9be09 2716
2717 playability_statuses = traverse_obj(
2718 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
2719
2720 trailer_video_id = get_first(
2721 playability_statuses,
2722 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
2723 expected_type=str)
2724 if trailer_video_id:
2725 return self.url_result(
2726 trailer_video_id, self.ie_key(), trailer_video_id)
2727
2728 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
2729 if webpage else (lambda x: None))
2730
2731 video_details = traverse_obj(
2732 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
2733 microformats = traverse_obj(
2734 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
2735 expected_type=dict, default=[])
2736 video_title = (
2737 get_first(video_details, 'title')
2738 or self._get_text(microformats, (..., 'title'))
2739 or search_meta(['og:title', 'twitter:title', 'title']))
2740 video_description = get_first(video_details, 'shortDescription')
2741
2742 if not smuggled_data.get('force_singlefeed', False):
2743 if not self.get_param('noplaylist'):
2744 multifeed_metadata_list = get_first(
2745 player_responses,
2746 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
2747 expected_type=str)
2748 if multifeed_metadata_list:
2749 entries = []
2750 feed_ids = []
2751 for feed in multifeed_metadata_list.split(','):
2752 # Unquote should take place before split on comma (,) since textual
2753 # fields may contain comma as well (see
2754 # https://github.com/ytdl-org/youtube-dl/issues/8536)
2755 feed_data = compat_parse_qs(
2756 compat_urllib_parse_unquote_plus(feed))
2757
2758 def feed_entry(name):
2759 return try_get(
2760 feed_data, lambda x: x[name][0], compat_str)
2761
2762 feed_id = feed_entry('id')
2763 if not feed_id:
2764 continue
2765 feed_title = feed_entry('title')
2766 title = video_title
2767 if feed_title:
2768 title += ' (%s)' % feed_title
2769 entries.append({
2770 '_type': 'url_transparent',
2771 'ie_key': 'Youtube',
2772 'url': smuggle_url(
2773 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
2774 {'force_singlefeed': True}),
2775 'title': title,
2776 })
2777 feed_ids.append(feed_id)
2778 self.to_screen(
2779 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
2780 % (', '.join(feed_ids), video_id))
2781 return self.playlist_result(
2782 entries, video_id, video_title, video_description)
2783 else:
2784 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2785
7ea65411 2786 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
11f9be09 2787 is_live = get_first(video_details, 'isLive')
7ea65411 2788 if is_live is None:
2789 is_live = get_first(live_broadcast_details, 'isLiveNow')
11f9be09 2790
2791 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
2792 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
bf1317d2 2793
545cc85d 2794 if not formats:
11f9be09 2795 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 2796 self.report_drm(video_id)
11f9be09 2797 pemr = get_first(
2798 playability_statuses,
2799 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
2800 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
2801 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 2802 if subreason:
545cc85d 2803 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 2804 countries = get_first(microformats, 'availableCountries')
545cc85d 2805 if not countries:
2806 regions_allowed = search_meta('regionsAllowed')
2807 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 2808 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 2809 reason += f'. {subreason}'
545cc85d 2810 if reason:
b7da73eb 2811 self.raise_no_formats(reason, expected=True)
bf1317d2 2812
11f9be09 2813 for f in formats:
2a9c6dcd 2814 if '&c=WEB&' in f['url'] and '&ratebypass=yes&' not in f['url']: # throttled
11f9be09 2815 f['source_preference'] = -10
3619f78d 2816 # TODO: this method is not reliable
2817 f['format_note'] = format_field(f, 'format_note', '%s ') + '(maybe throttled)'
11f9be09 2818
2a9c6dcd 2819 # Source is given priority since formats that throttle are given lower source_preference
2820 # When throttling issue is fully fixed, remove this
2821 self._sort_formats(formats, ('quality', 'height', 'fps', 'source'))
bf1317d2 2822
11f9be09 2823 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 2824 if not keywords and webpage:
2825 keywords = [
2826 unescapeHTML(m.group('content'))
2827 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
2828 for keyword in keywords:
2829 if keyword.startswith('yt:stretch='):
201c1459 2830 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
2831 if mobj:
2832 # NB: float is intentional for forcing float division
2833 w, h = (float(v) for v in mobj.groups())
2834 if w > 0 and h > 0:
2835 ratio = w / h
2836 for f in formats:
2837 if f.get('vcodec') != 'none':
2838 f['stretched_ratio'] = ratio
2839 break
6449cd80 2840
545cc85d 2841 thumbnails = []
11f9be09 2842 thumbnail_dicts = traverse_obj(
2843 (video_details, microformats), (..., ..., 'thumbnail', 'thumbnails', ...),
2844 expected_type=dict, default=[])
2845 for thumbnail in thumbnail_dicts:
2846 thumbnail_url = thumbnail.get('url')
2847 if not thumbnail_url:
2848 continue
2849 # Sometimes youtube gives a wrong thumbnail URL. See:
2850 # https://github.com/yt-dlp/yt-dlp/issues/233
2851 # https://github.com/ytdl-org/youtube-dl/issues/28023
2852 if 'maxresdefault' in thumbnail_url:
2853 thumbnail_url = thumbnail_url.split('?')[0]
2854 thumbnails.append({
2855 'url': thumbnail_url,
2856 'height': int_or_none(thumbnail.get('height')),
2857 'width': int_or_none(thumbnail.get('width')),
2858 })
ff2751ac 2859 thumbnail_url = search_meta(['og:image', 'twitter:image'])
2860 if thumbnail_url:
2861 thumbnails.append({
2862 'url': thumbnail_url,
ff2751ac 2863 })
0ba692ac 2864 # The best resolution thumbnails sometimes does not appear in the webpage
2865 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 2866 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
2867 hq_thumbnail_names = ['maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3']
245524e6 2868 # TODO: Test them also? - For some videos, even these don't exist
cca80fe6 2869 guaranteed_thumbnail_names = [
2870 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
2871 'mqdefault', 'mq1', 'mq2', 'mq3',
2872 'default', '1', '2', '3'
2873 ]
2874 thumbnail_names = hq_thumbnail_names + guaranteed_thumbnail_names
2875 n_thumbnail_names = len(thumbnail_names)
2876
0ba692ac 2877 thumbnails.extend({
2878 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
2879 video_id=video_id, name=name, ext=ext,
2880 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 2881 '_test_url': name in hq_thumbnail_names,
2882 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 2883 for thumb in thumbnails:
cca80fe6 2884 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 2885 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 2886 self._remove_duplicate_formats(thumbnails)
545cc85d 2887
7ea65411 2888 category = get_first(microformats, 'category') or search_meta('genre')
2889 channel_id = str_or_none(
2890 get_first(video_details, 'channelId')
2891 or get_first(microformats, 'externalChannelId')
2892 or search_meta('channelId'))
2893 duration = int_or_none(
2894 get_first(video_details, 'lengthSeconds')
2895 or get_first(microformats, 'lengthSeconds')
2896 or parse_duration(search_meta('duration'))) or None
2897 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
2898
2899 live_content = get_first(video_details, 'isLiveContent')
2900 is_upcoming = get_first(video_details, 'isUpcoming')
2901 if is_live is None:
2902 if is_upcoming or live_content is False:
2903 is_live = False
2904 if is_upcoming is None and (live_content or is_live):
2905 is_upcoming = False
2906 live_starttime = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
2907 live_endtime = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
2908 if not duration and live_endtime and live_starttime:
2909 duration = live_endtime - live_starttime
2910
545cc85d 2911 info = {
2912 'id': video_id,
2913 'title': self._live_title(video_title) if is_live else video_title,
2914 'formats': formats,
2915 'thumbnails': thumbnails,
2916 'description': video_description,
2917 'upload_date': unified_strdate(
11f9be09 2918 get_first(microformats, 'uploadDate')
545cc85d 2919 or search_meta('uploadDate')),
11f9be09 2920 'uploader': get_first(video_details, 'author'),
545cc85d 2921 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
2922 'uploader_url': owner_profile_url,
2923 'channel_id': channel_id,
11f9be09 2924 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
545cc85d 2925 'duration': duration,
2926 'view_count': int_or_none(
11f9be09 2927 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 2928 or search_meta('interactionCount')),
11f9be09 2929 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 2930 'age_limit': 18 if (
11f9be09 2931 get_first(microformats, 'isFamilySafe') is False
545cc85d 2932 or search_meta('isFamilyFriendly') == 'false'
2933 or search_meta('og:restrictions:age') == '18+') else 0,
2934 'webpage_url': webpage_url,
2935 'categories': [category] if category else None,
2936 'tags': keywords,
11f9be09 2937 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 2938 'is_live': is_live,
2939 'was_live': (False if is_live or is_upcoming or live_content is False
2940 else None if is_live is None or is_upcoming is None
2941 else live_content),
2942 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
2943 'release_timestamp': live_starttime,
545cc85d 2944 }
b477fc13 2945
3944e7af 2946 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
2947 # Converted into dicts to remove duplicates
2948 captions = {
2949 sub.get('baseUrl'): sub
2950 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
2951 translation_languages = {
2952 lang.get('languageCode'): lang.get('languageName')
2953 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
