]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[extractor/youtube, cleanup] Fix tests (#4293)
[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,
720c3099 25 bug_reports_message,
82d02080 26 classproperty,
c5e8d7af 27 clean_html,
d92f5d5a 28 datetime_from_str,
11f9be09 29 dict_get,
358de58c 30 error_to_compat_str,
2d30521a 31 float_or_none,
11f9be09 32 format_field,
ff91cf74 33 get_first,
dd27fd17 34 int_or_none,
641ad5d8 35 is_html,
34921b43 36 join_nonempty,
48416bc4 37 js_to_json,
94278f72 38 mimetype2ext,
9c0d7f49 39 network_exceptions,
11f9be09 40 orderedSet,
6310acf5 41 parse_codecs,
49bd8c66 42 parse_count,
7c80519c 43 parse_duration,
7ea65411 44 parse_iso8601,
4dfbf869 45 parse_qs,
dca3ff4a 46 qualities,
c0ac49bc 47 remove_end,
3995d37d 48 remove_start,
cf7e015f 49 smuggle_url,
dbdaaa23 50 str_or_none,
c93d53f5 51 str_to_int,
f3aa3c3f 52 strftime_or_none,
7c365c21 53 traverse_obj,
556dbe7f 54 try_get,
c5e8d7af
PH
55 unescapeHTML,
56 unified_strdate,
f0d785d3 57 unified_timestamp,
cf7e015f 58 unsmuggle_url,
8bdd16b4 59 update_url_query,
21c340b8 60 url_or_none,
fe93e2c4 61 urljoin,
7c365c21 62 variadic,
c5e8d7af
PH
63)
64
962ffcf8 65# any clients starting with _ cannot be explicitly requested by the user
000c15a4 66INNERTUBE_CLIENTS = {
67 'web': {
68 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
69 'INNERTUBE_CONTEXT': {
70 'client': {
71 'clientName': 'WEB',
18c7683d 72 'clientVersion': '2.20211221.00.00',
000c15a4 73 }
74 },
75 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
76 },
77 'web_embedded': {
78 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
79 'INNERTUBE_CONTEXT': {
80 'client': {
81 'clientName': 'WEB_EMBEDDED_PLAYER',
18c7683d 82 'clientVersion': '1.20211215.00.01',
000c15a4 83 },
84 },
85 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
86 },
87 'web_music': {
88 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
89 'INNERTUBE_HOST': 'music.youtube.com',
90 'INNERTUBE_CONTEXT': {
91 'client': {
92 'clientName': 'WEB_REMIX',
18c7683d 93 'clientVersion': '1.20211213.00.00',
000c15a4 94 }
95 },
96 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
97 },
e7e94f2a 98 'web_creator': {
18c7683d 99 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
100 'INNERTUBE_CONTEXT': {
101 'client': {
102 'clientName': 'WEB_CREATOR',
18c7683d 103 'clientVersion': '1.20211220.02.00',
e7e94f2a
D
104 }
105 },
106 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
107 },
000c15a4 108 'android': {
18c7683d 109 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 110 'INNERTUBE_CONTEXT': {
111 'client': {
112 'clientName': 'ANDROID',
18c7683d 113 'clientVersion': '16.49',
000c15a4 114 }
115 },
116 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 117 'REQUIRE_JS_PLAYER': False
000c15a4 118 },
119 'android_embedded': {
18c7683d 120 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 121 'INNERTUBE_CONTEXT': {
122 'client': {
123 'clientName': 'ANDROID_EMBEDDED_PLAYER',
18c7683d 124 'clientVersion': '16.49',
000c15a4 125 },
126 },
b6de707d 127 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
128 'REQUIRE_JS_PLAYER': False
000c15a4 129 },
130 'android_music': {
18c7683d 131 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 132 'INNERTUBE_CONTEXT': {
133 'client': {
134 'clientName': 'ANDROID_MUSIC',
18c7683d 135 'clientVersion': '4.57',
000c15a4 136 }
137 },
138 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 139 'REQUIRE_JS_PLAYER': False
000c15a4 140 },
e7e94f2a 141 'android_creator': {
18c7683d 142 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
143 'INNERTUBE_CONTEXT': {
144 'client': {
145 'clientName': 'ANDROID_CREATOR',
18c7683d 146 'clientVersion': '21.47',
e7e94f2a
D
147 },
148 },
b6de707d 149 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
150 'REQUIRE_JS_PLAYER': False
e7e94f2a 151 },
18c7683d 152 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
153 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 154 'ios': {
18c7683d 155 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 156 'INNERTUBE_CONTEXT': {
157 'client': {
158 'clientName': 'IOS',
18c7683d 159 'clientVersion': '16.46',
160 'deviceModel': 'iPhone14,3',
000c15a4 161 }
162 },
b6de707d 163 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
164 'REQUIRE_JS_PLAYER': False
000c15a4 165 },
166 'ios_embedded': {
000c15a4 167 'INNERTUBE_CONTEXT': {
168 'client': {
169 'clientName': 'IOS_MESSAGES_EXTENSION',
18c7683d 170 'clientVersion': '16.46',
171 'deviceModel': 'iPhone14,3',
000c15a4 172 },
173 },
b6de707d 174 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
175 'REQUIRE_JS_PLAYER': False
000c15a4 176 },
177 'ios_music': {
18c7683d 178 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 179 'INNERTUBE_CONTEXT': {
180 'client': {
181 'clientName': 'IOS_MUSIC',
18c7683d 182 'clientVersion': '4.57',
000c15a4 183 },
184 },
b6de707d 185 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
186 'REQUIRE_JS_PLAYER': False
000c15a4 187 },
e7e94f2a
D
188 'ios_creator': {
189 'INNERTUBE_CONTEXT': {
190 'client': {
191 'clientName': 'IOS_CREATOR',
18c7683d 192 'clientVersion': '21.47',
e7e94f2a
D
193 },
194 },
b6de707d 195 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
196 'REQUIRE_JS_PLAYER': False
e7e94f2a 197 },
3619f78d 198 # mweb has 'ultralow' formats
199 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 200 'mweb': {
18c7683d 201 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 202 'INNERTUBE_CONTEXT': {
203 'client': {
204 'clientName': 'MWEB',
18c7683d 205 'clientVersion': '2.20211221.01.00',
000c15a4 206 }
207 },
208 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
209 },
210 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
211 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
212 'tv_embedded': {
213 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
214 'INNERTUBE_CONTEXT': {
215 'client': {
216 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
217 'clientVersion': '2.0',
218 },
219 },
220 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
221 },
000c15a4 222}
223
224
e7870111
D
225def _split_innertube_client(client_name):
226 variant, *base = client_name.rsplit('.', 1)
227 if base:
228 return variant, base[0], variant
229 base, *variant = client_name.split('_', 1)
230 return client_name, base, variant[0] if variant else None
231
232
000c15a4 233def build_innertube_clients():
2e4cacd0 234 THIRD_PARTY = {
e7870111 235 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 236 }
e7870111 237 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 238 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 239
240 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 241 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 242 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 243 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 244 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 245
e7870111 246 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 247 ytcfg['priority'] = 10 * priority(base_client)
248
e48b3875 249 if not variant:
e7870111
D
250 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
251 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
252 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
253 embedscreen['priority'] -= 3
254 elif variant == 'embedded':
e48b3875 255 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 256 ytcfg['priority'] -= 2
e48b3875 257 else:
000c15a4 258 ytcfg['priority'] -= 3
259
260
261build_innertube_clients()
262
263
de7f3446 264class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 265 """Provide base functions for Youtube extractors"""
e00eb564 266
3462ffa8 267 _RESERVED_NAMES = (
3cd786db 268 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 269 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 270 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 271 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 272
3619f78d 273 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
274
52efa4b3 275 # _NETRC_MACHINE = 'youtube'
3619f78d 276
b2e8bc1b
JMF
277 # If True it will raise an error if no login info is provided
278 _LOGIN_REQUIRED = False
279
d9190e44
RH
280 _INVIDIOUS_SITES = (
281 # invidious-redirect websites
282 r'(?:www\.)?redirect\.invidious\.io',
283 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 284 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
285 r'(?:www\.)?invidious\.pussthecat\.org',
286 r'(?:www\.)?invidious\.zee\.li',
287 r'(?:www\.)?invidious\.ethibox\.fr',
288 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
289 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
290 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
291 # youtube-dl invidious instances list
292 r'(?:(?:www|no)\.)?invidiou\.sh',
293 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
294 r'(?:www\.)?invidious\.kabi\.tk',
295 r'(?:www\.)?invidious\.mastodon\.host',
296 r'(?:www\.)?invidious\.zapashcanon\.fr',
297 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
298 r'(?:www\.)?invidious\.tinfoil-hat\.net',
299 r'(?:www\.)?invidious\.himiko\.cloud',
300 r'(?:www\.)?invidious\.reallyancient\.tech',
301 r'(?:www\.)?invidious\.tube',
302 r'(?:www\.)?invidiou\.site',
303 r'(?:www\.)?invidious\.site',
304 r'(?:www\.)?invidious\.xyz',
305 r'(?:www\.)?invidious\.nixnet\.xyz',
306 r'(?:www\.)?invidious\.048596\.xyz',
307 r'(?:www\.)?invidious\.drycat\.fr',
308 r'(?:www\.)?inv\.skyn3t\.in',
309 r'(?:www\.)?tube\.poal\.co',
310 r'(?:www\.)?tube\.connect\.cafe',
311 r'(?:www\.)?vid\.wxzm\.sx',
312 r'(?:www\.)?vid\.mint\.lgbt',
313 r'(?:www\.)?vid\.puffyan\.us',
314 r'(?:www\.)?yewtu\.be',
315 r'(?:www\.)?yt\.elukerio\.org',
316 r'(?:www\.)?yt\.lelux\.fi',
317 r'(?:www\.)?invidious\.ggc-project\.de',
318 r'(?:www\.)?yt\.maisputain\.ovh',
319 r'(?:www\.)?ytprivate\.com',
320 r'(?:www\.)?invidious\.13ad\.de',
321 r'(?:www\.)?invidious\.toot\.koeln',
322 r'(?:www\.)?invidious\.fdn\.fr',
323 r'(?:www\.)?watch\.nettohikari\.com',
324 r'(?:www\.)?invidious\.namazso\.eu',
325 r'(?:www\.)?invidious\.silkky\.cloud',
326 r'(?:www\.)?invidious\.exonip\.de',
327 r'(?:www\.)?invidious\.riverside\.rocks',
328 r'(?:www\.)?invidious\.blamefran\.net',
329 r'(?:www\.)?invidious\.moomoo\.de',
330 r'(?:www\.)?ytb\.trom\.tf',
331 r'(?:www\.)?yt\.cyberhost\.uk',
332 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
333 r'(?:www\.)?qklhadlycap4cnod\.onion',
334 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
335 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
336 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
337 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
338 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
339 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
340 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
341 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
342 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
343 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
344 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
345 r'(?:www\.)?piped\.kavin\.rocks',
346 r'(?:www\.)?piped\.silkky\.cloud',
347 r'(?:www\.)?piped\.tokhmi\.xyz',
348 r'(?:www\.)?piped\.moomoo\.me',
349 r'(?:www\.)?il\.ax',
350 r'(?:www\.)?piped\.syncpundit\.com',
351 r'(?:www\.)?piped\.mha\.fi',
352 r'(?:www\.)?piped\.mint\.lgbt',
353 r'(?:www\.)?piped\.privacy\.com\.de',
d9190e44
RH
354 )
355
cce889b9 356 def _initialize_consent(self):
357 cookies = self._get_cookies('https://www.youtube.com/')
358 if cookies.get('__Secure-3PSID'):
359 return
360 consent_id = None
361 consent = cookies.get('CONSENT')
362 if consent:
363 if 'YES' in consent.value:
364 return
365 consent_id = self._search_regex(
366 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
367 if not consent_id:
368 consent_id = random.randint(100, 999)
369 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 370
f3aa3c3f 371 def _initialize_pref(self):
372 cookies = self._get_cookies('https://www.youtube.com/')
373 pref_cookie = cookies.get('PREF')
374 pref = {}
375 if pref_cookie:
376 try:
14f25df2 377 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 378 except ValueError:
379 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 380 pref.update({'hl': 'en', 'tz': 'UTC'})
14f25df2 381 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 382
b2e8bc1b 383 def _real_initialize(self):
f3aa3c3f 384 self._initialize_pref()
cce889b9 385 self._initialize_consent()
a25bca9f 386 self._check_login_required()
387
388 def _check_login_required(self):
24146491 389 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 390 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 391
b7c47b74 392 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
393 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 394
000c15a4 395 def _get_default_ytcfg(self, client='web'):
396 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 397
000c15a4 398 def _get_innertube_host(self, client='web'):
399 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 400
000c15a4 401 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 402 # try_get but with fallback to default ytcfg client values when present
403 _func = lambda y: try_get(y, getter, expected_type)
404 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
405
000c15a4 406 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 407 return self._ytcfg_get_safe(
408 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 409 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 410
000c15a4 411 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 412 return self._ytcfg_get_safe(
413 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 414 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 415
2ae778b8 416 def _select_api_hostname(self, req_api_hostname, default_client=None):
417 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
418 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
419
000c15a4 420 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 421 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 422
000c15a4 423 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 424 context = get_first(
425 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 426 # Enforce language and tz for extraction
427 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
428 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 429 return context
430
cf87314d 431 _SAPISID = None
432
109dd3b2 433 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 434 time_now = round(time.time())
cf87314d 435 if self._SAPISID is None:
436 yt_cookies = self._get_cookies('https://www.youtube.com')
437 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
438 # See: https://github.com/yt-dlp/yt-dlp/issues/393
439 sapisid_cookie = dict_get(
440 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
441 if sapisid_cookie and sapisid_cookie.value:
442 self._SAPISID = sapisid_cookie.value
443 self.write_debug('Extracted SAPISID cookie')
444 # SAPISID cookie is required if not already present
445 if not yt_cookies.get('SAPISID'):
446 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
447 self._set_cookie(
448 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
449 else:
450 self._SAPISID = False
451 if not self._SAPISID:
452 return None
1974e99f 453 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
454 sapisidhash = hashlib.sha1(
86e5f3ed 455 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 456 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
457
458 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 459 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 460 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 461
109dd3b2 462 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 463 data.update(query)
11f9be09 464 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 465 real_headers.update({'content-type': 'application/json'})
466 if headers:
467 real_headers.update(headers)
2ae778b8 468 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
469 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 470 return self._download_json(
2ae778b8 471 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 472 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 473 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 474 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 475
65141660 476 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
477 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 478
99e9e001 479 @staticmethod
480 def _extract_session_index(*data):
481 """
482 Index of current account in account list.
483 See: https://github.com/yt-dlp/yt-dlp/pull/519
484 """
485 for ytcfg in data:
486 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
487 if session_index is not None:
488 return session_index
489
490 # Deprecated?
