]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
Standardize retry mechanism (#1649)
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
6e634cbe 1import base64
d92f5d5a 2import calendar
109dd3b2 3import copy
fe93e2c4 4import datetime
a5c56234 5import hashlib
0ca96d48 6import itertools
c5e8d7af 7import json
720c3099 8import math
c4417ddb 9import os.path
d77ab8e2 10import random
c5e8d7af 11import re
46383212 12import sys
f8271158 13import threading
8a784c74 14import time
e0df6211 15import traceback
14f25df2 16import urllib.error
ac668111 17import urllib.parse
c5e8d7af 18
b05654f0 19from .common import InfoExtractor, SearchInfoExtractor
14f25df2 20from ..compat import functools
545cc85d 21from ..jsinterp import JSInterpreter
4bb4a188 22from ..utils import (
f8271158 23 NO_DEFAULT,
24 ExtractorError,
693f0600 25 UserNotLive,
720c3099 26 bug_reports_message,
82d02080 27 classproperty,
c5e8d7af 28 clean_html,
d92f5d5a 29 datetime_from_str,
11f9be09 30 dict_get,
2d30521a 31 float_or_none,
11f9be09 32 format_field,
ff91cf74 33 get_first,
dd27fd17 34 int_or_none,
641ad5d8 35 is_html,
34921b43 36 join_nonempty,
48416bc4 37 js_to_json,
94278f72 38 mimetype2ext,
9c0d7f49 39 network_exceptions,
11f9be09 40 orderedSet,
6310acf5 41 parse_codecs,
49bd8c66 42 parse_count,
7c80519c 43 parse_duration,
7ea65411 44 parse_iso8601,
4dfbf869 45 parse_qs,
dca3ff4a 46 qualities,
3995d37d 47 remove_start,
cf7e015f 48 smuggle_url,
dbdaaa23 49 str_or_none,
c93d53f5 50 str_to_int,
f3aa3c3f 51 strftime_or_none,
7c365c21 52 traverse_obj,
556dbe7f 53 try_get,
c5e8d7af
PH
54 unescapeHTML,
55 unified_strdate,
f0d785d3 56 unified_timestamp,
cf7e015f 57 unsmuggle_url,
8bdd16b4 58 update_url_query,
21c340b8 59 url_or_none,
fe93e2c4 60 urljoin,
7c365c21 61 variadic,
c5e8d7af
PH
62)
63
962ffcf8 64# any clients starting with _ cannot be explicitly requested by the user
000c15a4 65INNERTUBE_CLIENTS = {
66 'web': {
67 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
68 'INNERTUBE_CONTEXT': {
69 'client': {
70 'clientName': 'WEB',
18c7683d 71 'clientVersion': '2.20211221.00.00',
000c15a4 72 }
73 },
74 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
75 },
76 'web_embedded': {
77 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
78 'INNERTUBE_CONTEXT': {
79 'client': {
80 'clientName': 'WEB_EMBEDDED_PLAYER',
18c7683d 81 'clientVersion': '1.20211215.00.01',
000c15a4 82 },
83 },
84 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
85 },
86 'web_music': {
87 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
88 'INNERTUBE_HOST': 'music.youtube.com',
89 'INNERTUBE_CONTEXT': {
90 'client': {
91 'clientName': 'WEB_REMIX',
18c7683d 92 'clientVersion': '1.20211213.00.00',
000c15a4 93 }
94 },
95 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
96 },
e7e94f2a 97 'web_creator': {
18c7683d 98 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
99 'INNERTUBE_CONTEXT': {
100 'client': {
101 'clientName': 'WEB_CREATOR',
18c7683d 102 'clientVersion': '1.20211220.02.00',
e7e94f2a
D
103 }
104 },
105 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
106 },
000c15a4 107 'android': {
18c7683d 108 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 109 'INNERTUBE_CONTEXT': {
110 'client': {
111 'clientName': 'ANDROID',
18c7683d 112 'clientVersion': '16.49',
000c15a4 113 }
114 },
115 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 116 'REQUIRE_JS_PLAYER': False
000c15a4 117 },
118 'android_embedded': {
18c7683d 119 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 120 'INNERTUBE_CONTEXT': {
121 'client': {
122 'clientName': 'ANDROID_EMBEDDED_PLAYER',
18c7683d 123 'clientVersion': '16.49',
000c15a4 124 },
125 },
b6de707d 126 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
127 'REQUIRE_JS_PLAYER': False
000c15a4 128 },
129 'android_music': {
18c7683d 130 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 131 'INNERTUBE_CONTEXT': {
132 'client': {
133 'clientName': 'ANDROID_MUSIC',
18c7683d 134 'clientVersion': '4.57',
000c15a4 135 }
136 },
137 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 138 'REQUIRE_JS_PLAYER': False
000c15a4 139 },
e7e94f2a 140 'android_creator': {
18c7683d 141 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
142 'INNERTUBE_CONTEXT': {
143 'client': {
144 'clientName': 'ANDROID_CREATOR',
18c7683d 145 'clientVersion': '21.47',
e7e94f2a
D
146 },
147 },
b6de707d 148 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
149 'REQUIRE_JS_PLAYER': False
e7e94f2a 150 },
18c7683d 151 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
152 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 153 'ios': {
18c7683d 154 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 155 'INNERTUBE_CONTEXT': {
156 'client': {
157 'clientName': 'IOS',
18c7683d 158 'clientVersion': '16.46',
159 'deviceModel': 'iPhone14,3',
000c15a4 160 }
161 },
b6de707d 162 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
163 'REQUIRE_JS_PLAYER': False
000c15a4 164 },
165 'ios_embedded': {
000c15a4 166 'INNERTUBE_CONTEXT': {
167 'client': {
168 'clientName': 'IOS_MESSAGES_EXTENSION',
18c7683d 169 'clientVersion': '16.46',
170 'deviceModel': 'iPhone14,3',
000c15a4 171 },
172 },
b6de707d 173 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
174 'REQUIRE_JS_PLAYER': False
000c15a4 175 },
176 'ios_music': {
18c7683d 177 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 178 'INNERTUBE_CONTEXT': {
179 'client': {
180 'clientName': 'IOS_MUSIC',
18c7683d 181 'clientVersion': '4.57',
000c15a4 182 },
183 },
b6de707d 184 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
185 'REQUIRE_JS_PLAYER': False
000c15a4 186 },
e7e94f2a
D
187 'ios_creator': {
188 'INNERTUBE_CONTEXT': {
189 'client': {
190 'clientName': 'IOS_CREATOR',
18c7683d 191 'clientVersion': '21.47',
e7e94f2a
D
192 },
193 },
b6de707d 194 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
195 'REQUIRE_JS_PLAYER': False
e7e94f2a 196 },
3619f78d 197 # mweb has 'ultralow' formats
198 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 199 'mweb': {
18c7683d 200 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 201 'INNERTUBE_CONTEXT': {
202 'client': {
203 'clientName': 'MWEB',
18c7683d 204 'clientVersion': '2.20211221.01.00',
000c15a4 205 }
206 },
207 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
208 },
209 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
210 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
211 'tv_embedded': {
212 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
213 'INNERTUBE_CONTEXT': {
214 'client': {
215 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
216 'clientVersion': '2.0',
217 },
218 },
219 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
220 },
000c15a4 221}
222
223
e7870111
D
224def _split_innertube_client(client_name):
225 variant, *base = client_name.rsplit('.', 1)
226 if base:
227 return variant, base[0], variant
228 base, *variant = client_name.split('_', 1)
229 return client_name, base, variant[0] if variant else None
230
231
000c15a4 232def build_innertube_clients():
2e4cacd0 233 THIRD_PARTY = {
e7870111 234 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 235 }
e7870111 236 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 237 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 238
239 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 240 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 241 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 242 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 243 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 244
e7870111 245 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 246 ytcfg['priority'] = 10 * priority(base_client)
247
e48b3875 248 if not variant:
e7870111
D
249 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
250 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
251 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
252 embedscreen['priority'] -= 3
253 elif variant == 'embedded':
e48b3875 254 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 255 ytcfg['priority'] -= 2
e48b3875 256 else:
000c15a4 257 ytcfg['priority'] -= 3
258
259
260build_innertube_clients()
261
262
de7f3446 263class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 264 """Provide base functions for Youtube extractors"""
e00eb564 265
3462ffa8 266 _RESERVED_NAMES = (
3cd786db 267 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 268 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 269 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 270 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 271
3619f78d 272 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
273
52efa4b3 274 # _NETRC_MACHINE = 'youtube'
3619f78d 275
b2e8bc1b
JMF
276 # If True it will raise an error if no login info is provided
277 _LOGIN_REQUIRED = False
278
d9190e44
RH
279 _INVIDIOUS_SITES = (
280 # invidious-redirect websites
281 r'(?:www\.)?redirect\.invidious\.io',
282 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 283 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
284 r'(?:www\.)?invidious\.pussthecat\.org',
285 r'(?:www\.)?invidious\.zee\.li',
286 r'(?:www\.)?invidious\.ethibox\.fr',
287 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
288 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
289 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
290 # youtube-dl invidious instances list
291 r'(?:(?:www|no)\.)?invidiou\.sh',
292 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
293 r'(?:www\.)?invidious\.kabi\.tk',
294 r'(?:www\.)?invidious\.mastodon\.host',
295 r'(?:www\.)?invidious\.zapashcanon\.fr',
296 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
297 r'(?:www\.)?invidious\.tinfoil-hat\.net',
298 r'(?:www\.)?invidious\.himiko\.cloud',
299 r'(?:www\.)?invidious\.reallyancient\.tech',
300 r'(?:www\.)?invidious\.tube',
301 r'(?:www\.)?invidiou\.site',
302 r'(?:www\.)?invidious\.site',
303 r'(?:www\.)?invidious\.xyz',
304 r'(?:www\.)?invidious\.nixnet\.xyz',
305 r'(?:www\.)?invidious\.048596\.xyz',
306 r'(?:www\.)?invidious\.drycat\.fr',
307 r'(?:www\.)?inv\.skyn3t\.in',
308 r'(?:www\.)?tube\.poal\.co',
309 r'(?:www\.)?tube\.connect\.cafe',
310 r'(?:www\.)?vid\.wxzm\.sx',
311 r'(?:www\.)?vid\.mint\.lgbt',
312 r'(?:www\.)?vid\.puffyan\.us',
313 r'(?:www\.)?yewtu\.be',
314 r'(?:www\.)?yt\.elukerio\.org',
315 r'(?:www\.)?yt\.lelux\.fi',
316 r'(?:www\.)?invidious\.ggc-project\.de',
317 r'(?:www\.)?yt\.maisputain\.ovh',
318 r'(?:www\.)?ytprivate\.com',
319 r'(?:www\.)?invidious\.13ad\.de',
320 r'(?:www\.)?invidious\.toot\.koeln',
321 r'(?:www\.)?invidious\.fdn\.fr',
322 r'(?:www\.)?watch\.nettohikari\.com',
323 r'(?:www\.)?invidious\.namazso\.eu',
324 r'(?:www\.)?invidious\.silkky\.cloud',
325 r'(?:www\.)?invidious\.exonip\.de',
326 r'(?:www\.)?invidious\.riverside\.rocks',
327 r'(?:www\.)?invidious\.blamefran\.net',
328 r'(?:www\.)?invidious\.moomoo\.de',
329 r'(?:www\.)?ytb\.trom\.tf',
330 r'(?:www\.)?yt\.cyberhost\.uk',
331 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
332 r'(?:www\.)?qklhadlycap4cnod\.onion',
333 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
334 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
335 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
336 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
337 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
338 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
339 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
340 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
341 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
342 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
343 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
344 r'(?:www\.)?piped\.kavin\.rocks',
345 r'(?:www\.)?piped\.silkky\.cloud',
346 r'(?:www\.)?piped\.tokhmi\.xyz',
347 r'(?:www\.)?piped\.moomoo\.me',
348 r'(?:www\.)?il\.ax',
349 r'(?:www\.)?piped\.syncpundit\.com',
350 r'(?:www\.)?piped\.mha\.fi',
351 r'(?:www\.)?piped\.mint\.lgbt',
352 r'(?:www\.)?piped\.privacy\.com\.de',
d9190e44
RH
353 )
354
cce889b9 355 def _initialize_consent(self):
356 cookies = self._get_cookies('https://www.youtube.com/')
357 if cookies.get('__Secure-3PSID'):
358 return
359 consent_id = None
360 consent = cookies.get('CONSENT')
361 if consent:
362 if 'YES' in consent.value:
363 return
364 consent_id = self._search_regex(
365 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
366 if not consent_id:
367 consent_id = random.randint(100, 999)
368 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 369
f3aa3c3f 370 def _initialize_pref(self):
371 cookies = self._get_cookies('https://www.youtube.com/')
372 pref_cookie = cookies.get('PREF')
373 pref = {}
374 if pref_cookie:
375 try:
14f25df2 376 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 377 except ValueError:
378 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 379 pref.update({'hl': 'en', 'tz': 'UTC'})
14f25df2 380 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 381
b2e8bc1b 382 def _real_initialize(self):
f3aa3c3f 383 self._initialize_pref()
cce889b9 384 self._initialize_consent()
a25bca9f 385 self._check_login_required()
386
387 def _check_login_required(self):
24146491 388 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 389 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 390
b7c47b74 391 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
392 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 393
000c15a4 394 def _get_default_ytcfg(self, client='web'):
395 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 396
000c15a4 397 def _get_innertube_host(self, client='web'):
398 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 399
000c15a4 400 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 401 # try_get but with fallback to default ytcfg client values when present
402 _func = lambda y: try_get(y, getter, expected_type)
403 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
404
000c15a4 405 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 406 return self._ytcfg_get_safe(
407 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 408 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 409
000c15a4 410 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 411 return self._ytcfg_get_safe(
412 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 413 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 414
2ae778b8 415 def _select_api_hostname(self, req_api_hostname, default_client=None):
416 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
417 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
418
000c15a4 419 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 420 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 421
000c15a4 422 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 423 context = get_first(
424 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 425 # Enforce language and tz for extraction
426 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
427 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 428 return context
429
cf87314d 430 _SAPISID = None
431
109dd3b2 432 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 433 time_now = round(time.time())
cf87314d 434 if self._SAPISID is None:
435 yt_cookies = self._get_cookies('https://www.youtube.com')
436 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
437 # See: https://github.com/yt-dlp/yt-dlp/issues/393
438 sapisid_cookie = dict_get(
439 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
440 if sapisid_cookie and sapisid_cookie.value:
441 self._SAPISID = sapisid_cookie.value
442 self.write_debug('Extracted SAPISID cookie')
443 # SAPISID cookie is required if not already present
444 if not yt_cookies.get('SAPISID'):
445 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
446 self._set_cookie(
447 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
448 else:
449 self._SAPISID = False
450 if not self._SAPISID:
451 return None
1974e99f 452 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
453 sapisidhash = hashlib.sha1(
86e5f3ed 454 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 455 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
456
457 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 458 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 459 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 460
109dd3b2 461 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 462 data.update(query)
11f9be09 463 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 464 real_headers.update({'content-type': 'application/json'})
465 if headers:
466 real_headers.update(headers)
2ae778b8 467 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
468 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 469 return self._download_json(
2ae778b8 470 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 471 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 472 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 473 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 474
65141660 475 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
476 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 477
99e9e001 478 @staticmethod
479 def _extract_session_index(*data):
480 """
481 Index of current account in account list.
482 See: https://github.com/yt-dlp/yt-dlp/pull/519
483 """
484 for ytcfg in data:
485 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
486 if session_index is not None:
487 return session_index
488
489 # Deprecated?
490 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 491 if ytcfg:
14f25df2 492 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
493 if token:
494 return token
99e9e001 495 if webpage:
496 return self._search_regex(
497 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
498 'identity token', default=None, fatal=False)
a1c5d2ca
M
499
500 @staticmethod
fe93e2c4 501 def _extract_account_syncid(*args):
8ea3f7b9 502 """
503 Extract syncId required to download private playlists of secondary channels
fe93e2c4 504 @params response and/or ytcfg
8ea3f7b9 505 """
fe93e2c4 506 for data in args:
507 # ytcfg includes channel_syncid if on secondary channel
14f25df2 508 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 509 if delegated_sid:
510 return delegated_sid
511 sync_ids = (try_get(
512 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 513 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 514 if len(sync_ids) >= 2 and sync_ids[1]:
515 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
516 # and just "user_syncid||" for primary channel. We only want the channel_syncid
517 return sync_ids[0]
a1c5d2ca 518
ac56cf38 519 @staticmethod
520 def _extract_visitor_data(*args):
521 """
522 Extracts visitorData from an API response or ytcfg
523 Appears to be used to track session state
524 """
9222c381 525 return get_first(
6c73052c 526 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 527 expected_type=str)
ac56cf38 528
2762dbb1 529 @functools.cached_property
99e9e001 530 def is_authenticated(self):
531 return bool(self._generate_sapisidhash_header())
532
11f9be09 533 def extract_ytcfg(self, video_id, webpage):
8c54a305 534 if not webpage:
535 return {}
29f7c58a 536 return self._parse_json(
537 self._search_regex(
538 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 539 default='{}'), video_id, fatal=False) or {}
540
11f9be09 541 def generate_api_headers(
99e9e001 542 self, *, ytcfg=None, account_syncid=None, session_index=None,
543 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
544
2ae778b8 545 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 546 headers = {
14f25df2 547 'X-YouTube-Client-Name': str(
11f9be09 548 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
549 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 550 'Origin': origin,
551 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
552 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 553 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 554 }
555 if session_index is None:
314ee305 556 session_index = self._extract_session_index(ytcfg)
557 if account_syncid or session_index is not None:
558 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 559
109dd3b2 560 auth = self._generate_sapisidhash_header(origin)
f4f751af 561 if auth is not None:
562 headers['Authorization'] = auth
109dd3b2 563 headers['X-Origin'] = origin
99e9e001 564 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 565
a25bca9f 566 def _download_ytcfg(self, client, video_id):
567 url = {
568 'web': 'https://www.youtube.com',
569 'web_music': 'https://music.youtube.com',
570 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
571 }.get(client)
572 if not url:
573 return {}
574 webpage = self._download_webpage(
575 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
576 return self.extract_ytcfg(video_id, webpage) or {}
577
2d6659b9 578 @staticmethod
579 def _build_api_continuation_query(continuation, ctp=None):
580 query = {
581 'continuation': continuation
582 }
583 # TODO: Inconsistency with clickTrackingParams.
584 # Currently we have a fixed ctp contained within context (from ytcfg)
585 # and a ctp in root query for continuation.