545cc85d 2954 subtitles = {}
2955 if pctr:
774d79cc 2956 def process_language(container, base_url, lang_code, sub_name, query):
120916da 2957 lang_subs = container.setdefault(lang_code, [])
545cc85d 2958 for fmt in self._SUBTITLE_FORMATS:
2959 query.update({
2960 'fmt': fmt,
2961 })
2962 lang_subs.append({
2963 'ext': fmt,
2964 'url': update_url_query(base_url, query),
774d79cc 2965 'name': sub_name,
545cc85d 2966 })
7e72694b 2967
3944e7af 2968 for base_url, caption_track in captions.items():
545cc85d 2969 if not base_url:
2970 continue
2971 if caption_track.get('kind') != 'asr':
120916da 2972 lang_code = (
2973 remove_start(caption_track.get('vssId') or '', '.').replace('.', '-')
2974 or caption_track.get('languageCode'))
545cc85d 2975 if not lang_code:
2976 continue
2977 process_language(
774d79cc 2978 subtitles, base_url, lang_code,
3944e7af 2979 traverse_obj(caption_track, ('name', 'simpleText')),
774d79cc 2980 {})
545cc85d 2981 continue
2982 automatic_captions = {}
3944e7af 2983 for trans_code, trans_name in translation_languages.items():
2984 if not trans_code:
545cc85d 2985 continue
2986 process_language(
3944e7af 2987 automatic_captions, base_url, trans_code,
2988 self._get_text(trans_name, max_runs=1),
2989 {'tlang': trans_code})
545cc85d 2990 info['automatic_captions'] = automatic_captions
2991 info['subtitles'] = subtitles
7e72694b 2992
545cc85d 2993 parsed_url = compat_urllib_parse_urlparse(url)
2994 for component in [parsed_url.fragment, parsed_url.query]:
2995 query = compat_parse_qs(component)
2996 for k, v in query.items():
2997 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
2998 d_k += '_time'
2999 if d_k not in info and k in s_ks:
3000 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3001
3002 # Youtube Music Auto-generated description
822b9d9c 3003 if video_description:
38d70284 3004 mobj = re.search(r'(?s)(?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?.+\nAuto-generated by YouTube\.\s*$', video_description)
822b9d9c 3005 if mobj:
822b9d9c
RA
3006 release_year = mobj.group('release_year')
3007 release_date = mobj.group('release_date')
3008 if release_date:
3009 release_date = release_date.replace('-', '')
3010 if not release_year:
545cc85d 3011 release_year = release_date[:4]
3012 info.update({
3013 'album': mobj.group('album'.strip()),
3014 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3015 'track': mobj.group('track').strip(),
3016 'release_date': release_date,
cc2db878 3017 'release_year': int_or_none(release_year),
545cc85d 3018 })
7e72694b 3019
545cc85d 3020 initial_data = None
3021 if webpage:
3022 initial_data = self._extract_yt_initial_variable(
3023 webpage, self._YT_INITIAL_DATA_RE, video_id,
3024 'yt initial data')
3025 if not initial_data:
11f9be09 3026 headers = self.generate_api_headers(
3027 master_ytcfg, identity_token, self._extract_account_syncid(master_ytcfg),
3028 session_index=self._extract_session_index(master_ytcfg))
3029
109dd3b2 3030 initial_data = self._extract_response(
3031 item_id=video_id, ep='next', fatal=False,
11f9be09 3032 ytcfg=master_ytcfg, headers=headers, query={'videoId': video_id},
109dd3b2 3033 note='Downloading initial data API JSON')
545cc85d 3034
c60ee3a2 3035 try:
3036 # This will error if there is no livechat
3037 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3038 info['subtitles']['live_chat'] = [{
3039 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3040 'video_id': video_id,
3041 'ext': 'json',
f6745c49 3042 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3043 }]
3044 except (KeyError, IndexError, TypeError):
3045 pass
545cc85d 3046
3047 if initial_data:
7c365c21 3048 info['chapters'] = (
3049 self._extract_chapters_from_json(initial_data, duration)
3050 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3051 or None)
545cc85d 3052
3053 contents = try_get(
3054 initial_data,
3055 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
3056 list) or []
3057 for content in contents:
3058 vpir = content.get('videoPrimaryInfoRenderer')
3059 if vpir:
3060 stl = vpir.get('superTitleLink')
3061 if stl:
fe93e2c4 3062 stl = self._get_text(stl)
545cc85d 3063 if try_get(
3064 vpir,
3065 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3066 info['location'] = stl
3067 else:
3068 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3069 if mobj:
3070 info.update({
3071 'series': mobj.group(1),
3072 'season_number': int(mobj.group(2)),
3073 'episode_number': int(mobj.group(3)),
3074 })
3075 for tlb in (try_get(
3076 vpir,
3077 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3078 list) or []):
3079 tbr = tlb.get('toggleButtonRenderer') or {}
3080 for getter, regex in [(
3081 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3082 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3083 lambda x: x['accessibility'],
3084 lambda x: x['accessibilityData']['accessibilityData'],
3085 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3086 label = (try_get(tbr, getter, dict) or {}).get('label')
3087 if label:
3088 mobj = re.match(regex, label)
3089 if mobj:
3090 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3091 break
3092 sbr_tooltip = try_get(
3093 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3094 if sbr_tooltip:
3095 like_count, dislike_count = sbr_tooltip.split(' / ')
3096 info.update({
3097 'like_count': str_to_int(like_count),
3098 'dislike_count': str_to_int(dislike_count),
3099 })
3100 vsir = content.get('videoSecondaryInfoRenderer')
3101 if vsir:
052e1350 3102 info['channel'] = self._get_text(vsir, ('owner', 'videoOwnerRenderer', 'title'))
545cc85d 3103 rows = try_get(
3104 vsir,
3105 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3106 list) or []
3107 multiple_songs = False
3108 for row in rows:
3109 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3110 multiple_songs = True
3111 break
3112 for row in rows:
3113 mrr = row.get('metadataRowRenderer') or {}
3114 mrr_title = mrr.get('title')
3115 if not mrr_title:
3116 continue
052e1350 3117 mrr_title = self._get_text(mrr, 'title')
3118 mrr_contents_text = self._get_text(mrr, ('contents', 0))
545cc85d 3119 if mrr_title == 'License':
3120 info['license'] = mrr_contents_text
3121 elif not multiple_songs:
3122 if mrr_title == 'Album':
3123 info['album'] = mrr_contents_text
3124 elif mrr_title == 'Artist':
3125 info['artist'] = mrr_contents_text
3126 elif mrr_title == 'Song':
3127 info['track'] = mrr_contents_text
3128
3129 fallbacks = {
3130 'channel': 'uploader',
3131 'channel_id': 'uploader_id',
3132 'channel_url': 'uploader_url',
3133 }
3134 for to, frm in fallbacks.items():
3135 if not info.get(to):
3136 info[to] = info.get(frm)
3137
3138 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3139 v = info.get(s_k)
3140 if v:
3141 info[d_k] = v
b84071c0 3142
11f9be09 3143 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3144 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3145 is_membersonly = None
b28f8d24 3146 is_premium = None
c224251a
M
3147 if initial_data and is_private is not None:
3148 is_membersonly = False
b28f8d24 3149 is_premium = False
47193e02 3150 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3151 badge_labels = set()
3152 for content in contents:
3153 if not isinstance(content, dict):
3154 continue
3155 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3156 for badge_label in badge_labels:
3157 if badge_label.lower() == 'members only':
3158 is_membersonly = True
3159 elif badge_label.lower() == 'premium':
3160 is_premium = True
3161 elif badge_label.lower() == 'unlisted':
3162 is_unlisted = True
c224251a 3163
c224251a
M
3164 info['availability'] = self._availability(
3165 is_private=is_private,
b28f8d24 3166 needs_premium=is_premium,
c224251a
M
3167 needs_subscription=is_membersonly,
3168 needs_auth=info['age_limit'] >= 18,
3169 is_unlisted=None if is_private is None else is_unlisted)
3170
06167fbb 3171 # get xsrf for annotations or comments
a06916d9 3172 get_annotations = self.get_param('writeannotations', False)
3173 get_comments = self.get_param('getcomments', False)
06167fbb 3174 if get_annotations or get_comments:
29f7c58a 3175 xsrf_token = None
11f9be09 3176 if master_ytcfg:
3177 xsrf_token = try_get(master_ytcfg, lambda x: x['XSRF_TOKEN'], compat_str)
29f7c58a 3178 if not xsrf_token:
3179 xsrf_token = self._search_regex(
3180 r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>(?:(?!\2).)+)\2',
8a784c74 3181 webpage, 'xsrf token', group='xsrf_token', fatal=False)
06167fbb 3182
3183 # annotations
06167fbb 3184 if get_annotations:
11f9be09 3185 invideo_url = get_first(
3186 player_responses,
3187 ('annotations', 0, 'playerAnnotationsUrlsRenderer', 'invideoUrl'),
3188 expected_type=str)
64b6a4e9 3189 if xsrf_token and invideo_url:
29f7c58a 3190 xsrf_field_name = None
11f9be09 3191 if master_ytcfg:
3192 xsrf_field_name = try_get(master_ytcfg, lambda x: x['XSRF_FIELD_NAME'], compat_str)
29f7c58a 3193 if not xsrf_field_name:
3194 xsrf_field_name = self._search_regex(
3195 r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2',
8a784c74 3196 webpage, 'xsrf field name',
29f7c58a 3197 group='xsrf_field_name', default='session_token')
8a784c74 3198 info['annotations'] = self._download_webpage(
64b6a4e9
RA
3199 self._proto_relative_url(invideo_url),
3200 video_id, note='Downloading annotations',
3201 errnote='Unable to download video annotations', fatal=False,
3202 data=urlencode_postdata({xsrf_field_name: xsrf_token}))
7e72694b 3203
277d6ff5 3204 if get_comments:
11f9be09 3205 info['__post_extractor'] = lambda: self._extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3206
11f9be09 3207 self.mark_watched(video_id, player_responses)
d77ab8e2 3208
545cc85d 3209 return info
c5e8d7af 3210
5f6a1245 3211
8bdd16b4 3212class YoutubeTabIE(YoutubeBaseInfoExtractor):
3213 IE_DESC = 'YouTube.com tab'
70d5c17b 3214 _VALID_URL = r'''(?x)
3215 https?://
3216 (?:\w+\.)?