491 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 492 if ytcfg:
14f25df2 493 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
494 if token:
495 return token
99e9e001 496 if webpage:
497 return self._search_regex(
498 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
499 'identity token', default=None, fatal=False)
a1c5d2ca
M
500
501 @staticmethod
fe93e2c4 502 def _extract_account_syncid(*args):
8ea3f7b9 503 """
504 Extract syncId required to download private playlists of secondary channels
fe93e2c4 505 @params response and/or ytcfg
8ea3f7b9 506 """
fe93e2c4 507 for data in args:
508 # ytcfg includes channel_syncid if on secondary channel
14f25df2 509 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 510 if delegated_sid:
511 return delegated_sid
512 sync_ids = (try_get(
513 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 514 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 515 if len(sync_ids) >= 2 and sync_ids[1]:
516 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
517 # and just "user_syncid||" for primary channel. We only want the channel_syncid
518 return sync_ids[0]
a1c5d2ca 519
ac56cf38 520 @staticmethod
521 def _extract_visitor_data(*args):
522 """
523 Extracts visitorData from an API response or ytcfg
524 Appears to be used to track session state
525 """
9222c381 526 return get_first(
6c73052c 527 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 528 expected_type=str)
ac56cf38 529
2762dbb1 530 @functools.cached_property
99e9e001 531 def is_authenticated(self):
532 return bool(self._generate_sapisidhash_header())
533
11f9be09 534 def extract_ytcfg(self, video_id, webpage):
8c54a305 535 if not webpage:
536 return {}
29f7c58a 537 return self._parse_json(
538 self._search_regex(
539 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 540 default='{}'), video_id, fatal=False) or {}
541
11f9be09 542 def generate_api_headers(
99e9e001 543 self, *, ytcfg=None, account_syncid=None, session_index=None,
544 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
545
2ae778b8 546 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 547 headers = {
14f25df2 548 'X-YouTube-Client-Name': str(
11f9be09 549 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
550 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 551 'Origin': origin,
552 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
553 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 554 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 555 }
556 if session_index is None:
314ee305 557 session_index = self._extract_session_index(ytcfg)
558 if account_syncid or session_index is not None:
559 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 560
109dd3b2 561 auth = self._generate_sapisidhash_header(origin)
f4f751af 562 if auth is not None:
563 headers['Authorization'] = auth
109dd3b2 564 headers['X-Origin'] = origin
99e9e001 565 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 566
a25bca9f 567 def _download_ytcfg(self, client, video_id):
568 url = {
569 'web': 'https://www.youtube.com',
570 'web_music': 'https://music.youtube.com',
571 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
572 }.get(client)
573 if not url:
574 return {}
575 webpage = self._download_webpage(
576 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
577 return self.extract_ytcfg(video_id, webpage) or {}
578
2d6659b9 579 @staticmethod
580 def _build_api_continuation_query(continuation, ctp=None):
581 query = {
582 'continuation': continuation
583 }
584 # TODO: Inconsistency with clickTrackingParams.
585 # Currently we have a fixed ctp contained within context (from ytcfg)
586 # and a ctp in root query for continuation.
587 if ctp:
588 query['clickTracking'] = {'clickTrackingParams': ctp}
589 return query
590
2d6659b9 591 @classmethod
592 def _extract_next_continuation_data(cls, renderer):
593 next_continuation = try_get(
594 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
595 lambda x: x['continuation']['reloadContinuationData']), dict)
596 if not next_continuation:
597 return
598 continuation = next_continuation.get('continuation')
599 if not continuation:
600 return
601 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 602 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 603
604 @classmethod
605 def _extract_continuation_ep_data(cls, continuation_ep: dict):
606 if isinstance(continuation_ep, dict):
607 continuation = try_get(
14f25df2 608 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 609 if not continuation:
610 return
611 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 612 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 613
614 @classmethod
615 def _extract_continuation(cls, renderer):
616 next_continuation = cls._extract_next_continuation_data(renderer)
617 if next_continuation:
618 return next_continuation
fe93e2c4 619
2d6659b9 620 contents = []
621 for key in ('contents', 'items'):
622 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 623
2d6659b9 624 for content in contents:
625 if not isinstance(content, dict):
626 continue
627 continuation_ep = try_get(
628 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
629 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
630 dict)
631 continuation = cls._extract_continuation_ep_data(continuation_ep)
632 if continuation:
633 return continuation
634
fe93e2c4 635 @classmethod
636 def _extract_alerts(cls, data):
109dd3b2 637 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
638 if not isinstance(alert_dict, dict):
639 continue
640 for alert in alert_dict.values():
641 alert_type = alert.get('type')
642 if not alert_type:
643 continue
052e1350 644 message = cls._get_text(alert, 'text')
109dd3b2 645 if message:
646 yield alert_type, message
647
c0ac49bc 648 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 649 errors = []
650 warnings = []
651 for alert_type, alert_message in alerts:
641ad5d8 652 if alert_type.lower() == 'error' and fatal:
109dd3b2 653 errors.append([alert_type, alert_message])
654 else:
655 warnings.append([alert_type, alert_message])
656
657 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 658 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 659 if errors:
660 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
661
662 def _extract_and_report_alerts(self, data, *args, **kwargs):
663 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
664
47193e02 665 def _extract_badges(self, renderer: dict):
666 badges = set()
667 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
14f25df2 668 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], str)
47193e02 669 if label:
670 badges.add(label.lower())
671 return badges
672
673 @staticmethod
052e1350 674 def _get_text(data, *path_list, max_runs=None):
675 for path in path_list or [None]:
676 if path is None:
677 obj = [data]
678 else:
679 obj = traverse_obj(data, path, default=[])
680 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
681 obj = [obj]
682 for item in obj:
14f25df2 683 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 684 if text:
685 return text
686 runs = try_get(item, lambda x: x['runs'], list) or []
687 if not runs and isinstance(item, list):
688 runs = item
689
690 runs = runs[:min(len(runs), max_runs or len(runs))]
691 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
692 if text:
693 return text
47193e02 694
f0d785d3 695 def _get_count(self, data, *path_list):
696 count_text = self._get_text(data, *path_list) or ''
697 count = parse_count(count_text)
698 if count is None:
699 count = str_to_int(
700 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
701 return count
702
a709d873 703 @staticmethod
704 def _extract_thumbnails(data, *path_list):
705 """
706 Extract thumbnails from thumbnails dict
707 @param path_list: path list to level that contains 'thumbnails' key
708 """
709 thumbnails = []
710 for path in path_list or [()]:
711 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
712 thumbnail_url = url_or_none(thumbnail.get('url'))
713 if not thumbnail_url:
714 continue
715 # Sometimes youtube gives a wrong thumbnail URL. See:
716 # https://github.com/yt-dlp/yt-dlp/issues/233
717 # https://github.com/ytdl-org/youtube-dl/issues/28023
718 if 'maxresdefault' in thumbnail_url:
719 thumbnail_url = thumbnail_url.split('?')[0]
720 thumbnails.append({
721 'url': thumbnail_url,
722 'height': int_or_none(thumbnail.get('height')),
723 'width': int_or_none(thumbnail.get('width')),
724 })
725 return thumbnails
726
f3aa3c3f 727 @staticmethod
728 def extract_relative_time(relative_time_text):
729 """
730 Extracts a relative time from string and converts to dt object
f0d785d3 731 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 732 """
f0d785d3 733 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 734 if mobj:
f0d785d3 735 start = mobj.group('start')
736 if start:
737 return datetime_from_str(start)
f3aa3c3f 738 try:
f0d785d3 739 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 740 except ValueError:
741 return None
742
743 def _extract_time_text(self, renderer, *path_list):
a25bca9f 744 """@returns (timestamp, time_text)"""
f3aa3c3f 745 text = self._get_text(renderer, *path_list) or ''
746 dt = self.extract_relative_time(text)
747 timestamp = None
748 if isinstance(dt, datetime.datetime):
749 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 750
751 if timestamp is None:
752 timestamp = (
753 unified_timestamp(text) or unified_timestamp(
754 self._search_regex(
17322130 755 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 756 text.lower(), 'time text', default=None)))
f0d785d3 757
f3aa3c3f 758 if text and timestamp is None:
17322130 759 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
f3aa3c3f 760 return timestamp, text
761
109dd3b2 762 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
763 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 764 default_client='web'):
109dd3b2 765 response = None
766 last_error = None
767 count = -1
768 retries = self.get_param('extractor_retries', 3)
769 if check_get_keys is None:
770 check_get_keys = []
771 while count < retries:
772 count += 1
773 if last_error:
c0ac49bc 774 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
109dd3b2 775 try:
776 response = self._call_api(
777 ep=ep, fatal=True, headers=headers,
778 video_id=item_id, query=query,
779 context=self._extract_context(ytcfg, default_client),
780 api_key=self._extract_api_key(ytcfg, default_client),
781 api_hostname=api_hostname, default_client=default_client,
782 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
783 except ExtractorError as e:
9c0d7f49 784 if isinstance(e.cause, network_exceptions):
14f25df2 785 if isinstance(e.cause, urllib.error.HTTPError):
87e8e8a7 786 first_bytes = e.cause.read(512)
787 if not is_html(first_bytes):
788 yt_error = try_get(
789 self._parse_json(
790 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
14f25df2 791 lambda x: x['error']['message'], str)
87e8e8a7 792 if yt_error:
793 self._report_alerts([('ERROR', yt_error)], fatal=False)
109dd3b2 794 # Downloading page may result in intermittent 5xx HTTP error
962ffcf8 795 # Sometimes a 404 is also received. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 796 # We also want to catch all other network exceptions since errors in later pages can be troublesome
797 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
14f25df2 798 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
526d74ec 799 last_error = error_to_compat_str(e.cause or e.msg)
9c0d7f49 800 if count < retries:
801 continue
109dd3b2 802 if fatal:
803 raise
804 else:
805 self.report_warning(error_to_compat_str(e))
806 return
807
808 else:
109dd3b2 809 try:
ac56cf38 810 self._extract_and_report_alerts(response, only_once=True)
109dd3b2 811 except ExtractorError as e:
c0ac49bc 812 # YouTube servers may return errors we want to retry on in a 200 OK response
813 # See: https://github.com/yt-dlp/yt-dlp/issues/839
814 if 'unknown error' in e.msg.lower():
815 last_error = e.msg
816 continue
109dd3b2 817 if fatal:
818 raise
819 self.report_warning(error_to_compat_str(e))
820 return
821 if not check_get_keys or dict_get(response, check_get_keys):
822 break
823 # Youtube sometimes sends incomplete data
824 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
825 last_error = 'Incomplete data received'
826 if count >= retries:
827 if fatal:
828 raise ExtractorError(last_error)
829 else:
830 self.report_warning(last_error)
831 return
832 return response
833
9297939e 834 @staticmethod
835 def is_music_url(url):
836 return re.match(r'https?://music\.youtube\.com/', url) is not None
837
30a074c2 838 def _extract_video(self, renderer):
839 video_id = renderer.get('videoId')
052e1350 840 title = self._get_text(renderer, 'title')
841 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 842 duration = parse_duration(self._get_text(
843 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 844 if duration is None:
845 duration = parse_duration(self._search_regex(
846 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
847 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
848 video_id, default=None, group='duration'))
849
f0d785d3 850 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 851
052e1350 852 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 853 channel_id = traverse_obj(
a44ca5a4 854 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
855 expected_type=str, get_all=False)
f3aa3c3f 856 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
857 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
858 overlay_style = traverse_obj(
a44ca5a4 859 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
860 get_all=False, expected_type=str)
f3aa3c3f 861 badges = self._extract_badges(renderer)
a709d873 862 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
fd2ad7cb 863 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 864 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
865 expected_type=str)) or ''
fd2ad7cb 866 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 867 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 868 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 869
30a074c2 870 return {
39ed931e 871 '_type': 'url',
30a074c2 872 'ie_key': YoutubeIE.ie_key(),
873 'id': video_id,
fd2ad7cb 874 'url': url,
30a074c2 875 'title': title,
876 'description': description,
877 'duration': duration,
878 'view_count': view_count,
879 'uploader': uploader,
f3aa3c3f 880 'channel_id': channel_id,
a709d873 881 'thumbnails': thumbnails,
a44ca5a4 882 'upload_date': (strftime_or_none(timestamp, '%Y%m%d')
883 if self._configuration_arg('approximate_date', ie_key='youtubetab')
884 else None),
f3aa3c3f 885 'live_status': ('is_upcoming' if scheduled_timestamp is not None
886 else 'was_live' if 'streamed' in time_text.lower()
887 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
888 else None),
889 'release_timestamp': scheduled_timestamp,
890 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 891 }
892
0c148415 893
360e1ca5 894class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 895 IE_DESC = 'YouTube'
cb7dfeea 896 _VALID_URL = r"""(?x)^
c5e8d7af 897 (
edb53e2d 898 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 899 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
900 (?:www\.)?deturl\.com/www\.youtube\.com|
901 (?:www\.)?pwnyoutube\.com|
902 (?:www\.)?hooktube\.com|
903 (?:www\.)?yourepeat\.com|
904 tube\.majestyc\.net|
905 %(invidious)s|
906 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
907 (?:.*?\#/)? # handle anchor (#/) redirect urls
908 (?: # the various things that can precede the ID:
b6ce9bb0 909 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 910 |(?: # or the v= param in all its forms
f7000f3a 911 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 912 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 913 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
914 v=
915 )
f4b05232 916 ))
cbaed4bb
S
917 |(?:
918 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
919 vid\.plus| # or vid.plus/xxxx
920 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 921 %(invidious)s
cbaed4bb 922 )/
edb53e2d 923 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 924 )
c5e8d7af 925 )? # all until now is optional -> you can pass the naked ID
201c1459 926 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 927 (?(1).+)? # if we found the ID, everything can follow
9297939e 928 (?:\#|$)""" % {
d9190e44 929 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 930 }
e40c758c 931 _PLAYER_INFO_RE = (
cc2db878 932 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
933 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$',
545cc85d 934 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 935 )
2c62dc26 936 _formats = {
c2d3cb4c 937 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
938 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
939 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
940 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
941 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
942 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
943 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
944 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 945 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 946 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
947 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
948 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
949 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
950 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
951 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 952 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 953 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
954 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 955
956
957 # 3D videos
c2d3cb4c 958 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