586 if ctp:
587 query['clickTracking'] = {'clickTrackingParams': ctp}
588 return query
589
2d6659b9 590 @classmethod
591 def _extract_next_continuation_data(cls, renderer):
592 next_continuation = try_get(
593 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
594 lambda x: x['continuation']['reloadContinuationData']), dict)
595 if not next_continuation:
596 return
597 continuation = next_continuation.get('continuation')
598 if not continuation:
599 return
600 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 601 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 602
603 @classmethod
604 def _extract_continuation_ep_data(cls, continuation_ep: dict):
605 if isinstance(continuation_ep, dict):
606 continuation = try_get(
14f25df2 607 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 608 if not continuation:
609 return
610 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 611 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 612
613 @classmethod
614 def _extract_continuation(cls, renderer):
615 next_continuation = cls._extract_next_continuation_data(renderer)
616 if next_continuation:
617 return next_continuation
fe93e2c4 618
2d6659b9 619 contents = []
620 for key in ('contents', 'items'):
621 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 622
2d6659b9 623 for content in contents:
624 if not isinstance(content, dict):
625 continue
626 continuation_ep = try_get(
627 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
628 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
629 dict)
630 continuation = cls._extract_continuation_ep_data(continuation_ep)
631 if continuation:
632 return continuation
633
fe93e2c4 634 @classmethod
635 def _extract_alerts(cls, data):
109dd3b2 636 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
637 if not isinstance(alert_dict, dict):
638 continue
639 for alert in alert_dict.values():
640 alert_type = alert.get('type')
641 if not alert_type:
642 continue
052e1350 643 message = cls._get_text(alert, 'text')
109dd3b2 644 if message:
645 yield alert_type, message
646
c0ac49bc 647 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 648 errors = []
649 warnings = []
650 for alert_type, alert_message in alerts:
641ad5d8 651 if alert_type.lower() == 'error' and fatal:
109dd3b2 652 errors.append([alert_type, alert_message])
653 else:
654 warnings.append([alert_type, alert_message])
655
656 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 657 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 658 if errors:
659 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
660
661 def _extract_and_report_alerts(self, data, *args, **kwargs):
662 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
663
47193e02 664 def _extract_badges(self, renderer: dict):
665 badges = set()
666 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
14f25df2 667 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], str)
47193e02 668 if label:
669 badges.add(label.lower())
670 return badges
671
672 @staticmethod
052e1350 673 def _get_text(data, *path_list, max_runs=None):
674 for path in path_list or [None]:
675 if path is None:
676 obj = [data]
677 else:
678 obj = traverse_obj(data, path, default=[])
679 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
680 obj = [obj]
681 for item in obj:
14f25df2 682 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 683 if text:
684 return text
685 runs = try_get(item, lambda x: x['runs'], list) or []
686 if not runs and isinstance(item, list):
687 runs = item
688
689 runs = runs[:min(len(runs), max_runs or len(runs))]
690 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
691 if text:
692 return text
47193e02 693
f0d785d3 694 def _get_count(self, data, *path_list):
695 count_text = self._get_text(data, *path_list) or ''
696 count = parse_count(count_text)
697 if count is None:
698 count = str_to_int(
699 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
700 return count
701
a709d873 702 @staticmethod
703 def _extract_thumbnails(data, *path_list):
704 """
705 Extract thumbnails from thumbnails dict
706 @param path_list: path list to level that contains 'thumbnails' key
707 """
708 thumbnails = []
709 for path in path_list or [()]:
710 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
711 thumbnail_url = url_or_none(thumbnail.get('url'))
712 if not thumbnail_url:
713 continue
714 # Sometimes youtube gives a wrong thumbnail URL. See:
715 # https://github.com/yt-dlp/yt-dlp/issues/233
716 # https://github.com/ytdl-org/youtube-dl/issues/28023
717 if 'maxresdefault' in thumbnail_url:
718 thumbnail_url = thumbnail_url.split('?')[0]
719 thumbnails.append({
720 'url': thumbnail_url,
721 'height': int_or_none(thumbnail.get('height')),
722 'width': int_or_none(thumbnail.get('width')),
723 })
724 return thumbnails
725
f3aa3c3f 726 @staticmethod
727 def extract_relative_time(relative_time_text):
728 """
729 Extracts a relative time from string and converts to dt object
f0d785d3 730 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 731 """
f0d785d3 732 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 733 if mobj:
f0d785d3 734 start = mobj.group('start')
735 if start:
736 return datetime_from_str(start)
f3aa3c3f 737 try:
f0d785d3 738 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 739 except ValueError:
740 return None
741
742 def _extract_time_text(self, renderer, *path_list):
a25bca9f 743 """@returns (timestamp, time_text)"""
f3aa3c3f 744 text = self._get_text(renderer, *path_list) or ''
745 dt = self.extract_relative_time(text)
746 timestamp = None
747 if isinstance(dt, datetime.datetime):
748 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 749
750 if timestamp is None:
751 timestamp = (
752 unified_timestamp(text) or unified_timestamp(
753 self._search_regex(
17322130 754 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 755 text.lower(), 'time text', default=None)))
f0d785d3 756
f3aa3c3f 757 if text and timestamp is None:
17322130 758 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
f3aa3c3f 759 return timestamp, text
760
109dd3b2 761 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
762 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 763 default_client='web'):
be5c1ae8 764 for retry in self.RetryManager():
109dd3b2 765 try:
766 response = self._call_api(
767 ep=ep, fatal=True, headers=headers,
be5c1ae8 768 video_id=item_id, query=query, note=note,
109dd3b2 769 context=self._extract_context(ytcfg, default_client),
770 api_key=self._extract_api_key(ytcfg, default_client),
be5c1ae8 771 api_hostname=api_hostname, default_client=default_client)
109dd3b2 772 except ExtractorError as e:
be5c1ae8 773 if not isinstance(e.cause, network_exceptions):
774 return self._error_or_warning(e, fatal=fatal)
775 elif not isinstance(e.cause, urllib.error.HTTPError):
776 retry.error = e
777 continue
109dd3b2 778
be5c1ae8 779 first_bytes = e.cause.read(512)
780 if not is_html(first_bytes):
781 yt_error = try_get(
782 self._parse_json(
783 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
784 lambda x: x['error']['message'], str)
785 if yt_error:
786 self._report_alerts([('ERROR', yt_error)], fatal=False)
787 # Downloading page may result in intermittent 5xx HTTP error
788 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
789 # We also want to catch all other network exceptions since errors in later pages can be troublesome
790 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
791 if e.cause.code not in (403, 429):
792 retry.error = e
793 continue
794 return self._error_or_warning(e, fatal=fatal)
795
796 try:
797 self._extract_and_report_alerts(response, only_once=True)
798 except ExtractorError as e:
799 # YouTube servers may return errors we want to retry on in a 200 OK response
800 # See: https://github.com/yt-dlp/yt-dlp/issues/839
801 if 'unknown error' in e.msg.lower():
802 retry.error = e
803 continue
804 return self._error_or_warning(e, fatal=fatal)
805 # Youtube sometimes sends incomplete data
806 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
807 if not traverse_obj(response, *variadic(check_get_keys)):
808 retry.error = ExtractorError('Incomplete data received')
809 continue
810
811 return response
109dd3b2 812
9297939e 813 @staticmethod
814 def is_music_url(url):
815 return re.match(r'https?://music\.youtube\.com/', url) is not None
816
30a074c2 817 def _extract_video(self, renderer):
818 video_id = renderer.get('videoId')
052e1350 819 title = self._get_text(renderer, 'title')
820 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 821 duration = parse_duration(self._get_text(
822 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 823 if duration is None:
824 duration = parse_duration(self._search_regex(
825 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
826 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
827 video_id, default=None, group='duration'))
828
f0d785d3 829 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 830
052e1350 831 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 832 channel_id = traverse_obj(
a44ca5a4 833 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
834 expected_type=str, get_all=False)
f3aa3c3f 835 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
836 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
837 overlay_style = traverse_obj(
a44ca5a4 838 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
839 get_all=False, expected_type=str)
f3aa3c3f 840 badges = self._extract_badges(renderer)
a709d873 841 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
fd2ad7cb 842 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 843 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
844 expected_type=str)) or ''
fd2ad7cb 845 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 846 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 847 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 848
30a074c2 849 return {
39ed931e 850 '_type': 'url',
30a074c2 851 'ie_key': YoutubeIE.ie_key(),
852 'id': video_id,
fd2ad7cb 853 'url': url,
30a074c2 854 'title': title,
855 'description': description,
856 'duration': duration,
857 'view_count': view_count,
858 'uploader': uploader,
f3aa3c3f 859 'channel_id': channel_id,
a709d873 860 'thumbnails': thumbnails,
a44ca5a4 861 'upload_date': (strftime_or_none(timestamp, '%Y%m%d')
862 if self._configuration_arg('approximate_date', ie_key='youtubetab')
863 else None),
f3aa3c3f 864 'live_status': ('is_upcoming' if scheduled_timestamp is not None
865 else 'was_live' if 'streamed' in time_text.lower()
866 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
867 else None),
868 'release_timestamp': scheduled_timestamp,
869 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 870 }
871
0c148415 872
360e1ca5 873class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 874 IE_DESC = 'YouTube'
cb7dfeea 875 _VALID_URL = r"""(?x)^
c5e8d7af 876 (
edb53e2d 877 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 878 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
879 (?:www\.)?deturl\.com/www\.youtube\.com|
880 (?:www\.)?pwnyoutube\.com|
881 (?:www\.)?hooktube\.com|
882 (?:www\.)?yourepeat\.com|
883 tube\.majestyc\.net|
884 %(invidious)s|
885 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
886 (?:.*?\#/)? # handle anchor (#/) redirect urls
887 (?: # the various things that can precede the ID:
b6ce9bb0 888 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 889 |(?: # or the v= param in all its forms
f7000f3a 890 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 891 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 892 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
893 v=
894 )
f4b05232 895 ))
cbaed4bb
S
896 |(?:
897 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
898 vid\.plus| # or vid.plus/xxxx
899 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 900 %(invidious)s
cbaed4bb 901 )/
edb53e2d 902 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 903 )
c5e8d7af 904 )? # all until now is optional -> you can pass the naked ID
201c1459 905 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 906 (?(1).+)? # if we found the ID, everything can follow
9297939e 907 (?:\#|$)""" % {
d9190e44 908 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 909 }
bfd973ec 910 _EMBED_REGEX = [r'''(?x)
911 (?:
912 <iframe[^>]+?src=|
913 data-video-url=|
914 <embed[^>]+?src=|
915 embedSWF\(?:\s*|
916 <object[^>]+data=|
917 new\s+SWFObject\(
918 )
919 (["\'])
920 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
921 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
922 \1''']
e40c758c 923 _PLAYER_INFO_RE = (
cc2db878 924 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
925 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$',
545cc85d 926 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 927 )
2c62dc26 928 _formats = {
c2d3cb4c 929 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
930 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
931 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
932 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
933 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
934 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
935 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
936 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 937 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 938 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
939 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
940 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
941 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
942 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
943 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 944 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 945 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
946 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 947
948
949 # 3D videos
c2d3cb4c 950 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
951 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
952 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
953 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 954 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
955 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
956 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 957
96fb5605 958 # Apple HTTP Live Streaming
11f12195 959 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 960 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
961 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
962 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
963 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
964 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 965 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
966 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
967
968 # DASH mp4 video
d23028a8
S
969 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
970 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
971 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
972 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
973 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 974 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
975 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
976 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
977 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
978 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
979 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
980 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 981
f6f1fc92 982 # Dash mp4 audio
d23028a8
S
983 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
984 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
985 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
986 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
987 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
988 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
989 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
990
991 # Dash webm
d23028a8
S
992 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
993 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
994 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
995 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
996 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
997 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
998 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
999 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1000 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1001 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1002 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1003 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1004 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1005 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1006 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1007 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1008 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1009 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1010 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1011 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1012 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1013 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1014
1015 # Dash webm audio
d23028a8
S
1016 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1017 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1018
0857baad 1019 # Dash webm audio with opus inside
d23028a8
S
1020 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1021 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1022 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1023
ce6b9a2d
PH
1024 # RTMP (unnamed)
1025 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1026
1027 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1028 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1029 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1030 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1031 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1032 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1033 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1034 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1035 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1036 }
29f7c58a 1037 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1038
fd5c4aab
S
1039 _GEO_BYPASS = False
1040
78caa52a 1041 IE_NAME = 'youtube'
2eb88d95
PH
1042 _TESTS = [
1043 {
2d3d2997 1044 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1045 'info_dict': {
1046 'id': 'BaW_jenozKc',
1047 'ext': 'mp4',
3867038a 1048 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1049 'uploader': 'Philipp Hagemeister',
1050 'uploader_id': 'phihag',
ec85ded8 1051 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1052 'channel': 'Philipp Hagemeister',
dd4c4492
S
1053 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1054 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1055 'upload_date': '20121002',
ff9f925b 1056 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1057 'categories': ['Science & Technology'],
3867038a 1058 'tags': ['youtube-dl'],
556dbe7f 1059 'duration': 10,
dbdaaa23 1060 'view_count': int,
3e7c1224 1061 'like_count': int,
ff9f925b 1062 'availability': 'public',
1063 'playable_in_embed': True,
1064 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1065 'live_status': 'not_live',
1066 'age_limit': 0,
7c80519c 1067 'start_time': 1,
297a564b 1068 'end_time': 9,
12a1b225 1069 'comment_count': int,
6c73052c 1070 'channel_follower_count': int
2eb88d95 1071 }
0e853ca4 1072 },
fccd3771 1073 {
4bc3a23e
PH
1074 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1075 'note': 'Embed-only video (#1746)',
1076 'info_dict': {
1077 'id': 'yZIXLfi8CZQ',
1078 'ext': 'mp4',
1079 'upload_date': '20120608',
1080 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1081 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1082 'uploader': 'SET India',
94bfcd23 1083 'uploader_id': 'setindia',
ec85ded8 1084 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1085 'age_limit': 18,
545cc85d 1086 },
1087 'skip': 'Private video',
fccd3771 1088 },
11b56058 1089 {
8bdd16b4 1090 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1091 'note': 'Use the first video ID in the URL',
1092 'info_dict': {
1093 'id': 'BaW_jenozKc',
1094 'ext': 'mp4',
3867038a 1095 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1096 'uploader': 'Philipp Hagemeister',
1097 'uploader_id': 'phihag',
ec85ded8 1098 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1099 'channel': 'Philipp Hagemeister',
1100 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1101 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1102 'upload_date': '20121002',
976ae3ea 1103 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1104 'categories': ['Science & Technology'],
3867038a 1105 'tags': ['youtube-dl'],
556dbe7f 1106 'duration': 10,
dbdaaa23 1107 'view_count': int,
11b56058 1108 'like_count': int,
976ae3ea 1109 'availability': 'public',
1110 'playable_in_embed': True,
1111 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1112 'live_status': 'not_live',
1113 'age_limit': 0,
12a1b225 1114 'comment_count': int,
6c73052c 1115 'channel_follower_count': int
34a7de29
S
1116 },
1117 'params': {
1118 'skip_download': True,
1119 },
11b56058 1120 },
dd27fd17 1121 {
2d3d2997 1122 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1123 'note': '256k DASH audio (format 141) via DASH manifest',
1124 'info_dict': {
1125 'id': 'a9LDPn-MO4I',
1126 'ext': 'm4a',
1127 'upload_date': '20121002',
1128 'uploader_id': '8KVIDEO',
ec85ded8 1129 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1130 'description': '',
1131 'uploader': '8KVIDEO',
1132 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1133 },
4bc3a23e
PH
1134 'params': {
1135 'youtube_include_dash_manifest': True,
1136 'format': '141',
4919603f 1137 },
de3c7fe0 1138 'skip': 'format 141 not served anymore',
dd27fd17 1139 },
8bdd16b4 1140 # DASH manifest with encrypted signature
1141 {
1142 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1143 'info_dict': {
1144 'id': 'IB3lcPjvWLA',
1145 'ext': 'm4a',
1146 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1147 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1148 'duration': 244,
1149 'uploader': 'AfrojackVEVO',
1150 'uploader_id': 'AfrojackVEVO',
1151 'upload_date': '20131011',
cc2db878 1152 'abr': 129.495,
976ae3ea 1153 'like_count': int,
1154 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1155 'playable_in_embed': True,
1156 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1157 'view_count': int,
1158 'track': 'The Spark',
1159 'live_status': 'not_live',
1160 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1161 'channel': 'Afrojack',
1162 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1163 'tags': 'count:19',
1164 'availability': 'public',
1165 'categories': ['Music'],
1166 'age_limit': 0,
1167 'alt_title': 'The Spark',
6c73052c 1168 'channel_follower_count': int
8bdd16b4 1169 },
1170 'params': {
1171 'youtube_include_dash_manifest': True,
1172 'format': '141/bestaudio[ext=m4a]',
1173 },
1174 },
65c2fde2 1175 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1176 {
65c2fde2 1177 'note': 'Embed allowed age-gate video',
2d3d2997 1178 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1179 'info_dict': {
1180 'id': 'HtVdAasjOgU',
1181 'ext': 'mp4',
1182 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1183 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1184 'duration': 142,
c522adb1
JMF
1185 'uploader': 'The Witcher',
1186 'uploader_id': 'WitcherGame',
ec85ded8 1187 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1188 'upload_date': '20140605',
34952f09 1189 'age_limit': 18,
976ae3ea 1190 'categories': ['Gaming'],
1191 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1192 'availability': 'needs_auth',
1193 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1194 'like_count': int,
1195 'channel': 'The Witcher',
1196 'live_status': 'not_live',
1197 'tags': 'count:17',
1198 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1199 'playable_in_embed': True,
1200 'view_count': int,
6c73052c 1201 'channel_follower_count': int
c522adb1
JMF
1202 },
1203 },
65c2fde2 1204 {
1205 'note': 'Age-gate video with embed allowed in public site',
1206 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1207 'info_dict': {
1208 'id': 'HsUATh_Nc2U',
1209 'ext': 'mp4',
1210 'title': 'Godzilla 2 (Official Video)',
1211 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1212 'upload_date': '20200408',
1213 'uploader_id': 'FlyingKitty900',
1214 'uploader': 'FlyingKitty',
1215 'age_limit': 18,
976ae3ea 1216 'availability': 'needs_auth',
1217 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1218 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1219 'channel': 'FlyingKitty',
1220 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1221 'view_count': int,
1222 'categories': ['Entertainment'],
1223 'live_status': 'not_live',
1224 'tags': ['Flyingkitty', 'godzilla 2'],
1225 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1226 'like_count': int,
1227 'duration': 177,
1228 'playable_in_embed': True,
6c73052c 1229 'channel_follower_count': int
65c2fde2 1230 },
1231 },
1232 {
1233 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1234 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1235 'info_dict': {
1236 'id': 'Tq92D6wQ1mg',
1237 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1238 'ext': 'mp4',
17322130 1239 'upload_date': '20191228',
65c2fde2 1240 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1241 'uploader': 'Projekt Melody',
1242 'description': 'md5:17eccca93a786d51bc67646756894066',
1243 'age_limit': 18,
976ae3ea 1244 'like_count': int,
1245 'availability': 'needs_auth',
1246 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1247 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1248 'view_count': int,
1249 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1250 'channel': 'Projekt Melody',
1251 'live_status': 'not_live',
1252 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1253 'playable_in_embed': True,
1254 'categories': ['Entertainment'],
1255 'duration': 106,
1256 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1257 'comment_count': int,
6c73052c 1258 'channel_follower_count': int
65c2fde2 1259 },
1260 },
1261 {
1262 'note': 'Non-Agegated non-embeddable video',
1263 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1264 'info_dict': {
1265 'id': 'MeJVWBSsPAY',
1266 'ext': 'mp4',
1267 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1268 'uploader': 'Herr Lurik',
1269 'uploader_id': 'st3in234',
1270 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1271 'upload_date': '20130730',
976ae3ea 1272 'track': 'Such mich find mich',
1273 'age_limit': 0,
1274 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1275 'like_count': int,
1276 'playable_in_embed': False,
1277 'creator': 'OOMPH!',
1278 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1279 'view_count': int,
1280 'alt_title': 'Such mich find mich',
1281 'duration': 210,
1282 'channel': 'Herr Lurik',
1283 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1284 'categories': ['Music'],
1285 'availability': 'public',
1286 'uploader_url': 'http://www.youtube.com/user/st3in234',
1287 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1288 'live_status': 'not_live',
1289 'artist': 'OOMPH!',
6c73052c 1290 'channel_follower_count': int
65c2fde2 1291 },
1292 },
1293 {
1294 'note': 'Non-bypassable age-gated video',
1295 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1296 'only_matching': True,
1297 },
8bdd16b4 1298 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1299 # YouTube Red ad is not captured for creator
1300 {
1301 'url': '__2ABJjxzNo',
1302 'info_dict': {
1303 'id': '__2ABJjxzNo',
1304 'ext': 'mp4',
1305 'duration': 266,
1306 'upload_date': '20100430',
1307 'uploader_id': 'deadmau5',
1308 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1309 'creator': 'deadmau5',
1310 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1311 'uploader': 'deadmau5',
1312 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1313 'alt_title': 'Some Chords',
976ae3ea 1314 'availability': 'public',
1315 'tags': 'count:14',
1316 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1317 'view_count': int,
1318 'live_status': 'not_live',
1319 'channel': 'deadmau5',
1320 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1321 'like_count': int,
1322 'track': 'Some Chords',
1323 'artist': 'deadmau5',
1324 'playable_in_embed': True,
1325 'age_limit': 0,
1326 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1327 'categories': ['Music'],
1328 'album': 'Some Chords',
6c73052c 1329 'channel_follower_count': int
8bdd16b4 1330 },
1331 'expected_warnings': [
1332 'DASH manifest missing',
1333 ]
1334 },
067aa17e 1335 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1336 {
1337 'url': 'lqQg6PlCWgI',
1338 'info_dict': {
1339 'id': 'lqQg6PlCWgI',
1340 'ext': 'mp4',
556dbe7f 1341 'duration': 6085,
90227264 1342 'upload_date': '20150827',
cbe2bd91 1343 'uploader_id': 'olympic',
ec85ded8 1344 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
12a1b225 1345 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
11f9be09 1346 'uploader': 'Olympics',
cbe2bd91 1347 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1348 'like_count': int,
1349 'release_timestamp': 1343767800,
1350 'playable_in_embed': True,
1351 'categories': ['Sports'],
1352 'release_date': '20120731',
1353 'channel': 'Olympics',
1354 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1355 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1356 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1357 'age_limit': 0,
1358 'availability': 'public',
1359 'live_status': 'was_live',
1360 'view_count': int,
1361 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1362 'channel_follower_count': int
cbe2bd91
PH
1363 },
1364 'params': {
1365 'skip_download': 'requires avconv',
e52a40ab 1366 }
cbe2bd91 1367 },
6271f1ca
PH
1368 # Non-square pixels
1369 {
1370 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1371 'info_dict': {
1372 'id': '_b-2C3KPAM0',
1373 'ext': 'mp4',
1374 'stretched_ratio': 16 / 9.,
556dbe7f 1375 'duration': 85,
6271f1ca
PH
1376 'upload_date': '20110310',
1377 'uploader_id': 'AllenMeow',
ec85ded8 1378 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1379 '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 1380 'uploader': '孫ᄋᄅ',
6271f1ca 1381 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1382 'playable_in_embed': True,
1383 'channel': '孫ᄋᄅ',
1384 'age_limit': 0,
1385 'tags': 'count:11',
1386 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1387 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1388 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1389 'view_count': int,
1390 'categories': ['People & Blogs'],
1391 'like_count': int,
1392 'live_status': 'not_live',
1393 'availability': 'unlisted',
12a1b225 1394 'comment_count': int,
6c73052c 1395 'channel_follower_count': int
6271f1ca 1396 },
06b491eb
S
1397 },
1398 # url_encoded_fmt_stream_map is empty string
1399 {
1400 'url': 'qEJwOuvDf7I',
1401 'info_dict': {
1402 'id': 'qEJwOuvDf7I',
f57b7835 1403 'ext': 'webm',
06b491eb
S
1404 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1405 'description': '',
1406 'upload_date': '20150404',
1407 'uploader_id': 'spbelect',
1408 'uploader': 'Наблюдатели Петербурга',
1409 },
1410 'params': {
1411 'skip_download': 'requires avconv',
e323cf3f
S
1412 },
1413 'skip': 'This live event has ended.',
06b491eb 1414 },
067aa17e 1415 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1416 {
1417 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1418 'info_dict': {
1419 'id': 'FIl7x6_3R5Y',
eb6793ba 1420 'ext': 'webm',
da77d856
S
1421 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1422 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1423 'duration': 220,
da77d856
S
1424 'upload_date': '20150625',
1425 'uploader_id': 'dorappi2000',
ec85ded8 1426 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1427 'uploader': 'dorappi2000',
eb6793ba 1428 'formats': 'mincount:31',
da77d856 1429 },
eb6793ba 1430 'skip': 'not actual anymore',
2ee8f5d8 1431 },
8a1a26ce
YCH
1432 # DASH manifest with segment_list
1433 {
1434 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1435 'md5': '8ce563a1d667b599d21064e982ab9e31',
1436 'info_dict': {
1437 'id': 'CsmdDsKjzN8',
1438 'ext': 'mp4',
17ee98e1 1439 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1440 'uploader': 'Airtek',
1441 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1442 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1443 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1444 },
1445 'params': {
1446 'youtube_include_dash_manifest': True,
1447 'format': '135', # bestvideo
be49068d
S
1448 },
1449 'skip': 'This live event has ended.',
2ee8f5d8 1450 },
cf7e015f
S
1451 {
1452 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1453 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1454 'info_dict': {
545cc85d 1455 'id': 'jvGDaLqkpTg',
1456 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1457 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1458 },
1459 'playlist': [{
1460 'info_dict': {
545cc85d 1461 'id': 'jvGDaLqkpTg',
cf7e015f 1462 'ext': 'mp4',
545cc85d 1463 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1464 'description': 'md5:e03b909557865076822aa169218d6a5d',
1465 'duration': 10643,
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 'info_dict': {
545cc85d 1473 'id': '3AKt1R1aDnw',
cf7e015f 1474 'ext': 'mp4',
545cc85d 1475 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1476 'description': 'md5:e03b909557865076822aa169218d6a5d',
1477 'duration': 10991,
1478 'upload_date': '20161111',
1479 'uploader': 'Team PGP',
1480 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1481 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1482 },
1483 }, {
1484 'info_dict': {
545cc85d 1485 'id': 'RtAMM00gpVc',
cf7e015f 1486 'ext': 'mp4',
545cc85d 1487 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1488 'description': 'md5:e03b909557865076822aa169218d6a5d',
1489 'duration': 10995,
1490 'upload_date': '20161111',
1491 'uploader': 'Team PGP',
1492 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1493 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1494 },
1495 }, {
1496 'info_dict': {
545cc85d 1497 'id': '6N2fdlP3C5U',
cf7e015f 1498 'ext': 'mp4',
545cc85d 1499 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1500 'description': 'md5:e03b909557865076822aa169218d6a5d',
1501 'duration': 10990,
1502 'upload_date': '20161111',
1503 'uploader': 'Team PGP',
1504 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1505 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1506 },
1507 }],
1508 'params': {
1509 'skip_download': True,
1510 },
65c2fde2 1511 'skip': 'Not multifeed anymore',
cbaed4bb 1512 },
f9f49d87 1513 {
067aa17e 1514 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1515 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1516 'info_dict': {
1517 'id': 'gVfLd0zydlo',
1518 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1519 },
1520 'playlist_count': 2,
be49068d 1521 'skip': 'Not multifeed anymore',
f9f49d87 1522 },
cbaed4bb 1523 {
2d3d2997 1524 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1525 'only_matching': True,
0e49d9a6 1526 },
6d4fc66b 1527 {
2d3d2997 1528 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1529 'only_matching': True,
1530 },
0e49d9a6 1531 {
067aa17e 1532 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1533 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1534 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1535 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1536 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1537 'info_dict': {
1538 'id': 'lsguqyKfVQg',
1539 'ext': 'mp4',
1540 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1541 'alt_title': 'Dark Walk',
0e49d9a6 1542 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1543 'duration': 133,
0e49d9a6
LL
1544 'upload_date': '20151119',
1545 'uploader_id': 'IronSoulElf',
ec85ded8 1546 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1547 'uploader': 'IronSoulElf',
11f9be09 1548 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1549 'track': 'Dark Walk',
1550 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1551 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1552 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1553 'categories': ['Film & Animation'],
1554 'view_count': int,
1555 'live_status': 'not_live',
1556 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1557 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1558 'tags': 'count:13',
1559 'availability': 'public',
1560 'channel': 'IronSoulElf',
1561 'playable_in_embed': True,
1562 'like_count': int,
1563 'age_limit': 0,
6c73052c 1564 'channel_follower_count': int
0e49d9a6
LL
1565 },
1566 'params': {
1567 'skip_download': True,
1568 },
1569 },
61f92af1 1570 {
067aa17e 1571 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1572 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1573 'only_matching': True,
1574 },
313dfc45
LL
1575 {
1576 # Video with yt:stretch=17:0
1577 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1578 'info_dict': {
1579 'id': 'Q39EVAstoRM',
1580 'ext': 'mp4',
1581 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1582 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1583 'upload_date': '20151107',
1584 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1585 'uploader': 'CH GAMER DROID',
1586 },
1587 'params': {
1588 'skip_download': True,
1589 },
be49068d 1590 'skip': 'This video does not exist.',
313dfc45 1591 },
201c1459 1592 {
1593 # Video with incomplete 'yt:stretch=16:'
1594 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1595 'only_matching': True,
1596 },
7caf9830
S
1597 {
1598 # Video licensed under Creative Commons
1599 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1600 'info_dict': {
1601 'id': 'M4gD1WSo5mA',
1602 'ext': 'mp4',
1603 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1604 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1605 'duration': 721,
17322130 1606 'upload_date': '20150128',
7caf9830 1607 'uploader_id': 'BerkmanCenter',
ec85ded8 1608 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1609 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1610 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1611 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1612 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1613 'like_count': int,
1614 'age_limit': 0,
1615 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1616 'channel': 'The Berkman Klein Center for Internet & Society',
1617 'availability': 'public',
1618 'view_count': int,
1619 'categories': ['Education'],
1620 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1621 'live_status': 'not_live',
1622 'playable_in_embed': True,
12a1b225 1623 'comment_count': int,
6c73052c 1624 'channel_follower_count': int
7caf9830
S
1625 },
1626 'params': {
1627 'skip_download': True,
1628 },
1629 },
fd050249
S
1630 {
1631 # Channel-like uploader_url
1632 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1633 'info_dict': {
1634 'id': 'eQcmzGIKrzg',
1635 'ext': 'mp4',
1636 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1637 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1638 'duration': 4060,
17322130 1639 'upload_date': '20151120',
eb6793ba 1640 'uploader': 'Bernie Sanders',
fd050249 1641 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1642 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1643 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1644 'playable_in_embed': True,
1645 'tags': 'count:12',
1646 'like_count': int,
1647 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1648 'age_limit': 0,
1649 'availability': 'public',
1650 'categories': ['News & Politics'],
1651 'channel': 'Bernie Sanders',
1652 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1653 'view_count': int,
1654 'live_status': 'not_live',
1655 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1656 'comment_count': int,
6c73052c 1657 'channel_follower_count': int
fd050249
S
1658 },
1659 'params': {
1660 'skip_download': True,
1661 },
1662 },
040ac686
S
1663 {
1664 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1665 'only_matching': True,
7f29cf54
S
1666 },
1667 {
067aa17e 1668 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1669 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1670 'only_matching': True,
6496ccb4
S
1671 },
1672 {
1673 # Rental video preview
1674 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1675 'info_dict': {
1676 'id': 'uGpuVWrhIzE',
1677 'ext': 'mp4',
1678 'title': 'Piku - Trailer',
1679 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1680 'upload_date': '20150811',
1681 'uploader': 'FlixMatrix',
1682 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1683 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1684 'license': 'Standard YouTube License',
1685 },
1686 'params': {
1687 'skip_download': True,
1688 },
eb6793ba 1689 'skip': 'This video is not available.',
022a5d66 1690 },
12afdc2a
S
1691 {
1692 # YouTube Red video with episode data
1693 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1694 'info_dict': {
1695 'id': 'iqKdEhx-dD4',
1696 'ext': 'mp4',
1697 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1698 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1699 'duration': 2085,
12afdc2a
S
1700 'upload_date': '20170118',
1701 'uploader': 'Vsauce',
1702 'uploader_id': 'Vsauce',
1703 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1704 'series': 'Mind Field',
1705 'season_number': 1,
1706 'episode_number': 1,
976ae3ea 1707 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1708 'tags': 'count:12',
1709 'view_count': int,
1710 'availability': 'public',
1711 'age_limit': 0,
1712 'channel': 'Vsauce',
1713 'episode': 'Episode 1',
1714 'categories': ['Entertainment'],
1715 'season': 'Season 1',
1716 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1717 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1718 'like_count': int,
1719 'playable_in_embed': True,
1720 'live_status': 'not_live',
6c73052c 1721 'channel_follower_count': int
12afdc2a
S
1722 },
1723 'params': {
1724 'skip_download': True,
1725 },
1726 'expected_warnings': [
1727 'Skipping DASH manifest',
1728 ],
1729 },
c7121fa7
S
1730 {
1731 # The following content has been identified by the YouTube community
1732 # as inappropriate or offensive to some audiences.