3217 (?:
3218 youtube(?:kids)?\.com|
3219 invidio\.us
3220 )/
3221 (?:
fe03a6cd 3222 (?P<channel_type>channel|c|user|browse)/|
70d5c17b 3223 (?P<not_channel>
9ba5705a 3224 feed/|hashtag/|
70d5c17b 3225 (?:playlist|watch)\?.*?\blist=
3226 )|
29f7c58a 3227 (?!(?:%s)\b) # Direct URLs
70d5c17b 3228 )
3229 (?P<id>[^/?\#&]+)
3230 ''' % YoutubeBaseInfoExtractor._RESERVED_NAMES
8bdd16b4 3231 IE_NAME = 'youtube:tab'
3232
81127aa5 3233 _TESTS = [{
da692b79 3234 'note': 'playlists, multipage',
8bdd16b4 3235 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
3236 'playlist_mincount': 94,
3237 'info_dict': {
3238 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
3239 'title': 'Игорь Клейнер - Playlists',
3240 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
deaec5af 3241 'uploader': 'Игорь Клейнер',
3242 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
8bdd16b4 3243 },
3244 }, {
da692b79 3245 'note': 'playlists, multipage, different order',
8bdd16b4 3246 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
3247 'playlist_mincount': 94,
3248 'info_dict': {
3249 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
3250 'title': 'Игорь Клейнер - Playlists',
3251 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
deaec5af 3252 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
3253 'uploader': 'Игорь Клейнер',
8bdd16b4 3254 },
201c1459 3255 }, {
da692b79 3256 'note': 'playlists, series',
201c1459 3257 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
3258 'playlist_mincount': 5,
3259 'info_dict': {
3260 'id': 'UCYO_jab_esuFRV4b17AJtAw',
3261 'title': '3Blue1Brown - Playlists',
3262 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
da692b79 3263 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
3264 'uploader': '3Blue1Brown',
201c1459 3265 },
8bdd16b4 3266 }, {
da692b79 3267 'note': 'playlists, singlepage',
8bdd16b4 3268 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
3269 'playlist_mincount': 4,
3270 'info_dict': {
3271 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
3272 'title': 'ThirstForScience - Playlists',
3273 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
deaec5af 3274 'uploader': 'ThirstForScience',
3275 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
8bdd16b4 3276 }
3277 }, {
3278 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
3279 'only_matching': True,
3280 }, {
da692b79 3281 'note': 'basic, single video playlist',
0e30a7b9 3282 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
81127aa5 3283 'info_dict': {
0e30a7b9 3284 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
3285 'uploader': 'Sergey M.',
3286 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
3867038a 3287 'title': 'youtube-dl public playlist',
81127aa5 3288 },
0e30a7b9 3289 'playlist_count': 1,
9291475f 3290 }, {
da692b79 3291 'note': 'empty playlist',
0e30a7b9 3292 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
9291475f 3293 'info_dict': {
0e30a7b9 3294 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
3295 'uploader': 'Sergey M.',
3296 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
3867038a 3297 'title': 'youtube-dl empty playlist',
9291475f
PH
3298 },
3299 'playlist_count': 0,
3300 }, {
da692b79 3301 'note': 'Home tab',
8bdd16b4 3302 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
9291475f 3303 'info_dict': {
8bdd16b4 3304 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3305 'title': 'lex will - Home',
3306 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3307 'uploader': 'lex will',
3308 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
9291475f 3309 },
8bdd16b4 3310 'playlist_mincount': 2,
9291475f 3311 }, {
da692b79 3312 'note': 'Videos tab',
8bdd16b4 3313 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
9291475f 3314 'info_dict': {
8bdd16b4 3315 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3316 'title': 'lex will - Videos',
3317 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3318 'uploader': 'lex will',
3319 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
9291475f 3320 },
8bdd16b4 3321 'playlist_mincount': 975,
9291475f 3322 }, {
da692b79 3323 'note': 'Videos tab, sorted by popular',
8bdd16b4 3324 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
9291475f 3325 'info_dict': {
8bdd16b4 3326 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3327 'title': 'lex will - Videos',
3328 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3329 'uploader': 'lex will',
3330 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
9291475f 3331 },
8bdd16b4 3332 'playlist_mincount': 199,
9291475f 3333 }, {
da692b79 3334 'note': 'Playlists tab',
8bdd16b4 3335 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
9291475f 3336 'info_dict': {
8bdd16b4 3337 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3338 'title': 'lex will - Playlists',
3339 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3340 'uploader': 'lex will',
3341 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
9291475f 3342 },
8bdd16b4 3343 'playlist_mincount': 17,
ac7553d0 3344 }, {
da692b79 3345 'note': 'Community tab',
8bdd16b4 3346 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
ac7553d0 3347 'info_dict': {
8bdd16b4 3348 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3349 'title': 'lex will - Community',
3350 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3351 'uploader': 'lex will',
3352 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
8bdd16b4 3353 },
3354 'playlist_mincount': 18,
87dadd45 3355 }, {
da692b79 3356 'note': 'Channels tab',
8bdd16b4 3357 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
87dadd45 3358 'info_dict': {
8bdd16b4 3359 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3360 'title': 'lex will - Channels',
3361 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3362 'uploader': 'lex will',
3363 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
8bdd16b4 3364 },
deaec5af 3365 'playlist_mincount': 12,
cd684175 3366 }, {
3367 'note': 'Search tab',
3368 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
3369 'playlist_mincount': 40,
3370 'info_dict': {
3371 'id': 'UCYO_jab_esuFRV4b17AJtAw',
3372 'title': '3Blue1Brown - Search - linear algebra',
3373 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
3374 'uploader': '3Blue1Brown',
3375 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
3376 },
6b08cdf6 3377 }, {
a0566bbf 3378 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
8bdd16b4 3379 'only_matching': True,
3380 }, {
a0566bbf 3381 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
8bdd16b4 3382 'only_matching': True,
3383 }, {
a0566bbf 3384 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
8bdd16b4 3385 'only_matching': True,
3386 }, {
3387 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
3388 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
3389 'info_dict': {
3390 'title': '29C3: Not my department',
3391 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
3392 'uploader': 'Christiaan008',
3393 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
deaec5af 3394 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
8bdd16b4 3395 },
3396 'playlist_count': 96,
3397 }, {
3398 'note': 'Large playlist',
3399 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
6b08cdf6 3400 'info_dict': {
8bdd16b4 3401 'title': 'Uploads from Cauchemar',
3402 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
3403 'uploader': 'Cauchemar',
3404 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
13a75688 3405 },
8bdd16b4 3406 'playlist_mincount': 1123,
3407 }, {
da692b79 3408 'note': 'even larger playlist, 8832 videos',
8bdd16b4 3409 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
3410 'only_matching': True,
4b7df0d3
JMF
3411 }, {
3412 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
3413 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
3414 'info_dict': {
acf757f4
PH
3415 'title': 'Uploads from Interstellar Movie',
3416 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
13a75688 3417 'uploader': 'Interstellar Movie',
8bdd16b4 3418 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4b7df0d3 3419 },
481cc733 3420 'playlist_mincount': 21,
358de58c 3421 }, {
3422 'note': 'Playlist with "show unavailable videos" button',
3423 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
3424 'info_dict': {
3425 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
3426 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
3427 'uploader': 'Phim Siêu Nhân Nhật Bản',
3428 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
3429 },
da692b79 3430 'playlist_mincount': 200,
5d342002 3431 }, {
da692b79 3432 'note': 'Playlist with unavailable videos in page 7',
5d342002 3433 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
3434 'info_dict': {
3435 'title': 'Uploads from BlankTV',
3436 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
3437 'uploader': 'BlankTV',
3438 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
3439 },
da692b79 3440 'playlist_mincount': 1000,
8bdd16b4 3441 }, {
da692b79 3442 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
8bdd16b4 3443 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
3444 'info_dict': {
3445 'title': 'Data Analysis with Dr Mike Pound',
3446 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
3447 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
3448 'uploader': 'Computerphile',
deaec5af 3449 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
8bdd16b4 3450 },
3451 'playlist_mincount': 11,
3452 }, {
a0566bbf 3453 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
8bdd16b4 3454 'only_matching': True,
dacb3a86 3455 }, {
da692b79 3456 'note': 'Playlist URL that does not actually serve a playlist',
dacb3a86
S
3457 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
3458 'info_dict': {
3459 'id': 'FqZTN594JQw',
3460 'ext': 'webm',
3461 'title': "Smiley's People 01 detective, Adventure Series, Action",
3462 'uploader': 'STREEM',
3463 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
