]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[extractor] Support multiple archive ids for one video (#4307)
[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,
358de58c 31 error_to_compat_str,
2d30521a 32 float_or_none,
11f9be09 33 format_field,
ff91cf74 34 get_first,
dd27fd17 35 int_or_none,
641ad5d8 36 is_html,
34921b43 37 join_nonempty,
48416bc4 38 js_to_json,
94278f72 39 mimetype2ext,
9c0d7f49 40 network_exceptions,
11f9be09 41 orderedSet,
6310acf5 42 parse_codecs,
49bd8c66 43 parse_count,
7c80519c 44 parse_duration,
7ea65411 45 parse_iso8601,
4dfbf869 46 parse_qs,
dca3ff4a 47 qualities,
c0ac49bc 48 remove_end,
3995d37d 49 remove_start,
cf7e015f 50 smuggle_url,
dbdaaa23 51 str_or_none,
c93d53f5 52 str_to_int,
f3aa3c3f 53 strftime_or_none,
7c365c21 54 traverse_obj,
556dbe7f 55 try_get,
c5e8d7af
PH
56 unescapeHTML,
57 unified_strdate,
f0d785d3 58 unified_timestamp,
cf7e015f 59 unsmuggle_url,
8bdd16b4 60 update_url_query,
21c340b8 61 url_or_none,
fe93e2c4 62 urljoin,
7c365c21 63 variadic,
c5e8d7af
PH
64)
65
962ffcf8 66# any clients starting with _ cannot be explicitly requested by the user
000c15a4 67INNERTUBE_CLIENTS = {
68 'web': {
69 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
70 'INNERTUBE_CONTEXT': {
71 'client': {
72 'clientName': 'WEB',
18c7683d 73 'clientVersion': '2.20211221.00.00',
000c15a4 74 }
75 },
76 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
77 },
78 'web_embedded': {
79 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
80 'INNERTUBE_CONTEXT': {
81 'client': {
82 'clientName': 'WEB_EMBEDDED_PLAYER',
18c7683d 83 'clientVersion': '1.20211215.00.01',
000c15a4 84 },
85 },
86 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
87 },
88 'web_music': {
89 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
90 'INNERTUBE_HOST': 'music.youtube.com',
91 'INNERTUBE_CONTEXT': {
92 'client': {
93 'clientName': 'WEB_REMIX',
18c7683d 94 'clientVersion': '1.20211213.00.00',
000c15a4 95 }
96 },
97 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
98 },
e7e94f2a 99 'web_creator': {
18c7683d 100 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
101 'INNERTUBE_CONTEXT': {
102 'client': {
103 'clientName': 'WEB_CREATOR',
18c7683d 104 'clientVersion': '1.20211220.02.00',
e7e94f2a
D
105 }
106 },
107 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
108 },
000c15a4 109 'android': {
18c7683d 110 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 111 'INNERTUBE_CONTEXT': {
112 'client': {
113 'clientName': 'ANDROID',
18c7683d 114 'clientVersion': '16.49',
000c15a4 115 }
116 },
117 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 118 'REQUIRE_JS_PLAYER': False
000c15a4 119 },
120 'android_embedded': {
18c7683d 121 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 122 'INNERTUBE_CONTEXT': {
123 'client': {
124 'clientName': 'ANDROID_EMBEDDED_PLAYER',
18c7683d 125 'clientVersion': '16.49',
000c15a4 126 },
127 },
b6de707d 128 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
129 'REQUIRE_JS_PLAYER': False
000c15a4 130 },
131 'android_music': {
18c7683d 132 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 133 'INNERTUBE_CONTEXT': {
134 'client': {
135 'clientName': 'ANDROID_MUSIC',
18c7683d 136 'clientVersion': '4.57',
000c15a4 137 }
138 },
139 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 140 'REQUIRE_JS_PLAYER': False
000c15a4 141 },
e7e94f2a 142 'android_creator': {
18c7683d 143 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
144 'INNERTUBE_CONTEXT': {
145 'client': {
146 'clientName': 'ANDROID_CREATOR',
18c7683d 147 'clientVersion': '21.47',
e7e94f2a
D
148 },
149 },
b6de707d 150 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
151 'REQUIRE_JS_PLAYER': False
e7e94f2a 152 },
18c7683d 153 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
154 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 155 'ios': {
18c7683d 156 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 157 'INNERTUBE_CONTEXT': {
158 'client': {
159 'clientName': 'IOS',
18c7683d 160 'clientVersion': '16.46',
161 'deviceModel': 'iPhone14,3',
000c15a4 162 }
163 },
b6de707d 164 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
165 'REQUIRE_JS_PLAYER': False
000c15a4 166 },
167 'ios_embedded': {
000c15a4 168 'INNERTUBE_CONTEXT': {
169 'client': {
170 'clientName': 'IOS_MESSAGES_EXTENSION',
18c7683d 171 'clientVersion': '16.46',
172 'deviceModel': 'iPhone14,3',
000c15a4 173 },
174 },
b6de707d 175 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
176 'REQUIRE_JS_PLAYER': False
000c15a4 177 },
178 'ios_music': {
18c7683d 179 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 180 'INNERTUBE_CONTEXT': {
181 'client': {
182 'clientName': 'IOS_MUSIC',
18c7683d 183 'clientVersion': '4.57',
000c15a4 184 },
185 },
b6de707d 186 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
187 'REQUIRE_JS_PLAYER': False
000c15a4 188 },
e7e94f2a
D
189 'ios_creator': {
190 'INNERTUBE_CONTEXT': {
191 'client': {
192 'clientName': 'IOS_CREATOR',
18c7683d 193 'clientVersion': '21.47',
e7e94f2a
D
194 },
195 },
b6de707d 196 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
197 'REQUIRE_JS_PLAYER': False
e7e94f2a 198 },
3619f78d 199 # mweb has 'ultralow' formats
200 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 201 'mweb': {
18c7683d 202 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 203 'INNERTUBE_CONTEXT': {
204 'client': {
205 'clientName': 'MWEB',
18c7683d 206 'clientVersion': '2.20211221.01.00',
000c15a4 207 }
208 },
209 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
210 },
211 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
212 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
213 'tv_embedded': {
214 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
215 'INNERTUBE_CONTEXT': {
216 'client': {
217 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
218 'clientVersion': '2.0',
219 },
220 },
221 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
222 },
000c15a4 223}
224
225
e7870111
D
226def _split_innertube_client(client_name):
227 variant, *base = client_name.rsplit('.', 1)
228 if base:
229 return variant, base[0], variant
230 base, *variant = client_name.split('_', 1)
231 return client_name, base, variant[0] if variant else None
232
233
000c15a4 234def build_innertube_clients():
2e4cacd0 235 THIRD_PARTY = {
e7870111 236 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 237 }
e7870111 238 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 239 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 240
241 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 242 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 243 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 244 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 245 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 246
e7870111 247 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 248 ytcfg['priority'] = 10 * priority(base_client)
249
e48b3875 250 if not variant:
e7870111
D
251 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
252 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
253 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
254 embedscreen['priority'] -= 3
255 elif variant == 'embedded':
e48b3875 256 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 257 ytcfg['priority'] -= 2
e48b3875 258 else:
000c15a4 259 ytcfg['priority'] -= 3
260
261
262build_innertube_clients()
263
264
de7f3446 265class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 266 """Provide base functions for Youtube extractors"""
e00eb564 267
3462ffa8 268 _RESERVED_NAMES = (
3cd786db 269 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 270 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 271 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 272 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 273
3619f78d 274 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
275
52efa4b3 276 # _NETRC_MACHINE = 'youtube'
3619f78d 277
b2e8bc1b
JMF
278 # If True it will raise an error if no login info is provided
279 _LOGIN_REQUIRED = False
280
d9190e44
RH
281 _INVIDIOUS_SITES = (
282 # invidious-redirect websites
283 r'(?:www\.)?redirect\.invidious\.io',
284 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 285 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
286 r'(?:www\.)?invidious\.pussthecat\.org',
287 r'(?:www\.)?invidious\.zee\.li',
288 r'(?:www\.)?invidious\.ethibox\.fr',
289 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
290 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
291 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
292 # youtube-dl invidious instances list
293 r'(?:(?:www|no)\.)?invidiou\.sh',
294 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
295 r'(?:www\.)?invidious\.kabi\.tk',
296 r'(?:www\.)?invidious\.mastodon\.host',
297 r'(?:www\.)?invidious\.zapashcanon\.fr',
298 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
299 r'(?:www\.)?invidious\.tinfoil-hat\.net',
300 r'(?:www\.)?invidious\.himiko\.cloud',
301 r'(?:www\.)?invidious\.reallyancient\.tech',
302 r'(?:www\.)?invidious\.tube',
303 r'(?:www\.)?invidiou\.site',
304 r'(?:www\.)?invidious\.site',
305 r'(?:www\.)?invidious\.xyz',
306 r'(?:www\.)?invidious\.nixnet\.xyz',
307 r'(?:www\.)?invidious\.048596\.xyz',
308 r'(?:www\.)?invidious\.drycat\.fr',
309 r'(?:www\.)?inv\.skyn3t\.in',
310 r'(?:www\.)?tube\.poal\.co',
311 r'(?:www\.)?tube\.connect\.cafe',
312 r'(?:www\.)?vid\.wxzm\.sx',
313 r'(?:www\.)?vid\.mint\.lgbt',
314 r'(?:www\.)?vid\.puffyan\.us',
315 r'(?:www\.)?yewtu\.be',
316 r'(?:www\.)?yt\.elukerio\.org',
317 r'(?:www\.)?yt\.lelux\.fi',
318 r'(?:www\.)?invidious\.ggc-project\.de',
319 r'(?:www\.)?yt\.maisputain\.ovh',
320 r'(?:www\.)?ytprivate\.com',
321 r'(?:www\.)?invidious\.13ad\.de',
322 r'(?:www\.)?invidious\.toot\.koeln',
323 r'(?:www\.)?invidious\.fdn\.fr',
324 r'(?:www\.)?watch\.nettohikari\.com',
325 r'(?:www\.)?invidious\.namazso\.eu',
326 r'(?:www\.)?invidious\.silkky\.cloud',
327 r'(?:www\.)?invidious\.exonip\.de',
328 r'(?:www\.)?invidious\.riverside\.rocks',
329 r'(?:www\.)?invidious\.blamefran\.net',
330 r'(?:www\.)?invidious\.moomoo\.de',
331 r'(?:www\.)?ytb\.trom\.tf',
332 r'(?:www\.)?yt\.cyberhost\.uk',
333 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
334 r'(?:www\.)?qklhadlycap4cnod\.onion',
335 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
336 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
337 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
338 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
339 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
340 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
341 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
342 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
343 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
344 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
345 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
346 r'(?:www\.)?piped\.kavin\.rocks',
347 r'(?:www\.)?piped\.silkky\.cloud',
348 r'(?:www\.)?piped\.tokhmi\.xyz',
349 r'(?:www\.)?piped\.moomoo\.me',
350 r'(?:www\.)?il\.ax',
351 r'(?:www\.)?piped\.syncpundit\.com',
352 r'(?:www\.)?piped\.mha\.fi',
353 r'(?:www\.)?piped\.mint\.lgbt',
354 r'(?:www\.)?piped\.privacy\.com\.de',
d9190e44
RH
355 )
356
cce889b9 357 def _initialize_consent(self):
358 cookies = self._get_cookies('https://www.youtube.com/')
359 if cookies.get('__Secure-3PSID'):
360 return
361 consent_id = None
362 consent = cookies.get('CONSENT')
363 if consent:
364 if 'YES' in consent.value:
365 return
366 consent_id = self._search_regex(
367 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
368 if not consent_id:
369 consent_id = random.randint(100, 999)
370 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 371
f3aa3c3f 372 def _initialize_pref(self):
373 cookies = self._get_cookies('https://www.youtube.com/')
374 pref_cookie = cookies.get('PREF')
375 pref = {}
376 if pref_cookie:
377 try:
14f25df2 378 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 379 except ValueError:
380 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 381 pref.update({'hl': 'en', 'tz': 'UTC'})
14f25df2 382 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 383
b2e8bc1b 384 def _real_initialize(self):
f3aa3c3f 385 self._initialize_pref()
cce889b9 386 self._initialize_consent()
a25bca9f 387 self._check_login_required()
388
389 def _check_login_required(self):
24146491 390 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 391 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 392
b7c47b74 393 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
394 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 395
000c15a4 396 def _get_default_ytcfg(self, client='web'):
397 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 398
000c15a4 399 def _get_innertube_host(self, client='web'):
400 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 401
000c15a4 402 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 403 # try_get but with fallback to default ytcfg client values when present
404 _func = lambda y: try_get(y, getter, expected_type)
405 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
406
000c15a4 407 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 408 return self._ytcfg_get_safe(
409 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 410 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 411
000c15a4 412 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 413 return self._ytcfg_get_safe(
414 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 415 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 416
2ae778b8 417 def _select_api_hostname(self, req_api_hostname, default_client=None):
418 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
419 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
420
000c15a4 421 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 422 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 423
000c15a4 424 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 425 context = get_first(
426 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 427 # Enforce language and tz for extraction
428 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
429 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 430 return context
431
cf87314d 432 _SAPISID = None
433
109dd3b2 434 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 435 time_now = round(time.time())
cf87314d 436 if self._SAPISID is None:
437 yt_cookies = self._get_cookies('https://www.youtube.com')
438 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
439 # See: https://github.com/yt-dlp/yt-dlp/issues/393
440 sapisid_cookie = dict_get(
441 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
442 if sapisid_cookie and sapisid_cookie.value:
443 self._SAPISID = sapisid_cookie.value
444 self.write_debug('Extracted SAPISID cookie')
445 # SAPISID cookie is required if not already present
446 if not yt_cookies.get('SAPISID'):
447 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
448 self._set_cookie(
449 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
450 else:
451 self._SAPISID = False
452 if not self._SAPISID:
453 return None
1974e99f 454 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
455 sapisidhash = hashlib.sha1(
86e5f3ed 456 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 457 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
458
459 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 460 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 461 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 462
109dd3b2 463 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 464 data.update(query)
11f9be09 465 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 466 real_headers.update({'content-type': 'application/json'})
467 if headers:
468 real_headers.update(headers)
2ae778b8 469 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
470 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 471 return self._download_json(
2ae778b8 472 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 473 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 474 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 475 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 476
65141660 477 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
478 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 479
99e9e001 480 @staticmethod
481 def _extract_session_index(*data):
482 """
483 Index of current account in account list.
484 See: https://github.com/yt-dlp/yt-dlp/pull/519
485 """
486 for ytcfg in data:
487 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
488 if session_index is not None:
489 return session_index
490
491 # Deprecated?
492 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 493 if ytcfg:
14f25df2 494 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
495 if token:
496 return token
99e9e001 497 if webpage:
498 return self._search_regex(
499 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
500 'identity token', default=None, fatal=False)
a1c5d2ca
M
501
502 @staticmethod
fe93e2c4 503 def _extract_account_syncid(*args):
8ea3f7b9 504 """
505 Extract syncId required to download private playlists of secondary channels
fe93e2c4 506 @params response and/or ytcfg
8ea3f7b9 507 """
fe93e2c4 508 for data in args:
509 # ytcfg includes channel_syncid if on secondary channel
14f25df2 510 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 511 if delegated_sid:
512 return delegated_sid
513 sync_ids = (try_get(
514 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 515 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 516 if len(sync_ids) >= 2 and sync_ids[1]:
517 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
518 # and just "user_syncid||" for primary channel. We only want the channel_syncid
519 return sync_ids[0]
a1c5d2ca 520
ac56cf38 521 @staticmethod
522 def _extract_visitor_data(*args):
523 """
524 Extracts visitorData from an API response or ytcfg
525 Appears to be used to track session state
526 """
9222c381 527 return get_first(
6c73052c 528 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 529 expected_type=str)
ac56cf38 530
2762dbb1 531 @functools.cached_property
99e9e001 532 def is_authenticated(self):
533 return bool(self._generate_sapisidhash_header())
534
11f9be09 535 def extract_ytcfg(self, video_id, webpage):
8c54a305 536 if not webpage:
537 return {}
29f7c58a 538 return self._parse_json(
539 self._search_regex(
540 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 541 default='{}'), video_id, fatal=False) or {}
542
11f9be09 543 def generate_api_headers(
99e9e001 544 self, *, ytcfg=None, account_syncid=None, session_index=None,
545 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
546
2ae778b8 547 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 548 headers = {
14f25df2 549 'X-YouTube-Client-Name': str(
11f9be09 550 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
551 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 552 'Origin': origin,
553 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
554 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 555 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 556 }
557 if session_index is None:
314ee305 558 session_index = self._extract_session_index(ytcfg)
559 if account_syncid or session_index is not None:
560 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 561
109dd3b2 562 auth = self._generate_sapisidhash_header(origin)
f4f751af 563 if auth is not None:
564 headers['Authorization'] = auth
109dd3b2 565 headers['X-Origin'] = origin
99e9e001 566 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 567
a25bca9f 568 def _download_ytcfg(self, client, video_id):
569 url = {
570 'web': 'https://www.youtube.com',
571 'web_music': 'https://music.youtube.com',
572 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
573 }.get(client)
574 if not url:
575 return {}
576 webpage = self._download_webpage(
577 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
578 return self.extract_ytcfg(video_id, webpage) or {}
579
2d6659b9 580 @staticmethod
581 def _build_api_continuation_query(continuation, ctp=None):
582 query = {
583 'continuation': continuation
584 }
585 # TODO: Inconsistency with clickTrackingParams.
586 # Currently we have a fixed ctp contained within context (from ytcfg)
587 # and a ctp in root query for continuation.