959 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
960 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
961 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 962 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
963 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
964 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 965
96fb5605 966 # Apple HTTP Live Streaming
11f12195 967 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 968 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
969 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
970 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
971 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
972 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 973 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
974 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
975
976 # DASH mp4 video
d23028a8
S
977 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
978 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
979 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
980 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
981 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 982 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
983 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
984 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
985 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
986 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
987 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
988 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 989
f6f1fc92 990 # Dash mp4 audio
d23028a8
S
991 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
992 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
993 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
994 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
995 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
996 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
997 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
998
999 # Dash webm
d23028a8
S
1000 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1001 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1002 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1003 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1004 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1005 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1006 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1007 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1008 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1009 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1010 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1011 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1012 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1013 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1014 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1015 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1016 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1017 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1018 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1019 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1020 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1021 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1022
1023 # Dash webm audio
d23028a8
S
1024 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1025 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1026
0857baad 1027 # Dash webm audio with opus inside
d23028a8
S
1028 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1029 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1030 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1031
ce6b9a2d
PH
1032 # RTMP (unnamed)
1033 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1034
1035 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1036 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1037 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1038 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1039 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1040 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1041 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1042 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1043 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1044 }
29f7c58a 1045 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1046
fd5c4aab
S
1047 _GEO_BYPASS = False
1048
78caa52a 1049 IE_NAME = 'youtube'
2eb88d95
PH
1050 _TESTS = [
1051 {
2d3d2997 1052 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1053 'info_dict': {
1054 'id': 'BaW_jenozKc',
1055 'ext': 'mp4',
3867038a 1056 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1057 'uploader': 'Philipp Hagemeister',
1058 'uploader_id': 'phihag',
ec85ded8 1059 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1060 'channel': 'Philipp Hagemeister',
dd4c4492
S
1061 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1062 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1063 'upload_date': '20121002',
ff9f925b 1064 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1065 'categories': ['Science & Technology'],
3867038a 1066 'tags': ['youtube-dl'],
556dbe7f 1067 'duration': 10,
dbdaaa23 1068 'view_count': int,
3e7c1224 1069 'like_count': int,
ff9f925b 1070 'availability': 'public',
1071 'playable_in_embed': True,
1072 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1073 'live_status': 'not_live',
1074 'age_limit': 0,
7c80519c 1075 'start_time': 1,
297a564b 1076 'end_time': 9,
12a1b225 1077 'comment_count': int,
6c73052c 1078 'channel_follower_count': int
2eb88d95 1079 }
0e853ca4 1080 },
fccd3771 1081 {
4bc3a23e
PH
1082 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1083 'note': 'Embed-only video (#1746)',
1084 'info_dict': {
1085 'id': 'yZIXLfi8CZQ',
1086 'ext': 'mp4',
1087 'upload_date': '20120608',
1088 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1089 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1090 'uploader': 'SET India',
94bfcd23 1091 'uploader_id': 'setindia',
ec85ded8 1092 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1093 'age_limit': 18,
545cc85d 1094 },
1095 'skip': 'Private video',
fccd3771 1096 },
11b56058 1097 {
8bdd16b4 1098 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1099 'note': 'Use the first video ID in the URL',
1100 'info_dict': {
1101 'id': 'BaW_jenozKc',
1102 'ext': 'mp4',
3867038a 1103 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1104 'uploader': 'Philipp Hagemeister',
1105 'uploader_id': 'phihag',
ec85ded8 1106 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1107 'channel': 'Philipp Hagemeister',
1108 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1109 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1110 'upload_date': '20121002',
976ae3ea 1111 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1112 'categories': ['Science & Technology'],
3867038a 1113 'tags': ['youtube-dl'],
556dbe7f 1114 'duration': 10,
dbdaaa23 1115 'view_count': int,
11b56058 1116 'like_count': int,
976ae3ea 1117 'availability': 'public',
1118 'playable_in_embed': True,
1119 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1120 'live_status': 'not_live',
1121 'age_limit': 0,
12a1b225 1122 'comment_count': int,
6c73052c 1123 'channel_follower_count': int
34a7de29
S
1124 },
1125 'params': {
1126 'skip_download': True,
1127 },
11b56058 1128 },
dd27fd17 1129 {
2d3d2997 1130 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1131 'note': '256k DASH audio (format 141) via DASH manifest',
1132 'info_dict': {
1133 'id': 'a9LDPn-MO4I',
1134 'ext': 'm4a',
1135 'upload_date': '20121002',
1136 'uploader_id': '8KVIDEO',
ec85ded8 1137 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1138 'description': '',
1139 'uploader': '8KVIDEO',
1140 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1141 },
4bc3a23e
PH
1142 'params': {
1143 'youtube_include_dash_manifest': True,
1144 'format': '141',
4919603f 1145 },
de3c7fe0 1146 'skip': 'format 141 not served anymore',
dd27fd17 1147 },
8bdd16b4 1148 # DASH manifest with encrypted signature
1149 {
1150 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1151 'info_dict': {
1152 'id': 'IB3lcPjvWLA',
1153 'ext': 'm4a',
1154 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1155 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1156 'duration': 244,
1157 'uploader': 'AfrojackVEVO',
1158 'uploader_id': 'AfrojackVEVO',
1159 'upload_date': '20131011',
cc2db878 1160 'abr': 129.495,
976ae3ea 1161 'like_count': int,
1162 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1163 'playable_in_embed': True,
1164 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1165 'view_count': int,
1166 'track': 'The Spark',
1167 'live_status': 'not_live',
1168 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1169 'channel': 'Afrojack',
1170 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1171 'tags': 'count:19',
1172 'availability': 'public',
1173 'categories': ['Music'],
1174 'age_limit': 0,
1175 'alt_title': 'The Spark',
6c73052c 1176 'channel_follower_count': int
8bdd16b4 1177 },
1178 'params': {
1179 'youtube_include_dash_manifest': True,
1180 'format': '141/bestaudio[ext=m4a]',
1181 },
1182 },
65c2fde2 1183 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1184 {
65c2fde2 1185 'note': 'Embed allowed age-gate video',
2d3d2997 1186 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1187 'info_dict': {
1188 'id': 'HtVdAasjOgU',
1189 'ext': 'mp4',
1190 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1191 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1192 'duration': 142,
c522adb1
JMF
1193 'uploader': 'The Witcher',
1194 'uploader_id': 'WitcherGame',
ec85ded8 1195 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1196 'upload_date': '20140605',
34952f09 1197 'age_limit': 18,
976ae3ea 1198 'categories': ['Gaming'],
1199 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1200 'availability': 'needs_auth',
1201 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1202 'like_count': int,
1203 'channel': 'The Witcher',
1204 'live_status': 'not_live',
1205 'tags': 'count:17',
1206 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1207 'playable_in_embed': True,
1208 'view_count': int,
6c73052c 1209 'channel_follower_count': int
c522adb1
JMF
1210 },
1211 },
65c2fde2 1212 {
1213 'note': 'Age-gate video with embed allowed in public site',
1214 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1215 'info_dict': {
1216 'id': 'HsUATh_Nc2U',
1217 'ext': 'mp4',
1218 'title': 'Godzilla 2 (Official Video)',
1219 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1220 'upload_date': '20200408',
1221 'uploader_id': 'FlyingKitty900',
1222 'uploader': 'FlyingKitty',
1223 'age_limit': 18,
976ae3ea 1224 'availability': 'needs_auth',
1225 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1226 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1227 'channel': 'FlyingKitty',
1228 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1229 'view_count': int,
1230 'categories': ['Entertainment'],
1231 'live_status': 'not_live',
1232 'tags': ['Flyingkitty', 'godzilla 2'],
1233 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1234 'like_count': int,
1235 'duration': 177,
1236 'playable_in_embed': True,
6c73052c 1237 'channel_follower_count': int
65c2fde2 1238 },
1239 },
1240 {
1241 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1242 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1243 'info_dict': {
1244 'id': 'Tq92D6wQ1mg',
1245 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1246 'ext': 'mp4',
17322130 1247 'upload_date': '20191228',
65c2fde2 1248 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1249 'uploader': 'Projekt Melody',
1250 'description': 'md5:17eccca93a786d51bc67646756894066',
1251 'age_limit': 18,
976ae3ea 1252 'like_count': int,
1253 'availability': 'needs_auth',
1254 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1255 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1256 'view_count': int,
1257 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1258 'channel': 'Projekt Melody',
1259 'live_status': 'not_live',
1260 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1261 'playable_in_embed': True,
1262 'categories': ['Entertainment'],
1263 'duration': 106,
1264 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1265 'comment_count': int,
6c73052c 1266 'channel_follower_count': int
65c2fde2 1267 },
1268 },
1269 {
1270 'note': 'Non-Agegated non-embeddable video',
1271 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1272 'info_dict': {
1273 'id': 'MeJVWBSsPAY',
1274 'ext': 'mp4',
1275 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1276 'uploader': 'Herr Lurik',
1277 'uploader_id': 'st3in234',
1278 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1279 'upload_date': '20130730',
976ae3ea 1280 'track': 'Such mich find mich',
1281 'age_limit': 0,
1282 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1283 'like_count': int,
1284 'playable_in_embed': False,
1285 'creator': 'OOMPH!',
1286 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1287 'view_count': int,
1288 'alt_title': 'Such mich find mich',
1289 'duration': 210,
1290 'channel': 'Herr Lurik',
1291 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1292 'categories': ['Music'],
1293 'availability': 'public',
1294 'uploader_url': 'http://www.youtube.com/user/st3in234',
1295 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1296 'live_status': 'not_live',
1297 'artist': 'OOMPH!',
6c73052c 1298 'channel_follower_count': int
65c2fde2 1299 },
1300 },
1301 {
1302 'note': 'Non-bypassable age-gated video',
1303 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1304 'only_matching': True,
1305 },
8bdd16b4 1306 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1307 # YouTube Red ad is not captured for creator
1308 {
1309 'url': '__2ABJjxzNo',
1310 'info_dict': {
1311 'id': '__2ABJjxzNo',
1312 'ext': 'mp4',
1313 'duration': 266,
1314 'upload_date': '20100430',
1315 'uploader_id': 'deadmau5',
1316 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1317 'creator': 'deadmau5',
1318 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1319 'uploader': 'deadmau5',
1320 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1321 'alt_title': 'Some Chords',
976ae3ea 1322 'availability': 'public',
1323 'tags': 'count:14',
1324 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1325 'view_count': int,
1326 'live_status': 'not_live',
1327 'channel': 'deadmau5',
1328 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1329 'like_count': int,
1330 'track': 'Some Chords',
1331 'artist': 'deadmau5',
1332 'playable_in_embed': True,
1333 'age_limit': 0,
1334 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1335 'categories': ['Music'],
1336 'album': 'Some Chords',
6c73052c 1337 'channel_follower_count': int
8bdd16b4 1338 },
1339 'expected_warnings': [
1340 'DASH manifest missing',
1341 ]
1342 },
067aa17e 1343 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1344 {
1345 'url': 'lqQg6PlCWgI',
1346 'info_dict': {
1347 'id': 'lqQg6PlCWgI',
1348 'ext': 'mp4',
556dbe7f 1349 'duration': 6085,
90227264 1350 'upload_date': '20150827',
cbe2bd91 1351 'uploader_id': 'olympic',
ec85ded8 1352 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
12a1b225 1353 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
11f9be09 1354 'uploader': 'Olympics',
cbe2bd91 1355 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1356 'like_count': int,
1357 'release_timestamp': 1343767800,
1358 'playable_in_embed': True,
1359 'categories': ['Sports'],
1360 'release_date': '20120731',
1361 'channel': 'Olympics',
1362 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1363 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1364 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1365 'age_limit': 0,
1366 'availability': 'public',
1367 'live_status': 'was_live',
1368 'view_count': int,
1369 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1370 'channel_follower_count': int
cbe2bd91
PH
1371 },
1372 'params': {
1373 'skip_download': 'requires avconv',
e52a40ab 1374 }
cbe2bd91 1375 },
6271f1ca
PH
1376 # Non-square pixels
1377 {
1378 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1379 'info_dict': {
1380 'id': '_b-2C3KPAM0',
1381 'ext': 'mp4',
1382 'stretched_ratio': 16 / 9.,
556dbe7f 1383 'duration': 85,
6271f1ca
PH
1384 'upload_date': '20110310',
1385 'uploader_id': 'AllenMeow',
ec85ded8 1386 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1387 '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 1388 'uploader': '孫ᄋᄅ',
6271f1ca 1389 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1390 'playable_in_embed': True,
1391 'channel': '孫ᄋᄅ',
1392 'age_limit': 0,
1393 'tags': 'count:11',
1394 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1395 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1396 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1397 'view_count': int,
1398 'categories': ['People & Blogs'],
1399 'like_count': int,
1400 'live_status': 'not_live',
1401 'availability': 'unlisted',
12a1b225 1402 'comment_count': int,
6c73052c 1403 'channel_follower_count': int
6271f1ca 1404 },
06b491eb
S
1405 },
1406 # url_encoded_fmt_stream_map is empty string
1407 {
1408 'url': 'qEJwOuvDf7I',
1409 'info_dict': {
1410 'id': 'qEJwOuvDf7I',
f57b7835 1411 'ext': 'webm',
06b491eb
S
1412 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1413 'description': '',
1414 'upload_date': '20150404',
1415 'uploader_id': 'spbelect',
1416 'uploader': 'Наблюдатели Петербурга',
1417 },
1418 'params': {
1419 'skip_download': 'requires avconv',
e323cf3f
S
1420 },
1421 'skip': 'This live event has ended.',
06b491eb 1422 },
067aa17e 1423 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1424 {
1425 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1426 'info_dict': {
