]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[youtube] Add `player_client=all`
[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,
94278f72 41 mimetype2ext,
9c0d7f49 42 network_exceptions,
11f9be09 43 orderedSet,
6310acf5 44 parse_codecs,
49bd8c66 45 parse_count,
7c80519c 46 parse_duration,
7ea65411 47 parse_iso8601,
dca3ff4a 48 qualities,
3995d37d 49 remove_start,
cf7e015f 50 smuggle_url,
dbdaaa23 51 str_or_none,
c93d53f5 52 str_to_int,
7c365c21 53 traverse_obj,
556dbe7f 54 try_get,
c5e8d7af
PH
55 unescapeHTML,
56 unified_strdate,
cf7e015f 57 unsmuggle_url,
8bdd16b4 58 update_url_query,
21c340b8 59 url_or_none,
6e6bc8da 60 urlencode_postdata,
fe93e2c4 61 urljoin,
7c365c21 62 variadic,
c5e8d7af
PH
63)
64
5f6a1245 65
201c1459 66def parse_qs(url):
67 return compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
68
69
de7f3446 70class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b
JMF
71 """Provide base functions for Youtube extractors"""
72 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
9303ce3e 73 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
e00eb564
S
74
75 _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup'
3995d37d
S
76 _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge'
77 _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
e00eb564 78
3462ffa8 79 _RESERVED_NAMES = (
bea74222 80 r'channel|c|user|browse|playlist|watch|w|v|embed|e|watch_popup|shorts|'
46953e7e 81 r'movies|results|shared|hashtag|trending|feed|feeds|oembed|get_video_info|'
cd7c66cf 82 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 83
b2e8bc1b
JMF
84 _NETRC_MACHINE = 'youtube'
85 # If True it will raise an error if no login info is provided
86 _LOGIN_REQUIRED = False
87
70d5c17b 88 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
d0ba5587 89
b2e8bc1b 90 def _login(self):
83317f69 91 """
92 Attempt to log in to YouTube.
93 True is returned if successful or skipped.
94 False is returned if login failed.
95
96 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
97 """
9d5d4d64 98
99 def warn(message):
100 self.report_warning(message)
101
102 # username+password login is broken
982ee69a
MB
103 if (self._LOGIN_REQUIRED
104 and self.get_param('cookiefile') is None
105 and self.get_param('cookiesfrombrowser') is None):
9d5d4d64 106 self.raise_login_required(
107 'Login details are needed to download this content', method='cookies')
68217024 108 username, password = self._get_login_info()
9d5d4d64 109 if username:
110 warn('Logging in using username and password is broken. %s' % self._LOGIN_HINTS['cookies'])
111 return
9d5d4d64 112
2d6659b9 113 # Everything below this is broken!
114 r'''
b2e8bc1b
JMF
115 # No authentication to be performed
116 if username is None:
a06916d9 117 if self._LOGIN_REQUIRED and self.get_param('cookiefile') is None:
69ea8ca4 118 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
a06916d9 119 # if self.get_param('cookiefile'): # TODO remove 'and False' later - too many people using outdated cookies and open issues, remind them.
545cc85d 120 # self.to_screen('[Cookies] Reminder - Make sure to always use up to date cookies!')
83317f69 121 return True
b2e8bc1b 122
7cc3570e
PH
123 login_page = self._download_webpage(
124 self._LOGIN_URL, None,
69ea8ca4
PH
125 note='Downloading login page',
126 errnote='unable to fetch login page', fatal=False)
7cc3570e
PH
127 if login_page is False:
128 return
b2e8bc1b 129
1212e997 130 login_form = self._hidden_inputs(login_page)
c5e8d7af 131
e00eb564
S
132 def req(url, f_req, note, errnote):
133 data = login_form.copy()
134 data.update({
135 'pstMsg': 1,
136 'checkConnection': 'youtube',
137 'checkedDomains': 'youtube',
138 'hl': 'en',
139 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
3995d37d 140 'f.req': json.dumps(f_req),
e00eb564
S
141 'flowName': 'GlifWebSignIn',
142 'flowEntry': 'ServiceLogin',
baf67a60
S
143 # TODO: reverse actual botguard identifier generation algo
144 'bgRequest': '["identifier",""]',
041bc3ad 145 })
e00eb564
S
146 return self._download_json(
147 url, None, note=note, errnote=errnote,
148 transform_source=lambda s: re.sub(r'^[^[]*', '', s),
149 fatal=False,
150 data=urlencode_postdata(data), headers={
151 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
152 'Google-Accounts-XSRF': 1,
153 })
154
3995d37d
S
155 lookup_req = [
156 username,
157 None, [], None, 'US', None, None, 2, False, True,
158 [
159 None, None,
160 [2, 1, None, 1,
161 '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',
162 None, [], 4],
163 1, [None, None, []], None, None, None, True
164 ],
165 username,
166 ]
167
e00eb564 168 lookup_results = req(
3995d37d 169 self._LOOKUP_URL, lookup_req,
e00eb564
S
170 'Looking up account info', 'Unable to look up account info')
171
172 if lookup_results is False:
173 return False
041bc3ad 174
3995d37d
S
175 user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
176 if not user_hash:
177 warn('Unable to extract user hash')
178 return False
179
180 challenge_req = [
181 user_hash,
182 None, 1, None, [1, None, None, None, [password, None, True]],
183 [
184 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],
185 1, [None, None, []], None, None, None, True
186 ]]
83317f69 187
3995d37d
S
188 challenge_results = req(
189 self._CHALLENGE_URL, challenge_req,
190 'Logging in', 'Unable to log in')
83317f69 191
3995d37d 192 if challenge_results is False:
e00eb564 193 return
83317f69 194
3995d37d
S
195 login_res = try_get(challenge_results, lambda x: x[0][5], list)
196 if login_res:
197 login_msg = try_get(login_res, lambda x: x[5], compat_str)
198 warn(
199 'Unable to login: %s' % 'Invalid password'
200 if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
201 return False
202
203 res = try_get(challenge_results, lambda x: x[0][-1], list)
204 if not res:
205 warn('Unable to extract result entry')
206 return False
207
9a6628aa
S
208 login_challenge = try_get(res, lambda x: x[0][0], list)
209 if login_challenge:
210 challenge_str = try_get(login_challenge, lambda x: x[2], compat_str)
211 if challenge_str == 'TWO_STEP_VERIFICATION':
3995d37d
S
212 # SEND_SUCCESS - TFA code has been successfully sent to phone
213 # QUOTA_EXCEEDED - reached the limit of TFA codes
9a6628aa 214 status = try_get(login_challenge, lambda x: x[5], compat_str)
3995d37d
S
215 if status == 'QUOTA_EXCEEDED':
216 warn('Exceeded the limit of TFA codes, try later')
217 return False
218
219 tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
220 if not tl:
221 warn('Unable to extract TL')
222 return False
223
224 tfa_code = self._get_tfa_info('2-step verification code')
225
226 if not tfa_code:
227 warn(
228 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
229 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
230 return False
231
232 tfa_code = remove_start(tfa_code, 'G-')
233
234 tfa_req = [
235 user_hash, None, 2, None,
236 [
237 9, None, None, None, None, None, None, None,
238 [None, tfa_code, True, 2]
239 ]]
240
241 tfa_results = req(
242 self._TFA_URL.format(tl), tfa_req,
243 'Submitting TFA code', 'Unable to submit TFA code')
244
245 if tfa_results is False:
246 return False
247
248 tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
249 if tfa_res:
250 tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
251 warn(
252 'Unable to finish TFA: %s' % 'Invalid TFA code'
253 if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
254 return False
255
256 check_cookie_url = try_get(
257 tfa_results, lambda x: x[0][-1][2], compat_str)
9a6628aa
S
258 else:
259 CHALLENGES = {
260 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
261 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
262 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
263 }
264 challenge = CHALLENGES.get(
265 challenge_str,
266 '%s returned error %s.' % (self.IE_NAME, challenge_str))
267 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge)
268 return False
3995d37d
S
269 else:
270 check_cookie_url = try_get(res, lambda x: x[2], compat_str)
271
272 if not check_cookie_url:
273 warn('Unable to extract CheckCookie URL')
274 return False
e00eb564
S
275
276 check_cookie_results = self._download_webpage(
3995d37d
S
277 check_cookie_url, None, 'Checking cookie', fatal=False)
278
279 if check_cookie_results is False:
280 return False
e00eb564 281
3995d37d
S
282 if 'https://myaccount.google.com/' not in check_cookie_results:
283 warn('Unable to log in')
b2e8bc1b 284 return False
e00eb564 285
b2e8bc1b 286 return True
2d6659b9 287 '''
b2e8bc1b 288
cce889b9 289 def _initialize_consent(self):
290 cookies = self._get_cookies('https://www.youtube.com/')
291 if cookies.get('__Secure-3PSID'):
292 return
293 consent_id = None
294 consent = cookies.get('CONSENT')
295 if consent:
296 if 'YES' in consent.value:
297 return
298 consent_id = self._search_regex(
299 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
300 if not consent_id:
301 consent_id = random.randint(100, 999)
302 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 303
b2e8bc1b 304 def _real_initialize(self):
cce889b9 305 self._initialize_consent()
b2e8bc1b
JMF
306 if self._downloader is None:
307 return
b2e8bc1b
JMF
308 if not self._login():
309 return
c5e8d7af 310
a0566bbf 311 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
29f7c58a 312 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
313 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
a0566bbf 314
109dd3b2 315 _YT_DEFAULT_YTCFGS = {
316 'WEB': {
317 'INNERTUBE_API_VERSION': 'v1',
318 'INNERTUBE_CLIENT_NAME': 'WEB',
319 'INNERTUBE_CLIENT_VERSION': '2.20210622.10.00',
320 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
321 'INNERTUBE_CONTEXT': {
322 'client': {
323 'clientName': 'WEB',
324 'clientVersion': '2.20210622.10.00',
325 'hl': 'en',
326 }
327 },
328 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
329 },
330 'WEB_REMIX': {
331 'INNERTUBE_API_VERSION': 'v1',
332 'INNERTUBE_CLIENT_NAME': 'WEB_REMIX',
333 'INNERTUBE_CLIENT_VERSION': '1.20210621.00.00',
334 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
335 'INNERTUBE_CONTEXT': {
336 'client': {
337 'clientName': 'WEB_REMIX',
338 'clientVersion': '1.20210621.00.00',
339 'hl': 'en',
340 }
341 },
342 'INNERTUBE_CONTEXT_CLIENT_NAME': 67
343 },
344 'WEB_EMBEDDED_PLAYER': {
345 'INNERTUBE_API_VERSION': 'v1',
346 'INNERTUBE_CLIENT_NAME': 'WEB_EMBEDDED_PLAYER',
347 'INNERTUBE_CLIENT_VERSION': '1.20210620.0.1',
348 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
349 'INNERTUBE_CONTEXT': {
350 'client': {
351 'clientName': 'WEB_EMBEDDED_PLAYER',
352 'clientVersion': '1.20210620.0.1',
353 'hl': 'en',
354 }
355 },
356 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
357 },
358 'ANDROID': {
359 'INNERTUBE_API_VERSION': 'v1',
360 'INNERTUBE_CLIENT_NAME': 'ANDROID',
361 'INNERTUBE_CLIENT_VERSION': '16.20',
362 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
363 'INNERTUBE_CONTEXT': {
364 'client': {
365 'clientName': 'ANDROID',
366 'clientVersion': '16.20',
367 'hl': 'en',
368 }
369 },
fe93e2c4 370 'INNERTUBE_CONTEXT_CLIENT_NAME': 3
109dd3b2 371 },
372 'ANDROID_EMBEDDED_PLAYER': {
373 'INNERTUBE_API_VERSION': 'v1',
374 'INNERTUBE_CLIENT_NAME': 'ANDROID_EMBEDDED_PLAYER',
375 'INNERTUBE_CLIENT_VERSION': '16.20',
376 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
377 'INNERTUBE_CONTEXT': {
378 'client': {
379 'clientName': 'ANDROID_EMBEDDED_PLAYER',
380 'clientVersion': '16.20',
381 'hl': 'en',
382 }
383 },
fe93e2c4 384 'INNERTUBE_CONTEXT_CLIENT_NAME': 55
109dd3b2 385 },
386 'ANDROID_MUSIC': {
387 'INNERTUBE_API_VERSION': 'v1',
388 'INNERTUBE_CLIENT_NAME': 'ANDROID_MUSIC',
389 'INNERTUBE_CLIENT_VERSION': '4.32',
390 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
391 'INNERTUBE_CONTEXT': {
392 'client': {
393 'clientName': 'ANDROID_MUSIC',
394 'clientVersion': '4.32',
395 'hl': 'en',
396 }
397 },
fe93e2c4 398 'INNERTUBE_CONTEXT_CLIENT_NAME': 21
11f9be09 399 },
400 'IOS': {
401 'INNERTUBE_API_VERSION': 'v1',
402 'INNERTUBE_CLIENT_NAME': 'IOS',
403 'INNERTUBE_CLIENT_VERSION': '16.20',
404 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
405 'INNERTUBE_CONTEXT': {
406 'client': {
407 'clientName': 'IOS',
408 'clientVersion': '16.20',
409 'hl': 'en',
410 }
411 },
412 'INNERTUBE_CONTEXT_CLIENT_NAME': 5
413
414 },
415 'IOS_MUSIC': {
416 'INNERTUBE_API_VERSION': 'v1',
417 'INNERTUBE_CLIENT_NAME': 'IOS_MUSIC',
418 'INNERTUBE_CLIENT_VERSION': '4.32',
419 'INNERTUBE_API_KEY': 'AIzaSyDK3iBpDP9nHVTk2qL73FLJICfOC3c51Og',
420 'INNERTUBE_CONTEXT': {
421 'client': {
422 'clientName': 'IOS_MUSIC',
423 'clientVersion': '4.32',
424 'hl': 'en',
425 }
426 },
427 'INNERTUBE_CONTEXT_CLIENT_NAME': 26
428 },
429 'IOS_MESSAGES_EXTENSION': {
430 'INNERTUBE_API_VERSION': 'v1',
431 'INNERTUBE_CLIENT_NAME': 'IOS_MESSAGES_EXTENSION',
432 'INNERTUBE_CLIENT_VERSION': '16.20',
433 'INNERTUBE_API_KEY': 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8',
434 'INNERTUBE_CONTEXT': {
435 'client': {
436 'clientName': 'IOS_MESSAGES_EXTENSION',
437 'clientVersion': '16.20',
438 'hl': 'en',
439 }
440 },
441 'INNERTUBE_CONTEXT_CLIENT_NAME': 66
109dd3b2 442 }
443 }
444
445 _YT_DEFAULT_INNERTUBE_HOSTS = {
446 'DIRECT': 'youtubei.googleapis.com',
447 'WEB': 'www.youtube.com',
448 'WEB_REMIX': 'music.youtube.com',
449 'ANDROID_MUSIC': 'music.youtube.com'
450 }
451
11f9be09 452 # clients starting with _ cannot be explicity requested by the user
453 _YT_CLIENTS = {
11f9be09 454 'android': 'ANDROID',
455 'android_music': 'ANDROID_MUSIC',
456 '_android_embedded': 'ANDROID_EMBEDDED_PLAYER',
457 '_android_agegate': 'ANDROID',
458 'ios': 'IOS',
459 'ios_music': 'IOS_MUSIC',
460 '_ios_embedded': 'IOS_MESSAGES_EXTENSION',
b4c055ba 461 '_ios_agegate': 'IOS',
462 'web': 'WEB',
463 'web_music': 'WEB_REMIX',
464 '_web_embedded': 'WEB_EMBEDDED_PLAYER',
465 '_web_agegate': 'TVHTML5',
11f9be09 466 }
467
109dd3b2 468 def _get_default_ytcfg(self, client='WEB'):
469 if client in self._YT_DEFAULT_YTCFGS:
470 return copy.deepcopy(self._YT_DEFAULT_YTCFGS[client])
471 self.write_debug(f'INNERTUBE default client {client} does not exist - falling back to WEB client.')
472 return copy.deepcopy(self._YT_DEFAULT_YTCFGS['WEB'])
473
474 def _get_innertube_host(self, client='WEB'):
475 return dict_get(self._YT_DEFAULT_INNERTUBE_HOSTS, (client, 'WEB'))
476
477 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='WEB'):
478 # try_get but with fallback to default ytcfg client values when present
479 _func = lambda y: try_get(y, getter, expected_type)
480 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
481
482 def _extract_client_name(self, ytcfg, default_client='WEB'):
483 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CLIENT_NAME'], compat_str, default_client)
484
314ee305 485 @staticmethod
11f9be09 486 def _extract_session_index(*data):
487 for ytcfg in data:
488 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
489 if session_index is not None:
490 return session_index
314ee305 491
109dd3b2 492 def _extract_client_version(self, ytcfg, default_client='WEB'):
493 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CLIENT_VERSION'], compat_str, default_client)
494
495 def _extract_api_key(self, ytcfg=None, default_client='WEB'):
496 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
497
498 def _extract_context(self, ytcfg=None, default_client='WEB'):
499 _get_context = lambda y: try_get(y, lambda x: x['INNERTUBE_CONTEXT'], dict)
500 context = _get_context(ytcfg)
501 if context:
502 return context
503
504 context = _get_context(self._get_default_ytcfg(default_client))
505 if not ytcfg:
506 return context
507
508 # Recreate the client context (required)
509 context['client'].update({
510 'clientVersion': self._extract_client_version(ytcfg, default_client),
511 'clientName': self._extract_client_name(ytcfg, default_client),
512 })
513 visitor_data = try_get(ytcfg, lambda x: x['VISITOR_DATA'], compat_str)
514 if visitor_data:
515 context['client']['visitorData'] = visitor_data
516 return context
517
518 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
1974e99f 519 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
520 # See: https://github.com/yt-dlp/yt-dlp/issues/393
521 yt_cookies = self._get_cookies('https://www.youtube.com')
522 sapisid_cookie = dict_get(
523 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
c926c954 524 if sapisid_cookie is None or not sapisid_cookie.value:
a5c56234
M
525 return
526 time_now = round(time.time())
1974e99f 527 # SAPISID cookie is required if not already present
528 if not yt_cookies.get('SAPISID'):
c926c954 529 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie', only_once=True)
1974e99f 530 self._set_cookie(
531 '.youtube.com', 'SAPISID', sapisid_cookie.value, secure=True, expire_time=time_now + 3600)
c926c954 532 self.write_debug('Extracted SAPISID cookie', only_once=True)
1974e99f 533 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
534 sapisidhash = hashlib.sha1(
109dd3b2 535 f'{time_now} {sapisid_cookie.value} {origin}'.encode('utf-8')).hexdigest()
1974e99f 536 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
537
538 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 539 note='Downloading API JSON', errnote='Unable to download API page',
109dd3b2 540 context=None, api_key=None, api_hostname=None, default_client='WEB'):
f4f751af 541
109dd3b2 542 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 543 data.update(query)
11f9be09 544 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 545 real_headers.update({'content-type': 'application/json'})
546 if headers:
547 real_headers.update(headers)
545cc85d 548 return self._download_json(
109dd3b2 549 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
a5c56234 550 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 551 data=json.dumps(data).encode('utf8'), headers=real_headers,
552 query={'key': api_key or self._extract_api_key()})
553
11f9be09 554 def extract_yt_initial_data(self, video_id, webpage):
8bdd16b4 555 return self._parse_json(
556 self._search_regex(
29f7c58a 557 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
a0566bbf 558 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data'),
8bdd16b4 559 video_id)
0c148415 560
a1c5d2ca 561 def _extract_identity_token(self, webpage, item_id):
11f9be09 562 if not webpage:
563 return None
564 ytcfg = self.extract_ytcfg(item_id, webpage)
a1c5d2ca
M
565 if ytcfg:
566 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
567 if token:
568 return token
569 return self._search_regex(
570 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
571 'identity token', default=None)
572
573 @staticmethod
fe93e2c4 574 def _extract_account_syncid(*args):
8ea3f7b9 575 """
576 Extract syncId required to download private playlists of secondary channels
fe93e2c4 577 @params response and/or ytcfg
8ea3f7b9 578 """
fe93e2c4 579 for data in args:
580 # ytcfg includes channel_syncid if on secondary channel
581 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
582 if delegated_sid:
583 return delegated_sid
584 sync_ids = (try_get(
585 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
586 lambda x: x['DATASYNC_ID']), compat_str) or '').split("||")
587 if len(sync_ids) >= 2 and sync_ids[1]:
588 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
589 # and just "user_syncid||" for primary channel. We only want the channel_syncid
590 return sync_ids[0]
a1c5d2ca 591
11f9be09 592 def extract_ytcfg(self, video_id, webpage):
8c54a305 593 if not webpage:
594 return {}
29f7c58a 595 return self._parse_json(
596 self._search_regex(
597 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 598 default='{}'), video_id, fatal=False) or {}
599
11f9be09 600 def generate_api_headers(
601 self, ytcfg=None, identity_token=None, account_syncid=None,
602 visitor_data=None, api_hostname=None, default_client='WEB', session_index=None):
603 origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client))
f4f751af 604 headers = {
109dd3b2 605 'X-YouTube-Client-Name': compat_str(
11f9be09 606 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
607 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
109dd3b2 608 'Origin': origin
f4f751af 609 }
2d6659b9 610 if not visitor_data and ytcfg:
611 visitor_data = try_get(
11f9be09 612 self._extract_context(ytcfg, default_client), lambda x: x['client']['visitorData'], compat_str)
f4f751af 613 if identity_token:
109dd3b2 614 headers['X-Youtube-Identity-Token'] = identity_token
f4f751af 615 if account_syncid:
616 headers['X-Goog-PageId'] = account_syncid
314ee305 617 if session_index is None and ytcfg:
618 session_index = self._extract_session_index(ytcfg)
619 if account_syncid or session_index is not None:
620 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
f4f751af 621 if visitor_data:
109dd3b2 622 headers['X-Goog-Visitor-Id'] = visitor_data
623 auth = self._generate_sapisidhash_header(origin)
f4f751af 624 if auth is not None:
625 headers['Authorization'] = auth
109dd3b2 626 headers['X-Origin'] = origin
f4f751af 627 return headers
29f7c58a 628
2d6659b9 629 @staticmethod
630 def _build_api_continuation_query(continuation, ctp=None):
631 query = {
632 'continuation': continuation
633 }
634 # TODO: Inconsistency with clickTrackingParams.