588 if ctp:
589 query['clickTracking'] = {'clickTrackingParams': ctp}
590 return query
591
2d6659b9 592 @classmethod
593 def _extract_next_continuation_data(cls, renderer):
594 next_continuation = try_get(
595 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
596 lambda x: x['continuation']['reloadContinuationData']), dict)
597 if not next_continuation:
598 return
599 continuation = next_continuation.get('continuation')
600 if not continuation:
601 return
602 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 603 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 604
605 @classmethod
606 def _extract_continuation_ep_data(cls, continuation_ep: dict):
607 if isinstance(continuation_ep, dict):
608 continuation = try_get(
14f25df2 609 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 610 if not continuation:
611 return
612 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 613 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 614
615 @classmethod
616 def _extract_continuation(cls, renderer):
617 next_continuation = cls._extract_next_continuation_data(renderer)
618 if next_continuation:
619 return next_continuation
fe93e2c4 620
2d6659b9 621 contents = []
622 for key in ('contents', 'items'):
623 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 624
2d6659b9 625 for content in contents:
626 if not isinstance(content, dict):
627 continue
628 continuation_ep = try_get(
629 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
630 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
631 dict)
632 continuation = cls._extract_continuation_ep_data(continuation_ep)
633 if continuation:
634 return continuation
635
fe93e2c4 636 @classmethod
637 def _extract_alerts(cls, data):
109dd3b2 638 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
639 if not isinstance(alert_dict, dict):
640 continue
641 for alert in alert_dict.values():
642 alert_type = alert.get('type')
643 if not alert_type:
644 continue
052e1350 645 message = cls._get_text(alert, 'text')
109dd3b2 646 if message:
647 yield alert_type, message
648
c0ac49bc 649 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 650 errors = []
651 warnings = []
652 for alert_type, alert_message in alerts:
641ad5d8 653 if alert_type.lower() == 'error' and fatal:
109dd3b2 654 errors.append([alert_type, alert_message])
655 else:
656 warnings.append([alert_type, alert_message])
657
658 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 659 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 660 if errors:
661 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
662
663 def _extract_and_report_alerts(self, data, *args, **kwargs):
664 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
665
47193e02 666 def _extract_badges(self, renderer: dict):
667 badges = set()
668 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
14f25df2 669 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], str)
47193e02 670 if label:
671 badges.add(label.lower())
672 return badges
673
674 @staticmethod
052e1350 675 def _get_text(data, *path_list, max_runs=None):
676 for path in path_list or [None]:
677 if path is None:
678 obj = [data]
679 else:
680 obj = traverse_obj(data, path, default=[])
681 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
682 obj = [obj]
683 for item in obj:
14f25df2 684 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 685 if text:
686 return text
687 runs = try_get(item, lambda x: x['runs'], list) or []
688 if not runs and isinstance(item, list):
689 runs = item
690
691 runs = runs[:min(len(runs), max_runs or len(runs))]
692 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
693 if text:
694 return text
47193e02 695
f0d785d3 696 def _get_count(self, data, *path_list):
697 count_text = self._get_text(data, *path_list) or ''
698 count = parse_count(count_text)
699 if count is None:
700 count = str_to_int(
701 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
702 return count
703
a709d873 704 @staticmethod
705 def _extract_thumbnails(data, *path_list):
706 """
707 Extract thumbnails from thumbnails dict
708 @param path_list: path list to level that contains 'thumbnails' key
709 """
710 thumbnails = []
711 for path in path_list or [()]:
712 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
713 thumbnail_url = url_or_none(thumbnail.get('url'))
714 if not thumbnail_url:
715 continue
716 # Sometimes youtube gives a wrong thumbnail URL. See:
717 # https://github.com/yt-dlp/yt-dlp/issues/233
718 # https://github.com/ytdl-org/youtube-dl/issues/28023
719 if 'maxresdefault' in thumbnail_url:
720 thumbnail_url = thumbnail_url.split('?')[0]
721 thumbnails.append({
722 'url': thumbnail_url,
723 'height': int_or_none(thumbnail.get('height')),
724 'width': int_or_none(thumbnail.get('width')),
725 })
726 return thumbnails
727
f3aa3c3f 728 @staticmethod
729 def extract_relative_time(relative_time_text):
730 """
731 Extracts a relative time from string and converts to dt object
f0d785d3 732 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 733 """
f0d785d3 734 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 735 if mobj:
f0d785d3 736 start = mobj.group('start')
737 if start:
738 return datetime_from_str(start)
f3aa3c3f 739 try:
f0d785d3 740 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 741 except ValueError:
742 return None
743
744 def _extract_time_text(self, renderer, *path_list):
a25bca9f 745 """@returns (timestamp, time_text)"""
f3aa3c3f 746 text = self._get_text(renderer, *path_list) or ''
747 dt = self.extract_relative_time(text)
748 timestamp = None
749 if isinstance(dt, datetime.datetime):
750 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 751
752 if timestamp is None:
753 timestamp = (
754 unified_timestamp(text) or unified_timestamp(
755 self._search_regex(
17322130 756 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 757 text.lower(), 'time text', default=None)))
f0d785d3 758
f3aa3c3f 759 if text and timestamp is None:
17322130 760 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
f3aa3c3f 761 return timestamp, text
762
109dd3b2 763 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
764 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 765 default_client='web'):
109dd3b2 766 response = None
767 last_error = None
768 count = -1
769 retries = self.get_param('extractor_retries', 3)
770 if check_get_keys is None:
771 check_get_keys = []
772 while count < retries:
773 count += 1
774 if last_error:
c0ac49bc 775 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
109dd3b2 776 try:
777 response = self._call_api(
778 ep=ep, fatal=True, headers=headers,
779 video_id=item_id, query=query,
780 context=self._extract_context(ytcfg, default_client),
781 api_key=self._extract_api_key(ytcfg, default_client),
782 api_hostname=api_hostname, default_client=default_client,
783 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
784 except ExtractorError as e:
9c0d7f49 785 if isinstance(e.cause, network_exceptions):
14f25df2 786 if isinstance(e.cause, urllib.error.HTTPError):
87e8e8a7 787 first_bytes = e.cause.read(512)
788 if not is_html(first_bytes):
789 yt_error = try_get(
790 self._parse_json(
791 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
14f25df2 792 lambda x: x['error']['message'], str)
87e8e8a7 793 if yt_error:
794 self._report_alerts([('ERROR', yt_error)], fatal=False)
109dd3b2 795 # Downloading page may result in intermittent 5xx HTTP error
962ffcf8 796 # Sometimes a 404 is also received. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 797 # We also want to catch all other network exceptions since errors in later pages can be troublesome
798 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
14f25df2 799 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
526d74ec 800 last_error = error_to_compat_str(e.cause or e.msg)
9c0d7f49 801 if count < retries:
802 continue
109dd3b2 803 if fatal:
804 raise
805 else:
806 self.report_warning(error_to_compat_str(e))
807 return
808
809 else:
109dd3b2 810 try:
ac56cf38 811 self._extract_and_report_alerts(response, only_once=True)
109dd3b2 812 except ExtractorError as e:
c0ac49bc 813 # YouTube servers may return errors we want to retry on in a 200 OK response
814 # See: https://github.com/yt-dlp/yt-dlp/issues/839
815 if 'unknown error' in e.msg.lower():
816 last_error = e.msg
817 continue
109dd3b2 818 if fatal:
819 raise
820 self.report_warning(error_to_compat_str(e))
821 return
822 if not check_get_keys or dict_get(response, check_get_keys):
823 break
824 # Youtube sometimes sends incomplete data
825 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
826 last_error = 'Incomplete data received'
827 if count >= retries:
828 if fatal:
829 raise ExtractorError(last_error)
830 else:
831 self.report_warning(last_error)
832 return
833 return response
834
9297939e 835 @staticmethod
836 def is_music_url(url):
837 return re.match(r'https?://music\.youtube\.com/', url) is not None
838
30a074c2 839 def _extract_video(self, renderer):
840 video_id = renderer.get('videoId')
052e1350 841 title = self._get_text(renderer, 'title')
842 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 843 duration = parse_duration(self._get_text(
844 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 845 if duration is None:
846 duration = parse_duration(self._search_regex(
847 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
848 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
849 video_id, default=None, group='duration'))
850
f0d785d3 851 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 852
052e1350 853 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 854 channel_id = traverse_obj(
a44ca5a4 855 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
856 expected_type=str, get_all=False)
f3aa3c3f 857 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
858 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
859 overlay_style = traverse_obj(
a44ca5a4 860 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
861 get_all=False, expected_type=str)
f3aa3c3f 862 badges = self._extract_badges(renderer)
a709d873 863 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
fd2ad7cb 864 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 865 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
866 expected_type=str)) or ''
fd2ad7cb 867 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 868 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 869 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 870
30a074c2 871 return {
39ed931e 872 '_type': 'url',
30a074c2 873 'ie_key': YoutubeIE.ie_key(),
874 'id': video_id,
fd2ad7cb 875 'url': url,
30a074c2 876 'title': title,
877 'description': description,
878 'duration': duration,
879 'view_count': view_count,
880 'uploader': uploader,
f3aa3c3f 881 'channel_id': channel_id,
a709d873 882 'thumbnails': thumbnails,
a44ca5a4 883 'upload_date': (strftime_or_none(timestamp, '%Y%m%d')
884 if self._configuration_arg('approximate_date', ie_key='youtubetab')
885 else None),
f3aa3c3f 886 'live_status': ('is_upcoming' if scheduled_timestamp is not None
887 else 'was_live' if 'streamed' in time_text.lower()
888 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
889 else None),
890 'release_timestamp': scheduled_timestamp,
891 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 892 }
893
0c148415 894
360e1ca5 895class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 896 IE_DESC = 'YouTube'
cb7dfeea 897 _VALID_URL = r"""(?x)^
c5e8d7af 898 (
edb53e2d 899 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 900 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
901 (?:www\.)?deturl\.com/www\.youtube\.com|
902 (?:www\.)?pwnyoutube\.com|
903 (?:www\.)?hooktube\.com|
904 (?:www\.)?yourepeat\.com|
905 tube\.majestyc\.net|
906 %(invidious)s|
907 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
908 (?:.*?\#/)? # handle anchor (#/) redirect urls
909 (?: # the various things that can precede the ID:
b6ce9bb0 910 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 911 |(?: # or the v= param in all its forms
f7000f3a 912 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 913 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 914 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
915 v=
916 )
f4b05232 917 ))
cbaed4bb
S
918 |(?:
919 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
920 vid\.plus| # or vid.plus/xxxx
921 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 922 %(invidious)s
cbaed4bb 923 )/
edb53e2d 924 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 925 )
c5e8d7af 926 )? # all until now is optional -> you can pass the naked ID
201c1459 927 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 928 (?(1).+)? # if we found the ID, everything can follow
9297939e 929 (?:\#|$)""" % {
d9190e44 930 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 931 }
e40c758c 932 _PLAYER_INFO_RE = (
cc2db878 933 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
934 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$',
545cc85d 935 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 936 )
2c62dc26 937 _formats = {
c2d3cb4c 938 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
939 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
940 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
941 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
942 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
943 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
944 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
945 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 946 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 947 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
948 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
949 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
950 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
951 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
952 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 953 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 954 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
955 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 956
957
958 # 3D videos
c2d3cb4c 959 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
960 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
961 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
962 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 963 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
964 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
965 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 966
96fb5605 967 # Apple HTTP Live Streaming
11f12195 968 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 969 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
970 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
971 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
972 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
973 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 974 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
975 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
976
977 # DASH mp4 video
d23028a8
S
978 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
979 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
980 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
981 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
982 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 983 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
984 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
985 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
986 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
987 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
988 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
989 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 990
f6f1fc92 991 # Dash mp4 audio
d23028a8
S
992 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
993 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
994 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
995 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
996 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
997 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
998 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
999
1000 # Dash webm
d23028a8
S
1001 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1002 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1003 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1004 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1005 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1006 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1007 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1008 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1009 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1010 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1011 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1012 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1013 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1014 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1015 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1016 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1017 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1018 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1019 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1020 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1021 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1022 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1023
1024 # Dash webm audio
d23028a8
S
1025 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1026 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1027
0857baad 1028 # Dash webm audio with opus inside
d23028a8
S
1029 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1030 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1031 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1032
ce6b9a2d
PH
1033 # RTMP (unnamed)
1034 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1035
1036 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1037 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1038 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1039 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1040 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1041 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1042 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1043 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1044 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1045 }
29f7c58a 1046 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1047
fd5c4aab
S
1048 _GEO_BYPASS = False
1049
78caa52a 1050 IE_NAME = 'youtube'
2eb88d95
PH
1051 _TESTS = [
1052 {
2d3d2997 1053 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1054 'info_dict': {
1055 'id': 'BaW_jenozKc',
1056 'ext': 'mp4',
3867038a 1057 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1058 'uploader': 'Philipp Hagemeister',
1059 'uploader_id': 'phihag',
ec85ded8 1060 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1061 'channel': 'Philipp Hagemeister',
dd4c4492
S
1062 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1063 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1064 'upload_date': '20121002',
ff9f925b 1065 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1066 'categories': ['Science & Technology'],
3867038a 1067 'tags': ['youtube-dl'],
556dbe7f 1068 'duration': 10,
dbdaaa23 1069 'view_count': int,
3e7c1224 1070 'like_count': int,
ff9f925b 1071 'availability': 'public',
1072 'playable_in_embed': True,
1073 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1074 'live_status': 'not_live',
1075 'age_limit': 0,
7c80519c 1076 'start_time': 1,
297a564b 1077 'end_time': 9,
12a1b225 1078 'comment_count': int,
6c73052c 1079 'channel_follower_count': int
2eb88d95 1080 }
0e853ca4 1081 },
fccd3771 1082 {
4bc3a23e
PH
1083 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1084 'note': 'Embed-only video (#1746)',
1085 'info_dict': {
1086 'id': 'yZIXLfi8CZQ',
1087 'ext': 'mp4',
1088 'upload_date': '20120608',
1089 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1090 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1091 'uploader': 'SET India',
94bfcd23 1092 'uploader_id': 'setindia',
ec85ded8 1093 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1094 'age_limit': 18,
545cc85d 1095 },
1096 'skip': 'Private video',
fccd3771 1097 },
11b56058 1098 {
8bdd16b4 1099 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1100 'note': 'Use the first video ID in the URL',
1101 'info_dict': {
1102 'id': 'BaW_jenozKc',
1103 'ext': 'mp4',
3867038a 1104 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1105 'uploader': 'Philipp Hagemeister',
1106 'uploader_id': 'phihag',
ec85ded8 1107 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1108 'channel': 'Philipp Hagemeister',
1109 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1110 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1111 'upload_date': '20121002',
976ae3ea 1112 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1113 'categories': ['Science & Technology'],
3867038a 1114 'tags': ['youtube-dl'],
556dbe7f 1115 'duration': 10,
dbdaaa23 1116 'view_count': int,
11b56058 1117 'like_count': int,
976ae3ea 1118 'availability': 'public',
1119 'playable_in_embed': True,
1120 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1121 'live_status': 'not_live',
1122 'age_limit': 0,
12a1b225 1123 'comment_count': int,
6c73052c 1124 'channel_follower_count': int
34a7de29
S
1125 },
1126 'params': {
1127 'skip_download': True,
1128 },
11b56058 1129 },
dd27fd17 1130 {
2d3d2997 1131 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1132 'note': '256k DASH audio (format 141) via DASH manifest',
1133 'info_dict': {
1134 'id': 'a9LDPn-MO4I',
1135 'ext': 'm4a',
1136 'upload_date': '20121002',
1137 'uploader_id': '8KVIDEO',
ec85ded8 1138 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1139 'description': '',
1140 'uploader': '8KVIDEO',
1141 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1142 },
4bc3a23e
PH
1143 'params': {
1144 'youtube_include_dash_manifest': True,
1145 'format': '141',
4919603f 1146 },
de3c7fe0 1147 'skip': 'format 141 not served anymore',
dd27fd17 1148 },
8bdd16b4 1149 # DASH manifest with encrypted signature
1150 {
1151 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1152 'info_dict': {
1153 'id': 'IB3lcPjvWLA',
1154 'ext': 'm4a',
1155 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1156 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1157 'duration': 244,
1158 'uploader': 'AfrojackVEVO',
1159 'uploader_id': 'AfrojackVEVO',
1160 'upload_date': '20131011',
cc2db878 1161 'abr': 129.495,
976ae3ea 1162 'like_count': int,
1163 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1164 'playable_in_embed': True,
1165 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1166 'view_count': int,
1167 'track': 'The Spark',
1168 'live_status': 'not_live',
1169 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1170 'channel': 'Afrojack',
1171 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1172 'tags': 'count:19',
1173 'availability': 'public',
1174 'categories': ['Music'],
1175 'age_limit': 0,
1176 'alt_title': 'The Spark',
6c73052c 1177 'channel_follower_count': int
8bdd16b4 1178 },
1179 'params': {
1180 'youtube_include_dash_manifest': True,
1181 'format': '141/bestaudio[ext=m4a]',
1182 },
1183 },
65c2fde2 1184 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1185 {
65c2fde2 1186 'note': 'Embed allowed age-gate video',
2d3d2997 1187 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1188 'info_dict': {
1189 'id': 'HtVdAasjOgU',
1190 'ext': 'mp4',
1191 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1192 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1193 'duration': 142,
c522adb1
JMF
1194 'uploader': 'The Witcher',
1195 'uploader_id': 'WitcherGame',
ec85ded8 1196 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1197 'upload_date': '20140605',
34952f09 1198 'age_limit': 18,
976ae3ea 1199 'categories': ['Gaming'],
1200 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1201 'availability': 'needs_auth',
1202 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1203 'like_count': int,
1204 'channel': 'The Witcher',
1205 'live_status': 'not_live',
1206 'tags': 'count:17',
1207 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1208 'playable_in_embed': True,
1209 'view_count': int,
6c73052c 1210 'channel_follower_count': int
c522adb1
JMF
1211 },
1212 },
65c2fde2 1213 {
1214 'note': 'Age-gate video with embed allowed in public site',
1215 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1216 'info_dict': {
1217 'id': 'HsUATh_Nc2U',
1218 'ext': 'mp4',
1219 'title': 'Godzilla 2 (Official Video)',
1220 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1221 'upload_date': '20200408',
1222 'uploader_id': 'FlyingKitty900',
1223 'uploader': 'FlyingKitty',
1224 'age_limit': 18,
976ae3ea 1225 'availability': 'needs_auth',
1226 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1227 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1228 'channel': 'FlyingKitty',
1229 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1230 'view_count': int,
1231 'categories': ['Entertainment'],
1232 'live_status': 'not_live',
1233 'tags': ['Flyingkitty', 'godzilla 2'],
1234 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1235 'like_count': int,
1236 'duration': 177,
1237 'playable_in_embed': True,
6c73052c 1238 'channel_follower_count': int
65c2fde2 1239 },
1240 },
1241 {
1242 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1243 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1244 'info_dict': {
1245 'id': 'Tq92D6wQ1mg',
1246 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1247 'ext': 'mp4',
17322130 1248 'upload_date': '20191228',
65c2fde2 1249 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1250 'uploader': 'Projekt Melody',
1251 'description': 'md5:17eccca93a786d51bc67646756894066',
1252 'age_limit': 18,
976ae3ea 1253 'like_count': int,
1254 'availability': 'needs_auth',
1255 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1256 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1257 'view_count': int,
1258 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1259 'channel': 'Projekt Melody',
1260 'live_status': 'not_live',
1261 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1262 'playable_in_embed': True,
1263 'categories': ['Entertainment'],
1264 'duration': 106,
1265 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1266 'comment_count': int,
6c73052c 1267 'channel_follower_count': int
65c2fde2 1268 },
1269 },
1270 {
1271 'note': 'Non-Agegated non-embeddable video',
1272 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1273 'info_dict': {
1274 'id': 'MeJVWBSsPAY',
1275 'ext': 'mp4',
1276 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1277 'uploader': 'Herr Lurik',
1278 'uploader_id': 'st3in234',
1279 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1280 'upload_date': '20130730',
976ae3ea 1281 'track': 'Such mich find mich',
1282 'age_limit': 0,
1283 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1284 'like_count': int,
1285 'playable_in_embed': False,
1286 'creator': 'OOMPH!',
1287 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1288 'view_count': int,
1289 'alt_title': 'Such mich find mich',
1290 'duration': 210,
1291 'channel': 'Herr Lurik',
1292 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1293 'categories': ['Music'],
1294 'availability': 'public',
1295 'uploader_url': 'http://www.youtube.com/user/st3in234',
1296 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1297 'live_status': 'not_live',
1298 'artist': 'OOMPH!',
6c73052c 1299 'channel_follower_count': int
65c2fde2 1300 },
1301 },
1302 {
1303 'note': 'Non-bypassable age-gated video',
1304 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1305 'only_matching': True,
1306 },
8bdd16b4 1307 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1308 # YouTube Red ad is not captured for creator
1309 {
1310 'url': '__2ABJjxzNo',
1311 'info_dict': {
1312 'id': '__2ABJjxzNo',
1313 'ext': 'mp4',
1314 'duration': 266,
1315 'upload_date': '20100430',
1316 'uploader_id': 'deadmau5',
1317 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1318 'creator': 'deadmau5',
1319 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1320 'uploader': 'deadmau5',
1321 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1322 'alt_title': 'Some Chords',
976ae3ea 1323 'availability': 'public',
1324 'tags': 'count:14',
1325 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1326 'view_count': int,
1327 'live_status': 'not_live',
1328 'channel': 'deadmau5',
1329 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1330 'like_count': int,
1331 'track': 'Some Chords',
1332 'artist': 'deadmau5',
1333 'playable_in_embed': True,
1334 'age_limit': 0,
1335 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1336 'categories': ['Music'],
1337 'album': 'Some Chords',
6c73052c 1338 'channel_follower_count': int
8bdd16b4 1339 },
1340 'expected_warnings': [
1341 'DASH manifest missing',
1342 ]
1343 },
067aa17e 1344 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1345 {
1346 'url': 'lqQg6PlCWgI',
1347 'info_dict': {
1348 'id': 'lqQg6PlCWgI',
1349 'ext': 'mp4',
556dbe7f 1350 'duration': 6085,
90227264 1351 'upload_date': '20150827',
cbe2bd91 1352 'uploader_id': 'olympic',
ec85ded8 1353 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
12a1b225 1354 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
11f9be09 1355 'uploader': 'Olympics',
cbe2bd91 1356 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1357 'like_count': int,
1358 'release_timestamp': 1343767800,
1359 'playable_in_embed': True,
1360 'categories': ['Sports'],
1361 'release_date': '20120731',
1362 'channel': 'Olympics',
1363 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1364 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1365 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1366 'age_limit': 0,
1367 'availability': 'public',
1368 'live_status': 'was_live',
1369 'view_count': int,
1370 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1371 'channel_follower_count': int
cbe2bd91
PH
1372 },
1373 'params': {
1374 'skip_download': 'requires avconv',
e52a40ab 1375 }
cbe2bd91 1376 },
6271f1ca
PH
1377 # Non-square pixels
1378 {
1379 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1380 'info_dict': {
1381 'id': '_b-2C3KPAM0',
1382 'ext': 'mp4',
1383 'stretched_ratio': 16 / 9.,
556dbe7f 1384 'duration': 85,
6271f1ca
PH
1385 'upload_date': '20110310',
1386 'uploader_id': 'AllenMeow',
ec85ded8 1387 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1388 '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 1389 'uploader': '孫ᄋᄅ',
6271f1ca 1390 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1391 'playable_in_embed': True,
1392 'channel': '孫ᄋᄅ',
1393 'age_limit': 0,
1394 'tags': 'count:11',
1395 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1396 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1397 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1398 'view_count': int,
1399 'categories': ['People & Blogs'],
1400 'like_count': int,
1401 'live_status': 'not_live',
1402 'availability': 'unlisted',
12a1b225 1403 'comment_count': int,
6c73052c 1404 'channel_follower_count': int
6271f1ca 1405 },
06b491eb
S
1406 },
1407 # url_encoded_fmt_stream_map is empty string
1408 {
1409 'url': 'qEJwOuvDf7I',
1410 'info_dict': {
1411 'id': 'qEJwOuvDf7I',
f57b7835 1412 'ext': 'webm',
06b491eb
S
1413 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1414 'description': '',
1415 'upload_date': '20150404',
1416 'uploader_id': 'spbelect',
1417 'uploader': 'Наблюдатели Петербурга',
1418 },
1419 'params': {
1420 'skip_download': 'requires avconv',
e323cf3f
S
1421 },
1422 'skip': 'This live event has ended.',
06b491eb 1423 },
067aa17e 1424 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1425 {
1426 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1427 'info_dict': {
1428 'id': 'FIl7x6_3R5Y',
eb6793ba 1429 'ext': 'webm',
da77d856
S
1430 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1431 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1432 'duration': 220,
da77d856
S
1433 'upload_date': '20150625',
1434 'uploader_id': 'dorappi2000',
ec85ded8 1435 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1436 'uploader': 'dorappi2000',
eb6793ba 1437 'formats': 'mincount:31',
da77d856 1438 },
eb6793ba 1439 'skip': 'not actual anymore',
2ee8f5d8 1440 },
8a1a26ce
YCH
1441 # DASH manifest with segment_list
1442 {
1443 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1444 'md5': '8ce563a1d667b599d21064e982ab9e31',
1445 'info_dict': {
1446 'id': 'CsmdDsKjzN8',
1447 'ext': 'mp4',
17ee98e1 1448 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1449 'uploader': 'Airtek',
1450 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1451 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1452 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1453 },
1454 'params': {
1455 'youtube_include_dash_manifest': True,
1456 'format': '135', # bestvideo
be49068d
S
1457 },
1458 'skip': 'This live event has ended.',
2ee8f5d8 1459 },
cf7e015f
S
1460 {
1461 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1462 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1463 'info_dict': {
545cc85d 1464 'id': 'jvGDaLqkpTg',
1465 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1466 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1467 },
1468 'playlist': [{
1469 'info_dict': {
545cc85d 1470 'id': 'jvGDaLqkpTg',
cf7e015f 1471 'ext': 'mp4',
545cc85d 1472 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1473 'description': 'md5:e03b909557865076822aa169218d6a5d',
1474 'duration': 10643,
1475 'upload_date': '20161111',
1476 'uploader': 'Team PGP',
1477 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1478 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1479 },
1480 }, {
1481 'info_dict': {
545cc85d 1482 'id': '3AKt1R1aDnw',
cf7e015f 1483 'ext': 'mp4',
545cc85d 1484 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1485 'description': 'md5:e03b909557865076822aa169218d6a5d',
1486 'duration': 10991,
1487 'upload_date': '20161111',
1488 'uploader': 'Team PGP',
1489 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1490 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1491 },
1492 }, {
1493 'info_dict': {
545cc85d 1494 'id': 'RtAMM00gpVc',
cf7e015f 1495 'ext': 'mp4',
545cc85d 1496 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1497 'description': 'md5:e03b909557865076822aa169218d6a5d',
1498 'duration': 10995,
1499 'upload_date': '20161111',
1500 'uploader': 'Team PGP',
1501 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1502 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1503 },
1504 }, {
1505 'info_dict': {
545cc85d 1506 'id': '6N2fdlP3C5U',
cf7e015f 1507 'ext': 'mp4',
545cc85d 1508 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1509 'description': 'md5:e03b909557865076822aa169218d6a5d',
1510 'duration': 10990,
1511 'upload_date': '20161111',
1512 'uploader': 'Team PGP',
1513 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1514 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1515 },
1516 }],
1517 'params': {
1518 'skip_download': True,
1519 },
65c2fde2 1520 'skip': 'Not multifeed anymore',
cbaed4bb 1521 },
f9f49d87 1522 {
067aa17e 1523 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1524 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1525 'info_dict': {
1526 'id': 'gVfLd0zydlo',
1527 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1528 },
1529 'playlist_count': 2,
be49068d 1530 'skip': 'Not multifeed anymore',
f9f49d87 1531 },
cbaed4bb 1532 {
2d3d2997 1533 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1534 'only_matching': True,
0e49d9a6 1535 },
6d4fc66b 1536 {
2d3d2997 1537 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1538 'only_matching': True,
1539 },
0e49d9a6 1540 {
067aa17e 1541 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1542 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1543 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1544 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1545 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1546 'info_dict': {
1547 'id': 'lsguqyKfVQg',
1548 'ext': 'mp4',
1549 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1550 'alt_title': 'Dark Walk',
0e49d9a6 1551 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1552 'duration': 133,
0e49d9a6
LL
1553 'upload_date': '20151119',
1554 'uploader_id': 'IronSoulElf',
ec85ded8 1555 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1556 'uploader': 'IronSoulElf',
11f9be09 1557 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1558 'track': 'Dark Walk',
1559 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1560 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1561 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1562 'categories': ['Film & Animation'],
1563 'view_count': int,
1564 'live_status': 'not_live',
1565 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1566 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1567 'tags': 'count:13',
1568 'availability': 'public',
1569 'channel': 'IronSoulElf',
1570 'playable_in_embed': True,
1571 'like_count': int,
1572 'age_limit': 0,
6c73052c 1573 'channel_follower_count': int
0e49d9a6
LL
1574 },
1575 'params': {
1576 'skip_download': True,
1577 },
1578 },
61f92af1 1579 {
067aa17e 1580 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1581 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1582 'only_matching': True,
1583 },
313dfc45
LL
1584 {
1585 # Video with yt:stretch=17:0
1586 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1587 'info_dict': {
1588 'id': 'Q39EVAstoRM',
1589 'ext': 'mp4',
1590 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1591 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1592 'upload_date': '20151107',
1593 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1594 'uploader': 'CH GAMER DROID',
1595 },
1596 'params': {
1597 'skip_download': True,
1598 },
be49068d 1599 'skip': 'This video does not exist.',
313dfc45 1600 },
201c1459 1601 {
1602 # Video with incomplete 'yt:stretch=16:'
1603 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1604 'only_matching': True,
1605 },
7caf9830
S
1606 {
1607 # Video licensed under Creative Commons
1608 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1609 'info_dict': {
1610 'id': 'M4gD1WSo5mA',
1611 'ext': 'mp4',
1612 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1613 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1614 'duration': 721,
17322130 1615 'upload_date': '20150128',
7caf9830 1616 'uploader_id': 'BerkmanCenter',
ec85ded8 1617 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1618 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1619 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1620 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1621 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1622 'like_count': int,
1623 'age_limit': 0,
1624 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1625 'channel': 'The Berkman Klein Center for Internet & Society',
1626 'availability': 'public',
1627 'view_count': int,
1628 'categories': ['Education'],
1629 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1630 'live_status': 'not_live',
1631 'playable_in_embed': True,
12a1b225 1632 'comment_count': int,
6c73052c 1633 'channel_follower_count': int
7caf9830
S
1634 },
1635 'params': {
1636 'skip_download': True,
1637 },
1638 },
fd050249
S
1639 {
1640 # Channel-like uploader_url
1641 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1642 'info_dict': {
1643 'id': 'eQcmzGIKrzg',
1644 'ext': 'mp4',
1645 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1646 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1647 'duration': 4060,
17322130 1648 'upload_date': '20151120',
eb6793ba 1649 'uploader': 'Bernie Sanders',
fd050249 1650 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1651 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1652 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1653 'playable_in_embed': True,
1654 'tags': 'count:12',
1655 'like_count': int,
1656 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1657 'age_limit': 0,
1658 'availability': 'public',
1659 'categories': ['News & Politics'],
1660 'channel': 'Bernie Sanders',
1661 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1662 'view_count': int,
1663 'live_status': 'not_live',
1664 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1665 'comment_count': int,
6c73052c 1666 'channel_follower_count': int
fd050249
S
1667 },
1668 'params': {
1669 'skip_download': True,
1670 },
1671 },
040ac686
S
1672 {
1673 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1674 'only_matching': True,
7f29cf54
S
1675 },
1676 {
067aa17e 1677 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1678 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1679 'only_matching': True,
6496ccb4
S
1680 },
1681 {
1682 # Rental video preview
1683 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1684 'info_dict': {
1685 'id': 'uGpuVWrhIzE',
1686 'ext': 'mp4',
1687 'title': 'Piku - Trailer',
1688 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1689 'upload_date': '20150811',
1690 'uploader': 'FlixMatrix',
1691 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1692 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1693 'license': 'Standard YouTube License',
1694 },
1695 'params': {
1696 'skip_download': True,
1697 },
eb6793ba 1698 'skip': 'This video is not available.',
022a5d66 1699 },
12afdc2a
S
1700 {
1701 # YouTube Red video with episode data
1702 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1703 'info_dict': {
1704 'id': 'iqKdEhx-dD4',
1705 'ext': 'mp4',
1706 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1707 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1708 'duration': 2085,
12afdc2a
S
1709 'upload_date': '20170118',
1710 'uploader': 'Vsauce',
1711 'uploader_id': 'Vsauce',
1712 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1713 'series': 'Mind Field',
1714 'season_number': 1,
1715 'episode_number': 1,
976ae3ea 1716 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1717 'tags': 'count:12',
1718 'view_count': int,
1719 'availability': 'public',
1720 'age_limit': 0,
1721 'channel': 'Vsauce',
1722 'episode': 'Episode 1',
1723 'categories': ['Entertainment'],
1724 'season': 'Season 1',
1725 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1726 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1727 'like_count': int,
1728 'playable_in_embed': True,
1729 'live_status': 'not_live',
6c73052c 1730 'channel_follower_count': int
12afdc2a
S
1731 },
1732 'params': {
1733 'skip_download': True,
1734 },
1735 'expected_warnings': [
1736 'Skipping DASH manifest',
1737 ],
1738 },
c7121fa7
S
1739 {
1740 # The following content has been identified by the YouTube community
1741 # as inappropriate or offensive to some audiences.