1427 'id': 'FIl7x6_3R5Y',
eb6793ba 1428 'ext': 'webm',
da77d856
S
1429 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1430 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1431 'duration': 220,
da77d856
S
1432 'upload_date': '20150625',
1433 'uploader_id': 'dorappi2000',
ec85ded8 1434 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1435 'uploader': 'dorappi2000',
eb6793ba 1436 'formats': 'mincount:31',
da77d856 1437 },
eb6793ba 1438 'skip': 'not actual anymore',
2ee8f5d8 1439 },
8a1a26ce
YCH
1440 # DASH manifest with segment_list
1441 {
1442 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1443 'md5': '8ce563a1d667b599d21064e982ab9e31',
1444 'info_dict': {
1445 'id': 'CsmdDsKjzN8',
1446 'ext': 'mp4',
17ee98e1 1447 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1448 'uploader': 'Airtek',
1449 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1450 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1451 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1452 },
1453 'params': {
1454 'youtube_include_dash_manifest': True,
1455 'format': '135', # bestvideo
be49068d
S
1456 },
1457 'skip': 'This live event has ended.',
2ee8f5d8 1458 },
cf7e015f
S
1459 {
1460 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1461 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1462 'info_dict': {
545cc85d 1463 'id': 'jvGDaLqkpTg',
1464 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1465 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1466 },
1467 'playlist': [{
1468 'info_dict': {
545cc85d 1469 'id': 'jvGDaLqkpTg',
cf7e015f 1470 'ext': 'mp4',
545cc85d 1471 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1472 'description': 'md5:e03b909557865076822aa169218d6a5d',
1473 'duration': 10643,
1474 'upload_date': '20161111',
1475 'uploader': 'Team PGP',
1476 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1477 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1478 },
1479 }, {
1480 'info_dict': {
545cc85d 1481 'id': '3AKt1R1aDnw',
cf7e015f 1482 'ext': 'mp4',
545cc85d 1483 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1484 'description': 'md5:e03b909557865076822aa169218d6a5d',
1485 'duration': 10991,
1486 'upload_date': '20161111',
1487 'uploader': 'Team PGP',
1488 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1489 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1490 },
1491 }, {
1492 'info_dict': {
545cc85d 1493 'id': 'RtAMM00gpVc',
cf7e015f 1494 'ext': 'mp4',
545cc85d 1495 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1496 'description': 'md5:e03b909557865076822aa169218d6a5d',
1497 'duration': 10995,
1498 'upload_date': '20161111',
1499 'uploader': 'Team PGP',
1500 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1501 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1502 },
1503 }, {
1504 'info_dict': {
545cc85d 1505 'id': '6N2fdlP3C5U',
cf7e015f 1506 'ext': 'mp4',
545cc85d 1507 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1508 'description': 'md5:e03b909557865076822aa169218d6a5d',
1509 'duration': 10990,
1510 'upload_date': '20161111',
1511 'uploader': 'Team PGP',
1512 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1513 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1514 },
1515 }],
1516 'params': {
1517 'skip_download': True,
1518 },
65c2fde2 1519 'skip': 'Not multifeed anymore',
cbaed4bb 1520 },
f9f49d87 1521 {
067aa17e 1522 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1523 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1524 'info_dict': {
1525 'id': 'gVfLd0zydlo',
1526 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1527 },
1528 'playlist_count': 2,
be49068d 1529 'skip': 'Not multifeed anymore',
f9f49d87 1530 },
cbaed4bb 1531 {
2d3d2997 1532 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1533 'only_matching': True,
0e49d9a6 1534 },
6d4fc66b 1535 {
2d3d2997 1536 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1537 'only_matching': True,
1538 },
0e49d9a6 1539 {
067aa17e 1540 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1541 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1542 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1543 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1544 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1545 'info_dict': {
1546 'id': 'lsguqyKfVQg',
1547 'ext': 'mp4',
1548 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1549 'alt_title': 'Dark Walk',
0e49d9a6 1550 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1551 'duration': 133,
0e49d9a6
LL
1552 'upload_date': '20151119',
1553 'uploader_id': 'IronSoulElf',
ec85ded8 1554 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1555 'uploader': 'IronSoulElf',
11f9be09 1556 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1557 'track': 'Dark Walk',
1558 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1559 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1560 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1561 'categories': ['Film & Animation'],
1562 'view_count': int,
1563 'live_status': 'not_live',
1564 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1565 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1566 'tags': 'count:13',
1567 'availability': 'public',
1568 'channel': 'IronSoulElf',
1569 'playable_in_embed': True,
1570 'like_count': int,
1571 'age_limit': 0,
6c73052c 1572 'channel_follower_count': int
0e49d9a6
LL
1573 },
1574 'params': {
1575 'skip_download': True,
1576 },
1577 },
61f92af1 1578 {
067aa17e 1579 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1580 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1581 'only_matching': True,
1582 },
313dfc45
LL
1583 {
1584 # Video with yt:stretch=17:0
1585 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1586 'info_dict': {
1587 'id': 'Q39EVAstoRM',
1588 'ext': 'mp4',
1589 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1590 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1591 'upload_date': '20151107',
1592 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1593 'uploader': 'CH GAMER DROID',
1594 },
1595 'params': {
1596 'skip_download': True,
1597 },
be49068d 1598 'skip': 'This video does not exist.',
313dfc45 1599 },
201c1459 1600 {
1601 # Video with incomplete 'yt:stretch=16:'
1602 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1603 'only_matching': True,
1604 },
7caf9830
S
1605 {
1606 # Video licensed under Creative Commons
1607 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1608 'info_dict': {
1609 'id': 'M4gD1WSo5mA',
1610 'ext': 'mp4',
1611 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1612 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1613 'duration': 721,
17322130 1614 'upload_date': '20150128',
7caf9830 1615 'uploader_id': 'BerkmanCenter',
ec85ded8 1616 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1617 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1618 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1619 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1620 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1621 'like_count': int,
1622 'age_limit': 0,
1623 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1624 'channel': 'The Berkman Klein Center for Internet & Society',
1625 'availability': 'public',
1626 'view_count': int,
1627 'categories': ['Education'],
1628 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1629 'live_status': 'not_live',
1630 'playable_in_embed': True,
12a1b225 1631 'comment_count': int,
6c73052c 1632 'channel_follower_count': int
7caf9830
S
1633 },
1634 'params': {
1635 'skip_download': True,
1636 },
1637 },
fd050249
S
1638 {
1639 # Channel-like uploader_url
1640 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1641 'info_dict': {
1642 'id': 'eQcmzGIKrzg',
1643 'ext': 'mp4',
1644 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1645 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1646 'duration': 4060,
17322130 1647 'upload_date': '20151120',
eb6793ba 1648 'uploader': 'Bernie Sanders',
fd050249 1649 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1650 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1651 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1652 'playable_in_embed': True,
1653 'tags': 'count:12',
1654 'like_count': int,
1655 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1656 'age_limit': 0,
1657 'availability': 'public',
1658 'categories': ['News & Politics'],
1659 'channel': 'Bernie Sanders',
1660 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1661 'view_count': int,
1662 'live_status': 'not_live',
1663 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1664 'comment_count': int,
6c73052c 1665 'channel_follower_count': int
fd050249
S
1666 },
1667 'params': {
1668 'skip_download': True,
1669 },
1670 },
040ac686
S
1671 {
1672 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1673 'only_matching': True,
7f29cf54
S
1674 },
1675 {
067aa17e 1676 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1677 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1678 'only_matching': True,
6496ccb4
S
1679 },
1680 {
1681 # Rental video preview
1682 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1683 'info_dict': {
1684 'id': 'uGpuVWrhIzE',
1685 'ext': 'mp4',
1686 'title': 'Piku - Trailer',
1687 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1688 'upload_date': '20150811',
1689 'uploader': 'FlixMatrix',
1690 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1691 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1692 'license': 'Standard YouTube License',
1693 },
1694 'params': {
1695 'skip_download': True,
1696 },
eb6793ba 1697 'skip': 'This video is not available.',
022a5d66 1698 },
12afdc2a
S
1699 {
1700 # YouTube Red video with episode data
1701 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1702 'info_dict': {
1703 'id': 'iqKdEhx-dD4',
1704 'ext': 'mp4',
1705 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1706 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1707 'duration': 2085,
12afdc2a
S
1708 'upload_date': '20170118',
1709 'uploader': 'Vsauce',
1710 'uploader_id': 'Vsauce',
1711 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1712 'series': 'Mind Field',
1713 'season_number': 1,
1714 'episode_number': 1,
976ae3ea 1715 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1716 'tags': 'count:12',
1717 'view_count': int,
1718 'availability': 'public',
1719 'age_limit': 0,
1720 'channel': 'Vsauce',
1721 'episode': 'Episode 1',
1722 'categories': ['Entertainment'],
1723 'season': 'Season 1',
1724 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1725 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1726 'like_count': int,
1727 'playable_in_embed': True,
1728 'live_status': 'not_live',
6c73052c 1729 'channel_follower_count': int
12afdc2a
S
1730 },
1731 'params': {
1732 'skip_download': True,
1733 },
1734 'expected_warnings': [
1735 'Skipping DASH manifest',
1736 ],
1737 },
c7121fa7
S
1738 {
1739 # The following content has been identified by the YouTube community
1740 # as inappropriate or offensive to some audiences.
1741 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1742 'info_dict': {
1743 'id': '6SJNVb0GnPI',
1744 'ext': 'mp4',
1745 'title': 'Race Differences in Intelligence',
1746 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1747 'duration': 965,
1748 'upload_date': '20140124',
1749 'uploader': 'New Century Foundation',
1750 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1751 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1752 },
1753 'params': {
1754 'skip_download': True,
1755 },
545cc85d 1756 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1757 },
022a5d66
S
1758 {
1759 # itag 212
1760 'url': '1t24XAntNCY',
1761 'only_matching': True,
fd5c4aab
S
1762 },
1763 {
1764 # geo restricted to JP
1765 'url': 'sJL6WA-aGkQ',
1766 'only_matching': True,
1767 },
cd5a74a2
S
1768 {
1769 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1770 'only_matching': True,
1771 },
bc2ca1bb 1772 {
1773 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1774 'only_matching': True,
1775 },
1776 {
1777 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1778 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1779 'only_matching': True,
1780 },
825cd268
RA
1781 {
1782 # DRM protected
1783 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1784 'only_matching': True,
4fe54c12
S
1785 },
1786 {
1787 # Video with unsupported adaptive stream type formats
1788 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1789 'info_dict': {
1790 'id': 'Z4Vy8R84T1U',
1791 'ext': 'mp4',
1792 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1793 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1794 'duration': 433,
1795 'upload_date': '20130923',
1796 'uploader': 'Amelia Putri Harwita',
1797 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1798 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1799 'formats': 'maxcount:10',
1800 },
1801 'params': {
1802 'skip_download': True,
1803 'youtube_include_dash_manifest': False,
1804 },
5429d6a9 1805 'skip': 'not actual anymore',
5caabd3c 1806 },
1807 {
822b9d9c 1808 # Youtube Music Auto-generated description
5caabd3c 1809 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1810 'info_dict': {
1811 'id': 'MgNrAu2pzNs',
1812 'ext': 'mp4',
1813 'title': 'Voyeur Girl',
1814 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1815 'upload_date': '20190312',
5429d6a9
S
1816 'uploader': 'Stephen - Topic',
1817 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1818 'artist': 'Stephen',
1819 'track': 'Voyeur Girl',
1820 'album': 'it\'s too much love to know my dear',
1821 'release_date': '20190313',
1822 'release_year': 2019,
976ae3ea 1823 'alt_title': 'Voyeur Girl',
1824 'view_count': int,
1825 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1826 'playable_in_embed': True,
1827 'like_count': int,
1828 'categories': ['Music'],
1829 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1830 'channel': 'Stephen',
1831 'availability': 'public',
1832 'creator': 'Stephen',
1833 'duration': 169,
1834 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1835 'age_limit': 0,
1836 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1837 'tags': 'count:11',
1838 'live_status': 'not_live',
6c73052c 1839 'channel_follower_count': int
5caabd3c 1840 },
1841 'params': {
1842 'skip_download': True,
1843 },
1844 },
66b48727
RA
1845 {
1846 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1847 'only_matching': True,
1848 },
011e75e6
S
1849 {
1850 # invalid -> valid video id redirection
1851 'url': 'DJztXj2GPfl',
1852 'info_dict': {
1853 'id': 'DJztXj2GPfk',
1854 'ext': 'mp4',
1855 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1856 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1857 'upload_date': '20090125',
1858 'uploader': 'Prochorowka',
1859 'uploader_id': 'Prochorowka',
1860 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1861 'artist': 'Panjabi MC',
1862 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1863 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1864 },
1865 'params': {
1866 'skip_download': True,
1867 },
545cc85d 1868 'skip': 'Video unavailable',
ea74e00b
DP
1869 },
1870 {
1871 # empty description results in an empty string
1872 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1873 'info_dict': {
1874 'id': 'x41yOUIvK2k',
1875 'ext': 'mp4',
1876 'title': 'IMG 3456',
1877 'description': '',
1878 'upload_date': '20170613',
1879 'uploader_id': 'ElevageOrVert',
1880 'uploader': 'ElevageOrVert',
976ae3ea 1881 'view_count': int,
1882 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1883 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1884 'like_count': int,
1885 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1886 'tags': [],
1887 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1888 'availability': 'public',
1889 'age_limit': 0,
1890 'categories': ['Pets & Animals'],
1891 'duration': 7,
1892 'playable_in_embed': True,
1893 'live_status': 'not_live',
1894 'channel': 'ElevageOrVert',
6c73052c 1895 'channel_follower_count': int
ea74e00b
DP
1896 },
1897 'params': {
1898 'skip_download': True,
1899 },
1900 },
a0566bbf 1901 {
29f7c58a 1902 # with '};' inside yt initial data (see [1])
1903 # see [2] for an example with '};' inside ytInitialPlayerResponse
1904 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1905 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1906 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1907 'info_dict': {
1908 'id': 'CHqg6qOn4no',
1909 'ext': 'mp4',
1910 'title': 'Part 77 Sort a list of simple types in c#',
1911 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1912 'upload_date': '20130831',
1913 'uploader_id': 'kudvenkat',
1914 'uploader': 'kudvenkat',
976ae3ea 1915 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1916 'like_count': int,
1917 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1918 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1919 'live_status': 'not_live',
1920 'categories': ['Education'],
1921 'availability': 'public',
1922 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1923 'tags': 'count:12',
1924 'playable_in_embed': True,
1925 'age_limit': 0,
1926 'view_count': int,
1927 'duration': 522,
1928 'channel': 'kudvenkat',
12a1b225 1929 'comment_count': int,
6c73052c 1930 'channel_follower_count': int
a0566bbf 1931 },
1932 'params': {
1933 'skip_download': True,
1934 },
1935 },
29f7c58a 1936 {
1937 # another example of '};' in ytInitialData
1938 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1939 'only_matching': True,
1940 },
1941 {
1942 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1943 'only_matching': True,
1944 },
545cc85d 1945 {
cc2db878 1946 # https://github.com/ytdl-org/youtube-dl/pull/28094
1947 'url': 'OtqTfy26tG0',
1948 'info_dict': {
1949 'id': 'OtqTfy26tG0',
1950 'ext': 'mp4',
1951 'title': 'Burn Out',
1952 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1953 'upload_date': '20141120',