635 # Currently we have a fixed ctp contained within context (from ytcfg)
636 # and a ctp in root query for continuation.
637 if ctp:
638 query['clickTracking'] = {'clickTrackingParams': ctp}
639 return query
640
2d6659b9 641 @classmethod
642 def _extract_next_continuation_data(cls, renderer):
643 next_continuation = try_get(
644 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
645 lambda x: x['continuation']['reloadContinuationData']), dict)
646 if not next_continuation:
647 return
648 continuation = next_continuation.get('continuation')
649 if not continuation:
650 return
651 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 652 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 653
654 @classmethod
655 def _extract_continuation_ep_data(cls, continuation_ep: dict):
656 if isinstance(continuation_ep, dict):
657 continuation = try_get(
658 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
659 if not continuation:
660 return
661 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 662 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 663
664 @classmethod
665 def _extract_continuation(cls, renderer):
666 next_continuation = cls._extract_next_continuation_data(renderer)
667 if next_continuation:
668 return next_continuation
fe93e2c4 669
2d6659b9 670 contents = []
671 for key in ('contents', 'items'):
672 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 673
2d6659b9 674 for content in contents:
675 if not isinstance(content, dict):
676 continue
677 continuation_ep = try_get(
678 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
679 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
680 dict)
681 continuation = cls._extract_continuation_ep_data(continuation_ep)
682 if continuation:
683 return continuation
684
fe93e2c4 685 @classmethod
686 def _extract_alerts(cls, data):
109dd3b2 687 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
688 if not isinstance(alert_dict, dict):
689 continue
690 for alert in alert_dict.values():
691 alert_type = alert.get('type')
692 if not alert_type:
693 continue
052e1350 694 message = cls._get_text(alert, 'text')
109dd3b2 695 if message:
696 yield alert_type, message
697
698 def _report_alerts(self, alerts, expected=True):
699 errors = []
700 warnings = []
701 for alert_type, alert_message in alerts:
702 if alert_type.lower() == 'error':
703 errors.append([alert_type, alert_message])
704 else:
705 warnings.append([alert_type, alert_message])
706
707 for alert_type, alert_message in (warnings + errors[:-1]):
708 self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message))
709 if errors:
710 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
711
712 def _extract_and_report_alerts(self, data, *args, **kwargs):
713 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
714
47193e02 715 def _extract_badges(self, renderer: dict):
716 badges = set()
717 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
718 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
719 if label:
720 badges.add(label.lower())
721 return badges
722
723 @staticmethod
052e1350 724 def _get_text(data, *path_list, max_runs=None):
725 for path in path_list or [None]:
726 if path is None:
727 obj = [data]
728 else:
729 obj = traverse_obj(data, path, default=[])
730 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
731 obj = [obj]
732 for item in obj:
733 text = try_get(item, lambda x: x['simpleText'], compat_str)
734 if text:
735 return text
736 runs = try_get(item, lambda x: x['runs'], list) or []
737 if not runs and isinstance(item, list):
738 runs = item
739
740 runs = runs[:min(len(runs), max_runs or len(runs))]
741 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
742 if text:
743 return text
47193e02 744
109dd3b2 745 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
746 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
747 default_client='WEB'):
748 response = None
749 last_error = None
750 count = -1
751 retries = self.get_param('extractor_retries', 3)
752 if check_get_keys is None:
753 check_get_keys = []
754 while count < retries:
755 count += 1
756 if last_error:
757 self.report_warning('%s. Retrying ...' % last_error)
758 try:
759 response = self._call_api(
760 ep=ep, fatal=True, headers=headers,
761 video_id=item_id, query=query,
762 context=self._extract_context(ytcfg, default_client),
763 api_key=self._extract_api_key(ytcfg, default_client),
764 api_hostname=api_hostname, default_client=default_client,
765 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
766 except ExtractorError as e:
9c0d7f49 767 if isinstance(e.cause, network_exceptions):
109dd3b2 768 # Downloading page may result in intermittent 5xx HTTP error
769 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 770 # We also want to catch all other network exceptions since errors in later pages can be troublesome
771 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
772 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
773 last_error = error_to_compat_str(e.cause or e)
774 if count < retries:
775 continue
109dd3b2 776 if fatal:
777 raise
778 else:
779 self.report_warning(error_to_compat_str(e))
780 return
781
782 else:
783 # Youtube may send alerts if there was an issue with the continuation page
784 try:
785 self._extract_and_report_alerts(response, expected=False)
786 except ExtractorError as e:
787 if fatal:
788 raise
789 self.report_warning(error_to_compat_str(e))
790 return
791 if not check_get_keys or dict_get(response, check_get_keys):
792 break
793 # Youtube sometimes sends incomplete data
794 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
795 last_error = 'Incomplete data received'
796 if count >= retries:
797 if fatal:
798 raise ExtractorError(last_error)
799 else:
800 self.report_warning(last_error)
801 return
802 return response
803
9297939e 804 @staticmethod
805 def is_music_url(url):
806 return re.match(r'https?://music\.youtube\.com/', url) is not None
807
30a074c2 808 def _extract_video(self, renderer):
809 video_id = renderer.get('videoId')
052e1350 810 title = self._get_text(renderer, 'title')
811 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 812 duration = parse_duration(self._get_text(
813 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
052e1350 814 view_count_text = self._get_text(renderer, 'viewCountText') or ''
30a074c2 815 view_count = str_to_int(self._search_regex(
816 r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
817 'view count', default=None))
fe93e2c4 818
052e1350 819 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
fe93e2c4 820
30a074c2 821 return {
39ed931e 822 '_type': 'url',
30a074c2 823 'ie_key': YoutubeIE.ie_key(),
824 'id': video_id,
825 'url': video_id,
826 'title': title,
827 'description': description,
828 'duration': duration,
829 'view_count': view_count,
830 'uploader': uploader,
831 }
832
0c148415 833
360e1ca5 834class YoutubeIE(YoutubeBaseInfoExtractor):
78caa52a 835 IE_DESC = 'YouTube.com'
bc2ca1bb 836 _INVIDIOUS_SITES = (
837 # invidious-redirect websites
838 r'(?:www\.)?redirect\.invidious\.io',
839 r'(?:(?:www|dev)\.)?invidio\.us',
840 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
841 r'(?:www\.)?invidious\.pussthecat\.org',
bc2ca1bb 842 r'(?:www\.)?invidious\.zee\.li',
bc2ca1bb 843 r'(?:www\.)?invidious\.ethibox\.fr',
bc2ca1bb 844 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
bc2ca1bb 845 # youtube-dl invidious instances list
846 r'(?:(?:www|no)\.)?invidiou\.sh',
847 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
848 r'(?:www\.)?invidious\.kabi\.tk',
bc2ca1bb 849 r'(?:www\.)?invidious\.mastodon\.host',
850 r'(?:www\.)?invidious\.zapashcanon\.fr',
ed807c18 851 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
201c1459 852 r'(?:www\.)?invidious\.tinfoil-hat\.net',
853 r'(?:www\.)?invidious\.himiko\.cloud',
854 r'(?:www\.)?invidious\.reallyancient\.tech',
bc2ca1bb 855 r'(?:www\.)?invidious\.tube',
856 r'(?:www\.)?invidiou\.site',
857 r'(?:www\.)?invidious\.site',
858 r'(?:www\.)?invidious\.xyz',
859 r'(?:www\.)?invidious\.nixnet\.xyz',
201c1459 860 r'(?:www\.)?invidious\.048596\.xyz',
bc2ca1bb 861 r'(?:www\.)?invidious\.drycat\.fr',
201c1459 862 r'(?:www\.)?inv\.skyn3t\.in',
bc2ca1bb 863 r'(?:www\.)?tube\.poal\.co',
864 r'(?:www\.)?tube\.connect\.cafe',
865 r'(?:www\.)?vid\.wxzm\.sx',
866 r'(?:www\.)?vid\.mint\.lgbt',
201c1459 867 r'(?:www\.)?vid\.puffyan\.us',
bc2ca1bb 868 r'(?:www\.)?yewtu\.be',
869 r'(?:www\.)?yt\.elukerio\.org',
870 r'(?:www\.)?yt\.lelux\.fi',
871 r'(?:www\.)?invidious\.ggc-project\.de',
872 r'(?:www\.)?yt\.maisputain\.ovh',
201c1459 873 r'(?:www\.)?ytprivate\.com',
874 r'(?:www\.)?invidious\.13ad\.de',
bc2ca1bb 875 r'(?:www\.)?invidious\.toot\.koeln',
876 r'(?:www\.)?invidious\.fdn\.fr',
877 r'(?:www\.)?watch\.nettohikari\.com',
ed807c18 878 r'(?:www\.)?invidious\.namazso\.eu',
879 r'(?:www\.)?invidious\.silkky\.cloud',
880 r'(?:www\.)?invidious\.exonip\.de',
881 r'(?:www\.)?invidious\.riverside\.rocks',
882 r'(?:www\.)?invidious\.blamefran\.net',
883 r'(?:www\.)?invidious\.moomoo\.de',
884 r'(?:www\.)?ytb\.trom\.tf',
885 r'(?:www\.)?yt\.cyberhost\.uk',
bc2ca1bb 886 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
887 r'(?:www\.)?qklhadlycap4cnod\.onion',
888 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
889 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
890 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
891 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
892 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
893 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
ed807c18 894 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
895 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
896 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
897 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
bc2ca1bb 898 )
cb7dfeea 899 _VALID_URL = r"""(?x)^
c5e8d7af 900 (
edb53e2d 901 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 902 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
903 (?:www\.)?deturl\.com/www\.youtube\.com|
904 (?:www\.)?pwnyoutube\.com|
905 (?:www\.)?hooktube\.com|
906 (?:www\.)?yourepeat\.com|
907 tube\.majestyc\.net|
908 %(invidious)s|
909 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
910 (?:.*?\#/)? # handle anchor (#/) redirect urls
911 (?: # the various things that can precede the ID:
ac7553d0 912 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
c5e8d7af 913 |(?: # or the v= param in all its forms
f7000f3a 914 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 915 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 916 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
917 v=
918 )
f4b05232 919 ))
cbaed4bb
S
920 |(?:
921 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
922 vid\.plus| # or vid.plus/xxxx
923 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 924 %(invidious)s
cbaed4bb 925 )/
edb53e2d 926 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 927 )
c5e8d7af 928 )? # all until now is optional -> you can pass the naked ID
201c1459 929 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 930 (?(1).+)? # if we found the ID, everything can follow
9297939e 931 (?:\#|$)""" % {
bc2ca1bb 932 'invidious': '|'.join(_INVIDIOUS_SITES),
933 }
e40c758c 934 _PLAYER_INFO_RE = (
cc2db878 935 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
936 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
545cc85d 937 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 938 )
2c62dc26 939 _formats = {
c2d3cb4c 940 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
941 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
942 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
943 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
944 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
945 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
946 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
947 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 948 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 949 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
950 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
951 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
952 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
953 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
954 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 955 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 956 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
957 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 958
959
960 # 3D videos
c2d3cb4c 961 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
962 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
963 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
964 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 965 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
966 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
967 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 968
96fb5605 969 # Apple HTTP Live Streaming
11f12195 970 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 971 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
972 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
973 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
974 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
975 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 976 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
977 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
978
979 # DASH mp4 video
d23028a8
S
980 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
981 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
982 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
983 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
984 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 985 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
986 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
987 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
988 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
989 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
990 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
991 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 992
f6f1fc92 993 # Dash mp4 audio
d23028a8
S
994 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
995 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
996 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
997 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
998 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
999 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1000 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1001
1002 # Dash webm
d23028a8
S
1003 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1004 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1005 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1006 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1007 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1008 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1009 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1010 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1011 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1012 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1013 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1014 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1015 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1016 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1017 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1018 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1019 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1020 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1021 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1022 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1023 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1024 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1025
1026 # Dash webm audio
d23028a8
S
1027 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1028 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1029
0857baad 1030 # Dash webm audio with opus inside
d23028a8
S
1031 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1032 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1033 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1034
ce6b9a2d
PH
1035 # RTMP (unnamed)
1036 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1037
1038 # av01 video only formats sometimes served with "unknown" codecs
1039 '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
1040 '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
1041 '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
1042 '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
c5e8d7af 1043 }
29f7c58a 1044 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1045
109dd3b2 1046 _AGE_GATE_REASONS = (
1047 'Sign in to confirm your age',
1048 'This video may be inappropriate for some users.',
1049 'Sorry, this content is age-restricted.')
1050
fd5c4aab
S
1051 _GEO_BYPASS = False
1052
78caa52a 1053 IE_NAME = 'youtube'
2eb88d95
PH
1054 _TESTS = [
1055 {
2d3d2997 1056 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1057 'info_dict': {
1058 'id': 'BaW_jenozKc',
1059 'ext': 'mp4',
3867038a 1060 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1061 'uploader': 'Philipp Hagemeister',
1062 'uploader_id': 'phihag',
ec85ded8 1063 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
dd4c4492
S
1064 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1065 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1066 'upload_date': '20121002',
3867038a 1067 '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 1068 'categories': ['Science & Technology'],
3867038a 1069 'tags': ['youtube-dl'],
556dbe7f 1070 'duration': 10,
dbdaaa23 1071 'view_count': int,
3e7c1224
PH
1072 'like_count': int,
1073 'dislike_count': int,
7c80519c 1074 'start_time': 1,
297a564b 1075 'end_time': 9,
2eb88d95 1076 }
0e853ca4 1077 },
fccd3771 1078 {
4bc3a23e
PH
1079 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1080 'note': 'Embed-only video (#1746)',
1081 'info_dict': {
1082 'id': 'yZIXLfi8CZQ',
1083 'ext': 'mp4',
1084 'upload_date': '20120608',
1085 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1086 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1087 'uploader': 'SET India',
94bfcd23 1088 'uploader_id': 'setindia',
ec85ded8 1089 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1090 'age_limit': 18,
545cc85d 1091 },
1092 'skip': 'Private video',
fccd3771 1093 },
11b56058 1094 {
8bdd16b4 1095 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1096 'note': 'Use the first video ID in the URL',
1097 'info_dict': {
1098 'id': 'BaW_jenozKc',
1099 'ext': 'mp4',
3867038a 1100 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1101 'uploader': 'Philipp Hagemeister',
1102 'uploader_id': 'phihag',
ec85ded8 1103 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
11b56058 1104 'upload_date': '20121002',
3867038a 1105 '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 1106 'categories': ['Science & Technology'],
3867038a 1107 'tags': ['youtube-dl'],
556dbe7f 1108 'duration': 10,
dbdaaa23 1109 'view_count': int,
11b56058
PM
1110 'like_count': int,
1111 'dislike_count': int,
34a7de29
S
1112 },
1113 'params': {
1114 'skip_download': True,
1115 },
11b56058 1116 },
dd27fd17 1117 {
2d3d2997 1118 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1119 'note': '256k DASH audio (format 141) via DASH manifest',
1120 'info_dict': {
1121 'id': 'a9LDPn-MO4I',
1122 'ext': 'm4a',
1123 'upload_date': '20121002',
1124 'uploader_id': '8KVIDEO',
ec85ded8 1125 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1126 'description': '',
1127 'uploader': '8KVIDEO',
1128 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1129 },
4bc3a23e
PH
1130 'params': {
1131 'youtube_include_dash_manifest': True,
1132 'format': '141',
4919603f 1133 },
de3c7fe0 1134 'skip': 'format 141 not served anymore',
dd27fd17 1135 },
8bdd16b4 1136 # DASH manifest with encrypted signature
1137 {
1138 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1139 'info_dict': {
1140 'id': 'IB3lcPjvWLA',
1141 'ext': 'm4a',
1142 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1143 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1144 'duration': 244,
1145 'uploader': 'AfrojackVEVO',
1146 'uploader_id': 'AfrojackVEVO',
1147 'upload_date': '20131011',
cc2db878 1148 'abr': 129.495,
8bdd16b4 1149 },
1150 'params': {
1151 'youtube_include_dash_manifest': True,
1152 'format': '141/bestaudio[ext=m4a]',
1153 },
1154 },
dd2d55f1 1155 # Normal age-gate video (embed allowed)
c522adb1 1156 {
2d3d2997 1157 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1158 'info_dict': {
1159 'id': 'HtVdAasjOgU',
1160 'ext': 'mp4',
1161 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1162 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1163 'duration': 142,
c522adb1
JMF
1164 'uploader': 'The Witcher',
1165 'uploader_id': 'WitcherGame',
ec85ded8 1166 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1167 'upload_date': '20140605',
34952f09 1168 'age_limit': 18,
c522adb1
JMF
1169 },
1170 },
8bdd16b4 1171 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1172 # YouTube Red ad is not captured for creator
1173 {
1174 'url': '__2ABJjxzNo',
1175 'info_dict': {
1176 'id': '__2ABJjxzNo',
1177 'ext': 'mp4',
1178 'duration': 266,
1179 'upload_date': '20100430',
1180 'uploader_id': 'deadmau5',
1181 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1182 'creator': 'deadmau5',
1183 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1184 'uploader': 'deadmau5',
1185 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1186 'alt_title': 'Some Chords',
8bdd16b4 1187 },
1188 'expected_warnings': [
1189 'DASH manifest missing',
1190 ]
1191 },
067aa17e 1192 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1193 {
1194 'url': 'lqQg6PlCWgI',
1195 'info_dict': {
1196 'id': 'lqQg6PlCWgI',
1197 'ext': 'mp4',
556dbe7f 1198 'duration': 6085,
90227264 1199 'upload_date': '20150827',
cbe2bd91 1200 'uploader_id': 'olympic',
ec85ded8 1201 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1202 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1203 'uploader': 'Olympics',
cbe2bd91
PH
1204 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1205 },
1206 'params': {
1207 'skip_download': 'requires avconv',
e52a40ab 1208 }
cbe2bd91 1209 },
6271f1ca
PH
1210 # Non-square pixels
1211 {
1212 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1213 'info_dict': {
1214 'id': '_b-2C3KPAM0',
1215 'ext': 'mp4',
1216 'stretched_ratio': 16 / 9.,
556dbe7f 1217 'duration': 85,
6271f1ca
PH
1218 'upload_date': '20110310',
1219 'uploader_id': 'AllenMeow',
ec85ded8 1220 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1221 '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 1222 'uploader': '孫ᄋᄅ',
6271f1ca
PH
1223 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1224 },
06b491eb
S
1225 },
1226 # url_encoded_fmt_stream_map is empty string
1227 {
1228 'url': 'qEJwOuvDf7I',
1229 'info_dict': {
1230 'id': 'qEJwOuvDf7I',
f57b7835 1231 'ext': 'webm',
06b491eb
S
1232 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1233 'description': '',
1234 'upload_date': '20150404',
1235 'uploader_id': 'spbelect',
1236 'uploader': 'Наблюдатели Петербурга',
1237 },
1238 'params': {
1239 'skip_download': 'requires avconv',
e323cf3f
S
1240 },
1241 'skip': 'This live event has ended.',
06b491eb 1242 },
067aa17e 1243 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1244 {
1245 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1246 'info_dict': {
1247 'id': 'FIl7x6_3R5Y',
eb6793ba 1248 'ext': 'webm',
da77d856
S
1249 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1250 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1251 'duration': 220,
da77d856
S
1252 'upload_date': '20150625',