ec85ded8 3464 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
dacb3a86
S
3465 'upload_date': '20150526',
3466 'license': 'Standard YouTube License',
3467 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
3468 'categories': ['People & Blogs'],
3469 'tags': list,
dbdaaa23 3470 'view_count': int,
dacb3a86
S
3471 'like_count': int,
3472 'dislike_count': int,
3473 },
3474 'params': {
3475 'skip_download': True,
3476 },
13a75688 3477 'skip': 'This video is not available.',
dacb3a86 3478 'add_ie': [YoutubeIE.ie_key()],
481cc733 3479 }, {
8bdd16b4 3480 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
c0345b82 3481 'only_matching': True,
66b48727 3482 }, {
8bdd16b4 3483 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
66b48727 3484 'only_matching': True,
a0566bbf 3485 }, {
3486 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
3487 'info_dict': {
57015a4a 3488 'id': '3yImotZU3tw', # This will keep changing
a0566bbf 3489 'ext': 'mp4',
deaec5af 3490 'title': compat_str,
a0566bbf 3491 'uploader': 'Sky News',
3492 'uploader_id': 'skynews',
3493 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
da692b79 3494 'upload_date': r're:\d{8}',
3495 'description': compat_str,
a0566bbf 3496 'categories': ['News & Politics'],
3497 'tags': list,
3498 'like_count': int,
3499 'dislike_count': int,
3500 },
3501 'params': {
3502 'skip_download': True,
3503 },
da692b79 3504 'expected_warnings': ['Downloading just video ', 'Ignoring subtitle tracks found in '],
a0566bbf 3505 }, {
3506 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
3507 'info_dict': {
3508 'id': 'a48o2S1cPoo',
3509 'ext': 'mp4',
3510 'title': 'The Young Turks - Live Main Show',
3511 'uploader': 'The Young Turks',
3512 'uploader_id': 'TheYoungTurks',
3513 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
3514 'upload_date': '20150715',
3515 'license': 'Standard YouTube License',
3516 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
3517 'categories': ['News & Politics'],
3518 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
3519 'like_count': int,
3520 'dislike_count': int,
3521 },
3522 'params': {
3523 'skip_download': True,
3524 },
3525 'only_matching': True,
3526 }, {
3527 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
3528 'only_matching': True,
3529 }, {
3530 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
3531 'only_matching': True,
09f1580e 3532 }, {
3533 'note': 'A channel that is not live. Should raise error',
3534 'url': 'https://www.youtube.com/user/numberphile/live',
3535 'only_matching': True,
3d3dddc9 3536 }, {
3537 'url': 'https://www.youtube.com/feed/trending',
3538 'only_matching': True,
3539 }, {
3d3dddc9 3540 'url': 'https://www.youtube.com/feed/library',
3541 'only_matching': True,
3542 }, {
3d3dddc9 3543 'url': 'https://www.youtube.com/feed/history',
3544 'only_matching': True,
3545 }, {
3d3dddc9 3546 'url': 'https://www.youtube.com/feed/subscriptions',
3547 'only_matching': True,
3548 }, {
3d3dddc9 3549 'url': 'https://www.youtube.com/feed/watch_later',
3550 'only_matching': True,
3551 }, {
da692b79 3552 'note': 'Recommended - redirects to home page',
3d3dddc9 3553 'url': 'https://www.youtube.com/feed/recommended',
3554 'only_matching': True,
29f7c58a 3555 }, {
da692b79 3556 'note': 'inline playlist with not always working continuations',
29f7c58a 3557 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
3558 'only_matching': True,
3559 }, {
3560 'url': 'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8',
3561 'only_matching': True,
3562 }, {
3563 'url': 'https://www.youtube.com/course',
3564 'only_matching': True,
3565 }, {
3566 'url': 'https://www.youtube.com/zsecurity',
3567 'only_matching': True,
3568 }, {
3569 'url': 'http://www.youtube.com/NASAgovVideo/videos',
3570 'only_matching': True,
3571 }, {
3572 'url': 'https://www.youtube.com/TheYoungTurks/live',
3573 'only_matching': True,
39ed931e 3574 }, {
3575 'url': 'https://www.youtube.com/hashtag/cctv9',
3576 'info_dict': {
3577 'id': 'cctv9',
3578 'title': '#cctv9',
3579 },
3580 'playlist_mincount': 350,
201c1459 3581 }, {
3582 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
3583 'only_matching': True,
9297939e 3584 }, {
da692b79 3585 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
9297939e 3586 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3587 'only_matching': True
fe03a6cd 3588 }, {
3589 'note': '/browse/ should redirect to /channel/',
3590 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
3591 'only_matching': True
3592 }, {
3593 'note': 'VLPL, should redirect to playlist?list=PL...',
3594 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3595 'info_dict': {
3596 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3597 'uploader': 'NoCopyrightSounds',
3598 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
3599 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
3600 'title': 'NCS Releases',
3601 },
3602 'playlist_mincount': 166,
18db7548 3603 }, {
3604 'note': 'Topic, should redirect to playlist?list=UU...',
3605 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
3606 'info_dict': {
3607 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
3608 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
3609 'title': 'Uploads from Royalty Free Music - Topic',
3610 'uploader': 'Royalty Free Music - Topic',
3611 },
3612 'expected_warnings': [
3613 'A channel/user page was given',
3614 'The URL does not have a videos tab',
3615 ],
3616 'playlist_mincount': 101,
3617 }, {
3618 'note': 'Topic without a UU playlist',
3619 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
3620 'info_dict': {
3621 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
3622 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
3623 },
3624 'expected_warnings': [
3625 'A channel/user page was given',
3626 'The URL does not have a videos tab',
3627 'Falling back to channel URL',
3628 ],
3629 'playlist_mincount': 9,
abcdd12b 3630 }, {
3631 'note': 'Youtube music Album',
3632 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
3633 'info_dict': {
3634 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
3635 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
3636 },
3637 'playlist_count': 50,
47193e02 3638 }, {
3639 'note': 'unlisted single video playlist',
3640 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
3641 'info_dict': {
3642 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
3643 'uploader': 'colethedj',
3644 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
3645 'title': 'yt-dlp unlisted playlist test',
3646 'availability': 'unlisted'
3647 },
3648 'playlist_count': 1,
29f7c58a 3649 }]
3650
3651 @classmethod
3652 def suitable(cls, url):
3653 return False if YoutubeIE.suitable(url) else super(
3654 YoutubeTabIE, cls).suitable(url)
8bdd16b4 3655
3656 def _extract_channel_id(self, webpage):
3657 channel_id = self._html_search_meta(
3658 'channelId', webpage, 'channel id', default=None)
3659 if channel_id:
3660 return channel_id
3661 channel_url = self._html_search_meta(
3662 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3663 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3664 'twitter:app:url:googleplay'), webpage, 'channel url')
3665 return self._search_regex(
3666 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3667 channel_url, 'channel id')
15f6397c 3668
8bdd16b4 3669 @staticmethod
cd7c66cf 3670 def _extract_basic_item_renderer(item):
3671 # Modified from _extract_grid_item_renderer
201c1459 3672 known_basic_renderers = (
3673 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
cd7c66cf 3674 )
3675 for key, renderer in item.items():
201c1459 3676 if not isinstance(renderer, dict):
cd7c66cf 3677 continue
201c1459 3678 elif key in known_basic_renderers:
3679 return renderer
3680 elif key.startswith('grid') and key.endswith('Renderer'):
3681 return renderer
8bdd16b4 3682
8bdd16b4 3683 def _grid_entries(self, grid_renderer):
3684 for item in grid_renderer['items']:
3685 if not isinstance(item, dict):
39b62db1 3686 continue
cd7c66cf 3687 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3688 if not isinstance(renderer, dict):
3689 continue
052e1350 3690 title = self._get_text(renderer, 'title')
fe93e2c4 3691
8bdd16b4 3692 # playlist
3693 playlist_id = renderer.get('playlistId')
3694 if playlist_id:
3695 yield self.url_result(
3696 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3697 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3698 video_title=title)
201c1459 3699 continue
8bdd16b4 3700 # video
3701 video_id = renderer.get('videoId')
3702 if video_id:
3703 yield self._extract_video(renderer)
201c1459 3704 continue
8bdd16b4 3705 # channel
3706 channel_id = renderer.get('channelId')
3707 if channel_id:
8bdd16b4 3708 yield self.url_result(
3709 'https://www.youtube.com/channel/%s' % channel_id,
3710 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3711 continue
3712 # generic endpoint URL support
3713 ep_url = urljoin('https://www.youtube.com/', try_get(
3714 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3715 compat_str))
3716 if ep_url:
3717 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3718 if ie.suitable(ep_url):
3719 yield self.url_result(
3720 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3721 break
8bdd16b4 3722
3d3dddc9 3723 def _shelf_entries_from_content(self, shelf_renderer):
3724 content = shelf_renderer.get('content')
3725 if not isinstance(content, dict):
8bdd16b4 3726 return
cd7c66cf 3727 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3728 if renderer:
3729 # TODO: add support for nested playlists so each shelf is processed
3730 # as separate playlist
3731 # TODO: this includes only first N items
3732 for entry in self._grid_entries(renderer):
3733 yield entry
3734 renderer = content.get('horizontalListRenderer')
3735 if renderer:
3736 # TODO
3737 pass
8bdd16b4 3738
29f7c58a 3739 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3740 ep = try_get(
3741 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3742 compat_str)
