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