1253 'uploader_id': 'dorappi2000',
ec85ded8 1254 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1255 'uploader': 'dorappi2000',
eb6793ba 1256 'formats': 'mincount:31',
da77d856 1257 },
eb6793ba 1258 'skip': 'not actual anymore',
2ee8f5d8 1259 },
8a1a26ce
YCH
1260 # DASH manifest with segment_list
1261 {
1262 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1263 'md5': '8ce563a1d667b599d21064e982ab9e31',
1264 'info_dict': {
1265 'id': 'CsmdDsKjzN8',
1266 'ext': 'mp4',
17ee98e1 1267 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1268 'uploader': 'Airtek',
1269 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1270 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1271 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1272 },
1273 'params': {
1274 'youtube_include_dash_manifest': True,
1275 'format': '135', # bestvideo
be49068d
S
1276 },
1277 'skip': 'This live event has ended.',
2ee8f5d8 1278 },
cf7e015f
S
1279 {
1280 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1281 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1282 'info_dict': {
545cc85d 1283 'id': 'jvGDaLqkpTg',
1284 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1285 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1286 },
1287 'playlist': [{
1288 'info_dict': {
545cc85d 1289 'id': 'jvGDaLqkpTg',
cf7e015f 1290 'ext': 'mp4',
545cc85d 1291 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1292 'description': 'md5:e03b909557865076822aa169218d6a5d',
1293 'duration': 10643,
1294 'upload_date': '20161111',
1295 'uploader': 'Team PGP',
1296 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1297 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1298 },
1299 }, {
1300 'info_dict': {
545cc85d 1301 'id': '3AKt1R1aDnw',
cf7e015f 1302 'ext': 'mp4',
545cc85d 1303 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1304 'description': 'md5:e03b909557865076822aa169218d6a5d',
1305 'duration': 10991,
1306 'upload_date': '20161111',
1307 'uploader': 'Team PGP',
1308 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1309 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1310 },
1311 }, {
1312 'info_dict': {
545cc85d 1313 'id': 'RtAMM00gpVc',
cf7e015f 1314 'ext': 'mp4',
545cc85d 1315 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1316 'description': 'md5:e03b909557865076822aa169218d6a5d',
1317 'duration': 10995,
1318 'upload_date': '20161111',
1319 'uploader': 'Team PGP',
1320 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1321 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1322 },
1323 }, {
1324 'info_dict': {
545cc85d 1325 'id': '6N2fdlP3C5U',
cf7e015f 1326 'ext': 'mp4',
545cc85d 1327 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1328 'description': 'md5:e03b909557865076822aa169218d6a5d',
1329 'duration': 10990,
1330 'upload_date': '20161111',
1331 'uploader': 'Team PGP',
1332 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1333 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1334 },
1335 }],
1336 'params': {
1337 'skip_download': True,
1338 },
cbaed4bb 1339 },
f9f49d87 1340 {
067aa17e 1341 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1342 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1343 'info_dict': {
1344 'id': 'gVfLd0zydlo',
1345 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1346 },
1347 'playlist_count': 2,
be49068d 1348 'skip': 'Not multifeed anymore',
f9f49d87 1349 },
cbaed4bb 1350 {
2d3d2997 1351 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1352 'only_matching': True,
0e49d9a6 1353 },
6d4fc66b 1354 {
2d3d2997 1355 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1356 'only_matching': True,
1357 },
0e49d9a6 1358 {
067aa17e 1359 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1360 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1361 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1362 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1363 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1364 'info_dict': {
1365 'id': 'lsguqyKfVQg',
1366 'ext': 'mp4',
1367 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1368 'alt_title': 'Dark Walk',
0e49d9a6 1369 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1370 'duration': 133,
0e49d9a6
LL
1371 'upload_date': '20151119',
1372 'uploader_id': 'IronSoulElf',
ec85ded8 1373 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1374 'uploader': 'IronSoulElf',
11f9be09 1375 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1376 'track': 'Dark Walk',
1377 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1378 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
0e49d9a6
LL
1379 },
1380 'params': {
1381 'skip_download': True,
1382 },
1383 },
61f92af1 1384 {
067aa17e 1385 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1386 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1387 'only_matching': True,
1388 },
313dfc45
LL
1389 {
1390 # Video with yt:stretch=17:0
1391 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1392 'info_dict': {
1393 'id': 'Q39EVAstoRM',
1394 'ext': 'mp4',
1395 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1396 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1397 'upload_date': '20151107',
1398 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1399 'uploader': 'CH GAMER DROID',
1400 },
1401 'params': {
1402 'skip_download': True,
1403 },
be49068d 1404 'skip': 'This video does not exist.',
313dfc45 1405 },
201c1459 1406 {
1407 # Video with incomplete 'yt:stretch=16:'
1408 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1409 'only_matching': True,
1410 },
7caf9830
S
1411 {
1412 # Video licensed under Creative Commons
1413 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1414 'info_dict': {
1415 'id': 'M4gD1WSo5mA',
1416 'ext': 'mp4',
1417 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1418 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1419 'duration': 721,
7caf9830
S
1420 'upload_date': '20150127',
1421 'uploader_id': 'BerkmanCenter',
ec85ded8 1422 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1423 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830
S
1424 'license': 'Creative Commons Attribution license (reuse allowed)',
1425 },
1426 'params': {
1427 'skip_download': True,
1428 },
1429 },
fd050249
S
1430 {
1431 # Channel-like uploader_url
1432 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1433 'info_dict': {
1434 'id': 'eQcmzGIKrzg',
1435 'ext': 'mp4',
1436 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1437 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1438 'duration': 4060,
fd050249 1439 'upload_date': '20151119',
eb6793ba 1440 'uploader': 'Bernie Sanders',
fd050249 1441 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1442 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249
S
1443 'license': 'Creative Commons Attribution license (reuse allowed)',
1444 },
1445 'params': {
1446 'skip_download': True,
1447 },
1448 },
040ac686
S
1449 {
1450 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1451 'only_matching': True,
7f29cf54
S
1452 },
1453 {
067aa17e 1454 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1455 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1456 'only_matching': True,
6496ccb4
S
1457 },
1458 {
1459 # Rental video preview
1460 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1461 'info_dict': {
1462 'id': 'uGpuVWrhIzE',
1463 'ext': 'mp4',
1464 'title': 'Piku - Trailer',
1465 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1466 'upload_date': '20150811',
1467 'uploader': 'FlixMatrix',
1468 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1469 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1470 'license': 'Standard YouTube License',
1471 },
1472 'params': {
1473 'skip_download': True,
1474 },
eb6793ba 1475 'skip': 'This video is not available.',
022a5d66 1476 },
12afdc2a
S
1477 {
1478 # YouTube Red video with episode data
1479 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1480 'info_dict': {
1481 'id': 'iqKdEhx-dD4',
1482 'ext': 'mp4',
1483 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1484 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1485 'duration': 2085,
12afdc2a
S
1486 'upload_date': '20170118',
1487 'uploader': 'Vsauce',
1488 'uploader_id': 'Vsauce',
1489 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1490 'series': 'Mind Field',
1491 'season_number': 1,
1492 'episode_number': 1,
1493 },
1494 'params': {
1495 'skip_download': True,
1496 },
1497 'expected_warnings': [
1498 'Skipping DASH manifest',
1499 ],
1500 },
c7121fa7
S
1501 {
1502 # The following content has been identified by the YouTube community
1503 # as inappropriate or offensive to some audiences.
1504 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1505 'info_dict': {
1506 'id': '6SJNVb0GnPI',
1507 'ext': 'mp4',
1508 'title': 'Race Differences in Intelligence',
1509 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1510 'duration': 965,
1511 'upload_date': '20140124',
1512 'uploader': 'New Century Foundation',
1513 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1514 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1515 },
1516 'params': {
1517 'skip_download': True,
1518 },
545cc85d 1519 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1520 },
022a5d66
S
1521 {
1522 # itag 212
1523 'url': '1t24XAntNCY',
1524 'only_matching': True,
fd5c4aab
S
1525 },
1526 {
1527 # geo restricted to JP
1528 'url': 'sJL6WA-aGkQ',
1529 'only_matching': True,
1530 },
cd5a74a2
S
1531 {
1532 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1533 'only_matching': True,
1534 },
bc2ca1bb 1535 {
1536 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1537 'only_matching': True,
1538 },
1539 {
1540 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1541 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1542 'only_matching': True,
1543 },
825cd268
RA
1544 {
1545 # DRM protected
1546 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1547 'only_matching': True,
4fe54c12
S
1548 },
1549 {
1550 # Video with unsupported adaptive stream type formats
1551 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1552 'info_dict': {
1553 'id': 'Z4Vy8R84T1U',
1554 'ext': 'mp4',
1555 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1556 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1557 'duration': 433,
1558 'upload_date': '20130923',
1559 'uploader': 'Amelia Putri Harwita',
1560 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1561 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1562 'formats': 'maxcount:10',
1563 },
1564 'params': {
1565 'skip_download': True,
1566 'youtube_include_dash_manifest': False,
1567 },
5429d6a9 1568 'skip': 'not actual anymore',
5caabd3c 1569 },
1570 {
822b9d9c 1571 # Youtube Music Auto-generated description
5caabd3c 1572 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1573 'info_dict': {
1574 'id': 'MgNrAu2pzNs',
1575 'ext': 'mp4',
1576 'title': 'Voyeur Girl',
1577 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1578 'upload_date': '20190312',
5429d6a9
S
1579 'uploader': 'Stephen - Topic',
1580 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1581 'artist': 'Stephen',
1582 'track': 'Voyeur Girl',
1583 'album': 'it\'s too much love to know my dear',
1584 'release_date': '20190313',
1585 'release_year': 2019,
1586 },
1587 'params': {
1588 'skip_download': True,
1589 },
1590 },
66b48727
RA
1591 {
1592 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1593 'only_matching': True,
1594 },
011e75e6
S
1595 {
1596 # invalid -> valid video id redirection
1597 'url': 'DJztXj2GPfl',
1598 'info_dict': {
1599 'id': 'DJztXj2GPfk',
1600 'ext': 'mp4',
1601 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1602 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1603 'upload_date': '20090125',
1604 'uploader': 'Prochorowka',
1605 'uploader_id': 'Prochorowka',
1606 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1607 'artist': 'Panjabi MC',
1608 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1609 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1610 },
1611 'params': {
1612 'skip_download': True,
1613 },
545cc85d 1614 'skip': 'Video unavailable',
ea74e00b
DP
1615 },
1616 {
1617 # empty description results in an empty string
1618 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1619 'info_dict': {
1620 'id': 'x41yOUIvK2k',
1621 'ext': 'mp4',
1622 'title': 'IMG 3456',
1623 'description': '',
1624 'upload_date': '20170613',
1625 'uploader_id': 'ElevageOrVert',
1626 'uploader': 'ElevageOrVert',
1627 },
1628 'params': {
1629 'skip_download': True,
1630 },
1631 },
a0566bbf 1632 {
29f7c58a 1633 # with '};' inside yt initial data (see [1])
1634 # see [2] for an example with '};' inside ytInitialPlayerResponse
1635 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1636 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1637 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1638 'info_dict': {
1639 'id': 'CHqg6qOn4no',
1640 'ext': 'mp4',
1641 'title': 'Part 77 Sort a list of simple types in c#',
1642 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1643 'upload_date': '20130831',
1644 'uploader_id': 'kudvenkat',
1645 'uploader': 'kudvenkat',
1646 },
1647 'params': {
1648 'skip_download': True,
1649 },
1650 },
29f7c58a 1651 {
1652 # another example of '};' in ytInitialData
1653 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1654 'only_matching': True,
1655 },
1656 {
1657 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1658 'only_matching': True,
1659 },
545cc85d 1660 {
cc2db878 1661 # https://github.com/ytdl-org/youtube-dl/pull/28094
1662 'url': 'OtqTfy26tG0',
1663 'info_dict': {
1664 'id': 'OtqTfy26tG0',
1665 'ext': 'mp4',
1666 'title': 'Burn Out',
1667 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1668 'upload_date': '20141120',
1669 'uploader': 'The Cinematic Orchestra - Topic',
1670 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1671 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1672 'artist': 'The Cinematic Orchestra',
1673 'track': 'Burn Out',
1674 'album': 'Every Day',
1675 'release_data': None,
1676 'release_year': None,
1677 },
1678 'params': {
1679 'skip_download': True,
1680 },
545cc85d 1681 },
bc2ca1bb 1682 {
1683 # controversial video, only works with bpctr when authenticated with cookies
1684 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1685 'only_matching': True,
1686 },
a1a7907b 1687 {
1688 # controversial video, requires bpctr/contentCheckOk
1689 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1690 'info_dict': {
1691 'id': 'SZJvDhaSDnc',
1692 'ext': 'mp4',
1693 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1694 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1695 'uploader': 'CBS This Morning',
11f9be09 1696 'uploader_id': 'CBSThisMorning',
a1a7907b 1697 'upload_date': '20140716',
1698 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7'
1699 }
1700 },
f7ad7160 1701 {
1702 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1703 'url': 'cBvYw8_A0vQ',
1704 'info_dict': {
1705 'id': 'cBvYw8_A0vQ',
1706 'ext': 'mp4',
1707 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1708 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1709 'upload_date': '20201120',
1710 'uploader': 'Walk around Japan',
1711 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1712 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1713 },
1714 'params': {
1715 'skip_download': True,
1716 },
0fb983f6 1717 }, {
1718 # Has multiple audio streams
1719 'url': 'WaOKSUlf4TM',
1720 'only_matching': True
9297939e 1721 }, {
1722 # Requires Premium: has format 141 when requested using YTM url
1723 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
1724 'only_matching': True
1725 }, {
120916da 1726 # multiple subtitles with same lang_code
1727 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
1728 'only_matching': True,
109dd3b2 1729 }, {
1730 # Force use android client fallback
1731 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
1732 'info_dict': {
1733 'id': 'YOelRv7fMxY',
11f9be09 1734 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 1735 'ext': '3gp',
1736 'upload_date': '20210624',
1737 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
1738 'uploader': 'colinfurze',
11f9be09 1739 'uploader_id': 'colinfurze',
109dd3b2 1740 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
11f9be09 1741 'description': 'md5:b5096f56af7ccd7a555c84db81738b22'
109dd3b2 1742 },
1743 'params': {
1744 'format': '17', # 3gp format available on android
1745 'extractor_args': {'youtube': {'player_client': ['android']}},
1746 },
120916da 1747 },
109dd3b2 1748 {
1749 # Skip download of additional client configs (remix client config in this case)
1750 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1751 'only_matching': True,
1752 'params': {
1753 'extractor_args': {'youtube': {'player_skip': ['configs']}},
1754 },
1755 }
2eb88d95
PH
1756 ]
1757
201c1459 1758 @classmethod
1759 def suitable(cls, url):
1bdae7d3 1760 # Hack for lazy extractors until more generic solution is implemented
1761 # (see #28780)
1762 from .youtube import parse_qs
201c1459 1763 qs = parse_qs(url)
1764 if qs.get('list', [None])[0]:
1765 return False
1766 return super(YoutubeIE, cls).suitable(url)
1767
e0df6211
PH
1768 def __init__(self, *args, **kwargs):
1769 super(YoutubeIE, self).__init__(*args, **kwargs)
545cc85d 1770 self._code_cache = {}
83799698 1771 self._player_cache = {}
e0df6211 1772
109dd3b2 1773 def _extract_player_url(self, ytcfg=None, webpage=None):
1774 player_url = try_get(ytcfg, (lambda x: x['PLAYER_JS_URL']), str)
11f9be09 1775 if not player_url and webpage:
109dd3b2 1776 player_url = self._search_regex(
1777 r'"(?:PLAYER_JS_URL|jsUrl)"\s*:\s*"([^"]+)"',
1778 webpage, 'player URL', fatal=False)
11f9be09 1779 if not player_url:
1780 return None
109dd3b2 1781 if player_url.startswith('//'):
1782 player_url = 'https:' + player_url
1783 elif not re.match(r'https?://', player_url):
1784 player_url = compat_urlparse.urljoin(
1785 'https://www.youtube.com', player_url)
1786 return player_url
1787
60064c53
PH
1788 def _signature_cache_id(self, example_sig):
1789 """ Return a string representation of a signature """
78caa52a 1790 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 1791
e40c758c
S
1792 @classmethod
1793 def _extract_player_info(cls, player_url):
1794 for player_re in cls._PLAYER_INFO_RE:
1795 id_m = re.search(player_re, player_url)
1796 if id_m:
1797 break
1798 else:
c081b35c 1799 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 1800 return id_m.group('id')
e40c758c 1801
109dd3b2 1802 def _load_player(self, video_id, player_url, fatal=True) -> bool:
1803 player_id = self._extract_player_info(player_url)
1804 if player_id not in self._code_cache:
1805 self._code_cache[player_id] = self._download_webpage(
1806 player_url, video_id, fatal=fatal,
1807 note='Downloading player ' + player_id,
1808 errnote='Download of %s failed' % player_url)
1809 return player_id in self._code_cache
1810
e40c758c 1811 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 1812 player_id = self._extract_player_info(player_url)
e0df6211 1813
c4417ddb 1814 # Read from filesystem cache
545cc85d 1815 func_id = 'js_%s_%s' % (
1816 player_id, self._signature_cache_id(example_sig))
c4417ddb 1817 assert os.path.basename(func_id) == func_id
a0e07d31 1818
69ea8ca4 1819 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 1820 if cache_spec is not None:
78caa52a 1821 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 1822
109dd3b2 1823 if self._load_player(video_id, player_url):
1824 code = self._code_cache[player_id]
1825 res = self._parse_sig_js(code)
e0df6211 1826
109dd3b2 1827 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1828 cache_res = res(test_string)
1829 cache_spec = [ord(c) for c in cache_res]
83799698 1830
109dd3b2 1831 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
1832 return res
83799698 1833
60064c53 1834 def _print_sig_code(self, func, example_sig):
edf3e38e
PH
1835 def gen_sig_code(idxs):
1836 def _genslice(start, end, step):
78caa52a 1837 starts = '' if start == 0 else str(start)
8bcc8756 1838 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 1839 steps = '' if step == 1 else (':%d' % step)
78caa52a 1840 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
1841
1842 step = None
7af808a5
PH
1843 # Quelch pyflakes warnings - start will be set when step is set
1844 start = '(Never used)'
edf3e38e
PH
1845 for i, prev in zip(idxs[1:], idxs[:-1]):
1846 if step is not None:
1847 if i - prev == step:
1848 continue
1849 yield _genslice(start, prev, step)
1850 step = None
1851 continue
1852 if i - prev in [-1, 1]:
1853 step = i - prev
1854 start = prev
1855 continue
1856 else:
78caa52a 1857 yield 's[%d]' % prev
edf3e38e 1858 if step is None:
78caa52a 1859 yield 's[%d]' % i
edf3e38e
PH
1860 else:
1861 yield _genslice(start, i, step)
1862
78caa52a 1863 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 1864 cache_res = func(test_string)
edf3e38e 1865 cache_spec = [ord(c) for c in cache_res]
78caa52a 1866 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
1867 signature_id_tuple = '(%s)' % (
1868 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 1869 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 1870 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 1871 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 1872
e0df6211
PH
1873 def _parse_sig_js(self, jscode):
1874 funcname = self._search_regex(
abefc03f
S
1875 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1876 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
cc2db878 1877 r'\bm=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(h\.s\)\)',
1878 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(c\)\)',
1879 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}\(a,\d+\)',
e450f6cb 1880 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 1881 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
1882 # Obsolete patterns
1883 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 1884 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
1885 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1886 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1887 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1888 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1889 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1890 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 1891 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
1892
1893 jsi = JSInterpreter(jscode)
1894 initial_function = jsi.extract_function(funcname)
e0df6211
PH
1895 return lambda s: initial_function([s])
1896
545cc85d 1897 def _decrypt_signature(self, s, video_id, player_url):
257a2501 1898 """Turn the encrypted s field into a working signature"""
6b37f0be 1899
c8bf86d5 1900 if player_url is None:
69ea8ca4 1901 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 1902
c8bf86d5 1903 try:
62af3a0e 1904 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
1905 if player_id not in self._player_cache:
1906 func = self._extract_signature_function(
60064c53 1907 video_id, player_url, s
c8bf86d5
PH
1908 )
1909 self._player_cache[player_id] = func
1910 func = self._player_cache[player_id]
a06916d9 1911 if self.get_param('youtube_print_sig_code'):
60064c53 1912 self._print_sig_code(func, s)
c8bf86d5
PH
1913 return func(s)
1914 except Exception as e:
1915 tb = traceback.format_exc()
1916 raise ExtractorError(
78caa52a 1917 'Signature extraction failed: ' + tb, cause=e)
e0df6211 1918
109dd3b2 1919 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
1920 """
1921 Extract signatureTimestamp (sts)
1922 Required to tell API what sig/player version is in use.
1923 """
1924 sts = None
1925 if isinstance(ytcfg, dict):
1926 sts = int_or_none(ytcfg.get('STS'))
1927
1928 if not sts:
1929 # Attempt to extract from player
1930 if player_url is None:
1931 error_msg = 'Cannot extract signature timestamp without player_url.'
