]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[cleanup] Minor fixes
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
c5e8d7af 1# coding: utf-8
c5e8d7af 2
78caa52a
PH
3from __future__ import unicode_literals
4
d92f5d5a 5import calendar
109dd3b2 6import copy
fe93e2c4 7import datetime
adbc4ec4 8import functools
a5c56234 9import hashlib
0ca96d48 10import itertools
c5e8d7af 11import json
720c3099 12import math
c4417ddb 13import os.path
d77ab8e2 14import random
c5e8d7af 15import re
46383212 16import sys
8a784c74 17import time
e0df6211 18import traceback
adbc4ec4 19import threading
c5e8d7af 20
b05654f0 21from .common import InfoExtractor, SearchInfoExtractor
4bb4a188 22from ..compat import (
edf3e38e 23 compat_chr,
29f7c58a 24 compat_HTTPError,
c5e8d7af 25 compat_parse_qs,
545cc85d 26 compat_str,
7fd002c0 27 compat_urllib_parse_unquote_plus,
15707c7e 28 compat_urllib_parse_urlencode,
7c80519c 29 compat_urllib_parse_urlparse,
7c61bd36 30 compat_urlparse,
4bb4a188 31)
545cc85d 32from ..jsinterp import JSInterpreter
4bb4a188 33from ..utils import (
720c3099 34 bug_reports_message,
c5e8d7af 35 clean_html,
d92f5d5a 36 datetime_from_str,
11f9be09 37 dict_get,
358de58c 38 error_to_compat_str,
c5e8d7af 39 ExtractorError,
2d30521a 40 float_or_none,
11f9be09 41 format_field,
dd27fd17 42 int_or_none,
641ad5d8 43 is_html,
34921b43 44 join_nonempty,
94278f72 45 mimetype2ext,
9c0d7f49 46 network_exceptions,
a6213a49 47 NO_DEFAULT,
11f9be09 48 orderedSet,
6310acf5 49 parse_codecs,
49bd8c66 50 parse_count,
7c80519c 51 parse_duration,
7ea65411 52 parse_iso8601,
4dfbf869 53 parse_qs,
dca3ff4a 54 qualities,
c0ac49bc 55 remove_end,
3995d37d 56 remove_start,
cf7e015f 57 smuggle_url,
dbdaaa23 58 str_or_none,
c93d53f5 59 str_to_int,
f3aa3c3f 60 strftime_or_none,
7c365c21 61 traverse_obj,
556dbe7f 62 try_get,
c5e8d7af
PH
63 unescapeHTML,
64 unified_strdate,
f0d785d3 65 unified_timestamp,
cf7e015f 66 unsmuggle_url,
8bdd16b4 67 update_url_query,
21c340b8 68 url_or_none,
fe93e2c4 69 urljoin,
7c365c21 70 variadic,
c5e8d7af
PH
71)
72
5f6a1245 73
720c3099 74def get_first(obj, keys, **kwargs):
75 return traverse_obj(obj, (..., *variadic(keys)), **kwargs, get_all=False)
76
77
000c15a4 78# any clients starting with _ cannot be explicity requested by the user
79INNERTUBE_CLIENTS = {
80 'web': {
81 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
82 'INNERTUBE_CONTEXT': {
83 'client': {
84 'clientName': 'WEB',
18c7683d 85 'clientVersion': '2.20211221.00.00',
000c15a4 86 }
87 },
88 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
89 },
90 'web_embedded': {
91 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
92 'INNERTUBE_CONTEXT': {
93 'client': {
94 'clientName': 'WEB_EMBEDDED_PLAYER',
18c7683d 95 'clientVersion': '1.20211215.00.01',
000c15a4 96 },
97 },
98 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
99 },
100 'web_music': {
101 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
102 'INNERTUBE_HOST': 'music.youtube.com',
103 'INNERTUBE_CONTEXT': {
104 'client': {
105 'clientName': 'WEB_REMIX',
18c7683d 106 'clientVersion': '1.20211213.00.00',
000c15a4 107 }
108 },
109 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
110 },
e7e94f2a 111 'web_creator': {
18c7683d 112 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
113 'INNERTUBE_CONTEXT': {
114 'client': {
115 'clientName': 'WEB_CREATOR',
18c7683d 116 'clientVersion': '1.20211220.02.00',
e7e94f2a
D
117 }
118 },
119 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
120 },
000c15a4 121 'android': {
18c7683d 122 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 123 'INNERTUBE_CONTEXT': {
124 'client': {
125 'clientName': 'ANDROID',
18c7683d 126 'clientVersion': '16.49',
000c15a4 127 }
128 },
129 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 130 'REQUIRE_JS_PLAYER': False
000c15a4 131 },
132 'android_embedded': {
18c7683d 133 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 134 'INNERTUBE_CONTEXT': {
135 'client': {
136 'clientName': 'ANDROID_EMBEDDED_PLAYER',
18c7683d 137 'clientVersion': '16.49',
000c15a4 138 },
139 },
b6de707d 140 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
141 'REQUIRE_JS_PLAYER': False
000c15a4 142 },
143 'android_music': {
18c7683d 144 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 145 'INNERTUBE_CONTEXT': {
146 'client': {
147 'clientName': 'ANDROID_MUSIC',
18c7683d 148 'clientVersion': '4.57',
000c15a4 149 }
150 },
151 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 152 'REQUIRE_JS_PLAYER': False
000c15a4 153 },
e7e94f2a 154 'android_creator': {
18c7683d 155 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
156 'INNERTUBE_CONTEXT': {
157 'client': {
158 'clientName': 'ANDROID_CREATOR',
18c7683d 159 'clientVersion': '21.47',
e7e94f2a
D
160 },
161 },
b6de707d 162 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
163 'REQUIRE_JS_PLAYER': False
e7e94f2a 164 },
18c7683d 165 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
166 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 167 'ios': {
18c7683d 168 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 169 'INNERTUBE_CONTEXT': {
170 'client': {
171 'clientName': 'IOS',
18c7683d 172 'clientVersion': '16.46',
173 'deviceModel': 'iPhone14,3',
000c15a4 174 }
175 },
b6de707d 176 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
177 'REQUIRE_JS_PLAYER': False
000c15a4 178 },
179 'ios_embedded': {
000c15a4 180 'INNERTUBE_CONTEXT': {
181 'client': {
182 'clientName': 'IOS_MESSAGES_EXTENSION',
18c7683d 183 'clientVersion': '16.46',
184 'deviceModel': 'iPhone14,3',
000c15a4 185 },
186 },
b6de707d 187 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
188 'REQUIRE_JS_PLAYER': False
000c15a4 189 },
190 'ios_music': {
18c7683d 191 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 192 'INNERTUBE_CONTEXT': {
193 'client': {
194 'clientName': 'IOS_MUSIC',
18c7683d 195 'clientVersion': '4.57',
000c15a4 196 },
197 },
b6de707d 198 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
199 'REQUIRE_JS_PLAYER': False
000c15a4 200 },
e7e94f2a
D
201 'ios_creator': {
202 'INNERTUBE_CONTEXT': {
203 'client': {
204 'clientName': 'IOS_CREATOR',
18c7683d 205 'clientVersion': '21.47',
e7e94f2a
D
206 },
207 },
b6de707d 208 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
209 'REQUIRE_JS_PLAYER': False
e7e94f2a 210 },
3619f78d 211 # mweb has 'ultralow' formats
212 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 213 'mweb': {
18c7683d 214 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 215 'INNERTUBE_CONTEXT': {
216 'client': {
217 'clientName': 'MWEB',
18c7683d 218 'clientVersion': '2.20211221.01.00',
000c15a4 219 }
220 },
221 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
18c7683d 222 }
000c15a4 223}
224
225
226def build_innertube_clients():
65c2fde2 227 third_party = {
228 'embedUrl': 'https://google.com', # Can be any valid URL
229 }
000c15a4 230 base_clients = ('android', 'web', 'ios', 'mweb')
231 priority = qualities(base_clients[::-1])
232
233 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 234 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 235 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 236 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 237 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
238 ytcfg['priority'] = 10 * priority(client.split('_', 1)[0])
239
240 if client in base_clients:
241 INNERTUBE_CLIENTS[f'{client}_agegate'] = agegate_ytcfg = copy.deepcopy(ytcfg)
242 agegate_ytcfg['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
65c2fde2 243 agegate_ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party
000c15a4 244 agegate_ytcfg['priority'] -= 1
245 elif client.endswith('_embedded'):
65c2fde2 246 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = third_party
000c15a4 247 ytcfg['priority'] -= 2
248 else:
249 ytcfg['priority'] -= 3
250
251
252build_innertube_clients()
253
254
de7f3446 255class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 256 """Provide base functions for Youtube extractors"""
e00eb564 257
3462ffa8 258 _RESERVED_NAMES = (
3cd786db 259 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
6970b600 260 r'shorts|movies|results|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 261 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 262 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 263
3619f78d 264 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
265
b2e8bc1b 266 _NETRC_MACHINE = 'youtube'
3619f78d 267
b2e8bc1b
JMF
268 # If True it will raise an error if no login info is provided
269 _LOGIN_REQUIRED = False
270
d9190e44
RH
271 _INVIDIOUS_SITES = (
272 # invidious-redirect websites
273 r'(?:www\.)?redirect\.invidious\.io',
274 r'(?:(?:www|dev)\.)?invidio\.us',
275 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
276 r'(?:www\.)?invidious\.pussthecat\.org',
277 r'(?:www\.)?invidious\.zee\.li',
278 r'(?:www\.)?invidious\.ethibox\.fr',
279 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
280 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
281 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
282 # youtube-dl invidious instances list
283 r'(?:(?:www|no)\.)?invidiou\.sh',
284 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
285 r'(?:www\.)?invidious\.kabi\.tk',
286 r'(?:www\.)?invidious\.mastodon\.host',
287 r'(?:www\.)?invidious\.zapashcanon\.fr',
288 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
289 r'(?:www\.)?invidious\.tinfoil-hat\.net',
290 r'(?:www\.)?invidious\.himiko\.cloud',
291 r'(?:www\.)?invidious\.reallyancient\.tech',
292 r'(?:www\.)?invidious\.tube',
293 r'(?:www\.)?invidiou\.site',
294 r'(?:www\.)?invidious\.site',
295 r'(?:www\.)?invidious\.xyz',
296 r'(?:www\.)?invidious\.nixnet\.xyz',
297 r'(?:www\.)?invidious\.048596\.xyz',
298 r'(?:www\.)?invidious\.drycat\.fr',
299 r'(?:www\.)?inv\.skyn3t\.in',
300 r'(?:www\.)?tube\.poal\.co',
301 r'(?:www\.)?tube\.connect\.cafe',
302 r'(?:www\.)?vid\.wxzm\.sx',
303 r'(?:www\.)?vid\.mint\.lgbt',
304 r'(?:www\.)?vid\.puffyan\.us',
305 r'(?:www\.)?yewtu\.be',
306 r'(?:www\.)?yt\.elukerio\.org',
307 r'(?:www\.)?yt\.lelux\.fi',
308 r'(?:www\.)?invidious\.ggc-project\.de',
309 r'(?:www\.)?yt\.maisputain\.ovh',
310 r'(?:www\.)?ytprivate\.com',
311 r'(?:www\.)?invidious\.13ad\.de',
312 r'(?:www\.)?invidious\.toot\.koeln',
313 r'(?:www\.)?invidious\.fdn\.fr',
314 r'(?:www\.)?watch\.nettohikari\.com',
315 r'(?:www\.)?invidious\.namazso\.eu',
316 r'(?:www\.)?invidious\.silkky\.cloud',
317 r'(?:www\.)?invidious\.exonip\.de',
318 r'(?:www\.)?invidious\.riverside\.rocks',
319 r'(?:www\.)?invidious\.blamefran\.net',
320 r'(?:www\.)?invidious\.moomoo\.de',
321 r'(?:www\.)?ytb\.trom\.tf',
322 r'(?:www\.)?yt\.cyberhost\.uk',
323 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
324 r'(?:www\.)?qklhadlycap4cnod\.onion',
325 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
326 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
327 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
328 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
329 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
330 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
331 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
332 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
333 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
334 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
335 )
336
b2e8bc1b 337 def _login(self):
83317f69 338 """
339 Attempt to log in to YouTube.
83317f69 340 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
341 """
9d5d4d64 342
982ee69a
MB
343 if (self._LOGIN_REQUIRED
344 and self.get_param('cookiefile') is None
345 and self.get_param('cookiesfrombrowser') is None):
9d5d4d64 346 self.raise_login_required(
347 'Login details are needed to download this content', method='cookies')
68217024 348 username, password = self._get_login_info()
9d5d4d64 349 if username:
24b0a72b 350 self.report_warning(f'Cannot login to YouTube using username and password. {self._LOGIN_HINTS["cookies"]}')
b2e8bc1b 351
cce889b9 352 def _initialize_consent(self):
353 cookies = self._get_cookies('https://www.youtube.com/')
354 if cookies.get('__Secure-3PSID'):
355 return
356 consent_id = None
357 consent = cookies.get('CONSENT')
358 if consent:
359 if 'YES' in consent.value:
360 return
361 consent_id = self._search_regex(
362 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
363 if not consent_id:
364 consent_id = random.randint(100, 999)
365 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 366
f3aa3c3f 367 def _initialize_pref(self):
368 cookies = self._get_cookies('https://www.youtube.com/')
369 pref_cookie = cookies.get('PREF')
370 pref = {}
371 if pref_cookie:
372 try:
373 pref = dict(compat_urlparse.parse_qsl(pref_cookie.value))
374 except ValueError:
375 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 376 pref.update({'hl': 'en', 'tz': 'UTC'})
f3aa3c3f 377 self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref))
378
b2e8bc1b 379 def _real_initialize(self):
f3aa3c3f 380 self._initialize_pref()
cce889b9 381 self._initialize_consent()
24b0a72b 382 self._login()
c5e8d7af 383
a0566bbf 384 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
29f7c58a 385 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
386 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
a0566bbf 387
000c15a4 388 def _get_default_ytcfg(self, client='web'):
389 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 390
000c15a4 391 def _get_innertube_host(self, client='web'):
392 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 393
000c15a4 394 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 395 # try_get but with fallback to default ytcfg client values when present
396 _func = lambda y: try_get(y, getter, expected_type)
397 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
398
000c15a4 399 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 400 return self._ytcfg_get_safe(
401 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
402 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
109dd3b2 403
000c15a4 404 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 405 return self._ytcfg_get_safe(
406 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
407 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
109dd3b2 408
000c15a4 409 def _extract_api_key(self, ytcfg=None, default_client='web'):
109dd3b2 410 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
411
000c15a4 412 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 413 context = get_first(
414 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 415 # Enforce language and tz for extraction
416 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
417 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 418 return context
419
cf87314d 420 _SAPISID = None
421
109dd3b2 422 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 423 time_now = round(time.time())
cf87314d 424 if self._SAPISID is None:
425 yt_cookies = self._get_cookies('https://www.youtube.com')
426 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
427 # See: https://github.com/yt-dlp/yt-dlp/issues/393
428 sapisid_cookie = dict_get(
429 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
430 if sapisid_cookie and sapisid_cookie.value:
431 self._SAPISID = sapisid_cookie.value
432 self.write_debug('Extracted SAPISID cookie')
433 # SAPISID cookie is required if not already present
434 if not yt_cookies.get('SAPISID'):
435 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
436 self._set_cookie(
437 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
438 else:
439 self._SAPISID = False
440 if not self._SAPISID:
441 return None
1974e99f 442 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
443 sapisidhash = hashlib.sha1(
cf87314d 444 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
1974e99f 445 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
446
447 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 448 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 449 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 450
109dd3b2 451 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 452 data.update(query)
11f9be09 453 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 454 real_headers.update({'content-type': 'application/json'})
455 if headers:
456 real_headers.update(headers)
545cc85d 457 return self._download_json(
109dd3b2 458 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
a5c56234 459 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 460 data=json.dumps(data).encode('utf8'), headers=real_headers,
461 query={'key': api_key or self._extract_api_key()})
462
ac56cf38 463 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
464 data = self._search_regex(
465 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
466 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
467 if data:
468 return self._parse_json(data, item_id, fatal=fatal)
0c148415 469
99e9e001 470 @staticmethod
471 def _extract_session_index(*data):
472 """
473 Index of current account in account list.
474 See: https://github.com/yt-dlp/yt-dlp/pull/519
475 """
476 for ytcfg in data:
477 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
478 if session_index is not None:
479 return session_index
480
481 # Deprecated?
482 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca
M
483 if ytcfg:
484 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
485 if token:
486 return token
99e9e001 487 if webpage:
488 return self._search_regex(
489 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
490 'identity token', default=None, fatal=False)
a1c5d2ca
M
491
492 @staticmethod
fe93e2c4 493 def _extract_account_syncid(*args):
8ea3f7b9 494 """
495 Extract syncId required to download private playlists of secondary channels
fe93e2c4 496 @params response and/or ytcfg
8ea3f7b9 497 """
fe93e2c4 498 for data in args:
499 # ytcfg includes channel_syncid if on secondary channel
500 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
501 if delegated_sid:
502 return delegated_sid
503 sync_ids = (try_get(
504 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
e6f21b3d 505 lambda x: x['DATASYNC_ID']), compat_str) or '').split('||')
fe93e2c4 506 if len(sync_ids) >= 2 and sync_ids[1]:
507 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
508 # and just "user_syncid||" for primary channel. We only want the channel_syncid
509 return sync_ids[0]
a1c5d2ca 510
ac56cf38 511 @staticmethod
512 def _extract_visitor_data(*args):
513 """
514 Extracts visitorData from an API response or ytcfg
515 Appears to be used to track session state
516 """
9222c381 517 return get_first(
6c73052c 518 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 519 expected_type=str)
ac56cf38 520
99e9e001 521 @property
522 def is_authenticated(self):
523 return bool(self._generate_sapisidhash_header())
524
11f9be09 525 def extract_ytcfg(self, video_id, webpage):
8c54a305 526 if not webpage:
527 return {}
29f7c58a 528 return self._parse_json(
529 self._search_regex(
530 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 531 default='{}'), video_id, fatal=False) or {}
532
11f9be09 533 def generate_api_headers(
99e9e001 534 self, *, ytcfg=None, account_syncid=None, session_index=None,
535 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
536
11f9be09 537 origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client))
f4f751af 538 headers = {
109dd3b2 539 'X-YouTube-Client-Name': compat_str(
11f9be09 540 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
541 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 542 'Origin': origin,
543 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
544 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 545 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 546 }
547 if session_index is None:
314ee305 548 session_index = self._extract_session_index(ytcfg)
549 if account_syncid or session_index is not None:
550 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 551
109dd3b2 552 auth = self._generate_sapisidhash_header(origin)
f4f751af 553 if auth is not None:
554 headers['Authorization'] = auth
109dd3b2 555 headers['X-Origin'] = origin
99e9e001 556 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 557
2d6659b9 558 @staticmethod
559 def _build_api_continuation_query(continuation, ctp=None):
560 query = {
561 'continuation': continuation
562 }
563 # TODO: Inconsistency with clickTrackingParams.
564 # Currently we have a fixed ctp contained within context (from ytcfg)
565 # and a ctp in root query for continuation.