1733 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1734 'info_dict': {
1735 'id': '6SJNVb0GnPI',
1736 'ext': 'mp4',
1737 'title': 'Race Differences in Intelligence',
1738 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1739 'duration': 965,
1740 'upload_date': '20140124',
1741 'uploader': 'New Century Foundation',
1742 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1743 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1744 },
1745 'params': {
1746 'skip_download': True,
1747 },
545cc85d 1748 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1749 },
022a5d66
S
1750 {
1751 # itag 212
1752 'url': '1t24XAntNCY',
1753 'only_matching': True,
fd5c4aab
S
1754 },
1755 {
1756 # geo restricted to JP
1757 'url': 'sJL6WA-aGkQ',
1758 'only_matching': True,
1759 },
cd5a74a2
S
1760 {
1761 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1762 'only_matching': True,
1763 },
bc2ca1bb 1764 {
1765 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1766 'only_matching': True,
1767 },
1768 {
1769 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1770 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1771 'only_matching': True,
1772 },
825cd268
RA
1773 {
1774 # DRM protected
1775 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1776 'only_matching': True,
4fe54c12
S
1777 },
1778 {
1779 # Video with unsupported adaptive stream type formats
1780 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1781 'info_dict': {
1782 'id': 'Z4Vy8R84T1U',
1783 'ext': 'mp4',
1784 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1785 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1786 'duration': 433,
1787 'upload_date': '20130923',
1788 'uploader': 'Amelia Putri Harwita',
1789 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1790 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1791 'formats': 'maxcount:10',
1792 },
1793 'params': {
1794 'skip_download': True,
1795 'youtube_include_dash_manifest': False,
1796 },
5429d6a9 1797 'skip': 'not actual anymore',
5caabd3c 1798 },
1799 {
822b9d9c 1800 # Youtube Music Auto-generated description
5caabd3c 1801 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1802 'info_dict': {
1803 'id': 'MgNrAu2pzNs',
1804 'ext': 'mp4',
1805 'title': 'Voyeur Girl',
1806 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1807 'upload_date': '20190312',
5429d6a9
S
1808 'uploader': 'Stephen - Topic',
1809 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1810 'artist': 'Stephen',
1811 'track': 'Voyeur Girl',
1812 'album': 'it\'s too much love to know my dear',
1813 'release_date': '20190313',
1814 'release_year': 2019,
976ae3ea 1815 'alt_title': 'Voyeur Girl',
1816 'view_count': int,
1817 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1818 'playable_in_embed': True,
1819 'like_count': int,
1820 'categories': ['Music'],
1821 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1822 'channel': 'Stephen',
1823 'availability': 'public',
1824 'creator': 'Stephen',
1825 'duration': 169,
1826 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1827 'age_limit': 0,
1828 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1829 'tags': 'count:11',
1830 'live_status': 'not_live',
6c73052c 1831 'channel_follower_count': int
5caabd3c 1832 },
1833 'params': {
1834 'skip_download': True,
1835 },
1836 },
66b48727
RA
1837 {
1838 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1839 'only_matching': True,
1840 },
011e75e6
S
1841 {
1842 # invalid -> valid video id redirection
1843 'url': 'DJztXj2GPfl',
1844 'info_dict': {
1845 'id': 'DJztXj2GPfk',
1846 'ext': 'mp4',
1847 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1848 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1849 'upload_date': '20090125',
1850 'uploader': 'Prochorowka',
1851 'uploader_id': 'Prochorowka',
1852 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1853 'artist': 'Panjabi MC',
1854 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1855 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1856 },
1857 'params': {
1858 'skip_download': True,
1859 },
545cc85d 1860 'skip': 'Video unavailable',
ea74e00b
DP
1861 },
1862 {
1863 # empty description results in an empty string
1864 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1865 'info_dict': {
1866 'id': 'x41yOUIvK2k',
1867 'ext': 'mp4',
1868 'title': 'IMG 3456',
1869 'description': '',
1870 'upload_date': '20170613',
1871 'uploader_id': 'ElevageOrVert',
1872 'uploader': 'ElevageOrVert',
976ae3ea 1873 'view_count': int,
1874 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1875 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1876 'like_count': int,
1877 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1878 'tags': [],
1879 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1880 'availability': 'public',
1881 'age_limit': 0,
1882 'categories': ['Pets & Animals'],
1883 'duration': 7,
1884 'playable_in_embed': True,
1885 'live_status': 'not_live',
1886 'channel': 'ElevageOrVert',
6c73052c 1887 'channel_follower_count': int
ea74e00b
DP
1888 },
1889 'params': {
1890 'skip_download': True,
1891 },
1892 },
a0566bbf 1893 {
29f7c58a 1894 # with '};' inside yt initial data (see [1])
1895 # see [2] for an example with '};' inside ytInitialPlayerResponse
1896 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1897 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1898 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1899 'info_dict': {
1900 'id': 'CHqg6qOn4no',
1901 'ext': 'mp4',
1902 'title': 'Part 77 Sort a list of simple types in c#',
1903 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1904 'upload_date': '20130831',
1905 'uploader_id': 'kudvenkat',
1906 'uploader': 'kudvenkat',
976ae3ea 1907 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1908 'like_count': int,
1909 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1910 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1911 'live_status': 'not_live',
1912 'categories': ['Education'],
1913 'availability': 'public',
1914 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1915 'tags': 'count:12',
1916 'playable_in_embed': True,
1917 'age_limit': 0,
1918 'view_count': int,
1919 'duration': 522,
1920 'channel': 'kudvenkat',
12a1b225 1921 'comment_count': int,
6c73052c 1922 'channel_follower_count': int
a0566bbf 1923 },
1924 'params': {
1925 'skip_download': True,
1926 },
1927 },
29f7c58a 1928 {
1929 # another example of '};' in ytInitialData
1930 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1931 'only_matching': True,
1932 },
1933 {
1934 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1935 'only_matching': True,
1936 },
545cc85d 1937 {
cc2db878 1938 # https://github.com/ytdl-org/youtube-dl/pull/28094
1939 'url': 'OtqTfy26tG0',
1940 'info_dict': {
1941 'id': 'OtqTfy26tG0',
1942 'ext': 'mp4',
1943 'title': 'Burn Out',
1944 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1945 'upload_date': '20141120',
1946 'uploader': 'The Cinematic Orchestra - Topic',
1947 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1948 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1949 'artist': 'The Cinematic Orchestra',
1950 'track': 'Burn Out',
1951 'album': 'Every Day',
976ae3ea 1952 'like_count': int,
1953 'live_status': 'not_live',
1954 'alt_title': 'Burn Out',
1955 'duration': 614,
1956 'age_limit': 0,
1957 'view_count': int,
1958 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1959 'creator': 'The Cinematic Orchestra',
1960 'channel': 'The Cinematic Orchestra',
1961 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1962 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1963 'availability': 'public',
1964 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1965 'categories': ['Music'],
1966 'playable_in_embed': True,
6c73052c 1967 'channel_follower_count': int
cc2db878 1968 },
1969 'params': {
1970 'skip_download': True,
1971 },
545cc85d 1972 },
bc2ca1bb 1973 {
1974 # controversial video, only works with bpctr when authenticated with cookies
1975 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1976 'only_matching': True,
1977 },
a1a7907b 1978 {
1979 # controversial video, requires bpctr/contentCheckOk
1980 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1981 'info_dict': {
1982 'id': 'SZJvDhaSDnc',
1983 'ext': 'mp4',
1984 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1985 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1986 'uploader': 'CBS Mornings',
11f9be09 1987 'uploader_id': 'CBSThisMorning',
a1a7907b 1988 'upload_date': '20140716',
976ae3ea 1989 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1990 'duration': 170,
1991 'categories': ['News & Politics'],
1992 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1993 'view_count': int,
1994 'channel': 'CBS Mornings',
1995 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1996 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1997 'age_limit': 18,
1998 'availability': 'needs_auth',
1999 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2000 'like_count': int,
2001 'live_status': 'not_live',
2002 'playable_in_embed': True,
6c73052c 2003 'channel_follower_count': int
a1a7907b 2004 }
2005 },
f7ad7160 2006 {
2007 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2008 'url': 'cBvYw8_A0vQ',
2009 'info_dict': {
2010 'id': 'cBvYw8_A0vQ',
2011 'ext': 'mp4',
2012 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2013 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2014 'upload_date': '20201120',
2015 'uploader': 'Walk around Japan',
2016 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2017 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2018 'duration': 1456,
2019 'categories': ['Travel & Events'],
2020 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2021 'view_count': int,
2022 'channel': 'Walk around Japan',
2023 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2024 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2025 'age_limit': 0,
2026 'availability': 'public',
2027 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2028 'live_status': 'not_live',
2029 'playable_in_embed': True,
6c73052c 2030 'channel_follower_count': int
f7ad7160 2031 },
2032 'params': {
2033 'skip_download': True,
2034 },
0fb983f6 2035 }, {
2036 # Has multiple audio streams
2037 'url': 'WaOKSUlf4TM',
2038 'only_matching': True
9297939e 2039 }, {
2040 # Requires Premium: has format 141 when requested using YTM url
2041 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2042 'only_matching': True
2043 }, {
120916da 2044 # multiple subtitles with same lang_code
2045 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2046 'only_matching': True,
109dd3b2 2047 }, {
2048 # Force use android client fallback
2049 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2050 'info_dict': {
2051 'id': 'YOelRv7fMxY',
11f9be09 2052 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2053 'ext': '3gp',
2054 'upload_date': '20210624',
2055 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2056 'uploader': 'colinfurze',
11f9be09 2057 'uploader_id': 'colinfurze',
109dd3b2 2058 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2059 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2060 'duration': 596,
2061 'categories': ['Entertainment'],
2062 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2063 'view_count': int,
2064 'channel': 'colinfurze',
2065 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2066 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2067 'age_limit': 0,
2068 'availability': 'public',
2069 'like_count': int,
2070 'live_status': 'not_live',
2071 'playable_in_embed': True,
6c73052c 2072 'channel_follower_count': int
109dd3b2 2073 },
2074 'params': {
2075 'format': '17', # 3gp format available on android
2076 'extractor_args': {'youtube': {'player_client': ['android']}},
2077 },
120916da 2078 },
109dd3b2 2079 {
2080 # Skip download of additional client configs (remix client config in this case)
2081 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2082 'only_matching': True,
2083 'params': {
2084 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2085 },
8fc54b12 2086 }, {
2087 # shorts
2088 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2089 'only_matching': True,
9222c381 2090 }, {
2091 'note': 'Storyboards',
2092 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2093 'info_dict': {
2094 'id': '5KLPxDtMqe8',
2095 'ext': 'mhtml',
2096 'format_id': 'sb0',
2097 'title': 'Your Brain is Plastic',
2098 'uploader_id': 'scishow',
2099 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2100 'upload_date': '20140324',
2101 'uploader': 'SciShow',
976ae3ea 2102 'like_count': int,
2103 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2104 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2105 'view_count': int,
2106 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2107 'playable_in_embed': True,
2108 'tags': 'count:12',
2109 'uploader_url': 'http://www.youtube.com/user/scishow',
2110 'availability': 'public',
2111 'channel': 'SciShow',
2112 'live_status': 'not_live',
2113 'duration': 248,
2114 'categories': ['Education'],
2115 'age_limit': 0,
6c73052c 2116 'channel_follower_count': int
9222c381 2117 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2118 }, {
2119 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2120 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2121 'info_dict': {
2122 'id': '2NUZ8W2llS4',
2123 'ext': 'mp4',
2124 'title': 'The NP that test your phone performance 🙂',
2125 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2126 'uploader': 'Leon Nguyen',
2127 'uploader_id': 'VNSXIII',
2128 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2129 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2130 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2131 'duration': 21,
2132 'view_count': int,
2133 'age_limit': 0,
2134 'categories': ['Gaming'],
2135 'tags': 'count:23',
2136 'playable_in_embed': True,
2137 'live_status': 'not_live',
2138 'upload_date': '20220103',
2139 'like_count': int,
2140 'availability': 'public',
2141 'channel': 'Leon Nguyen',
2142 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2143 'comment_count': int,
992f9a73 2144 'channel_follower_count': int
2145 }
2146 }, {
2147 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2148 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2149 'info_dict': {
2150 'id': 'mzZzzBU6lrM',
2151 'ext': 'mp4',
2152 'title': 'I Met GeorgeNotFound In Real Life...',
2153 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2154 'uploader': 'Quackity',
2155 'uploader_id': 'QuackityHQ',
2156 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2157 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2158 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2159 'duration': 955,
2160 'view_count': int,
2161 'age_limit': 0,
2162 'categories': ['Entertainment'],
2163 'tags': 'count:26',
2164 'playable_in_embed': True,
2165 'live_status': 'not_live',
2166 'release_timestamp': 1641172509,
2167 'release_date': '20220103',
2168 'upload_date': '20220103',
2169 'like_count': int,
2170 'availability': 'public',
2171 'channel': 'Quackity',
2172 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2173 'channel_follower_count': int
2174 }
2175 },
2176 { # continuous livestream. Microformat upload date should be preferred.
2177 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2178 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2179 'info_dict': {
2180 'id': 'kgx4WGK0oNU',
2181 'title': r're:jazz\/lofi hip hop radio🌱chill beats to relax\/study to \[LIVE 24\/7\] \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
2182 'ext': 'mp4',
2183 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2184 'availability': 'public',
2185 'age_limit': 0,
2186 'release_timestamp': 1637975704,
2187 'upload_date': '20210619',
2188 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2189 'live_status': 'is_live',
2190 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2191 'uploader': '阿鲍Abao',
2192 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2193 'channel': 'Abao in Tokyo',
2194 'channel_follower_count': int,
2195 'release_date': '20211127',
2196 'tags': 'count:39',
2197 'categories': ['People & Blogs'],
2198 'like_count': int,
2199 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2200 'view_count': int,
2201 'playable_in_embed': True,
2202 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2203 },
2204 'params': {'skip_download': True}
6e634cbe 2205 }, {
2206 # Story. Requires specific player params to work.