1932 if fatal:
1933 raise ExtractorError(error_msg)
1934 self.report_warning(error_msg)
1935 return
1936 if self._load_player(video_id, player_url, fatal=fatal):
1937 player_id = self._extract_player_info(player_url)
1938 code = self._code_cache[player_id]
1939 sts = int_or_none(self._search_regex(
1940 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
1941 'JS player signature timestamp', group='sts', fatal=fatal))
1942 return sts
1943
11f9be09 1944 def _mark_watched(self, video_id, player_responses):
352d63fd 1945 playback_url = traverse_obj(
1946 player_responses, (..., 'playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
1947 expected_type=url_or_none, get_all=False)
d77ab8e2 1948 if not playback_url:
352d63fd 1949 self.report_warning('Unable to mark watched')
d77ab8e2
S
1950 return
1951 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1952 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1953
1954 # cpn generation algorithm is reverse engineered from base.js.
1955 # In fact it works even with dummy cpn.
1956 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1957 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1958
1959 qs.update({
1960 'ver': ['2'],
1961 'cpn': [cpn],
1962 })
1963 playback_url = compat_urlparse.urlunparse(
15707c7e 1964 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
1965
1966 self._download_webpage(
1967 playback_url, video_id, 'Marking watched',
1968 'Unable to mark watched', fatal=False)
1969
66c9fa36
S
1970 @staticmethod
1971 def _extract_urls(webpage):
1972 # Embedded YouTube player
1973 entries = [
1974 unescapeHTML(mobj.group('url'))
1975 for mobj in re.finditer(r'''(?x)
1976 (?:
1977 <iframe[^>]+?src=|
1978 data-video-url=|
1979 <embed[^>]+?src=|
1980 embedSWF\(?:\s*|
1981 <object[^>]+data=|
1982 new\s+SWFObject\(
1983 )
1984 (["\'])
1985 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 1986 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
1987 \1''', webpage)]
1988
1989 # lazyYT YouTube embed
1990 entries.extend(list(map(
1991 unescapeHTML,
1992 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1993
1994 # Wordpress "YouTube Video Importer" plugin
1995 matches = re.findall(r'''(?x)<div[^>]+
1996 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1997 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1998 entries.extend(m[-1] for m in matches)
1999
2000 return entries
2001
2002 @staticmethod
2003 def _extract_url(webpage):
2004 urls = YoutubeIE._extract_urls(webpage)
2005 return urls[0] if urls else None
2006
97665381
PH
2007 @classmethod
2008 def extract_id(cls, url):
2009 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 2010 if mobj is None:
69ea8ca4 2011 raise ExtractorError('Invalid URL: %s' % url)
c5e8d7af
PH
2012 video_id = mobj.group(2)
2013 return video_id
2014
7c365c21 2015 def _extract_chapters_from_json(self, data, duration):
2016 chapter_list = traverse_obj(
2017 data, (
2018 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2019 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2020 ), expected_type=list)
2021
2022 return self._extract_chapters(
2023 chapter_list,
2024 chapter_time=lambda chapter: float_or_none(
2025 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2026 chapter_title=lambda chapter: traverse_obj(
2027 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2028 duration=duration)
2029
2030 def _extract_chapters_from_engagement_panel(self, data, duration):
2031 content_list = traverse_obj(
8bdd16b4 2032 data,
7c365c21 2033 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2034 expected_type=list, default=[])
052e1350 2035 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2036 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2037
2038 return next((
2039 filter(None, (
2040 self._extract_chapters(
2041 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2042 chapter_time, chapter_title, duration)
2043 for contents in content_list
2044 ))), [])
2045
2046 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
84213ea8 2047 chapters = []
7c365c21 2048 last_chapter = {'start_time': 0}
2049 for idx, chapter in enumerate(chapter_list or []):
2050 title = chapter_title(chapter)
84213ea8
S
2051 start_time = chapter_time(chapter)
2052 if start_time is None:
2053 continue
7c365c21 2054 last_chapter['end_time'] = start_time
2055 if start_time < last_chapter['start_time']:
2056 if idx == 1:
2057 chapters.pop()
2058 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2059 else:
2060 self.report_warning(f'Invalid start time for chapter "{title}"')
2061 continue
2062 last_chapter = {'start_time': start_time, 'title': title}
2063 chapters.append(last_chapter)
2064 last_chapter['end_time'] = duration
84213ea8
S
2065 return chapters
2066
545cc85d 2067 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2068 return self._parse_json(self._search_regex(
2069 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2070 regex), webpage, name, default='{}'), video_id, fatal=False)
84213ea8 2071
d92f5d5a 2072 @staticmethod
2073 def parse_time_text(time_text):
2074 """
2075 Parse the comment time text
2076 time_text is in the format 'X units ago (edited)'
2077 """
2078 time_text_split = time_text.split(' ')
2079 if len(time_text_split) >= 3:
da503b7a 2080 try:
2081 return datetime_from_str('now-%s%s' % (time_text_split[0], time_text_split[1]), precision='auto')
2082 except ValueError:
2083 return None
d92f5d5a 2084
a1c5d2ca
M
2085 def _extract_comment(self, comment_renderer, parent=None):
2086 comment_id = comment_renderer.get('commentId')
2087 if not comment_id:
2088 return
fe93e2c4 2089
052e1350 2090 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2091
49bd8c66 2092 # note: timestamp is an estimate calculated from the current time and time_text
052e1350 2093 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
fe93e2c4 2094 time_text_dt = self.parse_time_text(time_text)
2095 if isinstance(time_text_dt, datetime.datetime):
2096 timestamp = calendar.timegm(time_text_dt.timetuple())
052e1350 2097 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2098 author_id = try_get(comment_renderer,
2099 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2100
49bd8c66 2101 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2102 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2103 author_thumbnail = try_get(comment_renderer,
2104 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2105
2106 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2107 is_favorited = 'creatorHeart' in (try_get(
2108 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2109 return {
2110 'id': comment_id,
2111 'text': text,
d92f5d5a 2112 'timestamp': timestamp,
a1c5d2ca
M
2113 'time_text': time_text,
2114 'like_count': votes,
97524332 2115 'is_favorited': is_favorited,
a1c5d2ca
M
2116 'author': author,
2117 'author_id': author_id,
2118 'author_thumbnail': author_thumbnail,
2119 'author_is_uploader': author_is_uploader,
2120 'parent': parent or 'root'
2121 }
2122
2123 def _comment_entries(self, root_continuation_data, identity_token, account_syncid,
2d6659b9 2124 ytcfg, video_id, parent=None, comment_counts=None):
2125
2126 def extract_header(contents):
2127 _total_comments = 0
2128 _continuation = None
2129 for content in contents:
2130 comments_header_renderer = try_get(content, lambda x: x['commentsHeaderRenderer'])
fe93e2c4 2131 expected_comment_count = parse_count(self._get_text(
052e1350 2132 comments_header_renderer, 'countText', 'commentsCount', max_runs=1))
fe93e2c4 2133
2d6659b9 2134 if expected_comment_count:
fe93e2c4 2135 comment_counts[1] = expected_comment_count
2136 self.to_screen('Downloading ~%d comments' % expected_comment_count)
2d6659b9 2137 _total_comments = comment_counts[1]
2138 sort_mode_str = self._configuration_arg('comment_sort', [''])[0]
2139 comment_sort_index = int(sort_mode_str != 'top') # 1 = new, 0 = top
2140
2141 sort_menu_item = try_get(
2142 comments_header_renderer,
2143 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2144 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2145
2146 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2147 if not _continuation:
2148 continue
2149
2150 sort_text = sort_menu_item.get('title')
2151 if isinstance(sort_text, compat_str):
2152 sort_text = sort_text.lower()
2153 else:
2154 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2155 self.to_screen('Sorting comments by %s' % sort_text)
2156 break
2157 return _total_comments, _continuation
a1c5d2ca 2158
2d6659b9 2159 def extract_thread(contents):
a1c5d2ca
M
2160 if not parent:
2161 comment_counts[2] = 0
2162 for content in contents:
2163 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2164 comment_renderer = try_get(
2165 comment_thread_renderer, (lambda x: x['comment']['commentRenderer'], dict)) or try_get(
2166 content, (lambda x: x['commentRenderer'], dict))
2167
2168 if not comment_renderer:
2169 continue
2170 comment = self._extract_comment(comment_renderer, parent)
2171 if not comment:
2172 continue
2173 comment_counts[0] += 1
2174 yield comment
2175 # Attempt to get the replies
2176 comment_replies_renderer = try_get(
2177 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2178
2179 if comment_replies_renderer:
2180 comment_counts[2] += 1
2181 comment_entries_iter = self._comment_entries(
f4f751af 2182 comment_replies_renderer, identity_token, account_syncid, ytcfg,
2d6659b9 2183 video_id, parent=comment.get('id'), comment_counts=comment_counts)
a1c5d2ca
M
2184
2185 for reply_comment in comment_entries_iter:
2186 yield reply_comment
2187
2d6659b9 2188 # YouTube comments have a max depth of 2
2189 max_depth = int_or_none(self._configuration_arg('max_comment_depth', [''])[0]) or float('inf')
2190 if max_depth == 1 and parent:
2191 return
a1c5d2ca
M
2192 if not comment_counts:
2193 # comment so far, est. total comments, current comment thread #
2194 comment_counts = [0, 0, 0]
a1c5d2ca 2195
2d6659b9 2196 continuation = self._extract_continuation(root_continuation_data)
fe93e2c4 2197 if continuation and len(continuation['continuation']) < 27:
2d6659b9 2198 self.write_debug('Detected old API continuation token. Generating new API compatible token.')
2199 continuation_token = self._generate_comment_continuation(video_id)
fe93e2c4 2200 continuation = self._build_api_continuation_query(continuation_token, None)
2d6659b9 2201
2202 visitor_data = None
2203 is_first_continuation = parent is None
a1c5d2ca
M
2204
2205 for page_num in itertools.count(0):
2206 if not continuation:
2207 break
11f9be09 2208 headers = self.generate_api_headers(ytcfg, identity_token, account_syncid, visitor_data)
2d6659b9 2209 comment_prog_str = '(%d/%d)' % (comment_counts[0], comment_counts[1])
2210 if page_num == 0:
2211 if is_first_continuation:
2212 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2213 else:
2d6659b9 2214 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2215 comment_counts[2], comment_prog_str)
2216 else:
2217 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2218 ' ' if parent else '', ' replies' if parent else '',
2219 page_num, comment_prog_str)
2220
2221 response = self._extract_response(
fe93e2c4 2222 item_id=None, query=continuation,
2d6659b9 2223 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2224 check_get_keys=('onResponseReceivedEndpoints', 'continuationContents'))
a1c5d2ca
M
2225 if not response:
2226 break
f4f751af 2227 visitor_data = try_get(
2228 response,
2229 lambda x: x['responseContext']['webResponseContextExtensionData']['ytConfigData']['visitorData'],
2230 compat_str) or visitor_data
a1c5d2ca 2231
2d6659b9 2232 continuation_contents = dict_get(response, ('onResponseReceivedEndpoints', 'continuationContents'))
a1c5d2ca 2233
2d6659b9 2234 continuation = None
2235 if isinstance(continuation_contents, list):
2236 for continuation_section in continuation_contents:
2237 if not isinstance(continuation_section, dict):
2238 continue
2239 continuation_items = try_get(
2240 continuation_section,
2241 (lambda x: x['reloadContinuationItemsCommand']['continuationItems'],
2242 lambda x: x['appendContinuationItemsAction']['continuationItems']),
2243 list) or []
2244 if is_first_continuation:
2245 total_comments, continuation = extract_header(continuation_items)
2246 if total_comments:
2247 yield total_comments
2248 is_first_continuation = False
2249 if continuation:
2250 break
2251 continue
2252 count = 0
2253 for count, entry in enumerate(extract_thread(continuation_items)):
2254 yield entry
2255 continuation = self._extract_continuation({'contents': continuation_items})
2256 if continuation:
2257 # Sometimes YouTube provides a continuation without any comments
2258 # In most cases we end up just downloading these with very little comments to come.
2259 if count == 0:
2260 if not parent:
2261 self.report_warning('No comments received - assuming end of comments')
2262 continuation = None
a1c5d2ca
M
2263 break
2264
2d6659b9 2265 # Deprecated response structure
2266 elif isinstance(continuation_contents, dict):
2267 known_continuation_renderers = ('itemSectionContinuation', 'commentRepliesContinuation')
2268 for key, continuation_renderer in continuation_contents.items():
2269 if key not in known_continuation_renderers:
2270 continue
2271 if not isinstance(continuation_renderer, dict):
2272 continue
2273 if is_first_continuation:
2274 header_continuation_items = [continuation_renderer.get('header') or {}]
2275 total_comments, continuation = extract_header(header_continuation_items)
2276 if total_comments:
2277 yield total_comments
2278 is_first_continuation = False
2279 if continuation:
2280 break
a1c5d2ca 2281
2d6659b9 2282 # Sometimes YouTube provides a continuation without any comments
2283 # In most cases we end up just downloading these with very little comments to come.
2284 count = 0
2285 for count, entry in enumerate(extract_thread(continuation_renderer.get('contents') or {})):
2286 yield entry
2287 continuation = self._extract_continuation(continuation_renderer)
2288 if count == 0:
2289 if not parent:
2290 self.report_warning('No comments received - assuming end of comments')
2291 continuation = None
2292 break
a1c5d2ca 2293
2d6659b9 2294 @staticmethod
2295 def _generate_comment_continuation(video_id):
2296 """
2297 Generates initial comment section continuation token from given video id
2298 """
2299 b64_vid_id = base64.b64encode(bytes(video_id.encode('utf-8')))
2300 parts = ('Eg0SCw==', b64_vid_id, 'GAYyJyIRIgs=', b64_vid_id, 'MAB4AjAAQhBjb21tZW50cy1zZWN0aW9u')
2301 new_continuation_intlist = list(itertools.chain.from_iterable(
2302 [bytes_to_intlist(base64.b64decode(part)) for part in parts]))
2303 return base64.b64encode(intlist_to_bytes(new_continuation_intlist)).decode('utf-8')
2304
2305 def _extract_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2306 """Entry for comment extraction"""
2d6659b9 2307 def _real_comment_extract(contents):
2308 if isinstance(contents, list):
2309 for entry in contents:
2310 for key, renderer in entry.items():
2311 if key not in known_entry_comment_renderers:
2312 continue
2313 yield from self._comment_entries(
2314 renderer, video_id=video_id, ytcfg=ytcfg,
2315 identity_token=self._extract_identity_token(webpage, item_id=video_id),
2316 account_syncid=self._extract_account_syncid(ytcfg))
2317 break
a1c5d2ca 2318 comments = []
2d6659b9 2319 known_entry_comment_renderers = ('itemSectionRenderer',)
a1c5d2ca 2320 estimated_total = 0
2d6659b9 2321 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0]) or float('inf')
a1c5d2ca 2322
2d6659b9 2323 try:
2324 for comment in _real_comment_extract(contents):
2325 if len(comments) >= max_comments:
2326 break
2327 if isinstance(comment, int):
2328 estimated_total = comment
2329 continue
2330 comments.append(comment)
2331 except KeyboardInterrupt:
2332 self.to_screen('Interrupted by user')
d92f5d5a 2333 self.to_screen('Downloaded %d/%d comments' % (len(comments), estimated_total))
a1c5d2ca
M
2334 return {
2335 'comments': comments,
2336 'comment_count': len(comments),
2337 }
2338
109dd3b2 2339 @staticmethod
2340 def _generate_player_context(sts=None):
2341 context = {
2342 'html5Preference': 'HTML5_PREF_WANTS',
2343 }
2344 if sts is not None:
2345 context['signatureTimestamp'] = sts
2346 return {
2347 'playbackContext': {
2348 'contentPlaybackContext': context
a1a7907b 2349 },
2fd226f6 2350 'contentCheckOk': True,
2351 'racyCheckOk': True
109dd3b2 2352 }
2353
4e6767b5 2354 @staticmethod
c888ffb9 2355 def _get_video_info_params(video_id, client='TVHTML5'):
2356 GVI_CLIENTS = {
2357 'ANDROID': {
2358 'c': 'ANDROID',
2359 'cver': '16.20',
2360 },
2361 'TVHTML5': {
2362 'c': 'TVHTML5',
2363 'cver': '6.20180913',
11f9be09 2364 },
2365 'IOS': {
2366 'c': 'IOS',
2367 'cver': '16.20'
c888ffb9 2368 }
2369 }
2370 query = {
4e6767b5 2371 'video_id': video_id,
2372 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
c888ffb9 2373 'html5': '1'
4e6767b5 2374 }
c888ffb9 2375 query.update(GVI_CLIENTS.get(client))
2376 return query
4e6767b5 2377
11f9be09 2378 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, identity_token, player_url, initial_pr):
109dd3b2 2379
11f9be09 2380 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2381 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
2382 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False)
2383 headers = self.generate_api_headers(
2384 player_ytcfg, identity_token, syncid,
2385 default_client=self._YT_CLIENTS[client], session_index=session_index)
9297939e 2386
11f9be09 2387 yt_query = {'videoId': video_id}
2388 yt_query.update(self._generate_player_context(sts))
2389 return self._extract_response(
2390 item_id=video_id, ep='player', query=yt_query,
2391 ytcfg=player_ytcfg, headers=headers, fatal=False,
2392 default_client=self._YT_CLIENTS[client],
2393 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2394 ) or None
2395
2396 def _extract_age_gated_player_response(self, client, video_id, ytcfg, identity_token, player_url, initial_pr):
c8fa48fd 2397 # get_video_info endpoint seems to be completely dead
f703a880 2398 gvi_client = None # self._YT_CLIENTS.get(f'_{client}_agegate')
c8fa48fd 2399 if gvi_client:
2400 pr = self._parse_json(traverse_obj(
2401 compat_parse_qs(self._download_webpage(
2402 self.http_scheme() + '//www.youtube.com/get_video_info', video_id,
2403 'Refetching age-gated %s info webpage' % gvi_client.lower(),
2404 'unable to download video info webpage', fatal=False,
2405 query=self._get_video_info_params(video_id, client=gvi_client))),
2406 ('player_response', 0), expected_type=str) or '{}', video_id)
2407 if pr:
2408 return pr
2409 self.report_warning('Falling back to embedded-only age-gate workaround')
2410
2411 if not self._YT_CLIENTS.get(f'_{client}_embedded'):
11f9be09 2412 return
11f9be09 2413 embed_webpage = None
2414 if client == 'web' and 'configs' not in self._configuration_arg('player_skip'):
2415 embed_webpage = self._download_webpage(
2416 'https://www.youtube.com/embed/%s?html5=1' % video_id,
2417 video_id=video_id, note=f'Downloading age-gated {client} embed config')
2418
2419 ytcfg_age = self.extract_ytcfg(video_id, embed_webpage) or {}
2420 # If we extracted the embed webpage, it'll tell us if we can view the video
2421 embedded_pr = self._parse_json(
2422 traverse_obj(ytcfg_age, ('PLAYER_VARS', 'embedded_player_response'), expected_type=str) or '{}',
2423 video_id=video_id)
2424 embedded_ps_reason = traverse_obj(embedded_pr, ('playabilityStatus', 'reason'), expected_type=str) or ''
2425 if embedded_ps_reason in self._AGE_GATE_REASONS:
2426 return
2427 return self._extract_player_response(
2428 f'_{client}_embedded', video_id,
2429 ytcfg_age or ytcfg, ytcfg_age if client == 'web' else {},
2430 identity_token, player_url, initial_pr)
545cc85d 2431
11f9be09 2432 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 2433 requested_clients = []
2434 allowed_clients = [client for client in self._YT_CLIENTS.keys() if client[:1] != '_']
2435 for client in self._configuration_arg('player_client'):
2436 if client in allowed_clients:
2437 requested_clients.append(client)
2438 elif client == 'all':
2439 requested_clients.extend(allowed_clients)
2440 else:
2441 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 2442 if not requested_clients:
2443 requested_clients = ['android', 'web']
cf7e015f 2444
11f9be09 2445 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2446 requested_clients.extend(
2447 f'{client}_music' for client in requested_clients if not client.endswith('_music'))
dbdaaa23 2448
11f9be09 2449 return orderedSet(requested_clients)
cf7e015f 2450
11f9be09 2451 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, player_url, identity_token):
2452 initial_pr = None
2453 if webpage:
2454 initial_pr = self._extract_yt_initial_variable(
2455 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2456 video_id, 'initial player response')
6b09401b 2457
11f9be09 2458 for client in clients:
2459 player_ytcfg = master_ytcfg if client == 'web' else {}
ad34b295 2460 if client == 'web' and initial_pr:
11f9be09 2461 pr = initial_pr
8fe10494 2462 else:
11f9be09 2463 if client == 'web_music' and 'configs' not in self._configuration_arg('player_skip'):
2464 ytm_webpage = self._download_webpage(
2465 'https://music.youtube.com',
2466 video_id, fatal=False, note='Downloading remix client config')
2467 player_ytcfg = self.extract_ytcfg(video_id, ytm_webpage) or {}
2468 pr = self._extract_player_response(
2469 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, identity_token, player_url, initial_pr)
2470 if pr:
2471 yield pr
ad34b295 2472 if traverse_obj(pr, ('playabilityStatus', 'reason')) in self._AGE_GATE_REASONS:
11f9be09 2473 pr = self._extract_age_gated_player_response(
2474 client, video_id, player_ytcfg or master_ytcfg, identity_token, player_url, initial_pr)
2475 if pr:
2476 yield pr
2477 # Android player_response does not have microFormats which are needed for
2478 # extraction of some data. So we return the initial_pr with formats
2479 # stripped out even if not requested by the user
2480 # See: https://github.com/yt-dlp/yt-dlp/issues/501
2481 if initial_pr and 'web' not in clients:
2482 initial_pr['streamingData'] = None
2483 yield initial_pr
2484
2485 def _extract_formats(self, streaming_data, video_id, player_url, is_live):
2486 itags, stream_ids = [], []
cc2db878 2487 itag_qualities = {}
d3fc8074 2488 q = qualities([
60bdb7bd 2489 # "tiny" is the smallest video-only format. But some audio-only formats
2490 # was also labeled "tiny". It is not clear if such formats still exist
d3fc8074 2491 'tiny', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
2492 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
2493 ])
11f9be09 2494 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 2495
545cc85d 2496 for fmt in streaming_formats:
2497 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
2498 continue
321bf820 2499
cc2db878 2500 itag = str_or_none(fmt.get('itag'))
9297939e 2501 audio_track = fmt.get('audioTrack') or {}
2502 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
2503 if stream_id in stream_ids:
2504 continue
2505
cc2db878 2506 quality = fmt.get('quality')
d3fc8074 2507 if quality == 'tiny' or not quality:
2508 quality = fmt.get('audioQuality', '').lower() or quality
cc2db878 2509 if itag and quality:
2510 itag_qualities[itag] = quality
2511 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
2512 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
2513 # number of fragment that would subsequently requested with (`&sq=N`)
2514 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
2515 continue
2516
545cc85d 2517 fmt_url = fmt.get('url')
2518 if not fmt_url:
2519 sc = compat_parse_qs(fmt.get('signatureCipher'))
2520 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