1742 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1743 'info_dict': {
1744 'id': '6SJNVb0GnPI',
1745 'ext': 'mp4',
1746 'title': 'Race Differences in Intelligence',
1747 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1748 'duration': 965,
1749 'upload_date': '20140124',
1750 'uploader': 'New Century Foundation',
1751 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1752 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1753 },
1754 'params': {
1755 'skip_download': True,
1756 },
545cc85d 1757 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1758 },
022a5d66
S
1759 {
1760 # itag 212
1761 'url': '1t24XAntNCY',
1762 'only_matching': True,
fd5c4aab
S
1763 },
1764 {
1765 # geo restricted to JP
1766 'url': 'sJL6WA-aGkQ',
1767 'only_matching': True,
1768 },
cd5a74a2
S
1769 {
1770 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1771 'only_matching': True,
1772 },
bc2ca1bb 1773 {
1774 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1775 'only_matching': True,
1776 },
1777 {
1778 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1779 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1780 'only_matching': True,
1781 },
825cd268
RA
1782 {
1783 # DRM protected
1784 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1785 'only_matching': True,
4fe54c12
S
1786 },
1787 {
1788 # Video with unsupported adaptive stream type formats
1789 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1790 'info_dict': {
1791 'id': 'Z4Vy8R84T1U',
1792 'ext': 'mp4',
1793 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1794 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1795 'duration': 433,
1796 'upload_date': '20130923',
1797 'uploader': 'Amelia Putri Harwita',
1798 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1799 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1800 'formats': 'maxcount:10',
1801 },
1802 'params': {
1803 'skip_download': True,
1804 'youtube_include_dash_manifest': False,
1805 },
5429d6a9 1806 'skip': 'not actual anymore',
5caabd3c 1807 },
1808 {
822b9d9c 1809 # Youtube Music Auto-generated description
5caabd3c 1810 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1811 'info_dict': {
1812 'id': 'MgNrAu2pzNs',
1813 'ext': 'mp4',
1814 'title': 'Voyeur Girl',
1815 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1816 'upload_date': '20190312',
5429d6a9
S
1817 'uploader': 'Stephen - Topic',
1818 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1819 'artist': 'Stephen',
1820 'track': 'Voyeur Girl',
1821 'album': 'it\'s too much love to know my dear',
1822 'release_date': '20190313',
1823 'release_year': 2019,
976ae3ea 1824 'alt_title': 'Voyeur Girl',
1825 'view_count': int,
1826 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1827 'playable_in_embed': True,
1828 'like_count': int,
1829 'categories': ['Music'],
1830 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1831 'channel': 'Stephen',
1832 'availability': 'public',
1833 'creator': 'Stephen',
1834 'duration': 169,
1835 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1836 'age_limit': 0,
1837 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1838 'tags': 'count:11',
1839 'live_status': 'not_live',
6c73052c 1840 'channel_follower_count': int
5caabd3c 1841 },
1842 'params': {
1843 'skip_download': True,
1844 },
1845 },
66b48727
RA
1846 {
1847 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1848 'only_matching': True,
1849 },
011e75e6
S
1850 {
1851 # invalid -> valid video id redirection
1852 'url': 'DJztXj2GPfl',
1853 'info_dict': {
1854 'id': 'DJztXj2GPfk',
1855 'ext': 'mp4',
1856 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1857 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1858 'upload_date': '20090125',
1859 'uploader': 'Prochorowka',
1860 'uploader_id': 'Prochorowka',
1861 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1862 'artist': 'Panjabi MC',
1863 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1864 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1865 },
1866 'params': {
1867 'skip_download': True,
1868 },
545cc85d 1869 'skip': 'Video unavailable',
ea74e00b
DP
1870 },
1871 {
1872 # empty description results in an empty string
1873 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1874 'info_dict': {
1875 'id': 'x41yOUIvK2k',
1876 'ext': 'mp4',
1877 'title': 'IMG 3456',
1878 'description': '',
1879 'upload_date': '20170613',
1880 'uploader_id': 'ElevageOrVert',
1881 'uploader': 'ElevageOrVert',
976ae3ea 1882 'view_count': int,
1883 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1884 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1885 'like_count': int,
1886 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1887 'tags': [],
1888 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1889 'availability': 'public',
1890 'age_limit': 0,
1891 'categories': ['Pets & Animals'],
1892 'duration': 7,
1893 'playable_in_embed': True,
1894 'live_status': 'not_live',
1895 'channel': 'ElevageOrVert',
6c73052c 1896 'channel_follower_count': int
ea74e00b
DP
1897 },
1898 'params': {
1899 'skip_download': True,
1900 },
1901 },
a0566bbf 1902 {
29f7c58a 1903 # with '};' inside yt initial data (see [1])
1904 # see [2] for an example with '};' inside ytInitialPlayerResponse
1905 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1906 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1907 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1908 'info_dict': {
1909 'id': 'CHqg6qOn4no',
1910 'ext': 'mp4',
1911 'title': 'Part 77 Sort a list of simple types in c#',
1912 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1913 'upload_date': '20130831',
1914 'uploader_id': 'kudvenkat',
1915 'uploader': 'kudvenkat',
976ae3ea 1916 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1917 'like_count': int,
1918 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1919 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1920 'live_status': 'not_live',
1921 'categories': ['Education'],
1922 'availability': 'public',
1923 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1924 'tags': 'count:12',
1925 'playable_in_embed': True,
1926 'age_limit': 0,
1927 'view_count': int,
1928 'duration': 522,
1929 'channel': 'kudvenkat',
12a1b225 1930 'comment_count': int,
6c73052c 1931 'channel_follower_count': int
a0566bbf 1932 },
1933 'params': {
1934 'skip_download': True,
1935 },
1936 },
29f7c58a 1937 {
1938 # another example of '};' in ytInitialData
1939 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1940 'only_matching': True,
1941 },
1942 {
1943 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1944 'only_matching': True,
1945 },
545cc85d 1946 {
cc2db878 1947 # https://github.com/ytdl-org/youtube-dl/pull/28094
1948 'url': 'OtqTfy26tG0',
1949 'info_dict': {
1950 'id': 'OtqTfy26tG0',
1951 'ext': 'mp4',
1952 'title': 'Burn Out',
1953 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1954 'upload_date': '20141120',
1955 'uploader': 'The Cinematic Orchestra - Topic',
1956 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1957 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1958 'artist': 'The Cinematic Orchestra',
1959 'track': 'Burn Out',
1960 'album': 'Every Day',
976ae3ea 1961 'like_count': int,
1962 'live_status': 'not_live',
1963 'alt_title': 'Burn Out',
1964 'duration': 614,
1965 'age_limit': 0,
1966 'view_count': int,
1967 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1968 'creator': 'The Cinematic Orchestra',
1969 'channel': 'The Cinematic Orchestra',
1970 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1971 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1972 'availability': 'public',
1973 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1974 'categories': ['Music'],
1975 'playable_in_embed': True,
6c73052c 1976 'channel_follower_count': int
cc2db878 1977 },
1978 'params': {
1979 'skip_download': True,
1980 },
545cc85d 1981 },
bc2ca1bb 1982 {
1983 # controversial video, only works with bpctr when authenticated with cookies
1984 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1985 'only_matching': True,
1986 },
a1a7907b 1987 {
1988 # controversial video, requires bpctr/contentCheckOk
1989 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1990 'info_dict': {
1991 'id': 'SZJvDhaSDnc',
1992 'ext': 'mp4',
1993 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1994 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1995 'uploader': 'CBS Mornings',
11f9be09 1996 'uploader_id': 'CBSThisMorning',
a1a7907b 1997 'upload_date': '20140716',
976ae3ea 1998 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1999 'duration': 170,
2000 'categories': ['News & Politics'],
2001 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2002 'view_count': int,
2003 'channel': 'CBS Mornings',
2004 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2005 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2006 'age_limit': 18,
2007 'availability': 'needs_auth',
2008 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2009 'like_count': int,
2010 'live_status': 'not_live',
2011 'playable_in_embed': True,
6c73052c 2012 'channel_follower_count': int
a1a7907b 2013 }
2014 },
f7ad7160 2015 {
2016 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2017 'url': 'cBvYw8_A0vQ',
2018 'info_dict': {
2019 'id': 'cBvYw8_A0vQ',
2020 'ext': 'mp4',
2021 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2022 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2023 'upload_date': '20201120',
2024 'uploader': 'Walk around Japan',
2025 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2026 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2027 'duration': 1456,
2028 'categories': ['Travel & Events'],
2029 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2030 'view_count': int,
2031 'channel': 'Walk around Japan',
2032 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2033 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2034 'age_limit': 0,
2035 'availability': 'public',
2036 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2037 'live_status': 'not_live',
2038 'playable_in_embed': True,
6c73052c 2039 'channel_follower_count': int
f7ad7160 2040 },
2041 'params': {
2042 'skip_download': True,
2043 },
0fb983f6 2044 }, {
2045 # Has multiple audio streams
2046 'url': 'WaOKSUlf4TM',
2047 'only_matching': True
9297939e 2048 }, {
2049 # Requires Premium: has format 141 when requested using YTM url
2050 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2051 'only_matching': True
2052 }, {
120916da 2053 # multiple subtitles with same lang_code
2054 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2055 'only_matching': True,
109dd3b2 2056 }, {
2057 # Force use android client fallback
2058 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2059 'info_dict': {
2060 'id': 'YOelRv7fMxY',
11f9be09 2061 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2062 'ext': '3gp',
2063 'upload_date': '20210624',
2064 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2065 'uploader': 'colinfurze',
11f9be09 2066 'uploader_id': 'colinfurze',
109dd3b2 2067 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2068 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2069 'duration': 596,
2070 'categories': ['Entertainment'],
2071 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2072 'view_count': int,
2073 'channel': 'colinfurze',
2074 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2075 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2076 'age_limit': 0,
2077 'availability': 'public',
2078 'like_count': int,
2079 'live_status': 'not_live',
2080 'playable_in_embed': True,
6c73052c 2081 'channel_follower_count': int
109dd3b2 2082 },
2083 'params': {
2084 'format': '17', # 3gp format available on android
2085 'extractor_args': {'youtube': {'player_client': ['android']}},
2086 },
120916da 2087 },
109dd3b2 2088 {
2089 # Skip download of additional client configs (remix client config in this case)
2090 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2091 'only_matching': True,
2092 'params': {
2093 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2094 },
8fc54b12 2095 }, {
2096 # shorts
2097 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2098 'only_matching': True,
9222c381 2099 }, {
2100 'note': 'Storyboards',
2101 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2102 'info_dict': {
2103 'id': '5KLPxDtMqe8',
2104 'ext': 'mhtml',
2105 'format_id': 'sb0',
2106 'title': 'Your Brain is Plastic',
2107 'uploader_id': 'scishow',
2108 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2109 'upload_date': '20140324',
2110 'uploader': 'SciShow',
976ae3ea 2111 'like_count': int,
2112 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2113 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2114 'view_count': int,
2115 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2116 'playable_in_embed': True,
2117 'tags': 'count:12',
2118 'uploader_url': 'http://www.youtube.com/user/scishow',
2119 'availability': 'public',
2120 'channel': 'SciShow',
2121 'live_status': 'not_live',
2122 'duration': 248,
2123 'categories': ['Education'],
2124 'age_limit': 0,
6c73052c 2125 'channel_follower_count': int
9222c381 2126 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2127 }, {
2128 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2129 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2130 'info_dict': {
2131 'id': '2NUZ8W2llS4',
2132 'ext': 'mp4',
2133 'title': 'The NP that test your phone performance 🙂',
2134 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2135 'uploader': 'Leon Nguyen',
2136 'uploader_id': 'VNSXIII',
2137 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2138 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2139 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2140 'duration': 21,
2141 'view_count': int,
2142 'age_limit': 0,
2143 'categories': ['Gaming'],
2144 'tags': 'count:23',
2145 'playable_in_embed': True,
2146 'live_status': 'not_live',
2147 'upload_date': '20220103',
2148 'like_count': int,
2149 'availability': 'public',
2150 'channel': 'Leon Nguyen',
2151 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2152 'comment_count': int,
992f9a73 2153 'channel_follower_count': int
2154 }
2155 }, {
2156 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2157 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2158 'info_dict': {
2159 'id': 'mzZzzBU6lrM',
2160 'ext': 'mp4',
2161 'title': 'I Met GeorgeNotFound In Real Life...',
2162 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2163 'uploader': 'Quackity',
2164 'uploader_id': 'QuackityHQ',
2165 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2166 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2167 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2168 'duration': 955,
2169 'view_count': int,
2170 'age_limit': 0,
2171 'categories': ['Entertainment'],
2172 'tags': 'count:26',
2173 'playable_in_embed': True,
2174 'live_status': 'not_live',
2175 'release_timestamp': 1641172509,
2176 'release_date': '20220103',
2177 'upload_date': '20220103',
2178 'like_count': int,
2179 'availability': 'public',
2180 'channel': 'Quackity',
2181 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2182 'channel_follower_count': int
2183 }
2184 },
2185 { # continuous livestream. Microformat upload date should be preferred.
2186 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2187 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2188 'info_dict': {
2189 'id': 'kgx4WGK0oNU',
2190 '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}',
2191 'ext': 'mp4',
2192 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2193 'availability': 'public',
2194 'age_limit': 0,
2195 'release_timestamp': 1637975704,
2196 'upload_date': '20210619',
2197 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2198 'live_status': 'is_live',
2199 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2200 'uploader': '阿鲍Abao',
2201 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2202 'channel': 'Abao in Tokyo',
2203 'channel_follower_count': int,
2204 'release_date': '20211127',
2205 'tags': 'count:39',
2206 'categories': ['People & Blogs'],
2207 'like_count': int,
2208 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2209 'view_count': int,
2210 'playable_in_embed': True,
2211 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2212 },
2213 'params': {'skip_download': True}
6e634cbe 2214 }, {
2215 # Story. Requires specific player params to work.