ee27297f 2207 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2208 'info_dict': {
ee27297f 2209 'id': 'vv8qTUWmulI',
6e634cbe 2210 'ext': 'mp4',
ee27297f 2211 'availability': 'unlisted',
2212 'view_count': int,
2213 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2214 'upload_date': '20220526',
2215 'categories': ['Education'],
2216 'title': 'Story',
2217 'channel': 'IT\'S HISTORY',
2218 'description': '',
2219 'uploader_id': 'BlastfromthePast',
2220 'duration': 12,
2221 'uploader': 'IT\'S HISTORY',
6e634cbe 2222 'playable_in_embed': True,
6e634cbe 2223 'age_limit': 0,
6e634cbe 2224 'live_status': 'not_live',
ee27297f 2225 'tags': [],
2226 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2227 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2228 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
12a1b225
A
2229 },
2230 'skip': 'stories get removed after some period of time',
ee27297f 2231 }, {
2232 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2233 'info_dict': {
2234 'id': 'tjjjtzRLHvA',
2235 'ext': 'mp4',
2236 'title': 'ハッシュタグ無し };if window.ytcsi',
2237 'upload_date': '20220323',
2238 'like_count': int,
2239 'availability': 'unlisted',
2240 'channel': 'nao20010128nao',
2241 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2242 'age_limit': 0,
2243 'uploader': 'nao20010128nao',
2244 'uploader_id': 'nao20010128nao',
2245 'categories': ['Music'],
6e634cbe 2246 'view_count': int,
2247 'description': '',
ee27297f 2248 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2249 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2250 'live_status': 'not_live',
2251 'playable_in_embed': True,
2252 'channel_follower_count': int,
2253 'duration': 6,
2254 'tags': [],
2255 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2256 }
2257 }
2eb88d95
PH
2258 ]
2259
f2e8dbcc 2260 _WEBPAGE_TESTS = [
2261 # YouTube <object> embed
2262 {
2263 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2264 'md5': '873c81d308b979f0e23ee7e620b312a3',
2265 'info_dict': {
2266 'id': 'msN87y-iEx0',
2267 'ext': 'mp4',
2268 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2269 'upload_date': '20080526',
2270 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2271 'uploader': 'Christopher Sykes',
2272 'uploader_id': 'ChristopherJSykes',
2273 'age_limit': 0,
2274 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2275 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2276 'playable_in_embed': True,
2277 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2278 'like_count': int,
2279 'comment_count': int,
2280 'channel': 'Christopher Sykes',
2281 'live_status': 'not_live',
2282 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2283 'availability': 'public',
2284 'duration': 195,
2285 'view_count': int,
2286 'categories': ['Science & Technology'],
2287 'channel_follower_count': int,
2288 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2289 },
2290 'params': {
2291 'skip_download': True,
2292 }
2293 },
2294 ]
2295
201c1459 2296 @classmethod
2297 def suitable(cls, url):
4dfbf869 2298 from ..utils import parse_qs
2299
201c1459 2300 qs = parse_qs(url)
2301 if qs.get('list', [None])[0]:
2302 return False
86e5f3ed 2303 return super().suitable(url)
201c1459 2304
e0df6211 2305 def __init__(self, *args, **kwargs):
86e5f3ed 2306 super().__init__(*args, **kwargs)
545cc85d 2307 self._code_cache = {}
83799698 2308 self._player_cache = {}
e0df6211 2309
adbc4ec4 2310 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2311 lock = threading.Lock()
2312
2313 is_live = True
185bf310 2314 start_time = time.time()
adbc4ec4
THD
2315 formats = [f for f in formats if f.get('is_from_start')]
2316
185bf310 2317 def refetch_manifest(format_id, delay):
2318 nonlocal formats, start_time, is_live
2319 if time.time() <= start_time + delay:
adbc4ec4
THD
2320 return
2321
2322 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2323 video_details = traverse_obj(
2324 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2325 microformats = traverse_obj(
2326 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2327 expected_type=dict, default=[])
c646d76f 2328 _, is_live, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2329 start_time = time.time()
adbc4ec4 2330
185bf310 2331 def mpd_feed(format_id, delay):
adbc4ec4
THD
2332 """
2333 @returns (manifest_url, manifest_stream_number, is_live) or None
2334 """
2335 with lock:
185bf310 2336 refetch_manifest(format_id, delay)
adbc4ec4
THD
2337
2338 f = next((f for f in formats if f['format_id'] == format_id), None)
2339 if not f:
185bf310 2340 if not is_live:
2341 self.to_screen(f'{video_id}: Video is no longer live')
2342 else:
2343 self.report_warning(
2344 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2345 return None
2346 return f['manifest_url'], f['manifest_stream_number'], is_live
2347
2348 for f in formats:
a539f065 2349 f['is_live'] = True
adbc4ec4
THD
2350 f['protocol'] = 'http_dash_segments_generator'
2351 f['fragments'] = functools.partial(
2352 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2353
2354 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2355 FETCH_SPAN, MAX_DURATION = 5, 432000
2356
2357 mpd_url, stream_number, is_live = None, None, True
2358
2359 begin_index = 0
2360 download_start_time = ctx.get('start') or time.time()
2361
2362 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2363 if lack_early_segments:
2364 self.report_warning(bug_reports_message(
2365 'Starting download from the last 120 hours of the live stream since '
2366 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2367 lack_early_segments = True
2368
2369 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2370 fragments, fragment_base_url = None, None
2371
a539f065 2372 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2373 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2374 # Obtain from MPD's maximum seq value
2375 old_mpd_url = mpd_url
185bf310 2376 last_error = ctx.pop('last_error', None)
14f25df2 2377 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2378 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2379 or (mpd_url, stream_number, False))
2380 if not refresh_sequence:
2381 if expire_fast and not is_live:
2382 return False, last_seq
2383 elif old_mpd_url == mpd_url:
2384 return True, last_seq
adbc4ec4
THD
2385 try:
2386 fmts, _ = self._extract_mpd_formats_and_subtitles(
2387 mpd_url, None, note=False, errnote=False, fatal=False)
2388 except ExtractorError:
2389 fmts = None
2390 if not fmts:
a539f065 2391 no_fragment_score += 2
adbc4ec4
THD
2392 return False, last_seq
2393 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2394 fragments = fmt_info['fragments']
2395 fragment_base_url = fmt_info['fragment_base_url']
2396 assert fragment_base_url
2397
2398 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2399 return True, _last_seq
2400
2401 while is_live:
2402 fetch_time = time.time()
2403 if no_fragment_score > 30:
2404 return
2405 if last_segment_url:
2406 # Obtain from "X-Head-Seqnum" header value from each segment
2407 try:
2408 urlh = self._request_webpage(
2409 last_segment_url, None, note=False, errnote=False, fatal=False)
2410 except ExtractorError:
2411 urlh = None
2412 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2413 if last_seq is None:
a539f065 2414 no_fragment_score += 2
adbc4ec4
THD
2415 last_segment_url = None
2416 continue
2417 else:
a539f065
LNO
2418 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2419 no_fragment_score += 2
185bf310 2420 if not should_continue:
adbc4ec4
THD
2421 continue
2422
2423 if known_idx > last_seq:
2424 last_segment_url = None
2425 continue
2426
2427 last_seq += 1
2428
2429 if begin_index < 0 and known_idx < 0:
2430 # skip from the start when it's negative value
2431 known_idx = last_seq + begin_index
2432 if lack_early_segments:
2433 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2434 try:
2435 for idx in range(known_idx, last_seq):
2436 # do not update sequence here or you'll get skipped some part of it
a539f065 2437 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2438 if not should_continue:
adbc4ec4
THD
2439 known_idx = idx - 1
2440 raise ExtractorError('breaking out of outer loop')
2441 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2442 yield {
2443 'url': last_segment_url,
36195c44 2444 'fragment_count': last_seq,
adbc4ec4
THD
2445 }
2446 if known_idx == last_seq:
2447 no_fragment_score += 5
2448 else:
2449 no_fragment_score = 0
2450 known_idx = last_seq
2451 except ExtractorError:
2452 continue
2453
2454 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2455
b6de707d 2456 def _extract_player_url(self, *ytcfgs, webpage=None):
2457 player_url = traverse_obj(
2458 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2459 get_all=False, expected_type=str)
11f9be09 2460 if not player_url:
b6de707d 2461 return
60f393e4 2462 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2463
b6de707d 2464 def _download_player_url(self, video_id, fatal=False):
2465 res = self._download_webpage(
2466 'https://www.youtube.com/iframe_api',
2467 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2468 if res:
2469 player_version = self._search_regex(
2470 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2471 if player_version:
2472 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2473
60064c53
PH
2474 def _signature_cache_id(self, example_sig):
2475 """ Return a string representation of a signature """
14f25df2 2476 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2477
e40c758c
S
2478 @classmethod
2479 def _extract_player_info(cls, player_url):
2480 for player_re in cls._PLAYER_INFO_RE:
2481 id_m = re.search(player_re, player_url)
2482 if id_m:
2483 break
2484 else:
c081b35c 2485 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2486 return id_m.group('id')
e40c758c 2487
404f611f 2488 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2489 player_id = self._extract_player_info(player_url)
2490 if player_id not in self._code_cache:
1276a43a 2491 code = self._download_webpage(
109dd3b2 2492 player_url, video_id, fatal=fatal,
2493 note='Downloading player ' + player_id,
2494 errnote='Download of %s failed' % player_url)
1276a43a 2495 if code:
2496 self._code_cache[player_id] = code
404f611f 2497 return self._code_cache.get(player_id)
109dd3b2 2498
e40c758c 2499 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2500 player_id = self._extract_player_info(player_url)
e0df6211 2501
c4417ddb 2502 # Read from filesystem cache
86e5f3ed 2503 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2504 assert os.path.basename(func_id) == func_id
a0e07d31 2505
ae61d108 2506 self.write_debug(f'Extracting signature function {func_id}')
9809740b 2507 cache_spec = self.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2508 if cache_spec is not None:
78caa52a 2509 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2510
404f611f 2511 code = self._load_player(video_id, player_url)
2512 if code:
109dd3b2 2513 res = self._parse_sig_js(code)
e0df6211 2514
ac668111 2515 test_string = ''.join(map(chr, range(len(example_sig))))
109dd3b2 2516 cache_res = res(test_string)
2517 cache_spec = [ord(c) for c in cache_res]
83799698 2518
9809740b 2519 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
109dd3b2 2520 return res
83799698 2521
60064c53 2522 def _print_sig_code(self, func, example_sig):
404f611f 2523 if not self.get_param('youtube_print_sig_code'):
2524 return
2525
edf3e38e
PH
2526 def gen_sig_code(idxs):
2527 def _genslice(start, end, step):
78caa52a 2528 starts = '' if start == 0 else str(start)
8bcc8756 2529 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2530 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2531 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2532
2533 step = None
7af808a5
PH
2534 # Quelch pyflakes warnings - start will be set when step is set
2535 start = '(Never used)'
edf3e38e
PH
2536 for i, prev in zip(idxs[1:], idxs[:-1]):
2537 if step is not None:
2538 if i - prev == step:
2539 continue
2540 yield _genslice(start, prev, step)
2541 step = None
2542 continue
2543 if i - prev in [-1, 1]:
2544 step = i - prev
2545 start = prev
2546 continue
2547 else:
78caa52a 2548 yield 's[%d]' % prev
edf3e38e 2549 if step is None:
78caa52a 2550 yield 's[%d]' % i
edf3e38e
PH
2551 else:
2552 yield _genslice(start, i, step)
2553
ac668111 2554 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2555 cache_res = func(test_string)
edf3e38e 2556 cache_spec = [ord(c) for c in cache_res]
78caa52a 2557 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2558 signature_id_tuple = '(%s)' % (
14f25df2 2559 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2560 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2561 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2562 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2563
e0df6211
PH
2564 def _parse_sig_js(self, jscode):
2565 funcname = self._search_regex(
abefc03f
S
2566 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2567 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
2568 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2569 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2570 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}\(a,\d+\)',
2571 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 2572 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2573 # Obsolete patterns
2574 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2575 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2576 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2577 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2578 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2579 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2580 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2581 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2582 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2583
2584 jsi = JSInterpreter(jscode)
2585 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2586 return lambda s: initial_function([s])
2587
545cc85d 2588 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2589 """Turn the encrypted s field into a working signature"""
c8bf86d5 2590 try:
62af3a0e 2591 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5 2592 if player_id not in self._player_cache:
52023f12 2593 func = self._extract_signature_function(video_id, player_url, s)
c8bf86d5
PH
2594 self._player_cache[player_id] = func
2595 func = self._player_cache[player_id]
404f611f 2596 self._print_sig_code(func, s)
c8bf86d5
PH
2597 return func(s)
2598 except Exception as e:
52023f12 2599 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2600
2601 def _decrypt_nsig(self, s, video_id, player_url):
2602 """Turn the encrypted n field into a working signature"""
2603 if player_url is None:
2604 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2605 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2606
2607 sig_id = ('nsig_value', s)
2608 if sig_id in self._player_cache:
2609 return self._player_cache[sig_id]
2610
2611 try:
2612 player_id = ('nsig', player_url)
2613 if player_id not in self._player_cache:
2614 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2615 func = self._player_cache[player_id]
2616 self._player_cache[sig_id] = func(s)
2617 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2618 return self._player_cache[sig_id]
2619 except Exception as e:
aa9369a2 2620 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2621
2622 def _extract_n_function_name(self, jscode):
48416bc4 2623 nfunc, idx = self._search_regex(
c571b3a6 2624 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2625 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2626 if not idx:
2627 return nfunc
2628 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2629 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2630 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2631
2632 def _extract_n_function(self, video_id, player_url):
2633 player_id = self._extract_player_info(player_url)
9809740b 2634 func_code = self.cache.load('youtube-nsig', player_id)
404f611f 2635
2636 if func_code:
2637 jsi = JSInterpreter(func_code)
2638 else:
2639 jscode = self._load_player(video_id, player_url)
2640 funcname = self._extract_n_function_name(jscode)
2641 jsi = JSInterpreter(jscode)
2642 func_code = jsi.extract_function_code(funcname)
9809740b 2643 self.cache.store('youtube-nsig', player_id, func_code)
404f611f 2644
2645 if self.get_param('youtube_print_sig_code'):
2646 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2647
2648 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2649
109dd3b2 2650 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2651 """
2652 Extract signatureTimestamp (sts)
2653 Required to tell API what sig/player version is in use.
2654 """
2655 sts = None
2656 if isinstance(ytcfg, dict):
2657 sts = int_or_none(ytcfg.get('STS'))
2658
2659 if not sts:
2660 # Attempt to extract from player
2661 if player_url is None:
2662 error_msg = 'Cannot extract signature timestamp without player_url.'
2663 if fatal:
2664 raise ExtractorError(error_msg)
2665 self.report_warning(error_msg)
2666 return
404f611f 2667 code = self._load_player(video_id, player_url, fatal=fatal)
2668 if code:
109dd3b2 2669 sts = int_or_none(self._search_regex(
2670 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2671 'JS player signature timestamp', group='sts', fatal=fatal))
2672 return sts
2673
11f9be09 2674 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
2675 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2676 label = 'fully ' if is_full else ''
2677 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2678 expected_type=url_or_none)
2679 if not url:
2680 self.report_warning(f'Unable to mark {label}watched')
2681 return
14f25df2 2682 parsed_url = urllib.parse.urlparse(url)
2683 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
2684
2685 # cpn generation algorithm is reverse engineered from base.js.
2686 # In fact it works even with dummy cpn.
2687 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2688 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2689
2690 # # more consistent results setting it to right before the end
2691 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2692
2693 qs.update({
2694 'ver': ['2'],
2695 'cpn': [cpn],
2696 'cmt': video_length,
2697 'el': 'detailpage', # otherwise defaults to "shorts"
2698 })
2699
2700 if is_full:
2701 # these seem to mark watchtime "history" in the real world
2702 # they're required, so send in a single value
2703 qs.update({
2704 'st': video_length,
2705 'et': video_length,
2706 })
2707
14f25df2 2708 url = urllib.parse.urlunparse(
2709 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
2710
2711 self._download_webpage(
2712 url, video_id, f'Marking {label}watched',
2713 'Unable to mark watched', fatal=False)
d77ab8e2 2714
bfd973ec 2715 @classmethod
2716 def _extract_from_webpage(cls, url, webpage):
2717 # Invidious Instances
2718 # https://github.com/yt-dlp/yt-dlp/issues/195
2719 # https://github.com/iv-org/invidious/pull/1730
2720 mobj = re.search(
2721 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2722 webpage)
2723 if mobj:
2724 yield cls.url_result(mobj.group('url'), cls)
2725 raise cls.StopExtraction()
2726
2727 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
2728
2729 # lazyYT YouTube embed
bfd973ec 2730 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
2731 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
2732
2733 # Wordpress "YouTube Video Importer" plugin
bfd973ec 2734 for m in re.findall(r'''(?x)<div[^>]+
2735 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2736 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
2737 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 2738
97665381
PH
2739 @classmethod
2740 def extract_id(cls, url):
ae61d108 2741 video_id = cls.get_temp_id(url)
2742 if not video_id:
2743 raise ExtractorError(f'Invalid URL: {url}')
2744 return video_id
c5e8d7af 2745
7c365c21 2746 def _extract_chapters_from_json(self, data, duration):
2747 chapter_list = traverse_obj(
2748 data, (
2749 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2750 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2751 ), expected_type=list)
2752
2753 return self._extract_chapters(
2754 chapter_list,
2755 chapter_time=lambda chapter: float_or_none(
2756 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2757 chapter_title=lambda chapter: traverse_obj(
2758 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2759 duration=duration)
2760
2761 def _extract_chapters_from_engagement_panel(self, data, duration):
2762 content_list = traverse_obj(
8bdd16b4 2763 data,
7c365c21 2764 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2765 expected_type=list, default=[])
052e1350 2766 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2767 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2768
1890fc63 2769 return next(filter(None, (
2770 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2771 chapter_time, chapter_title, duration)
2772 for contents in content_list)), [])
7c365c21 2773
1890fc63 2774 def _extract_chapters_from_description(self, description, duration):
2775 return self._extract_chapters(
2776 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2777 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2778 duration=duration, strict=False)
84213ea8 2779
1890fc63 2780 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2781 if not duration:
2782 return
2783 chapter_list = [{
2784 'start_time': chapter_time(chapter),
2785 'title': chapter_title(chapter),
2786 } for chapter in chapter_list or []]
2787 if not strict:
2788 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2789
a3976e07 2790 chapters = [{'start_time': 0}]
1890fc63 2791 for idx, chapter in enumerate(chapter_list):
a3976e07 2792 if chapter['start_time'] is None:
1890fc63 2793 self.report_warning(f'Incomplete chapter {idx}')
2794 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
1890fc63 2795 chapters.append(chapter)
2796 else:
2797 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}"')
a3976e07 2798 return chapters[1:]
84213ea8 2799
a1c5d2ca
M
2800 def _extract_comment(self, comment_renderer, parent=None):
2801 comment_id = comment_renderer.get('commentId')
2802 if not comment_id:
2803 return
fe93e2c4 2804
052e1350 2805 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2806
49bd8c66 2807 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2808 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2809 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca 2810 author_id = try_get(comment_renderer,
14f25df2 2811 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
fe93e2c4 2812
49bd8c66 2813 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
14f25df2 2814 lambda x: x['likeCount']), str)) or 0
a1c5d2ca 2815 author_thumbnail = try_get(comment_renderer,
14f25df2 2816 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
a1c5d2ca
M
2817
2818 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2819 is_favorited = 'creatorHeart' in (try_get(
2820 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2821 return {
2822 'id': comment_id,
2823 'text': text,
d92f5d5a 2824 'timestamp': timestamp,
a1c5d2ca
M
2825 'time_text': time_text,
2826 'like_count': votes,
97524332 2827 'is_favorited': is_favorited,
a1c5d2ca
M
2828 'author': author,
2829 'author_id': author_id,
2830 'author_thumbnail': author_thumbnail,
2831 'author_is_uploader': author_is_uploader,
2832 'parent': parent or 'root'
2833 }
2834
46383212 2835 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2836
2837 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2838
2839 def extract_header(contents):
2d6659b9 2840 _continuation = None
2841 for content in contents:
46383212 2842 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2843 expected_comment_count = self._get_count(
2844 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2845
2d6659b9 2846 if expected_comment_count:
46383212 2847 tracker['est_total'] = expected_comment_count
2848 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2849 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2850
2851 sort_menu_item = try_get(
2852 comments_header_renderer,
2853 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2854 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2855
2856 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2857 if not _continuation:
2858 continue
2859
46383212 2860 sort_text = str_or_none(sort_menu_item.get('title'))
2861 if not sort_text:
2d6659b9 2862 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2863 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2864 break
a2160aa4 2865 return _continuation
a1c5d2ca 2866
2d6659b9 2867 def extract_thread(contents):
a1c5d2ca 2868 if not parent:
46383212 2869 tracker['current_page_thread'] = 0
a1c5d2ca 2870 for content in contents:
46383212 2871 if not parent and tracker['total_parent_comments'] >= max_parents:
2872 yield
a1c5d2ca 2873 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2874 comment_renderer = get_first(
2875 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2876 expected_type=dict, default={})
a1c5d2ca 2877
a1c5d2ca
M
2878 comment = self._extract_comment(comment_renderer, parent)
2879 if not comment:
2880 continue
46383212 2881
2882 tracker['running_total'] += 1
2883 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2884 yield comment
46383212 2885
a1c5d2ca
M
2886 # Attempt to get the replies
2887 comment_replies_renderer = try_get(
2888 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2889
2890 if comment_replies_renderer:
46383212 2891 tracker['current_page_thread'] += 1
a1c5d2ca 2892 comment_entries_iter = self._comment_entries(
99e9e001 2893 comment_replies_renderer, ytcfg, video_id,
46383212 2894 parent=comment.get('id'), tracker=tracker)
86e5f3ed 2895 yield from itertools.islice(comment_entries_iter, min(
2896 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 2897
46383212 2898 # Keeps track of counts across recursive calls
2899 if not tracker:
2900 tracker = dict(
2901 running_total=0,
2902 est_total=0,
2903 current_page_thread=0,
2904 total_parent_comments=0,
2905 total_reply_comments=0)
2906
2907 # TODO: Deprecated
2d6659b9 2908 # YouTube comments have a max depth of 2
46383212 2909 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2910 if max_depth:
2911 self._downloader.deprecation_warning(
2912 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2913 if max_depth == 1 and parent:
2914 return
a1c5d2ca 2915
46383212 2916 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2917 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2918
46383212 2919 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2920
46383212 2921 response = None
6e634cbe 2922 is_forced_continuation = False
2d6659b9 2923 is_first_continuation = parent is None
6e634cbe 2924 if is_first_continuation and not continuation:
2925 # Sometimes you can get comments by generating the continuation yourself,
2926 # even if YouTube initially reports them being disabled - e.g. stories comments.
2927 # Note: if the comment section is actually disabled, YouTube may return a response with
2928 # required check_get_keys missing. So we will disable that check initially in this case.