2521 encrypted_sig = try_get(sc, lambda x: x['s'][0])
2522 if not (sc and fmt_url and encrypted_sig):
2523 continue
545cc85d 2524 if not player_url:
201e9eaa 2525 continue
545cc85d 2526 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2527 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2528 fmt_url += '&' + sp + '=' + signature
2529
545cc85d 2530 if itag:
2531 itags.append(itag)
9297939e 2532 stream_ids.append(stream_id)
2533
cc2db878 2534 tbr = float_or_none(
2535 fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
545cc85d 2536 dct = {
2537 'asr': int_or_none(fmt.get('audioSampleRate')),
2538 'filesize': int_or_none(fmt.get('contentLength')),
2539 'format_id': itag,
11f9be09 2540 'format_note': ', '.join(filter(None, (
2541 audio_track.get('displayName'), fmt.get('qualityLabel') or quality))),
545cc85d 2542 'fps': int_or_none(fmt.get('fps')),
2543 'height': int_or_none(fmt.get('height')),
dca3ff4a 2544 'quality': q(quality),
cc2db878 2545 'tbr': tbr,
545cc85d 2546 'url': fmt_url,
2547 'width': fmt.get('width'),
0fb983f6 2548 'language': audio_track.get('id', '').split('.')[0],
545cc85d 2549 }
60bdb7bd 2550 mime_mobj = re.match(
2551 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
2552 if mime_mobj:
2553 dct['ext'] = mimetype2ext(mime_mobj.group(1))
2554 dct.update(parse_codecs(mime_mobj.group(2)))
2555 # The 3gp format in android client has a quality of "small",
2556 # but is actually worse than all other formats
2557 if dct['ext'] == '3gp':
2558 dct['quality'] = q('tiny')
11f9be09 2559 dct['preference'] = -10
cc2db878 2560 no_audio = dct.get('acodec') == 'none'
2561 no_video = dct.get('vcodec') == 'none'
2562 if no_audio:
2563 dct['vbr'] = tbr
2564 if no_video:
2565 dct['abr'] = tbr
2566 if no_audio or no_video:
545cc85d 2567 dct['downloader_options'] = {
2568 # Youtube throttles chunks >~10M
2569 'http_chunk_size': 10485760,
bf1317d2 2570 }
7c60c33e 2571 if dct.get('ext'):
2572 dct['container'] = dct['ext'] + '_dash'
11f9be09 2573 yield dct
545cc85d 2574
4bb6b02f 2575 skip_manifests = self._configuration_arg('skip')
11f9be09 2576 get_dash = not is_live and 'dash' not in skip_manifests and self.get_param('youtube_include_dash_manifest', True)
5d3a0e79 2577 get_hls = 'hls' not in skip_manifests and self.get_param('youtube_include_hls_manifest', True)
2578
11f9be09 2579 for sd in streaming_data:
5d3a0e79 2580 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 2581 if hls_manifest_url:
2582 for f in self._extract_m3u8_formats(
2583 hls_manifest_url, video_id, 'mp4', fatal=False):
2584 itag = self._search_regex(
2585 r'/itag/(\d+)', f['url'], 'itag', default=None)
11f9be09 2586 if itag in itags:
2587 continue
9297939e 2588 if itag:
2589 f['format_id'] = itag
11f9be09 2590 itags.append(itag)
2591 yield f
545cc85d 2592
5d3a0e79 2593 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
2594 if dash_manifest_url:
2595 for f in self._extract_mpd_formats(
2596 dash_manifest_url, video_id, fatal=False):
2597 itag = f['format_id']
2598 if itag in itags:
2599 continue
11f9be09 2600 if itag:
2601 itags.append(itag)
5d3a0e79 2602 if itag in itag_qualities:
2603 f['quality'] = q(itag_qualities[itag])
2604 filesize = int_or_none(self._search_regex(
2605 r'/clen/(\d+)', f.get('fragment_base_url')
2606 or f['url'], 'file size', default=None))
2607 if filesize:
2608 f['filesize'] = filesize
11f9be09 2609 yield f
2610
2611 def _real_extract(self, url):
2612 url, smuggled_data = unsmuggle_url(url, {})
2613 video_id = self._match_id(url)
2614
2615 base_url = self.http_scheme() + '//www.youtube.com/'
2616 webpage_url = base_url + 'watch?v=' + video_id
2617 webpage = self._download_webpage(
2618 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
2619
2620 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
2621 player_url = self._extract_player_url(master_ytcfg, webpage)
2622 identity_token = self._extract_identity_token(webpage, video_id)
2623
2624 player_responses = list(self._extract_player_responses(
2625 self._get_requested_clients(url, smuggled_data),
2626 video_id, webpage, master_ytcfg, player_url, identity_token))
2627
352d63fd 2628 get_first = lambda obj, keys, **kwargs: traverse_obj(obj, (..., *variadic(keys)), **kwargs, get_all=False)
11f9be09 2629
2630 playability_statuses = traverse_obj(
2631 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
2632
2633 trailer_video_id = get_first(
2634 playability_statuses,
2635 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
2636 expected_type=str)
2637 if trailer_video_id:
2638 return self.url_result(
2639 trailer_video_id, self.ie_key(), trailer_video_id)
2640
2641 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
2642 if webpage else (lambda x: None))
2643
2644 video_details = traverse_obj(
2645 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
2646 microformats = traverse_obj(
2647 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
2648 expected_type=dict, default=[])
2649 video_title = (
2650 get_first(video_details, 'title')
2651 or self._get_text(microformats, (..., 'title'))
2652 or search_meta(['og:title', 'twitter:title', 'title']))
2653 video_description = get_first(video_details, 'shortDescription')
2654
2655 if not smuggled_data.get('force_singlefeed', False):
2656 if not self.get_param('noplaylist'):
2657 multifeed_metadata_list = get_first(
2658 player_responses,
2659 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
2660 expected_type=str)
2661 if multifeed_metadata_list:
2662 entries = []
2663 feed_ids = []
2664 for feed in multifeed_metadata_list.split(','):
2665 # Unquote should take place before split on comma (,) since textual
2666 # fields may contain comma as well (see
2667 # https://github.com/ytdl-org/youtube-dl/issues/8536)
2668 feed_data = compat_parse_qs(
2669 compat_urllib_parse_unquote_plus(feed))
2670
2671 def feed_entry(name):
2672 return try_get(
2673 feed_data, lambda x: x[name][0], compat_str)
2674
2675 feed_id = feed_entry('id')
2676 if not feed_id:
2677 continue
2678 feed_title = feed_entry('title')
2679 title = video_title
2680 if feed_title:
2681 title += ' (%s)' % feed_title
2682 entries.append({
2683 '_type': 'url_transparent',
2684 'ie_key': 'Youtube',
2685 'url': smuggle_url(
2686 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
2687 {'force_singlefeed': True}),
2688 'title': title,
2689 })
2690 feed_ids.append(feed_id)
2691 self.to_screen(
2692 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
2693 % (', '.join(feed_ids), video_id))
2694 return self.playlist_result(
2695 entries, video_id, video_title, video_description)
2696 else:
2697 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2698
7ea65411 2699 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
11f9be09 2700 is_live = get_first(video_details, 'isLive')
7ea65411 2701 if is_live is None:
2702 is_live = get_first(live_broadcast_details, 'isLiveNow')
11f9be09 2703
2704 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
2705 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
bf1317d2 2706
545cc85d 2707 if not formats:
11f9be09 2708 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
b7da73eb 2709 self.raise_no_formats(
545cc85d 2710 'This video is DRM protected.', expected=True)
11f9be09 2711 pemr = get_first(
2712 playability_statuses,
2713 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
2714 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
2715 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 2716 if subreason:
545cc85d 2717 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 2718 countries = get_first(microformats, 'availableCountries')
545cc85d 2719 if not countries:
2720 regions_allowed = search_meta('regionsAllowed')
2721 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 2722 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 2723 reason += f'. {subreason}'
545cc85d 2724 if reason:
b7da73eb 2725 self.raise_no_formats(reason, expected=True)
bf1317d2 2726
11f9be09 2727 for f in formats:
2728 # TODO: detect if throttled
2729 if '&n=' in f['url']: # possibly throttled
2730 f['source_preference'] = -10
2731 # note = f.get('format_note')
2732 # f['format_note'] = f'{note} (throttled)' if note else '(throttled)'
2733
545cc85d 2734 self._sort_formats(formats)
bf1317d2 2735
11f9be09 2736 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 2737 if not keywords and webpage:
2738 keywords = [
2739 unescapeHTML(m.group('content'))
2740 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
2741 for keyword in keywords:
2742 if keyword.startswith('yt:stretch='):
201c1459 2743 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
2744 if mobj:
2745 # NB: float is intentional for forcing float division
2746 w, h = (float(v) for v in mobj.groups())
2747 if w > 0 and h > 0:
2748 ratio = w / h
2749 for f in formats:
2750 if f.get('vcodec') != 'none':
2751 f['stretched_ratio'] = ratio
2752 break
6449cd80 2753
545cc85d 2754 thumbnails = []
11f9be09 2755 thumbnail_dicts = traverse_obj(
2756 (video_details, microformats), (..., ..., 'thumbnail', 'thumbnails', ...),
2757 expected_type=dict, default=[])
2758 for thumbnail in thumbnail_dicts:
2759 thumbnail_url = thumbnail.get('url')
2760 if not thumbnail_url:
2761 continue
2762 # Sometimes youtube gives a wrong thumbnail URL. See:
2763 # https://github.com/yt-dlp/yt-dlp/issues/233
2764 # https://github.com/ytdl-org/youtube-dl/issues/28023
2765 if 'maxresdefault' in thumbnail_url:
2766 thumbnail_url = thumbnail_url.split('?')[0]
2767 thumbnails.append({
2768 'url': thumbnail_url,
2769 'height': int_or_none(thumbnail.get('height')),
2770 'width': int_or_none(thumbnail.get('width')),
2771 })
ff2751ac 2772 thumbnail_url = search_meta(['og:image', 'twitter:image'])
2773 if thumbnail_url:
2774 thumbnails.append({
2775 'url': thumbnail_url,
ff2751ac 2776 })
0ba692ac 2777 # The best resolution thumbnails sometimes does not appear in the webpage
2778 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 2779 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
2780 hq_thumbnail_names = ['maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3']
245524e6 2781 # TODO: Test them also? - For some videos, even these don't exist
cca80fe6 2782 guaranteed_thumbnail_names = [
2783 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
2784 'mqdefault', 'mq1', 'mq2', 'mq3',
2785 'default', '1', '2', '3'
2786 ]
2787 thumbnail_names = hq_thumbnail_names + guaranteed_thumbnail_names
2788 n_thumbnail_names = len(thumbnail_names)
2789
0ba692ac 2790 thumbnails.extend({
2791 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
2792 video_id=video_id, name=name, ext=ext,
2793 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 2794 '_test_url': name in hq_thumbnail_names,
2795 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 2796 for thumb in thumbnails:
cca80fe6 2797 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 2798 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 2799 self._remove_duplicate_formats(thumbnails)
545cc85d 2800
7ea65411 2801 category = get_first(microformats, 'category') or search_meta('genre')
2802 channel_id = str_or_none(
2803 get_first(video_details, 'channelId')
2804 or get_first(microformats, 'externalChannelId')
2805 or search_meta('channelId'))
2806 duration = int_or_none(
2807 get_first(video_details, 'lengthSeconds')
2808 or get_first(microformats, 'lengthSeconds')
2809 or parse_duration(search_meta('duration'))) or None
2810 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
2811
2812 live_content = get_first(video_details, 'isLiveContent')
2813 is_upcoming = get_first(video_details, 'isUpcoming')
2814 if is_live is None:
2815 if is_upcoming or live_content is False:
2816 is_live = False
2817 if is_upcoming is None and (live_content or is_live):
2818 is_upcoming = False
2819 live_starttime = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
2820 live_endtime = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
2821 if not duration and live_endtime and live_starttime:
2822 duration = live_endtime - live_starttime
2823
545cc85d 2824 info = {
2825 'id': video_id,
2826 'title': self._live_title(video_title) if is_live else video_title,
2827 'formats': formats,
2828 'thumbnails': thumbnails,
2829 'description': video_description,
2830 'upload_date': unified_strdate(
11f9be09 2831 get_first(microformats, 'uploadDate')
545cc85d 2832 or search_meta('uploadDate')),
11f9be09 2833 'uploader': get_first(video_details, 'author'),
545cc85d 2834 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
2835 'uploader_url': owner_profile_url,
2836 'channel_id': channel_id,
11f9be09 2837 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
545cc85d 2838 'duration': duration,
2839 'view_count': int_or_none(
11f9be09 2840 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 2841 or search_meta('interactionCount')),
11f9be09 2842 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 2843 'age_limit': 18 if (
11f9be09 2844 get_first(microformats, 'isFamilySafe') is False
545cc85d 2845 or search_meta('isFamilyFriendly') == 'false'
2846 or search_meta('og:restrictions:age') == '18+') else 0,
2847 'webpage_url': webpage_url,
2848 'categories': [category] if category else None,
2849 'tags': keywords,
11f9be09 2850 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 2851 'is_live': is_live,
2852 'was_live': (False if is_live or is_upcoming or live_content is False
2853 else None if is_live is None or is_upcoming is None
2854 else live_content),
2855 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
2856 'release_timestamp': live_starttime,
545cc85d 2857 }
b477fc13 2858
3944e7af 2859 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
2860 # Converted into dicts to remove duplicates
2861 captions = {
2862 sub.get('baseUrl'): sub
2863 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
2864 translation_languages = {
2865 lang.get('languageCode'): lang.get('languageName')
2866 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
545cc85d 2867 subtitles = {}
2868 if pctr:
774d79cc 2869 def process_language(container, base_url, lang_code, sub_name, query):
120916da 2870 lang_subs = container.setdefault(lang_code, [])
545cc85d 2871 for fmt in self._SUBTITLE_FORMATS:
2872 query.update({
2873 'fmt': fmt,
2874 })
2875 lang_subs.append({
2876 'ext': fmt,
2877 'url': update_url_query(base_url, query),
774d79cc 2878 'name': sub_name,
545cc85d 2879 })
7e72694b 2880
3944e7af 2881 for base_url, caption_track in captions.items():
545cc85d 2882 if not base_url:
2883 continue
2884 if caption_track.get('kind') != 'asr':
120916da 2885 lang_code = (
2886 remove_start(caption_track.get('vssId') or '', '.').replace('.', '-')
2887 or caption_track.get('languageCode'))
545cc85d 2888 if not lang_code:
2889 continue
2890 process_language(
774d79cc 2891 subtitles, base_url, lang_code,
3944e7af 2892 traverse_obj(caption_track, ('name', 'simpleText')),
774d79cc 2893 {})
545cc85d 2894 continue
2895 automatic_captions = {}
3944e7af 2896 for trans_code, trans_name in translation_languages.items():
2897 if not trans_code:
545cc85d 2898 continue
2899 process_language(
3944e7af 2900 automatic_captions, base_url, trans_code,
2901 self._get_text(trans_name, max_runs=1),
2902 {'tlang': trans_code})
545cc85d 2903 info['automatic_captions'] = automatic_captions
2904 info['subtitles'] = subtitles
7e72694b 2905
545cc85d 2906 parsed_url = compat_urllib_parse_urlparse(url)
2907 for component in [parsed_url.fragment, parsed_url.query]:
2908 query = compat_parse_qs(component)
2909 for k, v in query.items():
2910 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
2911 d_k += '_time'
2912 if d_k not in info and k in s_ks:
2913 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
2914
2915 # Youtube Music Auto-generated description
822b9d9c 2916 if video_description:
38d70284 2917 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 2918 if mobj:
822b9d9c
RA
2919 release_year = mobj.group('release_year')
2920 release_date = mobj.group('release_date')
2921 if release_date:
2922 release_date = release_date.replace('-', '')
2923 if not release_year:
545cc85d 2924 release_year = release_date[:4]
2925 info.update({
2926 'album': mobj.group('album'.strip()),
2927 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
2928 'track': mobj.group('track').strip(),
2929 'release_date': release_date,
cc2db878 2930 'release_year': int_or_none(release_year),
545cc85d 2931 })
7e72694b 2932
545cc85d 2933 initial_data = None
2934 if webpage:
2935 initial_data = self._extract_yt_initial_variable(
2936 webpage, self._YT_INITIAL_DATA_RE, video_id,
2937 'yt initial data')
2938 if not initial_data:
11f9be09 2939 headers = self.generate_api_headers(
2940 master_ytcfg, identity_token, self._extract_account_syncid(master_ytcfg),
2941 session_index=self._extract_session_index(master_ytcfg))
2942
109dd3b2 2943 initial_data = self._extract_response(
2944 item_id=video_id, ep='next', fatal=False,
11f9be09 2945 ytcfg=master_ytcfg, headers=headers, query={'videoId': video_id},
109dd3b2 2946 note='Downloading initial data API JSON')
545cc85d 2947
c60ee3a2 2948 try:
2949 # This will error if there is no livechat
2950 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
2951 info['subtitles']['live_chat'] = [{
2952 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
2953 'video_id': video_id,
2954 'ext': 'json',
f6745c49 2955 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 2956 }]
2957 except (KeyError, IndexError, TypeError):
2958 pass
545cc85d 2959
2960 if initial_data:
7c365c21 2961 info['chapters'] = (
2962 self._extract_chapters_from_json(initial_data, duration)
2963 or self._extract_chapters_from_engagement_panel(initial_data, duration)
2964 or None)
545cc85d 2965
2966 contents = try_get(
2967 initial_data,
2968 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
2969 list) or []
2970 for content in contents:
2971 vpir = content.get('videoPrimaryInfoRenderer')
2972 if vpir:
2973 stl = vpir.get('superTitleLink')
2974 if stl:
fe93e2c4 2975 stl = self._get_text(stl)
545cc85d 2976 if try_get(
2977 vpir,
2978 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
2979 info['location'] = stl
2980 else:
2981 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
2982 if mobj:
2983 info.update({
2984 'series': mobj.group(1),
2985 'season_number': int(mobj.group(2)),
2986 'episode_number': int(mobj.group(3)),
2987 })
2988 for tlb in (try_get(
2989 vpir,
2990 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
2991 list) or []):
2992 tbr = tlb.get('toggleButtonRenderer') or {}
2993 for getter, regex in [(
2994 lambda x: x['defaultText']['accessibility']['accessibilityData'],
2995 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
2996 lambda x: x['accessibility'],
2997 lambda x: x['accessibilityData']['accessibilityData'],
2998 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
2999 label = (try_get(tbr, getter, dict) or {}).get('label')
3000 if label:
3001 mobj = re.match(regex, label)
3002 if mobj:
3003 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3004 break
3005 sbr_tooltip = try_get(
3006 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3007 if sbr_tooltip:
3008 like_count, dislike_count = sbr_tooltip.split(' / ')
3009 info.update({
3010 'like_count': str_to_int(like_count),
3011 'dislike_count': str_to_int(dislike_count),
3012 })
3013 vsir = content.get('videoSecondaryInfoRenderer')
3014 if vsir:
052e1350 3015 info['channel'] = self._get_text(vsir, ('owner', 'videoOwnerRenderer', 'title'))
545cc85d 3016 rows = try_get(
3017 vsir,
3018 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3019 list) or []
3020 multiple_songs = False
3021 for row in rows:
3022 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3023 multiple_songs = True
3024 break
3025 for row in rows:
3026 mrr = row.get('metadataRowRenderer') or {}
3027 mrr_title = mrr.get('title')
3028 if not mrr_title:
3029 continue
052e1350 3030 mrr_title = self._get_text(mrr, 'title')
3031 mrr_contents_text = self._get_text(mrr, ('contents', 0))
545cc85d 3032 if mrr_title == 'License':
3033 info['license'] = mrr_contents_text
3034 elif not multiple_songs:
3035 if mrr_title == 'Album':
3036 info['album'] = mrr_contents_text
3037 elif mrr_title == 'Artist':
3038 info['artist'] = mrr_contents_text
3039 elif mrr_title == 'Song':
3040 info['track'] = mrr_contents_text
3041
3042 fallbacks = {
3043 'channel': 'uploader',
3044 'channel_id': 'uploader_id',
3045 'channel_url': 'uploader_url',
3046 }
3047 for to, frm in fallbacks.items():
3048 if not info.get(to):
3049 info[to] = info.get(frm)
3050
3051 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3052 v = info.get(s_k)
3053 if v:
3054 info[d_k] = v
b84071c0 3055
11f9be09 3056 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3057 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3058 is_membersonly = None
b28f8d24 3059 is_premium = None
c224251a
M
3060 if initial_data and is_private is not None:
3061 is_membersonly = False
b28f8d24 3062 is_premium = False
47193e02 3063 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3064 badge_labels = set()
3065 for content in contents:
3066 if not isinstance(content, dict):
3067 continue
3068 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3069 for badge_label in badge_labels:
3070 if badge_label.lower() == 'members only':
3071 is_membersonly = True
3072 elif badge_label.lower() == 'premium':
3073 is_premium = True
3074 elif badge_label.lower() == 'unlisted':
3075 is_unlisted = True
c224251a 3076
c224251a
M
3077 info['availability'] = self._availability(
3078 is_private=is_private,
b28f8d24 3079 needs_premium=is_premium,
c224251a
M
3080 needs_subscription=is_membersonly,
3081 needs_auth=info['age_limit'] >= 18,
3082 is_unlisted=None if is_private is None else is_unlisted)
3083
06167fbb 3084 # get xsrf for annotations or comments
a06916d9 3085 get_annotations = self.get_param('writeannotations', False)
3086 get_comments = self.get_param('getcomments', False)
06167fbb 3087 if get_annotations or get_comments:
29f7c58a 3088 xsrf_token = None
11f9be09 3089 if master_ytcfg:
3090 xsrf_token = try_get(master_ytcfg, lambda x: x['XSRF_TOKEN'], compat_str)
29f7c58a 3091 if not xsrf_token:
3092 xsrf_token = self._search_regex(
3093 r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>(?:(?!\2).)+)\2',
8a784c74 3094 webpage, 'xsrf token', group='xsrf_token', fatal=False)
06167fbb 3095
3096 # annotations
06167fbb 3097 if get_annotations:
11f9be09 3098 invideo_url = get_first(
3099 player_responses,
3100 ('annotations', 0, 'playerAnnotationsUrlsRenderer', 'invideoUrl'),
3101 expected_type=str)
64b6a4e9 3102 if xsrf_token and invideo_url:
29f7c58a 3103 xsrf_field_name = None
11f9be09 3104 if master_ytcfg:
3105 xsrf_field_name = try_get(master_ytcfg, lambda x: x['XSRF_FIELD_NAME'], compat_str)
29f7c58a 3106 if not xsrf_field_name:
3107 xsrf_field_name = self._search_regex(
3108 r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2',
8a784c74 3109 webpage, 'xsrf field name',
29f7c58a 3110 group='xsrf_field_name', default='session_token')
8a784c74 3111 info['annotations'] = self._download_webpage(
64b6a4e9
RA
3112 self._proto_relative_url(invideo_url),
3113 video_id, note='Downloading annotations',
3114 errnote='Unable to download video annotations', fatal=False,
3115 data=urlencode_postdata({xsrf_field_name: xsrf_token}))
7e72694b 3116
277d6ff5 3117 if get_comments:
11f9be09 3118 info['__post_extractor'] = lambda: self._extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3119
11f9be09 3120 self.mark_watched(video_id, player_responses)
d77ab8e2 3121
545cc85d 3122 return info
c5e8d7af 3123
5f6a1245 3124
8bdd16b4 3125class YoutubeTabIE(YoutubeBaseInfoExtractor):
3126 IE_DESC = 'YouTube.com tab'
70d5c17b 3127 _VALID_URL = r'''(?x)
3128 https?://
3129 (?:\w+\.)?