ee27297f 2216 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2217 'info_dict': {
ee27297f 2218 'id': 'vv8qTUWmulI',
6e634cbe 2219 'ext': 'mp4',
ee27297f 2220 'availability': 'unlisted',
2221 'view_count': int,
2222 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2223 'upload_date': '20220526',
2224 'categories': ['Education'],
2225 'title': 'Story',
2226 'channel': 'IT\'S HISTORY',
2227 'description': '',
2228 'uploader_id': 'BlastfromthePast',
2229 'duration': 12,
2230 'uploader': 'IT\'S HISTORY',
6e634cbe 2231 'playable_in_embed': True,
6e634cbe 2232 'age_limit': 0,
6e634cbe 2233 'live_status': 'not_live',
ee27297f 2234 'tags': [],
2235 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2236 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2237 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
12a1b225
A
2238 },
2239 'skip': 'stories get removed after some period of time',
ee27297f 2240 }, {
2241 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2242 'info_dict': {
2243 'id': 'tjjjtzRLHvA',
2244 'ext': 'mp4',
2245 'title': 'ハッシュタグ無し };if window.ytcsi',
2246 'upload_date': '20220323',
2247 'like_count': int,
2248 'availability': 'unlisted',
2249 'channel': 'nao20010128nao',
2250 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2251 'age_limit': 0,
2252 'uploader': 'nao20010128nao',
2253 'uploader_id': 'nao20010128nao',
2254 'categories': ['Music'],
6e634cbe 2255 'view_count': int,
2256 'description': '',
ee27297f 2257 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2258 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2259 'live_status': 'not_live',
2260 'playable_in_embed': True,
2261 'channel_follower_count': int,
2262 'duration': 6,
2263 'tags': [],
2264 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2265 }
2266 }
2eb88d95
PH
2267 ]
2268
f2e8dbcc 2269 _WEBPAGE_TESTS = [
2270 # YouTube <object> embed
2271 {
2272 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2273 'md5': '873c81d308b979f0e23ee7e620b312a3',
2274 'info_dict': {
2275 'id': 'msN87y-iEx0',
2276 'ext': 'mp4',
2277 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2278 'upload_date': '20080526',
2279 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2280 'uploader': 'Christopher Sykes',
2281 'uploader_id': 'ChristopherJSykes',
2282 'age_limit': 0,
2283 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2284 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2285 'playable_in_embed': True,
2286 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2287 'like_count': int,
2288 'comment_count': int,
2289 'channel': 'Christopher Sykes',
2290 'live_status': 'not_live',
2291 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2292 'availability': 'public',
2293 'duration': 195,
2294 'view_count': int,
2295 'categories': ['Science & Technology'],
2296 'channel_follower_count': int,
2297 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2298 },
2299 'params': {
2300 'skip_download': True,
2301 }
2302 },
2303 ]
2304
201c1459 2305 @classmethod
2306 def suitable(cls, url):
4dfbf869 2307 from ..utils import parse_qs
2308
201c1459 2309 qs = parse_qs(url)
2310 if qs.get('list', [None])[0]:
2311 return False
86e5f3ed 2312 return super().suitable(url)
201c1459 2313
e0df6211 2314 def __init__(self, *args, **kwargs):
86e5f3ed 2315 super().__init__(*args, **kwargs)
545cc85d 2316 self._code_cache = {}
83799698 2317 self._player_cache = {}
e0df6211 2318
adbc4ec4 2319 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2320 lock = threading.Lock()
2321
2322 is_live = True
185bf310 2323 start_time = time.time()
adbc4ec4
THD
2324 formats = [f for f in formats if f.get('is_from_start')]
2325
185bf310 2326 def refetch_manifest(format_id, delay):
2327 nonlocal formats, start_time, is_live
2328 if time.time() <= start_time + delay:
adbc4ec4
THD
2329 return
2330
2331 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2332 video_details = traverse_obj(
2333 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2334 microformats = traverse_obj(
2335 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2336 expected_type=dict, default=[])
c646d76f 2337 _, is_live, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2338 start_time = time.time()
adbc4ec4 2339
185bf310 2340 def mpd_feed(format_id, delay):
adbc4ec4
THD
2341 """
2342 @returns (manifest_url, manifest_stream_number, is_live) or None
2343 """
2344 with lock:
185bf310 2345 refetch_manifest(format_id, delay)
adbc4ec4
THD
2346
2347 f = next((f for f in formats if f['format_id'] == format_id), None)
2348 if not f:
185bf310 2349 if not is_live:
2350 self.to_screen(f'{video_id}: Video is no longer live')
2351 else:
2352 self.report_warning(
2353 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2354 return None
2355 return f['manifest_url'], f['manifest_stream_number'], is_live
2356
2357 for f in formats:
a539f065 2358 f['is_live'] = True
adbc4ec4
THD
2359 f['protocol'] = 'http_dash_segments_generator'
2360 f['fragments'] = functools.partial(
2361 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2362
2363 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2364 FETCH_SPAN, MAX_DURATION = 5, 432000
2365
2366 mpd_url, stream_number, is_live = None, None, True
2367
2368 begin_index = 0
2369 download_start_time = ctx.get('start') or time.time()
2370
2371 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2372 if lack_early_segments:
2373 self.report_warning(bug_reports_message(
2374 'Starting download from the last 120 hours of the live stream since '
2375 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2376 lack_early_segments = True
2377
2378 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2379 fragments, fragment_base_url = None, None
2380
a539f065 2381 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2382 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2383 # Obtain from MPD's maximum seq value
2384 old_mpd_url = mpd_url
185bf310 2385 last_error = ctx.pop('last_error', None)
14f25df2 2386 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2387 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2388 or (mpd_url, stream_number, False))
2389 if not refresh_sequence:
2390 if expire_fast and not is_live:
2391 return False, last_seq
2392 elif old_mpd_url == mpd_url:
2393 return True, last_seq
adbc4ec4
THD
2394 try:
2395 fmts, _ = self._extract_mpd_formats_and_subtitles(
2396 mpd_url, None, note=False, errnote=False, fatal=False)
2397 except ExtractorError:
2398 fmts = None
2399 if not fmts:
a539f065 2400 no_fragment_score += 2
adbc4ec4
THD
2401 return False, last_seq
2402 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2403 fragments = fmt_info['fragments']
2404 fragment_base_url = fmt_info['fragment_base_url']
2405 assert fragment_base_url
2406
2407 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2408 return True, _last_seq
2409
2410 while is_live:
2411 fetch_time = time.time()
2412 if no_fragment_score > 30:
2413 return
2414 if last_segment_url:
2415 # Obtain from "X-Head-Seqnum" header value from each segment
2416 try:
2417 urlh = self._request_webpage(
2418 last_segment_url, None, note=False, errnote=False, fatal=False)
2419 except ExtractorError:
2420 urlh = None
2421 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2422 if last_seq is None:
a539f065 2423 no_fragment_score += 2
adbc4ec4
THD
2424 last_segment_url = None
2425 continue
2426 else:
a539f065
LNO
2427 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2428 no_fragment_score += 2
185bf310 2429 if not should_continue:
adbc4ec4
THD
2430 continue
2431
2432 if known_idx > last_seq:
2433 last_segment_url = None
2434 continue
2435
2436 last_seq += 1
2437
2438 if begin_index < 0 and known_idx < 0:
2439 # skip from the start when it's negative value
2440 known_idx = last_seq + begin_index
2441 if lack_early_segments:
2442 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2443 try:
2444 for idx in range(known_idx, last_seq):
2445 # do not update sequence here or you'll get skipped some part of it
a539f065 2446 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2447 if not should_continue:
adbc4ec4
THD
2448 known_idx = idx - 1
2449 raise ExtractorError('breaking out of outer loop')
2450 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2451 yield {
2452 'url': last_segment_url,
36195c44 2453 'fragment_count': last_seq,
adbc4ec4
THD
2454 }
2455 if known_idx == last_seq:
2456 no_fragment_score += 5
2457 else:
2458 no_fragment_score = 0
2459 known_idx = last_seq
2460 except ExtractorError:
2461 continue
2462
2463 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2464
b6de707d 2465 def _extract_player_url(self, *ytcfgs, webpage=None):
2466 player_url = traverse_obj(
2467 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2468 get_all=False, expected_type=str)
11f9be09 2469 if not player_url:
b6de707d 2470 return
60f393e4 2471 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2472
b6de707d 2473 def _download_player_url(self, video_id, fatal=False):
2474 res = self._download_webpage(
2475 'https://www.youtube.com/iframe_api',
2476 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2477 if res:
2478 player_version = self._search_regex(
2479 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2480 if player_version:
2481 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2482
60064c53
PH
2483 def _signature_cache_id(self, example_sig):
2484 """ Return a string representation of a signature """
14f25df2 2485 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2486
e40c758c
S
2487 @classmethod
2488 def _extract_player_info(cls, player_url):
2489 for player_re in cls._PLAYER_INFO_RE:
2490 id_m = re.search(player_re, player_url)
2491 if id_m:
2492 break
2493 else:
c081b35c 2494 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2495 return id_m.group('id')
e40c758c 2496
404f611f 2497 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2498 player_id = self._extract_player_info(player_url)
2499 if player_id not in self._code_cache:
1276a43a 2500 code = self._download_webpage(
109dd3b2 2501 player_url, video_id, fatal=fatal,
2502 note='Downloading player ' + player_id,
2503 errnote='Download of %s failed' % player_url)
1276a43a 2504 if code:
2505 self._code_cache[player_id] = code
404f611f 2506 return self._code_cache.get(player_id)
109dd3b2 2507
e40c758c 2508 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2509 player_id = self._extract_player_info(player_url)
e0df6211 2510
c4417ddb 2511 # Read from filesystem cache
86e5f3ed 2512 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2513 assert os.path.basename(func_id) == func_id
a0e07d31 2514
ae61d108 2515 self.write_debug(f'Extracting signature function {func_id}')
9809740b 2516 cache_spec = self.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2517 if cache_spec is not None:
78caa52a 2518 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2519
404f611f 2520 code = self._load_player(video_id, player_url)
2521 if code:
109dd3b2 2522 res = self._parse_sig_js(code)
e0df6211 2523
ac668111 2524 test_string = ''.join(map(chr, range(len(example_sig))))
109dd3b2 2525 cache_res = res(test_string)
2526 cache_spec = [ord(c) for c in cache_res]
83799698 2527
9809740b 2528 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
109dd3b2 2529 return res
83799698 2530
60064c53 2531 def _print_sig_code(self, func, example_sig):
404f611f 2532 if not self.get_param('youtube_print_sig_code'):
2533 return
2534
edf3e38e
PH
2535 def gen_sig_code(idxs):
2536 def _genslice(start, end, step):
78caa52a 2537 starts = '' if start == 0 else str(start)
8bcc8756 2538 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2539 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2540 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2541
2542 step = None
7af808a5
PH
2543 # Quelch pyflakes warnings - start will be set when step is set
2544 start = '(Never used)'
edf3e38e
PH
2545 for i, prev in zip(idxs[1:], idxs[:-1]):
2546 if step is not None:
2547 if i - prev == step:
2548 continue
2549 yield _genslice(start, prev, step)
2550 step = None
2551 continue
2552 if i - prev in [-1, 1]:
2553 step = i - prev
2554 start = prev
2555 continue
2556 else:
78caa52a 2557 yield 's[%d]' % prev
edf3e38e 2558 if step is None:
78caa52a 2559 yield 's[%d]' % i
edf3e38e
PH
2560 else:
2561 yield _genslice(start, i, step)
2562
ac668111 2563 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2564 cache_res = func(test_string)
edf3e38e 2565 cache_spec = [ord(c) for c in cache_res]
78caa52a 2566 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2567 signature_id_tuple = '(%s)' % (
14f25df2 2568 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2569 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2570 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2571 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2572
e0df6211
PH
2573 def _parse_sig_js(self, jscode):
2574 funcname = self._search_regex(
abefc03f
S
2575 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2576 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
2577 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2578 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2579 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}\(a,\d+\)',
2580 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 2581 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2582 # Obsolete patterns
2583 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2584 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2585 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2586 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2587 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2588 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2589 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2590 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2591 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2592
2593 jsi = JSInterpreter(jscode)
2594 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2595 return lambda s: initial_function([s])
2596
545cc85d 2597 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2598 """Turn the encrypted s field into a working signature"""
c8bf86d5 2599 try:
62af3a0e 2600 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5 2601 if player_id not in self._player_cache:
52023f12 2602 func = self._extract_signature_function(video_id, player_url, s)
c8bf86d5
PH
2603 self._player_cache[player_id] = func
2604 func = self._player_cache[player_id]
404f611f 2605 self._print_sig_code(func, s)
c8bf86d5
PH
2606 return func(s)
2607 except Exception as e:
52023f12 2608 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2609
2610 def _decrypt_nsig(self, s, video_id, player_url):
2611 """Turn the encrypted n field into a working signature"""
2612 if player_url is None:
2613 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2614 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2615
2616 sig_id = ('nsig_value', s)
2617 if sig_id in self._player_cache:
2618 return self._player_cache[sig_id]
2619
2620 try:
2621 player_id = ('nsig', player_url)
2622 if player_id not in self._player_cache:
2623 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2624 func = self._player_cache[player_id]
2625 self._player_cache[sig_id] = func(s)
2626 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2627 return self._player_cache[sig_id]
2628 except Exception as e:
aa9369a2 2629 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2630
2631 def _extract_n_function_name(self, jscode):
48416bc4 2632 nfunc, idx = self._search_regex(
c571b3a6 2633 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2634 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2635 if not idx:
2636 return nfunc
2637 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2638 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2639 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2640
2641 def _extract_n_function(self, video_id, player_url):
2642 player_id = self._extract_player_info(player_url)
9809740b 2643 func_code = self.cache.load('youtube-nsig', player_id)
404f611f 2644
2645 if func_code:
2646 jsi = JSInterpreter(func_code)
2647 else:
2648 jscode = self._load_player(video_id, player_url)
2649 funcname = self._extract_n_function_name(jscode)
2650 jsi = JSInterpreter(jscode)
2651 func_code = jsi.extract_function_code(funcname)
9809740b 2652 self.cache.store('youtube-nsig', player_id, func_code)
404f611f 2653
2654 if self.get_param('youtube_print_sig_code'):
2655 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2656
2657 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2658
109dd3b2 2659 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2660 """
2661 Extract signatureTimestamp (sts)
2662 Required to tell API what sig/player version is in use.
2663 """
2664 sts = None
2665 if isinstance(ytcfg, dict):
2666 sts = int_or_none(ytcfg.get('STS'))
2667
2668 if not sts:
2669 # Attempt to extract from player
2670 if player_url is None:
2671 error_msg = 'Cannot extract signature timestamp without player_url.'
2672 if fatal:
2673 raise ExtractorError(error_msg)
2674 self.report_warning(error_msg)
2675 return
404f611f 2676 code = self._load_player(video_id, player_url, fatal=fatal)
2677 if code:
109dd3b2 2678 sts = int_or_none(self._search_regex(
2679 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2680 'JS player signature timestamp', group='sts', fatal=fatal))
2681 return sts
2682
11f9be09 2683 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
2684 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2685 label = 'fully ' if is_full else ''
2686 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2687 expected_type=url_or_none)
2688 if not url:
2689 self.report_warning(f'Unable to mark {label}watched')
2690 return
14f25df2 2691 parsed_url = urllib.parse.urlparse(url)
2692 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
2693
2694 # cpn generation algorithm is reverse engineered from base.js.
2695 # In fact it works even with dummy cpn.
2696 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2697 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2698
2699 # # more consistent results setting it to right before the end
2700 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2701
2702 qs.update({
2703 'ver': ['2'],
2704 'cpn': [cpn],
2705 'cmt': video_length,
2706 'el': 'detailpage', # otherwise defaults to "shorts"
2707 })
2708
2709 if is_full:
2710 # these seem to mark watchtime "history" in the real world
2711 # they're required, so send in a single value
2712 qs.update({
2713 'st': video_length,
2714 'et': video_length,
2715 })
2716
14f25df2 2717 url = urllib.parse.urlunparse(
2718 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
2719
2720 self._download_webpage(
2721 url, video_id, f'Marking {label}watched',
2722 'Unable to mark watched', fatal=False)
d77ab8e2 2723
66c9fa36
S
2724 @staticmethod
2725 def _extract_urls(webpage):
2726 # Embedded YouTube player
2727 entries = [
2728 unescapeHTML(mobj.group('url'))
2729 for mobj in re.finditer(r'''(?x)
2730 (?:
2731 <iframe[^>]+?src=|
2732 data-video-url=|
2733 <embed[^>]+?src=|
2734 embedSWF\(?:\s*|
2735 <object[^>]+data=|
2736 new\s+SWFObject\(
2737 )
2738 (["\'])
2739 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2740 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2741 \1''', webpage)]
2742
2743 # lazyYT YouTube embed
2744 entries.extend(list(map(
2745 unescapeHTML,
2746 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2747
2748 # Wordpress "YouTube Video Importer" plugin
2749 matches = re.findall(r'''(?x)<div[^>]+
2750 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2751 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2752 entries.extend(m[-1] for m in matches)
2753
2754 return entries
2755
2756 @staticmethod
2757 def _extract_url(webpage):
2758 urls = YoutubeIE._extract_urls(webpage)
2759 return urls[0] if urls else None
2760
97665381
PH
2761 @classmethod
2762 def extract_id(cls, url):
ae61d108 2763 video_id = cls.get_temp_id(url)
2764 if not video_id:
2765 raise ExtractorError(f'Invalid URL: {url}')
2766 return video_id
c5e8d7af 2767
7c365c21 2768 def _extract_chapters_from_json(self, data, duration):
2769 chapter_list = traverse_obj(
2770 data, (
2771 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2772 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2773 ), expected_type=list)
2774
2775 return self._extract_chapters(
2776 chapter_list,
2777 chapter_time=lambda chapter: float_or_none(
2778 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2779 chapter_title=lambda chapter: traverse_obj(
2780 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2781 duration=duration)
2782
2783 def _extract_chapters_from_engagement_panel(self, data, duration):
2784 content_list = traverse_obj(
8bdd16b4 2785 data,
7c365c21 2786 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2787 expected_type=list, default=[])
052e1350 2788 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2789 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2790
1890fc63 2791 return next(filter(None, (
2792 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2793 chapter_time, chapter_title, duration)
2794 for contents in content_list)), [])
7c365c21 2795
1890fc63 2796 def _extract_chapters_from_description(self, description, duration):
2797 return self._extract_chapters(
2798 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2799 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2800 duration=duration, strict=False)
84213ea8 2801
1890fc63 2802 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2803 if not duration:
2804 return
2805 chapter_list = [{
2806 'start_time': chapter_time(chapter),
2807 'title': chapter_title(chapter),
2808 } for chapter in chapter_list or []]
2809 if not strict:
2810 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2811
a3976e07 2812 chapters = [{'start_time': 0}]
1890fc63 2813 for idx, chapter in enumerate(chapter_list):
a3976e07 2814 if chapter['start_time'] is None:
1890fc63 2815 self.report_warning(f'Incomplete chapter {idx}')
2816 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
1890fc63 2817 chapters.append(chapter)
2818 else:
2819 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}"')
a3976e07 2820 return chapters[1:]
84213ea8 2821
a1c5d2ca
M
2822 def _extract_comment(self, comment_renderer, parent=None):
2823 comment_id = comment_renderer.get('commentId')
2824 if not comment_id:
2825 return
fe93e2c4 2826
052e1350 2827 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2828
49bd8c66 2829 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2830 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2831 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca 2832 author_id = try_get(comment_renderer,
14f25df2 2833 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
fe93e2c4 2834
49bd8c66 2835 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
14f25df2 2836 lambda x: x['likeCount']), str)) or 0
a1c5d2ca 2837 author_thumbnail = try_get(comment_renderer,
14f25df2 2838 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
a1c5d2ca
M
2839
2840 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2841 is_favorited = 'creatorHeart' in (try_get(
2842 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2843 return {
2844 'id': comment_id,
2845 'text': text,
d92f5d5a 2846 'timestamp': timestamp,
a1c5d2ca
M
2847 'time_text': time_text,
2848 'like_count': votes,
97524332 2849 'is_favorited': is_favorited,
a1c5d2ca
M
2850 'author': author,
2851 'author_id': author_id,
2852 'author_thumbnail': author_thumbnail,
2853 'author_is_uploader': author_is_uploader,
2854 'parent': parent or 'root'
2855 }
2856
46383212 2857 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2858
2859 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2860
2861 def extract_header(contents):
2d6659b9 2862 _continuation = None
2863 for content in contents:
46383212 2864 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2865 expected_comment_count = self._get_count(
2866 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2867
2d6659b9 2868 if expected_comment_count:
46383212 2869 tracker['est_total'] = expected_comment_count
2870 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2871 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2872
2873 sort_menu_item = try_get(
2874 comments_header_renderer,
2875 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2876 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2877
2878 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2879 if not _continuation:
2880 continue
2881
46383212 2882 sort_text = str_or_none(sort_menu_item.get('title'))
2883 if not sort_text:
2d6659b9 2884 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2885 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2886 break
a2160aa4 2887 return _continuation
a1c5d2ca 2888
2d6659b9 2889 def extract_thread(contents):
a1c5d2ca 2890 if not parent:
46383212 2891 tracker['current_page_thread'] = 0
a1c5d2ca 2892 for content in contents:
46383212 2893 if not parent and tracker['total_parent_comments'] >= max_parents:
2894 yield
a1c5d2ca 2895 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2896 comment_renderer = get_first(
2897 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2898 expected_type=dict, default={})
a1c5d2ca 2899
a1c5d2ca
M
2900 comment = self._extract_comment(comment_renderer, parent)
2901 if not comment:
2902 continue
46383212 2903
2904 tracker['running_total'] += 1
2905 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2906 yield comment
46383212 2907
a1c5d2ca
M
2908 # Attempt to get the replies
2909 comment_replies_renderer = try_get(
2910 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2911
2912 if comment_replies_renderer:
46383212 2913 tracker['current_page_thread'] += 1
a1c5d2ca 2914 comment_entries_iter = self._comment_entries(
99e9e001 2915 comment_replies_renderer, ytcfg, video_id,
46383212 2916 parent=comment.get('id'), tracker=tracker)
86e5f3ed 2917 yield from itertools.islice(comment_entries_iter, min(
2918 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 2919
46383212 2920 # Keeps track of counts across recursive calls
2921 if not tracker:
2922 tracker = dict(
2923 running_total=0,
2924 est_total=0,
2925 current_page_thread=0,
2926 total_parent_comments=0,
2927 total_reply_comments=0)
2928
2929 # TODO: Deprecated
2d6659b9 2930 # YouTube comments have a max depth of 2
46383212 2931 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2932 if max_depth:
2933 self._downloader.deprecation_warning(
2934 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2935 if max_depth == 1 and parent:
2936 return
a1c5d2ca 2937
46383212 2938 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2939 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2940
46383212 2941 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2942
46383212 2943 response = None
6e634cbe 2944 is_forced_continuation = False
2d6659b9 2945 is_first_continuation = parent is None
6e634cbe 2946 if is_first_continuation and not continuation:
2947 # Sometimes you can get comments by generating the continuation yourself,
2948 # even if YouTube initially reports them being disabled - e.g. stories comments.
2949 # Note: if the comment section is actually disabled, YouTube may return a response with
2950 # required check_get_keys missing. So we will disable that check initially in this case.