3743 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3744 if shelf_url:
29f7c58a 3745 # Skipping links to another channels, note that checking for
3746 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3747 # will not work
3748 if skip_channels and '/channels?' in shelf_url:
3749 return
052e1350 3750 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 3751 yield self.url_result(shelf_url, video_title=title)
3752 # Shelf may not contain shelf URL, fallback to extraction from content
3753 for entry in self._shelf_entries_from_content(shelf_renderer):
3754 yield entry
c5e8d7af 3755
8bdd16b4 3756 def _playlist_entries(self, video_list_renderer):
3757 for content in video_list_renderer['contents']:
3758 if not isinstance(content, dict):
3759 continue
3760 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3761 if not isinstance(renderer, dict):
3762 continue
3763 video_id = renderer.get('videoId')
3764 if not video_id:
3765 continue
3766 yield self._extract_video(renderer)
07aeced6 3767
3462ffa8 3768 def _rich_entries(self, rich_grid_renderer):
3769 renderer = try_get(
70d5c17b 3770 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 3771 video_id = renderer.get('videoId')
3772 if not video_id:
3773 return
3774 yield self._extract_video(renderer)
3775
8bdd16b4 3776 def _video_entry(self, video_renderer):
3777 video_id = video_renderer.get('videoId')
3778 if video_id:
3779 return self._extract_video(video_renderer)
dacb3a86 3780
8bdd16b4 3781 def _post_thread_entries(self, post_thread_renderer):
3782 post_renderer = try_get(
3783 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3784 if not post_renderer:
3785 return
3786 # video attachment
3787 video_renderer = try_get(
895b0931 3788 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3789 video_id = video_renderer.get('videoId')
3790 if video_id:
3791 entry = self._extract_video(video_renderer)
8bdd16b4 3792 if entry:
3793 yield entry
895b0931 3794 # playlist attachment
3795 playlist_id = try_get(
3796 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3797 if playlist_id:
3798 yield self.url_result(
e28f1c0a 3799 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3800 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 3801 # inline video links
3802 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3803 for run in runs:
3804 if not isinstance(run, dict):
3805 continue
3806 ep_url = try_get(
3807 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3808 if not ep_url:
3809 continue
3810 if not YoutubeIE.suitable(ep_url):
3811 continue
3812 ep_video_id = YoutubeIE._match_id(ep_url)
3813 if video_id == ep_video_id:
3814 continue
895b0931 3815 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 3816
8bdd16b4 3817 def _post_thread_continuation_entries(self, post_thread_continuation):
3818 contents = post_thread_continuation.get('contents')
3819 if not isinstance(contents, list):
3820 return
3821 for content in contents:
3822 renderer = content.get('backstagePostThreadRenderer')
3823 if not isinstance(renderer, dict):
3824 continue
3825 for entry in self._post_thread_entries(renderer):
3826 yield entry
07aeced6 3827
39ed931e 3828 r''' # unused
3829 def _rich_grid_entries(self, contents):
3830 for content in contents:
3831 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3832 if video_renderer:
3833 entry = self._video_entry(video_renderer)
3834 if entry:
3835 yield entry
3836 '''
f4f751af 3837 def _entries(self, tab, item_id, identity_token, account_syncid, ytcfg):
3462ffa8 3838
70d5c17b 3839 def extract_entries(parent_renderer): # this needs to called again for continuation to work with feeds
3840 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3841 for content in contents:
3842 if not isinstance(content, dict):
8bdd16b4 3843 continue
70d5c17b 3844 is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict)
3462ffa8 3845 if not is_renderer:
70d5c17b 3846 renderer = content.get('richItemRenderer')
3462ffa8 3847 if renderer:
3848 for entry in self._rich_entries(renderer):
3849 yield entry
3850 continuation_list[0] = self._extract_continuation(parent_renderer)
8bdd16b4 3851 continue
3462ffa8 3852 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3853 for isr_content in isr_contents:
3854 if not isinstance(isr_content, dict):
3855 continue
69184e41 3856
3857 known_renderers = {
3858 'playlistVideoListRenderer': self._playlist_entries,
3859 'gridRenderer': self._grid_entries,
3860 'shelfRenderer': lambda x: self._shelf_entries(x, tab.get('title') != 'Channels'),
3861 'backstagePostThreadRenderer': self._post_thread_entries,
3862 'videoRenderer': lambda x: [self._video_entry(x)],
3863 }
3864 for key, renderer in isr_content.items():
3865 if key not in known_renderers:
3866 continue
3867 for entry in known_renderers[key](renderer):
3868 if entry:
3869 yield entry
3462ffa8 3870 continuation_list[0] = self._extract_continuation(renderer)
69184e41 3871 break
70d5c17b 3872
3462ffa8 3873 if not continuation_list[0]:
3874 continuation_list[0] = self._extract_continuation(is_renderer)
70d5c17b 3875
3876 if not continuation_list[0]:
3877 continuation_list[0] = self._extract_continuation(parent_renderer)
3462ffa8 3878
3879 continuation_list = [None] # Python 2 doesnot support nonlocal
29f7c58a 3880 tab_content = try_get(tab, lambda x: x['content'], dict)
3881 if not tab_content:
3882 return
3462ffa8 3883 parent_renderer = (
29f7c58a 3884 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3885 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
70d5c17b 3886 for entry in extract_entries(parent_renderer):
3887 yield entry
3462ffa8 3888 continuation = continuation_list[0]
fe93e2c4 3889 visitor_data = None
d069eca7 3890
8bdd16b4 3891 for page_num in itertools.count(1):
3892 if not continuation:
3893 break
11f9be09 3894 headers = self.generate_api_headers(ytcfg, identity_token, account_syncid, visitor_data)
79360d99 3895 response = self._extract_response(
3896 item_id='%s page %s' % (item_id, page_num),
fe93e2c4 3897 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 3898 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
3899
3900 if not response:
8bdd16b4 3901 break
f4f751af 3902 visitor_data = try_get(
3903 response, lambda x: x['responseContext']['visitorData'], compat_str) or visitor_data
ebf1b291 3904
69184e41 3905 known_continuation_renderers = {
3906 'playlistVideoListContinuation': self._playlist_entries,
3907 'gridContinuation': self._grid_entries,
3908 'itemSectionContinuation': self._post_thread_continuation_entries,
3909 'sectionListContinuation': extract_entries, # for feeds
3910 }
8bdd16b4 3911 continuation_contents = try_get(
69184e41 3912 response, lambda x: x['continuationContents'], dict) or {}
3913 continuation_renderer = None
3914 for key, value in continuation_contents.items():
3915 if key not in known_continuation_renderers:
3462ffa8 3916 continue
69184e41 3917 continuation_renderer = value
3918 continuation_list = [None]
3919 for entry in known_continuation_renderers[key](continuation_renderer):
3920 yield entry
3921 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3922 break
3923 if continuation_renderer:
3924 continue
c5e8d7af 3925
a1b535bd 3926 known_renderers = {
3927 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3928 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 3929 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 3930 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 3931 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 3932 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 3933 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 3934 }
cce889b9 3935 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 3936 continuation_items = try_get(
cce889b9 3937 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 3938 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3939 video_items_renderer = None
3940 for key, value in continuation_item.items():
3941 if key not in known_renderers:
8bdd16b4 3942 continue
a1b535bd 3943 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 3944 continuation_list = [None]
a1b535bd 3945 for entry in known_renderers[key][0](video_items_renderer):
3946 yield entry
9ba5705a 3947 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 3948 break
3949 if video_items_renderer:
3950 continue
8bdd16b4 3951 break
9558dcec 3952
8bdd16b4 3953 @staticmethod
3954 def _extract_selected_tab(tabs):
3955 for tab in tabs:
cd684175 3956 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
3957 if renderer.get('selected') is True:
3958 return renderer
2b3c2546 3959 else:
8bdd16b4 3960 raise ExtractorError('Unable to find selected tab')
b82f815f 3961
47193e02 3962 @classmethod
3963 def _extract_uploader(cls, data):
8bdd16b4 3964 uploader = {}
47193e02 3965 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
3966 owner = try_get(
3967 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3968 if owner:
3969 uploader['uploader'] = owner.get('text')
3970 uploader['uploader_id'] = try_get(
3971 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3972 uploader['uploader_url'] = urljoin(
3973 'https://www.youtube.com/',
3974 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 3975 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 3976
d069eca7 3977 def _extract_from_tabs(self, item_id, webpage, data, tabs):
b60419c5 3978 playlist_id = title = description = channel_url = channel_name = channel_id = None
3979 thumbnails_list = tags = []
3980
8bdd16b4 3981 selected_tab = self._extract_selected_tab(tabs)
3982 renderer = try_get(
3983 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3984 if renderer:
b60419c5 3985 channel_name = renderer.get('title')
3986 channel_url = renderer.get('channelUrl')
3987 channel_id = renderer.get('externalId')
39ed931e 3988 else:
64c0d954 3989 renderer = try_get(
3990 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 3991
8bdd16b4 3992 if renderer:
3993 title = renderer.get('title')