3130 (?:
3131 youtube(?:kids)?\.com|
3132 invidio\.us
3133 )/
3134 (?:
fe03a6cd 3135 (?P<channel_type>channel|c|user|browse)/|
70d5c17b 3136 (?P<not_channel>
9ba5705a 3137 feed/|hashtag/|
70d5c17b 3138 (?:playlist|watch)\?.*?\blist=
3139 )|
29f7c58a 3140 (?!(?:%s)\b) # Direct URLs
70d5c17b 3141 )
3142 (?P<id>[^/?\#&]+)
3143 ''' % YoutubeBaseInfoExtractor._RESERVED_NAMES
8bdd16b4 3144 IE_NAME = 'youtube:tab'
3145
81127aa5 3146 _TESTS = [{
da692b79 3147 'note': 'playlists, multipage',
8bdd16b4 3148 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
3149 'playlist_mincount': 94,
3150 'info_dict': {
3151 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
3152 'title': 'Игорь Клейнер - Playlists',
3153 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
deaec5af 3154 'uploader': 'Игорь Клейнер',
3155 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
8bdd16b4 3156 },
3157 }, {
da692b79 3158 'note': 'playlists, multipage, different order',
8bdd16b4 3159 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
3160 'playlist_mincount': 94,
3161 'info_dict': {
3162 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
3163 'title': 'Игорь Клейнер - Playlists',
3164 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
deaec5af 3165 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
3166 'uploader': 'Игорь Клейнер',
8bdd16b4 3167 },
201c1459 3168 }, {
da692b79 3169 'note': 'playlists, series',
201c1459 3170 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
3171 'playlist_mincount': 5,
3172 'info_dict': {
3173 'id': 'UCYO_jab_esuFRV4b17AJtAw',
3174 'title': '3Blue1Brown - Playlists',
3175 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
da692b79 3176 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
3177 'uploader': '3Blue1Brown',
201c1459 3178 },
8bdd16b4 3179 }, {
da692b79 3180 'note': 'playlists, singlepage',
8bdd16b4 3181 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
3182 'playlist_mincount': 4,
3183 'info_dict': {
3184 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
3185 'title': 'ThirstForScience - Playlists',
3186 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
deaec5af 3187 'uploader': 'ThirstForScience',
3188 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
8bdd16b4 3189 }
3190 }, {
3191 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
3192 'only_matching': True,
3193 }, {
da692b79 3194 'note': 'basic, single video playlist',
0e30a7b9 3195 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
81127aa5 3196 'info_dict': {
0e30a7b9 3197 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
3198 'uploader': 'Sergey M.',
3199 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
3867038a 3200 'title': 'youtube-dl public playlist',
81127aa5 3201 },
0e30a7b9 3202 'playlist_count': 1,
9291475f 3203 }, {
da692b79 3204 'note': 'empty playlist',
0e30a7b9 3205 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
9291475f 3206 'info_dict': {
0e30a7b9 3207 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
3208 'uploader': 'Sergey M.',
3209 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
3867038a 3210 'title': 'youtube-dl empty playlist',
9291475f
PH
3211 },
3212 'playlist_count': 0,
3213 }, {
da692b79 3214 'note': 'Home tab',
8bdd16b4 3215 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
9291475f 3216 'info_dict': {
8bdd16b4 3217 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3218 'title': 'lex will - Home',
3219 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3220 'uploader': 'lex will',
3221 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
9291475f 3222 },
8bdd16b4 3223 'playlist_mincount': 2,
9291475f 3224 }, {
da692b79 3225 'note': 'Videos tab',
8bdd16b4 3226 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
9291475f 3227 'info_dict': {
8bdd16b4 3228 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3229 'title': 'lex will - Videos',
3230 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3231 'uploader': 'lex will',
3232 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
9291475f 3233 },
8bdd16b4 3234 'playlist_mincount': 975,
9291475f 3235 }, {
da692b79 3236 'note': 'Videos tab, sorted by popular',
8bdd16b4 3237 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
9291475f 3238 'info_dict': {
8bdd16b4 3239 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3240 'title': 'lex will - Videos',
3241 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3242 'uploader': 'lex will',
3243 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
9291475f 3244 },
8bdd16b4 3245 'playlist_mincount': 199,
9291475f 3246 }, {
da692b79 3247 'note': 'Playlists tab',
8bdd16b4 3248 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
9291475f 3249 'info_dict': {
8bdd16b4 3250 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3251 'title': 'lex will - Playlists',
3252 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3253 'uploader': 'lex will',
3254 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
9291475f 3255 },
8bdd16b4 3256 'playlist_mincount': 17,
ac7553d0 3257 }, {
da692b79 3258 'note': 'Community tab',
8bdd16b4 3259 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
ac7553d0 3260 'info_dict': {
8bdd16b4 3261 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3262 'title': 'lex will - Community',
3263 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3264 'uploader': 'lex will',
3265 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
8bdd16b4 3266 },
3267 'playlist_mincount': 18,
87dadd45 3268 }, {
da692b79 3269 'note': 'Channels tab',
8bdd16b4 3270 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
87dadd45 3271 'info_dict': {
8bdd16b4 3272 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3273 'title': 'lex will - Channels',
3274 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
deaec5af 3275 'uploader': 'lex will',
3276 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
8bdd16b4 3277 },
deaec5af 3278 'playlist_mincount': 12,
cd684175 3279 }, {
3280 'note': 'Search tab',
3281 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
3282 'playlist_mincount': 40,
3283 'info_dict': {
3284 'id': 'UCYO_jab_esuFRV4b17AJtAw',
3285 'title': '3Blue1Brown - Search - linear algebra',
3286 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
3287 'uploader': '3Blue1Brown',
3288 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
3289 },
6b08cdf6 3290 }, {
a0566bbf 3291 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
8bdd16b4 3292 'only_matching': True,
3293 }, {
a0566bbf 3294 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
8bdd16b4 3295 'only_matching': True,
3296 }, {
a0566bbf 3297 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
8bdd16b4 3298 'only_matching': True,
3299 }, {
3300 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
3301 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
3302 'info_dict': {
3303 'title': '29C3: Not my department',
3304 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
3305 'uploader': 'Christiaan008',
3306 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
deaec5af 3307 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
8bdd16b4 3308 },
3309 'playlist_count': 96,
3310 }, {
3311 'note': 'Large playlist',
3312 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
6b08cdf6 3313 'info_dict': {
8bdd16b4 3314 'title': 'Uploads from Cauchemar',
3315 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
3316 'uploader': 'Cauchemar',
3317 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
13a75688 3318 },
8bdd16b4 3319 'playlist_mincount': 1123,
3320 }, {
da692b79 3321 'note': 'even larger playlist, 8832 videos',
8bdd16b4 3322 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
3323 'only_matching': True,
4b7df0d3
JMF
3324 }, {
3325 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
3326 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
3327 'info_dict': {
acf757f4
PH
3328 'title': 'Uploads from Interstellar Movie',
3329 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
13a75688 3330 'uploader': 'Interstellar Movie',
8bdd16b4 3331 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4b7df0d3 3332 },
481cc733 3333 'playlist_mincount': 21,
358de58c 3334 }, {
3335 'note': 'Playlist with "show unavailable videos" button',
3336 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
3337 'info_dict': {
3338 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
3339 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
3340 'uploader': 'Phim Siêu Nhân Nhật Bản',
3341 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
3342 },
da692b79 3343 'playlist_mincount': 200,
5d342002 3344 }, {
da692b79 3345 'note': 'Playlist with unavailable videos in page 7',
5d342002 3346 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
3347 'info_dict': {
3348 'title': 'Uploads from BlankTV',
3349 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
3350 'uploader': 'BlankTV',
3351 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
3352 },
da692b79 3353 'playlist_mincount': 1000,
8bdd16b4 3354 }, {
da692b79 3355 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
8bdd16b4 3356 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
3357 'info_dict': {
3358 'title': 'Data Analysis with Dr Mike Pound',
3359 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
3360 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
3361 'uploader': 'Computerphile',
deaec5af 3362 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
8bdd16b4 3363 },
3364 'playlist_mincount': 11,
3365 }, {
a0566bbf 3366 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
8bdd16b4 3367 'only_matching': True,
dacb3a86 3368 }, {
da692b79 3369 'note': 'Playlist URL that does not actually serve a playlist',
dacb3a86
S
3370 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
3371 'info_dict': {
3372 'id': 'FqZTN594JQw',
3373 'ext': 'webm',
3374 'title': "Smiley's People 01 detective, Adventure Series, Action",
3375 'uploader': 'STREEM',
3376 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
ec85ded8 3377 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
dacb3a86
S
3378 'upload_date': '20150526',
3379 'license': 'Standard YouTube License',
3380 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
3381 'categories': ['People & Blogs'],
3382 'tags': list,
dbdaaa23 3383 'view_count': int,
dacb3a86
S
3384 'like_count': int,
3385 'dislike_count': int,
3386 },
3387 'params': {
3388 'skip_download': True,
3389 },
13a75688 3390 'skip': 'This video is not available.',
dacb3a86 3391 'add_ie': [YoutubeIE.ie_key()],
481cc733 3392 }, {
8bdd16b4 3393 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
c0345b82 3394 'only_matching': True,
66b48727 3395 }, {
8bdd16b4 3396 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
66b48727 3397 'only_matching': True,
a0566bbf 3398 }, {
3399 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
3400 'info_dict': {
11f9be09 3401 'id': 'FMtPN8yp5LU', # This will keep changing
a0566bbf 3402 'ext': 'mp4',
deaec5af 3403 'title': compat_str,
a0566bbf 3404 'uploader': 'Sky News',
3405 'uploader_id': 'skynews',
3406 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
da692b79 3407 'upload_date': r're:\d{8}',
3408 'description': compat_str,
a0566bbf 3409 'categories': ['News & Politics'],
3410 'tags': list,
3411 'like_count': int,
3412 'dislike_count': int,
3413 },
3414 'params': {
3415 'skip_download': True,
3416 },
da692b79 3417 'expected_warnings': ['Downloading just video ', 'Ignoring subtitle tracks found in '],
a0566bbf 3418 }, {
3419 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
3420 'info_dict': {
3421 'id': 'a48o2S1cPoo',
3422 'ext': 'mp4',
3423 'title': 'The Young Turks - Live Main Show',
3424 'uploader': 'The Young Turks',
3425 'uploader_id': 'TheYoungTurks',
3426 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
3427 'upload_date': '20150715',
3428 'license': 'Standard YouTube License',
3429 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
3430 'categories': ['News & Politics'],
3431 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
3432 'like_count': int,
3433 'dislike_count': int,
3434 },
3435 'params': {
3436 'skip_download': True,
3437 },
3438 'only_matching': True,
3439 }, {
3440 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
3441 'only_matching': True,
3442 }, {
3443 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
3444 'only_matching': True,
09f1580e 3445 }, {
3446 'note': 'A channel that is not live. Should raise error',
3447 'url': 'https://www.youtube.com/user/numberphile/live',
3448 'only_matching': True,
3d3dddc9 3449 }, {
3450 'url': 'https://www.youtube.com/feed/trending',
3451 'only_matching': True,
3452 }, {
3d3dddc9 3453 'url': 'https://www.youtube.com/feed/library',
3454 'only_matching': True,
3455 }, {
3d3dddc9 3456 'url': 'https://www.youtube.com/feed/history',
3457 'only_matching': True,
3458 }, {
3d3dddc9 3459 'url': 'https://www.youtube.com/feed/subscriptions',
3460 'only_matching': True,
3461 }, {
3d3dddc9 3462 'url': 'https://www.youtube.com/feed/watch_later',
3463 'only_matching': True,
3464 }, {
da692b79 3465 'note': 'Recommended - redirects to home page',
3d3dddc9 3466 'url': 'https://www.youtube.com/feed/recommended',
3467 'only_matching': True,
29f7c58a 3468 }, {
da692b79 3469 'note': 'inline playlist with not always working continuations',
29f7c58a 3470 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
3471 'only_matching': True,
3472 }, {
3473 'url': 'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8',
3474 'only_matching': True,
3475 }, {
3476 'url': 'https://www.youtube.com/course',
3477 'only_matching': True,
3478 }, {
3479 'url': 'https://www.youtube.com/zsecurity',
3480 'only_matching': True,
3481 }, {
3482 'url': 'http://www.youtube.com/NASAgovVideo/videos',
3483 'only_matching': True,
3484 }, {
3485 'url': 'https://www.youtube.com/TheYoungTurks/live',
3486 'only_matching': True,
39ed931e 3487 }, {
3488 'url': 'https://www.youtube.com/hashtag/cctv9',
3489 'info_dict': {
3490 'id': 'cctv9',
3491 'title': '#cctv9',
3492 },
3493 'playlist_mincount': 350,
201c1459 3494 }, {
3495 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
3496 'only_matching': True,
9297939e 3497 }, {
da692b79 3498 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
9297939e 3499 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3500 'only_matching': True
fe03a6cd 3501 }, {
3502 'note': '/browse/ should redirect to /channel/',
3503 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
3504 'only_matching': True
3505 }, {
3506 'note': 'VLPL, should redirect to playlist?list=PL...',
3507 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3508 'info_dict': {
3509 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3510 'uploader': 'NoCopyrightSounds',
3511 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
3512 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
3513 'title': 'NCS Releases',
3514 },
3515 'playlist_mincount': 166,
18db7548 3516 }, {
3517 'note': 'Topic, should redirect to playlist?list=UU...',
3518 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
3519 'info_dict': {
3520 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
3521 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
3522 'title': 'Uploads from Royalty Free Music - Topic',
3523 'uploader': 'Royalty Free Music - Topic',
3524 },
3525 'expected_warnings': [
3526 'A channel/user page was given',
3527 'The URL does not have a videos tab',
3528 ],
3529 'playlist_mincount': 101,
3530 }, {
3531 'note': 'Topic without a UU playlist',
3532 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
3533 'info_dict': {
3534 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
3535 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
3536 },
3537 'expected_warnings': [
3538 'A channel/user page was given',
3539 'The URL does not have a videos tab',
3540 'Falling back to channel URL',
3541 ],
3542 'playlist_mincount': 9,
abcdd12b 3543 }, {
3544 'note': 'Youtube music Album',
3545 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
3546 'info_dict': {
3547 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
3548 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
3549 },
3550 'playlist_count': 50,
47193e02 3551 }, {
3552 'note': 'unlisted single video playlist',
3553 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
3554 'info_dict': {
3555 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
3556 'uploader': 'colethedj',
3557 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
3558 'title': 'yt-dlp unlisted playlist test',
3559 'availability': 'unlisted'
3560 },
3561 'playlist_count': 1,
29f7c58a 3562 }]
3563
3564 @classmethod
3565 def suitable(cls, url):
3566 return False if YoutubeIE.suitable(url) else super(
3567 YoutubeTabIE, cls).suitable(url)
8bdd16b4 3568
3569 def _extract_channel_id(self, webpage):
3570 channel_id = self._html_search_meta(
3571 'channelId', webpage, 'channel id', default=None)
3572 if channel_id:
3573 return channel_id
3574 channel_url = self._html_search_meta(
3575 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3576 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3577 'twitter:app:url:googleplay'), webpage, 'channel url')
3578 return self._search_regex(