2929 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2930 is_forced_continuation = True
a1c5d2ca
M
2931
2932 for page_num in itertools.count(0):
2933 if not continuation:
2934 break
46383212 2935 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2936 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2937 if page_num == 0:
2938 if is_first_continuation:
2939 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2940 else:
2d6659b9 2941 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2942 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2943 else:
2944 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2945 ' ' if parent else '', ' replies' if parent else '',
2946 page_num, comment_prog_str)
2947
2948 response = self._extract_response(
fe93e2c4 2949 item_id=None, query=continuation,
2d6659b9 2950 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
6e634cbe 2951 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2952 is_forced_continuation = False
46383212 2953 continuation_contents = traverse_obj(
2954 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2955
2d6659b9 2956 continuation = None
46383212 2957 for continuation_section in continuation_contents:
2958 continuation_items = traverse_obj(
2959 continuation_section,
2960 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2961 get_all=False, expected_type=list) or []
2962 if is_first_continuation:
2963 continuation = extract_header(continuation_items)
2964 is_first_continuation = False
2d6659b9 2965 if continuation:
a1c5d2ca 2966 break
46383212 2967 continue
a1c5d2ca 2968
46383212 2969 for entry in extract_thread(continuation_items):
2970 if not entry:
2971 return
2972 yield entry
2973 continuation = self._extract_continuation({'contents': continuation_items})
2974 if continuation:
2d6659b9 2975 break
a1c5d2ca 2976
6e634cbe 2977 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2978 if message and not parent and tracker['running_total'] == 0:
2979 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
2980
2981 @staticmethod
2982 def _generate_comment_continuation(video_id):
2983 """
2984 Generates initial comment section continuation token from given video id
2985 """
2986 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
2987 return base64.b64encode(token.encode()).decode()
2988
a2160aa4 2989 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2990 """Entry for comment extraction"""
2d6659b9 2991 def _real_comment_extract(contents):
aae16f6e 2992 renderer = next((
2993 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2994 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2995 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2996
a2160aa4 2997 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2998 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2999
109dd3b2 3000 @staticmethod
99e9e001 3001 def _get_checkok_params():
3002 return {'contentCheckOk': True, 'racyCheckOk': True}
3003
3004 @classmethod
3005 def _generate_player_context(cls, sts=None):
109dd3b2 3006 context = {
3007 'html5Preference': 'HTML5_PREF_WANTS',
3008 }
3009 if sts is not None:
3010 context['signatureTimestamp'] = sts
3011 return {
3012 'playbackContext': {
3013 'contentPlaybackContext': context
a1a7907b 3014 },
99e9e001 3015 **cls._get_checkok_params()
109dd3b2 3016 }
3017
e7e94f2a
D
3018 @staticmethod
3019 def _is_agegated(player_response):
3020 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3021 return True
e7e94f2a
D
3022
3023 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3024 AGE_GATE_REASONS = (
3025 'confirm your age', 'age-restricted', 'inappropriate', # reason
3026 'age_verification_required', 'age_check_required', # status
3027 )
3028 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3029
3030 @staticmethod
3031 def _is_unplayable(player_response):
3032 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3033
99e9e001 3034 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 3035
11f9be09 3036 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3037 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3038 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3039 headers = self.generate_api_headers(
99e9e001 3040 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3041
6e634cbe 3042 yt_query = {
3043 'videoId': video_id,
3044 'params': '8AEB' # enable stories
3045 }
11f9be09 3046 yt_query.update(self._generate_player_context(sts))
3047 return self._extract_response(
3048 item_id=video_id, ep='player', query=yt_query,
379e44ed 3049 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3050 default_client=client,
11f9be09 3051 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3052 ) or None
3053
11f9be09 3054 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3055 requested_clients = []
d0d012d4 3056 default = ['android', 'web']
000c15a4 3057 allowed_clients = sorted(
86e5f3ed 3058 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3059 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3060 for client in self._configuration_arg('player_client'):
3061 if client in allowed_clients:
3062 requested_clients.append(client)
d0d012d4 3063 elif client == 'default':
3064 requested_clients.extend(default)
b4c055ba 3065 elif client == 'all':
3066 requested_clients.extend(allowed_clients)
3067 else:
3068 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3069 if not requested_clients:
d0d012d4 3070 requested_clients = default
cf7e015f 3071
11f9be09 3072 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3073 requested_clients.extend(
e7e94f2a 3074 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3075
11f9be09 3076 return orderedSet(requested_clients)
cf7e015f 3077
99e9e001 3078 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 3079 initial_pr = None
3080 if webpage:
b7c47b74 3081 initial_pr = self._search_json(
3082 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3083
ae729626 3084 all_clients = set(clients)
c0bc527b 3085 clients = clients[::-1]
b6de707d 3086 prs = []
e7e94f2a 3087
ae729626 3088 def append_client(*client_names):
e7870111 3089 """ Append the first client name that exists but not already used """
ae729626 3090 for client_name in client_names:
e7870111
D
3091 actual_client = _split_innertube_client(client_name)[0]
3092 if actual_client in INNERTUBE_CLIENTS:
3093 if actual_client not in all_clients:
ae729626 3094 clients.append(client_name)
e7870111
D
3095 all_clients.add(actual_client)
3096 return
e7e94f2a 3097
379e44ed 3098 # Android player_response does not have microFormats which are needed for
3099 # extraction of some data. So we return the initial_pr with formats
3100 # stripped out even if not requested by the user
3101 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3102 if initial_pr:
3103 pr = dict(initial_pr)
3104 pr['streamingData'] = None
b6de707d 3105 prs.append(pr)
379e44ed 3106
3107 last_error = None
b6de707d 3108 tried_iframe_fallback = False
3109 player_url = None
c0bc527b 3110 while clients:
e7870111 3111 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3112 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3113 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3114 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3115
b6de707d 3116 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3117 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3118 if 'js' in self._configuration_arg('player_skip'):
3119 require_js_player = False
3120 player_url = None
3121
3122 if not player_url and not tried_iframe_fallback and require_js_player:
3123 player_url = self._download_player_url(video_id)
3124 tried_iframe_fallback = True
3125
379e44ed 3126 try:
3127 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 3128 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 3129 except ExtractorError as e:
3130 if last_error:
3131 self.report_warning(last_error)
3132 last_error = e
3133 continue
3134
11f9be09 3135 if pr:
b6de707d 3136 prs.append(pr)
c0bc527b 3137
e7e94f2a 3138 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3139 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3140 append_client(f'{base_client}_creator')
e7e94f2a 3141 elif self._is_agegated(pr):
e7870111
D
3142 if variant == 'tv_embedded':
3143 append_client(f'{base_client}_embedded')
3144 elif not variant:
3145 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3146
379e44ed 3147 if last_error:
b6de707d 3148 if not len(prs):
379e44ed 3149 raise last_error
3150 self.report_warning(last_error)
b6de707d 3151 return prs, player_url
11f9be09 3152
c646d76f 3153 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3154 itags, stream_ids = {}, []
2a9c6dcd 3155 itag_qualities, res_qualities = {}, {}
d3fc8074 3156 q = qualities([
2a9c6dcd 3157 # Normally tiny is the smallest video-only formats. But
3158 # audio-only formats with unknown quality may get tagged as tiny
3159 'tiny',
3160 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3161 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3162 ])
11f9be09 3163 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3164
545cc85d 3165 for fmt in streaming_formats:
727029c5 3166 if fmt.get('targetDurationSec'):
545cc85d 3167 continue
321bf820 3168
cc2db878 3169 itag = str_or_none(fmt.get('itag'))
9297939e 3170 audio_track = fmt.get('audioTrack') or {}
3171 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3172 if stream_id in stream_ids:
3173 continue
3174
cc2db878 3175 quality = fmt.get('quality')
2a9c6dcd 3176 height = int_or_none(fmt.get('height'))
d3fc8074 3177 if quality == 'tiny' or not quality:
3178 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3179 # The 3gp format (17) in android client has a quality of "small",
3180 # but is actually worse than other formats
3181 if itag == '17':
3182 quality = 'tiny'
3183 if quality:
3184 if itag:
3185 itag_qualities[itag] = quality
3186 if height:
3187 res_qualities[height] = quality
cc2db878 3188 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3189 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3190 # number of fragment that would subsequently requested with (`&sq=N`)
3191 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3192 continue
3193
545cc85d 3194 fmt_url = fmt.get('url')
3195 if not fmt_url:
14f25df2 3196 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3197 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3198 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3199 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3200 continue
52023f12 3201 try:
3202 fmt_url += '&%s=%s' % (
3203 traverse_obj(sc, ('sp', -1)) or 'signature',
3204 self._decrypt_signature(encrypted_sig, video_id, player_url)
3205 )
3206 except ExtractorError as e:
3207 self.report_warning('Signature extraction failed: Some formats may be missing', only_once=True)
3208 self.write_debug(e, only_once=True)
201e9eaa 3209 continue
545cc85d 3210
404f611f 3211 query = parse_qs(fmt_url)
3212 throttled = False
b2916526 3213 if query.get('n'):
404f611f 3214 try:
3215 fmt_url = update_url_query(fmt_url, {
3216 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3217 except ExtractorError as e:
aa9369a2 3218 self.report_warning(
1d485a1a 3219 'nsig extraction failed: You may experience throttling for some formats\n'
52023f12 3220 f'n = {query["n"][0]} ; player = {player_url}', only_once=True)
3221 self.write_debug(e, only_once=True)
404f611f 3222 throttled = True
3223
545cc85d 3224 if itag:
a0bb6ce5 3225 itags[itag] = 'https'
9297939e 3226 stream_ids.append(stream_id)
3227
0ad92dfb 3228 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3229 language_preference = (
3230 10 if audio_track.get('audioIsDefault') and 10
3231 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3232 else -1)
0ad92dfb 3233 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3234 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3235 # Make sure to avoid false positives with small duration differences.
3236 # Eg: __2ABJjxzNo, ySuUZEjARPY
3237 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3238 if is_damaged:
0f06bcd7 3239 self.report_warning(
3240 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3241 dct = {
3242 'asr': int_or_none(fmt.get('audioSampleRate')),
3243 'filesize': int_or_none(fmt.get('contentLength')),
3244 'format_id': itag,
34921b43 3245 'format_note': join_nonempty(
26e8e044 3246 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3247 ' (default)' if language_preference > 0 else ''),
404f611f 3248 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
0ad92dfb 3249 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3250 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3251 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3252 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3253 'height': height,
dca3ff4a 3254 'quality': q(quality),
727029c5 3255 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3256 'tbr': tbr,
545cc85d 3257 'url': fmt_url,
2a9c6dcd 3258 'width': int_or_none(fmt.get('width')),
ab6df717 3259 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3260 'desc' if language_preference < -1 else ''),
3261 'language_preference': language_preference,
a405b38f 3262 # Strictly de-prioritize damaged and 3gp formats
3263 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3264 }
60bdb7bd 3265 mime_mobj = re.match(
3266 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3267 if mime_mobj:
3268 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3269 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3270 no_audio = dct.get('acodec') == 'none'
3271 no_video = dct.get('vcodec') == 'none'
3272 if no_audio:
3273 dct['vbr'] = tbr
3274 if no_video:
3275 dct['abr'] = tbr
3276 if no_audio or no_video:
545cc85d 3277 dct['downloader_options'] = {
3278 # Youtube throttles chunks >~10M
3279 'http_chunk_size': 10485760,
bf1317d2 3280 }
7c60c33e 3281 if dct.get('ext'):
3282 dct['container'] = dct['ext'] + '_dash'
11f9be09 3283 yield dct
545cc85d 3284
adbc4ec4 3285 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3286 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3287 if not self.get_param('youtube_include_hls_manifest', True):
3288 skip_manifests.append('hls')
0f06bcd7 3289 if not self.get_param('youtube_include_dash_manifest', True):
3290 skip_manifests.append('dash')
adbc4ec4
THD
3291 get_dash = 'dash' not in skip_manifests and (
3292 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3293 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3294
a0bb6ce5 3295 def process_manifest_format(f, proto, itag):
3296 if itag in itags:
3297 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3298 return False
3299 itag = f'{itag}-{proto}'
3300 if itag:
3301 f['format_id'] = itag
3302 itags[itag] = proto
3303
3304 f['quality'] = next((
3305 q(qdict[val])
e339d25a 3306 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3307 if val in qdict), -1)
3308 return True
2a9c6dcd 3309
c646d76f 3310 subtitles = {}
11f9be09 3311 for sd in streaming_data:
5d3a0e79 3312 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3313 if hls_manifest_url:
c646d76f 3314 fmts, subs = self._extract_m3u8_formats_and_subtitles(hls_manifest_url, video_id, 'mp4', fatal=False, live=is_live)
3315 subtitles = self._merge_subtitles(subs, subtitles)
3316 for f in fmts:
a0bb6ce5 3317 if process_manifest_format(f, 'hls', self._search_regex(
3318 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3319 yield f
545cc85d 3320
5d3a0e79 3321 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3322 if dash_manifest_url:
c646d76f 3323 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3324 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3325 for f in formats:
a0bb6ce5 3326 if process_manifest_format(f, 'dash', f['format_id']):
3327 f['filesize'] = int_or_none(self._search_regex(
3328 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3329 if live_from_start:
3330 f['is_from_start'] = True
3331
a0bb6ce5 3332 yield f
c646d76f 3333 yield subtitles
11f9be09 3334
720c3099 3335 def _extract_storyboard(self, player_responses, duration):
3336 spec = get_first(
3337 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3338 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3339 if not base_url:
720c3099 3340 return
720c3099 3341 L = len(spec) - 1
3342 for i, args in enumerate(spec):
3343 args = args.split('#')
3344 counts = list(map(int_or_none, args[:5]))
3345 if len(args) != 8 or not all(counts):
3346 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3347 continue
3348 width, height, frame_count, cols, rows = counts
3349 N, sigh = args[6:]
3350
3351 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3352 fragment_count = frame_count / (cols * rows)
3353 fragment_duration = duration / fragment_count
3354 yield {
3355 'format_id': f'sb{i}',
3356 'format_note': 'storyboard',
3357 'ext': 'mhtml',
3358 'protocol': 'mhtml',
3359 'acodec': 'none',
3360 'vcodec': 'none',
3361 'url': url,
3362 'width': width,
3363 'height': height,
45e8a04e 3364 'fps': frame_count / duration,
3365 'rows': rows,
3366 'columns': cols,
720c3099 3367 'fragments': [{
b3edc806 3368 'url': url.replace('$M', str(j)),
720c3099 3369 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3370 } for j in range(math.ceil(fragment_count))],
3371 }
3372
adbc4ec4 3373 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3374 webpage = None
3375 if 'webpage' not in self._configuration_arg('player_skip'):
3376 webpage = self._download_webpage(
6e634cbe 3377 webpage_url + '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id, fatal=False)
11f9be09 3378
3379 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3380
b6de707d 3381 player_responses, player_url = self._extract_player_responses(
11f9be09 3382 self._get_requested_clients(url, smuggled_data),
99e9e001 3383 video_id, webpage, master_ytcfg)
11f9be09 3384
adbc4ec4
THD
3385 return webpage, master_ytcfg, player_responses, player_url
3386
a1b2d843 3387 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3388 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3389 is_live = get_first(video_details, 'isLive')
3390 if is_live is None:
3391 is_live = get_first(live_broadcast_details, 'isLiveNow')
3392
3393 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
c646d76f 3394 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, is_live, duration)
adbc4ec4 3395
c646d76f 3396 return live_broadcast_details, is_live, streaming_data, formats, subtitles
adbc4ec4
THD
3397
3398 def _real_extract(self, url):
3399 url, smuggled_data = unsmuggle_url(url, {})
3400 video_id = self._match_id(url)
3401
3402 base_url = self.http_scheme() + '//www.youtube.com/'
3403 webpage_url = base_url + 'watch?v=' + video_id
3404
3405 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3406
11f9be09 3407 playability_statuses = traverse_obj(
3408 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3409
3410 trailer_video_id = get_first(
3411 playability_statuses,
3412 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3413 expected_type=str)
3414 if trailer_video_id:
3415 return self.url_result(
3416 trailer_video_id, self.ie_key(), trailer_video_id)
3417
3418 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3419 if webpage else (lambda x: None))
3420
3421 video_details = traverse_obj(
3422 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3423 microformats = traverse_obj(
3424 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3425 expected_type=dict, default=[])
3426 video_title = (
3427 get_first(video_details, 'title')
3428 or self._get_text(microformats, (..., 'title'))
3429 or search_meta(['og:title', 'twitter:title', 'title']))
3430 video_description = get_first(video_details, 'shortDescription')
3431
d89257f3 3432 multifeed_metadata_list = get_first(
3433 player_responses,
3434 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3435 expected_type=str)
3436 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3437 if self.get_param('noplaylist'):
11f9be09 3438 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3439 else:
3440 entries = []
3441 feed_ids = []
3442 for feed in multifeed_metadata_list.split(','):
3443 # Unquote should take place before split on comma (,) since textual
3444 # fields may contain comma as well (see
3445 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3446 feed_data = urllib.parse.parse_qs(
ac668111 3447 urllib.parse.unquote_plus(feed))
d89257f3 3448
3449 def feed_entry(name):
3450 return try_get(
14f25df2 3451 feed_data, lambda x: x[name][0], str)
d89257f3 3452
3453 feed_id = feed_entry('id')
3454 if not feed_id:
3455 continue
3456 feed_title = feed_entry('title')
3457 title = video_title
3458 if feed_title:
3459 title += ' (%s)' % feed_title
3460 entries.append({
3461 '_type': 'url_transparent',
3462 'ie_key': 'Youtube',
3463 'url': smuggle_url(
3464 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3465 {'force_singlefeed': True}),
3466 'title': title,
3467 })
3468 feed_ids.append(feed_id)
3469 self.to_screen(
3470 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3471 % (', '.join(feed_ids), video_id))
3472 return self.playlist_result(
3473 entries, video_id, video_title, video_description)
11f9be09 3474
a1b2d843 3475 duration = int_or_none(
3476 get_first(video_details, 'lengthSeconds')
3477 or get_first(microformats, 'lengthSeconds')
3478 or parse_duration(search_meta('duration'))) or None
3479
c646d76f 3480 live_broadcast_details, is_live, streaming_data, formats, automatic_captions = \
3481 self._list_formats(video_id, microformats, video_details, player_responses, player_url)
bf1317d2 3482
545cc85d 3483 if not formats:
11f9be09 3484 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3485 self.report_drm(video_id)
11f9be09 3486 pemr = get_first(
3487 playability_statuses,
3488 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3489 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3490 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3491 if subreason:
545cc85d 3492 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3493 countries = get_first(microformats, 'availableCountries')
545cc85d 3494 if not countries:
3495 regions_allowed = search_meta('regionsAllowed')
3496 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3497 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3498 reason += f'. {subreason}'
545cc85d 3499 if reason:
b7da73eb 3500 self.raise_no_formats(reason, expected=True)
bf1317d2 3501
11f9be09 3502 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3503 if not keywords and webpage:
3504 keywords = [
3505 unescapeHTML(m.group('content'))
3506 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3507 for keyword in keywords:
3508 if keyword.startswith('yt:stretch='):
201c1459 3509 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3510 if mobj:
3511 # NB: float is intentional for forcing float division
3512 w, h = (float(v) for v in mobj.groups())
3513 if w > 0 and h > 0:
3514 ratio = w / h
3515 for f in formats:
3516 if f.get('vcodec') != 'none':
3517 f['stretched_ratio'] = ratio
3518 break
a709d873 3519 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3520 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3521 if thumbnail_url:
3522 thumbnails.append({
3523 'url': thumbnail_url,
ff2751ac 3524 })
fccf5021 3525 original_thumbnails = thumbnails.copy()
3526
0ba692ac 3527 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3528 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3529 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3530 thumbnail_names = [
962ffcf8 3531 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 3532 # in resolution, these are not the custom thumbnail. So de-prioritize them
3533 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3534 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3535 ]
cca80fe6 3536 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3537 thumbnails.extend({
3538 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3539 video_id=video_id, name=name, ext=ext,
3540 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3541 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3542 for thumb in thumbnails:
cca80fe6 3543 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3544 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3545 self._remove_duplicate_formats(thumbnails)
fccf5021 3546 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3547
7ea65411 3548 category = get_first(microformats, 'category') or search_meta('genre')
3549 channel_id = str_or_none(
3550 get_first(video_details, 'channelId')
3551 or get_first(microformats, 'externalChannelId')
3552 or search_meta('channelId'))
7ea65411 3553 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3554
3555 live_content = get_first(video_details, 'isLiveContent')
3556 is_upcoming = get_first(video_details, 'isUpcoming')
3557 if is_live is None:
3558 if is_upcoming or live_content is False:
3559 is_live = False
3560 if is_upcoming is None and (live_content or is_live):
3561 is_upcoming = False
adbc4ec4
THD
3562 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3563 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3564 if not duration and live_end_time and live_start_time:
3565 duration = live_end_time - live_start_time
3566
3567 if is_live and self.get_param('live_from_start'):
3568 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3569
720c3099 3570 formats.extend(self._extract_storyboard(player_responses, duration))
3571
31b532a1 3572 # source_preference is lower for throttled/potentially damaged formats
720c3099 3573 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3574
545cc85d 3575 info = {
3576 'id': video_id,
39ca3b5c 3577 'title': video_title,
545cc85d 3578 'formats': formats,
3579 'thumbnails': thumbnails,
fccf5021 3580 # The best thumbnail that we are sure exists. Prevents unnecessary
3581 # URL checking if user don't care about getting the best possible thumbnail
3582 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3583 'description': video_description,
11f9be09 3584 'uploader': get_first(video_details, 'author'),
545cc85d 3585 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3586 'uploader_url': owner_profile_url,
3587 'channel_id': channel_id,
a70635b8 3588 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3589 'duration': duration,
3590 'view_count': int_or_none(
11f9be09 3591 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3592 or search_meta('interactionCount')),
11f9be09 3593 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3594 'age_limit': 18 if (
11f9be09 3595 get_first(microformats, 'isFamilySafe') is False
545cc85d 3596 or search_meta('isFamilyFriendly') == 'false'
3597 or search_meta('og:restrictions:age') == '18+') else 0,
3598 'webpage_url': webpage_url,
3599 'categories': [category] if category else None,
3600 'tags': keywords,
11f9be09 3601 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3602 'is_live': is_live,
3603 'was_live': (False if is_live or is_upcoming or live_content is False
3604 else None if is_live is None or is_upcoming is None
3605 else live_content),
3606 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3607 'release_timestamp': live_start_time,
545cc85d 3608 }
b477fc13 3609
e325a21a 3610 if get_first(video_details, 'isPostLiveDvr'):
3611 self.write_debug('Video is in Post-Live Manifestless mode')
3612 info['live_status'] = 'post_live'
3613 if (duration or 0) > 4 * 3600:
3614 self.report_warning(
3615 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3616 'This is a known issue and patches are welcome')
3617
c646d76f 3618 subtitles = {}
3944e7af 3619 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3620 if pctr:
ecdc9049 3621 def get_lang_code(track):
3622 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3623 or track.get('languageCode'))
3624
3625 # Converted into dicts to remove duplicates
3626 captions = {
3627 get_lang_code(sub): sub
3628 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3629 translation_languages = {
3630 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3631 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3632
774d79cc 3633 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3634 lang_subs = container.setdefault(lang_code, [])
545cc85d 3635 for fmt in self._SUBTITLE_FORMATS:
3636 query.update({
3637 'fmt': fmt,
3638 })
3639 lang_subs.append({
3640 'ext': fmt,
60f393e4 3641 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3642 'name': sub_name,
545cc85d 3643 })
7e72694b 3644
07b47084 3645 # NB: Constructing the full subtitle dictionary is slow
3646 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
3647 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 3648 for lang_code, caption_track in captions.items():
3649 base_url = caption_track.get('baseUrl')
1235d333 3650 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3651 if not base_url:
3652 continue
ecdc9049 3653 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3654 if caption_track.get('kind') != 'asr':
545cc85d 3655 if not lang_code:
3656 continue
3657 process_language(
ecdc9049 3658 subtitles, base_url, lang_code, lang_name, {})
3659 if not caption_track.get('isTranslatable'):
3660 continue
3944e7af 3661 for trans_code, trans_name in translation_languages.items():
3662 if not trans_code:
545cc85d 3663 continue
1235d333 3664 orig_trans_code = trans_code
ecdc9049 3665 if caption_track.get('kind') != 'asr':
07b47084 3666 if not get_translated_subs:
18e49408 3667 continue
ecdc9049 3668 trans_code += f'-{lang_code}'
a70635b8 3669 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 3670 # Add an "-orig" label to the original language so that it can be distinguished.