566 if ctp:
567 query['clickTracking'] = {'clickTrackingParams': ctp}
568 return query
569
2d6659b9 570 @classmethod
571 def _extract_next_continuation_data(cls, renderer):
572 next_continuation = try_get(
573 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
574 lambda x: x['continuation']['reloadContinuationData']), dict)
575 if not next_continuation:
576 return
577 continuation = next_continuation.get('continuation')
578 if not continuation:
579 return
580 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 581 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 582
583 @classmethod
584 def _extract_continuation_ep_data(cls, continuation_ep: dict):
585 if isinstance(continuation_ep, dict):
586 continuation = try_get(
587 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
588 if not continuation:
589 return
590 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 591 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 592
593 @classmethod
594 def _extract_continuation(cls, renderer):
595 next_continuation = cls._extract_next_continuation_data(renderer)
596 if next_continuation:
597 return next_continuation
fe93e2c4 598
2d6659b9 599 contents = []
600 for key in ('contents', 'items'):
601 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 602
2d6659b9 603 for content in contents:
604 if not isinstance(content, dict):
605 continue
606 continuation_ep = try_get(
607 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
608 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
609 dict)
610 continuation = cls._extract_continuation_ep_data(continuation_ep)
611 if continuation:
612 return continuation
613
fe93e2c4 614 @classmethod
615 def _extract_alerts(cls, data):
109dd3b2 616 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
617 if not isinstance(alert_dict, dict):
618 continue
619 for alert in alert_dict.values():
620 alert_type = alert.get('type')
621 if not alert_type:
622 continue
052e1350 623 message = cls._get_text(alert, 'text')
109dd3b2 624 if message:
625 yield alert_type, message
626
c0ac49bc 627 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 628 errors = []
629 warnings = []
630 for alert_type, alert_message in alerts:
641ad5d8 631 if alert_type.lower() == 'error' and fatal:
109dd3b2 632 errors.append([alert_type, alert_message])
633 else:
634 warnings.append([alert_type, alert_message])
635
636 for alert_type, alert_message in (warnings + errors[:-1]):
c0ac49bc 637 self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message), only_once=only_once)
109dd3b2 638 if errors:
639 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
640
641 def _extract_and_report_alerts(self, data, *args, **kwargs):
642 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
643
47193e02 644 def _extract_badges(self, renderer: dict):
645 badges = set()
646 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
647 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
648 if label:
649 badges.add(label.lower())
650 return badges
651
652 @staticmethod
052e1350 653 def _get_text(data, *path_list, max_runs=None):
654 for path in path_list or [None]:
655 if path is None:
656 obj = [data]
657 else:
658 obj = traverse_obj(data, path, default=[])
659 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
660 obj = [obj]
661 for item in obj:
662 text = try_get(item, lambda x: x['simpleText'], compat_str)
663 if text:
664 return text
665 runs = try_get(item, lambda x: x['runs'], list) or []
666 if not runs and isinstance(item, list):
667 runs = item
668
669 runs = runs[:min(len(runs), max_runs or len(runs))]
670 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
671 if text:
672 return text
47193e02 673
f0d785d3 674 def _get_count(self, data, *path_list):
675 count_text = self._get_text(data, *path_list) or ''
676 count = parse_count(count_text)
677 if count is None:
678 count = str_to_int(
679 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
680 return count
681
a709d873 682 @staticmethod
683 def _extract_thumbnails(data, *path_list):
684 """
685 Extract thumbnails from thumbnails dict
686 @param path_list: path list to level that contains 'thumbnails' key
687 """
688 thumbnails = []
689 for path in path_list or [()]:
690 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
691 thumbnail_url = url_or_none(thumbnail.get('url'))
692 if not thumbnail_url:
693 continue
694 # Sometimes youtube gives a wrong thumbnail URL. See:
695 # https://github.com/yt-dlp/yt-dlp/issues/233
696 # https://github.com/ytdl-org/youtube-dl/issues/28023
697 if 'maxresdefault' in thumbnail_url:
698 thumbnail_url = thumbnail_url.split('?')[0]
699 thumbnails.append({
700 'url': thumbnail_url,
701 'height': int_or_none(thumbnail.get('height')),
702 'width': int_or_none(thumbnail.get('width')),
703 })
704 return thumbnails
705
f3aa3c3f 706 @staticmethod
707 def extract_relative_time(relative_time_text):
708 """
709 Extracts a relative time from string and converts to dt object
f0d785d3 710 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 711 """
f0d785d3 712 mobj = re.search(r'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>microsecond|second|minute|hour|day|week|month|year)s?\s*ago', relative_time_text)
f3aa3c3f 713 if mobj:
f0d785d3 714 start = mobj.group('start')
715 if start:
716 return datetime_from_str(start)
f3aa3c3f 717 try:
f0d785d3 718 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 719 except ValueError:
720 return None
721
722 def _extract_time_text(self, renderer, *path_list):
723 text = self._get_text(renderer, *path_list) or ''
724 dt = self.extract_relative_time(text)
725 timestamp = None
726 if isinstance(dt, datetime.datetime):
727 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 728
729 if timestamp is None:
730 timestamp = (
731 unified_timestamp(text) or unified_timestamp(
732 self._search_regex(
396a76f7 733 (r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*on)?\s*(.+\d)', r'\w+[\s,\.-]*\w+[\s,\.-]+20\d{2}'),
734 text.lower(), 'time text', default=None)))
f0d785d3 735
f3aa3c3f 736 if text and timestamp is None:
737 self.report_warning('Cannot parse localized time text' + bug_reports_message(), only_once=True)
738 return timestamp, text
739
109dd3b2 740 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
741 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 742 default_client='web'):
109dd3b2 743 response = None
744 last_error = None
745 count = -1
746 retries = self.get_param('extractor_retries', 3)
747 if check_get_keys is None:
748 check_get_keys = []
749 while count < retries:
750 count += 1
751 if last_error:
c0ac49bc 752 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
109dd3b2 753 try:
754 response = self._call_api(
755 ep=ep, fatal=True, headers=headers,
756 video_id=item_id, query=query,
757 context=self._extract_context(ytcfg, default_client),
758 api_key=self._extract_api_key(ytcfg, default_client),
759 api_hostname=api_hostname, default_client=default_client,
760 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
761 except ExtractorError as e:
9c0d7f49 762 if isinstance(e.cause, network_exceptions):
641ad5d8 763 if isinstance(e.cause, compat_HTTPError) and not is_html(e.cause.read(512)):
764 e.cause.seek(0)
765 yt_error = try_get(
766 self._parse_json(e.cause.read().decode(), item_id, fatal=False),
767 lambda x: x['error']['message'], compat_str)
768 if yt_error:
769 self._report_alerts([('ERROR', yt_error)], fatal=False)
109dd3b2 770 # Downloading page may result in intermittent 5xx HTTP error
771 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 772 # We also want to catch all other network exceptions since errors in later pages can be troublesome
773 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
774 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
526d74ec 775 last_error = error_to_compat_str(e.cause or e.msg)
9c0d7f49 776 if count < retries:
777 continue
109dd3b2 778 if fatal:
779 raise
780 else:
781 self.report_warning(error_to_compat_str(e))
782 return
783
784 else:
109dd3b2 785 try:
ac56cf38 786 self._extract_and_report_alerts(response, only_once=True)
109dd3b2 787 except ExtractorError as e:
c0ac49bc 788 # YouTube servers may return errors we want to retry on in a 200 OK response
789 # See: https://github.com/yt-dlp/yt-dlp/issues/839
790 if 'unknown error' in e.msg.lower():
791 last_error = e.msg
792 continue
109dd3b2 793 if fatal:
794 raise
795 self.report_warning(error_to_compat_str(e))
796 return
797 if not check_get_keys or dict_get(response, check_get_keys):
798 break
799 # Youtube sometimes sends incomplete data
800 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
801 last_error = 'Incomplete data received'
802 if count >= retries:
803 if fatal:
804 raise ExtractorError(last_error)
805 else:
806 self.report_warning(last_error)
807 return
808 return response
809
9297939e 810 @staticmethod
811 def is_music_url(url):
812 return re.match(r'https?://music\.youtube\.com/', url) is not None
813
30a074c2 814 def _extract_video(self, renderer):
815 video_id = renderer.get('videoId')
052e1350 816 title = self._get_text(renderer, 'title')
817 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 818 duration = parse_duration(self._get_text(
819 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
f0d785d3 820 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 821
052e1350 822 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 823 channel_id = traverse_obj(
824 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), expected_type=str, get_all=False)
825 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
826 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
827 overlay_style = traverse_obj(
828 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all=False, expected_type=str)
829 badges = self._extract_badges(renderer)
a709d873 830 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
831
30a074c2 832 return {
39ed931e 833 '_type': 'url',
30a074c2 834 'ie_key': YoutubeIE.ie_key(),
835 'id': video_id,
5e3f2f8f 836 'url': f'https://www.youtube.com/watch?v={video_id}',
30a074c2 837 'title': title,
838 'description': description,
839 'duration': duration,
840 'view_count': view_count,
841 'uploader': uploader,
f3aa3c3f 842 'channel_id': channel_id,
a709d873 843 'thumbnails': thumbnails,
66f7c6a3 844 # 'upload_date': strftime_or_none(timestamp, '%Y%m%d'),
f3aa3c3f 845 'live_status': ('is_upcoming' if scheduled_timestamp is not None
846 else 'was_live' if 'streamed' in time_text.lower()
847 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
848 else None),
849 'release_timestamp': scheduled_timestamp,
850 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 851 }
852
0c148415 853
360e1ca5 854class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 855 IE_DESC = 'YouTube'
cb7dfeea 856 _VALID_URL = r"""(?x)^
c5e8d7af 857 (
edb53e2d 858 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 859 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
860 (?:www\.)?deturl\.com/www\.youtube\.com|
861 (?:www\.)?pwnyoutube\.com|
862 (?:www\.)?hooktube\.com|
863 (?:www\.)?yourepeat\.com|
864 tube\.majestyc\.net|
865 %(invidious)s|
866 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
867 (?:.*?\#/)? # handle anchor (#/) redirect urls
868 (?: # the various things that can precede the ID:
b6ce9bb0 869 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 870 |(?: # or the v= param in all its forms
f7000f3a 871 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 872 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 873 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
874 v=
875 )
f4b05232 876 ))
cbaed4bb
S
877 |(?:
878 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
879 vid\.plus| # or vid.plus/xxxx
880 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 881 %(invidious)s
cbaed4bb 882 )/
edb53e2d 883 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 884 )
c5e8d7af 885 )? # all until now is optional -> you can pass the naked ID
201c1459 886 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 887 (?(1).+)? # if we found the ID, everything can follow
9297939e 888 (?:\#|$)""" % {
d9190e44 889 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 890 }
e40c758c 891 _PLAYER_INFO_RE = (
cc2db878 892 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
893 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
545cc85d 894 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 895 )
2c62dc26 896 _formats = {
c2d3cb4c 897 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
898 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
899 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
900 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
901 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
902 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
903 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
904 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 905 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 906 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
907 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
908 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
909 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
910 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
911 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 912 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 913 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
914 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 915
916
917 # 3D videos
c2d3cb4c 918 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
919 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
920 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
921 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 922 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
923 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
924 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 925
96fb5605 926 # Apple HTTP Live Streaming
11f12195 927 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 928 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
929 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
930 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
931 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
932 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 933 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
934 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
935
936 # DASH mp4 video
d23028a8
S
937 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
938 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
939 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
940 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
941 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 942 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
943 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
944 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
945 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
946 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
947 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
948 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 949
f6f1fc92 950 # Dash mp4 audio
d23028a8
S
951 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
952 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
953 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
954 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
955 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
956 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
957 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
958
959 # Dash webm
d23028a8
S
960 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
961 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
962 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
963 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
964 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
965 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
966 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
967 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
968 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
969 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
970 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
971 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
972 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
973 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
974 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 975 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
976 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
977 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
978 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
979 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
980 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
981 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
982
983 # Dash webm audio
d23028a8
S
984 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
985 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 986
0857baad 987 # Dash webm audio with opus inside
d23028a8
S
988 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
989 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
990 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 991
ce6b9a2d
PH
992 # RTMP (unnamed)
993 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
994
995 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
996 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
997 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
998 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
999 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1000 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1001 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1002 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1003 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1004 }
29f7c58a 1005 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1006
fd5c4aab
S
1007 _GEO_BYPASS = False
1008
78caa52a 1009 IE_NAME = 'youtube'
2eb88d95
PH
1010 _TESTS = [
1011 {
2d3d2997 1012 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1013 'info_dict': {
1014 'id': 'BaW_jenozKc',
1015 'ext': 'mp4',
3867038a 1016 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1017 'uploader': 'Philipp Hagemeister',
1018 'uploader_id': 'phihag',
ec85ded8 1019 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1020 'channel': 'Philipp Hagemeister',
dd4c4492
S
1021 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1022 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1023 'upload_date': '20121002',
ff9f925b 1024 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1025 'categories': ['Science & Technology'],
3867038a 1026 'tags': ['youtube-dl'],
556dbe7f 1027 'duration': 10,
dbdaaa23 1028 'view_count': int,
3e7c1224 1029 'like_count': int,
ff9f925b 1030 'availability': 'public',
1031 'playable_in_embed': True,
1032 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1033 'live_status': 'not_live',
1034 'age_limit': 0,
7c80519c 1035 'start_time': 1,
297a564b 1036 'end_time': 9,
6c73052c 1037 'channel_follower_count': int
2eb88d95 1038 }
0e853ca4 1039 },
fccd3771 1040 {
4bc3a23e
PH
1041 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1042 'note': 'Embed-only video (#1746)',
1043 'info_dict': {
1044 'id': 'yZIXLfi8CZQ',
1045 'ext': 'mp4',
1046 'upload_date': '20120608',
1047 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1048 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1049 'uploader': 'SET India',
94bfcd23 1050 'uploader_id': 'setindia',
ec85ded8 1051 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1052 'age_limit': 18,
545cc85d 1053 },
1054 'skip': 'Private video',
fccd3771 1055 },
11b56058 1056 {
8bdd16b4 1057 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1058 'note': 'Use the first video ID in the URL',
1059 'info_dict': {
1060 'id': 'BaW_jenozKc',
1061 'ext': 'mp4',
3867038a 1062 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1063 'uploader': 'Philipp Hagemeister',
1064 'uploader_id': 'phihag',
ec85ded8 1065 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1066 'channel': 'Philipp Hagemeister',
1067 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1068 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1069 'upload_date': '20121002',
976ae3ea 1070 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1071 'categories': ['Science & Technology'],
3867038a 1072 'tags': ['youtube-dl'],
556dbe7f 1073 'duration': 10,
dbdaaa23 1074 'view_count': int,
11b56058 1075 'like_count': int,
976ae3ea 1076 'availability': 'public',
1077 'playable_in_embed': True,
1078 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1079 'live_status': 'not_live',
1080 'age_limit': 0,
6c73052c 1081 'channel_follower_count': int
34a7de29
S
1082 },
1083 'params': {
1084 'skip_download': True,
1085 },
11b56058 1086 },
dd27fd17 1087 {
2d3d2997 1088 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1089 'note': '256k DASH audio (format 141) via DASH manifest',
1090 'info_dict': {
1091 'id': 'a9LDPn-MO4I',
1092 'ext': 'm4a',
1093 'upload_date': '20121002',
1094 'uploader_id': '8KVIDEO',
ec85ded8 1095 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1096 'description': '',
1097 'uploader': '8KVIDEO',
1098 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1099 },
4bc3a23e
PH
1100 'params': {
1101 'youtube_include_dash_manifest': True,
1102 'format': '141',
4919603f 1103 },
de3c7fe0 1104 'skip': 'format 141 not served anymore',
dd27fd17 1105 },
8bdd16b4 1106 # DASH manifest with encrypted signature
1107 {
1108 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1109 'info_dict': {
1110 'id': 'IB3lcPjvWLA',
1111 'ext': 'm4a',
1112 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1113 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1114 'duration': 244,
1115 'uploader': 'AfrojackVEVO',
1116 'uploader_id': 'AfrojackVEVO',
1117 'upload_date': '20131011',
cc2db878 1118 'abr': 129.495,
976ae3ea 1119 'like_count': int,
1120 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1121 'playable_in_embed': True,
1122 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1123 'view_count': int,
1124 'track': 'The Spark',
1125 'live_status': 'not_live',
1126 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1127 'channel': 'Afrojack',
1128 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1129 'tags': 'count:19',
1130 'availability': 'public',
1131 'categories': ['Music'],
1132 'age_limit': 0,
1133 'alt_title': 'The Spark',
6c73052c 1134 'channel_follower_count': int
8bdd16b4 1135 },
1136 'params': {
1137 'youtube_include_dash_manifest': True,
1138 'format': '141/bestaudio[ext=m4a]',
1139 },
1140 },
65c2fde2 1141 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1142 {
65c2fde2 1143 'note': 'Embed allowed age-gate video',
2d3d2997 1144 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1145 'info_dict': {
1146 'id': 'HtVdAasjOgU',
1147 'ext': 'mp4',
1148 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1149 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1150 'duration': 142,
c522adb1
JMF
1151 'uploader': 'The Witcher',
1152 'uploader_id': 'WitcherGame',
ec85ded8 1153 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1154 'upload_date': '20140605',
34952f09 1155 'age_limit': 18,
976ae3ea 1156 'categories': ['Gaming'],
1157 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1158 'availability': 'needs_auth',
1159 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1160 'like_count': int,
1161 'channel': 'The Witcher',
1162 'live_status': 'not_live',
1163 'tags': 'count:17',
1164 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1165 'playable_in_embed': True,
1166 'view_count': int,
6c73052c 1167 'channel_follower_count': int
c522adb1
JMF
1168 },
1169 },
65c2fde2 1170 {
1171 'note': 'Age-gate video with embed allowed in public site',
1172 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1173 'info_dict': {
1174 'id': 'HsUATh_Nc2U',
1175 'ext': 'mp4',
1176 'title': 'Godzilla 2 (Official Video)',
1177 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1178 'upload_date': '20200408',
1179 'uploader_id': 'FlyingKitty900',
1180 'uploader': 'FlyingKitty',
1181 'age_limit': 18,
976ae3ea 1182 'availability': 'needs_auth',
1183 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1184 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1185 'channel': 'FlyingKitty',
1186 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1187 'view_count': int,
1188 'categories': ['Entertainment'],
1189 'live_status': 'not_live',
1190 'tags': ['Flyingkitty', 'godzilla 2'],
1191 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1192 'like_count': int,
1193 'duration': 177,
1194 'playable_in_embed': True,
6c73052c 1195 'channel_follower_count': int
65c2fde2 1196 },
1197 },
1198 {
1199 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1200 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1201 'info_dict': {
1202 'id': 'Tq92D6wQ1mg',
1203 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1204 'ext': 'mp4',
1205 'upload_date': '20191227',
65c2fde2 1206 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1207 'uploader': 'Projekt Melody',
1208 'description': 'md5:17eccca93a786d51bc67646756894066',
1209 'age_limit': 18,
976ae3ea 1210 'like_count': int,
1211 'availability': 'needs_auth',
1212 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1213 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1214 'view_count': int,
1215 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1216 'channel': 'Projekt Melody',
1217 'live_status': 'not_live',
1218 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1219 'playable_in_embed': True,
1220 'categories': ['Entertainment'],
1221 'duration': 106,
1222 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
6c73052c 1223 'channel_follower_count': int
65c2fde2 1224 },
1225 },
1226 {
1227 'note': 'Non-Agegated non-embeddable video',
1228 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1229 'info_dict': {
1230 'id': 'MeJVWBSsPAY',
1231 'ext': 'mp4',
1232 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1233 'uploader': 'Herr Lurik',