ecc97af3 3994 description = renderer.get('description', '')
b60419c5 3995 playlist_id = channel_id
3996 tags = renderer.get('keywords', '').split()
3997 thumbnails_list = (
3998 try_get(renderer, lambda x: x['avatar']['thumbnails'], list)
ff84930c 3999 or try_get(
47193e02 4000 self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer'),
4001 lambda x: x['thumbnailRenderer']['playlistVideoThumbnailRenderer']['thumbnail']['thumbnails'],
ff84930c 4002 list)
b60419c5 4003 or [])
4004
4005 thumbnails = []
4006 for t in thumbnails_list:
4007 if not isinstance(t, dict):
4008 continue
4009 thumbnail_url = url_or_none(t.get('url'))
4010 if not thumbnail_url:
4011 continue
4012 thumbnails.append({
4013 'url': thumbnail_url,
4014 'width': int_or_none(t.get('width')),
4015 'height': int_or_none(t.get('height')),
4016 })
3462ffa8 4017 if playlist_id is None:
70d5c17b 4018 playlist_id = item_id
4019 if title is None:
39ed931e 4020 title = (
4021 try_get(data, lambda x: x['header']['hashtagHeaderRenderer']['hashtag']['simpleText'])
4022 or playlist_id)
b60419c5 4023 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4024 title += format_field(selected_tab, 'expandedText', ' - %s')
b60419c5 4025 metadata = {
4026 'playlist_id': playlist_id,
4027 'playlist_title': title,
4028 'playlist_description': description,
4029 'uploader': channel_name,
4030 'uploader_id': channel_id,
4031 'uploader_url': channel_url,
4032 'thumbnails': thumbnails,
4033 'tags': tags,
4034 }
47193e02 4035 availability = self._extract_availability(data)
4036 if availability:
4037 metadata['availability'] = availability
b60419c5 4038 if not channel_id:
4039 metadata.update(self._extract_uploader(data))
4040 metadata.update({
4041 'channel': metadata['uploader'],
4042 'channel_id': metadata['uploader_id'],
4043 'channel_url': metadata['uploader_url']})
11f9be09 4044 ytcfg = self.extract_ytcfg(item_id, webpage)
b60419c5 4045 return self.playlist_result(
d069eca7
M
4046 self._entries(
4047 selected_tab, playlist_id,
4048 self._extract_identity_token(webpage, item_id),
fe93e2c4 4049 self._extract_account_syncid(ytcfg, data), ytcfg),
b60419c5 4050 **metadata)
73c4ac2c 4051
79360d99 4052 def _extract_mix_playlist(self, playlist, playlist_id, data, webpage):
2be71994 4053 first_id = last_id = None
11f9be09 4054 ytcfg = self.extract_ytcfg(playlist_id, webpage)
4055 headers = self.generate_api_headers(
fe93e2c4 4056 ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4057 identity_token=self._extract_identity_token(webpage, item_id=playlist_id))
2be71994 4058 for page_num in itertools.count(1):
cd7c66cf 4059 videos = list(self._playlist_entries(playlist))
4060 if not videos:
4061 return
2be71994 4062 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4063 if start >= len(videos):
4064 return
4065 for video in videos[start:]:
4066 if video['id'] == first_id:
4067 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4068 return
4069 yield video
4070 first_id = first_id or videos[0]['id']
4071 last_id = videos[-1]['id']
79360d99 4072 watch_endpoint = try_get(
4073 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4074 query = {
4075 'playlistId': playlist_id,
4076 'videoId': watch_endpoint.get('videoId') or last_id,
4077 'index': watch_endpoint.get('index') or len(videos),
4078 'params': watch_endpoint.get('params') or 'OAE%3D'
4079 }
4080 response = self._extract_response(
4081 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4082 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4083 check_get_keys='contents'
4084 )
cd7c66cf 4085 playlist = try_get(
79360d99 4086 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4087
79360d99 4088 def _extract_from_playlist(self, item_id, url, data, playlist, webpage):
8bdd16b4 4089 title = playlist.get('title') or try_get(
4090 data, lambda x: x['titleText']['simpleText'], compat_str)
4091 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4092
4093 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4094 playlist_url = urljoin(url, try_get(
4095 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4096 compat_str))
4097 if playlist_url and playlist_url != url:
4098 return self.url_result(
4099 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4100 video_title=title)
cd7c66cf 4101
8bdd16b4 4102 return self.playlist_result(
79360d99 4103 self._extract_mix_playlist(playlist, playlist_id, data, webpage),
cd7c66cf 4104 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4105
47193e02 4106 def _extract_availability(self, data):
4107 """
4108 Gets the availability of a given playlist/tab.
4109 Note: Unless YouTube tells us explicitly, we do not assume it is public
4110 @param data: response
4111 """
4112 is_private = is_unlisted = None
4113 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4114 badge_labels = self._extract_badges(renderer)
4115
4116 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4117 privacy_dropdown_entries = try_get(
4118 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4119 for renderer_dict in privacy_dropdown_entries:
4120 is_selected = try_get(
4121 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4122 if not is_selected:
4123 continue
052e1350 4124 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4125 if label:
4126 badge_labels.add(label.lower())
4127 break
4128
4129 for badge_label in badge_labels:
4130 if badge_label == 'unlisted':
4131 is_unlisted = True
4132 elif badge_label == 'private':
4133 is_private = True
4134 elif badge_label == 'public':
4135 is_unlisted = is_private = False
4136 return self._availability(is_private, False, False, False, is_unlisted)
4137
4138 @staticmethod
4139 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4140 sidebar_renderer = try_get(
4141 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4142 for item in sidebar_renderer:
4143 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4144 if renderer:
4145 return renderer
4146
358de58c 4147 def _reload_with_unavailable_videos(self, item_id, data, webpage):
4148 """
4149 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4150 """
5d342002 4151 browse_id = params = None
47193e02 4152 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4153 if not renderer:
4154 return
4155 menu_renderer = try_get(
4156 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4157 for menu_item in menu_renderer:
4158 if not isinstance(menu_item, dict):
358de58c 4159 continue
47193e02 4160 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4161 text = try_get(
4162 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4163 if not text or text.lower() != 'show unavailable videos':
4164 continue
4165 browse_endpoint = try_get(
4166 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4167 browse_id = browse_endpoint.get('browseId')
4168 params = browse_endpoint.get('params')
4169 break
5d342002 4170
11f9be09 4171 ytcfg = self.extract_ytcfg(item_id, webpage)
4172 headers = self.generate_api_headers(
fe93e2c4 4173 ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
47193e02 4174 identity_token=self._extract_identity_token(webpage, item_id=item_id),
4175 visitor_data=try_get(
4176 self._extract_context(ytcfg), lambda x: x['client']['visitorData'], compat_str))
4177 query = {
4178 'params': params or 'wgYCCAA=',
4179 'browseId': browse_id or 'VL%s' % item_id
4180 }
4181 return self._extract_response(
4182 item_id=item_id, headers=headers, query=query,
fe93e2c4 4183 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4184 note='Downloading API JSON with unavailable videos')
358de58c 4185
cd7c66cf 4186 def _extract_webpage(self, url, item_id):
a06916d9 4187 retries = self.get_param('extractor_retries', 3)
62bff2c1 4188 count = -1
c705177d 4189 last_error = 'Incomplete yt initial data recieved'
14fdfea9 4190 while count < retries:
62bff2c1 4191 count += 1
14fdfea9 4192 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4193 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4194 if count:
c705177d 4195 self.report_warning('%s. Retrying ...' % last_error)
5ef7d9bd 4196 webpage = self._download_webpage(
4197 url, item_id,
cd7c66cf 4198 'Downloading webpage%s' % (' (retry #%d)' % count if count else ''))
11f9be09 4199 data = self.extract_yt_initial_data(item_id, webpage)
14fdfea9 4200 if data.get('contents') or data.get('currentVideoEndpoint'):
4201 break
95c01b6c 4202 # Extract alerts here only when there is error
4203 self._extract_and_report_alerts(data)
c705177d 4204 if count >= retries:
6a39ee13 4205 raise ExtractorError(last_error)
cd7c66cf 4206 return webpage, data
4207
9297939e 4208 @staticmethod
4209 def _smuggle_data(entries, data):
4210 for entry in entries:
4211 if data:
4212 entry['url'] = smuggle_url(entry['url'], data)
4213 yield entry
4214
cd7c66cf 4215 def _real_extract(self, url):
9297939e 4216 url, smuggled_data = unsmuggle_url(url, {})
4217 if self.is_music_url(url):
4218 smuggled_data['is_music_url'] = True
fe03a6cd 4219 info_dict = self.__real_extract(url, smuggled_data)
9297939e 4220 if info_dict.get('entries'):
4221 info_dict['entries'] = self._smuggle_data(info_dict['entries'], smuggled_data)
4222 return info_dict
4223
fe03a6cd 4224 _url_re = re.compile(r'(?P<pre>%s)(?(channel_type)(?P<tab>/\w+))?(?P<post>.*)$' % _VALID_URL)
4225
4226 def __real_extract(self, url, smuggled_data):
cd7c66cf 4227 item_id = self._match_id(url)
4228 url = compat_urlparse.urlunparse(
4229 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 4230 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 4231
fe03a6cd 4232 def get_mobj(url):
4233 mobj = self._url_re.match(url).groupdict()
07cce701 4234 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 4235 return mobj
4236
4237 mobj = get_mobj(url)
4238 # Youtube returns incomplete data if tabname is not lower case
4239 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
4240
4241 if is_channel:
4242 if smuggled_data.get('is_music_url'):
4243 if item_id[:2] == 'VL':
4244 # Youtube music VL channels have an equivalent playlist
4245 item_id = item_id[2:]