1954 'uploader': 'The Cinematic Orchestra - Topic',
1955 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1956 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1957 'artist': 'The Cinematic Orchestra',
1958 'track': 'Burn Out',
1959 'album': 'Every Day',
976ae3ea 1960 'like_count': int,
1961 'live_status': 'not_live',
1962 'alt_title': 'Burn Out',
1963 'duration': 614,
1964 'age_limit': 0,
1965 'view_count': int,
1966 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1967 'creator': 'The Cinematic Orchestra',
1968 'channel': 'The Cinematic Orchestra',
1969 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1970 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1971 'availability': 'public',
1972 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1973 'categories': ['Music'],
1974 'playable_in_embed': True,
6c73052c 1975 'channel_follower_count': int
cc2db878 1976 },
1977 'params': {
1978 'skip_download': True,
1979 },
545cc85d 1980 },
bc2ca1bb 1981 {
1982 # controversial video, only works with bpctr when authenticated with cookies
1983 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1984 'only_matching': True,
1985 },
a1a7907b 1986 {
1987 # controversial video, requires bpctr/contentCheckOk
1988 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1989 'info_dict': {
1990 'id': 'SZJvDhaSDnc',
1991 'ext': 'mp4',
1992 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1993 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1994 'uploader': 'CBS Mornings',
11f9be09 1995 'uploader_id': 'CBSThisMorning',
a1a7907b 1996 'upload_date': '20140716',
976ae3ea 1997 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1998 'duration': 170,
1999 'categories': ['News & Politics'],
2000 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2001 'view_count': int,
2002 'channel': 'CBS Mornings',
2003 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2004 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2005 'age_limit': 18,
2006 'availability': 'needs_auth',
2007 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2008 'like_count': int,
2009 'live_status': 'not_live',
2010 'playable_in_embed': True,
6c73052c 2011 'channel_follower_count': int
a1a7907b 2012 }
2013 },
f7ad7160 2014 {
2015 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2016 'url': 'cBvYw8_A0vQ',
2017 'info_dict': {
2018 'id': 'cBvYw8_A0vQ',
2019 'ext': 'mp4',
2020 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2021 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2022 'upload_date': '20201120',
2023 'uploader': 'Walk around Japan',
2024 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2025 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2026 'duration': 1456,
2027 'categories': ['Travel & Events'],
2028 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2029 'view_count': int,
2030 'channel': 'Walk around Japan',
2031 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2032 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2033 'age_limit': 0,
2034 'availability': 'public',
2035 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2036 'live_status': 'not_live',
2037 'playable_in_embed': True,
6c73052c 2038 'channel_follower_count': int
f7ad7160 2039 },
2040 'params': {
2041 'skip_download': True,
2042 },
0fb983f6 2043 }, {
2044 # Has multiple audio streams
2045 'url': 'WaOKSUlf4TM',
2046 'only_matching': True
9297939e 2047 }, {
2048 # Requires Premium: has format 141 when requested using YTM url
2049 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2050 'only_matching': True
2051 }, {
120916da 2052 # multiple subtitles with same lang_code
2053 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2054 'only_matching': True,
109dd3b2 2055 }, {
2056 # Force use android client fallback
2057 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2058 'info_dict': {
2059 'id': 'YOelRv7fMxY',
11f9be09 2060 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2061 'ext': '3gp',
2062 'upload_date': '20210624',
2063 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2064 'uploader': 'colinfurze',
11f9be09 2065 'uploader_id': 'colinfurze',
109dd3b2 2066 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2067 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2068 'duration': 596,
2069 'categories': ['Entertainment'],
2070 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2071 'view_count': int,
2072 'channel': 'colinfurze',
2073 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2074 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2075 'age_limit': 0,
2076 'availability': 'public',
2077 'like_count': int,
2078 'live_status': 'not_live',
2079 'playable_in_embed': True,
6c73052c 2080 'channel_follower_count': int
109dd3b2 2081 },
2082 'params': {
2083 'format': '17', # 3gp format available on android
2084 'extractor_args': {'youtube': {'player_client': ['android']}},
2085 },
120916da 2086 },
109dd3b2 2087 {
2088 # Skip download of additional client configs (remix client config in this case)
2089 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2090 'only_matching': True,
2091 'params': {
2092 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2093 },
8fc54b12 2094 }, {
2095 # shorts
2096 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2097 'only_matching': True,
9222c381 2098 }, {
2099 'note': 'Storyboards',
2100 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2101 'info_dict': {
2102 'id': '5KLPxDtMqe8',
2103 'ext': 'mhtml',
2104 'format_id': 'sb0',
2105 'title': 'Your Brain is Plastic',
2106 'uploader_id': 'scishow',
2107 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2108 'upload_date': '20140324',
2109 'uploader': 'SciShow',
976ae3ea 2110 'like_count': int,
2111 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2112 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2113 'view_count': int,
2114 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2115 'playable_in_embed': True,
2116 'tags': 'count:12',
2117 'uploader_url': 'http://www.youtube.com/user/scishow',
2118 'availability': 'public',
2119 'channel': 'SciShow',
2120 'live_status': 'not_live',
2121 'duration': 248,
2122 'categories': ['Education'],
2123 'age_limit': 0,
6c73052c 2124 'channel_follower_count': int
9222c381 2125 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2126 }, {
2127 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2128 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2129 'info_dict': {
2130 'id': '2NUZ8W2llS4',
2131 'ext': 'mp4',
2132 'title': 'The NP that test your phone performance 🙂',
2133 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2134 'uploader': 'Leon Nguyen',
2135 'uploader_id': 'VNSXIII',
2136 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2137 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2138 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2139 'duration': 21,
2140 'view_count': int,
2141 'age_limit': 0,
2142 'categories': ['Gaming'],
2143 'tags': 'count:23',
2144 'playable_in_embed': True,
2145 'live_status': 'not_live',
2146 'upload_date': '20220103',
2147 'like_count': int,
2148 'availability': 'public',
2149 'channel': 'Leon Nguyen',
2150 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2151 'comment_count': int,
992f9a73 2152 'channel_follower_count': int
2153 }
2154 }, {
2155 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2156 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2157 'info_dict': {
2158 'id': 'mzZzzBU6lrM',
2159 'ext': 'mp4',
2160 'title': 'I Met GeorgeNotFound In Real Life...',
2161 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2162 'uploader': 'Quackity',
2163 'uploader_id': 'QuackityHQ',
2164 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2165 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2166 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2167 'duration': 955,
2168 'view_count': int,
2169 'age_limit': 0,
2170 'categories': ['Entertainment'],
2171 'tags': 'count:26',
2172 'playable_in_embed': True,
2173 'live_status': 'not_live',
2174 'release_timestamp': 1641172509,
2175 'release_date': '20220103',
2176 'upload_date': '20220103',
2177 'like_count': int,
2178 'availability': 'public',
2179 'channel': 'Quackity',
2180 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2181 'channel_follower_count': int
2182 }
2183 },
2184 { # continuous livestream. Microformat upload date should be preferred.
2185 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2186 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2187 'info_dict': {
2188 'id': 'kgx4WGK0oNU',
2189 '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}',
2190 'ext': 'mp4',
2191 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2192 'availability': 'public',
2193 'age_limit': 0,
2194 'release_timestamp': 1637975704,
2195 'upload_date': '20210619',
2196 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2197 'live_status': 'is_live',
2198 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2199 'uploader': '阿鲍Abao',
2200 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2201 'channel': 'Abao in Tokyo',
2202 'channel_follower_count': int,
2203 'release_date': '20211127',
2204 'tags': 'count:39',
2205 'categories': ['People & Blogs'],
2206 'like_count': int,
2207 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2208 'view_count': int,
2209 'playable_in_embed': True,
2210 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2211 },
2212 'params': {'skip_download': True}
6e634cbe 2213 }, {
2214 # Story. Requires specific player params to work.
ee27297f 2215 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2216 'info_dict': {
ee27297f 2217 'id': 'vv8qTUWmulI',
6e634cbe 2218 'ext': 'mp4',
ee27297f 2219 'availability': 'unlisted',
2220 'view_count': int,
2221 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2222 'upload_date': '20220526',
2223 'categories': ['Education'],
2224 'title': 'Story',
2225 'channel': 'IT\'S HISTORY',
2226 'description': '',
2227 'uploader_id': 'BlastfromthePast',
2228 'duration': 12,
2229 'uploader': 'IT\'S HISTORY',
6e634cbe 2230 'playable_in_embed': True,
6e634cbe 2231 'age_limit': 0,
6e634cbe 2232 'live_status': 'not_live',
ee27297f 2233 'tags': [],
2234 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2235 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2236 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
12a1b225
A
2237 },
2238 'skip': 'stories get removed after some period of time',
ee27297f 2239 }, {
2240 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2241 'info_dict': {
2242 'id': 'tjjjtzRLHvA',
2243 'ext': 'mp4',
2244 'title': 'ハッシュタグ無し };if window.ytcsi',
2245 'upload_date': '20220323',
2246 'like_count': int,
2247 'availability': 'unlisted',
2248 'channel': 'nao20010128nao',
2249 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2250 'age_limit': 0,
2251 'uploader': 'nao20010128nao',
2252 'uploader_id': 'nao20010128nao',
2253 'categories': ['Music'],
6e634cbe 2254 'view_count': int,
2255 'description': '',
ee27297f 2256 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2257 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2258 'live_status': 'not_live',
2259 'playable_in_embed': True,
2260 'channel_follower_count': int,
2261 'duration': 6,
2262 'tags': [],
2263 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2264 }
2265 }
2eb88d95
PH
2266 ]
2267
201c1459 2268 @classmethod
2269 def suitable(cls, url):
4dfbf869 2270 from ..utils import parse_qs
2271
201c1459 2272 qs = parse_qs(url)
2273 if qs.get('list', [None])[0]:
2274 return False
86e5f3ed 2275 return super().suitable(url)
201c1459 2276
e0df6211 2277 def __init__(self, *args, **kwargs):
86e5f3ed 2278 super().__init__(*args, **kwargs)
545cc85d 2279 self._code_cache = {}
83799698 2280 self._player_cache = {}
e0df6211 2281
adbc4ec4 2282 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2283 lock = threading.Lock()
2284
2285 is_live = True
185bf310 2286 start_time = time.time()
adbc4ec4
THD
2287 formats = [f for f in formats if f.get('is_from_start')]
2288
185bf310 2289 def refetch_manifest(format_id, delay):
2290 nonlocal formats, start_time, is_live
2291 if time.time() <= start_time + delay:
adbc4ec4
THD
2292 return
2293
2294 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2295 video_details = traverse_obj(
2296 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2297 microformats = traverse_obj(
2298 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2299 expected_type=dict, default=[])
2300 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2301 start_time = time.time()
adbc4ec4 2302
185bf310 2303 def mpd_feed(format_id, delay):
adbc4ec4
THD
2304 """
2305 @returns (manifest_url, manifest_stream_number, is_live) or None
2306 """
2307 with lock:
185bf310 2308 refetch_manifest(format_id, delay)
adbc4ec4
THD
2309
2310 f = next((f for f in formats if f['format_id'] == format_id), None)
2311 if not f:
185bf310 2312 if not is_live:
2313 self.to_screen(f'{video_id}: Video is no longer live')
2314 else:
2315 self.report_warning(
2316 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2317 return None
2318 return f['manifest_url'], f['manifest_stream_number'], is_live
2319
2320 for f in formats:
a539f065 2321 f['is_live'] = True
adbc4ec4
THD
2322 f['protocol'] = 'http_dash_segments_generator'
2323 f['fragments'] = functools.partial(
2324 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2325
2326 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2327 FETCH_SPAN, MAX_DURATION = 5, 432000
2328
2329 mpd_url, stream_number, is_live = None, None, True
2330
2331 begin_index = 0
2332 download_start_time = ctx.get('start') or time.time()
2333
2334 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2335 if lack_early_segments:
2336 self.report_warning(bug_reports_message(
2337 'Starting download from the last 120 hours of the live stream since '
2338 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2339 lack_early_segments = True
2340
2341 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2342 fragments, fragment_base_url = None, None
2343
a539f065 2344 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2345 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2346 # Obtain from MPD's maximum seq value
2347 old_mpd_url = mpd_url
185bf310 2348 last_error = ctx.pop('last_error', None)
14f25df2 2349 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2350 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2351 or (mpd_url, stream_number, False))
2352 if not refresh_sequence:
2353 if expire_fast and not is_live:
2354 return False, last_seq
2355 elif old_mpd_url == mpd_url:
2356 return True, last_seq
adbc4ec4
THD
2357 try:
2358 fmts, _ = self._extract_mpd_formats_and_subtitles(
2359 mpd_url, None, note=False, errnote=False, fatal=False)
2360 except ExtractorError:
2361 fmts = None
2362 if not fmts:
a539f065 2363 no_fragment_score += 2
adbc4ec4
THD
2364 return False, last_seq
2365 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2366 fragments = fmt_info['fragments']
2367 fragment_base_url = fmt_info['fragment_base_url']
2368 assert fragment_base_url
2369
2370 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2371 return True, _last_seq
2372
2373 while is_live:
2374 fetch_time = time.time()
2375 if no_fragment_score > 30:
2376 return
2377 if last_segment_url:
2378 # Obtain from "X-Head-Seqnum" header value from each segment
2379 try:
2380 urlh = self._request_webpage(
2381 last_segment_url, None, note=False, errnote=False, fatal=False)
2382 except ExtractorError:
2383 urlh = None
2384 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2385 if last_seq is None:
a539f065 2386 no_fragment_score += 2
adbc4ec4
THD
2387 last_segment_url = None
2388 continue
2389 else:
a539f065
LNO
2390 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2391 no_fragment_score += 2
185bf310 2392 if not should_continue:
adbc4ec4
THD
2393 continue
2394
2395 if known_idx > last_seq:
2396 last_segment_url = None
2397 continue
2398
2399 last_seq += 1
2400
2401 if begin_index < 0 and known_idx < 0:
2402 # skip from the start when it's negative value
2403 known_idx = last_seq + begin_index
2404 if lack_early_segments:
2405 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2406 try:
2407 for idx in range(known_idx, last_seq):
2408 # do not update sequence here or you'll get skipped some part of it
a539f065 2409 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2410 if not should_continue:
adbc4ec4
THD
2411 known_idx = idx - 1
2412 raise ExtractorError('breaking out of outer loop')
2413 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2414 yield {
2415 'url': last_segment_url,
36195c44 2416 'fragment_count': last_seq,
adbc4ec4
THD
2417 }
2418 if known_idx == last_seq:
2419 no_fragment_score += 5
2420 else:
2421 no_fragment_score = 0
2422 known_idx = last_seq
2423 except ExtractorError:
2424 continue
2425
2426 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2427
b6de707d 2428 def _extract_player_url(self, *ytcfgs, webpage=None):
2429 player_url = traverse_obj(
2430 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2431 get_all=False, expected_type=str)
11f9be09 2432 if not player_url:
b6de707d 2433 return
60f393e4 2434 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2435
b6de707d 2436 def _download_player_url(self, video_id, fatal=False):
2437 res = self._download_webpage(
2438 'https://www.youtube.com/iframe_api',
2439 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2440 if res:
2441 player_version = self._search_regex(
2442 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2443 if player_version:
2444 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2445
60064c53
PH
2446 def _signature_cache_id(self, example_sig):
2447 """ Return a string representation of a signature """
14f25df2 2448 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2449
e40c758c
S
2450 @classmethod