1234 'uploader_id': 'st3in234',
1235 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1236 'upload_date': '20130730',
976ae3ea 1237 'track': 'Such mich find mich',
1238 'age_limit': 0,
1239 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1240 'like_count': int,
1241 'playable_in_embed': False,
1242 'creator': 'OOMPH!',
1243 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1244 'view_count': int,
1245 'alt_title': 'Such mich find mich',
1246 'duration': 210,
1247 'channel': 'Herr Lurik',
1248 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1249 'categories': ['Music'],
1250 'availability': 'public',
1251 'uploader_url': 'http://www.youtube.com/user/st3in234',
1252 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1253 'live_status': 'not_live',
1254 'artist': 'OOMPH!',
6c73052c 1255 'channel_follower_count': int
65c2fde2 1256 },
1257 },
1258 {
1259 'note': 'Non-bypassable age-gated video',
1260 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1261 'only_matching': True,
1262 },
8bdd16b4 1263 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1264 # YouTube Red ad is not captured for creator
1265 {
1266 'url': '__2ABJjxzNo',
1267 'info_dict': {
1268 'id': '__2ABJjxzNo',
1269 'ext': 'mp4',
1270 'duration': 266,
1271 'upload_date': '20100430',
1272 'uploader_id': 'deadmau5',
1273 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1274 'creator': 'deadmau5',
1275 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1276 'uploader': 'deadmau5',
1277 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1278 'alt_title': 'Some Chords',
976ae3ea 1279 'availability': 'public',
1280 'tags': 'count:14',
1281 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1282 'view_count': int,
1283 'live_status': 'not_live',
1284 'channel': 'deadmau5',
1285 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1286 'like_count': int,
1287 'track': 'Some Chords',
1288 'artist': 'deadmau5',
1289 'playable_in_embed': True,
1290 'age_limit': 0,
1291 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1292 'categories': ['Music'],
1293 'album': 'Some Chords',
6c73052c 1294 'channel_follower_count': int
8bdd16b4 1295 },
1296 'expected_warnings': [
1297 'DASH manifest missing',
1298 ]
1299 },
067aa17e 1300 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1301 {
1302 'url': 'lqQg6PlCWgI',
1303 'info_dict': {
1304 'id': 'lqQg6PlCWgI',
1305 'ext': 'mp4',
556dbe7f 1306 'duration': 6085,
90227264 1307 'upload_date': '20150827',
cbe2bd91 1308 'uploader_id': 'olympic',
ec85ded8 1309 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1310 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1311 'uploader': 'Olympics',
cbe2bd91 1312 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1313 'like_count': int,
1314 'release_timestamp': 1343767800,
1315 'playable_in_embed': True,
1316 'categories': ['Sports'],
1317 'release_date': '20120731',
1318 'channel': 'Olympics',
1319 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1320 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1321 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1322 'age_limit': 0,
1323 'availability': 'public',
1324 'live_status': 'was_live',
1325 'view_count': int,
1326 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1327 'channel_follower_count': int
cbe2bd91
PH
1328 },
1329 'params': {
1330 'skip_download': 'requires avconv',
e52a40ab 1331 }
cbe2bd91 1332 },
6271f1ca
PH
1333 # Non-square pixels
1334 {
1335 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1336 'info_dict': {
1337 'id': '_b-2C3KPAM0',
1338 'ext': 'mp4',
1339 'stretched_ratio': 16 / 9.,
556dbe7f 1340 'duration': 85,
6271f1ca
PH
1341 'upload_date': '20110310',
1342 'uploader_id': 'AllenMeow',
ec85ded8 1343 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1344 '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 1345 'uploader': '孫ᄋᄅ',
6271f1ca 1346 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1347 'playable_in_embed': True,
1348 'channel': '孫ᄋᄅ',
1349 'age_limit': 0,
1350 'tags': 'count:11',
1351 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1352 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1353 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1354 'view_count': int,
1355 'categories': ['People & Blogs'],
1356 'like_count': int,
1357 'live_status': 'not_live',
1358 'availability': 'unlisted',
6c73052c 1359 'channel_follower_count': int
6271f1ca 1360 },
06b491eb
S
1361 },
1362 # url_encoded_fmt_stream_map is empty string
1363 {
1364 'url': 'qEJwOuvDf7I',
1365 'info_dict': {
1366 'id': 'qEJwOuvDf7I',
f57b7835 1367 'ext': 'webm',
06b491eb
S
1368 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1369 'description': '',
1370 'upload_date': '20150404',
1371 'uploader_id': 'spbelect',
1372 'uploader': 'Наблюдатели Петербурга',
1373 },
1374 'params': {
1375 'skip_download': 'requires avconv',
e323cf3f
S
1376 },
1377 'skip': 'This live event has ended.',
06b491eb 1378 },
067aa17e 1379 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1380 {
1381 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1382 'info_dict': {
1383 'id': 'FIl7x6_3R5Y',
eb6793ba 1384 'ext': 'webm',
da77d856
S
1385 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1386 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1387 'duration': 220,
da77d856
S
1388 'upload_date': '20150625',
1389 'uploader_id': 'dorappi2000',
ec85ded8 1390 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1391 'uploader': 'dorappi2000',
eb6793ba 1392 'formats': 'mincount:31',
da77d856 1393 },
eb6793ba 1394 'skip': 'not actual anymore',
2ee8f5d8 1395 },
8a1a26ce
YCH
1396 # DASH manifest with segment_list
1397 {
1398 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1399 'md5': '8ce563a1d667b599d21064e982ab9e31',
1400 'info_dict': {
1401 'id': 'CsmdDsKjzN8',
1402 'ext': 'mp4',
17ee98e1 1403 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1404 'uploader': 'Airtek',
1405 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1406 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1407 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1408 },
1409 'params': {
1410 'youtube_include_dash_manifest': True,
1411 'format': '135', # bestvideo
be49068d
S
1412 },
1413 'skip': 'This live event has ended.',
2ee8f5d8 1414 },
cf7e015f
S
1415 {
1416 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1417 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1418 'info_dict': {
545cc85d 1419 'id': 'jvGDaLqkpTg',
1420 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1421 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1422 },
1423 'playlist': [{
1424 'info_dict': {
545cc85d 1425 'id': 'jvGDaLqkpTg',
cf7e015f 1426 'ext': 'mp4',
545cc85d 1427 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1428 'description': 'md5:e03b909557865076822aa169218d6a5d',
1429 'duration': 10643,
1430 'upload_date': '20161111',
1431 'uploader': 'Team PGP',
1432 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1433 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1434 },
1435 }, {
1436 'info_dict': {
545cc85d 1437 'id': '3AKt1R1aDnw',
cf7e015f 1438 'ext': 'mp4',
545cc85d 1439 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1440 'description': 'md5:e03b909557865076822aa169218d6a5d',
1441 'duration': 10991,
1442 'upload_date': '20161111',
1443 'uploader': 'Team PGP',
1444 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1445 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1446 },
1447 }, {
1448 'info_dict': {
545cc85d 1449 'id': 'RtAMM00gpVc',
cf7e015f 1450 'ext': 'mp4',
545cc85d 1451 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1452 'description': 'md5:e03b909557865076822aa169218d6a5d',
1453 'duration': 10995,
1454 'upload_date': '20161111',
1455 'uploader': 'Team PGP',
1456 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1457 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1458 },
1459 }, {
1460 'info_dict': {
545cc85d 1461 'id': '6N2fdlP3C5U',
cf7e015f 1462 'ext': 'mp4',
545cc85d 1463 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1464 'description': 'md5:e03b909557865076822aa169218d6a5d',
1465 'duration': 10990,
1466 'upload_date': '20161111',
1467 'uploader': 'Team PGP',
1468 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1469 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1470 },
1471 }],
1472 'params': {
1473 'skip_download': True,
1474 },
65c2fde2 1475 'skip': 'Not multifeed anymore',
cbaed4bb 1476 },
f9f49d87 1477 {
067aa17e 1478 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1479 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1480 'info_dict': {
1481 'id': 'gVfLd0zydlo',
1482 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1483 },
1484 'playlist_count': 2,
be49068d 1485 'skip': 'Not multifeed anymore',
f9f49d87 1486 },
cbaed4bb 1487 {
2d3d2997 1488 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1489 'only_matching': True,
0e49d9a6 1490 },
6d4fc66b 1491 {
2d3d2997 1492 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1493 'only_matching': True,
1494 },
0e49d9a6 1495 {
067aa17e 1496 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1497 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1498 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1499 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1500 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1501 'info_dict': {
1502 'id': 'lsguqyKfVQg',
1503 'ext': 'mp4',
1504 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1505 'alt_title': 'Dark Walk',
0e49d9a6 1506 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1507 'duration': 133,
0e49d9a6
LL
1508 'upload_date': '20151119',
1509 'uploader_id': 'IronSoulElf',
ec85ded8 1510 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1511 'uploader': 'IronSoulElf',
11f9be09 1512 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1513 'track': 'Dark Walk',
1514 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1515 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1516 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1517 'categories': ['Film & Animation'],
1518 'view_count': int,
1519 'live_status': 'not_live',
1520 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1521 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1522 'tags': 'count:13',
1523 'availability': 'public',
1524 'channel': 'IronSoulElf',
1525 'playable_in_embed': True,
1526 'like_count': int,
1527 'age_limit': 0,
6c73052c 1528 'channel_follower_count': int
0e49d9a6
LL
1529 },
1530 'params': {
1531 'skip_download': True,
1532 },
1533 },
61f92af1 1534 {
067aa17e 1535 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1536 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1537 'only_matching': True,
1538 },
313dfc45
LL
1539 {
1540 # Video with yt:stretch=17:0
1541 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1542 'info_dict': {
1543 'id': 'Q39EVAstoRM',
1544 'ext': 'mp4',
1545 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1546 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1547 'upload_date': '20151107',
1548 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1549 'uploader': 'CH GAMER DROID',
1550 },
1551 'params': {
1552 'skip_download': True,
1553 },
be49068d 1554 'skip': 'This video does not exist.',
313dfc45 1555 },
201c1459 1556 {
1557 # Video with incomplete 'yt:stretch=16:'
1558 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1559 'only_matching': True,
1560 },
7caf9830
S
1561 {
1562 # Video licensed under Creative Commons
1563 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1564 'info_dict': {
1565 'id': 'M4gD1WSo5mA',
1566 'ext': 'mp4',
1567 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1568 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1569 'duration': 721,
7caf9830
S
1570 'upload_date': '20150127',
1571 'uploader_id': 'BerkmanCenter',
ec85ded8 1572 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1573 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1574 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1575 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1576 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1577 'like_count': int,
1578 'age_limit': 0,
1579 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1580 'channel': 'The Berkman Klein Center for Internet & Society',
1581 'availability': 'public',
1582 'view_count': int,
1583 'categories': ['Education'],
1584 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1585 'live_status': 'not_live',
1586 'playable_in_embed': True,
6c73052c 1587 'channel_follower_count': int
7caf9830
S
1588 },
1589 'params': {
1590 'skip_download': True,
1591 },
1592 },
fd050249
S
1593 {
1594 # Channel-like uploader_url
1595 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1596 'info_dict': {
1597 'id': 'eQcmzGIKrzg',
1598 'ext': 'mp4',
1599 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1600 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1601 'duration': 4060,
fd050249 1602 'upload_date': '20151119',
eb6793ba 1603 'uploader': 'Bernie Sanders',
fd050249 1604 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1605 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1606 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1607 'playable_in_embed': True,
1608 'tags': 'count:12',
1609 'like_count': int,
1610 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1611 'age_limit': 0,
1612 'availability': 'public',
1613 'categories': ['News & Politics'],
1614 'channel': 'Bernie Sanders',
1615 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1616 'view_count': int,
1617 'live_status': 'not_live',
1618 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
6c73052c 1619 'channel_follower_count': int
fd050249
S
1620 },
1621 'params': {
1622 'skip_download': True,
1623 },
1624 },
040ac686
S
1625 {
1626 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1627 'only_matching': True,
7f29cf54
S
1628 },
1629 {
067aa17e 1630 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1631 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1632 'only_matching': True,
6496ccb4
S
1633 },
1634 {
1635 # Rental video preview
1636 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1637 'info_dict': {
1638 'id': 'uGpuVWrhIzE',
1639 'ext': 'mp4',
1640 'title': 'Piku - Trailer',
1641 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1642 'upload_date': '20150811',
1643 'uploader': 'FlixMatrix',
1644 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1645 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1646 'license': 'Standard YouTube License',
1647 },
1648 'params': {
1649 'skip_download': True,
1650 },
eb6793ba 1651 'skip': 'This video is not available.',
022a5d66 1652 },
12afdc2a
S
1653 {
1654 # YouTube Red video with episode data
1655 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1656 'info_dict': {
1657 'id': 'iqKdEhx-dD4',
1658 'ext': 'mp4',
1659 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1660 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1661 'duration': 2085,
12afdc2a
S
1662 'upload_date': '20170118',
1663 'uploader': 'Vsauce',
1664 'uploader_id': 'Vsauce',
1665 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1666 'series': 'Mind Field',
1667 'season_number': 1,
1668 'episode_number': 1,
976ae3ea 1669 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1670 'tags': 'count:12',
1671 'view_count': int,
1672 'availability': 'public',
1673 'age_limit': 0,
1674 'channel': 'Vsauce',
1675 'episode': 'Episode 1',
1676 'categories': ['Entertainment'],
1677 'season': 'Season 1',
1678 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1679 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1680 'like_count': int,
1681 'playable_in_embed': True,
1682 'live_status': 'not_live',
6c73052c 1683 'channel_follower_count': int
12afdc2a
S
1684 },
1685 'params': {
1686 'skip_download': True,
1687 },
1688 'expected_warnings': [
1689 'Skipping DASH manifest',
1690 ],
1691 },
c7121fa7
S
1692 {
1693 # The following content has been identified by the YouTube community
1694 # as inappropriate or offensive to some audiences.
1695 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1696 'info_dict': {
1697 'id': '6SJNVb0GnPI',
1698 'ext': 'mp4',
1699 'title': 'Race Differences in Intelligence',
1700 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1701 'duration': 965,
1702 'upload_date': '20140124',
1703 'uploader': 'New Century Foundation',
1704 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1705 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1706 },
1707 'params': {
1708 'skip_download': True,
1709 },
545cc85d 1710 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1711 },
022a5d66
S
1712 {
1713 # itag 212
1714 'url': '1t24XAntNCY',
1715 'only_matching': True,
fd5c4aab
S
1716 },
1717 {
1718 # geo restricted to JP
1719 'url': 'sJL6WA-aGkQ',
1720 'only_matching': True,
1721 },
cd5a74a2
S
1722 {
1723 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1724 'only_matching': True,
1725 },
bc2ca1bb 1726 {
1727 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1728 'only_matching': True,
1729 },
1730 {
1731 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1732 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1733 'only_matching': True,
1734 },
825cd268
RA
1735 {
1736 # DRM protected
1737 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1738 'only_matching': True,
4fe54c12
S
1739 },
1740 {
1741 # Video with unsupported adaptive stream type formats
1742 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1743 'info_dict': {
1744 'id': 'Z4Vy8R84T1U',
1745 'ext': 'mp4',
1746 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1747 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1748 'duration': 433,
1749 'upload_date': '20130923',
1750 'uploader': 'Amelia Putri Harwita',
1751 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1752 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1753 'formats': 'maxcount:10',
1754 },
1755 'params': {
1756 'skip_download': True,
1757 'youtube_include_dash_manifest': False,
1758 },
5429d6a9 1759 'skip': 'not actual anymore',
5caabd3c 1760 },
1761 {
822b9d9c 1762 # Youtube Music Auto-generated description
5caabd3c 1763 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1764 'info_dict': {
1765 'id': 'MgNrAu2pzNs',
1766 'ext': 'mp4',
1767 'title': 'Voyeur Girl',
1768 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1769 'upload_date': '20190312',
5429d6a9
S
1770 'uploader': 'Stephen - Topic',
1771 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1772 'artist': 'Stephen',
1773 'track': 'Voyeur Girl',
1774 'album': 'it\'s too much love to know my dear',
1775 'release_date': '20190313',
1776 'release_year': 2019,
976ae3ea 1777 'alt_title': 'Voyeur Girl',
1778 'view_count': int,
1779 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1780 'playable_in_embed': True,
1781 'like_count': int,
1782 'categories': ['Music'],
1783 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1784 'channel': 'Stephen',
1785 'availability': 'public',
1786 'creator': 'Stephen',
1787 'duration': 169,
1788 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1789 'age_limit': 0,
1790 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1791 'tags': 'count:11',
1792 'live_status': 'not_live',
6c73052c 1793 'channel_follower_count': int
5caabd3c 1794 },
1795 'params': {
1796 'skip_download': True,
1797 },
1798 },
66b48727
RA
1799 {
1800 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1801 'only_matching': True,
1802 },
011e75e6
S
1803 {
1804 # invalid -> valid video id redirection
1805 'url': 'DJztXj2GPfl',
1806 'info_dict': {
1807 'id': 'DJztXj2GPfk',
1808 'ext': 'mp4',
1809 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1810 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1811 'upload_date': '20090125',
1812 'uploader': 'Prochorowka',
1813 'uploader_id': 'Prochorowka',
1814 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1815 'artist': 'Panjabi MC',
1816 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1817 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1818 },
1819 'params': {
1820 'skip_download': True,
1821 },
545cc85d 1822 'skip': 'Video unavailable',
ea74e00b
DP
1823 },
1824 {
1825 # empty description results in an empty string
1826 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1827 'info_dict': {
1828 'id': 'x41yOUIvK2k',
1829 'ext': 'mp4',
1830 'title': 'IMG 3456',
1831 'description': '',
1832 'upload_date': '20170613',
1833 'uploader_id': 'ElevageOrVert',
1834 'uploader': 'ElevageOrVert',
976ae3ea 1835 'view_count': int,
1836 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1837 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1838 'like_count': int,
1839 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1840 'tags': [],
1841 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1842 'availability': 'public',
1843 'age_limit': 0,
1844 'categories': ['Pets & Animals'],
1845 'duration': 7,
1846 'playable_in_embed': True,
1847 'live_status': 'not_live',
1848 'channel': 'ElevageOrVert',
6c73052c 1849 'channel_follower_count': int
ea74e00b
DP
1850 },
1851 'params': {
1852 'skip_download': True,
1853 },
1854 },
a0566bbf 1855 {
29f7c58a 1856 # with '};' inside yt initial data (see [1])
1857 # see [2] for an example with '};' inside ytInitialPlayerResponse
1858 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1859 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1860 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1861 'info_dict': {
1862 'id': 'CHqg6qOn4no',
1863 'ext': 'mp4',
1864 'title': 'Part 77 Sort a list of simple types in c#',
1865 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1866 'upload_date': '20130831',
1867 'uploader_id': 'kudvenkat',
1868 'uploader': 'kudvenkat',
976ae3ea 1869 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1870 'like_count': int,
1871 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1872 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1873 'live_status': 'not_live',
1874 'categories': ['Education'],
1875 'availability': 'public',
1876 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1877 'tags': 'count:12',
1878 'playable_in_embed': True,
1879 'age_limit': 0,
1880 'view_count': int,
1881 'duration': 522,
1882 'channel': 'kudvenkat',
6c73052c 1883 'channel_follower_count': int
a0566bbf 1884 },
1885 'params': {
1886 'skip_download': True,
1887 },
1888 },
29f7c58a 1889 {
1890 # another example of '};' in ytInitialData
1891 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1892 'only_matching': True,
1893 },
1894 {
1895 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1896 'only_matching': True,
1897 },
545cc85d 1898 {
cc2db878 1899 # https://github.com/ytdl-org/youtube-dl/pull/28094
1900 'url': 'OtqTfy26tG0',
1901 'info_dict': {
1902 'id': 'OtqTfy26tG0',
1903 'ext': 'mp4',
1904 'title': 'Burn Out',
1905 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1906 'upload_date': '20141120',
1907 'uploader': 'The Cinematic Orchestra - Topic',
1908 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1909 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1910 'artist': 'The Cinematic Orchestra',
1911 'track': 'Burn Out',
1912 'album': 'Every Day',
976ae3ea 1913 'like_count': int,
1914 'live_status': 'not_live',
1915 'alt_title': 'Burn Out',
1916 'duration': 614,
1917 'age_limit': 0,
1918 'view_count': int,
1919 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1920 'creator': 'The Cinematic Orchestra',
1921 'channel': 'The Cinematic Orchestra',
1922 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1923 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1924 'availability': 'public',
1925 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1926 'categories': ['Music'],
1927 'playable_in_embed': True,
6c73052c 1928 'channel_follower_count': int
cc2db878 1929 },
1930 'params': {
1931 'skip_download': True,
1932 },
545cc85d 1933 },
bc2ca1bb 1934 {
1935 # controversial video, only works with bpctr when authenticated with cookies
1936 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1937 'only_matching': True,
1938 },
a1a7907b 1939 {
1940 # controversial video, requires bpctr/contentCheckOk
1941 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1942 'info_dict': {
1943 'id': 'SZJvDhaSDnc',
1944 'ext': 'mp4',
1945 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1946 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1947 'uploader': 'CBS Mornings',
11f9be09 1948 'uploader_id': 'CBSThisMorning',
a1a7907b 1949 'upload_date': '20140716',
976ae3ea 1950 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1951 'duration': 170,
1952 'categories': ['News & Politics'],
1953 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1954 'view_count': int,
1955 'channel': 'CBS Mornings',
1956 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1957 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1958 'age_limit': 18,
1959 'availability': 'needs_auth',
1960 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1961 'like_count': int,
1962 'live_status': 'not_live',
1963 'playable_in_embed': True,
6c73052c 1964 'channel_follower_count': int
a1a7907b 1965 }
1966 },
f7ad7160 1967 {
1968 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1969 'url': 'cBvYw8_A0vQ',
1970 'info_dict': {
1971 'id': 'cBvYw8_A0vQ',
1972 'ext': 'mp4',
1973 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1974 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1975 'upload_date': '20201120',
1976 'uploader': 'Walk around Japan',
1977 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1978 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 1979 'duration': 1456,
1980 'categories': ['Travel & Events'],
1981 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1982 'view_count': int,
1983 'channel': 'Walk around Japan',
1984 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
1985 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
1986 'age_limit': 0,
1987 'availability': 'public',
1988 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1989 'live_status': 'not_live',
1990 'playable_in_embed': True,
6c73052c 1991 'channel_follower_count': int
f7ad7160 1992 },
1993 'params': {