2951 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2952 is_forced_continuation = True
a1c5d2ca
M
2953
2954 for page_num in itertools.count(0):
2955 if not continuation:
2956 break
46383212 2957 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2958 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2959 if page_num == 0:
2960 if is_first_continuation:
2961 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2962 else:
2d6659b9 2963 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2964 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2965 else:
2966 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2967 ' ' if parent else '', ' replies' if parent else '',
2968 page_num, comment_prog_str)
2969
2970 response = self._extract_response(
fe93e2c4 2971 item_id=None, query=continuation,
2d6659b9 2972 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
6e634cbe 2973 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2974 is_forced_continuation = False
46383212 2975 continuation_contents = traverse_obj(
2976 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2977
2d6659b9 2978 continuation = None
46383212 2979 for continuation_section in continuation_contents:
2980 continuation_items = traverse_obj(
2981 continuation_section,
2982 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2983 get_all=False, expected_type=list) or []
2984 if is_first_continuation:
2985 continuation = extract_header(continuation_items)
2986 is_first_continuation = False
2d6659b9 2987 if continuation:
a1c5d2ca 2988 break
46383212 2989 continue
a1c5d2ca 2990
46383212 2991 for entry in extract_thread(continuation_items):
2992 if not entry:
2993 return
2994 yield entry
2995 continuation = self._extract_continuation({'contents': continuation_items})
2996 if continuation:
2d6659b9 2997 break
a1c5d2ca 2998
6e634cbe 2999 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3000 if message and not parent and tracker['running_total'] == 0:
3001 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3002
3003 @staticmethod
3004 def _generate_comment_continuation(video_id):
3005 """
3006 Generates initial comment section continuation token from given video id
3007 """
3008 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3009 return base64.b64encode(token.encode()).decode()
3010
a2160aa4 3011 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3012 """Entry for comment extraction"""
2d6659b9 3013 def _real_comment_extract(contents):
aae16f6e 3014 renderer = next((
3015 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3016 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3017 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3018
a2160aa4 3019 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3020 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3021
109dd3b2 3022 @staticmethod
99e9e001 3023 def _get_checkok_params():
3024 return {'contentCheckOk': True, 'racyCheckOk': True}
3025
3026 @classmethod
3027 def _generate_player_context(cls, sts=None):
109dd3b2 3028 context = {
3029 'html5Preference': 'HTML5_PREF_WANTS',
3030 }
3031 if sts is not None:
3032 context['signatureTimestamp'] = sts
3033 return {
3034 'playbackContext': {
3035 'contentPlaybackContext': context
a1a7907b 3036 },
99e9e001 3037 **cls._get_checkok_params()
109dd3b2 3038 }
3039
e7e94f2a
D
3040 @staticmethod
3041 def _is_agegated(player_response):
3042 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3043 return True
e7e94f2a
D
3044
3045 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3046 AGE_GATE_REASONS = (
3047 'confirm your age', 'age-restricted', 'inappropriate', # reason
3048 'age_verification_required', 'age_check_required', # status
3049 )
3050 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3051
3052 @staticmethod
3053 def _is_unplayable(player_response):
3054 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3055
99e9e001 3056 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 3057
11f9be09 3058 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3059 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3060 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3061 headers = self.generate_api_headers(
99e9e001 3062 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3063
6e634cbe 3064 yt_query = {
3065 'videoId': video_id,
3066 'params': '8AEB' # enable stories
3067 }
11f9be09 3068 yt_query.update(self._generate_player_context(sts))
3069 return self._extract_response(
3070 item_id=video_id, ep='player', query=yt_query,
379e44ed 3071 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3072 default_client=client,
11f9be09 3073 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3074 ) or None
3075
11f9be09 3076 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3077 requested_clients = []
d0d012d4 3078 default = ['android', 'web']
000c15a4 3079 allowed_clients = sorted(
86e5f3ed 3080 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3081 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3082 for client in self._configuration_arg('player_client'):
3083 if client in allowed_clients:
3084 requested_clients.append(client)
d0d012d4 3085 elif client == 'default':
3086 requested_clients.extend(default)
b4c055ba 3087 elif client == 'all':
3088 requested_clients.extend(allowed_clients)
3089 else:
3090 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3091 if not requested_clients:
d0d012d4 3092 requested_clients = default
cf7e015f 3093
11f9be09 3094 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3095 requested_clients.extend(
e7e94f2a 3096 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3097
11f9be09 3098 return orderedSet(requested_clients)
cf7e015f 3099
99e9e001 3100 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 3101 initial_pr = None
3102 if webpage:
b7c47b74 3103 initial_pr = self._search_json(
3104 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3105
ae729626 3106 all_clients = set(clients)
c0bc527b 3107 clients = clients[::-1]
b6de707d 3108 prs = []
e7e94f2a 3109
ae729626 3110 def append_client(*client_names):
e7870111 3111 """ Append the first client name that exists but not already used """
ae729626 3112 for client_name in client_names:
e7870111
D
3113 actual_client = _split_innertube_client(client_name)[0]
3114 if actual_client in INNERTUBE_CLIENTS:
3115 if actual_client not in all_clients:
ae729626 3116 clients.append(client_name)
e7870111
D
3117 all_clients.add(actual_client)
3118 return
e7e94f2a 3119
379e44ed 3120 # Android player_response does not have microFormats which are needed for
3121 # extraction of some data. So we return the initial_pr with formats
3122 # stripped out even if not requested by the user
3123 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3124 if initial_pr:
3125 pr = dict(initial_pr)
3126 pr['streamingData'] = None
b6de707d 3127 prs.append(pr)
379e44ed 3128
3129 last_error = None
b6de707d 3130 tried_iframe_fallback = False
3131 player_url = None
c0bc527b 3132 while clients:
e7870111 3133 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3134 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3135 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3136 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3137
b6de707d 3138 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3139 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3140 if 'js' in self._configuration_arg('player_skip'):
3141 require_js_player = False
3142 player_url = None
3143
3144 if not player_url and not tried_iframe_fallback and require_js_player:
3145 player_url = self._download_player_url(video_id)
3146 tried_iframe_fallback = True
3147
379e44ed 3148 try:
3149 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 3150 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 3151 except ExtractorError as e:
3152 if last_error:
3153 self.report_warning(last_error)
3154 last_error = e
3155 continue
3156
11f9be09 3157 if pr:
b6de707d 3158 prs.append(pr)
c0bc527b 3159
e7e94f2a 3160 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3161 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3162 append_client(f'{base_client}_creator')
e7e94f2a 3163 elif self._is_agegated(pr):
e7870111
D
3164 if variant == 'tv_embedded':
3165 append_client(f'{base_client}_embedded')
3166 elif not variant:
3167 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3168
379e44ed 3169 if last_error:
b6de707d 3170 if not len(prs):
379e44ed 3171 raise last_error
3172 self.report_warning(last_error)
b6de707d 3173 return prs, player_url
11f9be09 3174
c646d76f 3175 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3176 itags, stream_ids = {}, []
2a9c6dcd 3177 itag_qualities, res_qualities = {}, {}
d3fc8074 3178 q = qualities([
2a9c6dcd 3179 # Normally tiny is the smallest video-only formats. But
3180 # audio-only formats with unknown quality may get tagged as tiny
3181 'tiny',
3182 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3183 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3184 ])
11f9be09 3185 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3186
545cc85d 3187 for fmt in streaming_formats:
727029c5 3188 if fmt.get('targetDurationSec'):
545cc85d 3189 continue
321bf820 3190
cc2db878 3191 itag = str_or_none(fmt.get('itag'))
9297939e 3192 audio_track = fmt.get('audioTrack') or {}
3193 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3194 if stream_id in stream_ids:
3195 continue
3196
cc2db878 3197 quality = fmt.get('quality')
2a9c6dcd 3198 height = int_or_none(fmt.get('height'))
d3fc8074 3199 if quality == 'tiny' or not quality:
3200 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3201 # The 3gp format (17) in android client has a quality of "small",
3202 # but is actually worse than other formats
3203 if itag == '17':
3204 quality = 'tiny'
3205 if quality:
3206 if itag:
3207 itag_qualities[itag] = quality
3208 if height:
3209 res_qualities[height] = quality
cc2db878 3210 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3211 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3212 # number of fragment that would subsequently requested with (`&sq=N`)
3213 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3214 continue
3215
545cc85d 3216 fmt_url = fmt.get('url')
3217 if not fmt_url:
14f25df2 3218 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3219 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3220 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3221 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3222 continue
52023f12 3223 try:
3224 fmt_url += '&%s=%s' % (
3225 traverse_obj(sc, ('sp', -1)) or 'signature',
3226 self._decrypt_signature(encrypted_sig, video_id, player_url)
3227 )
3228 except ExtractorError as e:
3229 self.report_warning('Signature extraction failed: Some formats may be missing', only_once=True)
3230 self.write_debug(e, only_once=True)
201e9eaa 3231 continue
545cc85d 3232
404f611f 3233 query = parse_qs(fmt_url)
3234 throttled = False
b2916526 3235 if query.get('n'):
404f611f 3236 try:
3237 fmt_url = update_url_query(fmt_url, {
3238 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3239 except ExtractorError as e:
aa9369a2 3240 self.report_warning(
1d485a1a 3241 'nsig extraction failed: You may experience throttling for some formats\n'
52023f12 3242 f'n = {query["n"][0]} ; player = {player_url}', only_once=True)
3243 self.write_debug(e, only_once=True)
404f611f 3244 throttled = True
3245
545cc85d 3246 if itag:
a0bb6ce5 3247 itags[itag] = 'https'
9297939e 3248 stream_ids.append(stream_id)
3249
0ad92dfb 3250 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3251 language_preference = (
3252 10 if audio_track.get('audioIsDefault') and 10
3253 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3254 else -1)
0ad92dfb 3255 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3256 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3257 # Make sure to avoid false positives with small duration differences.
3258 # Eg: __2ABJjxzNo, ySuUZEjARPY
3259 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3260 if is_damaged:
0f06bcd7 3261 self.report_warning(
3262 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3263 dct = {
3264 'asr': int_or_none(fmt.get('audioSampleRate')),
3265 'filesize': int_or_none(fmt.get('contentLength')),
3266 'format_id': itag,
34921b43 3267 'format_note': join_nonempty(
26e8e044 3268 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3269 ' (default)' if language_preference > 0 else ''),
404f611f 3270 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
0ad92dfb 3271 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3272 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3273 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3274 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3275 'height': height,
dca3ff4a 3276 'quality': q(quality),
727029c5 3277 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3278 'tbr': tbr,
545cc85d 3279 'url': fmt_url,
2a9c6dcd 3280 'width': int_or_none(fmt.get('width')),
ab6df717 3281 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3282 'desc' if language_preference < -1 else ''),
3283 'language_preference': language_preference,
a405b38f 3284 # Strictly de-prioritize damaged and 3gp formats
3285 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3286 }
60bdb7bd 3287 mime_mobj = re.match(
3288 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3289 if mime_mobj:
3290 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3291 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3292 no_audio = dct.get('acodec') == 'none'
3293 no_video = dct.get('vcodec') == 'none'
3294 if no_audio:
3295 dct['vbr'] = tbr
3296 if no_video:
3297 dct['abr'] = tbr
3298 if no_audio or no_video:
545cc85d 3299 dct['downloader_options'] = {
3300 # Youtube throttles chunks >~10M
3301 'http_chunk_size': 10485760,
bf1317d2 3302 }
7c60c33e 3303 if dct.get('ext'):
3304 dct['container'] = dct['ext'] + '_dash'
11f9be09 3305 yield dct
545cc85d 3306
adbc4ec4 3307 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3308 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3309 if not self.get_param('youtube_include_hls_manifest', True):
3310 skip_manifests.append('hls')
0f06bcd7 3311 if not self.get_param('youtube_include_dash_manifest', True):
3312 skip_manifests.append('dash')
adbc4ec4
THD
3313 get_dash = 'dash' not in skip_manifests and (
3314 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3315 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3316
a0bb6ce5 3317 def process_manifest_format(f, proto, itag):
3318 if itag in itags:
3319 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3320 return False
3321 itag = f'{itag}-{proto}'
3322 if itag:
3323 f['format_id'] = itag
3324 itags[itag] = proto
3325
3326 f['quality'] = next((
3327 q(qdict[val])
e339d25a 3328 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3329 if val in qdict), -1)
3330 return True
2a9c6dcd 3331
c646d76f 3332 subtitles = {}
11f9be09 3333 for sd in streaming_data:
5d3a0e79 3334 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3335 if hls_manifest_url:
c646d76f 3336 fmts, subs = self._extract_m3u8_formats_and_subtitles(hls_manifest_url, video_id, 'mp4', fatal=False, live=is_live)
3337 subtitles = self._merge_subtitles(subs, subtitles)
3338 for f in fmts:
a0bb6ce5 3339 if process_manifest_format(f, 'hls', self._search_regex(
3340 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3341 yield f
545cc85d 3342
5d3a0e79 3343 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3344 if dash_manifest_url:
c646d76f 3345 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3346 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3347 for f in formats:
a0bb6ce5 3348 if process_manifest_format(f, 'dash', f['format_id']):
3349 f['filesize'] = int_or_none(self._search_regex(
3350 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3351 if live_from_start:
3352 f['is_from_start'] = True
3353
a0bb6ce5 3354 yield f
c646d76f 3355 yield subtitles
11f9be09 3356
720c3099 3357 def _extract_storyboard(self, player_responses, duration):
3358 spec = get_first(
3359 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3360 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3361 if not base_url:
720c3099 3362 return
720c3099 3363 L = len(spec) - 1
3364 for i, args in enumerate(spec):
3365 args = args.split('#')
3366 counts = list(map(int_or_none, args[:5]))
3367 if len(args) != 8 or not all(counts):
3368 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3369 continue
3370 width, height, frame_count, cols, rows = counts
3371 N, sigh = args[6:]
3372
3373 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3374 fragment_count = frame_count / (cols * rows)
3375 fragment_duration = duration / fragment_count
3376 yield {
3377 'format_id': f'sb{i}',
3378 'format_note': 'storyboard',
3379 'ext': 'mhtml',
3380 'protocol': 'mhtml',
3381 'acodec': 'none',
3382 'vcodec': 'none',
3383 'url': url,
3384 'width': width,
3385 'height': height,
45e8a04e 3386 'fps': frame_count / duration,
3387 'rows': rows,
3388 'columns': cols,
720c3099 3389 'fragments': [{
b3edc806 3390 'url': url.replace('$M', str(j)),
720c3099 3391 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3392 } for j in range(math.ceil(fragment_count))],
3393 }
3394
adbc4ec4 3395 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3396 webpage = None
3397 if 'webpage' not in self._configuration_arg('player_skip'):
3398 webpage = self._download_webpage(
6e634cbe 3399 webpage_url + '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id, fatal=False)
11f9be09 3400
3401 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3402
b6de707d 3403 player_responses, player_url = self._extract_player_responses(
11f9be09 3404 self._get_requested_clients(url, smuggled_data),
99e9e001 3405 video_id, webpage, master_ytcfg)
11f9be09 3406
adbc4ec4
THD
3407 return webpage, master_ytcfg, player_responses, player_url
3408
a1b2d843 3409 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3410 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3411 is_live = get_first(video_details, 'isLive')
3412 if is_live is None:
3413 is_live = get_first(live_broadcast_details, 'isLiveNow')
3414
3415 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
c646d76f 3416 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, is_live, duration)
adbc4ec4 3417
c646d76f 3418 return live_broadcast_details, is_live, streaming_data, formats, subtitles
adbc4ec4
THD
3419
3420 def _real_extract(self, url):
3421 url, smuggled_data = unsmuggle_url(url, {})
3422 video_id = self._match_id(url)
3423
3424 base_url = self.http_scheme() + '//www.youtube.com/'
3425 webpage_url = base_url + 'watch?v=' + video_id
3426
3427 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3428
11f9be09 3429 playability_statuses = traverse_obj(
3430 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3431
3432 trailer_video_id = get_first(
3433 playability_statuses,
3434 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3435 expected_type=str)
3436 if trailer_video_id:
3437 return self.url_result(
3438 trailer_video_id, self.ie_key(), trailer_video_id)
3439
3440 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3441 if webpage else (lambda x: None))
3442
3443 video_details = traverse_obj(
3444 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3445 microformats = traverse_obj(
3446 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3447 expected_type=dict, default=[])
3448 video_title = (
3449 get_first(video_details, 'title')
3450 or self._get_text(microformats, (..., 'title'))
3451 or search_meta(['og:title', 'twitter:title', 'title']))
3452 video_description = get_first(video_details, 'shortDescription')
3453
d89257f3 3454 multifeed_metadata_list = get_first(
3455 player_responses,
3456 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3457 expected_type=str)
3458 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3459 if self.get_param('noplaylist'):
11f9be09 3460 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3461 else:
3462 entries = []
3463 feed_ids = []
3464 for feed in multifeed_metadata_list.split(','):
3465 # Unquote should take place before split on comma (,) since textual
3466 # fields may contain comma as well (see
3467 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3468 feed_data = urllib.parse.parse_qs(
ac668111 3469 urllib.parse.unquote_plus(feed))
d89257f3 3470
3471 def feed_entry(name):
3472 return try_get(
14f25df2 3473 feed_data, lambda x: x[name][0], str)
d89257f3 3474
3475 feed_id = feed_entry('id')
3476 if not feed_id:
3477 continue
3478 feed_title = feed_entry('title')
3479 title = video_title
3480 if feed_title:
3481 title += ' (%s)' % feed_title
3482 entries.append({
3483 '_type': 'url_transparent',
3484 'ie_key': 'Youtube',
3485 'url': smuggle_url(
3486 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3487 {'force_singlefeed': True}),
3488 'title': title,
3489 })
3490 feed_ids.append(feed_id)
3491 self.to_screen(
3492 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3493 % (', '.join(feed_ids), video_id))
3494 return self.playlist_result(
3495 entries, video_id, video_title, video_description)
11f9be09 3496
a1b2d843 3497 duration = int_or_none(
3498 get_first(video_details, 'lengthSeconds')
3499 or get_first(microformats, 'lengthSeconds')
3500 or parse_duration(search_meta('duration'))) or None
3501
c646d76f 3502 live_broadcast_details, is_live, streaming_data, formats, automatic_captions = \
3503 self._list_formats(video_id, microformats, video_details, player_responses, player_url)
bf1317d2 3504
545cc85d 3505 if not formats:
11f9be09 3506 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3507 self.report_drm(video_id)
11f9be09 3508 pemr = get_first(
3509 playability_statuses,
3510 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3511 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3512 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3513 if subreason:
545cc85d 3514 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3515 countries = get_first(microformats, 'availableCountries')
545cc85d 3516 if not countries:
3517 regions_allowed = search_meta('regionsAllowed')
3518 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3519 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3520 reason += f'. {subreason}'
545cc85d 3521 if reason:
b7da73eb 3522 self.raise_no_formats(reason, expected=True)
bf1317d2 3523
11f9be09 3524 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3525 if not keywords and webpage:
3526 keywords = [
3527 unescapeHTML(m.group('content'))
3528 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3529 for keyword in keywords:
3530 if keyword.startswith('yt:stretch='):
201c1459 3531 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3532 if mobj:
3533 # NB: float is intentional for forcing float division
3534 w, h = (float(v) for v in mobj.groups())
3535 if w > 0 and h > 0:
3536 ratio = w / h
3537 for f in formats:
3538 if f.get('vcodec') != 'none':
3539 f['stretched_ratio'] = ratio
3540 break
a709d873 3541 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3542 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3543 if thumbnail_url:
3544 thumbnails.append({
3545 'url': thumbnail_url,
ff2751ac 3546 })
fccf5021 3547 original_thumbnails = thumbnails.copy()
3548
0ba692ac 3549 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3550 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3551 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3552 thumbnail_names = [
962ffcf8 3553 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 3554 # in resolution, these are not the custom thumbnail. So de-prioritize them
3555 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3556 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3557 ]
cca80fe6 3558 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3559 thumbnails.extend({
3560 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3561 video_id=video_id, name=name, ext=ext,
3562 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3563 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3564 for thumb in thumbnails:
cca80fe6 3565 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3566 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3567 self._remove_duplicate_formats(thumbnails)
fccf5021 3568 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3569
7ea65411 3570 category = get_first(microformats, 'category') or search_meta('genre')
3571 channel_id = str_or_none(
3572 get_first(video_details, 'channelId')
3573 or get_first(microformats, 'externalChannelId')
3574 or search_meta('channelId'))
7ea65411 3575 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3576
3577 live_content = get_first(video_details, 'isLiveContent')
3578 is_upcoming = get_first(video_details, 'isUpcoming')
3579 if is_live is None:
3580 if is_upcoming or live_content is False:
3581 is_live = False
3582 if is_upcoming is None and (live_content or is_live):
3583 is_upcoming = False
adbc4ec4
THD
3584 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3585 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3586 if not duration and live_end_time and live_start_time:
3587 duration = live_end_time - live_start_time
3588
3589 if is_live and self.get_param('live_from_start'):
3590 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3591
720c3099 3592 formats.extend(self._extract_storyboard(player_responses, duration))
3593
31b532a1 3594 # source_preference is lower for throttled/potentially damaged formats
720c3099 3595 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3596
545cc85d 3597 info = {
3598 'id': video_id,
39ca3b5c 3599 'title': video_title,
545cc85d 3600 'formats': formats,
3601 'thumbnails': thumbnails,
fccf5021 3602 # The best thumbnail that we are sure exists. Prevents unnecessary
3603 # URL checking if user don't care about getting the best possible thumbnail
3604 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3605 'description': video_description,
11f9be09 3606 'uploader': get_first(video_details, 'author'),
545cc85d 3607 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3608 'uploader_url': owner_profile_url,
3609 'channel_id': channel_id,
a70635b8 3610 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3611 'duration': duration,
3612 'view_count': int_or_none(
11f9be09 3613 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3614 or search_meta('interactionCount')),
11f9be09 3615 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3616 'age_limit': 18 if (
11f9be09 3617 get_first(microformats, 'isFamilySafe') is False
545cc85d 3618 or search_meta('isFamilyFriendly') == 'false'
3619 or search_meta('og:restrictions:age') == '18+') else 0,
3620 'webpage_url': webpage_url,
3621 'categories': [category] if category else None,
3622 'tags': keywords,
11f9be09 3623 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3624 'is_live': is_live,
3625 'was_live': (False if is_live or is_upcoming or live_content is False
3626 else None if is_live is None or is_upcoming is None
3627 else live_content),
3628 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3629 'release_timestamp': live_start_time,
545cc85d 3630 }
b477fc13 3631
e325a21a 3632 if get_first(video_details, 'isPostLiveDvr'):
3633 self.write_debug('Video is in Post-Live Manifestless mode')
3634 info['live_status'] = 'post_live'
3635 if (duration or 0) > 4 * 3600:
3636 self.report_warning(
3637 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3638 'This is a known issue and patches are welcome')
3639
c646d76f 3640 subtitles = {}
3944e7af 3641 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3642 if pctr:
ecdc9049 3643 def get_lang_code(track):
3644 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3645 or track.get('languageCode'))
3646
3647 # Converted into dicts to remove duplicates
3648 captions = {
3649 get_lang_code(sub): sub
3650 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3651 translation_languages = {
3652 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3653 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3654
774d79cc 3655 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3656 lang_subs = container.setdefault(lang_code, [])
545cc85d 3657 for fmt in self._SUBTITLE_FORMATS:
3658 query.update({
3659 'fmt': fmt,
3660 })
3661 lang_subs.append({
3662 'ext': fmt,
60f393e4 3663 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3664 'name': sub_name,
545cc85d 3665 })
7e72694b 3666
07b47084 3667 # NB: Constructing the full subtitle dictionary is slow
3668 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
3669 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 3670 for lang_code, caption_track in captions.items():
3671 base_url = caption_track.get('baseUrl')
1235d333 3672 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3673 if not base_url:
3674 continue
ecdc9049 3675 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3676 if caption_track.get('kind') != 'asr':
545cc85d 3677 if not lang_code:
3678 continue
3679 process_language(
ecdc9049 3680 subtitles, base_url, lang_code, lang_name, {})
3681 if not caption_track.get('isTranslatable'):
3682 continue
3944e7af 3683 for trans_code, trans_name in translation_languages.items():
3684 if not trans_code:
545cc85d 3685 continue
1235d333 3686 orig_trans_code = trans_code
ecdc9049 3687 if caption_track.get('kind') != 'asr':
07b47084 3688 if not get_translated_subs:
18e49408 3689 continue
ecdc9049 3690 trans_code += f'-{lang_code}'
a70635b8 3691 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 3692 # Add an "-orig" label to the original language so that it can be distinguished.