2451 def _extract_player_info(cls, player_url):
2452 for player_re in cls._PLAYER_INFO_RE:
2453 id_m = re.search(player_re, player_url)
2454 if id_m:
2455 break
2456 else:
c081b35c 2457 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2458 return id_m.group('id')
e40c758c 2459
404f611f 2460 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2461 player_id = self._extract_player_info(player_url)
2462 if player_id not in self._code_cache:
1276a43a 2463 code = self._download_webpage(
109dd3b2 2464 player_url, video_id, fatal=fatal,
2465 note='Downloading player ' + player_id,
2466 errnote='Download of %s failed' % player_url)
1276a43a 2467 if code:
2468 self._code_cache[player_id] = code
404f611f 2469 return self._code_cache.get(player_id)
109dd3b2 2470
e40c758c 2471 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2472 player_id = self._extract_player_info(player_url)
e0df6211 2473
c4417ddb 2474 # Read from filesystem cache
86e5f3ed 2475 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2476 assert os.path.basename(func_id) == func_id
a0e07d31 2477
ae61d108 2478 self.write_debug(f'Extracting signature function {func_id}')
9809740b 2479 cache_spec = self.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2480 if cache_spec is not None:
78caa52a 2481 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2482
404f611f 2483 code = self._load_player(video_id, player_url)
2484 if code:
109dd3b2 2485 res = self._parse_sig_js(code)
e0df6211 2486
ac668111 2487 test_string = ''.join(map(chr, range(len(example_sig))))
109dd3b2 2488 cache_res = res(test_string)
2489 cache_spec = [ord(c) for c in cache_res]
83799698 2490
9809740b 2491 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
109dd3b2 2492 return res
83799698 2493
60064c53 2494 def _print_sig_code(self, func, example_sig):
404f611f 2495 if not self.get_param('youtube_print_sig_code'):
2496 return
2497
edf3e38e
PH
2498 def gen_sig_code(idxs):
2499 def _genslice(start, end, step):
78caa52a 2500 starts = '' if start == 0 else str(start)
8bcc8756 2501 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2502 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2503 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2504
2505 step = None
7af808a5
PH
2506 # Quelch pyflakes warnings - start will be set when step is set
2507 start = '(Never used)'
edf3e38e
PH
2508 for i, prev in zip(idxs[1:], idxs[:-1]):
2509 if step is not None:
2510 if i - prev == step:
2511 continue
2512 yield _genslice(start, prev, step)
2513 step = None
2514 continue
2515 if i - prev in [-1, 1]:
2516 step = i - prev
2517 start = prev
2518 continue
2519 else:
78caa52a 2520 yield 's[%d]' % prev
edf3e38e 2521 if step is None:
78caa52a 2522 yield 's[%d]' % i
edf3e38e
PH
2523 else:
2524 yield _genslice(start, i, step)
2525
ac668111 2526 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2527 cache_res = func(test_string)
edf3e38e 2528 cache_spec = [ord(c) for c in cache_res]
78caa52a 2529 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2530 signature_id_tuple = '(%s)' % (
14f25df2 2531 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2532 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2533 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2534 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2535
e0df6211
PH
2536 def _parse_sig_js(self, jscode):
2537 funcname = self._search_regex(
abefc03f
S
2538 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2539 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
2540 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2541 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2542 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}\(a,\d+\)',
2543 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 2544 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2545 # Obsolete patterns
2546 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2547 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2548 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2549 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2550 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2551 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2552 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2553 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2554 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2555
2556 jsi = JSInterpreter(jscode)
2557 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2558 return lambda s: initial_function([s])
2559
545cc85d 2560 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2561 """Turn the encrypted s field into a working signature"""
c8bf86d5 2562 try:
62af3a0e 2563 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5 2564 if player_id not in self._player_cache:
52023f12 2565 func = self._extract_signature_function(video_id, player_url, s)
c8bf86d5
PH
2566 self._player_cache[player_id] = func
2567 func = self._player_cache[player_id]
404f611f 2568 self._print_sig_code(func, s)
c8bf86d5
PH
2569 return func(s)
2570 except Exception as e:
52023f12 2571 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2572
2573 def _decrypt_nsig(self, s, video_id, player_url):
2574 """Turn the encrypted n field into a working signature"""
2575 if player_url is None:
2576 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2577 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2578
2579 sig_id = ('nsig_value', s)
2580 if sig_id in self._player_cache:
2581 return self._player_cache[sig_id]
2582
2583 try:
2584 player_id = ('nsig', player_url)
2585 if player_id not in self._player_cache:
2586 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2587 func = self._player_cache[player_id]
2588 self._player_cache[sig_id] = func(s)
2589 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2590 return self._player_cache[sig_id]
2591 except Exception as e:
aa9369a2 2592 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2593
2594 def _extract_n_function_name(self, jscode):
48416bc4 2595 nfunc, idx = self._search_regex(
c571b3a6 2596 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2597 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2598 if not idx:
2599 return nfunc
2600 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2601 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2602 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2603
2604 def _extract_n_function(self, video_id, player_url):
2605 player_id = self._extract_player_info(player_url)
9809740b 2606 func_code = self.cache.load('youtube-nsig', player_id)
404f611f 2607
2608 if func_code:
2609 jsi = JSInterpreter(func_code)
2610 else:
2611 jscode = self._load_player(video_id, player_url)
2612 funcname = self._extract_n_function_name(jscode)
2613 jsi = JSInterpreter(jscode)
2614 func_code = jsi.extract_function_code(funcname)
9809740b 2615 self.cache.store('youtube-nsig', player_id, func_code)
404f611f 2616
2617 if self.get_param('youtube_print_sig_code'):
2618 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2619
2620 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2621
109dd3b2 2622 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2623 """
2624 Extract signatureTimestamp (sts)
2625 Required to tell API what sig/player version is in use.
2626 """
2627 sts = None
2628 if isinstance(ytcfg, dict):
2629 sts = int_or_none(ytcfg.get('STS'))
2630
2631 if not sts:
2632 # Attempt to extract from player
2633 if player_url is None:
2634 error_msg = 'Cannot extract signature timestamp without player_url.'
2635 if fatal:
2636 raise ExtractorError(error_msg)
2637 self.report_warning(error_msg)
2638 return
404f611f 2639 code = self._load_player(video_id, player_url, fatal=fatal)
2640 if code:
109dd3b2 2641 sts = int_or_none(self._search_regex(
2642 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2643 'JS player signature timestamp', group='sts', fatal=fatal))
2644 return sts
2645
11f9be09 2646 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
2647 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2648 label = 'fully ' if is_full else ''
2649 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2650 expected_type=url_or_none)
2651 if not url:
2652 self.report_warning(f'Unable to mark {label}watched')
2653 return
14f25df2 2654 parsed_url = urllib.parse.urlparse(url)
2655 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
2656
2657 # cpn generation algorithm is reverse engineered from base.js.
2658 # In fact it works even with dummy cpn.
2659 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2660 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2661
2662 # # more consistent results setting it to right before the end
2663 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2664
2665 qs.update({
2666 'ver': ['2'],
2667 'cpn': [cpn],
2668 'cmt': video_length,
2669 'el': 'detailpage', # otherwise defaults to "shorts"
2670 })
2671
2672 if is_full:
2673 # these seem to mark watchtime "history" in the real world
2674 # they're required, so send in a single value
2675 qs.update({
2676 'st': video_length,
2677 'et': video_length,
2678 })
2679
14f25df2 2680 url = urllib.parse.urlunparse(
2681 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
2682
2683 self._download_webpage(
2684 url, video_id, f'Marking {label}watched',
2685 'Unable to mark watched', fatal=False)
d77ab8e2 2686
66c9fa36
S
2687 @staticmethod
2688 def _extract_urls(webpage):
2689 # Embedded YouTube player
2690 entries = [
2691 unescapeHTML(mobj.group('url'))
2692 for mobj in re.finditer(r'''(?x)
2693 (?:
2694 <iframe[^>]+?src=|
2695 data-video-url=|
2696 <embed[^>]+?src=|
2697 embedSWF\(?:\s*|
2698 <object[^>]+data=|
2699 new\s+SWFObject\(
2700 )
2701 (["\'])
2702 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2703 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2704 \1''', webpage)]
2705
2706 # lazyYT YouTube embed
2707 entries.extend(list(map(
2708 unescapeHTML,
2709 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2710
2711 # Wordpress "YouTube Video Importer" plugin
2712 matches = re.findall(r'''(?x)<div[^>]+
2713 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2714 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2715 entries.extend(m[-1] for m in matches)
2716
2717 return entries
2718
2719 @staticmethod
2720 def _extract_url(webpage):
2721 urls = YoutubeIE._extract_urls(webpage)
2722 return urls[0] if urls else None
2723
97665381
PH
2724 @classmethod
2725 def extract_id(cls, url):
ae61d108 2726 video_id = cls.get_temp_id(url)
2727 if not video_id:
2728 raise ExtractorError(f'Invalid URL: {url}')
2729 return video_id
c5e8d7af 2730
7c365c21 2731 def _extract_chapters_from_json(self, data, duration):
2732 chapter_list = traverse_obj(
2733 data, (
2734 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2735 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2736 ), expected_type=list)
2737
2738 return self._extract_chapters(
2739 chapter_list,
2740 chapter_time=lambda chapter: float_or_none(
2741 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2742 chapter_title=lambda chapter: traverse_obj(
2743 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2744 duration=duration)
2745
2746 def _extract_chapters_from_engagement_panel(self, data, duration):
2747 content_list = traverse_obj(
8bdd16b4 2748 data,
7c365c21 2749 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2750 expected_type=list, default=[])
052e1350 2751 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2752 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2753
1890fc63 2754 return next(filter(None, (
2755 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2756 chapter_time, chapter_title, duration)
2757 for contents in content_list)), [])
7c365c21 2758
1890fc63 2759 def _extract_chapters_from_description(self, description, duration):
2760 return self._extract_chapters(
2761 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2762 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2763 duration=duration, strict=False)
84213ea8 2764
1890fc63 2765 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2766 if not duration:
2767 return
2768 chapter_list = [{
2769 'start_time': chapter_time(chapter),
2770 'title': chapter_title(chapter),
2771 } for chapter in chapter_list or []]
2772 if not strict:
2773 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2774
a3976e07 2775 chapters = [{'start_time': 0}]
1890fc63 2776 for idx, chapter in enumerate(chapter_list):
a3976e07 2777 if chapter['start_time'] is None:
1890fc63 2778 self.report_warning(f'Incomplete chapter {idx}')
2779 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
1890fc63 2780 chapters.append(chapter)
2781 else:
2782 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}"')
a3976e07 2783 return chapters[1:]
84213ea8 2784
a1c5d2ca
M
2785 def _extract_comment(self, comment_renderer, parent=None):
2786 comment_id = comment_renderer.get('commentId')
2787 if not comment_id:
2788 return
fe93e2c4 2789
052e1350 2790 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2791
49bd8c66 2792 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2793 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2794 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca 2795 author_id = try_get(comment_renderer,
14f25df2 2796 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
fe93e2c4 2797
49bd8c66 2798 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
14f25df2 2799 lambda x: x['likeCount']), str)) or 0
a1c5d2ca 2800 author_thumbnail = try_get(comment_renderer,
14f25df2 2801 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
a1c5d2ca
M
2802
2803 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2804 is_favorited = 'creatorHeart' in (try_get(
2805 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2806 return {
2807 'id': comment_id,
2808 'text': text,
d92f5d5a 2809 'timestamp': timestamp,
a1c5d2ca
M
2810 'time_text': time_text,
2811 'like_count': votes,
97524332 2812 'is_favorited': is_favorited,
a1c5d2ca
M
2813 'author': author,
2814 'author_id': author_id,
2815 'author_thumbnail': author_thumbnail,
2816 'author_is_uploader': author_is_uploader,
2817 'parent': parent or 'root'
2818 }
2819
46383212 2820 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2821
2822 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2823
2824 def extract_header(contents):
2d6659b9 2825 _continuation = None
2826 for content in contents:
46383212 2827 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2828 expected_comment_count = self._get_count(
2829 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2830
2d6659b9 2831 if expected_comment_count:
46383212 2832 tracker['est_total'] = expected_comment_count
2833 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2834 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2835
2836 sort_menu_item = try_get(
2837 comments_header_renderer,
2838 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2839 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2840
2841 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2842 if not _continuation:
2843 continue
2844
46383212 2845 sort_text = str_or_none(sort_menu_item.get('title'))
2846 if not sort_text:
2d6659b9 2847 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2848 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2849 break
a2160aa4 2850 return _continuation
a1c5d2ca 2851
2d6659b9 2852 def extract_thread(contents):
a1c5d2ca 2853 if not parent:
46383212 2854 tracker['current_page_thread'] = 0
a1c5d2ca 2855 for content in contents:
46383212 2856 if not parent and tracker['total_parent_comments'] >= max_parents:
2857 yield
a1c5d2ca 2858 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2859 comment_renderer = get_first(
2860 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2861 expected_type=dict, default={})
a1c5d2ca 2862
a1c5d2ca
M
2863 comment = self._extract_comment(comment_renderer, parent)
2864 if not comment:
2865 continue
46383212 2866
2867 tracker['running_total'] += 1
2868 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2869 yield comment
46383212 2870
a1c5d2ca
M
2871 # Attempt to get the replies
2872 comment_replies_renderer = try_get(
2873 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2874
2875 if comment_replies_renderer:
46383212 2876 tracker['current_page_thread'] += 1
a1c5d2ca 2877 comment_entries_iter = self._comment_entries(
99e9e001 2878 comment_replies_renderer, ytcfg, video_id,
46383212 2879 parent=comment.get('id'), tracker=tracker)
86e5f3ed 2880 yield from itertools.islice(comment_entries_iter, min(
2881 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 2882
46383212 2883 # Keeps track of counts across recursive calls
2884 if not tracker:
2885 tracker = dict(
2886 running_total=0,
2887 est_total=0,
2888 current_page_thread=0,
2889 total_parent_comments=0,
2890 total_reply_comments=0)
2891
2892 # TODO: Deprecated
2d6659b9 2893 # YouTube comments have a max depth of 2
46383212 2894 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2895 if max_depth:
2896 self._downloader.deprecation_warning(
2897 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2898 if max_depth == 1 and parent:
2899 return
a1c5d2ca 2900
46383212 2901 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2902 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2903
46383212 2904 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2905
46383212 2906 response = None
6e634cbe 2907 is_forced_continuation = False
2d6659b9 2908 is_first_continuation = parent is None
6e634cbe 2909 if is_first_continuation and not continuation:
2910 # Sometimes you can get comments by generating the continuation yourself,
2911 # even if YouTube initially reports them being disabled - e.g. stories comments.
2912 # Note: if the comment section is actually disabled, YouTube may return a response with
2913 # required check_get_keys missing. So we will disable that check initially in this case.