1994 'skip_download': True,
1995 },
0fb983f6 1996 }, {
1997 # Has multiple audio streams
1998 'url': 'WaOKSUlf4TM',
1999 'only_matching': True
9297939e 2000 }, {
2001 # Requires Premium: has format 141 when requested using YTM url
2002 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2003 'only_matching': True
2004 }, {
120916da 2005 # multiple subtitles with same lang_code
2006 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2007 'only_matching': True,
109dd3b2 2008 }, {
2009 # Force use android client fallback
2010 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2011 'info_dict': {
2012 'id': 'YOelRv7fMxY',
11f9be09 2013 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2014 'ext': '3gp',
2015 'upload_date': '20210624',
2016 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2017 'uploader': 'colinfurze',
11f9be09 2018 'uploader_id': 'colinfurze',
109dd3b2 2019 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2020 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2021 'duration': 596,
2022 'categories': ['Entertainment'],
2023 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2024 'view_count': int,
2025 'channel': 'colinfurze',
2026 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2027 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2028 'age_limit': 0,
2029 'availability': 'public',
2030 'like_count': int,
2031 'live_status': 'not_live',
2032 'playable_in_embed': True,
6c73052c 2033 'channel_follower_count': int
109dd3b2 2034 },
2035 'params': {
2036 'format': '17', # 3gp format available on android
2037 'extractor_args': {'youtube': {'player_client': ['android']}},
2038 },
120916da 2039 },
109dd3b2 2040 {
2041 # Skip download of additional client configs (remix client config in this case)
2042 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2043 'only_matching': True,
2044 'params': {
2045 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2046 },
8fc54b12 2047 }, {
2048 # shorts
2049 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2050 'only_matching': True,
9222c381 2051 }, {
2052 'note': 'Storyboards',
2053 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2054 'info_dict': {
2055 'id': '5KLPxDtMqe8',
2056 'ext': 'mhtml',
2057 'format_id': 'sb0',
2058 'title': 'Your Brain is Plastic',
2059 'uploader_id': 'scishow',
2060 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2061 'upload_date': '20140324',
2062 'uploader': 'SciShow',
976ae3ea 2063 'like_count': int,
2064 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2065 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2066 'view_count': int,
2067 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2068 'playable_in_embed': True,
2069 'tags': 'count:12',
2070 'uploader_url': 'http://www.youtube.com/user/scishow',
2071 'availability': 'public',
2072 'channel': 'SciShow',
2073 'live_status': 'not_live',
2074 'duration': 248,
2075 'categories': ['Education'],
2076 'age_limit': 0,
6c73052c 2077 'channel_follower_count': int
9222c381 2078 }, 'params': {'format': 'mhtml', 'skip_download': True}
2079 }
2eb88d95
PH
2080 ]
2081
201c1459 2082 @classmethod
2083 def suitable(cls, url):
4dfbf869 2084 from ..utils import parse_qs
2085
201c1459 2086 qs = parse_qs(url)
2087 if qs.get('list', [None])[0]:
2088 return False
2089 return super(YoutubeIE, cls).suitable(url)
2090
e0df6211
PH
2091 def __init__(self, *args, **kwargs):
2092 super(YoutubeIE, self).__init__(*args, **kwargs)
545cc85d 2093 self._code_cache = {}
83799698 2094 self._player_cache = {}
e0df6211 2095
adbc4ec4 2096 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2097 lock = threading.Lock()
2098
2099 is_live = True
185bf310 2100 start_time = time.time()
adbc4ec4
THD
2101 formats = [f for f in formats if f.get('is_from_start')]
2102
185bf310 2103 def refetch_manifest(format_id, delay):
2104 nonlocal formats, start_time, is_live
2105 if time.time() <= start_time + delay:
adbc4ec4
THD
2106 return
2107
2108 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2109 video_details = traverse_obj(
2110 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2111 microformats = traverse_obj(
2112 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2113 expected_type=dict, default=[])
2114 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2115 start_time = time.time()
adbc4ec4 2116
185bf310 2117 def mpd_feed(format_id, delay):
adbc4ec4
THD
2118 """
2119 @returns (manifest_url, manifest_stream_number, is_live) or None
2120 """
2121 with lock:
185bf310 2122 refetch_manifest(format_id, delay)
adbc4ec4
THD
2123
2124 f = next((f for f in formats if f['format_id'] == format_id), None)
2125 if not f:
185bf310 2126 if not is_live:
2127 self.to_screen(f'{video_id}: Video is no longer live')
2128 else:
2129 self.report_warning(
2130 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2131 return None
2132 return f['manifest_url'], f['manifest_stream_number'], is_live
2133
2134 for f in formats:
2135 f['protocol'] = 'http_dash_segments_generator'
2136 f['fragments'] = functools.partial(
2137 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2138
2139 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2140 FETCH_SPAN, MAX_DURATION = 5, 432000
2141
2142 mpd_url, stream_number, is_live = None, None, True
2143
2144 begin_index = 0
2145 download_start_time = ctx.get('start') or time.time()
2146
2147 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2148 if lack_early_segments:
2149 self.report_warning(bug_reports_message(
2150 'Starting download from the last 120 hours of the live stream since '
2151 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2152 lack_early_segments = True
2153
2154 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2155 fragments, fragment_base_url = None, None
2156
2157 def _extract_sequence_from_mpd(refresh_sequence):
2158 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2159 # Obtain from MPD's maximum seq value
2160 old_mpd_url = mpd_url
185bf310 2161 last_error = ctx.pop('last_error', None)
2162 expire_fast = last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
2163 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2164 or (mpd_url, stream_number, False))
2165 if not refresh_sequence:
2166 if expire_fast and not is_live:
2167 return False, last_seq
2168 elif old_mpd_url == mpd_url:
2169 return True, last_seq
adbc4ec4
THD
2170 try:
2171 fmts, _ = self._extract_mpd_formats_and_subtitles(
2172 mpd_url, None, note=False, errnote=False, fatal=False)
2173 except ExtractorError:
2174 fmts = None
2175 if not fmts:
2176 no_fragment_score += 1
2177 return False, last_seq
2178 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2179 fragments = fmt_info['fragments']
2180 fragment_base_url = fmt_info['fragment_base_url']
2181 assert fragment_base_url
2182
2183 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2184 return True, _last_seq
2185
2186 while is_live:
2187 fetch_time = time.time()
2188 if no_fragment_score > 30:
2189 return
2190 if last_segment_url:
2191 # Obtain from "X-Head-Seqnum" header value from each segment
2192 try:
2193 urlh = self._request_webpage(
2194 last_segment_url, None, note=False, errnote=False, fatal=False)
2195 except ExtractorError:
2196 urlh = None
2197 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2198 if last_seq is None:
2199 no_fragment_score += 1
2200 last_segment_url = None
2201 continue
2202 else:
185bf310 2203 should_continue, last_seq = _extract_sequence_from_mpd(True)
2204 if not should_continue:
adbc4ec4
THD
2205 continue
2206
2207 if known_idx > last_seq:
2208 last_segment_url = None
2209 continue
2210
2211 last_seq += 1
2212
2213 if begin_index < 0 and known_idx < 0:
2214 # skip from the start when it's negative value
2215 known_idx = last_seq + begin_index
2216 if lack_early_segments:
2217 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2218 try:
2219 for idx in range(known_idx, last_seq):
2220 # do not update sequence here or you'll get skipped some part of it
185bf310 2221 should_continue, _ = _extract_sequence_from_mpd(False)
2222 if not should_continue:
adbc4ec4
THD
2223 known_idx = idx - 1
2224 raise ExtractorError('breaking out of outer loop')
2225 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2226 yield {
2227 'url': last_segment_url,
2228 }
2229 if known_idx == last_seq:
2230 no_fragment_score += 5
2231 else:
2232 no_fragment_score = 0
2233 known_idx = last_seq
2234 except ExtractorError:
2235 continue
2236
2237 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2238
b6de707d 2239 def _extract_player_url(self, *ytcfgs, webpage=None):
2240 player_url = traverse_obj(
2241 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2242 get_all=False, expected_type=compat_str)
11f9be09 2243 if not player_url:
b6de707d 2244 return
109dd3b2 2245 if player_url.startswith('//'):
2246 player_url = 'https:' + player_url
2247 elif not re.match(r'https?://', player_url):
2248 player_url = compat_urlparse.urljoin(
2249 'https://www.youtube.com', player_url)
2250 return player_url
2251
b6de707d 2252 def _download_player_url(self, video_id, fatal=False):
2253 res = self._download_webpage(
2254 'https://www.youtube.com/iframe_api',
2255 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2256 if res:
2257 player_version = self._search_regex(
2258 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2259 if player_version:
2260 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2261
60064c53
PH
2262 def _signature_cache_id(self, example_sig):
2263 """ Return a string representation of a signature """
78caa52a 2264 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 2265
e40c758c
S
2266 @classmethod
2267 def _extract_player_info(cls, player_url):
2268 for player_re in cls._PLAYER_INFO_RE:
2269 id_m = re.search(player_re, player_url)
2270 if id_m:
2271 break
2272 else:
c081b35c 2273 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2274 return id_m.group('id')
e40c758c 2275
404f611f 2276 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2277 player_id = self._extract_player_info(player_url)
2278 if player_id not in self._code_cache:
1276a43a 2279 code = self._download_webpage(
109dd3b2 2280 player_url, video_id, fatal=fatal,
2281 note='Downloading player ' + player_id,
2282 errnote='Download of %s failed' % player_url)
1276a43a 2283 if code:
2284 self._code_cache[player_id] = code
404f611f 2285 return self._code_cache.get(player_id)
109dd3b2 2286
e40c758c 2287 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2288 player_id = self._extract_player_info(player_url)
e0df6211 2289
c4417ddb 2290 # Read from filesystem cache
545cc85d 2291 func_id = 'js_%s_%s' % (
2292 player_id, self._signature_cache_id(example_sig))
c4417ddb 2293 assert os.path.basename(func_id) == func_id
a0e07d31 2294
69ea8ca4 2295 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2296 if cache_spec is not None:
78caa52a 2297 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2298
404f611f 2299 code = self._load_player(video_id, player_url)
2300 if code:
109dd3b2 2301 res = self._parse_sig_js(code)
e0df6211 2302
109dd3b2 2303 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2304 cache_res = res(test_string)
2305 cache_spec = [ord(c) for c in cache_res]
83799698 2306
109dd3b2 2307 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
2308 return res
83799698 2309
60064c53 2310 def _print_sig_code(self, func, example_sig):
404f611f 2311 if not self.get_param('youtube_print_sig_code'):
2312 return
2313
edf3e38e
PH
2314 def gen_sig_code(idxs):
2315 def _genslice(start, end, step):
78caa52a 2316 starts = '' if start == 0 else str(start)
8bcc8756 2317 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2318 steps = '' if step == 1 else (':%d' % step)
78caa52a 2319 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
2320
2321 step = None
7af808a5
PH
2322 # Quelch pyflakes warnings - start will be set when step is set
2323 start = '(Never used)'
edf3e38e
PH
2324 for i, prev in zip(idxs[1:], idxs[:-1]):
2325 if step is not None:
2326 if i - prev == step:
2327 continue
2328 yield _genslice(start, prev, step)
2329 step = None
2330 continue
2331 if i - prev in [-1, 1]:
2332 step = i - prev
2333 start = prev
2334 continue
2335 else:
78caa52a 2336 yield 's[%d]' % prev
edf3e38e 2337 if step is None:
78caa52a 2338 yield 's[%d]' % i
edf3e38e
PH
2339 else:
2340 yield _genslice(start, i, step)
2341
78caa52a 2342 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 2343 cache_res = func(test_string)
edf3e38e 2344 cache_spec = [ord(c) for c in cache_res]
78caa52a 2345 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
2346 signature_id_tuple = '(%s)' % (
2347 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2348 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2349 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2350 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2351
e0df6211
PH
2352 def _parse_sig_js(self, jscode):
2353 funcname = self._search_regex(
abefc03f
S
2354 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2355 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
858a65ec
P
2356 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2357 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2358 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}\(a,\d+\)',
2359 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 2360 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2361 # Obsolete patterns
2362 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2363 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2364 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2365 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2366 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2367 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2368 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2369 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2370 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2371
2372 jsi = JSInterpreter(jscode)
2373 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2374 return lambda s: initial_function([s])
2375
545cc85d 2376 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2377 """Turn the encrypted s field into a working signature"""
6b37f0be 2378
c8bf86d5 2379 if player_url is None:
69ea8ca4 2380 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 2381
c8bf86d5 2382 try:
62af3a0e 2383 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
2384 if player_id not in self._player_cache:
2385 func = self._extract_signature_function(
60064c53 2386 video_id, player_url, s
c8bf86d5
PH
2387 )
2388 self._player_cache[player_id] = func
2389 func = self._player_cache[player_id]
404f611f 2390 self._print_sig_code(func, s)
c8bf86d5
PH
2391 return func(s)
2392 except Exception as e:
404f611f 2393 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
2394
2395 def _decrypt_nsig(self, s, video_id, player_url):
2396 """Turn the encrypted n field into a working signature"""
2397 if player_url is None:
2398 raise ExtractorError('Cannot decrypt nsig without player_url')
2399 if player_url.startswith('//'):
2400 player_url = 'https:' + player_url
2401 elif not re.match(r'https?://', player_url):
2402 player_url = compat_urlparse.urljoin(
2403 'https://www.youtube.com', player_url)
2404
2405 sig_id = ('nsig_value', s)
2406 if sig_id in self._player_cache:
2407 return self._player_cache[sig_id]
2408
2409 try:
2410 player_id = ('nsig', player_url)
2411 if player_id not in self._player_cache:
2412 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2413 func = self._player_cache[player_id]
2414 self._player_cache[sig_id] = func(s)
2415 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2416 return self._player_cache[sig_id]
2417 except Exception as e:
aa9369a2 2418 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2419
2420 def _extract_n_function_name(self, jscode):
2421 return self._search_regex(
2422 (r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]{3})\([a-zA-Z0-9]\)',),
2423 jscode, 'Initial JS player n function name', group='nfunc')
2424
2425 def _extract_n_function(self, video_id, player_url):
2426 player_id = self._extract_player_info(player_url)
2427 func_code = self._downloader.cache.load('youtube-nsig', player_id)
2428
2429 if func_code:
2430 jsi = JSInterpreter(func_code)
2431 else:
2432 jscode = self._load_player(video_id, player_url)
2433 funcname = self._extract_n_function_name(jscode)
2434 jsi = JSInterpreter(jscode)
2435 func_code = jsi.extract_function_code(funcname)
2436 self._downloader.cache.store('youtube-nsig', player_id, func_code)
2437
2438 if self.get_param('youtube_print_sig_code'):
2439 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2440
2441 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2442
109dd3b2 2443 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2444 """
2445 Extract signatureTimestamp (sts)
2446 Required to tell API what sig/player version is in use.
2447 """
2448 sts = None
2449 if isinstance(ytcfg, dict):
2450 sts = int_or_none(ytcfg.get('STS'))
2451
2452 if not sts:
2453 # Attempt to extract from player
2454 if player_url is None:
2455 error_msg = 'Cannot extract signature timestamp without player_url.'
2456 if fatal:
2457 raise ExtractorError(error_msg)
2458 self.report_warning(error_msg)
2459 return
404f611f 2460 code = self._load_player(video_id, player_url, fatal=fatal)
2461 if code:
109dd3b2 2462 sts = int_or_none(self._search_regex(
2463 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2464 'JS player signature timestamp', group='sts', fatal=fatal))
2465 return sts
2466
11f9be09 2467 def _mark_watched(self, video_id, player_responses):
9222c381 2468 playback_url = get_first(
2469 player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2470 expected_type=url_or_none)
d77ab8e2 2471 if not playback_url:
352d63fd 2472 self.report_warning('Unable to mark watched')
d77ab8e2
S
2473 return
2474 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2475 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2476
2477 # cpn generation algorithm is reverse engineered from base.js.
2478 # In fact it works even with dummy cpn.
2479 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2480 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2481
2482 qs.update({
2483 'ver': ['2'],
2484 'cpn': [cpn],
2485 })
2486 playback_url = compat_urlparse.urlunparse(
15707c7e 2487 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
2488
2489 self._download_webpage(
2490 playback_url, video_id, 'Marking watched',
2491 'Unable to mark watched', fatal=False)
2492
66c9fa36
S
2493 @staticmethod
2494 def _extract_urls(webpage):
2495 # Embedded YouTube player
2496 entries = [
2497 unescapeHTML(mobj.group('url'))
2498 for mobj in re.finditer(r'''(?x)
2499 (?:
2500 <iframe[^>]+?src=|
2501 data-video-url=|
2502 <embed[^>]+?src=|
2503 embedSWF\(?:\s*|
2504 <object[^>]+data=|
2505 new\s+SWFObject\(
2506 )
2507 (["\'])
2508 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2509 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2510 \1''', webpage)]
2511
2512 # lazyYT YouTube embed
2513 entries.extend(list(map(
2514 unescapeHTML,
2515 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2516
2517 # Wordpress "YouTube Video Importer" plugin
2518 matches = re.findall(r'''(?x)<div[^>]+
2519 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2520 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2521 entries.extend(m[-1] for m in matches)
2522
2523 return entries
2524
2525 @staticmethod
2526 def _extract_url(webpage):
2527 urls = YoutubeIE._extract_urls(webpage)
2528 return urls[0] if urls else None
2529
97665381
PH
2530 @classmethod
2531 def extract_id(cls, url):
2532 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 2533 if mobj is None:
69ea8ca4 2534 raise ExtractorError('Invalid URL: %s' % url)
5ad28e7f 2535 return mobj.group('id')
c5e8d7af 2536
7c365c21 2537 def _extract_chapters_from_json(self, data, duration):
2538 chapter_list = traverse_obj(
2539 data, (
2540 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2541 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2542 ), expected_type=list)
2543
2544 return self._extract_chapters(
2545 chapter_list,
2546 chapter_time=lambda chapter: float_or_none(
2547 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2548 chapter_title=lambda chapter: traverse_obj(
2549 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2550 duration=duration)
2551
2552 def _extract_chapters_from_engagement_panel(self, data, duration):
2553 content_list = traverse_obj(
8bdd16b4 2554 data,
7c365c21 2555 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2556 expected_type=list, default=[])
052e1350 2557 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2558 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2559
2560 return next((
2561 filter(None, (
2562 self._extract_chapters(
2563 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2564 chapter_time, chapter_title, duration)
2565 for contents in content_list
2566 ))), [])
2567
2568 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
84213ea8 2569 chapters = []
7c365c21 2570 last_chapter = {'start_time': 0}
2571 for idx, chapter in enumerate(chapter_list or []):
2572 title = chapter_title(chapter)
84213ea8
S
2573 start_time = chapter_time(chapter)
2574 if start_time is None:
2575 continue
7c365c21 2576 last_chapter['end_time'] = start_time
2577 if start_time < last_chapter['start_time']:
2578 if idx == 1:
2579 chapters.pop()
2580 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2581 else:
2582 self.report_warning(f'Invalid start time for chapter "{title}"')
2583 continue
2584 last_chapter = {'start_time': start_time, 'title': title}
2585 chapters.append(last_chapter)
2586 last_chapter['end_time'] = duration
84213ea8
S
2587 return chapters
2588
545cc85d 2589 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2590 return self._parse_json(self._search_regex(
2591 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2592 regex), webpage, name, default='{}'), video_id, fatal=False)
84213ea8 2593
a1c5d2ca
M
2594 def _extract_comment(self, comment_renderer, parent=None):
2595 comment_id = comment_renderer.get('commentId')
2596 if not comment_id:
2597 return
fe93e2c4 2598
052e1350 2599 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2600
49bd8c66 2601 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2602 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2603 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2604 author_id = try_get(comment_renderer,
2605 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2606
49bd8c66 2607 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2608 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2609 author_thumbnail = try_get(comment_renderer,
2610 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2611
2612 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2613 is_favorited = 'creatorHeart' in (try_get(
2614 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2615 return {
2616 'id': comment_id,
2617 'text': text,
d92f5d5a 2618 'timestamp': timestamp,
a1c5d2ca
M
2619 'time_text': time_text,
2620 'like_count': votes,
97524332 2621 'is_favorited': is_favorited,
a1c5d2ca
M
2622 'author': author,
2623 'author_id': author_id,
2624 'author_thumbnail': author_thumbnail,
2625 'author_is_uploader': author_is_uploader,
2626 'parent': parent or 'root'
2627 }
2628
46383212 2629 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2630
2631 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2632
2633 def extract_header(contents):
2d6659b9 2634 _continuation = None
2635 for content in contents:
46383212 2636 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2637 expected_comment_count = self._get_count(
2638 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2639
2d6659b9 2640 if expected_comment_count:
46383212 2641 tracker['est_total'] = expected_comment_count
2642 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2643 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2644
2645 sort_menu_item = try_get(
2646 comments_header_renderer,
2647 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2648 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2649
2650 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2651 if not _continuation:
2652 continue
2653
46383212 2654 sort_text = str_or_none(sort_menu_item.get('title'))
2655 if not sort_text:
2d6659b9 2656 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2657 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2658 break
a2160aa4 2659 return _continuation
a1c5d2ca 2660
2d6659b9 2661 def extract_thread(contents):
a1c5d2ca 2662 if not parent:
46383212 2663 tracker['current_page_thread'] = 0
a1c5d2ca 2664 for content in contents:
46383212 2665 if not parent and tracker['total_parent_comments'] >= max_parents:
2666 yield
a1c5d2ca 2667 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2668 comment_renderer = get_first(
2669 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2670 expected_type=dict, default={})
a1c5d2ca 2671
a1c5d2ca
M
2672 comment = self._extract_comment(comment_renderer, parent)
2673 if not comment:
2674 continue
46383212 2675
2676 tracker['running_total'] += 1
2677 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2678 yield comment
46383212 2679
a1c5d2ca
M
2680 # Attempt to get the replies
2681 comment_replies_renderer = try_get(
2682 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2683
2684 if comment_replies_renderer:
46383212 2685 tracker['current_page_thread'] += 1
a1c5d2ca 2686 comment_entries_iter = self._comment_entries(
99e9e001 2687 comment_replies_renderer, ytcfg, video_id,
46383212 2688 parent=comment.get('id'), tracker=tracker)
2689 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
a1c5d2ca
M
2690 yield reply_comment
2691
46383212 2692 # Keeps track of counts across recursive calls
2693 if not tracker:
2694 tracker = dict(
2695 running_total=0,
2696 est_total=0,
2697 current_page_thread=0,
2698 total_parent_comments=0,
2699 total_reply_comments=0)
2700
2701 # TODO: Deprecated
2d6659b9 2702 # YouTube comments have a max depth of 2
46383212 2703 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2704 if max_depth:
2705 self._downloader.deprecation_warning(
2706 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2707 if max_depth == 1 and parent:
2708 return
a1c5d2ca 2709
46383212 2710 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2711 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2712
46383212 2713 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2714 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2715 if message and not parent:
2716 self.report_warning(message, video_id=video_id)
2717
46383212 2718 response = None
2d6659b9 2719 is_first_continuation = parent is None
a1c5d2ca
M
2720
2721 for page_num in itertools.count(0):
2722 if not continuation:
2723 break
46383212 2724 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2725 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2726 if page_num == 0:
2727 if is_first_continuation:
2728 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2729 else:
2d6659b9 2730 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2731 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2732 else:
2733 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2734 ' ' if parent else '', ' replies' if parent else '',
2735 page_num, comment_prog_str)
2736
2737 response = self._extract_response(
fe93e2c4 2738 item_id=None, query=continuation,
2d6659b9 2739 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
46383212 2740 check_get_keys='onResponseReceivedEndpoints')
a1c5d2ca 2741
46383212 2742 continuation_contents = traverse_obj(
2743 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2744
2d6659b9 2745 continuation = None
46383212 2746 for continuation_section in continuation_contents:
2747 continuation_items = traverse_obj(
2748 continuation_section,
2749 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2750 get_all=False, expected_type=list) or []
2751 if is_first_continuation:
2752 continuation = extract_header(continuation_items)
2753 is_first_continuation = False
2d6659b9 2754 if continuation:
a1c5d2ca 2755 break
46383212 2756 continue
a1c5d2ca 2757
46383212 2758 for entry in extract_thread(continuation_items):
2759 if not entry:
2760 return
2761 yield entry
2762 continuation = self._extract_continuation({'contents': continuation_items})
2763 if continuation:
2d6659b9 2764 break
a1c5d2ca 2765
a2160aa4 2766 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2767 """Entry for comment extraction"""
2d6659b9 2768 def _real_comment_extract(contents):
aae16f6e 2769 renderer = next((
2770 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2771 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2772 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2773
a2160aa4 2774 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2775 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2776
109dd3b2 2777 @staticmethod
99e9e001 2778 def _get_checkok_params():
2779 return {'contentCheckOk': True, 'racyCheckOk': True}
2780
2781 @classmethod
2782 def _generate_player_context(cls, sts=None):
109dd3b2 2783 context = {
2784 'html5Preference': 'HTML5_PREF_WANTS',
2785 }
2786 if sts is not None:
2787 context['signatureTimestamp'] = sts
2788 return {
2789 'playbackContext': {
2790 'contentPlaybackContext': context
a1a7907b 2791 },
99e9e001 2792 **cls._get_checkok_params()
109dd3b2 2793 }
2794
e7e94f2a
D
2795 @staticmethod
2796 def _is_agegated(player_response):
2797 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 2798 return True
e7e94f2a
D
2799
2800 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2801 AGE_GATE_REASONS = (
2802 'confirm your age', 'age-restricted', 'inappropriate', # reason
2803 'age_verification_required', 'age_check_required', # status
2804 )
2805 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2806
2807 @staticmethod
2808 def _is_unplayable(player_response):
2809 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 2810
99e9e001 2811 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 2812
11f9be09 2813 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2814 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 2815 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 2816 headers = self.generate_api_headers(
99e9e001 2817 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 2818
11f9be09 2819 yt_query = {'videoId': video_id}
2820 yt_query.update(self._generate_player_context(sts))
2821 return self._extract_response(
2822 item_id=video_id, ep='player', query=yt_query,
379e44ed 2823 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 2824 default_client=client,
11f9be09 2825 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2826 ) or None
2827
11f9be09 2828 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 2829 requested_clients = []
d0d012d4 2830 default = ['android', 'web']
000c15a4 2831 allowed_clients = sorted(
2832 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2833 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 2834 for client in self._configuration_arg('player_client'):
2835 if client in allowed_clients:
2836 requested_clients.append(client)
d0d012d4 2837 elif client == 'default':
2838 requested_clients.extend(default)
b4c055ba 2839 elif client == 'all':
2840 requested_clients.extend(allowed_clients)
2841 else:
2842 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 2843 if not requested_clients:
d0d012d4 2844 requested_clients = default
cf7e015f 2845
11f9be09 2846 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2847 requested_clients.extend(
e7e94f2a 2848 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 2849
11f9be09 2850 return orderedSet(requested_clients)
cf7e015f 2851
c0bc527b
M
2852 def _extract_player_ytcfg(self, client, video_id):
2853 url = {
2854 'web_music': 'https://music.youtube.com',
2855 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2856 }.get(client)
2857 if not url:
2858 return {}
18c7683d 2859 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
c0bc527b
M
2860 return self.extract_ytcfg(video_id, webpage) or {}
2861
99e9e001 2862 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 2863 initial_pr = None
2864 if webpage:
2865 initial_pr = self._extract_yt_initial_variable(
2866 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2867 video_id, 'initial player response')
6b09401b 2868
c0bc527b
M
2869 original_clients = clients
2870 clients = clients[::-1]
b6de707d 2871 prs = []
e7e94f2a
D
2872
2873 def append_client(client_name):
2874 if client_name in INNERTUBE_CLIENTS and client_name not in original_clients:
2875 clients.append(client_name)
2876
379e44ed 2877 # Android player_response does not have microFormats which are needed for
2878 # extraction of some data. So we return the initial_pr with formats
2879 # stripped out even if not requested by the user
2880 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 2881 if initial_pr:
2882 pr = dict(initial_pr)
2883 pr['streamingData'] = None
b6de707d 2884 prs.append(pr)
379e44ed 2885
2886 last_error = None
b6de707d 2887 tried_iframe_fallback = False
2888 player_url = None
c0bc527b
M
2889 while clients:
2890 client = clients.pop()
11f9be09 2891 player_ytcfg = master_ytcfg if client == 'web' else {}
c0bc527b
M
2892 if 'configs' not in self._configuration_arg('player_skip'):
2893 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
c0bc527b 2894
b6de707d 2895 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
2896 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
2897 if 'js' in self._configuration_arg('player_skip'):
2898 require_js_player = False
2899 player_url = None
2900
2901 if not player_url and not tried_iframe_fallback and require_js_player:
2902 player_url = self._download_player_url(video_id)
2903 tried_iframe_fallback = True
2904
379e44ed 2905 try:
2906 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 2907 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 2908 except ExtractorError as e:
2909 if last_error:
2910 self.report_warning(last_error)
2911 last_error = e
2912 continue
2913
11f9be09 2914 if pr:
b6de707d 2915 prs.append(pr)
c0bc527b 2916
e7e94f2a 2917 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
99e9e001 2918 if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated:
e7e94f2a
D
2919 append_client(client.replace('_agegate', '_creator'))
2920 elif self._is_agegated(pr):
2921 append_client(f'{client}_agegate')
c0bc527b 2922
379e44ed 2923 if last_error:
b6de707d 2924 if not len(prs):
379e44ed 2925 raise last_error
2926 self.report_warning(last_error)
b6de707d 2927 return prs, player_url
11f9be09 2928
2929 def _extract_formats(self, streaming_data, video_id, player_url, is_live):
a0bb6ce5 2930 itags, stream_ids = {}, []
2a9c6dcd 2931 itag_qualities, res_qualities = {}, {}
d3fc8074 2932 q = qualities([
2a9c6dcd 2933 # Normally tiny is the smallest video-only formats. But
2934 # audio-only formats with unknown quality may get tagged as tiny
2935 'tiny',
2936 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 2937 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
2938 ])
11f9be09 2939 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 2940
545cc85d 2941 for fmt in streaming_formats:
2942 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
2943 continue
321bf820 2944
cc2db878 2945 itag = str_or_none(fmt.get('itag'))
9297939e 2946 audio_track = fmt.get('audioTrack') or {}
2947 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
2948 if stream_id in stream_ids:
2949 continue
2950
cc2db878 2951 quality = fmt.get('quality')
2a9c6dcd 2952 height = int_or_none(fmt.get('height'))
d3fc8074 2953 if quality == 'tiny' or not quality:
2954 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 2955 # The 3gp format (17) in android client has a quality of "small",
2956 # but is actually worse than other formats
2957 if itag == '17':
2958 quality = 'tiny'
2959 if quality:
2960 if itag:
2961 itag_qualities[itag] = quality
2962 if height:
2963 res_qualities[height] = quality
cc2db878 2964 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
2965 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
2966 # number of fragment that would subsequently requested with (`&sq=N`)
2967 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
2968 continue
2969
545cc85d 2970 fmt_url = fmt.get('url')
2971 if not fmt_url:
2972 sc = compat_parse_qs(fmt.get('signatureCipher'))
2973 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
2974 encrypted_sig = try_get(sc, lambda x: x['s'][0])
2975 if not (sc and fmt_url and encrypted_sig):
2976 continue
545cc85d 2977 if not player_url:
201e9eaa 2978 continue
545cc85d 2979 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2980 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2981 fmt_url += '&' + sp + '=' + signature
2982
404f611f 2983 query = parse_qs(fmt_url)
2984 throttled = False
b2916526 2985 if query.get('n'):
404f611f 2986 try:
2987 fmt_url = update_url_query(fmt_url, {
2988 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
2989 except ExtractorError as e:
aa9369a2 2990 self.report_warning(
2991 f'nsig extraction failed: You may experience throttling for some formats\n'
2992 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
404f611f 2993 throttled = True
2994
545cc85d 2995 if itag:
a0bb6ce5 2996 itags[itag] = 'https'
9297939e 2997 stream_ids.append(stream_id)
2998
cc2db878 2999 tbr = float_or_none(
3000 fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
545cc85d 3001 dct = {
3002 'asr': int_or_none(fmt.get('audioSampleRate')),
3003 'filesize': int_or_none(fmt.get('contentLength')),
3004 'format_id': itag,
34921b43 3005 'format_note': join_nonempty(
26e8e044 3006 '%s%s' % (audio_track.get('displayName') or '',
3007 ' (default)' if audio_track.get('audioIsDefault') else ''),
404f611f 3008 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
34921b43 3009 throttled and 'THROTTLED', delim=', '),
c18d4482 3010 'source_preference': -10 if throttled else -1,
a4211baf 3011 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3012 'height': height,
dca3ff4a 3013 'quality': q(quality),
cc2db878 3014 'tbr': tbr,
545cc85d 3015 'url': fmt_url,
2a9c6dcd 3016 'width': int_or_none(fmt.get('width')),
0fb983f6 3017 'language': audio_track.get('id', '').split('.')[0],
26e8e044 3018 'language_preference': 1 if audio_track.get('audioIsDefault') else -1,
545cc85d 3019 }
60bdb7bd 3020 mime_mobj = re.match(
3021 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3022 if mime_mobj:
3023 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3024 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3025 no_audio = dct.get('acodec') == 'none'
3026 no_video = dct.get('vcodec') == 'none'
3027 if no_audio:
3028 dct['vbr'] = tbr
3029 if no_video:
3030 dct['abr'] = tbr
3031 if no_audio or no_video:
545cc85d 3032 dct['downloader_options'] = {
3033 # Youtube throttles chunks >~10M
3034 'http_chunk_size': 10485760,
bf1317d2 3035 }
7c60c33e 3036 if dct.get('ext'):
3037 dct['container'] = dct['ext'] + '_dash'
11f9be09 3038 yield dct
545cc85d 3039
adbc4ec4 3040 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3041 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3042 if not self.get_param('youtube_include_hls_manifest', True):
3043 skip_manifests.append('hls')
3044 get_dash = 'dash' not in skip_manifests and (
3045 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3046 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3047
a0bb6ce5 3048 def process_manifest_format(f, proto, itag):
3049 if itag in itags:
3050 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3051 return False
3052 itag = f'{itag}-{proto}'
3053 if itag:
3054 f['format_id'] = itag
3055 itags[itag] = proto
3056
3057 f['quality'] = next((
3058 q(qdict[val])
e339d25a 3059 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3060 if val in qdict), -1)
3061 return True
2a9c6dcd 3062
11f9be09 3063 for sd in streaming_data:
5d3a0e79 3064 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3065 if hls_manifest_url:
2a9c6dcd 3066 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 3067 if process_manifest_format(f, 'hls', self._search_regex(
3068 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3069 yield f
545cc85d 3070
5d3a0e79 3071 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3072 if dash_manifest_url:
2a9c6dcd 3073 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 3074 if process_manifest_format(f, 'dash', f['format_id']):
3075 f['filesize'] = int_or_none(self._search_regex(
3076 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3077 if live_from_start:
3078 f['is_from_start'] = True
3079
a0bb6ce5 3080 yield f
11f9be09 3081
720c3099 3082 def _extract_storyboard(self, player_responses, duration):
3083 spec = get_first(
3084 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3085 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3086 if not base_url:
720c3099 3087 return
720c3099 3088 L = len(spec) - 1
3089 for i, args in enumerate(spec):
3090 args = args.split('#')
3091 counts = list(map(int_or_none, args[:5]))
3092 if len(args) != 8 or not all(counts):
3093 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3094 continue
3095 width, height, frame_count, cols, rows = counts
3096 N, sigh = args[6:]
3097
3098 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3099 fragment_count = frame_count / (cols * rows)
3100 fragment_duration = duration / fragment_count
3101 yield {
3102 'format_id': f'sb{i}',
3103 'format_note': 'storyboard',
3104 'ext': 'mhtml',
3105 'protocol': 'mhtml',
3106 'acodec': 'none',
3107 'vcodec': 'none',
3108 'url': url,
3109 'width': width,
3110 'height': height,
3111 'fragments': [{
3112 'path': url.replace('$M', str(j)),
3113 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3114 } for j in range(math.ceil(fragment_count))],
3115 }
3116
adbc4ec4 3117 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3118 webpage = None
3119 if 'webpage' not in self._configuration_arg('player_skip'):
3120 webpage = self._download_webpage(
3121 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
11f9be09 3122
3123 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3124
b6de707d 3125 player_responses, player_url = self._extract_player_responses(
11f9be09 3126 self._get_requested_clients(url, smuggled_data),
99e9e001 3127 video_id, webpage, master_ytcfg)
11f9be09 3128
adbc4ec4
THD
3129 return webpage, master_ytcfg, player_responses, player_url
3130
3131 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url):
3132 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3133 is_live = get_first(video_details, 'isLive')
3134 if is_live is None:
3135 is_live = get_first(live_broadcast_details, 'isLiveNow')
3136
3137 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
3138 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
3139
3140 return live_broadcast_details, is_live, streaming_data, formats
3141
3142 def _real_extract(self, url):
3143 url, smuggled_data = unsmuggle_url(url, {})
3144 video_id = self._match_id(url)
3145
3146 base_url = self.http_scheme() + '//www.youtube.com/'
3147 webpage_url = base_url + 'watch?v=' + video_id
3148
3149 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3150
11f9be09 3151 playability_statuses = traverse_obj(
3152 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3153
3154 trailer_video_id = get_first(
3155 playability_statuses,
3156 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3157 expected_type=str)
3158 if trailer_video_id:
3159 return self.url_result(
3160 trailer_video_id, self.ie_key(), trailer_video_id)
3161
3162 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3163 if webpage else (lambda x: None))
3164
3165 video_details = traverse_obj(
3166 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3167 microformats = traverse_obj(
3168 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3169 expected_type=dict, default=[])
3170 video_title = (
3171 get_first(video_details, 'title')
3172 or self._get_text(microformats, (..., 'title'))
3173 or search_meta(['og:title', 'twitter:title', 'title']))
3174 video_description = get_first(video_details, 'shortDescription')
3175
d89257f3 3176 multifeed_metadata_list = get_first(
3177 player_responses,
3178 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3179 expected_type=str)
3180 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3181 if self.get_param('noplaylist'):
11f9be09 3182 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3183 else:
3184 entries = []
3185 feed_ids = []
3186 for feed in multifeed_metadata_list.split(','):
3187 # Unquote should take place before split on comma (,) since textual
3188 # fields may contain comma as well (see
3189 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3190 feed_data = compat_parse_qs(
3191 compat_urllib_parse_unquote_plus(feed))
3192
3193 def feed_entry(name):
3194 return try_get(
3195 feed_data, lambda x: x[name][0], compat_str)
3196
3197 feed_id = feed_entry('id')
3198 if not feed_id:
3199 continue
3200 feed_title = feed_entry('title')
3201 title = video_title
3202 if feed_title:
3203 title += ' (%s)' % feed_title
3204 entries.append({
3205 '_type': 'url_transparent',
3206 'ie_key': 'Youtube',
3207 'url': smuggle_url(
3208 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3209 {'force_singlefeed': True}),
3210 'title': title,
3211 })
3212 feed_ids.append(feed_id)
3213 self.to_screen(
3214 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3215 % (', '.join(feed_ids), video_id))
3216 return self.playlist_result(
3217 entries, video_id, video_title, video_description)
11f9be09 3218
adbc4ec4 3219 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(video_id, microformats, video_details, player_responses, player_url)
bf1317d2 3220
545cc85d 3221 if not formats:
11f9be09 3222 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3223 self.report_drm(video_id)
11f9be09 3224 pemr = get_first(
3225 playability_statuses,
3226 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3227 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3228 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3229 if subreason:
545cc85d 3230 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3231 countries = get_first(microformats, 'availableCountries')
545cc85d 3232 if not countries:
3233 regions_allowed = search_meta('regionsAllowed')
3234 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3235 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3236 reason += f'. {subreason}'
545cc85d 3237 if reason:
b7da73eb 3238 self.raise_no_formats(reason, expected=True)
bf1317d2 3239
11f9be09 3240 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3241 if not keywords and webpage:
3242 keywords = [
3243 unescapeHTML(m.group('content'))
3244 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3245 for keyword in keywords:
3246 if keyword.startswith('yt:stretch='):
201c1459 3247 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3248 if mobj:
3249 # NB: float is intentional for forcing float division
3250 w, h = (float(v) for v in mobj.groups())
3251 if w > 0 and h > 0:
3252 ratio = w / h
3253 for f in formats:
3254 if f.get('vcodec') != 'none':
3255 f['stretched_ratio'] = ratio
3256 break
a709d873 3257 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3258 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3259 if thumbnail_url:
3260 thumbnails.append({
3261 'url': thumbnail_url,
ff2751ac 3262 })
fccf5021 3263 original_thumbnails = thumbnails.copy()
3264
0ba692ac 3265 # The best resolution thumbnails sometimes does not appear in the webpage
3266 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3267 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3268 thumbnail_names = [
3269 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
cca80fe6 3270 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3271 'mqdefault', 'mq1', 'mq2', 'mq3',
3272 'default', '1', '2', '3'
3273 ]
cca80fe6 3274 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3275 thumbnails.extend({
3276 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3277 video_id=video_id, name=name, ext=ext,
3278 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3279 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3280 for thumb in thumbnails:
cca80fe6 3281 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3282 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3283 self._remove_duplicate_formats(thumbnails)
fccf5021 3284 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3285
7ea65411 3286 category = get_first(microformats, 'category') or search_meta('genre')
3287 channel_id = str_or_none(
3288 get_first(video_details, 'channelId')
3289 or get_first(microformats, 'externalChannelId')
3290 or search_meta('channelId'))
3291 duration = int_or_none(
3292 get_first(video_details, 'lengthSeconds')
3293 or get_first(microformats, 'lengthSeconds')
3294 or parse_duration(search_meta('duration'))) or None
3295 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3296
3297 live_content = get_first(video_details, 'isLiveContent')
3298 is_upcoming = get_first(video_details, 'isUpcoming')
3299 if is_live is None:
3300 if is_upcoming or live_content is False:
3301 is_live = False
3302 if is_upcoming is None and (live_content or is_live):
3303 is_upcoming = False
adbc4ec4
THD
3304 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3305 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3306 if not duration and live_end_time and live_start_time:
3307 duration = live_end_time - live_start_time
3308
3309 if is_live and self.get_param('live_from_start'):
3310 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3311
720c3099 3312 formats.extend(self._extract_storyboard(player_responses, duration))
3313
3314 # Source is given priority since formats that throttle are given lower source_preference
3315 # When throttling issue is fully fixed, remove this
3316 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3317
545cc85d 3318 info = {
3319 'id': video_id,
39ca3b5c 3320 'title': video_title,
545cc85d 3321 'formats': formats,
3322 'thumbnails': thumbnails,
fccf5021 3323 # The best thumbnail that we are sure exists. Prevents unnecessary
3324 # URL checking if user don't care about getting the best possible thumbnail
3325 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3326 'description': video_description,
3327 'upload_date': unified_strdate(
11f9be09 3328 get_first(microformats, 'uploadDate')
545cc85d 3329 or search_meta('uploadDate')),
11f9be09 3330 'uploader': get_first(video_details, 'author'),
545cc85d 3331 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3332 'uploader_url': owner_profile_url,
3333 'channel_id': channel_id,
e0ddbd02 3334 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
545cc85d 3335 'duration': duration,
3336 'view_count': int_or_none(
11f9be09 3337 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3338 or search_meta('interactionCount')),
11f9be09 3339 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3340 'age_limit': 18 if (
11f9be09 3341 get_first(microformats, 'isFamilySafe') is False
545cc85d 3342 or search_meta('isFamilyFriendly') == 'false'
3343 or search_meta('og:restrictions:age') == '18+') else 0,
3344 'webpage_url': webpage_url,
3345 'categories': [category] if category else None,
3346 'tags': keywords,
11f9be09 3347 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3348 'is_live': is_live,
3349 'was_live': (False if is_live or is_upcoming or live_content is False
3350 else None if is_live is None or is_upcoming is None
3351 else live_content),
3352 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3353 'release_timestamp': live_start_time,
545cc85d 3354 }
b477fc13 3355
3944e7af 3356 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3357 if pctr:
ecdc9049 3358 def get_lang_code(track):
3359 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3360 or track.get('languageCode'))
3361
3362 # Converted into dicts to remove duplicates
3363 captions = {
3364 get_lang_code(sub): sub
3365 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3366 translation_languages = {
3367 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3368 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3369
774d79cc 3370 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3371 lang_subs = container.setdefault(lang_code, [])