3579 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3580 channel_url, 'channel id')
15f6397c 3581
8bdd16b4 3582 @staticmethod
cd7c66cf 3583 def _extract_basic_item_renderer(item):
3584 # Modified from _extract_grid_item_renderer
201c1459 3585 known_basic_renderers = (
3586 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
cd7c66cf 3587 )
3588 for key, renderer in item.items():
201c1459 3589 if not isinstance(renderer, dict):
cd7c66cf 3590 continue
201c1459 3591 elif key in known_basic_renderers:
3592 return renderer
3593 elif key.startswith('grid') and key.endswith('Renderer'):
3594 return renderer
8bdd16b4 3595
8bdd16b4 3596 def _grid_entries(self, grid_renderer):
3597 for item in grid_renderer['items']:
3598 if not isinstance(item, dict):
39b62db1 3599 continue
cd7c66cf 3600 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3601 if not isinstance(renderer, dict):
3602 continue
052e1350 3603 title = self._get_text(renderer, 'title')
fe93e2c4 3604
8bdd16b4 3605 # playlist
3606 playlist_id = renderer.get('playlistId')
3607 if playlist_id:
3608 yield self.url_result(
3609 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3610 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3611 video_title=title)
201c1459 3612 continue
8bdd16b4 3613 # video
3614 video_id = renderer.get('videoId')
3615 if video_id:
3616 yield self._extract_video(renderer)
201c1459 3617 continue
8bdd16b4 3618 # channel
3619 channel_id = renderer.get('channelId')
3620 if channel_id:
8bdd16b4 3621 yield self.url_result(
3622 'https://www.youtube.com/channel/%s' % channel_id,
3623 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3624 continue
3625 # generic endpoint URL support
3626 ep_url = urljoin('https://www.youtube.com/', try_get(
3627 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3628 compat_str))
3629 if ep_url:
3630 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3631 if ie.suitable(ep_url):
3632 yield self.url_result(
3633 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3634 break
8bdd16b4 3635
3d3dddc9 3636 def _shelf_entries_from_content(self, shelf_renderer):
3637 content = shelf_renderer.get('content')
3638 if not isinstance(content, dict):
8bdd16b4 3639 return
cd7c66cf 3640 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3641 if renderer:
3642 # TODO: add support for nested playlists so each shelf is processed
3643 # as separate playlist
3644 # TODO: this includes only first N items
3645 for entry in self._grid_entries(renderer):
3646 yield entry
3647 renderer = content.get('horizontalListRenderer')
3648 if renderer:
3649 # TODO
3650 pass
8bdd16b4 3651
29f7c58a 3652 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3653 ep = try_get(
3654 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3655 compat_str)
3656 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3657 if shelf_url:
29f7c58a 3658 # Skipping links to another channels, note that checking for
3659 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3660 # will not work
3661 if skip_channels and '/channels?' in shelf_url:
3662 return
052e1350 3663 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 3664 yield self.url_result(shelf_url, video_title=title)
3665 # Shelf may not contain shelf URL, fallback to extraction from content
3666 for entry in self._shelf_entries_from_content(shelf_renderer):
3667 yield entry
c5e8d7af 3668
8bdd16b4 3669 def _playlist_entries(self, video_list_renderer):
3670 for content in video_list_renderer['contents']:
3671 if not isinstance(content, dict):
3672 continue
3673 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3674 if not isinstance(renderer, dict):
3675 continue
3676 video_id = renderer.get('videoId')
3677 if not video_id:
3678 continue
3679 yield self._extract_video(renderer)
07aeced6 3680
3462ffa8 3681 def _rich_entries(self, rich_grid_renderer):
3682 renderer = try_get(
70d5c17b 3683 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 3684 video_id = renderer.get('videoId')
3685 if not video_id:
3686 return
3687 yield self._extract_video(renderer)
3688
8bdd16b4 3689 def _video_entry(self, video_renderer):
3690 video_id = video_renderer.get('videoId')
3691 if video_id:
3692 return self._extract_video(video_renderer)
dacb3a86 3693
8bdd16b4 3694 def _post_thread_entries(self, post_thread_renderer):
3695 post_renderer = try_get(
3696 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3697 if not post_renderer:
3698 return
3699 # video attachment
3700 video_renderer = try_get(
895b0931 3701 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3702 video_id = video_renderer.get('videoId')
3703 if video_id:
3704 entry = self._extract_video(video_renderer)
8bdd16b4 3705 if entry:
3706 yield entry
895b0931 3707 # playlist attachment
3708 playlist_id = try_get(
3709 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3710 if playlist_id:
3711 yield self.url_result(
e28f1c0a 3712 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3713 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 3714 # inline video links
3715 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3716 for run in runs:
3717 if not isinstance(run, dict):
3718 continue
3719 ep_url = try_get(
3720 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3721 if not ep_url:
3722 continue
3723 if not YoutubeIE.suitable(ep_url):
3724 continue
3725 ep_video_id = YoutubeIE._match_id(ep_url)
3726 if video_id == ep_video_id:
3727 continue
895b0931 3728 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 3729
8bdd16b4 3730 def _post_thread_continuation_entries(self, post_thread_continuation):
3731 contents = post_thread_continuation.get('contents')
3732 if not isinstance(contents, list):
3733 return
3734 for content in contents:
3735 renderer = content.get('backstagePostThreadRenderer')
3736 if not isinstance(renderer, dict):
3737 continue
3738 for entry in self._post_thread_entries(renderer):
3739 yield entry
07aeced6 3740
39ed931e 3741 r''' # unused
3742 def _rich_grid_entries(self, contents):
3743 for content in contents:
3744 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3745 if video_renderer:
3746 entry = self._video_entry(video_renderer)
3747 if entry:
3748 yield entry
3749 '''
f4f751af 3750 def _entries(self, tab, item_id, identity_token, account_syncid, ytcfg):
3462ffa8 3751
70d5c17b 3752 def extract_entries(parent_renderer): # this needs to called again for continuation to work with feeds
3753 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3754 for content in contents:
3755 if not isinstance(content, dict):
8bdd16b4 3756 continue
70d5c17b 3757 is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict)
3462ffa8 3758 if not is_renderer:
70d5c17b 3759 renderer = content.get('richItemRenderer')
3462ffa8 3760 if renderer:
3761 for entry in self._rich_entries(renderer):
3762 yield entry
3763 continuation_list[0] = self._extract_continuation(parent_renderer)
8bdd16b4 3764 continue
3462ffa8 3765 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3766 for isr_content in isr_contents:
3767 if not isinstance(isr_content, dict):
3768 continue
69184e41 3769
3770 known_renderers = {
3771 'playlistVideoListRenderer': self._playlist_entries,
3772 'gridRenderer': self._grid_entries,
3773 'shelfRenderer': lambda x: self._shelf_entries(x, tab.get('title') != 'Channels'),
3774 'backstagePostThreadRenderer': self._post_thread_entries,
3775 'videoRenderer': lambda x: [self._video_entry(x)],
3776 }
3777 for key, renderer in isr_content.items():
3778 if key not in known_renderers:
3779 continue
3780 for entry in known_renderers[key](renderer):
3781 if entry:
3782 yield entry
3462ffa8 3783 continuation_list[0] = self._extract_continuation(renderer)
69184e41 3784 break
70d5c17b 3785
3462ffa8 3786 if not continuation_list[0]:
3787 continuation_list[0] = self._extract_continuation(is_renderer)
70d5c17b 3788
3789 if not continuation_list[0]:
3790 continuation_list[0] = self._extract_continuation(parent_renderer)
3462ffa8 3791
3792 continuation_list = [None] # Python 2 doesnot support nonlocal
29f7c58a 3793 tab_content = try_get(tab, lambda x: x['content'], dict)
3794 if not tab_content:
3795 return
3462ffa8 3796 parent_renderer = (
29f7c58a 3797 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3798 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
70d5c17b 3799 for entry in extract_entries(parent_renderer):
3800 yield entry
3462ffa8 3801 continuation = continuation_list[0]
fe93e2c4 3802 visitor_data = None
d069eca7 3803
8bdd16b4 3804 for page_num in itertools.count(1):
3805 if not continuation:
3806 break
11f9be09 3807 headers = self.generate_api_headers(ytcfg, identity_token, account_syncid, visitor_data)
79360d99 3808 response = self._extract_response(
3809 item_id='%s page %s' % (item_id, page_num),
fe93e2c4 3810 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 3811 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
3812
3813 if not response:
8bdd16b4 3814 break
f4f751af 3815 visitor_data = try_get(
3816 response, lambda x: x['responseContext']['visitorData'], compat_str) or visitor_data
ebf1b291 3817
69184e41 3818 known_continuation_renderers = {
3819 'playlistVideoListContinuation': self._playlist_entries,
3820 'gridContinuation': self._grid_entries,
3821 'itemSectionContinuation': self._post_thread_continuation_entries,
3822 'sectionListContinuation': extract_entries, # for feeds
3823 }
8bdd16b4 3824 continuation_contents = try_get(
69184e41 3825 response, lambda x: x['continuationContents'], dict) or {}
3826 continuation_renderer = None
3827 for key, value in continuation_contents.items():
3828 if key not in known_continuation_renderers:
3462ffa8 3829 continue
69184e41 3830 continuation_renderer = value
3831 continuation_list = [None]
3832 for entry in known_continuation_renderers[key](continuation_renderer):
3833 yield entry
3834 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3835 break
3836 if continuation_renderer:
3837 continue
c5e8d7af 3838
a1b535bd 3839 known_renderers = {
3840 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3841 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 3842 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 3843 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 3844 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 3845 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 3846 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 3847 }
cce889b9 3848 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 3849 continuation_items = try_get(
cce889b9 3850 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 3851 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3852 video_items_renderer = None
3853 for key, value in continuation_item.items():
3854 if key not in known_renderers:
8bdd16b4 3855 continue
a1b535bd 3856 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 3857 continuation_list = [None]
a1b535bd 3858 for entry in known_renderers[key][0](video_items_renderer):
3859 yield entry
9ba5705a 3860 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 3861 break
3862 if video_items_renderer:
3863 continue
8bdd16b4 3864 break
9558dcec 3865
8bdd16b4 3866 @staticmethod
3867 def _extract_selected_tab(tabs):
3868 for tab in tabs:
cd684175 3869 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
3870 if renderer.get('selected') is True:
3871 return renderer
2b3c2546 3872 else:
8bdd16b4 3873 raise ExtractorError('Unable to find selected tab')
b82f815f 3874
47193e02 3875 @classmethod
3876 def _extract_uploader(cls, data):
8bdd16b4 3877 uploader = {}
47193e02 3878 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
3879 owner = try_get(
3880 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3881 if owner:
3882 uploader['uploader'] = owner.get('text')
3883 uploader['uploader_id'] = try_get(
3884 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3885 uploader['uploader_url'] = urljoin(
3886 'https://www.youtube.com/',
3887 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 3888 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 3889
d069eca7 3890 def _extract_from_tabs(self, item_id, webpage, data, tabs):
b60419c5 3891 playlist_id = title = description = channel_url = channel_name = channel_id = None
3892 thumbnails_list = tags = []
3893
8bdd16b4 3894 selected_tab = self._extract_selected_tab(tabs)
3895 renderer = try_get(
3896 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3897 if renderer:
b60419c5 3898 channel_name = renderer.get('title')
3899 channel_url = renderer.get('channelUrl')
3900 channel_id = renderer.get('externalId')
39ed931e 3901 else:
64c0d954 3902 renderer = try_get(
3903 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 3904
8bdd16b4 3905 if renderer:
3906 title = renderer.get('title')
ecc97af3 3907 description = renderer.get('description', '')
b60419c5 3908 playlist_id = channel_id
3909 tags = renderer.get('keywords', '').split()
3910 thumbnails_list = (
3911 try_get(renderer, lambda x: x['avatar']['thumbnails'], list)
ff84930c 3912 or try_get(
47193e02 3913 self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer'),
3914 lambda x: x['thumbnailRenderer']['playlistVideoThumbnailRenderer']['thumbnail']['thumbnails'],
ff84930c 3915 list)
b60419c5 3916 or [])
3917
3918 thumbnails = []
3919 for t in thumbnails_list:
3920 if not isinstance(t, dict):
3921 continue
3922 thumbnail_url = url_or_none(t.get('url'))
3923 if not thumbnail_url:
3924 continue
3925 thumbnails.append({
3926 'url': thumbnail_url,
3927 'width': int_or_none(t.get('width')),
3928 'height': int_or_none(t.get('height')),
3929 })
3462ffa8 3930 if playlist_id is None:
70d5c17b 3931 playlist_id = item_id
3932 if title is None:
39ed931e 3933 title = (
3934 try_get(data, lambda x: x['header']['hashtagHeaderRenderer']['hashtag']['simpleText'])
3935 or playlist_id)
b60419c5 3936 title += format_field(selected_tab, 'title', ' - %s')
cd684175 3937 title += format_field(selected_tab, 'expandedText', ' - %s')
b60419c5 3938 metadata = {
3939 'playlist_id': playlist_id,
3940 'playlist_title': title,
3941 'playlist_description': description,
3942 'uploader': channel_name,
3943 'uploader_id': channel_id,
3944 'uploader_url': channel_url,
3945 'thumbnails': thumbnails,
3946 'tags': tags,
3947 }
47193e02 3948 availability = self._extract_availability(data)
3949 if availability:
3950 metadata['availability'] = availability
b60419c5 3951 if not channel_id:
3952 metadata.update(self._extract_uploader(data))
3953 metadata.update({
3954 'channel': metadata['uploader'],
3955 'channel_id': metadata['uploader_id'],
3956 'channel_url': metadata['uploader_url']})
11f9be09 3957 ytcfg = self.extract_ytcfg(item_id, webpage)
b60419c5 3958 return self.playlist_result(
d069eca7
M
3959 self._entries(
3960 selected_tab, playlist_id,
3961 self._extract_identity_token(webpage, item_id),
fe93e2c4 3962 self._extract_account_syncid(ytcfg, data), ytcfg),
b60419c5 3963 **metadata)
73c4ac2c 3964
79360d99 3965 def _extract_mix_playlist(self, playlist, playlist_id, data, webpage):
2be71994 3966 first_id = last_id = None
11f9be09 3967 ytcfg = self.extract_ytcfg(playlist_id, webpage)
3968 headers = self.generate_api_headers(
fe93e2c4 3969 ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
3970 identity_token=self._extract_identity_token(webpage, item_id=playlist_id))
2be71994 3971 for page_num in itertools.count(1):
cd7c66cf 3972 videos = list(self._playlist_entries(playlist))
3973 if not videos:
3974 return
2be71994 3975 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
3976 if start >= len(videos):
3977 return
3978 for video in videos[start:]:
3979 if video['id'] == first_id:
3980 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
3981 return
3982 yield video
3983 first_id = first_id or videos[0]['id']
3984 last_id = videos[-1]['id']
79360d99 3985 watch_endpoint = try_get(
3986 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
3987 query = {
3988 'playlistId': playlist_id,
3989 'videoId': watch_endpoint.get('videoId') or last_id,
3990 'index': watch_endpoint.get('index') or len(videos),
3991 'params': watch_endpoint.get('params') or 'OAE%3D'
3992 }
3993 response = self._extract_response(
3994 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 3995 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 3996 check_get_keys='contents'
3997 )
cd7c66cf 3998 playlist = try_get(
79360d99 3999 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4000
79360d99 4001 def _extract_from_playlist(self, item_id, url, data, playlist, webpage):
8bdd16b4 4002 title = playlist.get('title') or try_get(
4003 data, lambda x: x['titleText']['simpleText'], compat_str)
4004 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4005
4006 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4007 playlist_url = urljoin(url, try_get(
4008 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4009 compat_str))
4010 if playlist_url and playlist_url != url:
4011 return self.url_result(
4012 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4013 video_title=title)
cd7c66cf 4014
8bdd16b4 4015 return self.playlist_result(
79360d99 4016 self._extract_mix_playlist(playlist, playlist_id, data, webpage),
cd7c66cf 4017 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4018
47193e02 4019 def _extract_availability(self, data):
4020 """