3693 # The subs are returned without "-orig" as well for compatibility
1235d333 3694 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3695 process_language(
d49669ac 3696 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3697 # Setting tlang=lang returns damaged subtitles.
d49669ac 3698 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3699 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 3700
3701 info['automatic_captions'] = automatic_captions
3702 info['subtitles'] = subtitles
7e72694b 3703
14f25df2 3704 parsed_url = urllib.parse.urlparse(url)
545cc85d 3705 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 3706 query = urllib.parse.parse_qs(component)
545cc85d 3707 for k, v in query.items():
3708 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3709 d_k += '_time'
3710 if d_k not in info and k in s_ks:
3711 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3712
3713 # Youtube Music Auto-generated description
822b9d9c 3714 if video_description:
1890fc63 3715 mobj = re.search(
3716 r'''(?xs)
3717 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3718 (?P<album>[^\n]+)
3719 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3720 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3721 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3722 .+\nAuto-generated\ by\ YouTube\.\s*$
3723 ''', video_description)
822b9d9c 3724 if mobj:
822b9d9c
RA
3725 release_year = mobj.group('release_year')
3726 release_date = mobj.group('release_date')
3727 if release_date:
3728 release_date = release_date.replace('-', '')
3729 if not release_year:
545cc85d 3730 release_year = release_date[:4]
3731 info.update({
3732 'album': mobj.group('album'.strip()),
3733 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3734 'track': mobj.group('track').strip(),
3735 'release_date': release_date,
cc2db878 3736 'release_year': int_or_none(release_year),
545cc85d 3737 })
7e72694b 3738
545cc85d 3739 initial_data = None
3740 if webpage:
56ba69e4 3741 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 3742 if not initial_data:
99e9e001 3743 query = {'videoId': video_id}
3744 query.update(self._get_checkok_params())
109dd3b2 3745 initial_data = self._extract_response(
3746 item_id=video_id, ep='next', fatal=False,
99e9e001 3747 ytcfg=master_ytcfg, query=query,
3748 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3749 note='Downloading initial data API JSON')
545cc85d 3750
0df111a3 3751 info['comment_count'] = traverse_obj(initial_data, (
3752 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3753 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3754 ), (
3755 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3756 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3757 ), expected_type=int_or_none, get_all=False)
3758
19a03940 3759 try: # This will error if there is no livechat
c60ee3a2 3760 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 3761 except (KeyError, IndexError, TypeError):
3762 pass
3763 else:
ecdc9049 3764 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 3765 # url is needed to set cookies
3766 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 3767 'video_id': video_id,
3768 'ext': 'json',
f6745c49 3769 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3770 }]
545cc85d 3771
3772 if initial_data:
7c365c21 3773 info['chapters'] = (
3774 self._extract_chapters_from_json(initial_data, duration)
3775 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 3776 or self._extract_chapters_from_description(video_description, duration)
7c365c21 3777 or None)
545cc85d 3778
17322130 3779 contents = traverse_obj(
3780 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3781 expected_type=list, default=[])
3782
3783 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3784 if vpir:
3785 stl = vpir.get('superTitleLink')
3786 if stl:
3787 stl = self._get_text(stl)
3788 if try_get(
3789 vpir,
3790 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3791 info['location'] = stl
3792 else:
affc4fef 3793 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 3794 if mobj:
545cc85d 3795 info.update({
17322130 3796 'series': mobj.group(1),
3797 'season_number': int(mobj.group(2)),
3798 'episode_number': int(mobj.group(3)),
545cc85d 3799 })
17322130 3800 for tlb in (try_get(
3801 vpir,
3802 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3803 list) or []):
3804 tbr = tlb.get('toggleButtonRenderer') or {}
3805 for getter, regex in [(
3806 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3807 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3808 lambda x: x['accessibility'],
3809 lambda x: x['accessibilityData']['accessibilityData'],
3810 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3811 label = (try_get(tbr, getter, dict) or {}).get('label')
3812 if label:
3813 mobj = re.match(regex, label)
3814 if mobj:
3815 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3816 break
17322130 3817 sbr_tooltip = try_get(
3818 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3819 if sbr_tooltip:
3820 like_count, dislike_count = sbr_tooltip.split(' / ')
3821 info.update({
3822 'like_count': str_to_int(like_count),
3823 'dislike_count': str_to_int(dislike_count),
3824 })
3825 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3826 if vsir:
3827 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3828 info.update({
3829 'channel': self._get_text(vor, 'title'),
3830 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3831
3832 rows = try_get(
3833 vsir,
3834 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3835 list) or []
3836 multiple_songs = False
3837 for row in rows:
3838 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3839 multiple_songs = True
3840 break
3841 for row in rows:
3842 mrr = row.get('metadataRowRenderer') or {}
3843 mrr_title = mrr.get('title')
3844 if not mrr_title:
3845 continue
3846 mrr_title = self._get_text(mrr, 'title')
3847 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3848 if mrr_title == 'License':
3849 info['license'] = mrr_contents_text
3850 elif not multiple_songs:
3851 if mrr_title == 'Album':
3852 info['album'] = mrr_contents_text
3853 elif mrr_title == 'Artist':
3854 info['artist'] = mrr_contents_text
3855 elif mrr_title == 'Song':
3856 info['track'] = mrr_contents_text
545cc85d 3857
3858 fallbacks = {
3859 'channel': 'uploader',
3860 'channel_id': 'uploader_id',
3861 'channel_url': 'uploader_url',
3862 }
992f9a73 3863
17322130 3864 # The upload date for scheduled, live and past live streams / premieres in microformats
3865 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3866 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3867 upload_date = (
3868 unified_strdate(get_first(microformats, 'uploadDate'))
3869 or unified_strdate(search_meta('uploadDate')))
3870 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
6e634cbe 3871 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date
17322130 3872 info['upload_date'] = upload_date
992f9a73 3873
545cc85d 3874 for to, frm in fallbacks.items():
3875 if not info.get(to):
3876 info[to] = info.get(frm)
3877
3878 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3879 v = info.get(s_k)
3880 if v:
3881 info[d_k] = v
b84071c0 3882
11f9be09 3883 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3884 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3885 is_membersonly = None
b28f8d24 3886 is_premium = None
c224251a
M
3887 if initial_data and is_private is not None:
3888 is_membersonly = False
b28f8d24 3889 is_premium = False
47193e02 3890 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3891 badge_labels = set()
3892 for content in contents:
3893 if not isinstance(content, dict):
3894 continue
3895 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3896 for badge_label in badge_labels:
3897 if badge_label.lower() == 'members only':
3898 is_membersonly = True
3899 elif badge_label.lower() == 'premium':
3900 is_premium = True
3901 elif badge_label.lower() == 'unlisted':
3902 is_unlisted = True
c224251a 3903
c224251a
M
3904 info['availability'] = self._availability(
3905 is_private=is_private,
b28f8d24 3906 needs_premium=is_premium,
c224251a
M
3907 needs_subscription=is_membersonly,
3908 needs_auth=info['age_limit'] >= 18,
3909 is_unlisted=None if is_private is None else is_unlisted)
3910
a2160aa4 3911 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3912
11f9be09 3913 self.mark_watched(video_id, player_responses)
d77ab8e2 3914
545cc85d 3915 return info
c5e8d7af 3916
a61fd4cf 3917
a6213a49 3918class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3919
182bda88 3920 @staticmethod
3921 def passthrough_smuggled_data(func):
3922 def _smuggle(entries, smuggled_data):
3923 for entry in entries:
3924 # TODO: Convert URL to music.youtube instead.
3925 # Do we need to passthrough any other smuggled_data?
3926 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3927 yield entry
3928
3929 @functools.wraps(func)
3930 def wrapper(self, url):
3931 url, smuggled_data = unsmuggle_url(url, {})
3932 if self.is_music_url(url):
3933 smuggled_data['is_music_url'] = True
3934 info_dict = func(self, url, smuggled_data)
3935 if smuggled_data and info_dict.get('entries'):
3936 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3937 return info_dict
3938 return wrapper
3939
a6213a49 3940 def _extract_channel_id(self, webpage):
3941 channel_id = self._html_search_meta(
3942 'channelId', webpage, 'channel id', default=None)
3943 if channel_id:
3944 return channel_id
3945 channel_url = self._html_search_meta(
3946 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3947 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3948 'twitter:app:url:googleplay'), webpage, 'channel url')
3949 return self._search_regex(
3950 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3951 channel_url, 'channel id')
15f6397c 3952
8bdd16b4 3953 @staticmethod
cd7c66cf 3954 def _extract_basic_item_renderer(item):
3955 # Modified from _extract_grid_item_renderer
201c1459 3956 known_basic_renderers = (
a17526e4 3957 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 3958 )
3959 for key, renderer in item.items():
201c1459 3960 if not isinstance(renderer, dict):
cd7c66cf 3961 continue
201c1459 3962 elif key in known_basic_renderers:
3963 return renderer
3964 elif key.startswith('grid') and key.endswith('Renderer'):
3965 return renderer
8bdd16b4 3966
8bdd16b4 3967 def _grid_entries(self, grid_renderer):
3968 for item in grid_renderer['items']:
3969 if not isinstance(item, dict):
39b62db1 3970 continue
cd7c66cf 3971 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3972 if not isinstance(renderer, dict):
3973 continue
052e1350 3974 title = self._get_text(renderer, 'title')
fe93e2c4 3975
8bdd16b4 3976 # playlist
3977 playlist_id = renderer.get('playlistId')
3978 if playlist_id:
3979 yield self.url_result(
3980 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3981 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3982 video_title=title)
201c1459 3983 continue
8bdd16b4 3984 # video
3985 video_id = renderer.get('videoId')
3986 if video_id:
3987 yield self._extract_video(renderer)
201c1459 3988 continue
8bdd16b4 3989 # channel
3990 channel_id = renderer.get('channelId')
3991 if channel_id:
8bdd16b4 3992 yield self.url_result(
3993 'https://www.youtube.com/channel/%s' % channel_id,
3994 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3995 continue
3996 # generic endpoint URL support
3997 ep_url = urljoin('https://www.youtube.com/', try_get(
3998 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 3999 str))
201c1459 4000 if ep_url:
4001 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4002 if ie.suitable(ep_url):
4003 yield self.url_result(
4004 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4005 break
8bdd16b4 4006
16aa9ea4 4007 def _music_reponsive_list_entry(self, renderer):
4008 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4009 if video_id:
4010 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4011 ie=YoutubeIE.ie_key(), video_id=video_id)
4012 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4013 if playlist_id:
4014 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4015 if video_id:
4016 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4017 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4018 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4019 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4020 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4021 if browse_id:
4022 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4023 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4024
3d3dddc9 4025 def _shelf_entries_from_content(self, shelf_renderer):
4026 content = shelf_renderer.get('content')
4027 if not isinstance(content, dict):
8bdd16b4 4028 return
cd7c66cf 4029 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4030 if renderer:
4031 # TODO: add support for nested playlists so each shelf is processed
4032 # as separate playlist
4033 # TODO: this includes only first N items
86e5f3ed 4034 yield from self._grid_entries(renderer)
3d3dddc9 4035 renderer = content.get('horizontalListRenderer')
4036 if renderer:
4037 # TODO
4038 pass
8bdd16b4 4039
29f7c58a 4040 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4041 ep = try_get(
4042 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4043 str)
8bdd16b4 4044 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4045 if shelf_url:
29f7c58a 4046 # Skipping links to another channels, note that checking for
4047 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4048 # will not work
4049 if skip_channels and '/channels?' in shelf_url:
4050 return
052e1350 4051 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4052 yield self.url_result(shelf_url, video_title=title)
4053 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4054 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4055
8bdd16b4 4056 def _playlist_entries(self, video_list_renderer):
4057 for content in video_list_renderer['contents']:
4058 if not isinstance(content, dict):
4059 continue
4060 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4061 if not isinstance(renderer, dict):
4062 continue
4063 video_id = renderer.get('videoId')
4064 if not video_id:
4065 continue
4066 yield self._extract_video(renderer)
07aeced6 4067
3462ffa8 4068 def _rich_entries(self, rich_grid_renderer):
4069 renderer = try_get(
70d5c17b 4070 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 4071 video_id = renderer.get('videoId')
4072 if not video_id:
4073 return
4074 yield self._extract_video(renderer)
4075
8bdd16b4 4076 def _video_entry(self, video_renderer):
4077 video_id = video_renderer.get('videoId')
4078 if video_id:
4079 return self._extract_video(video_renderer)
dacb3a86 4080
ad210f4f 4081 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4082 url = urljoin('https://youtube.com', traverse_obj(
4083 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4084 if url:
4085 return self.url_result(
4086 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4087
8bdd16b4 4088 def _post_thread_entries(self, post_thread_renderer):
4089 post_renderer = try_get(
4090 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4091 if not post_renderer:
4092 return
4093 # video attachment
4094 video_renderer = try_get(
895b0931 4095 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4096 video_id = video_renderer.get('videoId')
4097 if video_id:
4098 entry = self._extract_video(video_renderer)
8bdd16b4 4099 if entry:
4100 yield entry
895b0931 4101 # playlist attachment
4102 playlist_id = try_get(
14f25df2 4103 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4104 if playlist_id:
4105 yield self.url_result(
e28f1c0a 4106 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4107 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4108 # inline video links
4109 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4110 for run in runs:
4111 if not isinstance(run, dict):
4112 continue
4113 ep_url = try_get(
14f25df2 4114 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4115 if not ep_url:
4116 continue
4117 if not YoutubeIE.suitable(ep_url):
4118 continue
4119 ep_video_id = YoutubeIE._match_id(ep_url)
4120 if video_id == ep_video_id:
4121 continue
895b0931 4122 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4123
8bdd16b4 4124 def _post_thread_continuation_entries(self, post_thread_continuation):
4125 contents = post_thread_continuation.get('contents')
4126 if not isinstance(contents, list):
4127 return
4128 for content in contents:
4129 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4130 if isinstance(renderer, dict):
4131 yield from self._post_thread_entries(renderer)
8bdd16b4 4132 continue
6b0b0a28 4133 renderer = content.get('videoRenderer')
4134 if isinstance(renderer, dict):
4135 yield self._video_entry(renderer)
07aeced6 4136
39ed931e 4137 r''' # unused
4138 def _rich_grid_entries(self, contents):
4139 for content in contents:
4140 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4141 if video_renderer:
4142 entry = self._video_entry(video_renderer)
4143 if entry:
4144 yield entry
4145 '''
52efa4b3 4146
a6213a49 4147 def _extract_entries(self, parent_renderer, continuation_list):
4148 # continuation_list is modified in-place with continuation_list = [continuation_token]
4149 continuation_list[:] = [None]
4150 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4151 for content in contents:
4152 if not isinstance(content, dict):
4153 continue
16aa9ea4 4154 is_renderer = traverse_obj(
4155 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4156 expected_type=dict)
a6213a49 4157 if not is_renderer:
4158 renderer = content.get('richItemRenderer')
4159 if renderer:
4160 for entry in self._rich_entries(renderer):
4161 yield entry
4162 continuation_list[0] = self._extract_continuation(parent_renderer)
4163 continue
4164 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4165 for isr_content in isr_contents:
4166 if not isinstance(isr_content, dict):
8bdd16b4 4167 continue
69184e41 4168
a6213a49 4169 known_renderers = {
4170 'playlistVideoListRenderer': self._playlist_entries,
4171 'gridRenderer': self._grid_entries,
a17526e4 4172 'reelShelfRenderer': self._grid_entries,
4173 'shelfRenderer': self._shelf_entries,
16aa9ea4 4174 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4175 'backstagePostThreadRenderer': self._post_thread_entries,
4176 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4177 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4178 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4179 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4180 }
4181 for key, renderer in isr_content.items():
4182 if key not in known_renderers:
4183 continue
4184 for entry in known_renderers[key](renderer):
4185 if entry:
4186 yield entry
4187 continuation_list[0] = self._extract_continuation(renderer)
4188 break
70d5c17b 4189
4190 if not continuation_list[0]:
a6213a49 4191 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4192
a6213a49 4193 if not continuation_list[0]:
4194 continuation_list[0] = self._extract_continuation(parent_renderer)
4195
4196 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4197 continuation_list = [None]
4198 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4199 tab_content = try_get(tab, lambda x: x['content'], dict)
4200 if not tab_content:
4201 return
3462ffa8 4202 parent_renderer = (
29f7c58a 4203 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4204 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4205 yield from extract_entries(parent_renderer)
3462ffa8 4206 continuation = continuation_list[0]
d069eca7 4207
8bdd16b4 4208 for page_num in itertools.count(1):
4209 if not continuation:
4210 break
99e9e001 4211 headers = self.generate_api_headers(
4212 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4213 response = self._extract_response(
86e5f3ed 4214 item_id=f'{item_id} page {page_num}',
fe93e2c4 4215 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4216 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4217
4218 if not response:
8bdd16b4 4219 break
ac56cf38 4220 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4221 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4222 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4223
69184e41 4224 known_continuation_renderers = {
4225 'playlistVideoListContinuation': self._playlist_entries,
4226 'gridContinuation': self._grid_entries,
4227 'itemSectionContinuation': self._post_thread_continuation_entries,
4228 'sectionListContinuation': extract_entries, # for feeds
4229 }
8bdd16b4 4230 continuation_contents = try_get(
69184e41 4231 response, lambda x: x['continuationContents'], dict) or {}
4232 continuation_renderer = None
4233 for key, value in continuation_contents.items():
4234 if key not in known_continuation_renderers:
3462ffa8 4235 continue
69184e41 4236 continuation_renderer = value
4237 continuation_list = [None]
86e5f3ed 4238 yield from known_continuation_renderers[key](continuation_renderer)
69184e41 4239 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4240 break
4241 if continuation_renderer:
4242 continue
c5e8d7af 4243
a1b535bd 4244 known_renderers = {
e4b98809 4245 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4246 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4247 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4248 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4249 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4250 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4251 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4252 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4253 }
cce889b9 4254 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4255 continuation_items = try_get(
cce889b9 4256 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4257 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4258 video_items_renderer = None
4259 for key, value in continuation_item.items():
4260 if key not in known_renderers:
8bdd16b4 4261 continue
a1b535bd 4262 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4263 continuation_list = [None]
86e5f3ed 4264 yield from known_renderers[key][0](video_items_renderer)
9ba5705a 4265 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4266 break
4267 if video_items_renderer:
4268 continue
8bdd16b4 4269 break
9558dcec 4270
8bdd16b4 4271 @staticmethod
7c219ea6 4272 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4273 for tab in tabs:
cd684175 4274 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4275 if renderer.get('selected') is True:
4276 return renderer
2b3c2546 4277 else:
7c219ea6 4278 if fatal:
4279 raise ExtractorError('Unable to find selected tab')
b82f815f 4280
61d3665d 4281 def _extract_uploader(self, data):
8bdd16b4 4282 uploader = {}
61d3665d 4283 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
47193e02 4284 owner = try_get(
4285 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4286 if owner:
61d3665d 4287 owner_text = owner.get('text')
4288 uploader['uploader'] = self._search_regex(
4289 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
47193e02 4290 uploader['uploader_id'] = try_get(
14f25df2 4291 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], str)
47193e02 4292 uploader['uploader_url'] = urljoin(
4293 'https://www.youtube.com/',
14f25df2 4294 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
9c3fe2ef 4295 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4296
ac56cf38 4297 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4298 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4299 tags = []
b60419c5 4300
8bdd16b4 4301 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4302 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4303 renderer = try_get(
4304 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4305 if renderer:
b60419c5 4306 channel_name = renderer.get('title')
4307 channel_url = renderer.get('channelUrl')
4308 channel_id = renderer.get('externalId')
39ed931e 4309 else:
64c0d954 4310 renderer = try_get(
4311 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4312
8bdd16b4 4313 if renderer:
4314 title = renderer.get('title')
ecc97af3 4315 description = renderer.get('description', '')
b60419c5 4316 playlist_id = channel_id
4317 tags = renderer.get('keywords', '').split()
b60419c5 4318
301d07fc 4319 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4320 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4321 def _get_uncropped(url):
4322 return url_or_none((url or '').split('=')[0] + '=s0')
4323
4324 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4325 if avatar_thumbnails:
4326 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4327 if uncropped_avatar:
4328 avatar_thumbnails.append({
4329 'url': uncropped_avatar,
4330 'id': 'avatar_uncropped',
4331 'preference': 1
4332 })
4333
4334 channel_banners = self._extract_thumbnails(
4335 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4336 for banner in channel_banners:
4337 banner['preference'] = -10
4338
4339 if channel_banners:
4340 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4341 if uncropped_banner:
4342 channel_banners.append({
4343 'url': uncropped_banner,
4344 'id': 'banner_uncropped',
4345 'preference': -5
4346 })
4347
4348 primary_thumbnails = self._extract_thumbnails(
a17526e4 4349 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4350
3462ffa8 4351 if playlist_id is None:
70d5c17b 4352 playlist_id = item_id
f0d785d3 4353
4354 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4355 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4356 if title is None:
f0d785d3 4357 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4358 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4359 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4360
b60419c5 4361 metadata = {
4362 'playlist_id': playlist_id,
4363 'playlist_title': title,
4364 'playlist_description': description,
4365 'uploader': channel_name,
4366 'uploader_id': channel_id,
4367 'uploader_url': channel_url,
301d07fc 4368 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4369 'tags': tags,
f0d785d3 4370 'view_count': self._get_count(playlist_stats, 1),
4371 'availability': self._extract_availability(data),
4372 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4373 'playlist_count': self._get_count(playlist_stats, 0),
4374 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4375 }
4376 if not channel_id:
4377 metadata.update(self._extract_uploader(data))
4378 metadata.update({
4379 'channel': metadata['uploader'],
4380 'channel_id': metadata['uploader_id'],
4381 'channel_url': metadata['uploader_url']})
4382 return self.playlist_result(
d069eca7 4383 self._entries(
ac56cf38 4384 selected_tab, playlist_id, ytcfg,
4385 self._extract_account_syncid(ytcfg, data),
4386 self._extract_visitor_data(data, ytcfg)),
b60419c5 4387 **metadata)
73c4ac2c 4388
6e634cbe 4389 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4390 first_id = last_id = response = None
2be71994 4391 for page_num in itertools.count(1):
cd7c66cf 4392 videos = list(self._playlist_entries(playlist))
4393 if not videos:
4394 return
2be71994 4395 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4396 if start >= len(videos):
4397 return
24146491 4398 yield from videos[start:]
2be71994 4399 first_id = first_id or videos[0]['id']
4400 last_id = videos[-1]['id']
79360d99 4401 watch_endpoint = try_get(
4402 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4403 headers = self.generate_api_headers(
4404 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4405 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4406 query = {
4407 'playlistId': playlist_id,
4408 'videoId': watch_endpoint.get('videoId') or last_id,
4409 'index': watch_endpoint.get('index') or len(videos),
4410 'params': watch_endpoint.get('params') or 'OAE%3D'
4411 }
4412 response = self._extract_response(
4413 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4414 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4415 check_get_keys='contents'
4416 )
cd7c66cf 4417 playlist = try_get(
79360d99 4418 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4419
ac56cf38 4420 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4421 title = playlist.get('title') or try_get(
14f25df2 4422 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4423 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4424
4425 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4426 playlist_url = urljoin(url, try_get(
4427 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4428 str))
6e634cbe 4429
4430 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4431 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4432 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4433
4434 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4435 return self.url_result(
4436 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4437 video_title=title)
cd7c66cf 4438
8bdd16b4 4439 return self.playlist_result(
6e634cbe 4440 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4441 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4442
47193e02 4443 def _extract_availability(self, data):
4444 """
4445 Gets the availability of a given playlist/tab.
4446 Note: Unless YouTube tells us explicitly, we do not assume it is public
4447 @param data: response
4448 """
4449 is_private = is_unlisted = None
4450 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4451 badge_labels = self._extract_badges(renderer)
4452
4453 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4454 privacy_dropdown_entries = try_get(
4455 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4456 for renderer_dict in privacy_dropdown_entries:
4457 is_selected = try_get(
4458 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4459 if not is_selected:
4460 continue
052e1350 4461 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4462 if label:
4463 badge_labels.add(label.lower())
4464 break
4465
4466 for badge_label in badge_labels:
4467 if badge_label == 'unlisted':
4468 is_unlisted = True
4469 elif badge_label == 'private':
4470 is_private = True
4471 elif badge_label == 'public':
4472 is_unlisted = is_private = False
4473 return self._availability(is_private, False, False, False, is_unlisted)
4474
4475 @staticmethod
4476 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4477 sidebar_renderer = try_get(
4478 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4479 for item in sidebar_renderer:
4480 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4481 if renderer:
4482 return renderer
4483
ac56cf38 4484 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4485 """
4486 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4487 """
5d342002 4488 browse_id = params = None
47193e02 4489 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4490 if not renderer:
4491 return
4492 menu_renderer = try_get(
4493 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4494 for menu_item in menu_renderer:
4495 if not isinstance(menu_item, dict):
358de58c 4496 continue
47193e02 4497 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4498 text = try_get(
14f25df2 4499 nav_item_renderer, lambda x: x['text']['simpleText'], str)
47193e02 4500 if not text or text.lower() != 'show unavailable videos':
4501 continue
4502 browse_endpoint = try_get(
4503 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4504 browse_id = browse_endpoint.get('browseId')
4505 params = browse_endpoint.get('params')
4506 break
5d342002 4507
11f9be09 4508 headers = self.generate_api_headers(
99e9e001 4509 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4510 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4511 query = {
4512 'params': params or 'wgYCCAA=',
4513 'browseId': browse_id or 'VL%s' % item_id
4514 }
4515 return self._extract_response(
4516 item_id=item_id, headers=headers, query=query,
fe93e2c4 4517 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4518 note='Downloading API JSON with unavailable videos')
358de58c 4519
2762dbb1 4520 @functools.cached_property
a25bca9f 4521 def skip_webpage(self):
4522 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4523
ac56cf38 4524 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4525 retries = self.get_param('extractor_retries', 3)
62bff2c1 4526 count = -1
ac56cf38 4527 webpage = data = last_error = None
14fdfea9 4528 while count < retries:
62bff2c1 4529 count += 1
14fdfea9 4530 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4531 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4532 if last_error:
c705177d 4533 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4534 try:
4535 webpage = self._download_webpage(
4536 url, item_id,
4537 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4538 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4539 except ExtractorError as e:
4540 if isinstance(e.cause, network_exceptions):
14f25df2 4541 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
ac56cf38 4542 last_error = error_to_compat_str(e.cause or e.msg)
4543 if count < retries:
4544 continue
4545 if fatal:
4546 raise
4547 self.report_warning(error_to_compat_str(e))
14fdfea9 4548 break
ac56cf38 4549 else:
4550 try:
4551 self._extract_and_report_alerts(data)
4552 except ExtractorError as e:
4553 if fatal:
4554 raise
4555 self.report_warning(error_to_compat_str(e))
4556 break
4557
7c219ea6 4558 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
ac56cf38 4559 break
4560
4561 last_error = 'Incomplete yt initial data received'
4562 if count >= retries:
4563 if fatal:
4564 raise ExtractorError(last_error)
4565 self.report_warning(last_error)
4566 break
4567
cd7c66cf 4568 return webpage, data
4569
a25bca9f 4570 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4571 """Use if failed to extract ytcfg (and data) from initial webpage"""
4572 if not ytcfg and self.is_authenticated:
4573 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4574 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4575 raise ExtractorError(
4576 f'{msg}. If you are not downloading private content, or '
4577 'your cookies are only for the first account and channel,'
4578 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4579 expected=True)
4580 self.report_warning(msg, only_once=True)
4581
ac56cf38 4582 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4583 data = None
a25bca9f 4584 if not self.skip_webpage:
ac56cf38 4585 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4586 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4587 # Reject webpage data if redirected to home page without explicitly requesting
4588 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4589 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4590 if (url != 'https://www.youtube.com/feed/recommended'
4591 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4592 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4593 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4594 if fatal:
4595 raise ExtractorError(msg, expected=True)
4596 self.report_warning(msg, only_once=True)
ac56cf38 4597 if not data:
a25bca9f 4598 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4599 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4600 return data, ytcfg
4601
4602 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4603 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4604 resolve_response = self._extract_response(
4605 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4606 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4607 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4608 for ep_key, ep in endpoints.items():
4609 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4610 if params:
4611 return self._extract_response(
4612 item_id=item_id, query=params, ep=ep, headers=headers,
4613 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4614 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4615 err_note = 'Failed to resolve url (does the playlist exist?)'