4246 pre, tab, post, is_channel = 'https://www.youtube.com/playlist?list=%s' % item_id, '', '', False
abcdd12b 4247 elif item_id[:2] == 'MP':
4248 # Youtube music albums (/channel/MP...) have a OLAK playlist that can be extracted from the webpage
4249 item_id = self._search_regex(
4250 r'\\x22audioPlaylistId\\x22:\\x22([0-9A-Za-z_-]+)\\x22',
4251 self._download_webpage('https://music.youtube.com/channel/%s' % item_id, item_id),
4252 'playlist id')
4253 pre, tab, post, is_channel = 'https://www.youtube.com/playlist?list=%s' % item_id, '', '', False
fe03a6cd 4254 elif mobj['channel_type'] == 'browse':
4255 # Youtube music /browse/ should be changed to /channel/
4256 pre = 'https://www.youtube.com/channel/%s' % item_id
4257 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
4258 # Home URLs should redirect to /videos/
6a39ee13 4259 self.report_warning(
cd7c66cf 4260 'A channel/user page was given. All the channel\'s videos will be downloaded. '
4261 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 4262 tab = '/videos'
4263
4264 url = ''.join((pre, tab, post))
4265 mobj = get_mobj(url)
cd7c66cf 4266
4267 # Handle both video/playlist URLs
201c1459 4268 qs = parse_qs(url)
cd7c66cf 4269 video_id = qs.get('v', [None])[0]
4270 playlist_id = qs.get('list', [None])[0]
4271
fe03a6cd 4272 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 4273 if not playlist_id:
fe03a6cd 4274 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 4275 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 4276 # Common mistake: https://www.youtube.com/watch?list=playlist_id
6a39ee13 4277 self.report_warning('A video URL was given without video ID. Trying to download playlist %s' % playlist_id)
cd7c66cf 4278 url = 'https://www.youtube.com/playlist?list=%s' % playlist_id
18db7548 4279 mobj = get_mobj(url)
cd7c66cf 4280
4281 if video_id and playlist_id:
a06916d9 4282 if self.get_param('noplaylist'):
cd7c66cf 4283 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
4284 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
4285 self.to_screen('Downloading playlist %s; add --no-playlist to just download video %s' % (playlist_id, video_id))
4286
4287 webpage, data = self._extract_webpage(url, item_id)
14fdfea9 4288
18db7548 4289 tabs = try_get(
4290 data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
4291 if tabs:
4292 selected_tab = self._extract_selected_tab(tabs)
4293 tab_name = selected_tab.get('title', '')
09f1580e 4294 if 'no-youtube-channel-redirect' not in compat_opts:
4295 if mobj['tab'] == '/live':
4296 # Live tab should have redirected to the video
4297 raise ExtractorError('The channel is not currently live', expected=True)
4298 if mobj['tab'] == '/videos' and tab_name.lower() != mobj['tab'][1:]:
4299 if not mobj['not_channel'] and item_id[:2] == 'UC':
4300 # Topic channels don't have /videos. Use the equivalent playlist instead
4301 self.report_warning('The URL does not have a %s tab. Trying to redirect to playlist UU%s instead' % (mobj['tab'][1:], item_id[2:]))
4302 pl_id = 'UU%s' % item_id[2:]
4303 pl_url = 'https://www.youtube.com/playlist?list=%s%s' % (pl_id, mobj['post'])
4304 try:
4305 pl_webpage, pl_data = self._extract_webpage(pl_url, pl_id)
4306 for alert_type, alert_message in self._extract_alerts(pl_data):
4307 if alert_type == 'error':
4308 raise ExtractorError('Youtube said: %s' % alert_message)
4309 item_id, url, webpage, data = pl_id, pl_url, pl_webpage, pl_data
4310 except ExtractorError:
4311 self.report_warning('The playlist gave error. Falling back to channel URL')
4312 else:
4313 self.report_warning('The URL does not have a %s tab. %s is being downloaded instead' % (mobj['tab'][1:], tab_name))
18db7548 4314
4315 self.write_debug('Final URL: %s' % url)
4316
358de58c 4317 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 4318 if 'no-youtube-unavailable-videos' not in compat_opts:
4319 data = self._reload_with_unavailable_videos(item_id, data, webpage) or data
95c01b6c 4320 self._extract_and_report_alerts(data)
8bdd16b4 4321 tabs = try_get(
4322 data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
4323 if tabs:
d069eca7 4324 return self._extract_from_tabs(item_id, webpage, data, tabs)
cd7c66cf 4325
8bdd16b4 4326 playlist = try_get(
4327 data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4328 if playlist:
79360d99 4329 return self._extract_from_playlist(item_id, url, data, playlist, webpage)
cd7c66cf 4330
a0566bbf 4331 video_id = try_get(
4332 data, lambda x: x['currentVideoEndpoint']['watchEndpoint']['videoId'],
4333 compat_str) or video_id
8bdd16b4 4334 if video_id:
09f1580e 4335 if mobj['tab'] != '/live': # live tab is expected to redirect to video
4336 self.report_warning('Unable to recognize playlist. Downloading just video %s' % video_id)
8bdd16b4 4337 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 4338
8bdd16b4 4339 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 4340
c5e8d7af 4341
8bdd16b4 4342class YoutubePlaylistIE(InfoExtractor):
4343 IE_DESC = 'YouTube.com playlists'
4344 _VALID_URL = r'''(?x)(?:
4345 (?:https?://)?
4346 (?:\w+\.)?
4347 (?:
4348 (?:
4349 youtube(?:kids)?\.com|
29f7c58a 4350 invidio\.us
8bdd16b4 4351 )
4352 /.*?\?.*?\blist=
4353 )?
4354 (?P<id>%(playlist_id)s)
4355 )''' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
4356 IE_NAME = 'youtube:playlist'
cdc628a4 4357 _TESTS = [{
8bdd16b4 4358 'note': 'issue #673',
4359 'url': 'PLBB231211A4F62143',
cdc628a4 4360 'info_dict': {
8bdd16b4 4361 'title': '[OLD]Team Fortress 2 (Class-based LP)',
4362 'id': 'PLBB231211A4F62143',
4363 'uploader': 'Wickydoo',
4364 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 4365 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
8bdd16b4 4366 },
4367 'playlist_mincount': 29,
4368 }, {
4369 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
4370 'info_dict': {
4371 'title': 'YDL_safe_search',
4372 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
4373 },
4374 'playlist_count': 2,
4375 'skip': 'This playlist is private',
9558dcec 4376 }, {
8bdd16b4 4377 'note': 'embedded',
4378 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
4379 'playlist_count': 4,
9558dcec 4380 'info_dict': {
8bdd16b4 4381 'title': 'JODA15',
4382 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
4383 'uploader': 'milan',
4384 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
9558dcec 4385 }
cdc628a4 4386 }, {
8bdd16b4 4387 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 4388 'playlist_mincount': 654,
8bdd16b4 4389 'info_dict': {
4390 'title': '2018 Chinese New Singles (11/6 updated)',
4391 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
4392 'uploader': 'LBK',
4393 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 4394 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
8bdd16b4 4395 }
daa0df9e 4396 }, {
29f7c58a 4397 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
4398 'only_matching': True,
4399 }, {
4400 # music album playlist
4401 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
4402 'only_matching': True,
4403 }]
4404
4405 @classmethod
4406 def suitable(cls, url):
201c1459 4407 if YoutubeTabIE.suitable(url):
4408 return False
1bdae7d3 4409 # Hack for lazy extractors until more generic solution is implemented
4410 # (see #28780)
4411 from .youtube import parse_qs
201c1459 4412 qs = parse_qs(url)
4413 if qs.get('v', [None])[0]:
4414 return False
4415 return super(YoutubePlaylistIE, cls).suitable(url)
29f7c58a 4416
4417 def _real_extract(self, url):
4418 playlist_id = self._match_id(url)
46953e7e 4419 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 4420 url = update_url_query(
4421 'https://www.youtube.com/playlist',
4422 parse_qs(url) or {'list': playlist_id})
4423 if is_music_url:
4424 url = smuggle_url(url, {'is_music_url': True})
4425 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 4426
4427
4428class YoutubeYtBeIE(InfoExtractor):
c76eb41b 4429 IE_DESC = 'youtu.be'
29f7c58a 4430 _VALID_URL = r'https?://youtu\.be/(?P<id>[0-9A-Za-z_-]{11})/*?.*?\blist=(?P<playlist_id>%(playlist_id)s)' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
4431 _TESTS = [{
8bdd16b4 4432 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
4433 'info_dict': {
4434 'id': 'yeWKywCrFtk',
4435 'ext': 'mp4',
4436 'title': 'Small Scale Baler and Braiding Rugs',
4437 'uploader': 'Backus-Page House Museum',
4438 'uploader_id': 'backuspagemuseum',
4439 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
4440 'upload_date': '20161008',
4441 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
4442 'categories': ['Nonprofits & Activism'],
4443 'tags': list,
4444 'like_count': int,
4445 'dislike_count': int,
4446 },
4447 'params': {
4448 'noplaylist': True,
4449 'skip_download': True,
4450 },
39e7107d 4451 }, {
8bdd16b4 4452 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 4453 'only_matching': True,
cdc628a4
PH
4454 }]
4455
8bdd16b4 4456 def _real_extract(self, url):
5ad28e7f 4457 mobj = self._match_valid_url(url)
29f7c58a 4458 video_id = mobj.group('id')
4459 playlist_id = mobj.group('playlist_id')
8bdd16b4 4460 return self.url_result(
29f7c58a 4461 update_url_query('https://www.youtube.com/watch', {
4462 'v': video_id,
4463 'list': playlist_id,
4464 'feature': 'youtu.be',
4465 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4466
4467
4468class YoutubeYtUserIE(InfoExtractor):
c76eb41b 4469 IE_DESC = 'YouTube.com user videos, URL or "ytuser" keyword'
8bdd16b4 4470 _VALID_URL = r'ytuser:(?P<id>.+)'
4471 _TESTS = [{
4472 'url': 'ytuser:phihag',
4473 'only_matching': True,
4474 }]
4475
4476 def _real_extract(self, url):
4477 user_id = self._match_id(url)
4478 return self.url_result(
4479 'https://www.youtube.com/user/%s' % user_id,
4480 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 4481
b05654f0 4482
3d3dddc9 4483class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 4484 IE_NAME = 'youtube:favorites'
4485 IE_DESC = 'YouTube.com liked videos, ":ytfav" for short (requires authentication)'
4486 _VALID_URL = r':ytfav(?:ou?rite)?s?'