545cc85d 3372 for fmt in self._SUBTITLE_FORMATS:
3373 query.update({
3374 'fmt': fmt,
3375 })
3376 lang_subs.append({
3377 'ext': fmt,
3378 'url': update_url_query(base_url, query),
774d79cc 3379 'name': sub_name,
545cc85d 3380 })
7e72694b 3381
ecdc9049 3382 subtitles, automatic_captions = {}, {}
3383 for lang_code, caption_track in captions.items():
3384 base_url = caption_track.get('baseUrl')
545cc85d 3385 if not base_url:
3386 continue
ecdc9049 3387 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3388 if caption_track.get('kind') != 'asr':
545cc85d 3389 if not lang_code:
3390 continue
3391 process_language(
ecdc9049 3392 subtitles, base_url, lang_code, lang_name, {})
3393 if not caption_track.get('isTranslatable'):
3394 continue
3944e7af 3395 for trans_code, trans_name in translation_languages.items():
3396 if not trans_code:
545cc85d 3397 continue
ecdc9049 3398 if caption_track.get('kind') != 'asr':
3399 trans_code += f'-{lang_code}'
3400 trans_name += format_field(lang_name, template=' from %s')
545cc85d 3401 process_language(
ecdc9049 3402 automatic_captions, base_url, trans_code, trans_name, {'tlang': trans_code})
3403 info['automatic_captions'] = automatic_captions
3404 info['subtitles'] = subtitles
7e72694b 3405
545cc85d 3406 parsed_url = compat_urllib_parse_urlparse(url)
3407 for component in [parsed_url.fragment, parsed_url.query]:
3408 query = compat_parse_qs(component)
3409 for k, v in query.items():
3410 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3411 d_k += '_time'
3412 if d_k not in info and k in s_ks:
3413 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3414
3415 # Youtube Music Auto-generated description
822b9d9c 3416 if video_description:
38d70284 3417 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 3418 if mobj:
822b9d9c
RA
3419 release_year = mobj.group('release_year')
3420 release_date = mobj.group('release_date')
3421 if release_date:
3422 release_date = release_date.replace('-', '')
3423 if not release_year:
545cc85d 3424 release_year = release_date[:4]
3425 info.update({
3426 'album': mobj.group('album'.strip()),
3427 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3428 'track': mobj.group('track').strip(),
3429 'release_date': release_date,
cc2db878 3430 'release_year': int_or_none(release_year),
545cc85d 3431 })
7e72694b 3432
545cc85d 3433 initial_data = None
3434 if webpage:
3435 initial_data = self._extract_yt_initial_variable(
3436 webpage, self._YT_INITIAL_DATA_RE, video_id,
3437 'yt initial data')
3438 if not initial_data:
99e9e001 3439 query = {'videoId': video_id}
3440 query.update(self._get_checkok_params())
109dd3b2 3441 initial_data = self._extract_response(
3442 item_id=video_id, ep='next', fatal=False,
99e9e001 3443 ytcfg=master_ytcfg, query=query,
3444 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3445 note='Downloading initial data API JSON')
545cc85d 3446
c60ee3a2 3447 try:
3448 # This will error if there is no livechat
3449 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
ecdc9049 3450 info.setdefault('subtitles', {})['live_chat'] = [{
c60ee3a2 3451 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3452 'video_id': video_id,
3453 'ext': 'json',
f6745c49 3454 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3455 }]
3456 except (KeyError, IndexError, TypeError):
3457 pass
545cc85d 3458
3459 if initial_data:
7c365c21 3460 info['chapters'] = (
3461 self._extract_chapters_from_json(initial_data, duration)
3462 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3463 or None)
545cc85d 3464
3465 contents = try_get(
3466 initial_data,
3467 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
3468 list) or []
3469 for content in contents:
3470 vpir = content.get('videoPrimaryInfoRenderer')
3471 if vpir:
3472 stl = vpir.get('superTitleLink')
3473 if stl:
fe93e2c4 3474 stl = self._get_text(stl)
545cc85d 3475 if try_get(
3476 vpir,
3477 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3478 info['location'] = stl
3479 else:
3480 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3481 if mobj:
3482 info.update({
3483 'series': mobj.group(1),
3484 'season_number': int(mobj.group(2)),
3485 'episode_number': int(mobj.group(3)),
3486 })
3487 for tlb in (try_get(
3488 vpir,
3489 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3490 list) or []):
3491 tbr = tlb.get('toggleButtonRenderer') or {}
3492 for getter, regex in [(
3493 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3494 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3495 lambda x: x['accessibility'],
3496 lambda x: x['accessibilityData']['accessibilityData'],
3497 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3498 label = (try_get(tbr, getter, dict) or {}).get('label')
3499 if label:
3500 mobj = re.match(regex, label)
3501 if mobj:
3502 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3503 break
3504 sbr_tooltip = try_get(
3505 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3506 if sbr_tooltip:
3507 like_count, dislike_count = sbr_tooltip.split(' / ')
3508 info.update({
3509 'like_count': str_to_int(like_count),
3510 'dislike_count': str_to_int(dislike_count),
3511 })
3512 vsir = content.get('videoSecondaryInfoRenderer')
3513 if vsir:
6c73052c 3514 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3515 info.update({
3516 'channel': self._get_text(vor, 'title'),
3517 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3518
545cc85d 3519 rows = try_get(
3520 vsir,
3521 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3522 list) or []
3523 multiple_songs = False
3524 for row in rows:
3525 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3526 multiple_songs = True
3527 break
3528 for row in rows:
3529 mrr = row.get('metadataRowRenderer') or {}
3530 mrr_title = mrr.get('title')
3531 if not mrr_title:
3532 continue
052e1350 3533 mrr_title = self._get_text(mrr, 'title')
3534 mrr_contents_text = self._get_text(mrr, ('contents', 0))
545cc85d 3535 if mrr_title == 'License':
3536 info['license'] = mrr_contents_text
3537 elif not multiple_songs:
3538 if mrr_title == 'Album':
3539 info['album'] = mrr_contents_text
3540 elif mrr_title == 'Artist':
3541 info['artist'] = mrr_contents_text
3542 elif mrr_title == 'Song':
3543 info['track'] = mrr_contents_text
3544
3545 fallbacks = {
3546 'channel': 'uploader',
3547 'channel_id': 'uploader_id',
3548 'channel_url': 'uploader_url',
3549 }
3550 for to, frm in fallbacks.items():
3551 if not info.get(to):
3552 info[to] = info.get(frm)
3553
3554 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3555 v = info.get(s_k)
3556 if v:
3557 info[d_k] = v
b84071c0 3558
11f9be09 3559 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3560 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3561 is_membersonly = None
b28f8d24 3562 is_premium = None
c224251a
M
3563 if initial_data and is_private is not None:
3564 is_membersonly = False
b28f8d24 3565 is_premium = False
47193e02 3566 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3567 badge_labels = set()
3568 for content in contents:
3569 if not isinstance(content, dict):
3570 continue
3571 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3572 for badge_label in badge_labels:
3573 if badge_label.lower() == 'members only':
3574 is_membersonly = True
3575 elif badge_label.lower() == 'premium':
3576 is_premium = True
3577 elif badge_label.lower() == 'unlisted':
3578 is_unlisted = True
c224251a 3579
c224251a
M
3580 info['availability'] = self._availability(
3581 is_private=is_private,
b28f8d24 3582 needs_premium=is_premium,
c224251a
M
3583 needs_subscription=is_membersonly,
3584 needs_auth=info['age_limit'] >= 18,
3585 is_unlisted=None if is_private is None else is_unlisted)
3586
a2160aa4 3587 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3588
11f9be09 3589 self.mark_watched(video_id, player_responses)
d77ab8e2 3590
545cc85d 3591 return info
c5e8d7af 3592
a61fd4cf 3593
a6213a49 3594class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3595
a6213a49 3596 def _extract_channel_id(self, webpage):
3597 channel_id = self._html_search_meta(
3598 'channelId', webpage, 'channel id', default=None)
3599 if channel_id:
3600 return channel_id
3601 channel_url = self._html_search_meta(
3602 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3603 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3604 'twitter:app:url:googleplay'), webpage, 'channel url')
3605 return self._search_regex(
3606 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3607 channel_url, 'channel id')
15f6397c 3608
8bdd16b4 3609 @staticmethod
cd7c66cf 3610 def _extract_basic_item_renderer(item):
3611 # Modified from _extract_grid_item_renderer
201c1459 3612 known_basic_renderers = (
3613 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
cd7c66cf 3614 )
3615 for key, renderer in item.items():
201c1459 3616 if not isinstance(renderer, dict):
cd7c66cf 3617 continue
201c1459 3618 elif key in known_basic_renderers:
3619 return renderer
3620 elif key.startswith('grid') and key.endswith('Renderer'):
3621 return renderer
8bdd16b4 3622
8bdd16b4 3623 def _grid_entries(self, grid_renderer):
3624 for item in grid_renderer['items']:
3625 if not isinstance(item, dict):
39b62db1 3626 continue
cd7c66cf 3627 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3628 if not isinstance(renderer, dict):
3629 continue
052e1350 3630 title = self._get_text(renderer, 'title')
fe93e2c4 3631
8bdd16b4 3632 # playlist
3633 playlist_id = renderer.get('playlistId')
3634 if playlist_id:
3635 yield self.url_result(
3636 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3637 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3638 video_title=title)
201c1459 3639 continue
8bdd16b4 3640 # video
3641 video_id = renderer.get('videoId')
3642 if video_id:
3643 yield self._extract_video(renderer)
201c1459 3644 continue
8bdd16b4 3645 # channel
3646 channel_id = renderer.get('channelId')
3647 if channel_id:
8bdd16b4 3648 yield self.url_result(
3649 'https://www.youtube.com/channel/%s' % channel_id,
3650 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3651 continue
3652 # generic endpoint URL support
3653 ep_url = urljoin('https://www.youtube.com/', try_get(
3654 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3655 compat_str))
3656 if ep_url:
3657 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3658 if ie.suitable(ep_url):
3659 yield self.url_result(
3660 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3661 break
8bdd16b4 3662
3d3dddc9 3663 def _shelf_entries_from_content(self, shelf_renderer):
3664 content = shelf_renderer.get('content')
3665 if not isinstance(content, dict):
8bdd16b4 3666 return
cd7c66cf 3667 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3668 if renderer:
3669 # TODO: add support for nested playlists so each shelf is processed
3670 # as separate playlist
3671 # TODO: this includes only first N items
3672 for entry in self._grid_entries(renderer):
3673 yield entry
3674 renderer = content.get('horizontalListRenderer')
3675 if renderer:
3676 # TODO
3677 pass
8bdd16b4 3678
29f7c58a 3679 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3680 ep = try_get(
3681 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3682 compat_str)
3683 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3684 if shelf_url:
29f7c58a 3685 # Skipping links to another channels, note that checking for
3686 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3687 # will not work
3688 if skip_channels and '/channels?' in shelf_url:
3689 return
052e1350 3690 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 3691 yield self.url_result(shelf_url, video_title=title)
3692 # Shelf may not contain shelf URL, fallback to extraction from content
3693 for entry in self._shelf_entries_from_content(shelf_renderer):
3694 yield entry
c5e8d7af 3695
8bdd16b4 3696 def _playlist_entries(self, video_list_renderer):
3697 for content in video_list_renderer['contents']:
3698 if not isinstance(content, dict):
3699 continue
3700 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3701 if not isinstance(renderer, dict):
3702 continue
3703 video_id = renderer.get('videoId')
3704 if not video_id:
3705 continue
3706 yield self._extract_video(renderer)
07aeced6 3707
3462ffa8 3708 def _rich_entries(self, rich_grid_renderer):
3709 renderer = try_get(
70d5c17b 3710 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 3711 video_id = renderer.get('videoId')
3712 if not video_id:
3713 return
3714 yield self._extract_video(renderer)
3715
8bdd16b4 3716 def _video_entry(self, video_renderer):
3717 video_id = video_renderer.get('videoId')
3718 if video_id:
3719 return self._extract_video(video_renderer)
dacb3a86 3720
8bdd16b4 3721 def _post_thread_entries(self, post_thread_renderer):
3722 post_renderer = try_get(
3723 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3724 if not post_renderer:
3725 return
3726 # video attachment
3727 video_renderer = try_get(
895b0931 3728 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3729 video_id = video_renderer.get('videoId')
3730 if video_id:
3731 entry = self._extract_video(video_renderer)
8bdd16b4 3732 if entry:
3733 yield entry
895b0931 3734 # playlist attachment
3735 playlist_id = try_get(
3736 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3737 if playlist_id:
3738 yield self.url_result(
e28f1c0a 3739 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3740 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 3741 # inline video links
3742 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3743 for run in runs:
3744 if not isinstance(run, dict):
3745 continue
3746 ep_url = try_get(
3747 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3748 if not ep_url:
3749 continue
3750 if not YoutubeIE.suitable(ep_url):
3751 continue
3752 ep_video_id = YoutubeIE._match_id(ep_url)
3753 if video_id == ep_video_id:
3754 continue
895b0931 3755 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 3756
8bdd16b4 3757 def _post_thread_continuation_entries(self, post_thread_continuation):
3758 contents = post_thread_continuation.get('contents')
3759 if not isinstance(contents, list):
3760 return
3761 for content in contents:
3762 renderer = content.get('backstagePostThreadRenderer')
3763 if not isinstance(renderer, dict):
3764 continue
3765 for entry in self._post_thread_entries(renderer):
3766 yield entry
07aeced6 3767
39ed931e 3768 r''' # unused
3769 def _rich_grid_entries(self, contents):
3770 for content in contents:
3771 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3772 if video_renderer:
3773 entry = self._video_entry(video_renderer)
3774 if entry:
3775 yield entry
3776 '''
a6213a49 3777 def _extract_entries(self, parent_renderer, continuation_list):
3778 # continuation_list is modified in-place with continuation_list = [continuation_token]
3779 continuation_list[:] = [None]
3780 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3781 for content in contents:
3782 if not isinstance(content, dict):
3783 continue
3784 is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict)
3785 if not is_renderer:
3786 renderer = content.get('richItemRenderer')
3787 if renderer:
3788 for entry in self._rich_entries(renderer):
3789 yield entry
3790 continuation_list[0] = self._extract_continuation(parent_renderer)
3791 continue
3792 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3793 for isr_content in isr_contents:
3794 if not isinstance(isr_content, dict):
8bdd16b4 3795 continue
69184e41 3796
a6213a49 3797 known_renderers = {
3798 'playlistVideoListRenderer': self._playlist_entries,
3799 'gridRenderer': self._grid_entries,
3800 'shelfRenderer': lambda x: self._shelf_entries(x),
3801 'backstagePostThreadRenderer': self._post_thread_entries,
3802 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 3803 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
3804 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
a6213a49 3805 }
3806 for key, renderer in isr_content.items():
3807 if key not in known_renderers:
3808 continue
3809 for entry in known_renderers[key](renderer):
3810 if entry:
3811 yield entry
3812 continuation_list[0] = self._extract_continuation(renderer)
3813 break
70d5c17b 3814
3815 if not continuation_list[0]:
a6213a49 3816 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 3817
a6213a49 3818 if not continuation_list[0]:
3819 continuation_list[0] = self._extract_continuation(parent_renderer)
3820
3821 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
3822 continuation_list = [None]
3823 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 3824 tab_content = try_get(tab, lambda x: x['content'], dict)
3825 if not tab_content:
3826 return
3462ffa8 3827 parent_renderer = (
29f7c58a 3828 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3829 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
70d5c17b 3830 for entry in extract_entries(parent_renderer):
3831 yield entry
3462ffa8 3832 continuation = continuation_list[0]
d069eca7 3833
8bdd16b4 3834 for page_num in itertools.count(1):
3835 if not continuation:
3836 break
99e9e001 3837 headers = self.generate_api_headers(
3838 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 3839 response = self._extract_response(
3840 item_id='%s page %s' % (item_id, page_num),
fe93e2c4 3841 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 3842 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
3843
3844 if not response:
8bdd16b4 3845 break
ac56cf38 3846 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
3847 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
3848 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 3849
69184e41 3850 known_continuation_renderers = {
3851 'playlistVideoListContinuation': self._playlist_entries,
3852 'gridContinuation': self._grid_entries,
3853 'itemSectionContinuation': self._post_thread_continuation_entries,
3854 'sectionListContinuation': extract_entries, # for feeds
3855 }
8bdd16b4 3856 continuation_contents = try_get(
69184e41 3857 response, lambda x: x['continuationContents'], dict) or {}
3858 continuation_renderer = None
3859 for key, value in continuation_contents.items():
3860 if key not in known_continuation_renderers:
3462ffa8 3861 continue
69184e41 3862 continuation_renderer = value
3863 continuation_list = [None]
3864 for entry in known_continuation_renderers[key](continuation_renderer):
3865 yield entry
3866 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3867 break
3868 if continuation_renderer:
3869 continue
c5e8d7af 3870
a1b535bd 3871 known_renderers = {
3872 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3873 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 3874 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 3875 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 3876 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 3877 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 3878 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 3879 }
cce889b9 3880 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 3881 continuation_items = try_get(
cce889b9 3882 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 3883 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3884 video_items_renderer = None
3885 for key, value in continuation_item.items():
3886 if key not in known_renderers:
8bdd16b4 3887 continue
a1b535bd 3888 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 3889 continuation_list = [None]
a1b535bd 3890 for entry in known_renderers[key][0](video_items_renderer):
3891 yield entry
9ba5705a 3892 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 3893 break
3894 if video_items_renderer:
3895 continue
8bdd16b4 3896 break
9558dcec 3897
8bdd16b4 3898 @staticmethod
3899 def _extract_selected_tab(tabs):
3900 for tab in tabs:
cd684175 3901 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
3902 if renderer.get('selected') is True:
3903 return renderer
2b3c2546 3904 else:
8bdd16b4 3905 raise ExtractorError('Unable to find selected tab')
b82f815f 3906
47193e02 3907 @classmethod
3908 def _extract_uploader(cls, data):
8bdd16b4 3909 uploader = {}
47193e02 3910 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
3911 owner = try_get(
3912 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3913 if owner:
3914 uploader['uploader'] = owner.get('text')
3915 uploader['uploader_id'] = try_get(
3916 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3917 uploader['uploader_url'] = urljoin(
3918 'https://www.youtube.com/',
3919 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 3920 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 3921
ac56cf38 3922 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 3923 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 3924 tags = []
b60419c5 3925
8bdd16b4 3926 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 3927 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 3928 renderer = try_get(
3929 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3930 if renderer:
b60419c5 3931 channel_name = renderer.get('title')
3932 channel_url = renderer.get('channelUrl')
3933 channel_id = renderer.get('externalId')
39ed931e 3934 else:
64c0d954 3935 renderer = try_get(
3936 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 3937
8bdd16b4 3938 if renderer:
3939 title = renderer.get('title')
ecc97af3 3940 description = renderer.get('description', '')
b60419c5 3941 playlist_id = channel_id
3942 tags = renderer.get('keywords', '').split()
b60419c5 3943
301d07fc 3944 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
3945 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
3946 def _get_uncropped(url):
3947 return url_or_none((url or '').split('=')[0] + '=s0')
3948
3949 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
3950 if avatar_thumbnails:
3951 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
3952 if uncropped_avatar:
3953 avatar_thumbnails.append({
3954 'url': uncropped_avatar,
3955 'id': 'avatar_uncropped',
3956 'preference': 1
3957 })
3958
3959 channel_banners = self._extract_thumbnails(
3960 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
3961 for banner in channel_banners:
3962 banner['preference'] = -10
3963
3964 if channel_banners:
3965 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
3966 if uncropped_banner:
3967 channel_banners.append({
3968 'url': uncropped_banner,
3969 'id': 'banner_uncropped',
3970 'preference': -5
3971 })
3972
3973 primary_thumbnails = self._extract_thumbnails(
3974 primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
a709d873 3975
3462ffa8 3976 if playlist_id is None:
70d5c17b 3977 playlist_id = item_id
f0d785d3 3978
3979 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
3980 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 3981 if title is None:
f0d785d3 3982 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 3983 title += format_field(selected_tab, 'title', ' - %s')
cd684175 3984 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 3985
b60419c5 3986 metadata = {
3987 'playlist_id': playlist_id,
3988 'playlist_title': title,
3989 'playlist_description': description,
3990 'uploader': channel_name,
3991 'uploader_id': channel_id,
3992 'uploader_url': channel_url,
301d07fc 3993 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 3994 'tags': tags,
f0d785d3 3995 'view_count': self._get_count(playlist_stats, 1),
3996 'availability': self._extract_availability(data),
3997 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 3998 'playlist_count': self._get_count(playlist_stats, 0),
3999 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4000 }
4001 if not channel_id:
4002 metadata.update(self._extract_uploader(data))
4003 metadata.update({
4004 'channel': metadata['uploader'],
4005 'channel_id': metadata['uploader_id'],
4006 'channel_url': metadata['uploader_url']})
4007 return self.playlist_result(
d069eca7 4008 self._entries(
ac56cf38 4009 selected_tab, playlist_id, ytcfg,
4010 self._extract_account_syncid(ytcfg, data),
4011 self._extract_visitor_data(data, ytcfg)),
b60419c5 4012 **metadata)
73c4ac2c 4013
ac56cf38 4014 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4015 first_id = last_id = response = None
2be71994 4016 for page_num in itertools.count(1):
cd7c66cf 4017 videos = list(self._playlist_entries(playlist))
4018 if not videos:
4019 return
2be71994 4020 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4021 if start >= len(videos):
4022 return
4023 for video in videos[start:]:
4024 if video['id'] == first_id:
4025 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4026 return
4027 yield video
4028 first_id = first_id or videos[0]['id']
4029 last_id = videos[-1]['id']
79360d99 4030 watch_endpoint = try_get(
4031 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4032 headers = self.generate_api_headers(
4033 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4034 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4035 query = {
4036 'playlistId': playlist_id,
4037 'videoId': watch_endpoint.get('videoId') or last_id,
4038 'index': watch_endpoint.get('index') or len(videos),
4039 'params': watch_endpoint.get('params') or 'OAE%3D'
4040 }
4041 response = self._extract_response(
4042 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4043 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4044 check_get_keys='contents'
4045 )
cd7c66cf 4046 playlist = try_get(
79360d99 4047 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4048
ac56cf38 4049 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4050 title = playlist.get('title') or try_get(
4051 data, lambda x: x['titleText']['simpleText'], compat_str)
4052 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4053
4054 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4055 playlist_url = urljoin(url, try_get(
4056 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4057 compat_str))
4058 if playlist_url and playlist_url != url:
4059 return self.url_result(
4060 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4061 video_title=title)
cd7c66cf 4062
8bdd16b4 4063 return self.playlist_result(
ac56cf38 4064 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4065 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4066
47193e02 4067 def _extract_availability(self, data):
4068 """