2914 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2915 is_forced_continuation = True
a1c5d2ca
M
2916
2917 for page_num in itertools.count(0):
2918 if not continuation:
2919 break
46383212 2920 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2921 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2922 if page_num == 0:
2923 if is_first_continuation:
2924 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2925 else:
2d6659b9 2926 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2927 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2928 else:
2929 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2930 ' ' if parent else '', ' replies' if parent else '',
2931 page_num, comment_prog_str)
2932
2933 response = self._extract_response(
fe93e2c4 2934 item_id=None, query=continuation,
2d6659b9 2935 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
6e634cbe 2936 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2937 is_forced_continuation = False
46383212 2938 continuation_contents = traverse_obj(
2939 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2940
2d6659b9 2941 continuation = None
46383212 2942 for continuation_section in continuation_contents:
2943 continuation_items = traverse_obj(
2944 continuation_section,
2945 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2946 get_all=False, expected_type=list) or []
2947 if is_first_continuation:
2948 continuation = extract_header(continuation_items)
2949 is_first_continuation = False
2d6659b9 2950 if continuation:
a1c5d2ca 2951 break
46383212 2952 continue
a1c5d2ca 2953
46383212 2954 for entry in extract_thread(continuation_items):
2955 if not entry:
2956 return
2957 yield entry
2958 continuation = self._extract_continuation({'contents': continuation_items})
2959 if continuation:
2d6659b9 2960 break
a1c5d2ca 2961
6e634cbe 2962 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2963 if message and not parent and tracker['running_total'] == 0:
2964 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
2965
2966 @staticmethod
2967 def _generate_comment_continuation(video_id):
2968 """
2969 Generates initial comment section continuation token from given video id
2970 """
2971 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
2972 return base64.b64encode(token.encode()).decode()
2973
a2160aa4 2974 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2975 """Entry for comment extraction"""
2d6659b9 2976 def _real_comment_extract(contents):
aae16f6e 2977 renderer = next((
2978 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2979 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2980 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2981
a2160aa4 2982 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2983 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2984
109dd3b2 2985 @staticmethod
99e9e001 2986 def _get_checkok_params():
2987 return {'contentCheckOk': True, 'racyCheckOk': True}
2988
2989 @classmethod
2990 def _generate_player_context(cls, sts=None):
109dd3b2 2991 context = {
2992 'html5Preference': 'HTML5_PREF_WANTS',
2993 }
2994 if sts is not None:
2995 context['signatureTimestamp'] = sts
2996 return {
2997 'playbackContext': {
2998 'contentPlaybackContext': context
a1a7907b 2999 },
99e9e001 3000 **cls._get_checkok_params()
109dd3b2 3001 }
3002
e7e94f2a
D
3003 @staticmethod
3004 def _is_agegated(player_response):
3005 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3006 return True
e7e94f2a
D
3007
3008 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3009 AGE_GATE_REASONS = (
3010 'confirm your age', 'age-restricted', 'inappropriate', # reason
3011 'age_verification_required', 'age_check_required', # status
3012 )
3013 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3014
3015 @staticmethod
3016 def _is_unplayable(player_response):
3017 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3018
99e9e001 3019 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 3020
11f9be09 3021 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3022 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3023 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3024 headers = self.generate_api_headers(
99e9e001 3025 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3026
6e634cbe 3027 yt_query = {
3028 'videoId': video_id,
3029 'params': '8AEB' # enable stories
3030 }
11f9be09 3031 yt_query.update(self._generate_player_context(sts))
3032 return self._extract_response(
3033 item_id=video_id, ep='player', query=yt_query,
379e44ed 3034 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3035 default_client=client,
11f9be09 3036 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3037 ) or None
3038
11f9be09 3039 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3040 requested_clients = []
d0d012d4 3041 default = ['android', 'web']
000c15a4 3042 allowed_clients = sorted(
86e5f3ed 3043 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3044 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3045 for client in self._configuration_arg('player_client'):
3046 if client in allowed_clients:
3047 requested_clients.append(client)
d0d012d4 3048 elif client == 'default':
3049 requested_clients.extend(default)
b4c055ba 3050 elif client == 'all':
3051 requested_clients.extend(allowed_clients)
3052 else:
3053 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3054 if not requested_clients:
d0d012d4 3055 requested_clients = default
cf7e015f 3056
11f9be09 3057 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3058 requested_clients.extend(
e7e94f2a 3059 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3060
11f9be09 3061 return orderedSet(requested_clients)
cf7e015f 3062
99e9e001 3063 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 3064 initial_pr = None
3065 if webpage:
b7c47b74 3066 initial_pr = self._search_json(
3067 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3068
ae729626 3069 all_clients = set(clients)
c0bc527b 3070 clients = clients[::-1]
b6de707d 3071 prs = []
e7e94f2a 3072
ae729626 3073 def append_client(*client_names):
e7870111 3074 """ Append the first client name that exists but not already used """
ae729626 3075 for client_name in client_names:
e7870111
D
3076 actual_client = _split_innertube_client(client_name)[0]
3077 if actual_client in INNERTUBE_CLIENTS:
3078 if actual_client not in all_clients:
ae729626 3079 clients.append(client_name)
e7870111
D
3080 all_clients.add(actual_client)
3081 return
e7e94f2a 3082
379e44ed 3083 # Android player_response does not have microFormats which are needed for
3084 # extraction of some data. So we return the initial_pr with formats
3085 # stripped out even if not requested by the user
3086 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3087 if initial_pr:
3088 pr = dict(initial_pr)
3089 pr['streamingData'] = None
b6de707d 3090 prs.append(pr)
379e44ed 3091
3092 last_error = None
b6de707d 3093 tried_iframe_fallback = False
3094 player_url = None
c0bc527b 3095 while clients:
e7870111 3096 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3097 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3098 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3099 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3100
b6de707d 3101 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3102 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3103 if 'js' in self._configuration_arg('player_skip'):
3104 require_js_player = False
3105 player_url = None
3106
3107 if not player_url and not tried_iframe_fallback and require_js_player:
3108 player_url = self._download_player_url(video_id)
3109 tried_iframe_fallback = True
3110
379e44ed 3111 try:
3112 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 3113 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 3114 except ExtractorError as e:
3115 if last_error:
3116 self.report_warning(last_error)
3117 last_error = e
3118 continue
3119
11f9be09 3120 if pr:
b6de707d 3121 prs.append(pr)
c0bc527b 3122
e7e94f2a 3123 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3124 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3125 append_client(f'{base_client}_creator')
e7e94f2a 3126 elif self._is_agegated(pr):
e7870111
D
3127 if variant == 'tv_embedded':
3128 append_client(f'{base_client}_embedded')
3129 elif not variant:
3130 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3131
379e44ed 3132 if last_error:
b6de707d 3133 if not len(prs):
379e44ed 3134 raise last_error
3135 self.report_warning(last_error)
b6de707d 3136 return prs, player_url
11f9be09 3137
a1b2d843 3138 def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3139 itags, stream_ids = {}, []
2a9c6dcd 3140 itag_qualities, res_qualities = {}, {}
d3fc8074 3141 q = qualities([
2a9c6dcd 3142 # Normally tiny is the smallest video-only formats. But
3143 # audio-only formats with unknown quality may get tagged as tiny
3144 'tiny',
3145 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3146 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3147 ])
11f9be09 3148 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3149
545cc85d 3150 for fmt in streaming_formats:
727029c5 3151 if fmt.get('targetDurationSec'):
545cc85d 3152 continue
321bf820 3153
cc2db878 3154 itag = str_or_none(fmt.get('itag'))
9297939e 3155 audio_track = fmt.get('audioTrack') or {}
3156 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3157 if stream_id in stream_ids:
3158 continue
3159
cc2db878 3160 quality = fmt.get('quality')
2a9c6dcd 3161 height = int_or_none(fmt.get('height'))
d3fc8074 3162 if quality == 'tiny' or not quality:
3163 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3164 # The 3gp format (17) in android client has a quality of "small",
3165 # but is actually worse than other formats
3166 if itag == '17':
3167 quality = 'tiny'
3168 if quality:
3169 if itag:
3170 itag_qualities[itag] = quality
3171 if height:
3172 res_qualities[height] = quality
cc2db878 3173 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3174 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3175 # number of fragment that would subsequently requested with (`&sq=N`)
3176 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3177 continue
3178
545cc85d 3179 fmt_url = fmt.get('url')
3180 if not fmt_url:
14f25df2 3181 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3182 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3183 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3184 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3185 continue
52023f12 3186 try:
3187 fmt_url += '&%s=%s' % (
3188 traverse_obj(sc, ('sp', -1)) or 'signature',
3189 self._decrypt_signature(encrypted_sig, video_id, player_url)
3190 )
3191 except ExtractorError as e:
3192 self.report_warning('Signature extraction failed: Some formats may be missing', only_once=True)
3193 self.write_debug(e, only_once=True)
201e9eaa 3194 continue
545cc85d 3195
404f611f 3196 query = parse_qs(fmt_url)
3197 throttled = False
b2916526 3198 if query.get('n'):
404f611f 3199 try:
3200 fmt_url = update_url_query(fmt_url, {
3201 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3202 except ExtractorError as e:
aa9369a2 3203 self.report_warning(
1d485a1a 3204 'nsig extraction failed: You may experience throttling for some formats\n'
52023f12 3205 f'n = {query["n"][0]} ; player = {player_url}', only_once=True)
3206 self.write_debug(e, only_once=True)
404f611f 3207 throttled = True
3208
545cc85d 3209 if itag:
a0bb6ce5 3210 itags[itag] = 'https'
9297939e 3211 stream_ids.append(stream_id)
3212
0ad92dfb 3213 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3214 language_preference = (
3215 10 if audio_track.get('audioIsDefault') and 10
3216 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3217 else -1)
0ad92dfb 3218 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3219 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3220 # Make sure to avoid false positives with small duration differences.
3221 # Eg: __2ABJjxzNo, ySuUZEjARPY
3222 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3223 if is_damaged:
0f06bcd7 3224 self.report_warning(
3225 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3226 dct = {
3227 'asr': int_or_none(fmt.get('audioSampleRate')),
3228 'filesize': int_or_none(fmt.get('contentLength')),
3229 'format_id': itag,
34921b43 3230 'format_note': join_nonempty(
26e8e044 3231 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3232 ' (default)' if language_preference > 0 else ''),
404f611f 3233 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
0ad92dfb 3234 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3235 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3236 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3237 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3238 'height': height,
dca3ff4a 3239 'quality': q(quality),
727029c5 3240 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3241 'tbr': tbr,
545cc85d 3242 'url': fmt_url,
2a9c6dcd 3243 'width': int_or_none(fmt.get('width')),
ab6df717 3244 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3245 'desc' if language_preference < -1 else ''),
3246 'language_preference': language_preference,
a405b38f 3247 # Strictly de-prioritize damaged and 3gp formats
3248 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3249 }
60bdb7bd 3250 mime_mobj = re.match(
3251 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3252 if mime_mobj:
3253 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3254 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3255 no_audio = dct.get('acodec') == 'none'
3256 no_video = dct.get('vcodec') == 'none'
3257 if no_audio:
3258 dct['vbr'] = tbr
3259 if no_video:
3260 dct['abr'] = tbr
3261 if no_audio or no_video:
545cc85d 3262 dct['downloader_options'] = {
3263 # Youtube throttles chunks >~10M
3264 'http_chunk_size': 10485760,
bf1317d2 3265 }
7c60c33e 3266 if dct.get('ext'):
3267 dct['container'] = dct['ext'] + '_dash'
11f9be09 3268 yield dct
545cc85d 3269
adbc4ec4 3270 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3271 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3272 if not self.get_param('youtube_include_hls_manifest', True):
3273 skip_manifests.append('hls')
0f06bcd7 3274 if not self.get_param('youtube_include_dash_manifest', True):
3275 skip_manifests.append('dash')
adbc4ec4
THD
3276 get_dash = 'dash' not in skip_manifests and (
3277 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3278 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3279
a0bb6ce5 3280 def process_manifest_format(f, proto, itag):
3281 if itag in itags:
3282 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3283 return False
3284 itag = f'{itag}-{proto}'
3285 if itag:
3286 f['format_id'] = itag
3287 itags[itag] = proto
3288
3289 f['quality'] = next((
3290 q(qdict[val])
e339d25a 3291 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3292 if val in qdict), -1)
3293 return True
2a9c6dcd 3294
11f9be09 3295 for sd in streaming_data:
5d3a0e79 3296 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3297 if hls_manifest_url:
2a9c6dcd 3298 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 3299 if process_manifest_format(f, 'hls', self._search_regex(
3300 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3301 yield f
545cc85d 3302
5d3a0e79 3303 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3304 if dash_manifest_url:
2a9c6dcd 3305 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 3306 if process_manifest_format(f, 'dash', f['format_id']):
3307 f['filesize'] = int_or_none(self._search_regex(
3308 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3309 if live_from_start:
3310 f['is_from_start'] = True
3311
a0bb6ce5 3312 yield f
11f9be09 3313
720c3099 3314 def _extract_storyboard(self, player_responses, duration):
3315 spec = get_first(
3316 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3317 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3318 if not base_url:
720c3099 3319 return
720c3099 3320 L = len(spec) - 1
3321 for i, args in enumerate(spec):
3322 args = args.split('#')
3323 counts = list(map(int_or_none, args[:5]))
3324 if len(args) != 8 or not all(counts):
3325 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3326 continue
3327 width, height, frame_count, cols, rows = counts
3328 N, sigh = args[6:]
3329
3330 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3331 fragment_count = frame_count / (cols * rows)
3332 fragment_duration = duration / fragment_count
3333 yield {
3334 'format_id': f'sb{i}',
3335 'format_note': 'storyboard',
3336 'ext': 'mhtml',
3337 'protocol': 'mhtml',
3338 'acodec': 'none',
3339 'vcodec': 'none',
3340 'url': url,
3341 'width': width,
3342 'height': height,
3343 'fragments': [{
b3edc806 3344 'url': url.replace('$M', str(j)),
720c3099 3345 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3346 } for j in range(math.ceil(fragment_count))],
3347 }
3348
adbc4ec4 3349 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3350 webpage = None
3351 if 'webpage' not in self._configuration_arg('player_skip'):
3352 webpage = self._download_webpage(
6e634cbe 3353 webpage_url + '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id, fatal=False)
11f9be09 3354
3355 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3356
b6de707d 3357 player_responses, player_url = self._extract_player_responses(
11f9be09 3358 self._get_requested_clients(url, smuggled_data),
99e9e001 3359 video_id, webpage, master_ytcfg)
11f9be09 3360
adbc4ec4
THD
3361 return webpage, master_ytcfg, player_responses, player_url
3362
a1b2d843 3363 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3364 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3365 is_live = get_first(video_details, 'isLive')
3366 if is_live is None:
3367 is_live = get_first(live_broadcast_details, 'isLiveNow')
3368
3369 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
a1b2d843 3370 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration))