3671 # The subs are returned without "-orig" as well for compatibility
1235d333 3672 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3673 process_language(
d49669ac 3674 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3675 # Setting tlang=lang returns damaged subtitles.
d49669ac 3676 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3677 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 3678
3679 info['automatic_captions'] = automatic_captions
3680 info['subtitles'] = subtitles
7e72694b 3681
14f25df2 3682 parsed_url = urllib.parse.urlparse(url)
545cc85d 3683 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 3684 query = urllib.parse.parse_qs(component)
545cc85d 3685 for k, v in query.items():
3686 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3687 d_k += '_time'
3688 if d_k not in info and k in s_ks:
3689 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3690
3691 # Youtube Music Auto-generated description
822b9d9c 3692 if video_description:
1890fc63 3693 mobj = re.search(
3694 r'''(?xs)
3695 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3696 (?P<album>[^\n]+)
3697 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3698 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3699 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3700 .+\nAuto-generated\ by\ YouTube\.\s*$
3701 ''', video_description)
822b9d9c 3702 if mobj:
822b9d9c
RA
3703 release_year = mobj.group('release_year')
3704 release_date = mobj.group('release_date')
3705 if release_date:
3706 release_date = release_date.replace('-', '')
3707 if not release_year:
545cc85d 3708 release_year = release_date[:4]
3709 info.update({
3710 'album': mobj.group('album'.strip()),
3711 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3712 'track': mobj.group('track').strip(),
3713 'release_date': release_date,
cc2db878 3714 'release_year': int_or_none(release_year),
545cc85d 3715 })
7e72694b 3716
545cc85d 3717 initial_data = None
3718 if webpage:
56ba69e4 3719 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 3720 if not initial_data:
99e9e001 3721 query = {'videoId': video_id}
3722 query.update(self._get_checkok_params())
109dd3b2 3723 initial_data = self._extract_response(
3724 item_id=video_id, ep='next', fatal=False,
99e9e001 3725 ytcfg=master_ytcfg, query=query,
3726 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3727 note='Downloading initial data API JSON')
545cc85d 3728
0df111a3 3729 info['comment_count'] = traverse_obj(initial_data, (
3730 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3731 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3732 ), (
3733 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3734 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3735 ), expected_type=int_or_none, get_all=False)
3736
19a03940 3737 try: # This will error if there is no livechat
c60ee3a2 3738 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 3739 except (KeyError, IndexError, TypeError):
3740 pass
3741 else:
ecdc9049 3742 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 3743 # url is needed to set cookies
3744 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 3745 'video_id': video_id,
3746 'ext': 'json',
f6745c49 3747 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3748 }]
545cc85d 3749
3750 if initial_data:
7c365c21 3751 info['chapters'] = (
3752 self._extract_chapters_from_json(initial_data, duration)
3753 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 3754 or self._extract_chapters_from_description(video_description, duration)
7c365c21 3755 or None)
545cc85d 3756
17322130 3757 contents = traverse_obj(
3758 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3759 expected_type=list, default=[])
3760
3761 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3762 if vpir:
3763 stl = vpir.get('superTitleLink')
3764 if stl:
3765 stl = self._get_text(stl)
3766 if try_get(
3767 vpir,
3768 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3769 info['location'] = stl
3770 else:
affc4fef 3771 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 3772 if mobj:
545cc85d 3773 info.update({
17322130 3774 'series': mobj.group(1),
3775 'season_number': int(mobj.group(2)),
3776 'episode_number': int(mobj.group(3)),
545cc85d 3777 })
17322130 3778 for tlb in (try_get(
3779 vpir,
3780 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3781 list) or []):
3782 tbr = tlb.get('toggleButtonRenderer') or {}
3783 for getter, regex in [(
3784 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3785 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3786 lambda x: x['accessibility'],
3787 lambda x: x['accessibilityData']['accessibilityData'],
3788 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3789 label = (try_get(tbr, getter, dict) or {}).get('label')
3790 if label:
3791 mobj = re.match(regex, label)
3792 if mobj:
3793 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3794 break
17322130 3795 sbr_tooltip = try_get(
3796 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3797 if sbr_tooltip:
3798 like_count, dislike_count = sbr_tooltip.split(' / ')
3799 info.update({
3800 'like_count': str_to_int(like_count),
3801 'dislike_count': str_to_int(dislike_count),
3802 })
3803 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3804 if vsir:
3805 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3806 info.update({
3807 'channel': self._get_text(vor, 'title'),
3808 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3809
3810 rows = try_get(
3811 vsir,
3812 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3813 list) or []
3814 multiple_songs = False
3815 for row in rows:
3816 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3817 multiple_songs = True
3818 break
3819 for row in rows:
3820 mrr = row.get('metadataRowRenderer') or {}
3821 mrr_title = mrr.get('title')
3822 if not mrr_title:
3823 continue
3824 mrr_title = self._get_text(mrr, 'title')
3825 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3826 if mrr_title == 'License':
3827 info['license'] = mrr_contents_text
3828 elif not multiple_songs:
3829 if mrr_title == 'Album':
3830 info['album'] = mrr_contents_text
3831 elif mrr_title == 'Artist':
3832 info['artist'] = mrr_contents_text
3833 elif mrr_title == 'Song':
3834 info['track'] = mrr_contents_text
545cc85d 3835
3836 fallbacks = {
3837 'channel': 'uploader',
3838 'channel_id': 'uploader_id',
3839 'channel_url': 'uploader_url',
3840 }
992f9a73 3841
17322130 3842 # The upload date for scheduled, live and past live streams / premieres in microformats
3843 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3844 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3845 upload_date = (
3846 unified_strdate(get_first(microformats, 'uploadDate'))
3847 or unified_strdate(search_meta('uploadDate')))
3848 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
6e634cbe 3849 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date
17322130 3850 info['upload_date'] = upload_date
992f9a73 3851
545cc85d 3852 for to, frm in fallbacks.items():
3853 if not info.get(to):
3854 info[to] = info.get(frm)
3855
3856 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3857 v = info.get(s_k)
3858 if v:
3859 info[d_k] = v
b84071c0 3860
11f9be09 3861 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3862 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3863 is_membersonly = None
b28f8d24 3864 is_premium = None
c224251a
M
3865 if initial_data and is_private is not None:
3866 is_membersonly = False
b28f8d24 3867 is_premium = False
47193e02 3868 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3869 badge_labels = set()
3870 for content in contents:
3871 if not isinstance(content, dict):
3872 continue
3873 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3874 for badge_label in badge_labels:
3875 if badge_label.lower() == 'members only':
3876 is_membersonly = True
3877 elif badge_label.lower() == 'premium':
3878 is_premium = True
3879 elif badge_label.lower() == 'unlisted':
3880 is_unlisted = True
c224251a 3881
c224251a
M
3882 info['availability'] = self._availability(
3883 is_private=is_private,
b28f8d24 3884 needs_premium=is_premium,
c224251a
M
3885 needs_subscription=is_membersonly,
3886 needs_auth=info['age_limit'] >= 18,
3887 is_unlisted=None if is_private is None else is_unlisted)
3888
a2160aa4 3889 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3890
11f9be09 3891 self.mark_watched(video_id, player_responses)
d77ab8e2 3892
545cc85d 3893 return info
c5e8d7af 3894
a61fd4cf 3895
a6213a49 3896class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3897
182bda88 3898 @staticmethod
3899 def passthrough_smuggled_data(func):
3900 def _smuggle(entries, smuggled_data):
3901 for entry in entries:
3902 # TODO: Convert URL to music.youtube instead.
3903 # Do we need to passthrough any other smuggled_data?
3904 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3905 yield entry
3906
3907 @functools.wraps(func)
3908 def wrapper(self, url):
3909 url, smuggled_data = unsmuggle_url(url, {})
3910 if self.is_music_url(url):
3911 smuggled_data['is_music_url'] = True
3912 info_dict = func(self, url, smuggled_data)
3913 if smuggled_data and info_dict.get('entries'):
3914 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3915 return info_dict
3916 return wrapper
3917
a6213a49 3918 def _extract_channel_id(self, webpage):
3919 channel_id = self._html_search_meta(
3920 'channelId', webpage, 'channel id', default=None)
3921 if channel_id:
3922 return channel_id
3923 channel_url = self._html_search_meta(
3924 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3925 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3926 'twitter:app:url:googleplay'), webpage, 'channel url')
3927 return self._search_regex(
3928 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3929 channel_url, 'channel id')
15f6397c 3930
8bdd16b4 3931 @staticmethod
cd7c66cf 3932 def _extract_basic_item_renderer(item):
3933 # Modified from _extract_grid_item_renderer
201c1459 3934 known_basic_renderers = (
a17526e4 3935 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 3936 )
3937 for key, renderer in item.items():
201c1459 3938 if not isinstance(renderer, dict):
cd7c66cf 3939 continue
201c1459 3940 elif key in known_basic_renderers:
3941 return renderer
3942 elif key.startswith('grid') and key.endswith('Renderer'):
3943 return renderer
8bdd16b4 3944
8bdd16b4 3945 def _grid_entries(self, grid_renderer):
3946 for item in grid_renderer['items']:
3947 if not isinstance(item, dict):
39b62db1 3948 continue
cd7c66cf 3949 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3950 if not isinstance(renderer, dict):
3951 continue
052e1350 3952 title = self._get_text(renderer, 'title')
fe93e2c4 3953
8bdd16b4 3954 # playlist
3955 playlist_id = renderer.get('playlistId')
3956 if playlist_id:
3957 yield self.url_result(
3958 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3959 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3960 video_title=title)
201c1459 3961 continue
8bdd16b4 3962 # video
3963 video_id = renderer.get('videoId')
3964 if video_id:
3965 yield self._extract_video(renderer)
201c1459 3966 continue
8bdd16b4 3967 # channel
3968 channel_id = renderer.get('channelId')
3969 if channel_id:
8bdd16b4 3970 yield self.url_result(
3971 'https://www.youtube.com/channel/%s' % channel_id,
3972 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3973 continue
3974 # generic endpoint URL support
3975 ep_url = urljoin('https://www.youtube.com/', try_get(
3976 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 3977 str))
201c1459 3978 if ep_url:
3979 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3980 if ie.suitable(ep_url):
3981 yield self.url_result(
3982 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3983 break
8bdd16b4 3984
16aa9ea4 3985 def _music_reponsive_list_entry(self, renderer):
3986 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3987 if video_id:
3988 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3989 ie=YoutubeIE.ie_key(), video_id=video_id)
3990 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3991 if playlist_id:
3992 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3993 if video_id:
3994 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3995 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3996 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3997 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3998 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3999 if browse_id:
4000 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4001 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4002
3d3dddc9 4003 def _shelf_entries_from_content(self, shelf_renderer):
4004 content = shelf_renderer.get('content')
4005 if not isinstance(content, dict):
8bdd16b4 4006 return
cd7c66cf 4007 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4008 if renderer:
4009 # TODO: add support for nested playlists so each shelf is processed
4010 # as separate playlist
4011 # TODO: this includes only first N items
86e5f3ed 4012 yield from self._grid_entries(renderer)
3d3dddc9 4013 renderer = content.get('horizontalListRenderer')
4014 if renderer:
4015 # TODO
4016 pass
8bdd16b4 4017
29f7c58a 4018 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4019 ep = try_get(
4020 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4021 str)
8bdd16b4 4022 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4023 if shelf_url:
29f7c58a 4024 # Skipping links to another channels, note that checking for
4025 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4026 # will not work
4027 if skip_channels and '/channels?' in shelf_url:
4028 return
052e1350 4029 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4030 yield self.url_result(shelf_url, video_title=title)
4031 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4032 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4033
8bdd16b4 4034 def _playlist_entries(self, video_list_renderer):
4035 for content in video_list_renderer['contents']:
4036 if not isinstance(content, dict):
4037 continue
4038 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4039 if not isinstance(renderer, dict):
4040 continue
4041 video_id = renderer.get('videoId')
4042 if not video_id:
4043 continue
4044 yield self._extract_video(renderer)
07aeced6 4045
3462ffa8 4046 def _rich_entries(self, rich_grid_renderer):
4047 renderer = try_get(
70d5c17b 4048 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 4049 video_id = renderer.get('videoId')
4050 if not video_id:
4051 return
4052 yield self._extract_video(renderer)
4053
8bdd16b4 4054 def _video_entry(self, video_renderer):
4055 video_id = video_renderer.get('videoId')
4056 if video_id:
4057 return self._extract_video(video_renderer)
dacb3a86 4058
ad210f4f 4059 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4060 url = urljoin('https://youtube.com', traverse_obj(
4061 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4062 if url:
4063 return self.url_result(
4064 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4065
8bdd16b4 4066 def _post_thread_entries(self, post_thread_renderer):
4067 post_renderer = try_get(
4068 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4069 if not post_renderer:
4070 return
4071 # video attachment
4072 video_renderer = try_get(
895b0931 4073 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4074 video_id = video_renderer.get('videoId')
4075 if video_id:
4076 entry = self._extract_video(video_renderer)
8bdd16b4 4077 if entry:
4078 yield entry
895b0931 4079 # playlist attachment
4080 playlist_id = try_get(
14f25df2 4081 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4082 if playlist_id:
4083 yield self.url_result(
e28f1c0a 4084 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4085 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4086 # inline video links
4087 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4088 for run in runs:
4089 if not isinstance(run, dict):
4090 continue
4091 ep_url = try_get(
14f25df2 4092 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4093 if not ep_url:
4094 continue
4095 if not YoutubeIE.suitable(ep_url):
4096 continue
4097 ep_video_id = YoutubeIE._match_id(ep_url)
4098 if video_id == ep_video_id:
4099 continue
895b0931 4100 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4101
8bdd16b4 4102 def _post_thread_continuation_entries(self, post_thread_continuation):
4103 contents = post_thread_continuation.get('contents')
4104 if not isinstance(contents, list):
4105 return
4106 for content in contents:
4107 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4108 if isinstance(renderer, dict):
4109 yield from self._post_thread_entries(renderer)
8bdd16b4 4110 continue
6b0b0a28 4111 renderer = content.get('videoRenderer')
4112 if isinstance(renderer, dict):
4113 yield self._video_entry(renderer)
07aeced6 4114
39ed931e 4115 r''' # unused
4116 def _rich_grid_entries(self, contents):
4117 for content in contents:
4118 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4119 if video_renderer:
4120 entry = self._video_entry(video_renderer)
4121 if entry:
4122 yield entry
4123 '''
52efa4b3 4124
a6213a49 4125 def _extract_entries(self, parent_renderer, continuation_list):
4126 # continuation_list is modified in-place with continuation_list = [continuation_token]
4127 continuation_list[:] = [None]
4128 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4129 for content in contents:
4130 if not isinstance(content, dict):
4131 continue
16aa9ea4 4132 is_renderer = traverse_obj(
4133 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4134 expected_type=dict)
a6213a49 4135 if not is_renderer:
4136 renderer = content.get('richItemRenderer')
4137 if renderer:
4138 for entry in self._rich_entries(renderer):
4139 yield entry
4140 continuation_list[0] = self._extract_continuation(parent_renderer)
4141 continue
4142 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4143 for isr_content in isr_contents:
4144 if not isinstance(isr_content, dict):
8bdd16b4 4145 continue
69184e41 4146
a6213a49 4147 known_renderers = {
4148 'playlistVideoListRenderer': self._playlist_entries,
4149 'gridRenderer': self._grid_entries,
a17526e4 4150 'reelShelfRenderer': self._grid_entries,
4151 'shelfRenderer': self._shelf_entries,
16aa9ea4 4152 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4153 'backstagePostThreadRenderer': self._post_thread_entries,
4154 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4155 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4156 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4157 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4158 }
4159 for key, renderer in isr_content.items():
4160 if key not in known_renderers:
4161 continue
4162 for entry in known_renderers[key](renderer):
4163 if entry:
4164 yield entry
4165 continuation_list[0] = self._extract_continuation(renderer)
4166 break
70d5c17b 4167
4168 if not continuation_list[0]:
a6213a49 4169 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4170
a6213a49 4171 if not continuation_list[0]:
4172 continuation_list[0] = self._extract_continuation(parent_renderer)
4173
4174 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4175 continuation_list = [None]
4176 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4177 tab_content = try_get(tab, lambda x: x['content'], dict)
4178 if not tab_content:
4179 return
3462ffa8 4180 parent_renderer = (
29f7c58a 4181 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4182 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4183 yield from extract_entries(parent_renderer)
3462ffa8 4184 continuation = continuation_list[0]
d069eca7 4185
8bdd16b4 4186 for page_num in itertools.count(1):
4187 if not continuation:
4188 break
99e9e001 4189 headers = self.generate_api_headers(
4190 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4191 response = self._extract_response(
86e5f3ed 4192 item_id=f'{item_id} page {page_num}',
fe93e2c4 4193 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4194 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4195
4196 if not response:
8bdd16b4 4197 break
ac56cf38 4198 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4199 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4200 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4201
69184e41 4202 known_continuation_renderers = {
4203 'playlistVideoListContinuation': self._playlist_entries,
4204 'gridContinuation': self._grid_entries,
4205 'itemSectionContinuation': self._post_thread_continuation_entries,
4206 'sectionListContinuation': extract_entries, # for feeds
4207 }
8bdd16b4 4208 continuation_contents = try_get(
69184e41 4209 response, lambda x: x['continuationContents'], dict) or {}
4210 continuation_renderer = None
4211 for key, value in continuation_contents.items():
4212 if key not in known_continuation_renderers:
3462ffa8 4213 continue
69184e41 4214 continuation_renderer = value
4215 continuation_list = [None]
86e5f3ed 4216 yield from known_continuation_renderers[key](continuation_renderer)
69184e41 4217 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4218 break
4219 if continuation_renderer:
4220 continue
c5e8d7af 4221
a1b535bd 4222 known_renderers = {
e4b98809 4223 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4224 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4225 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4226 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4227 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4228 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4229 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4230 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4231 }
cce889b9 4232 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4233 continuation_items = try_get(
cce889b9 4234 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4235 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4236 video_items_renderer = None
4237 for key, value in continuation_item.items():
4238 if key not in known_renderers:
8bdd16b4 4239 continue
a1b535bd 4240 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4241 continuation_list = [None]
86e5f3ed 4242 yield from known_renderers[key][0](video_items_renderer)
9ba5705a 4243 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4244 break
4245 if video_items_renderer:
4246 continue
8bdd16b4 4247 break
9558dcec 4248
8bdd16b4 4249 @staticmethod
7c219ea6 4250 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4251 for tab in tabs:
cd684175 4252 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4253 if renderer.get('selected') is True:
4254 return renderer
2b3c2546 4255 else:
7c219ea6 4256 if fatal:
4257 raise ExtractorError('Unable to find selected tab')
b82f815f 4258
61d3665d 4259 def _extract_uploader(self, data):
8bdd16b4 4260 uploader = {}
61d3665d 4261 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
47193e02 4262 owner = try_get(
4263 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4264 if owner:
61d3665d 4265 owner_text = owner.get('text')
4266 uploader['uploader'] = self._search_regex(
4267 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
47193e02 4268 uploader['uploader_id'] = try_get(
14f25df2 4269 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], str)
47193e02 4270 uploader['uploader_url'] = urljoin(
4271 'https://www.youtube.com/',
14f25df2 4272 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
9c3fe2ef 4273 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4274
ac56cf38 4275 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4276 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4277 tags = []
b60419c5 4278
8bdd16b4 4279 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4280 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4281 renderer = try_get(
4282 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4283 if renderer:
b60419c5 4284 channel_name = renderer.get('title')
4285 channel_url = renderer.get('channelUrl')
4286 channel_id = renderer.get('externalId')
39ed931e 4287 else:
64c0d954 4288 renderer = try_get(
4289 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4290
8bdd16b4 4291 if renderer:
4292 title = renderer.get('title')
ecc97af3 4293 description = renderer.get('description', '')
b60419c5 4294 playlist_id = channel_id
4295 tags = renderer.get('keywords', '').split()
b60419c5 4296
301d07fc 4297 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4298 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4299 def _get_uncropped(url):
4300 return url_or_none((url or '').split('=')[0] + '=s0')
4301
4302 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4303 if avatar_thumbnails:
4304 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4305 if uncropped_avatar:
4306 avatar_thumbnails.append({
4307 'url': uncropped_avatar,
4308 'id': 'avatar_uncropped',
4309 'preference': 1
4310 })
4311
4312 channel_banners = self._extract_thumbnails(
4313 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4314 for banner in channel_banners:
4315 banner['preference'] = -10
4316
4317 if channel_banners:
4318 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4319 if uncropped_banner:
4320 channel_banners.append({
4321 'url': uncropped_banner,
4322 'id': 'banner_uncropped',
4323 'preference': -5
4324 })
4325
4326 primary_thumbnails = self._extract_thumbnails(
a17526e4 4327 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4328
3462ffa8 4329 if playlist_id is None:
70d5c17b 4330 playlist_id = item_id
f0d785d3 4331
4332 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4333 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4334 if title is None:
f0d785d3 4335 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4336 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4337 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4338
b60419c5 4339 metadata = {
4340 'playlist_id': playlist_id,
4341 'playlist_title': title,
4342 'playlist_description': description,
4343 'uploader': channel_name,
4344 'uploader_id': channel_id,
4345 'uploader_url': channel_url,
301d07fc 4346 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4347 'tags': tags,
f0d785d3 4348 'view_count': self._get_count(playlist_stats, 1),
4349 'availability': self._extract_availability(data),
4350 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4351 'playlist_count': self._get_count(playlist_stats, 0),
4352 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4353 }
4354 if not channel_id:
4355 metadata.update(self._extract_uploader(data))
4356 metadata.update({
4357 'channel': metadata['uploader'],
4358 'channel_id': metadata['uploader_id'],
4359 'channel_url': metadata['uploader_url']})
4360 return self.playlist_result(
d069eca7 4361 self._entries(
ac56cf38 4362 selected_tab, playlist_id, ytcfg,
4363 self._extract_account_syncid(ytcfg, data),
4364 self._extract_visitor_data(data, ytcfg)),
b60419c5 4365 **metadata)
73c4ac2c 4366
6e634cbe 4367 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4368 first_id = last_id = response = None
2be71994 4369 for page_num in itertools.count(1):
cd7c66cf 4370 videos = list(self._playlist_entries(playlist))
4371 if not videos:
4372 return
2be71994 4373 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4374 if start >= len(videos):
4375 return
24146491 4376 yield from videos[start:]
2be71994 4377 first_id = first_id or videos[0]['id']
4378 last_id = videos[-1]['id']
79360d99 4379 watch_endpoint = try_get(
4380 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4381 headers = self.generate_api_headers(
4382 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4383 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4384 query = {
4385 'playlistId': playlist_id,
4386 'videoId': watch_endpoint.get('videoId') or last_id,
4387 'index': watch_endpoint.get('index') or len(videos),
4388 'params': watch_endpoint.get('params') or 'OAE%3D'
4389 }
4390 response = self._extract_response(
4391 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4392 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4393 check_get_keys='contents'
4394 )
cd7c66cf 4395 playlist = try_get(
79360d99 4396 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4397
ac56cf38 4398 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4399 title = playlist.get('title') or try_get(
14f25df2 4400 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4401 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4402
4403 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4404 playlist_url = urljoin(url, try_get(
4405 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4406 str))
6e634cbe 4407
4408 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4409 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4410 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4411
4412 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4413 return self.url_result(
4414 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4415 video_title=title)
cd7c66cf 4416
8bdd16b4 4417 return self.playlist_result(
6e634cbe 4418 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4419 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4420
47193e02 4421 def _extract_availability(self, data):
4422 """
4423 Gets the availability of a given playlist/tab.
4424 Note: Unless YouTube tells us explicitly, we do not assume it is public
4425 @param data: response
4426 """
4427 is_private = is_unlisted = None
4428 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4429 badge_labels = self._extract_badges(renderer)
4430
4431 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4432 privacy_dropdown_entries = try_get(
4433 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4434 for renderer_dict in privacy_dropdown_entries:
4435 is_selected = try_get(
4436 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4437 if not is_selected:
4438 continue
052e1350 4439 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4440 if label:
4441 badge_labels.add(label.lower())
4442 break
4443
4444 for badge_label in badge_labels:
4445 if badge_label == 'unlisted':
4446 is_unlisted = True
4447 elif badge_label == 'private':
4448 is_private = True
4449 elif badge_label == 'public':
4450 is_unlisted = is_private = False
4451 return self._availability(is_private, False, False, False, is_unlisted)
4452
4453 @staticmethod
4454 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4455 sidebar_renderer = try_get(
4456 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4457 for item in sidebar_renderer:
4458 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4459 if renderer:
4460 return renderer
4461
ac56cf38 4462 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4463 """
4464 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4465 """
5d342002 4466 browse_id = params = None
47193e02 4467 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4468 if not renderer:
4469 return
4470 menu_renderer = try_get(
4471 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4472 for menu_item in menu_renderer:
4473 if not isinstance(menu_item, dict):
358de58c 4474 continue
47193e02 4475 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4476 text = try_get(
14f25df2 4477 nav_item_renderer, lambda x: x['text']['simpleText'], str)
47193e02 4478 if not text or text.lower() != 'show unavailable videos':
4479 continue
4480 browse_endpoint = try_get(
4481 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4482 browse_id = browse_endpoint.get('browseId')
4483 params = browse_endpoint.get('params')
4484 break
5d342002 4485
11f9be09 4486 headers = self.generate_api_headers(
99e9e001 4487 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4488 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4489 query = {
4490 'params': params or 'wgYCCAA=',
4491 'browseId': browse_id or 'VL%s' % item_id
4492 }
4493 return self._extract_response(
4494 item_id=item_id, headers=headers, query=query,
fe93e2c4 4495 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4496 note='Downloading API JSON with unavailable videos')
358de58c 4497
2762dbb1 4498 @functools.cached_property
a25bca9f 4499 def skip_webpage(self):
4500 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4501
ac56cf38 4502 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 4503 webpage, data = None, None
4504 for retry in self.RetryManager(fatal=fatal):
ac56cf38 4505 try:
be5c1ae8 4506 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 4507 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4508 except ExtractorError as e:
4509 if isinstance(e.cause, network_exceptions):
14f25df2 4510 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 4511 retry.error = e
4512 continue
4513 self._error_or_warning(e, fatal=fatal)
14fdfea9 4514 break
ac56cf38 4515
be5c1ae8 4516 try:
4517 self._extract_and_report_alerts(data)
4518 except ExtractorError as e:
4519 self._error_or_warning(e, fatal=fatal)
4520 break
ac56cf38 4521
be5c1ae8 4522 # Sometimes youtube returns a webpage with incomplete ytInitialData
4523 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4524 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4525 retry.error = ExtractorError('Incomplete yt initial data received')
4526 continue
ac56cf38 4527
cd7c66cf 4528 return webpage, data
4529
a25bca9f 4530 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4531 """Use if failed to extract ytcfg (and data) from initial webpage"""
4532 if not ytcfg and self.is_authenticated:
4533 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4534 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4535 raise ExtractorError(
4536 f'{msg}. If you are not downloading private content, or '
4537 'your cookies are only for the first account and channel,'
4538 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4539 expected=True)
4540 self.report_warning(msg, only_once=True)
4541
ac56cf38 4542 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4543 data = None
a25bca9f 4544 if not self.skip_webpage:
ac56cf38 4545 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4546 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4547 # Reject webpage data if redirected to home page without explicitly requesting
4548 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4549 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4550 if (url != 'https://www.youtube.com/feed/recommended'
4551 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4552 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4553 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4554 if fatal:
4555 raise ExtractorError(msg, expected=True)
4556 self.report_warning(msg, only_once=True)
ac56cf38 4557 if not data:
a25bca9f 4558 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4559 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4560 return data, ytcfg
4561
4562 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4563 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4564 resolve_response = self._extract_response(
4565 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4566 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4567 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4568 for ep_key, ep in endpoints.items():
4569 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4570 if params:
4571 return self._extract_response(
4572 item_id=item_id, query=params, ep=ep, headers=headers,
4573 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4574 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4575 err_note = 'Failed to resolve url (does the playlist exist?)'