4069 Gets the availability of a given playlist/tab.
4070 Note: Unless YouTube tells us explicitly, we do not assume it is public
4071 @param data: response
4072 """
4073 is_private = is_unlisted = None
4074 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4075 badge_labels = self._extract_badges(renderer)
4076
4077 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4078 privacy_dropdown_entries = try_get(
4079 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4080 for renderer_dict in privacy_dropdown_entries:
4081 is_selected = try_get(
4082 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4083 if not is_selected:
4084 continue
052e1350 4085 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4086 if label:
4087 badge_labels.add(label.lower())
4088 break
4089
4090 for badge_label in badge_labels:
4091 if badge_label == 'unlisted':
4092 is_unlisted = True
4093 elif badge_label == 'private':
4094 is_private = True
4095 elif badge_label == 'public':
4096 is_unlisted = is_private = False
4097 return self._availability(is_private, False, False, False, is_unlisted)
4098
4099 @staticmethod
4100 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4101 sidebar_renderer = try_get(
4102 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4103 for item in sidebar_renderer:
4104 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4105 if renderer:
4106 return renderer
4107
ac56cf38 4108 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4109 """
4110 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4111 """
5d342002 4112 browse_id = params = None
47193e02 4113 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4114 if not renderer:
4115 return
4116 menu_renderer = try_get(
4117 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4118 for menu_item in menu_renderer:
4119 if not isinstance(menu_item, dict):
358de58c 4120 continue
47193e02 4121 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4122 text = try_get(
4123 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4124 if not text or text.lower() != 'show unavailable videos':
4125 continue
4126 browse_endpoint = try_get(
4127 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4128 browse_id = browse_endpoint.get('browseId')
4129 params = browse_endpoint.get('params')
4130 break
5d342002 4131
11f9be09 4132 headers = self.generate_api_headers(
99e9e001 4133 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4134 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4135 query = {
4136 'params': params or 'wgYCCAA=',
4137 'browseId': browse_id or 'VL%s' % item_id
4138 }
4139 return self._extract_response(
4140 item_id=item_id, headers=headers, query=query,
fe93e2c4 4141 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4142 note='Downloading API JSON with unavailable videos')
358de58c 4143
ac56cf38 4144 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4145 retries = self.get_param('extractor_retries', 3)
62bff2c1 4146 count = -1
ac56cf38 4147 webpage = data = last_error = None
14fdfea9 4148 while count < retries:
62bff2c1 4149 count += 1
14fdfea9 4150 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4151 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4152 if last_error:
c705177d 4153 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4154 try:
4155 webpage = self._download_webpage(
4156 url, item_id,
4157 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4158 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4159 except ExtractorError as e:
4160 if isinstance(e.cause, network_exceptions):
4161 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4162 last_error = error_to_compat_str(e.cause or e.msg)
4163 if count < retries:
4164 continue
4165 if fatal:
4166 raise
4167 self.report_warning(error_to_compat_str(e))
14fdfea9 4168 break
ac56cf38 4169 else:
4170 try:
4171 self._extract_and_report_alerts(data)
4172 except ExtractorError as e:
4173 if fatal:
4174 raise
4175 self.report_warning(error_to_compat_str(e))
4176 break
4177
4178 if dict_get(data, ('contents', 'currentVideoEndpoint')):
4179 break
4180
4181 last_error = 'Incomplete yt initial data received'
4182 if count >= retries:
4183 if fatal:
4184 raise ExtractorError(last_error)
4185 self.report_warning(last_error)
4186 break
4187
cd7c66cf 4188 return webpage, data
4189
ac56cf38 4190 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4191 data = None
4192 if 'webpage' not in self._configuration_arg('skip'):
4193 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4194 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
4195 if not data:
4196 if not ytcfg and self.is_authenticated:
4197 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4198 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4199 raise ExtractorError(
4200 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4201 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4202 expected=True)
4203 self.report_warning(msg, only_once=True)
4204 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4205 return data, ytcfg
4206
4207 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4208 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4209 resolve_response = self._extract_response(
4210 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4211 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4212 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4213 for ep_key, ep in endpoints.items():
4214 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4215 if params:
4216 return self._extract_response(
4217 item_id=item_id, query=params, ep=ep, headers=headers,
4218 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
4219 check_get_keys=('contents', 'currentVideoEndpoint'))
4220 err_note = 'Failed to resolve url (does the playlist exist?)'
4221 if fatal:
4222 raise ExtractorError(err_note, expected=True)
4223 self.report_warning(err_note, item_id)
4224
a6213a49 4225 @staticmethod
4226 def _smuggle_data(entries, data):
4227 for entry in entries:
4228 if data:
4229 entry['url'] = smuggle_url(entry['url'], data)
4230 yield entry
4231
4232 _SEARCH_PARAMS = None
4233
4234 def _search_results(self, query, params=NO_DEFAULT):
4235 data = {'query': query}
4236 if params is NO_DEFAULT:
4237 params = self._SEARCH_PARAMS
4238 if params:
4239 data['params'] = params
a61fd4cf 4240 continuation_list = [None]
a6213a49 4241 for page_num in itertools.count(1):
a61fd4cf 4242 data.update(continuation_list[0] or {})
a6213a49 4243 search = self._extract_response(
4244 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
a61fd4cf 4245 check_get_keys=('contents', 'onResponseReceivedCommands'))
a6213a49 4246 slr_contents = try_get(
4247 search,
4248 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
4249 lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
4250 list)
a61fd4cf 4251 yield from self._extract_entries({'contents': slr_contents}, continuation_list)
4252 if not continuation_list[0]:
a6213a49 4253 break
4254
4255
4256class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4257 IE_DESC = 'YouTube Tabs'
4258 _VALID_URL = r'''(?x:
4259 https?://
4260 (?:\w+\.)?
4261 (?:
4262 youtube(?:kids)?\.com|
4263 %(invidious)s
4264 )/
4265 (?:
4266 (?P<channel_type>channel|c|user|browse)/|
4267 (?P<not_channel>
4268 feed/|hashtag/|
4269 (?:playlist|watch)\?.*?\blist=
4270 )|
4271 (?!(?:%(reserved_names)s)\b) # Direct URLs
4272 )
4273 (?P<id>[^/?\#&]+)
4274 )''' % {
4275 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4276 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4277 }
4278 IE_NAME = 'youtube:tab'
4279
4280 _TESTS = [{
4281 'note': 'playlists, multipage',
4282 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4283 'playlist_mincount': 94,
4284 'info_dict': {
4285 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4286 'title': 'Igor Kleiner - Playlists',
a6213a49 4287 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4288 'uploader': 'Igor Kleiner',
a6213a49 4289 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4290 'channel': 'Igor Kleiner',
4291 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4292 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4293 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4294 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4295 'channel_follower_count': int
a6213a49 4296 },
4297 }, {
4298 'note': 'playlists, multipage, different order',
4299 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4300 'playlist_mincount': 94,
4301 'info_dict': {
4302 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4303 'title': 'Igor Kleiner - Playlists',
a6213a49 4304 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4305 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4306 'uploader': 'Igor Kleiner',
4307 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4308 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4309 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4310 'channel': 'Igor Kleiner',
4311 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4312 'channel_follower_count': int
a6213a49 4313 },
4314 }, {
4315 'note': 'playlists, series',
4316 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4317 'playlist_mincount': 5,
4318 'info_dict': {
4319 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4320 'title': '3Blue1Brown - Playlists',
4321 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4322 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4323 'uploader': '3Blue1Brown',
976ae3ea 4324 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4325 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4326 'channel': '3Blue1Brown',
4327 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4328 'tags': ['Mathematics'],
6c73052c 4329 'channel_follower_count': int
a6213a49 4330 },
4331 }, {
4332 'note': 'playlists, singlepage',
4333 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4334 'playlist_mincount': 4,
4335 'info_dict': {
4336 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4337 'title': 'ThirstForScience - Playlists',
4338 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4339 'uploader': 'ThirstForScience',
4340 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4341 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4342 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4343 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4344 'tags': 'count:13',
4345 'channel': 'ThirstForScience',
6c73052c 4346 'channel_follower_count': int
a6213a49 4347 }
4348 }, {
4349 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4350 'only_matching': True,
4351 }, {
4352 'note': 'basic, single video playlist',
4353 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4354 'info_dict': {
4355 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4356 'uploader': 'Sergey M.',
4357 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4358 'title': 'youtube-dl public playlist',
976ae3ea 4359 'description': '',
4360 'tags': [],
4361 'view_count': int,
4362 'modified_date': '20201130',
4363 'channel': 'Sergey M.',
4364 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4365 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4366 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4367 },
4368 'playlist_count': 1,
4369 }, {
4370 'note': 'empty playlist',
4371 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4372 'info_dict': {
4373 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4374 'uploader': 'Sergey M.',
4375 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4376 'title': 'youtube-dl empty playlist',
976ae3ea 4377 'tags': [],
4378 'channel': 'Sergey M.',
4379 'description': '',
4380 'modified_date': '20160902',
4381 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4382 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4383 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4384 },
4385 'playlist_count': 0,
4386 }, {
4387 'note': 'Home tab',
4388 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4389 'info_dict': {
4390 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4391 'title': 'lex will - Home',
4392 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4393 'uploader': 'lex will',
4394 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4395 'channel': 'lex will',
4396 'tags': ['bible', 'history', 'prophesy'],
4397 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4398 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4399 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4400 'channel_follower_count': int
a6213a49 4401 },
4402 'playlist_mincount': 2,
4403 }, {
4404 'note': 'Videos tab',
4405 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4406 'info_dict': {
4407 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4408 'title': 'lex will - Videos',
4409 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4410 'uploader': 'lex will',
4411 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4412 'tags': ['bible', 'history', 'prophesy'],
4413 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4414 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4415 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4416 'channel': 'lex will',
6c73052c 4417 'channel_follower_count': int
a6213a49 4418 },
4419 'playlist_mincount': 975,
4420 }, {
4421 'note': 'Videos tab, sorted by popular',
4422 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4423 'info_dict': {
4424 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4425 'title': 'lex will - Videos',
4426 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4427 'uploader': 'lex will',
4428 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4429 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4430 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4431 'channel': 'lex will',
4432 'tags': ['bible', 'history', 'prophesy'],
4433 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4434 'channel_follower_count': int
a6213a49 4435 },
4436 'playlist_mincount': 199,
4437 }, {
4438 'note': 'Playlists tab',
4439 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4440 'info_dict': {
4441 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4442 'title': 'lex will - Playlists',
4443 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4444 'uploader': 'lex will',
4445 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4446 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4447 'channel': 'lex will',
4448 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4449 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4450 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4451 'channel_follower_count': int
a6213a49 4452 },
4453 'playlist_mincount': 17,
4454 }, {
4455 'note': 'Community tab',
4456 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4457 'info_dict': {
4458 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4459 'title': 'lex will - Community',
4460 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4461 'uploader': 'lex will',
4462 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4463 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4464 'channel': 'lex will',
4465 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4466 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4467 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4468 'channel_follower_count': int
a6213a49 4469 },
4470 'playlist_mincount': 18,
4471 }, {
4472 'note': 'Channels tab',
4473 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4474 'info_dict': {
4475 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4476 'title': 'lex will - Channels',
4477 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4478 'uploader': 'lex will',
4479 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4480 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4481 'channel': 'lex will',
4482 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4483 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4484 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4485 'channel_follower_count': int
a6213a49 4486 },
4487 'playlist_mincount': 12,
4488 }, {
4489 'note': 'Search tab',
4490 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4491 'playlist_mincount': 40,
4492 'info_dict': {
4493 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4494 'title': '3Blue1Brown - Search - linear algebra',
4495 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4496 'uploader': '3Blue1Brown',
4497 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4498 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4499 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4500 'tags': ['Mathematics'],
4501 'channel': '3Blue1Brown',
4502 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4503 'channel_follower_count': int
a6213a49 4504 },
4505 }, {
4506 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4507 'only_matching': True,
4508 }, {
4509 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4510 'only_matching': True,
4511 }, {
4512 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4513 'only_matching': True,
4514 }, {
4515 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4516 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4517 'info_dict': {
4518 'title': '29C3: Not my department',
4519 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4520 'uploader': 'Christiaan008',
4521 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4522 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4523 'tags': [],
4524 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4525 'view_count': int,
4526 'modified_date': '20150605',
4527 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4528 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4529 'channel': 'Christiaan008',
a6213a49 4530 },
4531 'playlist_count': 96,
4532 }, {
4533 'note': 'Large playlist',
4534 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4535 'info_dict': {
4536 'title': 'Uploads from Cauchemar',
4537 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4538 'uploader': 'Cauchemar',
4539 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4540 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4541 'tags': [],
4542 'modified_date': r're:\d{8}',
4543 'channel': 'Cauchemar',
4544 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4545 'view_count': int,
4546 'description': '',
4547 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4548 },
4549 'playlist_mincount': 1123,
976ae3ea 4550 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4551 }, {
4552 'note': 'even larger playlist, 8832 videos',
4553 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4554 'only_matching': True,
4555 }, {
4556 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4557 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4558 'info_dict': {
4559 'title': 'Uploads from Interstellar Movie',
4560 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4561 'uploader': 'Interstellar Movie',
4562 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4563 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4564 'tags': [],
4565 'view_count': int,
4566 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4567 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4568 'channel': 'Interstellar Movie',
4569 'description': '',
4570 'modified_date': r're:\d{8}',
a6213a49 4571 },
4572 'playlist_mincount': 21,
4573 }, {
4574 'note': 'Playlist with "show unavailable videos" button',
4575 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4576 'info_dict': {
4577 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4578 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4579 'uploader': 'Phim Siêu Nhân Nhật Bản',
4580 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4581 'view_count': int,
4582 'channel': 'Phim Siêu Nhân Nhật Bản',
4583 'tags': [],
4584 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4585 'description': '',
4586 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4587 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4588 'modified_date': r're:\d{8}',
a6213a49 4589 },
4590 'playlist_mincount': 200,
976ae3ea 4591 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4592 }, {
4593 'note': 'Playlist with unavailable videos in page 7',
4594 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4595 'info_dict': {
4596 'title': 'Uploads from BlankTV',
4597 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4598 'uploader': 'BlankTV',
4599 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4600 'channel': 'BlankTV',
4601 'channel_url': 'https://www.youtube.com/c/blanktv',
4602 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4603 'view_count': int,
4604 'tags': [],
4605 'uploader_url': 'https://www.youtube.com/c/blanktv',
4606 'modified_date': r're:\d{8}',
4607 'description': '',
a6213a49 4608 },
4609 'playlist_mincount': 1000,
976ae3ea 4610 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4611 }, {
4612 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4613 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4614 'info_dict': {
4615 'title': 'Data Analysis with Dr Mike Pound',
4616 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4617 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4618 'uploader': 'Computerphile',
4619 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4620 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4621 'tags': [],
4622 'view_count': int,
4623 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4624 'channel_url': 'https://www.youtube.com/user/Computerphile',
4625 'channel': 'Computerphile',
a6213a49 4626 },
4627 'playlist_mincount': 11,
4628 }, {
4629 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4630 'only_matching': True,
4631 }, {
4632 'note': 'Playlist URL that does not actually serve a playlist',
4633 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4634 'info_dict': {
4635 'id': 'FqZTN594JQw',
4636 'ext': 'webm',
4637 'title': "Smiley's People 01 detective, Adventure Series, Action",
4638 'uploader': 'STREEM',
4639 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4640 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4641 'upload_date': '20150526',
4642 'license': 'Standard YouTube License',
4643 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4644 'categories': ['People & Blogs'],
4645 'tags': list,
4646 'view_count': int,
4647 'like_count': int,
a6213a49 4648 },
4649 'params': {
4650 'skip_download': True,
4651 },
4652 'skip': 'This video is not available.',
4653 'add_ie': [YoutubeIE.ie_key()],
4654 }, {
4655 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4656 'only_matching': True,
4657 }, {
4658 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4659 'only_matching': True,
4660 }, {
4661 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4662 'info_dict': {
6c73052c 4663 'id': 'GgL890LIznQ', # This will keep changing
a6213a49 4664 'ext': 'mp4',
976ae3ea 4665 'title': str,
a6213a49 4666 'uploader': 'Sky News',
4667 'uploader_id': 'skynews',
4668 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4669 'upload_date': r're:\d{8}',
976ae3ea 4670 'description': str,
a6213a49 4671 'categories': ['News & Politics'],
4672 'tags': list,
4673 'like_count': int,
6c73052c 4674 'release_timestamp': 1642502819,
976ae3ea 4675 'channel': 'Sky News',
4676 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4677 'age_limit': 0,
4678 'view_count': int,
6c73052c 4679 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 4680 'playable_in_embed': True,
6c73052c 4681 'release_date': '20220118',
976ae3ea 4682 'availability': 'public',
4683 'live_status': 'is_live',
4684 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 4685 'channel_follower_count': int
a6213a49 4686 },
4687 'params': {
4688 'skip_download': True,
4689 },
976ae3ea 4690 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 4691 }, {
4692 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4693 'info_dict': {
4694 'id': 'a48o2S1cPoo',
4695 'ext': 'mp4',
4696 'title': 'The Young Turks - Live Main Show',
4697 'uploader': 'The Young Turks',
4698 'uploader_id': 'TheYoungTurks',
4699 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4700 'upload_date': '20150715',
4701 'license': 'Standard YouTube License',
4702 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4703 'categories': ['News & Politics'],
4704 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4705 'like_count': int,
a6213a49 4706 },
4707 'params': {
4708 'skip_download': True,
4709 },
4710 'only_matching': True,
4711 }, {
4712 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4713 'only_matching': True,
4714 }, {
4715 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4716 'only_matching': True,
4717 }, {
4718 'note': 'A channel that is not live. Should raise error',
4719 'url': 'https://www.youtube.com/user/numberphile/live',
4720 'only_matching': True,
4721 }, {
4722 'url': 'https://www.youtube.com/feed/trending',
4723 'only_matching': True,
4724 }, {
4725 'url': 'https://www.youtube.com/feed/library',
4726 'only_matching': True,
4727 }, {
4728 'url': 'https://www.youtube.com/feed/history',
4729 'only_matching': True,
4730 }, {
4731 'url': 'https://www.youtube.com/feed/subscriptions',
4732 'only_matching': True,
4733 }, {
4734 'url': 'https://www.youtube.com/feed/watch_later',
4735 'only_matching': True,
4736 }, {
4737 'note': 'Recommended - redirects to home page.',
4738 'url': 'https://www.youtube.com/feed/recommended',
4739 'only_matching': True,
4740 }, {
4741 'note': 'inline playlist with not always working continuations',
4742 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4743 'only_matching': True,
4744 }, {
4745 'url': 'https://www.youtube.com/course',
4746 'only_matching': True,
4747 }, {
4748 'url': 'https://www.youtube.com/zsecurity',
4749 'only_matching': True,
4750 }, {