4616 if fatal:
4617 raise ExtractorError(err_note, expected=True)
4618 self.report_warning(err_note, item_id)
4619
a6213a49 4620 _SEARCH_PARAMS = None
4621
af5c1c55 4622 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4623 data = {'query': query}
4624 if params is NO_DEFAULT:
4625 params = self._SEARCH_PARAMS
4626 if params:
4627 data['params'] = params
16aa9ea4 4628
4629 content_keys = (
4630 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4631 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4632 # ytmusic search
4633 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4634 ('continuationContents', ),
4635 )
a25bca9f 4636 display_id = f'query "{query}"'
86e5f3ed 4637 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4638 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4639 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4640
a61fd4cf 4641 continuation_list = [None]
a25bca9f 4642 search = None
a6213a49 4643 for page_num in itertools.count(1):
a61fd4cf 4644 data.update(continuation_list[0] or {})
a25bca9f 4645 headers = self.generate_api_headers(
4646 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4647 search = self._extract_response(
a25bca9f 4648 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4649 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4650 slr_contents = traverse_obj(search, *content_keys)
4651 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4652 if not continuation_list[0]:
a6213a49 4653 break
4654
4655
4656class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4657 IE_DESC = 'YouTube Tabs'
4658 _VALID_URL = r'''(?x:
4659 https?://
4660 (?:\w+\.)?
4661 (?:
4662 youtube(?:kids)?\.com|
4663 %(invidious)s
4664 )/
4665 (?:
4666 (?P<channel_type>channel|c|user|browse)/|
4667 (?P<not_channel>
4668 feed/|hashtag/|
4669 (?:playlist|watch)\?.*?\blist=
4670 )|
4671 (?!(?:%(reserved_names)s)\b) # Direct URLs
4672 )
4673 (?P<id>[^/?\#&]+)
4674 )''' % {
4675 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4676 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4677 }
4678 IE_NAME = 'youtube:tab'
4679
4680 _TESTS = [{
4681 'note': 'playlists, multipage',
4682 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4683 'playlist_mincount': 94,
4684 'info_dict': {
4685 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4686 'title': 'Igor Kleiner - Playlists',
a6213a49 4687 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4688 'uploader': 'Igor Kleiner',
a6213a49 4689 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4690 'channel': 'Igor Kleiner',
4691 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4692 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4693 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4694 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4695 'channel_follower_count': int
a6213a49 4696 },
4697 }, {
4698 'note': 'playlists, multipage, different order',
4699 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4700 'playlist_mincount': 94,
4701 'info_dict': {
4702 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4703 'title': 'Igor Kleiner - Playlists',
a6213a49 4704 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4705 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4706 'uploader': 'Igor Kleiner',
4707 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4708 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4709 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4710 'channel': 'Igor Kleiner',
4711 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4712 'channel_follower_count': int
a6213a49 4713 },
4714 }, {
4715 'note': 'playlists, series',
4716 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4717 'playlist_mincount': 5,
4718 'info_dict': {
4719 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4720 'title': '3Blue1Brown - Playlists',
4721 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4722 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4723 'uploader': '3Blue1Brown',
976ae3ea 4724 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4725 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4726 'channel': '3Blue1Brown',
4727 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4728 'tags': ['Mathematics'],
6c73052c 4729 'channel_follower_count': int
a6213a49 4730 },
4731 }, {
4732 'note': 'playlists, singlepage',
4733 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4734 'playlist_mincount': 4,
4735 'info_dict': {
4736 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4737 'title': 'ThirstForScience - Playlists',
4738 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4739 'uploader': 'ThirstForScience',
4740 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4741 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4742 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4743 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4744 'tags': 'count:13',
4745 'channel': 'ThirstForScience',
6c73052c 4746 'channel_follower_count': int
a6213a49 4747 }
4748 }, {
4749 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4750 'only_matching': True,
4751 }, {
4752 'note': 'basic, single video playlist',
4753 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4754 'info_dict': {
4755 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4756 'uploader': 'Sergey M.',
4757 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4758 'title': 'youtube-dl public playlist',
976ae3ea 4759 'description': '',
4760 'tags': [],
4761 'view_count': int,
4762 'modified_date': '20201130',
4763 'channel': 'Sergey M.',
4764 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4765 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4766 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4767 },
4768 'playlist_count': 1,
4769 }, {
4770 'note': 'empty playlist',
4771 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4772 'info_dict': {
4773 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4774 'uploader': 'Sergey M.',
4775 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4776 'title': 'youtube-dl empty playlist',
976ae3ea 4777 'tags': [],
4778 'channel': 'Sergey M.',
4779 'description': '',
4780 'modified_date': '20160902',
4781 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4782 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4783 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4784 },
4785 'playlist_count': 0,
4786 }, {
4787 'note': 'Home tab',
4788 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4789 'info_dict': {
4790 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4791 'title': 'lex will - Home',
4792 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4793 'uploader': 'lex will',
4794 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4795 'channel': 'lex will',
4796 'tags': ['bible', 'history', 'prophesy'],
4797 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4798 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4799 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4800 'channel_follower_count': int
a6213a49 4801 },
4802 'playlist_mincount': 2,
4803 }, {
4804 'note': 'Videos tab',
4805 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4806 'info_dict': {
4807 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4808 'title': 'lex will - Videos',
4809 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4810 'uploader': 'lex will',
4811 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4812 'tags': ['bible', 'history', 'prophesy'],
4813 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4814 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4815 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4816 'channel': 'lex will',
6c73052c 4817 'channel_follower_count': int
a6213a49 4818 },
4819 'playlist_mincount': 975,
4820 }, {
4821 'note': 'Videos tab, sorted by popular',
4822 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4823 'info_dict': {
4824 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4825 'title': 'lex will - Videos',
4826 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4827 'uploader': 'lex will',
4828 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4829 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4830 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4831 'channel': 'lex will',
4832 'tags': ['bible', 'history', 'prophesy'],
4833 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4834 'channel_follower_count': int
a6213a49 4835 },
4836 'playlist_mincount': 199,
4837 }, {
4838 'note': 'Playlists tab',
4839 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4840 'info_dict': {
4841 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4842 'title': 'lex will - Playlists',
4843 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4844 'uploader': 'lex will',
4845 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4846 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4847 'channel': 'lex will',
4848 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4849 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4850 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4851 'channel_follower_count': int
a6213a49 4852 },
4853 'playlist_mincount': 17,
4854 }, {
4855 'note': 'Community tab',
4856 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4857 'info_dict': {
4858 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4859 'title': 'lex will - Community',
4860 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4861 'uploader': 'lex will',
4862 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4863 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4864 'channel': 'lex will',
4865 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4866 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4867 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4868 'channel_follower_count': int
a6213a49 4869 },
4870 'playlist_mincount': 18,
4871 }, {
4872 'note': 'Channels tab',
4873 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4874 'info_dict': {
4875 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4876 'title': 'lex will - Channels',
4877 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4878 'uploader': 'lex will',
4879 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4880 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4881 'channel': 'lex will',
4882 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4883 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4884 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4885 'channel_follower_count': int
a6213a49 4886 },
4887 'playlist_mincount': 12,
4888 }, {
4889 'note': 'Search tab',
4890 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4891 'playlist_mincount': 40,
4892 'info_dict': {
4893 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4894 'title': '3Blue1Brown - Search - linear algebra',
4895 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4896 'uploader': '3Blue1Brown',
4897 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4898 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4899 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4900 'tags': ['Mathematics'],
4901 'channel': '3Blue1Brown',
4902 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4903 'channel_follower_count': int
a6213a49 4904 },
4905 }, {
4906 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4907 'only_matching': True,
4908 }, {
4909 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4910 'only_matching': True,
4911 }, {
4912 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4913 'only_matching': True,
4914 }, {
4915 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4916 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4917 'info_dict': {
4918 'title': '29C3: Not my department',
4919 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4920 'uploader': 'Christiaan008',
4921 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4922 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4923 'tags': [],
4924 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4925 'view_count': int,
4926 'modified_date': '20150605',
4927 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4928 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4929 'channel': 'Christiaan008',
a6213a49 4930 },
4931 'playlist_count': 96,
4932 }, {
4933 'note': 'Large playlist',
4934 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4935 'info_dict': {
4936 'title': 'Uploads from Cauchemar',
4937 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4938 'uploader': 'Cauchemar',
4939 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4940 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4941 'tags': [],
4942 'modified_date': r're:\d{8}',
4943 'channel': 'Cauchemar',
4944 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4945 'view_count': int,
4946 'description': '',
4947 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4948 },
4949 'playlist_mincount': 1123,
976ae3ea 4950 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4951 }, {
4952 'note': 'even larger playlist, 8832 videos',
4953 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4954 'only_matching': True,
4955 }, {
4956 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4957 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4958 'info_dict': {
4959 'title': 'Uploads from Interstellar Movie',
4960 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4961 'uploader': 'Interstellar Movie',
4962 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4963 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4964 'tags': [],
4965 'view_count': int,
4966 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4967 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4968 'channel': 'Interstellar Movie',
4969 'description': '',
4970 'modified_date': r're:\d{8}',
a6213a49 4971 },
4972 'playlist_mincount': 21,
4973 }, {
4974 'note': 'Playlist with "show unavailable videos" button',
4975 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4976 'info_dict': {
4977 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4978 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4979 'uploader': 'Phim Siêu Nhân Nhật Bản',
4980 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4981 'view_count': int,
4982 'channel': 'Phim Siêu Nhân Nhật Bản',
4983 'tags': [],
4984 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4985 'description': '',
4986 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4987 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4988 'modified_date': r're:\d{8}',
a6213a49 4989 },
4990 'playlist_mincount': 200,
976ae3ea 4991 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4992 }, {
4993 'note': 'Playlist with unavailable videos in page 7',
4994 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4995 'info_dict': {
4996 'title': 'Uploads from BlankTV',
4997 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4998 'uploader': 'BlankTV',
4999 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5000 'channel': 'BlankTV',
5001 'channel_url': 'https://www.youtube.com/c/blanktv',
5002 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5003 'view_count': int,
5004 'tags': [],
5005 'uploader_url': 'https://www.youtube.com/c/blanktv',
5006 'modified_date': r're:\d{8}',
5007 'description': '',
a6213a49 5008 },
5009 'playlist_mincount': 1000,
976ae3ea 5010 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5011 }, {
5012 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5013 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5014 'info_dict': {
5015 'title': 'Data Analysis with Dr Mike Pound',
5016 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5017 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5018 'uploader': 'Computerphile',
5019 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5020 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5021 'tags': [],
5022 'view_count': int,
5023 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5024 'channel_url': 'https://www.youtube.com/user/Computerphile',
5025 'channel': 'Computerphile',
a6213a49 5026 },
5027 'playlist_mincount': 11,
5028 }, {
5029 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5030 'only_matching': True,
5031 }, {
5032 'note': 'Playlist URL that does not actually serve a playlist',
5033 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5034 'info_dict': {
5035 'id': 'FqZTN594JQw',
5036 'ext': 'webm',
5037 'title': "Smiley's People 01 detective, Adventure Series, Action",
5038 'uploader': 'STREEM',
5039 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5040 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5041 'upload_date': '20150526',
5042 'license': 'Standard YouTube License',
5043 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5044 'categories': ['People & Blogs'],
5045 'tags': list,
5046 'view_count': int,
5047 'like_count': int,
a6213a49 5048 },
5049 'params': {
5050 'skip_download': True,
5051 },
5052 'skip': 'This video is not available.',
5053 'add_ie': [YoutubeIE.ie_key()],
5054 }, {
5055 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5056 'only_matching': True,
5057 }, {
5058 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5059 'only_matching': True,
5060 }, {
5061 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5062 'info_dict': {
12a1b225 5063 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5064 'ext': 'mp4',
976ae3ea 5065 'title': str,
a6213a49 5066 'uploader': 'Sky News',
5067 'uploader_id': 'skynews',
5068 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5069 'upload_date': r're:\d{8}',
976ae3ea 5070 'description': str,
a6213a49 5071 'categories': ['News & Politics'],
5072 'tags': list,
5073 'like_count': int,
6c73052c 5074 'release_timestamp': 1642502819,
976ae3ea 5075 'channel': 'Sky News',
5076 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5077 'age_limit': 0,
5078 'view_count': int,
6c73052c 5079 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 5080 'playable_in_embed': True,
6c73052c 5081 'release_date': '20220118',
976ae3ea 5082 'availability': 'public',
5083 'live_status': 'is_live',
5084 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 5085 'channel_follower_count': int
a6213a49 5086 },
5087 'params': {
5088 'skip_download': True,
5089 },
976ae3ea 5090 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5091 }, {
5092 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5093 'info_dict': {
5094 'id': 'a48o2S1cPoo',
5095 'ext': 'mp4',
5096 'title': 'The Young Turks - Live Main Show',
5097 'uploader': 'The Young Turks',
5098 'uploader_id': 'TheYoungTurks',
5099 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5100 'upload_date': '20150715',
5101 'license': 'Standard YouTube License',
5102 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5103 'categories': ['News & Politics'],
5104 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5105 'like_count': int,
a6213a49 5106 },
5107 'params': {
5108 'skip_download': True,
5109 },
5110 'only_matching': True,
5111 }, {
5112 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5113 'only_matching': True,
5114 }, {
5115 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5116 'only_matching': True,
5117 }, {
5118 'note': 'A channel that is not live. Should raise error',
5119 'url': 'https://www.youtube.com/user/numberphile/live',
5120 'only_matching': True,
5121 }, {
5122 'url': 'https://www.youtube.com/feed/trending',
5123 'only_matching': True,
5124 }, {
5125 'url': 'https://www.youtube.com/feed/library',
5126 'only_matching': True,
5127 }, {
5128 'url': 'https://www.youtube.com/feed/history',
5129 'only_matching': True,
5130 }, {
5131 'url': 'https://www.youtube.com/feed/subscriptions',
5132 'only_matching': True,
5133 }, {
5134 'url': 'https://www.youtube.com/feed/watch_later',
5135 'only_matching': True,
5136 }, {
5137 'note': 'Recommended - redirects to home page.',
5138 'url': 'https://www.youtube.com/feed/recommended',
5139 'only_matching': True,
5140 }, {
5141 'note': 'inline playlist with not always working continuations',
5142 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5143 'only_matching': True,
5144 }, {
5145 'url': 'https://www.youtube.com/course',
5146 'only_matching': True,
5147 }, {
5148 'url': 'https://www.youtube.com/zsecurity',
5149 'only_matching': True,
5150 }, {
5151 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5152 'only_matching': True,
5153 }, {
5154 'url': 'https://www.youtube.com/TheYoungTurks/live',
5155 'only_matching': True,
5156 }, {
5157 'url': 'https://www.youtube.com/hashtag/cctv9',
5158 'info_dict': {
5159 'id': 'cctv9',
5160 'title': '#cctv9',
976ae3ea 5161 'tags': [],
a6213a49 5162 },
5163 'playlist_mincount': 350,
5164 }, {
5165 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5166 'only_matching': True,
5167 }, {
5168 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5169 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5170 'only_matching': True
5171 }, {
5172 'note': '/browse/ should redirect to /channel/',
5173 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5174 'only_matching': True
5175 }, {
5176 'note': 'VLPL, should redirect to playlist?list=PL...',
5177 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5178 'info_dict': {
5179 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5180 'uploader': 'NoCopyrightSounds',
5181 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5182 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5183 'title': 'NCS : All Releases 💿',
976ae3ea 5184 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5185 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5186 'modified_date': r're:\d{8}',
5187 'view_count': int,
5188 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5189 'tags': [],
5190 'channel': 'NoCopyrightSounds',
a6213a49 5191 },
5192 'playlist_mincount': 166,
976ae3ea 5193 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5194 }, {
5195 'note': 'Topic, should redirect to playlist?list=UU...',
5196 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5197 'info_dict': {
5198 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5199 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5200 'title': 'Uploads from Royalty Free Music - Topic',
5201 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5202 'tags': [],
5203 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5204 'channel': 'Royalty Free Music - Topic',
5205 'view_count': int,
5206 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5207 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5208 'modified_date': r're:\d{8}',
5209 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5210 'description': '',
a6213a49 5211 },
5212 'expected_warnings': [
a6213a49 5213 'The URL does not have a videos tab',
976ae3ea 5214 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5215 ],
5216 'playlist_mincount': 101,
5217 }, {
5218 'note': 'Topic without a UU playlist',
5219 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5220 'info_dict': {
5221 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5222 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5223 'tags': [],
a6213a49 5224 },
5225 'expected_warnings': [
976ae3ea 5226 'the playlist redirect gave error',
a6213a49 5227 ],
5228 'playlist_mincount': 9,
5229 }, {
5230 'note': 'Youtube music Album',
5231 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5232 'info_dict': {
5233 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5234 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5235 'tags': [],
5236 'view_count': int,
5237 'description': '',
5238 'availability': 'unlisted',
5239 'modified_date': r're:\d{8}',
a6213a49 5240 },
5241 'playlist_count': 50,
5242 }, {
5243 'note': 'unlisted single video playlist',
5244 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5245 'info_dict': {
5246 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5247 'uploader': 'colethedj',
5248 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5249 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5250 'availability': 'unlisted',
5251 'tags': [],
12a1b225 5252 'modified_date': '20220418',
976ae3ea 5253 'channel': 'colethedj',
5254 'view_count': int,
5255 'description': '',
5256 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5257 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5258 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5259 },
5260 'playlist_count': 1,
5261 }, {
5262 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5263 'url': 'https://www.youtube.com/feed/recommended',
5264 'info_dict': {
5265 'id': 'recommended',
5266 'title': 'recommended',
6c73052c 5267 'tags': [],
a6213a49 5268 },
5269 'playlist_mincount': 50,
5270 'params': {
5271 'skip_download': True,
5272 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5273 },
5274 }, {
5275 'note': 'API Fallback: /videos tab, sorted by oldest first',
5276 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5277 'info_dict': {
5278 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5279 'title': 'Cody\'sLab - Videos',
5280 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5281 'uploader': 'Cody\'sLab',
5282 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5283 'channel': 'Cody\'sLab',
5284 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5285 'tags': [],
5286 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5287 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5288 'channel_follower_count': int
a6213a49 5289 },
5290 'playlist_mincount': 650,
5291 'params': {
5292 'skip_download': True,
5293 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5294 },
5295 }, {
5296 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5297 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5298 'info_dict': {
5299 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5300 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5301 'title': 'Uploads from Royalty Free Music - Topic',
5302 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5303 'modified_date': r're:\d{8}',
5304 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5305 'description': '',
5306 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5307 'tags': [],
5308 'channel': 'Royalty Free Music - Topic',
5309 'view_count': int,
5310 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5311 },
5312 'expected_warnings': [
976ae3ea 5313 'does not have a videos tab',
5314 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5315 ],
5316 'playlist_mincount': 101,
5317 'params': {
5318 'skip_download': True,
5319 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5320 },
7c219ea6 5321 }, {
5322 'note': 'non-standard redirect to regional channel',
5323 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5324 'only_matching': True
61d3665d 5325 }, {
5326 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5327 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5328 'info_dict': {
5329 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5330 'modified_date': '20220407',
5331 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5332 'tags': [],
5333 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5334 'uploader': 'pukkandan',
5335 'availability': 'unlisted',
5336 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5337 'channel': 'pukkandan',
5338 'description': 'Test for collaborative playlist',
5339 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5340 'view_count': int,
61d3665d 5341 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5342 },
5343 'playlist_mincount': 2
a6213a49 5344 }]
5345
5346 @classmethod
5347 def suitable(cls, url):
86e5f3ed 5348 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5349
64f36541 5350 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5351
182bda88 5352 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5353 def _real_extract(self, url, smuggled_data):
cd7c66cf 5354 item_id = self._match_id(url)
14f25df2 5355 url = urllib.parse.urlunparse(
5356 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5357 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5358
fe03a6cd 5359 def get_mobj(url):
37e57a9f 5360 mobj = self._URL_RE.match(url).groupdict()
07cce701 5361 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5362 return mobj
5363
37e57a9f 5364 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5365 # Youtube returns incomplete data if tabname is not lower case
5366 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5367 if is_channel:
5368 if smuggled_data.get('is_music_url'):
37e57a9f 5369 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5370 item_id = item_id[2:]
37e57a9f 5371 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5372 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5373 mdata = self._extract_tab_endpoint(
37e57a9f 5374 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5375 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
14f25df2 5376 get_all=False, expected_type=str)
ac56cf38 5377 if not murl:
37e57a9f 5378 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5379 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5380 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5381 pre = f'https://www.youtube.com/channel/{item_id}'
5382
64f36541 5383 original_tab_name = tab
fe03a6cd 5384 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5385 # Home URLs should redirect to /videos/
37e57a9f 5386 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5387 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5388 tab = '/videos'
5389
5390 url = ''.join((pre, tab, post))
5391 mobj = get_mobj(url)
cd7c66cf 5392
5393 # Handle both video/playlist URLs
201c1459 5394 qs = parse_qs(url)
86e5f3ed 5395 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5396
fe03a6cd 5397 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5398 if not playlist_id:
fe03a6cd 5399 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5400 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5401 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5402 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5403 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5404 mobj = get_mobj(url)
cd7c66cf 5405
5406 if video_id and playlist_id:
a06916d9 5407 if self.get_param('noplaylist'):
37e57a9f 5408 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5409 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5410 ie=YoutubeIE.ie_key(), video_id=video_id)
5411 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5412
ac56cf38 5413 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5414
7c219ea6 5415 # YouTube may provide a non-standard redirect to the regional channel
5416 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5417 redirect_url = traverse_obj(
5418 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5419 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5420 redirect_url = ''.join((
5421 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5422 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5423 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5424
37e57a9f 5425 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5426 if tabs:
5427 selected_tab = self._extract_selected_tab(tabs)
64f36541 5428 selected_tab_name = selected_tab.get('title', '').lower()
5429 if selected_tab_name == 'home':
5430 selected_tab_name = 'featured'
5431 requested_tab_name = mobj['tab'][1:]
09f1580e 5432 if 'no-youtube-channel-redirect' not in compat_opts:
693f0600 5433 if requested_tab_name == 'live': # Live tab should have redirected to the video
5434 raise UserNotLive(video_id=mobj['id'])
64f36541 5435 if requested_tab_name not in ('', selected_tab_name):
5436 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5437 if not original_tab_name:
5438 if item_id[:2] == 'UC':
5439 # Topic channels don't have /videos. Use the equivalent playlist instead
5440 pl_id = f'UU{item_id[2:]}'
5441 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5442 try:
5443 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5444 except ExtractorError:
5445 redirect_warning += ' and the playlist redirect gave error'
5446 else:
5447 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5448 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5449 if selected_tab_name and selected_tab_name != requested_tab_name:
5450 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5451 else:
5452 raise ExtractorError(redirect_warning, expected=True)
18db7548 5453
37e57a9f 5454 if redirect_warning:
64f36541 5455 self.to_screen(redirect_warning)
37e57a9f 5456 self.write_debug(f'Final URL: {url}')
18db7548 5457
358de58c 5458 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5459 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5460 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5461 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5462 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5463 if tabs:
ac56cf38 5464 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5465
37e57a9f 5466 playlist = traverse_obj(
5467 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5468 if playlist:
ac56cf38 5469 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5470
37e57a9f 5471 video_id = traverse_obj(
5472 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5473 if video_id:
09f1580e 5474 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5475 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5476 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5477 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5478
8bdd16b4 5479 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5480
c5e8d7af 5481
8bdd16b4 5482class YoutubePlaylistIE(InfoExtractor):
96565c7e 5483 IE_DESC = 'YouTube playlists'
8bdd16b4 5484 _VALID_URL = r'''(?x)(?:
5485 (?:https?://)?