4576 if fatal:
4577 raise ExtractorError(err_note, expected=True)
4578 self.report_warning(err_note, item_id)
4579
a6213a49 4580 _SEARCH_PARAMS = None
4581
af5c1c55 4582 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4583 data = {'query': query}
4584 if params is NO_DEFAULT:
4585 params = self._SEARCH_PARAMS
4586 if params:
4587 data['params'] = params
16aa9ea4 4588
4589 content_keys = (
4590 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4591 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4592 # ytmusic search
4593 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4594 ('continuationContents', ),
4595 )
a25bca9f 4596 display_id = f'query "{query}"'
86e5f3ed 4597 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4598 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4599 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4600
a61fd4cf 4601 continuation_list = [None]
a25bca9f 4602 search = None
a6213a49 4603 for page_num in itertools.count(1):
a61fd4cf 4604 data.update(continuation_list[0] or {})
a25bca9f 4605 headers = self.generate_api_headers(
4606 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4607 search = self._extract_response(
a25bca9f 4608 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4609 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4610 slr_contents = traverse_obj(search, *content_keys)
4611 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4612 if not continuation_list[0]:
a6213a49 4613 break
4614
4615
4616class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4617 IE_DESC = 'YouTube Tabs'
4618 _VALID_URL = r'''(?x:
4619 https?://
4620 (?:\w+\.)?
4621 (?:
4622 youtube(?:kids)?\.com|
4623 %(invidious)s
4624 )/
4625 (?:
4626 (?P<channel_type>channel|c|user|browse)/|
4627 (?P<not_channel>
4628 feed/|hashtag/|
4629 (?:playlist|watch)\?.*?\blist=
4630 )|
4631 (?!(?:%(reserved_names)s)\b) # Direct URLs
4632 )
4633 (?P<id>[^/?\#&]+)
4634 )''' % {
4635 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4636 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4637 }
4638 IE_NAME = 'youtube:tab'
4639
4640 _TESTS = [{
4641 'note': 'playlists, multipage',
4642 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4643 'playlist_mincount': 94,
4644 'info_dict': {
4645 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4646 'title': 'Igor Kleiner - Playlists',
a6213a49 4647 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4648 'uploader': 'Igor Kleiner',
a6213a49 4649 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4650 'channel': 'Igor Kleiner',
4651 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4652 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4653 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4654 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4655 'channel_follower_count': int
a6213a49 4656 },
4657 }, {
4658 'note': 'playlists, multipage, different order',
4659 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4660 'playlist_mincount': 94,
4661 'info_dict': {
4662 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4663 'title': 'Igor Kleiner - Playlists',
a6213a49 4664 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4665 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4666 'uploader': 'Igor Kleiner',
4667 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4668 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4669 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4670 'channel': 'Igor Kleiner',
4671 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4672 'channel_follower_count': int
a6213a49 4673 },
4674 }, {
4675 'note': 'playlists, series',
4676 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4677 'playlist_mincount': 5,
4678 'info_dict': {
4679 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4680 'title': '3Blue1Brown - Playlists',
4681 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4682 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4683 'uploader': '3Blue1Brown',
976ae3ea 4684 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4685 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4686 'channel': '3Blue1Brown',
4687 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4688 'tags': ['Mathematics'],
6c73052c 4689 'channel_follower_count': int
a6213a49 4690 },
4691 }, {
4692 'note': 'playlists, singlepage',
4693 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4694 'playlist_mincount': 4,
4695 'info_dict': {
4696 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4697 'title': 'ThirstForScience - Playlists',
4698 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4699 'uploader': 'ThirstForScience',
4700 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4701 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4702 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4703 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4704 'tags': 'count:13',
4705 'channel': 'ThirstForScience',
6c73052c 4706 'channel_follower_count': int
a6213a49 4707 }
4708 }, {
4709 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4710 'only_matching': True,
4711 }, {
4712 'note': 'basic, single video playlist',
4713 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4714 'info_dict': {
4715 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4716 'uploader': 'Sergey M.',
4717 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4718 'title': 'youtube-dl public playlist',
976ae3ea 4719 'description': '',
4720 'tags': [],
4721 'view_count': int,
4722 'modified_date': '20201130',
4723 'channel': 'Sergey M.',
4724 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4725 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4726 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4727 },
4728 'playlist_count': 1,
4729 }, {
4730 'note': 'empty playlist',
4731 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4732 'info_dict': {
4733 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4734 'uploader': 'Sergey M.',
4735 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4736 'title': 'youtube-dl empty playlist',
976ae3ea 4737 'tags': [],
4738 'channel': 'Sergey M.',
4739 'description': '',
4740 'modified_date': '20160902',
4741 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4742 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4743 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4744 },
4745 'playlist_count': 0,
4746 }, {
4747 'note': 'Home tab',
4748 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4749 'info_dict': {
4750 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4751 'title': 'lex will - Home',
4752 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4753 'uploader': 'lex will',
4754 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4755 'channel': 'lex will',
4756 'tags': ['bible', 'history', 'prophesy'],
4757 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4758 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4759 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4760 'channel_follower_count': int
a6213a49 4761 },
4762 'playlist_mincount': 2,
4763 }, {
4764 'note': 'Videos tab',
4765 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4766 'info_dict': {
4767 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4768 'title': 'lex will - Videos',
4769 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4770 'uploader': 'lex will',
4771 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4772 'tags': ['bible', 'history', 'prophesy'],
4773 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4774 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4775 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4776 'channel': 'lex will',
6c73052c 4777 'channel_follower_count': int
a6213a49 4778 },
4779 'playlist_mincount': 975,
4780 }, {
4781 'note': 'Videos tab, sorted by popular',
4782 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4783 'info_dict': {
4784 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4785 'title': 'lex will - Videos',
4786 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4787 'uploader': 'lex will',
4788 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4789 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4790 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4791 'channel': 'lex will',
4792 'tags': ['bible', 'history', 'prophesy'],
4793 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4794 'channel_follower_count': int
a6213a49 4795 },
4796 'playlist_mincount': 199,
4797 }, {
4798 'note': 'Playlists tab',
4799 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4800 'info_dict': {
4801 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4802 'title': 'lex will - Playlists',
4803 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4804 'uploader': 'lex will',
4805 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4806 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4807 'channel': 'lex will',
4808 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4809 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4810 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4811 'channel_follower_count': int
a6213a49 4812 },
4813 'playlist_mincount': 17,
4814 }, {
4815 'note': 'Community tab',
4816 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4817 'info_dict': {
4818 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4819 'title': 'lex will - Community',
4820 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4821 'uploader': 'lex will',
4822 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4823 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4824 'channel': 'lex will',
4825 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4826 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4827 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4828 'channel_follower_count': int
a6213a49 4829 },
4830 'playlist_mincount': 18,
4831 }, {
4832 'note': 'Channels tab',
4833 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4834 'info_dict': {
4835 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4836 'title': 'lex will - Channels',
4837 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4838 'uploader': 'lex will',
4839 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4840 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4841 'channel': 'lex will',
4842 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4843 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4844 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4845 'channel_follower_count': int
a6213a49 4846 },
4847 'playlist_mincount': 12,
4848 }, {
4849 'note': 'Search tab',
4850 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4851 'playlist_mincount': 40,
4852 'info_dict': {
4853 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4854 'title': '3Blue1Brown - Search - linear algebra',
4855 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4856 'uploader': '3Blue1Brown',
4857 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4858 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4859 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4860 'tags': ['Mathematics'],
4861 'channel': '3Blue1Brown',
4862 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4863 'channel_follower_count': int
a6213a49 4864 },
4865 }, {
4866 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4867 'only_matching': True,
4868 }, {
4869 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4870 'only_matching': True,
4871 }, {
4872 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4873 'only_matching': True,
4874 }, {
4875 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4876 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4877 'info_dict': {
4878 'title': '29C3: Not my department',
4879 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4880 'uploader': 'Christiaan008',
4881 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4882 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4883 'tags': [],
4884 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4885 'view_count': int,
4886 'modified_date': '20150605',
4887 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4888 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4889 'channel': 'Christiaan008',
a6213a49 4890 },
4891 'playlist_count': 96,
4892 }, {
4893 'note': 'Large playlist',
4894 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4895 'info_dict': {
4896 'title': 'Uploads from Cauchemar',
4897 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4898 'uploader': 'Cauchemar',
4899 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4900 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4901 'tags': [],
4902 'modified_date': r're:\d{8}',
4903 'channel': 'Cauchemar',
4904 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4905 'view_count': int,
4906 'description': '',
4907 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4908 },
4909 'playlist_mincount': 1123,
976ae3ea 4910 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4911 }, {
4912 'note': 'even larger playlist, 8832 videos',
4913 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4914 'only_matching': True,
4915 }, {
4916 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4917 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4918 'info_dict': {
4919 'title': 'Uploads from Interstellar Movie',
4920 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4921 'uploader': 'Interstellar Movie',
4922 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4923 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4924 'tags': [],
4925 'view_count': int,
4926 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4927 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4928 'channel': 'Interstellar Movie',
4929 'description': '',
4930 'modified_date': r're:\d{8}',
a6213a49 4931 },
4932 'playlist_mincount': 21,
4933 }, {
4934 'note': 'Playlist with "show unavailable videos" button',
4935 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4936 'info_dict': {
4937 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4938 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4939 'uploader': 'Phim Siêu Nhân Nhật Bản',
4940 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4941 'view_count': int,
4942 'channel': 'Phim Siêu Nhân Nhật Bản',
4943 'tags': [],
4944 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4945 'description': '',
4946 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4947 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4948 'modified_date': r're:\d{8}',
a6213a49 4949 },
4950 'playlist_mincount': 200,
976ae3ea 4951 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4952 }, {
4953 'note': 'Playlist with unavailable videos in page 7',
4954 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4955 'info_dict': {
4956 'title': 'Uploads from BlankTV',
4957 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4958 'uploader': 'BlankTV',
4959 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4960 'channel': 'BlankTV',
4961 'channel_url': 'https://www.youtube.com/c/blanktv',
4962 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4963 'view_count': int,
4964 'tags': [],
4965 'uploader_url': 'https://www.youtube.com/c/blanktv',
4966 'modified_date': r're:\d{8}',
4967 'description': '',
a6213a49 4968 },
4969 'playlist_mincount': 1000,
976ae3ea 4970 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4971 }, {
4972 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4973 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4974 'info_dict': {
4975 'title': 'Data Analysis with Dr Mike Pound',
4976 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4977 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4978 'uploader': 'Computerphile',
4979 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4980 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4981 'tags': [],
4982 'view_count': int,
4983 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4984 'channel_url': 'https://www.youtube.com/user/Computerphile',
4985 'channel': 'Computerphile',
a6213a49 4986 },
4987 'playlist_mincount': 11,
4988 }, {
4989 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4990 'only_matching': True,
4991 }, {
4992 'note': 'Playlist URL that does not actually serve a playlist',
4993 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4994 'info_dict': {
4995 'id': 'FqZTN594JQw',
4996 'ext': 'webm',
4997 'title': "Smiley's People 01 detective, Adventure Series, Action",
4998 'uploader': 'STREEM',
4999 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5000 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5001 'upload_date': '20150526',
5002 'license': 'Standard YouTube License',
5003 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5004 'categories': ['People & Blogs'],
5005 'tags': list,
5006 'view_count': int,
5007 'like_count': int,
a6213a49 5008 },
5009 'params': {
5010 'skip_download': True,
5011 },
5012 'skip': 'This video is not available.',
5013 'add_ie': [YoutubeIE.ie_key()],
5014 }, {
5015 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5016 'only_matching': True,
5017 }, {
5018 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5019 'only_matching': True,
5020 }, {
5021 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5022 'info_dict': {
12a1b225 5023 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5024 'ext': 'mp4',
976ae3ea 5025 'title': str,
a6213a49 5026 'uploader': 'Sky News',
5027 'uploader_id': 'skynews',
5028 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5029 'upload_date': r're:\d{8}',
976ae3ea 5030 'description': str,
a6213a49 5031 'categories': ['News & Politics'],
5032 'tags': list,
5033 'like_count': int,
6c73052c 5034 'release_timestamp': 1642502819,
976ae3ea 5035 'channel': 'Sky News',
5036 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5037 'age_limit': 0,
5038 'view_count': int,
6c73052c 5039 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 5040 'playable_in_embed': True,
6c73052c 5041 'release_date': '20220118',
976ae3ea 5042 'availability': 'public',
5043 'live_status': 'is_live',
5044 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 5045 'channel_follower_count': int
a6213a49 5046 },
5047 'params': {
5048 'skip_download': True,
5049 },
976ae3ea 5050 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5051 }, {
5052 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5053 'info_dict': {
5054 'id': 'a48o2S1cPoo',
5055 'ext': 'mp4',
5056 'title': 'The Young Turks - Live Main Show',
5057 'uploader': 'The Young Turks',
5058 'uploader_id': 'TheYoungTurks',
5059 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5060 'upload_date': '20150715',
5061 'license': 'Standard YouTube License',
5062 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5063 'categories': ['News & Politics'],
5064 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5065 'like_count': int,
a6213a49 5066 },
5067 'params': {
5068 'skip_download': True,
5069 },
5070 'only_matching': True,
5071 }, {
5072 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5073 'only_matching': True,
5074 }, {
5075 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5076 'only_matching': True,
5077 }, {
5078 'note': 'A channel that is not live. Should raise error',
5079 'url': 'https://www.youtube.com/user/numberphile/live',
5080 'only_matching': True,
5081 }, {
5082 'url': 'https://www.youtube.com/feed/trending',
5083 'only_matching': True,
5084 }, {
5085 'url': 'https://www.youtube.com/feed/library',
5086 'only_matching': True,
5087 }, {
5088 'url': 'https://www.youtube.com/feed/history',
5089 'only_matching': True,
5090 }, {
5091 'url': 'https://www.youtube.com/feed/subscriptions',
5092 'only_matching': True,
5093 }, {
5094 'url': 'https://www.youtube.com/feed/watch_later',
5095 'only_matching': True,
5096 }, {
5097 'note': 'Recommended - redirects to home page.',
5098 'url': 'https://www.youtube.com/feed/recommended',
5099 'only_matching': True,
5100 }, {
5101 'note': 'inline playlist with not always working continuations',
5102 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5103 'only_matching': True,
5104 }, {
5105 'url': 'https://www.youtube.com/course',
5106 'only_matching': True,
5107 }, {
5108 'url': 'https://www.youtube.com/zsecurity',
5109 'only_matching': True,
5110 }, {
5111 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5112 'only_matching': True,
5113 }, {
5114 'url': 'https://www.youtube.com/TheYoungTurks/live',
5115 'only_matching': True,
5116 }, {
5117 'url': 'https://www.youtube.com/hashtag/cctv9',
5118 'info_dict': {
5119 'id': 'cctv9',
5120 'title': '#cctv9',
976ae3ea 5121 'tags': [],
a6213a49 5122 },
5123 'playlist_mincount': 350,
5124 }, {
5125 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5126 'only_matching': True,
5127 }, {
5128 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5129 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5130 'only_matching': True
5131 }, {
5132 'note': '/browse/ should redirect to /channel/',
5133 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5134 'only_matching': True
5135 }, {
5136 'note': 'VLPL, should redirect to playlist?list=PL...',
5137 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5138 'info_dict': {
5139 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5140 'uploader': 'NoCopyrightSounds',
5141 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5142 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5143 'title': 'NCS : All Releases 💿',
976ae3ea 5144 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5145 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5146 'modified_date': r're:\d{8}',
5147 'view_count': int,
5148 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5149 'tags': [],
5150 'channel': 'NoCopyrightSounds',
a6213a49 5151 },
5152 'playlist_mincount': 166,
976ae3ea 5153 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5154 }, {
5155 'note': 'Topic, should redirect to playlist?list=UU...',
5156 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5157 'info_dict': {
5158 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5159 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5160 'title': 'Uploads from Royalty Free Music - Topic',
5161 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5162 'tags': [],
5163 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5164 'channel': 'Royalty Free Music - Topic',
5165 'view_count': int,
5166 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5167 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5168 'modified_date': r're:\d{8}',
5169 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5170 'description': '',
a6213a49 5171 },
5172 'expected_warnings': [
a6213a49 5173 'The URL does not have a videos tab',
976ae3ea 5174 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5175 ],
5176 'playlist_mincount': 101,
5177 }, {
5178 'note': 'Topic without a UU playlist',
5179 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5180 'info_dict': {
5181 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5182 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5183 'tags': [],
a6213a49 5184 },
5185 'expected_warnings': [
976ae3ea 5186 'the playlist redirect gave error',
a6213a49 5187 ],
5188 'playlist_mincount': 9,
5189 }, {
5190 'note': 'Youtube music Album',
5191 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5192 'info_dict': {
5193 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5194 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5195 'tags': [],
5196 'view_count': int,
5197 'description': '',
5198 'availability': 'unlisted',
5199 'modified_date': r're:\d{8}',
a6213a49 5200 },
5201 'playlist_count': 50,
5202 }, {
5203 'note': 'unlisted single video playlist',
5204 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5205 'info_dict': {
5206 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5207 'uploader': 'colethedj',
5208 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5209 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5210 'availability': 'unlisted',
5211 'tags': [],
12a1b225 5212 'modified_date': '20220418',
976ae3ea 5213 'channel': 'colethedj',
5214 'view_count': int,
5215 'description': '',
5216 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5217 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5218 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5219 },
5220 'playlist_count': 1,
5221 }, {
5222 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5223 'url': 'https://www.youtube.com/feed/recommended',
5224 'info_dict': {
5225 'id': 'recommended',
5226 'title': 'recommended',
6c73052c 5227 'tags': [],
a6213a49 5228 },
5229 'playlist_mincount': 50,
5230 'params': {
5231 'skip_download': True,
5232 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5233 },
5234 }, {
5235 'note': 'API Fallback: /videos tab, sorted by oldest first',
5236 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5237 'info_dict': {
5238 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5239 'title': 'Cody\'sLab - Videos',
5240 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5241 'uploader': 'Cody\'sLab',
5242 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5243 'channel': 'Cody\'sLab',
5244 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5245 'tags': [],
5246 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5247 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5248 'channel_follower_count': int
a6213a49 5249 },
5250 'playlist_mincount': 650,
5251 'params': {
5252 'skip_download': True,
5253 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5254 },
5255 }, {
5256 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5257 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5258 'info_dict': {
5259 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5260 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5261 'title': 'Uploads from Royalty Free Music - Topic',
5262 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5263 'modified_date': r're:\d{8}',
5264 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5265 'description': '',
5266 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5267 'tags': [],
5268 'channel': 'Royalty Free Music - Topic',
5269 'view_count': int,
5270 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5271 },
5272 'expected_warnings': [
976ae3ea 5273 'does not have a videos tab',
5274 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5275 ],
5276 'playlist_mincount': 101,
5277 'params': {
5278 'skip_download': True,
5279 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5280 },
7c219ea6 5281 }, {
5282 'note': 'non-standard redirect to regional channel',
5283 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5284 'only_matching': True
61d3665d 5285 }, {
5286 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5287 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5288 'info_dict': {
5289 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5290 'modified_date': '20220407',
5291 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5292 'tags': [],
5293 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5294 'uploader': 'pukkandan',
5295 'availability': 'unlisted',
5296 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5297 'channel': 'pukkandan',
5298 'description': 'Test for collaborative playlist',
5299 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5300 'view_count': int,
61d3665d 5301 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5302 },
5303 'playlist_mincount': 2
a6213a49 5304 }]
5305
5306 @classmethod
5307 def suitable(cls, url):
86e5f3ed 5308 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5309
64f36541 5310 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5311
182bda88 5312 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5313 def _real_extract(self, url, smuggled_data):
cd7c66cf 5314 item_id = self._match_id(url)
14f25df2 5315 url = urllib.parse.urlunparse(
5316 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5317 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5318
fe03a6cd 5319 def get_mobj(url):
37e57a9f 5320 mobj = self._URL_RE.match(url).groupdict()
07cce701 5321 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5322 return mobj
5323
37e57a9f 5324 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5325 # Youtube returns incomplete data if tabname is not lower case
5326 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5327 if is_channel:
5328 if smuggled_data.get('is_music_url'):
37e57a9f 5329 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5330 item_id = item_id[2:]
37e57a9f 5331 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5332 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5333 mdata = self._extract_tab_endpoint(
37e57a9f 5334 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5335 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
14f25df2 5336 get_all=False, expected_type=str)
ac56cf38 5337 if not murl:
37e57a9f 5338 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5339 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5340 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5341 pre = f'https://www.youtube.com/channel/{item_id}'
5342
64f36541 5343 original_tab_name = tab
fe03a6cd 5344 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5345 # Home URLs should redirect to /videos/
37e57a9f 5346 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5347 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5348 tab = '/videos'
5349
5350 url = ''.join((pre, tab, post))
5351 mobj = get_mobj(url)
cd7c66cf 5352
5353 # Handle both video/playlist URLs
201c1459 5354 qs = parse_qs(url)
86e5f3ed 5355 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5356
fe03a6cd 5357 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5358 if not playlist_id:
fe03a6cd 5359 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5360 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5361 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5362 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5363 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5364 mobj = get_mobj(url)
cd7c66cf 5365
5366 if video_id and playlist_id:
a06916d9 5367 if self.get_param('noplaylist'):
37e57a9f 5368 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5369 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5370 ie=YoutubeIE.ie_key(), video_id=video_id)
5371 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5372
ac56cf38 5373 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5374
7c219ea6 5375 # YouTube may provide a non-standard redirect to the regional channel
5376 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5377 redirect_url = traverse_obj(
5378 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5379 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5380 redirect_url = ''.join((
5381 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5382 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5383 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5384
37e57a9f 5385 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5386 if tabs:
5387 selected_tab = self._extract_selected_tab(tabs)
64f36541 5388 selected_tab_name = selected_tab.get('title', '').lower()
5389 if selected_tab_name == 'home':
5390 selected_tab_name = 'featured'
5391 requested_tab_name = mobj['tab'][1:]
09f1580e 5392 if 'no-youtube-channel-redirect' not in compat_opts:
693f0600 5393 if requested_tab_name == 'live': # Live tab should have redirected to the video
5394 raise UserNotLive(video_id=mobj['id'])
64f36541 5395 if requested_tab_name not in ('', selected_tab_name):
5396 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5397 if not original_tab_name:
5398 if item_id[:2] == 'UC':
5399 # Topic channels don't have /videos. Use the equivalent playlist instead
5400 pl_id = f'UU{item_id[2:]}'
5401 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5402 try:
5403 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5404 except ExtractorError:
5405 redirect_warning += ' and the playlist redirect gave error'
5406 else:
5407 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5408 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5409 if selected_tab_name and selected_tab_name != requested_tab_name:
5410 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5411 else:
5412 raise ExtractorError(redirect_warning, expected=True)
18db7548 5413
37e57a9f 5414 if redirect_warning:
64f36541 5415 self.to_screen(redirect_warning)
37e57a9f 5416 self.write_debug(f'Final URL: {url}')
18db7548 5417
358de58c 5418 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5419 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5420 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5421 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5422 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5423 if tabs:
ac56cf38 5424 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5425
37e57a9f 5426 playlist = traverse_obj(
5427 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5428 if playlist:
ac56cf38 5429 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5430
37e57a9f 5431 video_id = traverse_obj(
5432 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5433 if video_id:
09f1580e 5434 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5435 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5436 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5437 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5438
8bdd16b4 5439 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5440
c5e8d7af 5441
8bdd16b4 5442class YoutubePlaylistIE(InfoExtractor):
96565c7e 5443 IE_DESC = 'YouTube playlists'
8bdd16b4 5444 _VALID_URL = r'''(?x)(?:
5445 (?:https?://)?