4751 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4752 'only_matching': True,
4753 }, {
4754 'url': 'https://www.youtube.com/TheYoungTurks/live',
4755 'only_matching': True,
4756 }, {
4757 'url': 'https://www.youtube.com/hashtag/cctv9',
4758 'info_dict': {
4759 'id': 'cctv9',
4760 'title': '#cctv9',
976ae3ea 4761 'tags': [],
a6213a49 4762 },
4763 'playlist_mincount': 350,
4764 }, {
4765 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4766 'only_matching': True,
4767 }, {
4768 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4769 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4770 'only_matching': True
4771 }, {
4772 'note': '/browse/ should redirect to /channel/',
4773 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4774 'only_matching': True
4775 }, {
4776 'note': 'VLPL, should redirect to playlist?list=PL...',
4777 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4778 'info_dict': {
4779 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4780 'uploader': 'NoCopyrightSounds',
4781 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4782 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4783 'title': 'NCS Releases',
976ae3ea 4784 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4785 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4786 'modified_date': r're:\d{8}',
4787 'view_count': int,
4788 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4789 'tags': [],
4790 'channel': 'NoCopyrightSounds',
a6213a49 4791 },
4792 'playlist_mincount': 166,
976ae3ea 4793 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4794 }, {
4795 'note': 'Topic, should redirect to playlist?list=UU...',
4796 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4797 'info_dict': {
4798 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4799 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4800 'title': 'Uploads from Royalty Free Music - Topic',
4801 'uploader': 'Royalty Free Music - Topic',
976ae3ea 4802 'tags': [],
4803 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4804 'channel': 'Royalty Free Music - Topic',
4805 'view_count': int,
4806 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4807 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4808 'modified_date': r're:\d{8}',
4809 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4810 'description': '',
a6213a49 4811 },
4812 'expected_warnings': [
a6213a49 4813 'The URL does not have a videos tab',
976ae3ea 4814 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 4815 ],
4816 'playlist_mincount': 101,
4817 }, {
4818 'note': 'Topic without a UU playlist',
4819 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
4820 'info_dict': {
4821 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
4822 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 4823 'tags': [],
a6213a49 4824 },
4825 'expected_warnings': [
976ae3ea 4826 'the playlist redirect gave error',
a6213a49 4827 ],
4828 'playlist_mincount': 9,
4829 }, {
4830 'note': 'Youtube music Album',
4831 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
4832 'info_dict': {
4833 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
4834 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 4835 'tags': [],
4836 'view_count': int,
4837 'description': '',
4838 'availability': 'unlisted',
4839 'modified_date': r're:\d{8}',
a6213a49 4840 },
4841 'playlist_count': 50,
4842 }, {
4843 'note': 'unlisted single video playlist',
4844 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4845 'info_dict': {
4846 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4847 'uploader': 'colethedj',
4848 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4849 'title': 'yt-dlp unlisted playlist test',
976ae3ea 4850 'availability': 'unlisted',
4851 'tags': [],
4852 'modified_date': '20211208',
4853 'channel': 'colethedj',
4854 'view_count': int,
4855 'description': '',
4856 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
4857 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4858 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 4859 },
4860 'playlist_count': 1,
4861 }, {
4862 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
4863 'url': 'https://www.youtube.com/feed/recommended',
4864 'info_dict': {
4865 'id': 'recommended',
4866 'title': 'recommended',
6c73052c 4867 'tags': [],
a6213a49 4868 },
4869 'playlist_mincount': 50,
4870 'params': {
4871 'skip_download': True,
4872 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4873 },
4874 }, {
4875 'note': 'API Fallback: /videos tab, sorted by oldest first',
4876 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
4877 'info_dict': {
4878 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4879 'title': 'Cody\'sLab - Videos',
4880 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
4881 'uploader': 'Cody\'sLab',
4882 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 4883 'channel': 'Cody\'sLab',
4884 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4885 'tags': [],
4886 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
4887 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 4888 'channel_follower_count': int
a6213a49 4889 },
4890 'playlist_mincount': 650,
4891 'params': {
4892 'skip_download': True,
4893 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4894 },
4895 }, {
4896 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
4897 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4898 'info_dict': {
4899 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4900 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4901 'title': 'Uploads from Royalty Free Music - Topic',
4902 'uploader': 'Royalty Free Music - Topic',
976ae3ea 4903 'modified_date': r're:\d{8}',
4904 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4905 'description': '',
4906 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4907 'tags': [],
4908 'channel': 'Royalty Free Music - Topic',
4909 'view_count': int,
4910 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 4911 },
4912 'expected_warnings': [
976ae3ea 4913 'does not have a videos tab',
4914 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 4915 ],
4916 'playlist_mincount': 101,
4917 'params': {
4918 'skip_download': True,
4919 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4920 },
4921 }]
4922
4923 @classmethod
4924 def suitable(cls, url):
4925 return False if YoutubeIE.suitable(url) else super(
4926 YoutubeTabIE, cls).suitable(url)
9297939e 4927
cd7c66cf 4928 def _real_extract(self, url):
9297939e 4929 url, smuggled_data = unsmuggle_url(url, {})
4930 if self.is_music_url(url):
4931 smuggled_data['is_music_url'] = True
fe03a6cd 4932 info_dict = self.__real_extract(url, smuggled_data)
9297939e 4933 if info_dict.get('entries'):
4934 info_dict['entries'] = self._smuggle_data(info_dict['entries'], smuggled_data)
4935 return info_dict
4936
64f36541 4937 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 4938
4939 def __real_extract(self, url, smuggled_data):
cd7c66cf 4940 item_id = self._match_id(url)
4941 url = compat_urlparse.urlunparse(
4942 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 4943 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 4944
fe03a6cd 4945 def get_mobj(url):
37e57a9f 4946 mobj = self._URL_RE.match(url).groupdict()
07cce701 4947 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 4948 return mobj
4949
37e57a9f 4950 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 4951 # Youtube returns incomplete data if tabname is not lower case
4952 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 4953 if is_channel:
4954 if smuggled_data.get('is_music_url'):
37e57a9f 4955 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 4956 item_id = item_id[2:]
37e57a9f 4957 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
4958 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 4959 mdata = self._extract_tab_endpoint(
37e57a9f 4960 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
4961 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
4962 get_all=False, expected_type=compat_str)
ac56cf38 4963 if not murl:
37e57a9f 4964 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 4965 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 4966 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
4967 pre = f'https://www.youtube.com/channel/{item_id}'
4968
64f36541 4969 original_tab_name = tab
fe03a6cd 4970 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
4971 # Home URLs should redirect to /videos/
37e57a9f 4972 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
4973 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 4974 tab = '/videos'
4975
4976 url = ''.join((pre, tab, post))
4977 mobj = get_mobj(url)
cd7c66cf 4978
4979 # Handle both video/playlist URLs
201c1459 4980 qs = parse_qs(url)
37e57a9f 4981 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
cd7c66cf 4982
fe03a6cd 4983 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 4984 if not playlist_id:
fe03a6cd 4985 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 4986 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 4987 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 4988 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
4989 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 4990 mobj = get_mobj(url)
cd7c66cf 4991
4992 if video_id and playlist_id:
a06916d9 4993 if self.get_param('noplaylist'):
37e57a9f 4994 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
4995 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
4996 ie=YoutubeIE.ie_key(), video_id=video_id)
4997 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 4998
ac56cf38 4999 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5000
37e57a9f 5001 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5002 if tabs:
5003 selected_tab = self._extract_selected_tab(tabs)
64f36541 5004 selected_tab_name = selected_tab.get('title', '').lower()
5005 if selected_tab_name == 'home':
5006 selected_tab_name = 'featured'
5007 requested_tab_name = mobj['tab'][1:]
09f1580e 5008 if 'no-youtube-channel-redirect' not in compat_opts:
64f36541 5009 if requested_tab_name == 'live':
09f1580e 5010 # Live tab should have redirected to the video
5011 raise ExtractorError('The channel is not currently live', expected=True)
64f36541 5012 if requested_tab_name not in ('', selected_tab_name):
5013 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5014 if not original_tab_name:
5015 if item_id[:2] == 'UC':
5016 # Topic channels don't have /videos. Use the equivalent playlist instead
5017 pl_id = f'UU{item_id[2:]}'
5018 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5019 try:
5020 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5021 except ExtractorError:
5022 redirect_warning += ' and the playlist redirect gave error'
5023 else:
5024 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5025 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5026 if selected_tab_name and selected_tab_name != requested_tab_name:
5027 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5028 else:
5029 raise ExtractorError(redirect_warning, expected=True)
18db7548 5030
37e57a9f 5031 if redirect_warning:
64f36541 5032 self.to_screen(redirect_warning)
37e57a9f 5033 self.write_debug(f'Final URL: {url}')
18db7548 5034
358de58c 5035 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5036 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5037 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5038 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5039 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5040 if tabs:
ac56cf38 5041 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5042
37e57a9f 5043 playlist = traverse_obj(
5044 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5045 if playlist:
ac56cf38 5046 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5047
37e57a9f 5048 video_id = traverse_obj(
5049 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5050 if video_id:
09f1580e 5051 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5052 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5053 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5054 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5055
8bdd16b4 5056 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5057
c5e8d7af 5058
8bdd16b4 5059class YoutubePlaylistIE(InfoExtractor):
96565c7e 5060 IE_DESC = 'YouTube playlists'
8bdd16b4 5061 _VALID_URL = r'''(?x)(?:
5062 (?:https?://)?
5063 (?:\w+\.)?
5064 (?:
5065 (?:
5066 youtube(?:kids)?\.com|
d9190e44 5067 %(invidious)s
8bdd16b4 5068 )
5069 /.*?\?.*?\blist=
5070 )?
5071 (?P<id>%(playlist_id)s)
d9190e44
RH
5072 )''' % {
5073 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5074 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5075 }
8bdd16b4 5076 IE_NAME = 'youtube:playlist'
cdc628a4 5077 _TESTS = [{
8bdd16b4 5078 'note': 'issue #673',
5079 'url': 'PLBB231211A4F62143',
cdc628a4 5080 'info_dict': {
8bdd16b4 5081 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5082 'id': 'PLBB231211A4F62143',
976ae3ea 5083 'uploader': 'Wickman',
8bdd16b4 5084 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5085 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5086 'view_count': int,
5087 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5088 'modified_date': r're:\d{8}',
5089 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5090 'channel': 'Wickman',
5091 'tags': [],
5092 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5093 },
5094 'playlist_mincount': 29,
5095 }, {
5096 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5097 'info_dict': {
5098 'title': 'YDL_safe_search',
5099 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5100 },
5101 'playlist_count': 2,
5102 'skip': 'This playlist is private',
9558dcec 5103 }, {
8bdd16b4 5104 'note': 'embedded',
5105 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5106 'playlist_count': 4,
9558dcec 5107 'info_dict': {
8bdd16b4 5108 'title': 'JODA15',
5109 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5110 'uploader': 'milan',
5111 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5112 'description': '',
5113 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5114 'tags': [],
5115 'modified_date': '20140919',
5116 'view_count': int,
5117 'channel': 'milan',
5118 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5119 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5120 },
5121 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5122 }, {
8bdd16b4 5123 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 5124 'playlist_mincount': 654,
8bdd16b4 5125 'info_dict': {
5126 'title': '2018 Chinese New Singles (11/6 updated)',
5127 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5128 'uploader': 'LBK',
5129 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5130 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5131 'channel': 'LBK',
5132 'view_count': int,
5133 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5134 'tags': [],
5135 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5136 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5137 'modified_date': r're:\d{8}',
5138 },
5139 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5140 }, {
29f7c58a 5141 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5142 'only_matching': True,
5143 }, {
5144 # music album playlist
5145 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5146 'only_matching': True,
5147 }]
5148
5149 @classmethod
5150 def suitable(cls, url):
201c1459 5151 if YoutubeTabIE.suitable(url):
5152 return False
49a57e70 5153 from ..utils import parse_qs
201c1459 5154 qs = parse_qs(url)
5155 if qs.get('v', [None])[0]:
5156 return False
5157 return super(YoutubePlaylistIE, cls).suitable(url)
29f7c58a 5158
5159 def _real_extract(self, url):
5160 playlist_id = self._match_id(url)
46953e7e 5161 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5162 url = update_url_query(
5163 'https://www.youtube.com/playlist',
5164 parse_qs(url) or {'list': playlist_id})
5165 if is_music_url:
5166 url = smuggle_url(url, {'is_music_url': True})
5167 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5168
5169
5170class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5171 IE_DESC = 'youtu.be'
29f7c58a 5172 _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}
5173 _TESTS = [{
8bdd16b4 5174 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5175 'info_dict': {
5176 'id': 'yeWKywCrFtk',
5177 'ext': 'mp4',
5178 'title': 'Small Scale Baler and Braiding Rugs',
5179 'uploader': 'Backus-Page House Museum',
5180 'uploader_id': 'backuspagemuseum',
5181 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5182 'upload_date': '20161008',
5183 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5184 'categories': ['Nonprofits & Activism'],
5185 'tags': list,
5186 'like_count': int,
976ae3ea 5187 'age_limit': 0,
5188 'playable_in_embed': True,
5189 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5190 'channel': 'Backus-Page House Museum',
5191 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5192 'live_status': 'not_live',
5193 'view_count': int,
5194 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5195 'availability': 'public',
5196 'duration': 59,
8bdd16b4 5197 },
5198 'params': {
5199 'noplaylist': True,
5200 'skip_download': True,
5201 },
39e7107d 5202 }, {
8bdd16b4 5203 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5204 'only_matching': True,
cdc628a4
PH
5205 }]
5206
8bdd16b4 5207 def _real_extract(self, url):
5ad28e7f 5208 mobj = self._match_valid_url(url)
29f7c58a 5209 video_id = mobj.group('id')
5210 playlist_id = mobj.group('playlist_id')
8bdd16b4 5211 return self.url_result(
29f7c58a 5212 update_url_query('https://www.youtube.com/watch', {
5213 'v': video_id,
5214 'list': playlist_id,
5215 'feature': 'youtu.be',
5216 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5217
5218
b6ce9bb0 5219class YoutubeLivestreamEmbedIE(InfoExtractor):
5220 IE_DESC = 'YouTube livestream embeds'
5221 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5222 _TESTS = [{
5223 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5224 'only_matching': True,
5225 }]
5226
5227 def _real_extract(self, url):
5228 channel_id = self._match_id(url)
5229 return self.url_result(
5230 f'https://www.youtube.com/channel/{channel_id}/live',
5231 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5232
5233
8bdd16b4 5234class YoutubeYtUserIE(InfoExtractor):
96565c7e 5235 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5236 IE_NAME = 'youtube:user'
8bdd16b4 5237 _VALID_URL = r'ytuser:(?P<id>.+)'
5238 _TESTS = [{
5239 'url': 'ytuser:phihag',
5240 'only_matching': True,
5241 }]
5242
5243 def _real_extract(self, url):
5244 user_id = self._match_id(url)
5245 return self.url_result(
c586f9e8 5246 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5247 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5248
b05654f0 5249
3d3dddc9 5250class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5251 IE_NAME = 'youtube:favorites'
96565c7e 5252 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5253 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5254 _LOGIN_REQUIRED = True
5255 _TESTS = [{
5256 'url': ':ytfav',
5257 'only_matching': True,
5258 }, {
5259 'url': ':ytfavorites',
5260 'only_matching': True,
5261 }]
5262
5263 def _real_extract(self, url):
5264 return self.url_result(
5265 'https://www.youtube.com/playlist?list=LL',
5266 ie=YoutubeTabIE.ie_key())
5267
5268
a6213a49 5269class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5270 IE_DESC = 'YouTube search'
78caa52a 5271 IE_NAME = 'youtube:search'
b05654f0 5272 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5273 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
9dd8e46a 5274 _TESTS = []
b05654f0 5275
a61fd4cf 5276
5f7cb91a 5277class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5278 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5279 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5280 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5281 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
75dff0ee 5282
c9ae7b95 5283
a6213a49 5284class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5285 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5286 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
5287 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
3462ffa8 5288 _TESTS = [{
5289 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5290 'playlist_mincount': 5,
5291 'info_dict': {
11f9be09 5292 'id': 'youtube-dl test video',
3462ffa8 5293 'title': 'youtube-dl test video',
5294 }
a61fd4cf 5295 }, {
5296 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5297 'playlist_mincount': 5,
5298 'info_dict': {
5299 'id': 'python',
5300 'title': 'python',
5301 }
5302
3462ffa8 5303 }, {
5304 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5305 'only_matching': True,
5306 }]
5307
5308 def _real_extract(self, url):
4dfbf869 5309 qs = parse_qs(url)
386e1dd9 5310 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5311 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5312
5313
5314class YoutubeFeedsInfoExtractor(YoutubeTabIE):
d7ae0639 5315 """
25f14e9f 5316 Base class for feed extractors
3d3dddc9 5317 Subclasses must define the _FEED_NAME property.
d7ae0639 5318 """
b2e8bc1b 5319 _LOGIN_REQUIRED = True
ef2f3c7f 5320 _TESTS = []
d7ae0639
JMF
5321
5322 @property
5323 def IE_NAME(self):
78caa52a 5324 return 'youtube:%s' % self._FEED_NAME
04cc9617 5325
3853309f 5326 def _real_extract(self, url):
3d3dddc9 5327 return self.url_result(
5328 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
5329 ie=YoutubeTabIE.ie_key())
25f14e9f
S
5330
5331
ef2f3c7f 5332class YoutubeWatchLaterIE(InfoExtractor):
5333 IE_NAME = 'youtube:watchlater'
96565c7e 5334 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5335 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5336 _TESTS = [{
8bdd16b4 5337 'url': ':ytwatchlater',
bc7a9cd8
S
5338 'only_matching': True,
5339 }]
25f14e9f
S
5340
5341 def _real_extract(self, url):
ef2f3c7f 5342 return self.url_result(
5343 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5344
5345
25f14e9f 5346class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5347 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5348 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5349 _FEED_NAME = 'recommended'
45db527f 5350 _LOGIN_REQUIRED = False
3d3dddc9 5351 _TESTS = [{
5352 'url': ':ytrec',
5353 'only_matching': True,
5354 }, {
5355 'url': ':ytrecommended',
5356 'only_matching': True,
5357 }, {
5358 'url': 'https://youtube.com',
5359 'only_matching': True,
5360 }]
1ed5b5c9 5361
1ed5b5c9 5362
25f14e9f 5363class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5364 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5365 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5366 _FEED_NAME = 'subscriptions'
3d3dddc9 5367 _TESTS = [{
5368 'url': ':ytsubs',
5369 'only_matching': True,
5370 }, {
5371 'url': ':ytsubscriptions',
5372 'only_matching': True,
5373 }]
1ed5b5c9 5374
1ed5b5c9 5375
25f14e9f 5376class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5377 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5378 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5379 _FEED_NAME = 'history'
3d3dddc9 5380 _TESTS = [{
5381 'url': ':ythistory',
5382 'only_matching': True,
5383 }]
1ed5b5c9
JMF
5384
5385
15870e90
PH
5386class YoutubeTruncatedURLIE(InfoExtractor):
5387 IE_NAME = 'youtube:truncated_url'
5388 IE_DESC = False # Do not list
975d35db 5389 _VALID_URL = r'''(?x)
b95aab84
PH
5390 (?:https?://)?
5391 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5392 (?:watch\?(?:
c4808c60 5393 feature=[a-z_]+|
b95aab84
PH
5394 annotation_id=annotation_[^&]+|
5395 x-yt-cl=[0-9]+|
c1708b89 5396 hl=[^&]*|
287be8c6 5397 t=[0-9]+
b95aab84
PH
5398 )?
5399 |
5400 attribution_link\?a=[^&]+
5401 )
5402 $
975d35db 5403 '''
15870e90 5404
c4808c60 5405 _TESTS = [{
2d3d2997 5406 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5407 'only_matching': True,
dc2fc736 5408 }, {
2d3d2997 5409 'url': 'https://www.youtube.com/watch?',
dc2fc736 5410 'only_matching': True,
b95aab84
PH
5411 }, {
5412 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5413 'only_matching': True,
5414 }, {
5415 'url': 'https://www.youtube.com/watch?feature=foo',
5416 'only_matching': True,
c1708b89
PH
5417 }, {
5418 'url': 'https://www.youtube.com/watch?hl=en-GB',
5419 'only_matching': True,
287be8c6
PH
5420 }, {
5421 'url': 'https://www.youtube.com/watch?t=2372',
5422 'only_matching': True,
c4808c60
PH
5423 }]
5424
15870e90
PH
5425 def _real_extract(self, url):
5426 raise ExtractorError(
78caa52a
PH
5427 'Did you forget to quote the URL? Remember that & is a meta '
5428 'character in most shells, so you want to put the URL in quotes, '
3867038a 5429 'like youtube-dl '
2d3d2997 5430 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 5431 ' or simply youtube-dl BaW_jenozKc .',
15870e90 5432 expected=True)
772fd5cc
PH
5433
5434
3cd786db 5435class YoutubeClipIE(InfoExtractor):
5436 IE_NAME = 'youtube:clip'
5437 IE_DESC = False # Do not list
5438 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5439
5440 def _real_extract(self, url):
5441 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5442 return self.url_result(url, 'Generic')
5443
5444
772fd5cc
PH
5445class YoutubeTruncatedIDIE(InfoExtractor):
5446 IE_NAME = 'youtube:truncated_id'
5447 IE_DESC = False # Do not list
b95aab84 5448 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
5449
5450 _TESTS = [{
5451 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5452 'only_matching': True,
5453 }]
5454
5455 def _real_extract(self, url):
5456 video_id = self._match_id(url)
5457 raise ExtractorError(
5458 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
5459 expected=True)