4487 _LOGIN_REQUIRED = True
4488 _TESTS = [{
4489 'url': ':ytfav',
4490 'only_matching': True,
4491 }, {
4492 'url': ':ytfavorites',
4493 'only_matching': True,
4494 }]
4495
4496 def _real_extract(self, url):
4497 return self.url_result(
4498 'https://www.youtube.com/playlist?list=LL',
4499 ie=YoutubeTabIE.ie_key())
4500
4501
79360d99 4502class YoutubeSearchIE(SearchInfoExtractor, YoutubeTabIE):
69184e41 4503 IE_DESC = 'YouTube.com searches, "ytsearch" keyword'
b4c08069
JMF
4504 # there doesn't appear to be a real limit, for example if you search for
4505 # 'python' you get more than 8.000.000 results
4506 _MAX_RESULTS = float('inf')
78caa52a 4507 IE_NAME = 'youtube:search'
b05654f0 4508 _SEARCH_KEY = 'ytsearch'
6c894ea1 4509 _SEARCH_PARAMS = None
9dd8e46a 4510 _TESTS = []
b05654f0 4511
6c894ea1 4512 def _entries(self, query, n):
a5c56234 4513 data = {'query': query}
6c894ea1
U
4514 if self._SEARCH_PARAMS:
4515 data['params'] = self._SEARCH_PARAMS
4516 total = 0
fe93e2c4 4517 continuation = {}
6c894ea1 4518 for page_num in itertools.count(1):
fe93e2c4 4519 data.update(continuation)
79360d99 4520 search = self._extract_response(
4521 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
4522 check_get_keys=('contents', 'onResponseReceivedCommands')
4523 )
6c894ea1 4524 if not search:
b4c08069 4525 break
6c894ea1
U
4526 slr_contents = try_get(
4527 search,
4528 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
4529 lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
4530 list)
4531 if not slr_contents:
a22b2fd1 4532 break
0366ae87 4533
0366ae87
M
4534 # Youtube sometimes adds promoted content to searches,
4535 # changing the index location of videos and token.
4536 # So we search through all entries till we find them.
fe93e2c4 4537 continuation = None
30a074c2 4538 for slr_content in slr_contents:
fe93e2c4 4539 if not continuation:
4540 continuation = self._extract_continuation({'contents': [slr_content]})
a96c6d15 4541
30a074c2 4542 isr_contents = try_get(
4543 slr_content,
4544 lambda x: x['itemSectionRenderer']['contents'],
4545 list)
9da76d30 4546 if not isr_contents:
30a074c2 4547 continue
4548 for content in isr_contents:
4549 if not isinstance(content, dict):
4550 continue
4551 video = content.get('videoRenderer')
4552 if not isinstance(video, dict):
4553 continue
4554 video_id = video.get('videoId')
4555 if not video_id:
4556 continue
4557
4558 yield self._extract_video(video)
4559 total += 1
4560 if total == n:
4561 return
0366ae87 4562
fe93e2c4 4563 if not continuation:
6c894ea1 4564 break
b05654f0 4565
6c894ea1
U
4566 def _get_n_results(self, query, n):
4567 """Get a specified number of results for a query"""
11f9be09 4568 return self.playlist_result(self._entries(query, n), query, query)
75dff0ee 4569
c9ae7b95 4570
a3dd9248 4571class YoutubeSearchDateIE(YoutubeSearchIE):
cb7fb546 4572 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 4573 _SEARCH_KEY = 'ytsearchdate'
c76eb41b 4574 IE_DESC = 'YouTube.com searches, newest videos first, "ytsearchdate" keyword'
6c894ea1 4575 _SEARCH_PARAMS = 'CAI%3D'
75dff0ee 4576
c9ae7b95 4577
386e1dd9 4578class YoutubeSearchURLIE(YoutubeSearchIE):
69184e41 4579 IE_DESC = 'YouTube.com search URLs'
386e1dd9 4580 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
4581 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
ef2f3c7f 4582 # _MAX_RESULTS = 100
3462ffa8 4583 _TESTS = [{
4584 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
4585 'playlist_mincount': 5,
4586 'info_dict': {
11f9be09 4587 'id': 'youtube-dl test video',
3462ffa8 4588 'title': 'youtube-dl test video',
4589 }
4590 }, {
4591 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
4592 'only_matching': True,
4593 }]
4594
386e1dd9 4595 @classmethod
4596 def _make_valid_url(cls):
4597 return cls._VALID_URL
4598
3462ffa8 4599 def _real_extract(self, url):
4dfbf869 4600 qs = parse_qs(url)
386e1dd9 4601 query = (qs.get('search_query') or qs.get('q'))[0]
4602 self._SEARCH_PARAMS = qs.get('sp', ('',))[0]
4603 return self._get_n_results(query, self._MAX_RESULTS)
3462ffa8 4604
4605
4606class YoutubeFeedsInfoExtractor(YoutubeTabIE):
d7ae0639 4607 """
25f14e9f 4608 Base class for feed extractors
3d3dddc9 4609 Subclasses must define the _FEED_NAME property.
d7ae0639 4610 """
b2e8bc1b 4611 _LOGIN_REQUIRED = True
ef2f3c7f 4612 _TESTS = []
d7ae0639
JMF
4613
4614 @property
4615 def IE_NAME(self):
78caa52a 4616 return 'youtube:%s' % self._FEED_NAME
04cc9617 4617
3853309f 4618 def _real_extract(self, url):
3d3dddc9 4619 return self.url_result(
4620 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
4621 ie=YoutubeTabIE.ie_key())
25f14e9f
S
4622
4623
ef2f3c7f 4624class YoutubeWatchLaterIE(InfoExtractor):
4625 IE_NAME = 'youtube:watchlater'
70d5c17b 4626 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
3d3dddc9 4627 _VALID_URL = r':ytwatchlater'
bc7a9cd8 4628 _TESTS = [{
8bdd16b4 4629 'url': ':ytwatchlater',
bc7a9cd8
S
4630 'only_matching': True,
4631 }]
25f14e9f
S
4632
4633 def _real_extract(self, url):
ef2f3c7f 4634 return self.url_result(
4635 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 4636
4637
25f14e9f
S
4638class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
4639 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
3d3dddc9 4640 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 4641 _FEED_NAME = 'recommended'
45db527f 4642 _LOGIN_REQUIRED = False
3d3dddc9 4643 _TESTS = [{
4644 'url': ':ytrec',
4645 'only_matching': True,
4646 }, {
4647 'url': ':ytrecommended',
4648 'only_matching': True,
4649 }, {
4650 'url': 'https://youtube.com',
4651 'only_matching': True,
4652 }]
1ed5b5c9 4653
1ed5b5c9 4654
25f14e9f 4655class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
70d5c17b 4656 IE_DESC = 'YouTube.com subscriptions feed, ":ytsubs" for short (requires authentication)'
3d3dddc9 4657 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 4658 _FEED_NAME = 'subscriptions'
3d3dddc9 4659 _TESTS = [{
4660 'url': ':ytsubs',
4661 'only_matching': True,
4662 }, {
4663 'url': ':ytsubscriptions',
4664 'only_matching': True,
4665 }]
1ed5b5c9 4666
1ed5b5c9 4667
25f14e9f 4668class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
a5c56234
M
4669 IE_DESC = 'Youtube watch history, ":ythis" for short (requires authentication)'
4670 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 4671 _FEED_NAME = 'history'
3d3dddc9 4672 _TESTS = [{
4673 'url': ':ythistory',
4674 'only_matching': True,
4675 }]
1ed5b5c9
JMF
4676
4677
15870e90
PH
4678class YoutubeTruncatedURLIE(InfoExtractor):
4679 IE_NAME = 'youtube:truncated_url'
4680 IE_DESC = False # Do not list
975d35db 4681 _VALID_URL = r'''(?x)
b95aab84
PH
4682 (?:https?://)?
4683 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
4684 (?:watch\?(?:
c4808c60 4685 feature=[a-z_]+|
b95aab84
PH
4686 annotation_id=annotation_[^&]+|
4687 x-yt-cl=[0-9]+|
c1708b89 4688 hl=[^&]*|
287be8c6 4689 t=[0-9]+
b95aab84
PH
4690 )?
4691 |
4692 attribution_link\?a=[^&]+
4693 )
4694 $
975d35db 4695 '''
15870e90 4696
c4808c60 4697 _TESTS = [{
2d3d2997 4698 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 4699 'only_matching': True,
dc2fc736 4700 }, {
2d3d2997 4701 'url': 'https://www.youtube.com/watch?',
dc2fc736 4702 'only_matching': True,
b95aab84
PH
4703 }, {
4704 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
4705 'only_matching': True,
4706 }, {
4707 'url': 'https://www.youtube.com/watch?feature=foo',
4708 'only_matching': True,
c1708b89
PH
4709 }, {
4710 'url': 'https://www.youtube.com/watch?hl=en-GB',
4711 'only_matching': True,
287be8c6
PH
4712 }, {
4713 'url': 'https://www.youtube.com/watch?t=2372',
4714 'only_matching': True,
c4808c60
PH
4715 }]
4716
15870e90
PH
4717 def _real_extract(self, url):
4718 raise ExtractorError(
78caa52a
PH
4719 'Did you forget to quote the URL? Remember that & is a meta '
4720 'character in most shells, so you want to put the URL in quotes, '
3867038a 4721 'like youtube-dl '
2d3d2997 4722 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 4723 ' or simply youtube-dl BaW_jenozKc .',
15870e90 4724 expected=True)
772fd5cc
PH
4725
4726
4727class YoutubeTruncatedIDIE(InfoExtractor):
4728 IE_NAME = 'youtube:truncated_id'
4729 IE_DESC = False # Do not list
b95aab84 4730 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
4731
4732 _TESTS = [{
4733 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
4734 'only_matching': True,
4735 }]
4736
4737 def _real_extract(self, url):
4738 video_id = self._match_id(url)
4739 raise ExtractorError(
4740 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
4741 expected=True)