4021 Gets the availability of a given playlist/tab.
4022 Note: Unless YouTube tells us explicitly, we do not assume it is public
4023 @param data: response
4024 """
4025 is_private = is_unlisted = None
4026 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4027 badge_labels = self._extract_badges(renderer)
4028
4029 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4030 privacy_dropdown_entries = try_get(
4031 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4032 for renderer_dict in privacy_dropdown_entries:
4033 is_selected = try_get(
4034 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4035 if not is_selected:
4036 continue
052e1350 4037 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4038 if label:
4039 badge_labels.add(label.lower())
4040 break
4041
4042 for badge_label in badge_labels:
4043 if badge_label == 'unlisted':
4044 is_unlisted = True
4045 elif badge_label == 'private':
4046 is_private = True
4047 elif badge_label == 'public':
4048 is_unlisted = is_private = False
4049 return self._availability(is_private, False, False, False, is_unlisted)
4050
4051 @staticmethod
4052 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4053 sidebar_renderer = try_get(
4054 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4055 for item in sidebar_renderer:
4056 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4057 if renderer:
4058 return renderer
4059
358de58c 4060 def _reload_with_unavailable_videos(self, item_id, data, webpage):
4061 """
4062 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4063 """
5d342002 4064 browse_id = params = None
47193e02 4065 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4066 if not renderer:
4067 return
4068 menu_renderer = try_get(
4069 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4070 for menu_item in menu_renderer:
4071 if not isinstance(menu_item, dict):
358de58c 4072 continue
47193e02 4073 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4074 text = try_get(
4075 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4076 if not text or text.lower() != 'show unavailable videos':
4077 continue
4078 browse_endpoint = try_get(
4079 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4080 browse_id = browse_endpoint.get('browseId')
4081 params = browse_endpoint.get('params')
4082 break
5d342002 4083
11f9be09 4084 ytcfg = self.extract_ytcfg(item_id, webpage)
4085 headers = self.generate_api_headers(
fe93e2c4 4086 ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
47193e02 4087 identity_token=self._extract_identity_token(webpage, item_id=item_id),
4088 visitor_data=try_get(
4089 self._extract_context(ytcfg), lambda x: x['client']['visitorData'], compat_str))
4090 query = {
4091 'params': params or 'wgYCCAA=',
4092 'browseId': browse_id or 'VL%s' % item_id
4093 }
4094 return self._extract_response(
4095 item_id=item_id, headers=headers, query=query,
fe93e2c4 4096 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4097 note='Downloading API JSON with unavailable videos')
358de58c 4098
cd7c66cf 4099 def _extract_webpage(self, url, item_id):
a06916d9 4100 retries = self.get_param('extractor_retries', 3)
62bff2c1 4101 count = -1
c705177d 4102 last_error = 'Incomplete yt initial data recieved'
14fdfea9 4103 while count < retries:
62bff2c1 4104 count += 1
14fdfea9 4105 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4106 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4107 if count:
c705177d 4108 self.report_warning('%s. Retrying ...' % last_error)
5ef7d9bd 4109 webpage = self._download_webpage(
4110 url, item_id,
cd7c66cf 4111 'Downloading webpage%s' % (' (retry #%d)' % count if count else ''))
11f9be09 4112 data = self.extract_yt_initial_data(item_id, webpage)
14fdfea9 4113 if data.get('contents') or data.get('currentVideoEndpoint'):
4114 break
95c01b6c 4115 # Extract alerts here only when there is error
4116 self._extract_and_report_alerts(data)
c705177d 4117 if count >= retries:
6a39ee13 4118 raise ExtractorError(last_error)
cd7c66cf 4119 return webpage, data
4120
9297939e 4121 @staticmethod
4122 def _smuggle_data(entries, data):
4123 for entry in entries:
4124 if data:
4125 entry['url'] = smuggle_url(entry['url'], data)
4126 yield entry
4127
cd7c66cf 4128 def _real_extract(self, url):
9297939e 4129 url, smuggled_data = unsmuggle_url(url, {})
4130 if self.is_music_url(url):
4131 smuggled_data['is_music_url'] = True
fe03a6cd 4132 info_dict = self.__real_extract(url, smuggled_data)
9297939e 4133 if info_dict.get('entries'):
4134 info_dict['entries'] = self._smuggle_data(info_dict['entries'], smuggled_data)
4135 return info_dict
4136
fe03a6cd 4137 _url_re = re.compile(r'(?P<pre>%s)(?(channel_type)(?P<tab>/\w+))?(?P<post>.*)$' % _VALID_URL)
4138
4139 def __real_extract(self, url, smuggled_data):
cd7c66cf 4140 item_id = self._match_id(url)
4141 url = compat_urlparse.urlunparse(
4142 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 4143 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 4144
fe03a6cd 4145 def get_mobj(url):
4146 mobj = self._url_re.match(url).groupdict()
07cce701 4147 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 4148 return mobj
4149
4150 mobj = get_mobj(url)
4151 # Youtube returns incomplete data if tabname is not lower case
4152 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
4153
4154 if is_channel:
4155 if smuggled_data.get('is_music_url'):
4156 if item_id[:2] == 'VL':
4157 # Youtube music VL channels have an equivalent playlist
4158 item_id = item_id[2:]
4159 pre, tab, post, is_channel = 'https://www.youtube.com/playlist?list=%s' % item_id, '', '', False
abcdd12b 4160 elif item_id[:2] == 'MP':
4161 # Youtube music albums (/channel/MP...) have a OLAK playlist that can be extracted from the webpage
4162 item_id = self._search_regex(
4163 r'\\x22audioPlaylistId\\x22:\\x22([0-9A-Za-z_-]+)\\x22',
4164 self._download_webpage('https://music.youtube.com/channel/%s' % item_id, item_id),
4165 'playlist id')
4166 pre, tab, post, is_channel = 'https://www.youtube.com/playlist?list=%s' % item_id, '', '', False
fe03a6cd 4167 elif mobj['channel_type'] == 'browse':
4168 # Youtube music /browse/ should be changed to /channel/
4169 pre = 'https://www.youtube.com/channel/%s' % item_id
4170 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
4171 # Home URLs should redirect to /videos/
6a39ee13 4172 self.report_warning(
cd7c66cf 4173 'A channel/user page was given. All the channel\'s videos will be downloaded. '
4174 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 4175 tab = '/videos'
4176
4177 url = ''.join((pre, tab, post))
4178 mobj = get_mobj(url)
cd7c66cf 4179
4180 # Handle both video/playlist URLs
201c1459 4181 qs = parse_qs(url)
cd7c66cf 4182 video_id = qs.get('v', [None])[0]
4183 playlist_id = qs.get('list', [None])[0]
4184
fe03a6cd 4185 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 4186 if not playlist_id:
fe03a6cd 4187 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 4188 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 4189 # Common mistake: https://www.youtube.com/watch?list=playlist_id
6a39ee13 4190 self.report_warning('A video URL was given without video ID. Trying to download playlist %s' % playlist_id)
cd7c66cf 4191 url = 'https://www.youtube.com/playlist?list=%s' % playlist_id
18db7548 4192 mobj = get_mobj(url)
cd7c66cf 4193
4194 if video_id and playlist_id:
a06916d9 4195 if self.get_param('noplaylist'):
cd7c66cf 4196 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
4197 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
4198 self.to_screen('Downloading playlist %s; add --no-playlist to just download video %s' % (playlist_id, video_id))
4199
4200 webpage, data = self._extract_webpage(url, item_id)
14fdfea9 4201
18db7548 4202 tabs = try_get(
4203 data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
4204 if tabs:
4205 selected_tab = self._extract_selected_tab(tabs)
4206 tab_name = selected_tab.get('title', '')
09f1580e 4207 if 'no-youtube-channel-redirect' not in compat_opts:
4208 if mobj['tab'] == '/live':
4209 # Live tab should have redirected to the video
4210 raise ExtractorError('The channel is not currently live', expected=True)
4211 if mobj['tab'] == '/videos' and tab_name.lower() != mobj['tab'][1:]:
4212 if not mobj['not_channel'] and item_id[:2] == 'UC':
4213 # Topic channels don't have /videos. Use the equivalent playlist instead
4214 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:]))
4215 pl_id = 'UU%s' % item_id[2:]
4216 pl_url = 'https://www.youtube.com/playlist?list=%s%s' % (pl_id, mobj['post'])
4217 try:
4218 pl_webpage, pl_data = self._extract_webpage(pl_url, pl_id)
4219 for alert_type, alert_message in self._extract_alerts(pl_data):
4220 if alert_type == 'error':
4221 raise ExtractorError('Youtube said: %s' % alert_message)
4222 item_id, url, webpage, data = pl_id, pl_url, pl_webpage, pl_data
4223 except ExtractorError:
4224 self.report_warning('The playlist gave error. Falling back to channel URL')
4225 else:
4226 self.report_warning('The URL does not have a %s tab. %s is being downloaded instead' % (mobj['tab'][1:], tab_name))
18db7548 4227
4228 self.write_debug('Final URL: %s' % url)
4229
358de58c 4230 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 4231 if 'no-youtube-unavailable-videos' not in compat_opts:
4232 data = self._reload_with_unavailable_videos(item_id, data, webpage) or data
95c01b6c 4233 self._extract_and_report_alerts(data)
8bdd16b4 4234 tabs = try_get(
4235 data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
4236 if tabs:
d069eca7 4237 return self._extract_from_tabs(item_id, webpage, data, tabs)
cd7c66cf 4238
8bdd16b4 4239 playlist = try_get(
4240 data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4241 if playlist:
79360d99 4242 return self._extract_from_playlist(item_id, url, data, playlist, webpage)
cd7c66cf 4243
a0566bbf 4244 video_id = try_get(
4245 data, lambda x: x['currentVideoEndpoint']['watchEndpoint']['videoId'],
4246 compat_str) or video_id
8bdd16b4 4247 if video_id:
09f1580e 4248 if mobj['tab'] != '/live': # live tab is expected to redirect to video
4249 self.report_warning('Unable to recognize playlist. Downloading just video %s' % video_id)
8bdd16b4 4250 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 4251
8bdd16b4 4252 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 4253
c5e8d7af 4254
8bdd16b4 4255class YoutubePlaylistIE(InfoExtractor):
4256 IE_DESC = 'YouTube.com playlists'
4257 _VALID_URL = r'''(?x)(?:
4258 (?:https?://)?
4259 (?:\w+\.)?
4260 (?:
4261 (?:
4262 youtube(?:kids)?\.com|
29f7c58a 4263 invidio\.us
8bdd16b4 4264 )
4265 /.*?\?.*?\blist=
4266 )?
4267 (?P<id>%(playlist_id)s)
4268 )''' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
4269 IE_NAME = 'youtube:playlist'
cdc628a4 4270 _TESTS = [{
8bdd16b4 4271 'note': 'issue #673',
4272 'url': 'PLBB231211A4F62143',
cdc628a4 4273 'info_dict': {
8bdd16b4 4274 'title': '[OLD]Team Fortress 2 (Class-based LP)',
4275 'id': 'PLBB231211A4F62143',
4276 'uploader': 'Wickydoo',
4277 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 4278 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
8bdd16b4 4279 },
4280 'playlist_mincount': 29,
4281 }, {
4282 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
4283 'info_dict': {
4284 'title': 'YDL_safe_search',
4285 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
4286 },
4287 'playlist_count': 2,
4288 'skip': 'This playlist is private',
9558dcec 4289 }, {
8bdd16b4 4290 'note': 'embedded',
4291 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
4292 'playlist_count': 4,
9558dcec 4293 'info_dict': {
8bdd16b4 4294 'title': 'JODA15',
4295 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
4296 'uploader': 'milan',
4297 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
9558dcec 4298 }
cdc628a4 4299 }, {
8bdd16b4 4300 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 4301 'playlist_mincount': 654,
8bdd16b4 4302 'info_dict': {
4303 'title': '2018 Chinese New Singles (11/6 updated)',
4304 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
4305 'uploader': 'LBK',
4306 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 4307 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
8bdd16b4 4308 }
daa0df9e 4309 }, {
29f7c58a 4310 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
4311 'only_matching': True,
4312 }, {
4313 # music album playlist
4314 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
4315 'only_matching': True,
4316 }]
4317
4318 @classmethod
4319 def suitable(cls, url):
201c1459 4320 if YoutubeTabIE.suitable(url):
4321 return False
1bdae7d3 4322 # Hack for lazy extractors until more generic solution is implemented
4323 # (see #28780)
4324 from .youtube import parse_qs
201c1459 4325 qs = parse_qs(url)
4326 if qs.get('v', [None])[0]:
4327 return False
4328 return super(YoutubePlaylistIE, cls).suitable(url)
29f7c58a 4329
4330 def _real_extract(self, url):
4331 playlist_id = self._match_id(url)
46953e7e 4332 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 4333 url = update_url_query(
4334 'https://www.youtube.com/playlist',
4335 parse_qs(url) or {'list': playlist_id})
4336 if is_music_url:
4337 url = smuggle_url(url, {'is_music_url': True})
4338 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 4339
4340
4341class YoutubeYtBeIE(InfoExtractor):
c76eb41b 4342 IE_DESC = 'youtu.be'
29f7c58a 4343 _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}
4344 _TESTS = [{
8bdd16b4 4345 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
4346 'info_dict': {
4347 'id': 'yeWKywCrFtk',
4348 'ext': 'mp4',
4349 'title': 'Small Scale Baler and Braiding Rugs',
4350 'uploader': 'Backus-Page House Museum',
4351 'uploader_id': 'backuspagemuseum',
4352 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
4353 'upload_date': '20161008',
4354 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
4355 'categories': ['Nonprofits & Activism'],
4356 'tags': list,
4357 'like_count': int,
4358 'dislike_count': int,
4359 },
4360 'params': {
4361 'noplaylist': True,
4362 'skip_download': True,
4363 },
39e7107d 4364 }, {
8bdd16b4 4365 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 4366 'only_matching': True,
cdc628a4
PH
4367 }]
4368
8bdd16b4 4369 def _real_extract(self, url):
29f7c58a 4370 mobj = re.match(self._VALID_URL, url)
4371 video_id = mobj.group('id')
4372 playlist_id = mobj.group('playlist_id')
8bdd16b4 4373 return self.url_result(
29f7c58a 4374 update_url_query('https://www.youtube.com/watch', {
4375 'v': video_id,
4376 'list': playlist_id,
4377 'feature': 'youtu.be',
4378 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4379
4380
4381class YoutubeYtUserIE(InfoExtractor):
c76eb41b 4382 IE_DESC = 'YouTube.com user videos, URL or "ytuser" keyword'
8bdd16b4 4383 _VALID_URL = r'ytuser:(?P<id>.+)'
4384 _TESTS = [{
4385 'url': 'ytuser:phihag',
4386 'only_matching': True,
4387 }]
4388
4389 def _real_extract(self, url):
4390 user_id = self._match_id(url)
4391 return self.url_result(
4392 'https://www.youtube.com/user/%s' % user_id,
4393 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 4394
b05654f0 4395
3d3dddc9 4396class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 4397 IE_NAME = 'youtube:favorites'
4398 IE_DESC = 'YouTube.com liked videos, ":ytfav" for short (requires authentication)'
4399 _VALID_URL = r':ytfav(?:ou?rite)?s?'
4400 _LOGIN_REQUIRED = True
4401 _TESTS = [{
4402 'url': ':ytfav',
4403 'only_matching': True,
4404 }, {
4405 'url': ':ytfavorites',
4406 'only_matching': True,
4407 }]
4408
4409 def _real_extract(self, url):
4410 return self.url_result(
4411 'https://www.youtube.com/playlist?list=LL',
4412 ie=YoutubeTabIE.ie_key())
4413
4414
79360d99 4415class YoutubeSearchIE(SearchInfoExtractor, YoutubeTabIE):
69184e41 4416 IE_DESC = 'YouTube.com searches, "ytsearch" keyword'
b4c08069
JMF
4417 # there doesn't appear to be a real limit, for example if you search for
4418 # 'python' you get more than 8.000.000 results
4419 _MAX_RESULTS = float('inf')
78caa52a 4420 IE_NAME = 'youtube:search'
b05654f0 4421 _SEARCH_KEY = 'ytsearch'
6c894ea1 4422 _SEARCH_PARAMS = None
9dd8e46a 4423 _TESTS = []
b05654f0 4424
6c894ea1 4425 def _entries(self, query, n):
a5c56234 4426 data = {'query': query}
6c894ea1
U
4427 if self._SEARCH_PARAMS:
4428 data['params'] = self._SEARCH_PARAMS
4429 total = 0
fe93e2c4 4430 continuation = {}
6c894ea1 4431 for page_num in itertools.count(1):
fe93e2c4 4432 data.update(continuation)
79360d99 4433 search = self._extract_response(
4434 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
4435 check_get_keys=('contents', 'onResponseReceivedCommands')
4436 )
6c894ea1 4437 if not search:
b4c08069 4438 break
6c894ea1
U
4439 slr_contents = try_get(
4440 search,
4441 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
4442 lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
4443 list)
4444 if not slr_contents:
a22b2fd1 4445 break
0366ae87 4446
0366ae87
M
4447 # Youtube sometimes adds promoted content to searches,
4448 # changing the index location of videos and token.
4449 # So we search through all entries till we find them.
fe93e2c4 4450 continuation = None
30a074c2 4451 for slr_content in slr_contents:
fe93e2c4 4452 if not continuation:
4453 continuation = self._extract_continuation({'contents': [slr_content]})
a96c6d15 4454
30a074c2 4455 isr_contents = try_get(
4456 slr_content,
4457 lambda x: x['itemSectionRenderer']['contents'],
4458 list)
9da76d30 4459 if not isr_contents:
30a074c2 4460 continue
4461 for content in isr_contents:
4462 if not isinstance(content, dict):
4463 continue
4464 video = content.get('videoRenderer')
4465 if not isinstance(video, dict):
4466 continue
4467 video_id = video.get('videoId')
4468 if not video_id:
4469 continue
4470
4471 yield self._extract_video(video)
4472 total += 1
4473 if total == n:
4474 return
0366ae87 4475
fe93e2c4 4476 if not continuation:
6c894ea1 4477 break
b05654f0 4478
6c894ea1
U
4479 def _get_n_results(self, query, n):
4480 """Get a specified number of results for a query"""
11f9be09 4481 return self.playlist_result(self._entries(query, n), query, query)
75dff0ee 4482
c9ae7b95 4483
a3dd9248 4484class YoutubeSearchDateIE(YoutubeSearchIE):
cb7fb546 4485 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 4486 _SEARCH_KEY = 'ytsearchdate'
c76eb41b 4487 IE_DESC = 'YouTube.com searches, newest videos first, "ytsearchdate" keyword'
6c894ea1 4488 _SEARCH_PARAMS = 'CAI%3D'
75dff0ee 4489
c9ae7b95 4490
386e1dd9 4491class YoutubeSearchURLIE(YoutubeSearchIE):
69184e41 4492 IE_DESC = 'YouTube.com search URLs'
386e1dd9 4493 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
4494 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
ef2f3c7f 4495 # _MAX_RESULTS = 100
3462ffa8 4496 _TESTS = [{
4497 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
4498 'playlist_mincount': 5,
4499 'info_dict': {
11f9be09 4500 'id': 'youtube-dl test video',
3462ffa8 4501 'title': 'youtube-dl test video',
4502 }
4503 }, {
4504 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
4505 'only_matching': True,
4506 }]
4507
386e1dd9 4508 @classmethod
4509 def _make_valid_url(cls):
4510 return cls._VALID_URL
4511
3462ffa8 4512 def _real_extract(self, url):
386e1dd9 4513 qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
4514 query = (qs.get('search_query') or qs.get('q'))[0]
4515 self._SEARCH_PARAMS = qs.get('sp', ('',))[0]
4516 return self._get_n_results(query, self._MAX_RESULTS)
3462ffa8 4517
4518
4519class YoutubeFeedsInfoExtractor(YoutubeTabIE):
d7ae0639 4520 """
25f14e9f 4521 Base class for feed extractors
3d3dddc9 4522 Subclasses must define the _FEED_NAME property.
d7ae0639 4523 """
b2e8bc1b 4524 _LOGIN_REQUIRED = True
ef2f3c7f 4525 _TESTS = []
d7ae0639
JMF
4526
4527 @property
4528 def IE_NAME(self):
78caa52a 4529 return 'youtube:%s' % self._FEED_NAME
04cc9617 4530
3853309f 4531 def _real_extract(self, url):
3d3dddc9 4532 return self.url_result(
4533 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
4534 ie=YoutubeTabIE.ie_key())
25f14e9f
S
4535
4536
ef2f3c7f 4537class YoutubeWatchLaterIE(InfoExtractor):
4538 IE_NAME = 'youtube:watchlater'
70d5c17b 4539 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
3d3dddc9 4540 _VALID_URL = r':ytwatchlater'
bc7a9cd8 4541 _TESTS = [{
8bdd16b4 4542 'url': ':ytwatchlater',
bc7a9cd8
S
4543 'only_matching': True,
4544 }]
25f14e9f
S
4545
4546 def _real_extract(self, url):
ef2f3c7f 4547 return self.url_result(
4548 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 4549
4550
25f14e9f
S
4551class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
4552 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
3d3dddc9 4553 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 4554 _FEED_NAME = 'recommended'
45db527f 4555 _LOGIN_REQUIRED = False
3d3dddc9 4556 _TESTS = [{
4557 'url': ':ytrec',
4558 'only_matching': True,
4559 }, {
4560 'url': ':ytrecommended',
4561 'only_matching': True,
4562 }, {
4563 'url': 'https://youtube.com',
4564 'only_matching': True,
4565 }]
1ed5b5c9 4566
1ed5b5c9 4567
25f14e9f 4568class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
70d5c17b 4569 IE_DESC = 'YouTube.com subscriptions feed, ":ytsubs" for short (requires authentication)'
3d3dddc9 4570 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 4571 _FEED_NAME = 'subscriptions'
3d3dddc9 4572 _TESTS = [{
4573 'url': ':ytsubs',
4574 'only_matching': True,
4575 }, {
4576 'url': ':ytsubscriptions',
4577 'only_matching': True,
4578 }]
1ed5b5c9 4579
1ed5b5c9 4580
25f14e9f 4581class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
a5c56234
M
4582 IE_DESC = 'Youtube watch history, ":ythis" for short (requires authentication)'
4583 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 4584 _FEED_NAME = 'history'
3d3dddc9 4585 _TESTS = [{
4586 'url': ':ythistory',
4587 'only_matching': True,
4588 }]
1ed5b5c9
JMF
4589
4590
15870e90
PH
4591class YoutubeTruncatedURLIE(InfoExtractor):
4592 IE_NAME = 'youtube:truncated_url'
4593 IE_DESC = False # Do not list
975d35db 4594 _VALID_URL = r'''(?x)
b95aab84
PH
4595 (?:https?://)?
4596 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
4597 (?:watch\?(?:
c4808c60 4598 feature=[a-z_]+|
b95aab84
PH
4599 annotation_id=annotation_[^&]+|
4600 x-yt-cl=[0-9]+|
c1708b89 4601 hl=[^&]*|
287be8c6 4602 t=[0-9]+
b95aab84
PH
4603 )?
4604 |
4605 attribution_link\?a=[^&]+
4606 )
4607 $
975d35db 4608 '''
15870e90 4609
c4808c60 4610 _TESTS = [{
2d3d2997 4611 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 4612 'only_matching': True,
dc2fc736 4613 }, {
2d3d2997 4614 'url': 'https://www.youtube.com/watch?',
dc2fc736 4615 'only_matching': True,
b95aab84
PH
4616 }, {
4617 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
4618 'only_matching': True,
4619 }, {
4620 'url': 'https://www.youtube.com/watch?feature=foo',
4621 'only_matching': True,
c1708b89
PH
4622 }, {
4623 'url': 'https://www.youtube.com/watch?hl=en-GB',
4624 'only_matching': True,
287be8c6
PH
4625 }, {
4626 'url': 'https://www.youtube.com/watch?t=2372',
4627 'only_matching': True,
c4808c60
PH
4628 }]
4629
15870e90
PH
4630 def _real_extract(self, url):
4631 raise ExtractorError(
78caa52a
PH
4632 'Did you forget to quote the URL? Remember that & is a meta '
4633 'character in most shells, so you want to put the URL in quotes, '
3867038a 4634 'like youtube-dl '
2d3d2997 4635 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 4636 ' or simply youtube-dl BaW_jenozKc .',
15870e90 4637 expected=True)
772fd5cc
PH
4638
4639
4640class YoutubeTruncatedIDIE(InfoExtractor):
4641 IE_NAME = 'youtube:truncated_id'
4642 IE_DESC = False # Do not list
b95aab84 4643 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
4644
4645 _TESTS = [{
4646 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
4647 'only_matching': True,
4648 }]
4649
4650 def _real_extract(self, url):
4651 video_id = self._match_id(url)
4652 raise ExtractorError(
4653 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
4654 expected=True)