5486 (?:\w+\.)?
5487 (?:
5488 (?:
5489 youtube(?:kids)?\.com|
d9190e44 5490 %(invidious)s
8bdd16b4 5491 )
5492 /.*?\?.*?\blist=
5493 )?
5494 (?P<id>%(playlist_id)s)
d9190e44
RH
5495 )''' % {
5496 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5497 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5498 }
8bdd16b4 5499 IE_NAME = 'youtube:playlist'
cdc628a4 5500 _TESTS = [{
8bdd16b4 5501 'note': 'issue #673',
5502 'url': 'PLBB231211A4F62143',
cdc628a4 5503 'info_dict': {
8bdd16b4 5504 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5505 'id': 'PLBB231211A4F62143',
976ae3ea 5506 'uploader': 'Wickman',
8bdd16b4 5507 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5508 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5509 'view_count': int,
5510 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5511 'modified_date': r're:\d{8}',
5512 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5513 'channel': 'Wickman',
5514 'tags': [],
5515 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5516 },
5517 'playlist_mincount': 29,
5518 }, {
5519 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5520 'info_dict': {
5521 'title': 'YDL_safe_search',
5522 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5523 },
5524 'playlist_count': 2,
5525 'skip': 'This playlist is private',
9558dcec 5526 }, {
8bdd16b4 5527 'note': 'embedded',
5528 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5529 'playlist_count': 4,
9558dcec 5530 'info_dict': {
8bdd16b4 5531 'title': 'JODA15',
5532 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5533 'uploader': 'milan',
5534 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5535 'description': '',
5536 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5537 'tags': [],
5538 'modified_date': '20140919',
5539 'view_count': int,
5540 'channel': 'milan',
5541 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5542 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5543 },
5544 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5545 }, {
8bdd16b4 5546 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 5547 'playlist_mincount': 455,
8bdd16b4 5548 'info_dict': {
5549 'title': '2018 Chinese New Singles (11/6 updated)',
5550 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5551 'uploader': 'LBK',
5552 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5553 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5554 'channel': 'LBK',
5555 'view_count': int,
5556 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5557 'tags': [],
5558 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5559 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5560 'modified_date': r're:\d{8}',
5561 },
5562 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5563 }, {
29f7c58a 5564 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5565 'only_matching': True,
5566 }, {
5567 # music album playlist
5568 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5569 'only_matching': True,
5570 }]
5571
5572 @classmethod
5573 def suitable(cls, url):
201c1459 5574 if YoutubeTabIE.suitable(url):
5575 return False
49a57e70 5576 from ..utils import parse_qs
201c1459 5577 qs = parse_qs(url)
5578 if qs.get('v', [None])[0]:
5579 return False
86e5f3ed 5580 return super().suitable(url)
29f7c58a 5581
5582 def _real_extract(self, url):
5583 playlist_id = self._match_id(url)
46953e7e 5584 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5585 url = update_url_query(
5586 'https://www.youtube.com/playlist',
5587 parse_qs(url) or {'list': playlist_id})
5588 if is_music_url:
5589 url = smuggle_url(url, {'is_music_url': True})
5590 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5591
5592
5593class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5594 IE_DESC = 'youtu.be'
29f7c58a 5595 _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}
5596 _TESTS = [{
8bdd16b4 5597 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5598 'info_dict': {
5599 'id': 'yeWKywCrFtk',
5600 'ext': 'mp4',
5601 'title': 'Small Scale Baler and Braiding Rugs',
5602 'uploader': 'Backus-Page House Museum',
5603 'uploader_id': 'backuspagemuseum',
5604 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5605 'upload_date': '20161008',
5606 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5607 'categories': ['Nonprofits & Activism'],
5608 'tags': list,
5609 'like_count': int,
976ae3ea 5610 'age_limit': 0,
5611 'playable_in_embed': True,
5612 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5613 'channel': 'Backus-Page House Museum',
5614 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5615 'live_status': 'not_live',
5616 'view_count': int,
5617 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5618 'availability': 'public',
5619 'duration': 59,
12a1b225
A
5620 'comment_count': int,
5621 'channel_follower_count': int
8bdd16b4 5622 },
5623 'params': {
5624 'noplaylist': True,
5625 'skip_download': True,
5626 },
39e7107d 5627 }, {
8bdd16b4 5628 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5629 'only_matching': True,
cdc628a4
PH
5630 }]
5631
8bdd16b4 5632 def _real_extract(self, url):
5ad28e7f 5633 mobj = self._match_valid_url(url)
29f7c58a 5634 video_id = mobj.group('id')
5635 playlist_id = mobj.group('playlist_id')
8bdd16b4 5636 return self.url_result(
29f7c58a 5637 update_url_query('https://www.youtube.com/watch', {
5638 'v': video_id,
5639 'list': playlist_id,
5640 'feature': 'youtu.be',
5641 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5642
5643
b6ce9bb0 5644class YoutubeLivestreamEmbedIE(InfoExtractor):
5645 IE_DESC = 'YouTube livestream embeds'
5646 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5647 _TESTS = [{
5648 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5649 'only_matching': True,
5650 }]
5651
5652 def _real_extract(self, url):
5653 channel_id = self._match_id(url)
5654 return self.url_result(
5655 f'https://www.youtube.com/channel/{channel_id}/live',
5656 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5657
5658
8bdd16b4 5659class YoutubeYtUserIE(InfoExtractor):
96565c7e 5660 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5661 IE_NAME = 'youtube:user'
8bdd16b4 5662 _VALID_URL = r'ytuser:(?P<id>.+)'
5663 _TESTS = [{
5664 'url': 'ytuser:phihag',
5665 'only_matching': True,
5666 }]
5667
5668 def _real_extract(self, url):
5669 user_id = self._match_id(url)
5670 return self.url_result(
c586f9e8 5671 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5672 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5673
b05654f0 5674
3d3dddc9 5675class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5676 IE_NAME = 'youtube:favorites'
96565c7e 5677 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5678 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5679 _LOGIN_REQUIRED = True
5680 _TESTS = [{
5681 'url': ':ytfav',
5682 'only_matching': True,
5683 }, {
5684 'url': ':ytfavorites',
5685 'only_matching': True,
5686 }]
5687
5688 def _real_extract(self, url):
5689 return self.url_result(
5690 'https://www.youtube.com/playlist?list=LL',
5691 ie=YoutubeTabIE.ie_key())
5692
5693
ca5300c7 5694class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
5695 IE_NAME = 'youtube:notif'
5696 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5697 _VALID_URL = r':ytnotif(?:ication)?s?'
5698 _LOGIN_REQUIRED = True
5699 _TESTS = [{
5700 'url': ':ytnotif',
5701 'only_matching': True,
5702 }, {
5703 'url': ':ytnotifications',
5704 'only_matching': True,
5705 }]
5706
5707 def _extract_notification_menu(self, response, continuation_list):
5708 notification_list = traverse_obj(
5709 response,
5710 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5711 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5712 expected_type=list) or []
5713 continuation_list[0] = None
5714 for item in notification_list:
5715 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
5716 if entry:
5717 yield entry
5718 continuation = item.get('continuationItemRenderer')
5719 if continuation:
5720 continuation_list[0] = continuation
5721
5722 def _extract_notification_renderer(self, notification):
5723 video_id = traverse_obj(
5724 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
5725 url = f'https://www.youtube.com/watch?v={video_id}'
5726 channel_id = None
5727 if not video_id:
5728 browse_ep = traverse_obj(
5729 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
5730 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
5731 post_id = self._search_regex(
5732 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
5733 'post id', default=None)
5734 if not channel_id or not post_id:
5735 return
5736 # The direct /post url redirects to this in the browser
5737 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5738
5739 channel = traverse_obj(
5740 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5741 expected_type=str)
c7a7baaa 5742 notification_title = self._get_text(notification, 'shortMessage')
5743 if notification_title:
5744 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
5745 # TODO: handle recommended videos
ca5300c7 5746 title = self._search_regex(
c7a7baaa 5747 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 5748 'video title', default=None)
ca5300c7 5749 upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d')
5750 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
5751 else None)
5752 return {
5753 '_type': 'url',
5754 'url': url,
5755 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
5756 'video_id': video_id,
5757 'title': title,
5758 'channel_id': channel_id,
5759 'channel': channel,
5760 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5761 'upload_date': upload_date,
5762 }
5763
5764 def _notification_menu_entries(self, ytcfg):
5765 continuation_list = [None]
5766 response = None
5767 for page in itertools.count(1):
5768 ctoken = traverse_obj(
5769 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
5770 response = self._extract_response(
5771 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
5772 ep='notification/get_notification_menu', check_get_keys='actions',
5773 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
5774 yield from self._extract_notification_menu(response, continuation_list)
5775 if not continuation_list[0]:
5776 break
5777
5778 def _real_extract(self, url):
5779 display_id = 'notifications'
5780 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
5781 self._report_playlist_authcheck(ytcfg)
5782 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
5783
5784
a6213a49 5785class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5786 IE_DESC = 'YouTube search'
78caa52a 5787 IE_NAME = 'youtube:search'
b05654f0 5788 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5789 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5790 _TESTS = [{
5791 'url': 'ytsearch5:youtube-dl test video',
5792 'playlist_count': 5,
5793 'info_dict': {
5794 'id': 'youtube-dl test video',
5795 'title': 'youtube-dl test video',
5796 }
5797 }]
b05654f0 5798
a61fd4cf 5799
5f7cb91a 5800class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5801 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5802 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5803 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5804 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5805 _TESTS = [{
5806 'url': 'ytsearchdate5:youtube-dl test video',
5807 'playlist_count': 5,
5808 'info_dict': {
5809 'id': 'youtube-dl test video',
5810 'title': 'youtube-dl test video',
5811 }
5812 }]
75dff0ee 5813
c9ae7b95 5814
a6213a49 5815class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5816 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5817 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5818 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5819 _TESTS = [{
5820 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5821 'playlist_mincount': 5,
5822 'info_dict': {
11f9be09 5823 'id': 'youtube-dl test video',
3462ffa8 5824 'title': 'youtube-dl test video',
5825 }
a61fd4cf 5826 }, {
5827 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5828 'playlist_mincount': 5,
5829 'info_dict': {
5830 'id': 'python',
5831 'title': 'python',
5832 }
ad210f4f 5833 }, {
5834 'url': 'https://www.youtube.com/results?search_query=%23cats',
5835 'playlist_mincount': 1,
5836 'info_dict': {
5837 'id': '#cats',
5838 'title': '#cats',
12a1b225
A
5839 # The test suite does not have support for nested playlists
5840 # 'entries': [{
5841 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5842 # 'title': '#cats',
5843 # }],
ad210f4f 5844 },
3462ffa8 5845 }, {
5846 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5847 'only_matching': True,
5848 }]
5849
5850 def _real_extract(self, url):
4dfbf869 5851 qs = parse_qs(url)
386e1dd9 5852 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5853 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5854
5855
16aa9ea4 5856class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
455a15e2 5857 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
16aa9ea4 5858 IE_NAME = 'youtube:music:search_url'
5859 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5860 _TESTS = [{
5861 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5862 'playlist_count': 16,
5863 'info_dict': {
5864 'id': 'royalty free music',
5865 'title': 'royalty free music',
5866 }
5867 }, {
5868 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5869 'playlist_mincount': 30,
5870 'info_dict': {
5871 'id': 'royalty free music - songs',
5872 'title': 'royalty free music - songs',
5873 },
5874 'params': {'extract_flat': 'in_playlist'}
5875 }, {
5876 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5877 'playlist_mincount': 30,
5878 'info_dict': {
5879 'id': 'royalty free music - community playlists',
5880 'title': 'royalty free music - community playlists',
5881 },
5882 'params': {'extract_flat': 'in_playlist'}
5883 }]
5884
5885 _SECTIONS = {
5886 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5887 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5888 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5889 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5890 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5891 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5892 }
5893
5894 def _real_extract(self, url):
5895 qs = parse_qs(url)
5896 query = (qs.get('search_query') or qs.get('q'))[0]
5897 params = qs.get('sp', (None,))[0]
5898 if params:
5899 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5900 else:
ac668111 5901 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 5902 params = self._SECTIONS.get(section)
5903 if not params:
5904 section = None
5905 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5906 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5907
5908
182bda88 5909class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5910 """
25f14e9f 5911 Base class for feed extractors
82d02080 5912 Subclasses must re-define the _FEED_NAME property.
d7ae0639 5913 """
b2e8bc1b 5914 _LOGIN_REQUIRED = True
82d02080 5915 _FEED_NAME = 'feeds'
a25bca9f 5916
5917 def _real_initialize(self):
5918 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 5919
82d02080 5920 @classproperty
d7ae0639 5921 def IE_NAME(self):
82d02080 5922 return f'youtube:{self._FEED_NAME}'
04cc9617 5923
3853309f 5924 def _real_extract(self, url):
3d3dddc9 5925 return self.url_result(
182bda88 5926 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5927
5928
ef2f3c7f 5929class YoutubeWatchLaterIE(InfoExtractor):
5930 IE_NAME = 'youtube:watchlater'
96565c7e 5931 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5932 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5933 _TESTS = [{
8bdd16b4 5934 'url': ':ytwatchlater',
bc7a9cd8
S
5935 'only_matching': True,
5936 }]
25f14e9f
S
5937
5938 def _real_extract(self, url):
ef2f3c7f 5939 return self.url_result(
5940 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5941
5942
25f14e9f 5943class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5944 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5945 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5946 _FEED_NAME = 'recommended'
45db527f 5947 _LOGIN_REQUIRED = False
3d3dddc9 5948 _TESTS = [{
5949 'url': ':ytrec',
5950 'only_matching': True,
5951 }, {
5952 'url': ':ytrecommended',
5953 'only_matching': True,
5954 }, {
5955 'url': 'https://youtube.com',
5956 'only_matching': True,
5957 }]
1ed5b5c9 5958
1ed5b5c9 5959
25f14e9f 5960class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5961 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5962 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5963 _FEED_NAME = 'subscriptions'
3d3dddc9 5964 _TESTS = [{
5965 'url': ':ytsubs',
5966 'only_matching': True,
5967 }, {
5968 'url': ':ytsubscriptions',
5969 'only_matching': True,
5970 }]
1ed5b5c9 5971
1ed5b5c9 5972
25f14e9f 5973class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5974 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5975 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5976 _FEED_NAME = 'history'
3d3dddc9 5977 _TESTS = [{
5978 'url': ':ythistory',
5979 'only_matching': True,
5980 }]
1ed5b5c9
JMF
5981
5982
6e634cbe 5983class YoutubeStoriesIE(InfoExtractor):
5984 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
5985 IE_NAME = 'youtube:stories'
5986 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
5987 _TESTS = [{
5988 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
5989 'only_matching': True,
5990 }]
5991
5992 def _real_extract(self, url):
5993 playlist_id = f'RLTD{self._match_id(url)}'
5994 return self.url_result(
5995 f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
5996 ie=YoutubeTabIE, video_id=playlist_id)
5997
5998
15870e90
PH
5999class YoutubeTruncatedURLIE(InfoExtractor):
6000 IE_NAME = 'youtube:truncated_url'
6001 IE_DESC = False # Do not list
975d35db 6002 _VALID_URL = r'''(?x)
b95aab84
PH
6003 (?:https?://)?
6004 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6005 (?:watch\?(?:
c4808c60 6006 feature=[a-z_]+|
b95aab84
PH
6007 annotation_id=annotation_[^&]+|
6008 x-yt-cl=[0-9]+|
c1708b89 6009 hl=[^&]*|
287be8c6 6010 t=[0-9]+
b95aab84
PH
6011 )?
6012 |
6013 attribution_link\?a=[^&]+
6014 )
6015 $
975d35db 6016 '''
15870e90 6017
c4808c60 6018 _TESTS = [{
2d3d2997 6019 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 6020 'only_matching': True,
dc2fc736 6021 }, {
2d3d2997 6022 'url': 'https://www.youtube.com/watch?',
dc2fc736 6023 'only_matching': True,
b95aab84
PH
6024 }, {
6025 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6026 'only_matching': True,
6027 }, {
6028 'url': 'https://www.youtube.com/watch?feature=foo',
6029 'only_matching': True,
c1708b89
PH
6030 }, {
6031 'url': 'https://www.youtube.com/watch?hl=en-GB',
6032 'only_matching': True,
287be8c6
PH
6033 }, {
6034 'url': 'https://www.youtube.com/watch?t=2372',
6035 'only_matching': True,
c4808c60
PH
6036 }]
6037
15870e90
PH
6038 def _real_extract(self, url):
6039 raise ExtractorError(
78caa52a
PH
6040 'Did you forget to quote the URL? Remember that & is a meta '
6041 'character in most shells, so you want to put the URL in quotes, '
3867038a 6042 'like youtube-dl '
2d3d2997 6043 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 6044 ' or simply youtube-dl BaW_jenozKc .',
15870e90 6045 expected=True)
772fd5cc
PH
6046
6047
471d0367 6048class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6049 IE_NAME = 'youtube:clip'
471d0367 6050 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6051 _TESTS = [{
6052 # FIXME: Other metadata should be extracted from the clip, not from the base video
6053 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6054 'info_dict': {
6055 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6056 'ext': 'mp4',
6057 'section_start': 29.0,
6058 'section_end': 39.7,
6059 'duration': 10.7,
12a1b225
A
6060 'age_limit': 0,
6061 'availability': 'public',
6062 'categories': ['Gaming'],
6063 'channel': 'Scott The Woz',
6064 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6065 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6066 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6067 'like_count': int,
6068 'playable_in_embed': True,
6069 'tags': 'count:17',
6070 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6071 'title': 'Mobile Games on Console - Scott The Woz',
6072 'upload_date': '20210920',
6073 'uploader': 'Scott The Woz',
6074 'uploader_id': 'scottthewoz',
6075 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6076 'view_count': int,
6077 'live_status': 'not_live',
6078 'channel_follower_count': int
471d0367 6079 }
6080 }]
3cd786db 6081
6082 def _real_extract(self, url):
471d0367 6083 clip_id = self._match_id(url)
6084 _, data = self._extract_webpage(url, clip_id)
6085
6086 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6087 if not video_id:
6088 raise ExtractorError('Unable to find video ID')
6089
6090 clip_data = traverse_obj(data, (
6091 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6092 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6093 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6094 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6095
6096 return {
6097 '_type': 'url_transparent',
6098 'url': f'https://www.youtube.com/watch?v={video_id}',
6099 'ie_key': YoutubeIE.ie_key(),
6100 'id': clip_id,
6101 'section_start': int(clip_data['startTimeMs']) / 1000,
6102 'section_end': int(clip_data['endTimeMs']) / 1000,
6103 }
3cd786db 6104
6105
772fd5cc
PH
6106class YoutubeTruncatedIDIE(InfoExtractor):
6107 IE_NAME = 'youtube:truncated_id'
6108 IE_DESC = False # Do not list
b95aab84 6109 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6110
6111 _TESTS = [{
6112 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6113 'only_matching': True,
6114 }]
6115
6116 def _real_extract(self, url):
6117 video_id = self._match_id(url)
6118 raise ExtractorError(
86e5f3ed 6119 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6120 expected=True)