5446 (?:\w+\.)?
5447 (?:
5448 (?:
5449 youtube(?:kids)?\.com|
d9190e44 5450 %(invidious)s
8bdd16b4 5451 )
5452 /.*?\?.*?\blist=
5453 )?
5454 (?P<id>%(playlist_id)s)
d9190e44
RH
5455 )''' % {
5456 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5457 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5458 }
8bdd16b4 5459 IE_NAME = 'youtube:playlist'
cdc628a4 5460 _TESTS = [{
8bdd16b4 5461 'note': 'issue #673',
5462 'url': 'PLBB231211A4F62143',
cdc628a4 5463 'info_dict': {
8bdd16b4 5464 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5465 'id': 'PLBB231211A4F62143',
976ae3ea 5466 'uploader': 'Wickman',
8bdd16b4 5467 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5468 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5469 'view_count': int,
5470 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5471 'modified_date': r're:\d{8}',
5472 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5473 'channel': 'Wickman',
5474 'tags': [],
5475 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5476 },
5477 'playlist_mincount': 29,
5478 }, {
5479 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5480 'info_dict': {
5481 'title': 'YDL_safe_search',
5482 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5483 },
5484 'playlist_count': 2,
5485 'skip': 'This playlist is private',
9558dcec 5486 }, {
8bdd16b4 5487 'note': 'embedded',
5488 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5489 'playlist_count': 4,
9558dcec 5490 'info_dict': {
8bdd16b4 5491 'title': 'JODA15',
5492 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5493 'uploader': 'milan',
5494 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5495 'description': '',
5496 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5497 'tags': [],
5498 'modified_date': '20140919',
5499 'view_count': int,
5500 'channel': 'milan',
5501 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5502 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5503 },
5504 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5505 }, {
8bdd16b4 5506 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 5507 'playlist_mincount': 455,
8bdd16b4 5508 'info_dict': {
5509 'title': '2018 Chinese New Singles (11/6 updated)',
5510 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5511 'uploader': 'LBK',
5512 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5513 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5514 'channel': 'LBK',
5515 'view_count': int,
5516 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5517 'tags': [],
5518 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5519 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5520 'modified_date': r're:\d{8}',
5521 },
5522 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5523 }, {
29f7c58a 5524 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5525 'only_matching': True,
5526 }, {
5527 # music album playlist
5528 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5529 'only_matching': True,
5530 }]
5531
5532 @classmethod
5533 def suitable(cls, url):
201c1459 5534 if YoutubeTabIE.suitable(url):
5535 return False
49a57e70 5536 from ..utils import parse_qs
201c1459 5537 qs = parse_qs(url)
5538 if qs.get('v', [None])[0]:
5539 return False
86e5f3ed 5540 return super().suitable(url)
29f7c58a 5541
5542 def _real_extract(self, url):
5543 playlist_id = self._match_id(url)
46953e7e 5544 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5545 url = update_url_query(
5546 'https://www.youtube.com/playlist',
5547 parse_qs(url) or {'list': playlist_id})
5548 if is_music_url:
5549 url = smuggle_url(url, {'is_music_url': True})
5550 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5551
5552
5553class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5554 IE_DESC = 'youtu.be'
29f7c58a 5555 _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}
5556 _TESTS = [{
8bdd16b4 5557 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5558 'info_dict': {
5559 'id': 'yeWKywCrFtk',
5560 'ext': 'mp4',
5561 'title': 'Small Scale Baler and Braiding Rugs',
5562 'uploader': 'Backus-Page House Museum',
5563 'uploader_id': 'backuspagemuseum',
5564 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5565 'upload_date': '20161008',
5566 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5567 'categories': ['Nonprofits & Activism'],
5568 'tags': list,
5569 'like_count': int,
976ae3ea 5570 'age_limit': 0,
5571 'playable_in_embed': True,
5572 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5573 'channel': 'Backus-Page House Museum',
5574 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5575 'live_status': 'not_live',
5576 'view_count': int,
5577 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5578 'availability': 'public',
5579 'duration': 59,
12a1b225
A
5580 'comment_count': int,
5581 'channel_follower_count': int
8bdd16b4 5582 },
5583 'params': {
5584 'noplaylist': True,
5585 'skip_download': True,
5586 },
39e7107d 5587 }, {
8bdd16b4 5588 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5589 'only_matching': True,
cdc628a4
PH
5590 }]
5591
8bdd16b4 5592 def _real_extract(self, url):
5ad28e7f 5593 mobj = self._match_valid_url(url)
29f7c58a 5594 video_id = mobj.group('id')
5595 playlist_id = mobj.group('playlist_id')
8bdd16b4 5596 return self.url_result(
29f7c58a 5597 update_url_query('https://www.youtube.com/watch', {
5598 'v': video_id,
5599 'list': playlist_id,
5600 'feature': 'youtu.be',
5601 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5602
5603
b6ce9bb0 5604class YoutubeLivestreamEmbedIE(InfoExtractor):
5605 IE_DESC = 'YouTube livestream embeds'
5606 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5607 _TESTS = [{
5608 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5609 'only_matching': True,
5610 }]
5611
5612 def _real_extract(self, url):
5613 channel_id = self._match_id(url)
5614 return self.url_result(
5615 f'https://www.youtube.com/channel/{channel_id}/live',
5616 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5617
5618
8bdd16b4 5619class YoutubeYtUserIE(InfoExtractor):
96565c7e 5620 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5621 IE_NAME = 'youtube:user'
8bdd16b4 5622 _VALID_URL = r'ytuser:(?P<id>.+)'
5623 _TESTS = [{
5624 'url': 'ytuser:phihag',
5625 'only_matching': True,
5626 }]
5627
5628 def _real_extract(self, url):
5629 user_id = self._match_id(url)
5630 return self.url_result(
c586f9e8 5631 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5632 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5633
b05654f0 5634
3d3dddc9 5635class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5636 IE_NAME = 'youtube:favorites'
96565c7e 5637 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5638 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5639 _LOGIN_REQUIRED = True
5640 _TESTS = [{
5641 'url': ':ytfav',
5642 'only_matching': True,
5643 }, {
5644 'url': ':ytfavorites',
5645 'only_matching': True,
5646 }]
5647
5648 def _real_extract(self, url):
5649 return self.url_result(
5650 'https://www.youtube.com/playlist?list=LL',
5651 ie=YoutubeTabIE.ie_key())
5652
5653
ca5300c7 5654class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
5655 IE_NAME = 'youtube:notif'
5656 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5657 _VALID_URL = r':ytnotif(?:ication)?s?'
5658 _LOGIN_REQUIRED = True
5659 _TESTS = [{
5660 'url': ':ytnotif',
5661 'only_matching': True,
5662 }, {
5663 'url': ':ytnotifications',
5664 'only_matching': True,
5665 }]
5666
5667 def _extract_notification_menu(self, response, continuation_list):
5668 notification_list = traverse_obj(
5669 response,
5670 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5671 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5672 expected_type=list) or []
5673 continuation_list[0] = None
5674 for item in notification_list:
5675 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
5676 if entry:
5677 yield entry
5678 continuation = item.get('continuationItemRenderer')
5679 if continuation:
5680 continuation_list[0] = continuation
5681
5682 def _extract_notification_renderer(self, notification):
5683 video_id = traverse_obj(
5684 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
5685 url = f'https://www.youtube.com/watch?v={video_id}'
5686 channel_id = None
5687 if not video_id:
5688 browse_ep = traverse_obj(
5689 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
5690 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
5691 post_id = self._search_regex(
5692 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
5693 'post id', default=None)
5694 if not channel_id or not post_id:
5695 return
5696 # The direct /post url redirects to this in the browser
5697 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5698
5699 channel = traverse_obj(
5700 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5701 expected_type=str)
c7a7baaa 5702 notification_title = self._get_text(notification, 'shortMessage')
5703 if notification_title:
5704 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
5705 # TODO: handle recommended videos
ca5300c7 5706 title = self._search_regex(
c7a7baaa 5707 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 5708 'video title', default=None)
ca5300c7 5709 upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d')
5710 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
5711 else None)
5712 return {
5713 '_type': 'url',
5714 'url': url,
5715 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
5716 'video_id': video_id,
5717 'title': title,
5718 'channel_id': channel_id,
5719 'channel': channel,
5720 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5721 'upload_date': upload_date,
5722 }
5723
5724 def _notification_menu_entries(self, ytcfg):
5725 continuation_list = [None]
5726 response = None
5727 for page in itertools.count(1):
5728 ctoken = traverse_obj(
5729 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
5730 response = self._extract_response(
5731 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
5732 ep='notification/get_notification_menu', check_get_keys='actions',
5733 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
5734 yield from self._extract_notification_menu(response, continuation_list)
5735 if not continuation_list[0]:
5736 break
5737
5738 def _real_extract(self, url):
5739 display_id = 'notifications'
5740 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
5741 self._report_playlist_authcheck(ytcfg)
5742 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
5743
5744
a6213a49 5745class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5746 IE_DESC = 'YouTube search'
78caa52a 5747 IE_NAME = 'youtube:search'
b05654f0 5748 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5749 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5750 _TESTS = [{
5751 'url': 'ytsearch5:youtube-dl test video',
5752 'playlist_count': 5,
5753 'info_dict': {
5754 'id': 'youtube-dl test video',
5755 'title': 'youtube-dl test video',
5756 }
5757 }]
b05654f0 5758
a61fd4cf 5759
5f7cb91a 5760class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5761 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5762 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5763 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5764 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5765 _TESTS = [{
5766 'url': 'ytsearchdate5:youtube-dl test video',
5767 'playlist_count': 5,
5768 'info_dict': {
5769 'id': 'youtube-dl test video',
5770 'title': 'youtube-dl test video',
5771 }
5772 }]
75dff0ee 5773
c9ae7b95 5774
a6213a49 5775class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5776 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5777 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5778 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5779 _TESTS = [{
5780 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5781 'playlist_mincount': 5,
5782 'info_dict': {
11f9be09 5783 'id': 'youtube-dl test video',
3462ffa8 5784 'title': 'youtube-dl test video',
5785 }
a61fd4cf 5786 }, {
5787 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5788 'playlist_mincount': 5,
5789 'info_dict': {
5790 'id': 'python',
5791 'title': 'python',
5792 }
ad210f4f 5793 }, {
5794 'url': 'https://www.youtube.com/results?search_query=%23cats',
5795 'playlist_mincount': 1,
5796 'info_dict': {
5797 'id': '#cats',
5798 'title': '#cats',
12a1b225
A
5799 # The test suite does not have support for nested playlists
5800 # 'entries': [{
5801 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5802 # 'title': '#cats',
5803 # }],
ad210f4f 5804 },
3462ffa8 5805 }, {
5806 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5807 'only_matching': True,
5808 }]
5809
5810 def _real_extract(self, url):
4dfbf869 5811 qs = parse_qs(url)
386e1dd9 5812 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5813 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5814
5815
16aa9ea4 5816class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
455a15e2 5817 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
16aa9ea4 5818 IE_NAME = 'youtube:music:search_url'
5819 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5820 _TESTS = [{
5821 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5822 'playlist_count': 16,
5823 'info_dict': {
5824 'id': 'royalty free music',
5825 'title': 'royalty free music',
5826 }
5827 }, {
5828 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5829 'playlist_mincount': 30,
5830 'info_dict': {
5831 'id': 'royalty free music - songs',
5832 'title': 'royalty free music - songs',
5833 },
5834 'params': {'extract_flat': 'in_playlist'}
5835 }, {
5836 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5837 'playlist_mincount': 30,
5838 'info_dict': {
5839 'id': 'royalty free music - community playlists',
5840 'title': 'royalty free music - community playlists',
5841 },
5842 'params': {'extract_flat': 'in_playlist'}
5843 }]
5844
5845 _SECTIONS = {
5846 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5847 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5848 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5849 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5850 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5851 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5852 }
5853
5854 def _real_extract(self, url):
5855 qs = parse_qs(url)
5856 query = (qs.get('search_query') or qs.get('q'))[0]
5857 params = qs.get('sp', (None,))[0]
5858 if params:
5859 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5860 else:
ac668111 5861 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 5862 params = self._SECTIONS.get(section)
5863 if not params:
5864 section = None
5865 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5866 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5867
5868
182bda88 5869class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5870 """
25f14e9f 5871 Base class for feed extractors
82d02080 5872 Subclasses must re-define the _FEED_NAME property.
d7ae0639 5873 """
b2e8bc1b 5874 _LOGIN_REQUIRED = True
82d02080 5875 _FEED_NAME = 'feeds'
a25bca9f 5876
5877 def _real_initialize(self):
5878 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 5879
82d02080 5880 @classproperty
d7ae0639 5881 def IE_NAME(self):
82d02080 5882 return f'youtube:{self._FEED_NAME}'
04cc9617 5883
3853309f 5884 def _real_extract(self, url):
3d3dddc9 5885 return self.url_result(
182bda88 5886 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5887
5888
ef2f3c7f 5889class YoutubeWatchLaterIE(InfoExtractor):
5890 IE_NAME = 'youtube:watchlater'
96565c7e 5891 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5892 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5893 _TESTS = [{
8bdd16b4 5894 'url': ':ytwatchlater',
bc7a9cd8
S
5895 'only_matching': True,
5896 }]
25f14e9f
S
5897
5898 def _real_extract(self, url):
ef2f3c7f 5899 return self.url_result(
5900 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5901
5902
25f14e9f 5903class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5904 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5905 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5906 _FEED_NAME = 'recommended'
45db527f 5907 _LOGIN_REQUIRED = False
3d3dddc9 5908 _TESTS = [{
5909 'url': ':ytrec',
5910 'only_matching': True,
5911 }, {
5912 'url': ':ytrecommended',
5913 'only_matching': True,
5914 }, {
5915 'url': 'https://youtube.com',
5916 'only_matching': True,
5917 }]
1ed5b5c9 5918
1ed5b5c9 5919
25f14e9f 5920class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5921 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5922 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5923 _FEED_NAME = 'subscriptions'
3d3dddc9 5924 _TESTS = [{
5925 'url': ':ytsubs',
5926 'only_matching': True,
5927 }, {
5928 'url': ':ytsubscriptions',
5929 'only_matching': True,
5930 }]
1ed5b5c9 5931
1ed5b5c9 5932
25f14e9f 5933class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5934 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5935 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5936 _FEED_NAME = 'history'
3d3dddc9 5937 _TESTS = [{
5938 'url': ':ythistory',
5939 'only_matching': True,
5940 }]
1ed5b5c9
JMF
5941
5942
6e634cbe 5943class YoutubeStoriesIE(InfoExtractor):
5944 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
5945 IE_NAME = 'youtube:stories'
5946 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
5947 _TESTS = [{
5948 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
5949 'only_matching': True,
5950 }]
5951
5952 def _real_extract(self, url):
5953 playlist_id = f'RLTD{self._match_id(url)}'
5954 return self.url_result(
5955 f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
5956 ie=YoutubeTabIE, video_id=playlist_id)
5957
5958
15870e90
PH
5959class YoutubeTruncatedURLIE(InfoExtractor):
5960 IE_NAME = 'youtube:truncated_url'
5961 IE_DESC = False # Do not list
975d35db 5962 _VALID_URL = r'''(?x)
b95aab84
PH
5963 (?:https?://)?
5964 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5965 (?:watch\?(?:
c4808c60 5966 feature=[a-z_]+|
b95aab84
PH
5967 annotation_id=annotation_[^&]+|
5968 x-yt-cl=[0-9]+|
c1708b89 5969 hl=[^&]*|
287be8c6 5970 t=[0-9]+
b95aab84
PH
5971 )?
5972 |
5973 attribution_link\?a=[^&]+
5974 )
5975 $
975d35db 5976 '''
15870e90 5977
c4808c60 5978 _TESTS = [{
2d3d2997 5979 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5980 'only_matching': True,
dc2fc736 5981 }, {
2d3d2997 5982 'url': 'https://www.youtube.com/watch?',
dc2fc736 5983 'only_matching': True,
b95aab84
PH
5984 }, {
5985 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5986 'only_matching': True,
5987 }, {
5988 'url': 'https://www.youtube.com/watch?feature=foo',
5989 'only_matching': True,
c1708b89
PH
5990 }, {
5991 'url': 'https://www.youtube.com/watch?hl=en-GB',
5992 'only_matching': True,
287be8c6
PH
5993 }, {
5994 'url': 'https://www.youtube.com/watch?t=2372',
5995 'only_matching': True,
c4808c60
PH
5996 }]
5997
15870e90
PH
5998 def _real_extract(self, url):
5999 raise ExtractorError(
78caa52a
PH
6000 'Did you forget to quote the URL? Remember that & is a meta '
6001 'character in most shells, so you want to put the URL in quotes, '
3867038a 6002 'like youtube-dl '
2d3d2997 6003 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 6004 ' or simply youtube-dl BaW_jenozKc .',
15870e90 6005 expected=True)
772fd5cc
PH
6006
6007
471d0367 6008class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6009 IE_NAME = 'youtube:clip'
471d0367 6010 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6011 _TESTS = [{
6012 # FIXME: Other metadata should be extracted from the clip, not from the base video
6013 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6014 'info_dict': {
6015 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6016 'ext': 'mp4',
6017 'section_start': 29.0,
6018 'section_end': 39.7,
6019 'duration': 10.7,
12a1b225
A
6020 'age_limit': 0,
6021 'availability': 'public',
6022 'categories': ['Gaming'],
6023 'channel': 'Scott The Woz',
6024 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6025 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6026 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6027 'like_count': int,
6028 'playable_in_embed': True,
6029 'tags': 'count:17',
6030 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6031 'title': 'Mobile Games on Console - Scott The Woz',
6032 'upload_date': '20210920',
6033 'uploader': 'Scott The Woz',
6034 'uploader_id': 'scottthewoz',
6035 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6036 'view_count': int,
6037 'live_status': 'not_live',
6038 'channel_follower_count': int
471d0367 6039 }
6040 }]
3cd786db 6041
6042 def _real_extract(self, url):
471d0367 6043 clip_id = self._match_id(url)
6044 _, data = self._extract_webpage(url, clip_id)
6045
6046 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6047 if not video_id:
6048 raise ExtractorError('Unable to find video ID')
6049
6050 clip_data = traverse_obj(data, (
6051 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6052 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6053 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6054 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6055
6056 return {
6057 '_type': 'url_transparent',
6058 'url': f'https://www.youtube.com/watch?v={video_id}',
6059 'ie_key': YoutubeIE.ie_key(),
6060 'id': clip_id,
6061 'section_start': int(clip_data['startTimeMs']) / 1000,
6062 'section_end': int(clip_data['endTimeMs']) / 1000,
6063 }
3cd786db 6064
6065
772fd5cc
PH
6066class YoutubeTruncatedIDIE(InfoExtractor):
6067 IE_NAME = 'youtube:truncated_id'
6068 IE_DESC = False # Do not list
b95aab84 6069 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6070
6071 _TESTS = [{
6072 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6073 'only_matching': True,
6074 }]
6075
6076 def _real_extract(self, url):
6077 video_id = self._match_id(url)
6078 raise ExtractorError(
86e5f3ed 6079 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6080 expected=True)