adbc4ec4
THD
3371
3372 return live_broadcast_details, is_live, streaming_data, formats
3373
3374 def _real_extract(self, url):
3375 url, smuggled_data = unsmuggle_url(url, {})
3376 video_id = self._match_id(url)
3377
3378 base_url = self.http_scheme() + '//www.youtube.com/'
3379 webpage_url = base_url + 'watch?v=' + video_id
3380
3381 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3382
11f9be09 3383 playability_statuses = traverse_obj(
3384 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3385
3386 trailer_video_id = get_first(
3387 playability_statuses,
3388 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3389 expected_type=str)
3390 if trailer_video_id:
3391 return self.url_result(
3392 trailer_video_id, self.ie_key(), trailer_video_id)
3393
3394 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3395 if webpage else (lambda x: None))
3396
3397 video_details = traverse_obj(
3398 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3399 microformats = traverse_obj(
3400 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3401 expected_type=dict, default=[])
3402 video_title = (
3403 get_first(video_details, 'title')
3404 or self._get_text(microformats, (..., 'title'))
3405 or search_meta(['og:title', 'twitter:title', 'title']))
3406 video_description = get_first(video_details, 'shortDescription')
3407
d89257f3 3408 multifeed_metadata_list = get_first(
3409 player_responses,
3410 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3411 expected_type=str)
3412 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3413 if self.get_param('noplaylist'):
11f9be09 3414 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3415 else:
3416 entries = []
3417 feed_ids = []
3418 for feed in multifeed_metadata_list.split(','):
3419 # Unquote should take place before split on comma (,) since textual
3420 # fields may contain comma as well (see
3421 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3422 feed_data = urllib.parse.parse_qs(
ac668111 3423 urllib.parse.unquote_plus(feed))
d89257f3 3424
3425 def feed_entry(name):
3426 return try_get(
14f25df2 3427 feed_data, lambda x: x[name][0], str)
d89257f3 3428
3429 feed_id = feed_entry('id')
3430 if not feed_id:
3431 continue
3432 feed_title = feed_entry('title')
3433 title = video_title
3434 if feed_title:
3435 title += ' (%s)' % feed_title
3436 entries.append({
3437 '_type': 'url_transparent',
3438 'ie_key': 'Youtube',
3439 'url': smuggle_url(
3440 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3441 {'force_singlefeed': True}),
3442 'title': title,
3443 })
3444 feed_ids.append(feed_id)
3445 self.to_screen(
3446 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3447 % (', '.join(feed_ids), video_id))
3448 return self.playlist_result(
3449 entries, video_id, video_title, video_description)
11f9be09 3450
a1b2d843 3451 duration = int_or_none(
3452 get_first(video_details, 'lengthSeconds')
3453 or get_first(microformats, 'lengthSeconds')
3454 or parse_duration(search_meta('duration'))) or None
3455
829bbd1d 3456 if get_first(video_details, 'isPostLiveDvr'):
3457 self.write_debug('Video is in Post-Live Manifestless mode')
3458 if duration or 0 > 4 * 3600:
3459 self.report_warning(
3460 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3461 'This is a known issue and patches are welcome')
3462
a1b2d843 3463 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(
3464 video_id, microformats, video_details, player_responses, player_url, duration)
bf1317d2 3465
545cc85d 3466 if not formats:
11f9be09 3467 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3468 self.report_drm(video_id)
11f9be09 3469 pemr = get_first(
3470 playability_statuses,
3471 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3472 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3473 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3474 if subreason:
545cc85d 3475 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3476 countries = get_first(microformats, 'availableCountries')
545cc85d 3477 if not countries:
3478 regions_allowed = search_meta('regionsAllowed')
3479 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3480 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3481 reason += f'. {subreason}'
545cc85d 3482 if reason:
b7da73eb 3483 self.raise_no_formats(reason, expected=True)
bf1317d2 3484
11f9be09 3485 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3486 if not keywords and webpage:
3487 keywords = [
3488 unescapeHTML(m.group('content'))
3489 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3490 for keyword in keywords:
3491 if keyword.startswith('yt:stretch='):
201c1459 3492 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3493 if mobj:
3494 # NB: float is intentional for forcing float division
3495 w, h = (float(v) for v in mobj.groups())
3496 if w > 0 and h > 0:
3497 ratio = w / h
3498 for f in formats:
3499 if f.get('vcodec') != 'none':
3500 f['stretched_ratio'] = ratio
3501 break
a709d873 3502 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3503 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3504 if thumbnail_url:
3505 thumbnails.append({
3506 'url': thumbnail_url,
ff2751ac 3507 })
fccf5021 3508 original_thumbnails = thumbnails.copy()
3509
0ba692ac 3510 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3511 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3512 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3513 thumbnail_names = [
962ffcf8 3514 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 3515 # in resolution, these are not the custom thumbnail. So de-prioritize them
3516 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3517 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3518 ]
cca80fe6 3519 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3520 thumbnails.extend({
3521 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3522 video_id=video_id, name=name, ext=ext,
3523 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3524 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3525 for thumb in thumbnails:
cca80fe6 3526 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3527 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3528 self._remove_duplicate_formats(thumbnails)
fccf5021 3529 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3530
7ea65411 3531 category = get_first(microformats, 'category') or search_meta('genre')
3532 channel_id = str_or_none(
3533 get_first(video_details, 'channelId')
3534 or get_first(microformats, 'externalChannelId')
3535 or search_meta('channelId'))
7ea65411 3536 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3537
3538 live_content = get_first(video_details, 'isLiveContent')
3539 is_upcoming = get_first(video_details, 'isUpcoming')
3540 if is_live is None:
3541 if is_upcoming or live_content is False:
3542 is_live = False
3543 if is_upcoming is None and (live_content or is_live):
3544 is_upcoming = False
adbc4ec4
THD
3545 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3546 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3547 if not duration and live_end_time and live_start_time:
3548 duration = live_end_time - live_start_time
3549
3550 if is_live and self.get_param('live_from_start'):
3551 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3552
720c3099 3553 formats.extend(self._extract_storyboard(player_responses, duration))
3554
3555 # Source is given priority since formats that throttle are given lower source_preference
3556 # When throttling issue is fully fixed, remove this
3557 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3558
545cc85d 3559 info = {
3560 'id': video_id,
39ca3b5c 3561 'title': video_title,
545cc85d 3562 'formats': formats,
3563 'thumbnails': thumbnails,
fccf5021 3564 # The best thumbnail that we are sure exists. Prevents unnecessary
3565 # URL checking if user don't care about getting the best possible thumbnail
3566 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3567 'description': video_description,
11f9be09 3568 'uploader': get_first(video_details, 'author'),
545cc85d 3569 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3570 'uploader_url': owner_profile_url,
3571 'channel_id': channel_id,
a70635b8 3572 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3573 'duration': duration,
3574 'view_count': int_or_none(
11f9be09 3575 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3576 or search_meta('interactionCount')),
11f9be09 3577 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3578 'age_limit': 18 if (
11f9be09 3579 get_first(microformats, 'isFamilySafe') is False
545cc85d 3580 or search_meta('isFamilyFriendly') == 'false'
3581 or search_meta('og:restrictions:age') == '18+') else 0,
3582 'webpage_url': webpage_url,
3583 'categories': [category] if category else None,
3584 'tags': keywords,
11f9be09 3585 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3586 'is_live': is_live,
3587 'was_live': (False if is_live or is_upcoming or live_content is False
3588 else None if is_live is None or is_upcoming is None
3589 else live_content),
3590 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3591 'release_timestamp': live_start_time,
545cc85d 3592 }
b477fc13 3593
3944e7af 3594 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3595 if pctr:
ecdc9049 3596 def get_lang_code(track):
3597 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3598 or track.get('languageCode'))
3599
3600 # Converted into dicts to remove duplicates
3601 captions = {
3602 get_lang_code(sub): sub
3603 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3604 translation_languages = {
3605 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3606 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3607
774d79cc 3608 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3609 lang_subs = container.setdefault(lang_code, [])
545cc85d 3610 for fmt in self._SUBTITLE_FORMATS:
3611 query.update({
3612 'fmt': fmt,
3613 })
3614 lang_subs.append({
3615 'ext': fmt,
60f393e4 3616 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3617 'name': sub_name,
545cc85d 3618 })
7e72694b 3619
ecdc9049 3620 subtitles, automatic_captions = {}, {}
3621 for lang_code, caption_track in captions.items():
3622 base_url = caption_track.get('baseUrl')
1235d333 3623 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3624 if not base_url:
3625 continue
ecdc9049 3626 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3627 if caption_track.get('kind') != 'asr':
545cc85d 3628 if not lang_code:
3629 continue
3630 process_language(
ecdc9049 3631 subtitles, base_url, lang_code, lang_name, {})
3632 if not caption_track.get('isTranslatable'):
3633 continue
3944e7af 3634 for trans_code, trans_name in translation_languages.items():
3635 if not trans_code:
545cc85d 3636 continue
1235d333 3637 orig_trans_code = trans_code
ecdc9049 3638 if caption_track.get('kind') != 'asr':
18e49408 3639 if 'translated_subs' in self._configuration_arg('skip'):
3640 continue
ecdc9049 3641 trans_code += f'-{lang_code}'
a70635b8 3642 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 3643 # Add an "-orig" label to the original language so that it can be distinguished.
3644 # The subs are returned without "-orig" as well for compatibility
1235d333 3645 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3646 process_language(
d49669ac 3647 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3648 # Setting tlang=lang returns damaged subtitles.
d49669ac 3649 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3650 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
ecdc9049 3651 info['automatic_captions'] = automatic_captions
3652 info['subtitles'] = subtitles
7e72694b 3653
14f25df2 3654 parsed_url = urllib.parse.urlparse(url)
545cc85d 3655 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 3656 query = urllib.parse.parse_qs(component)
545cc85d 3657 for k, v in query.items():
3658 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3659 d_k += '_time'
3660 if d_k not in info and k in s_ks:
3661 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3662
3663 # Youtube Music Auto-generated description
822b9d9c 3664 if video_description:
1890fc63 3665 mobj = re.search(
3666 r'''(?xs)
3667 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3668 (?P<album>[^\n]+)
3669 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3670 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3671 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3672 .+\nAuto-generated\ by\ YouTube\.\s*$
3673 ''', video_description)
822b9d9c 3674 if mobj:
822b9d9c
RA
3675 release_year = mobj.group('release_year')
3676 release_date = mobj.group('release_date')
3677 if release_date:
3678 release_date = release_date.replace('-', '')
3679 if not release_year:
545cc85d 3680 release_year = release_date[:4]
3681 info.update({
3682 'album': mobj.group('album'.strip()),
3683 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3684 'track': mobj.group('track').strip(),
3685 'release_date': release_date,
cc2db878 3686 'release_year': int_or_none(release_year),
545cc85d 3687 })
7e72694b 3688
545cc85d 3689 initial_data = None
3690 if webpage:
56ba69e4 3691 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 3692 if not initial_data:
99e9e001 3693 query = {'videoId': video_id}
3694 query.update(self._get_checkok_params())
109dd3b2 3695 initial_data = self._extract_response(
3696 item_id=video_id, ep='next', fatal=False,
99e9e001 3697 ytcfg=master_ytcfg, query=query,
3698 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3699 note='Downloading initial data API JSON')
545cc85d 3700
0df111a3 3701 info['comment_count'] = traverse_obj(initial_data, (
3702 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3703 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3704 ), (
3705 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3706 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3707 ), expected_type=int_or_none, get_all=False)
3708
19a03940 3709 try: # This will error if there is no livechat
c60ee3a2 3710 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 3711 except (KeyError, IndexError, TypeError):
3712 pass
3713 else:
ecdc9049 3714 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 3715 # url is needed to set cookies
3716 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 3717 'video_id': video_id,
3718 'ext': 'json',
f6745c49 3719 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3720 }]
545cc85d 3721
3722 if initial_data:
7c365c21 3723 info['chapters'] = (
3724 self._extract_chapters_from_json(initial_data, duration)
3725 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 3726 or self._extract_chapters_from_description(video_description, duration)
7c365c21 3727 or None)
545cc85d 3728
17322130 3729 contents = traverse_obj(
3730 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3731 expected_type=list, default=[])
3732
3733 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3734 if vpir:
3735 stl = vpir.get('superTitleLink')
3736 if stl:
3737 stl = self._get_text(stl)
3738 if try_get(
3739 vpir,
3740 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3741 info['location'] = stl
3742 else:
affc4fef 3743 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 3744 if mobj:
545cc85d 3745 info.update({
17322130 3746 'series': mobj.group(1),
3747 'season_number': int(mobj.group(2)),
3748 'episode_number': int(mobj.group(3)),
545cc85d 3749 })
17322130 3750 for tlb in (try_get(
3751 vpir,
3752 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3753 list) or []):
3754 tbr = tlb.get('toggleButtonRenderer') or {}
3755 for getter, regex in [(
3756 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3757 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3758 lambda x: x['accessibility'],
3759 lambda x: x['accessibilityData']['accessibilityData'],
3760 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3761 label = (try_get(tbr, getter, dict) or {}).get('label')
3762 if label:
3763 mobj = re.match(regex, label)
3764 if mobj:
3765 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3766 break
17322130 3767 sbr_tooltip = try_get(
3768 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3769 if sbr_tooltip:
3770 like_count, dislike_count = sbr_tooltip.split(' / ')
3771 info.update({
3772 'like_count': str_to_int(like_count),
3773 'dislike_count': str_to_int(dislike_count),
3774 })
3775 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3776 if vsir:
3777 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3778 info.update({
3779 'channel': self._get_text(vor, 'title'),
3780 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3781
3782 rows = try_get(
3783 vsir,
3784 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3785 list) or []
3786 multiple_songs = False
3787 for row in rows:
3788 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3789 multiple_songs = True
3790 break
3791 for row in rows:
3792 mrr = row.get('metadataRowRenderer') or {}
3793 mrr_title = mrr.get('title')
3794 if not mrr_title:
3795 continue
3796 mrr_title = self._get_text(mrr, 'title')
3797 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3798 if mrr_title == 'License':
3799 info['license'] = mrr_contents_text
3800 elif not multiple_songs:
3801 if mrr_title == 'Album':
3802 info['album'] = mrr_contents_text
3803 elif mrr_title == 'Artist':
3804 info['artist'] = mrr_contents_text
3805 elif mrr_title == 'Song':
3806 info['track'] = mrr_contents_text
545cc85d 3807
3808 fallbacks = {
3809 'channel': 'uploader',
3810 'channel_id': 'uploader_id',
3811 'channel_url': 'uploader_url',
3812 }
992f9a73 3813
17322130 3814 # The upload date for scheduled, live and past live streams / premieres in microformats
3815 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3816 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3817 upload_date = (
3818 unified_strdate(get_first(microformats, 'uploadDate'))
3819 or unified_strdate(search_meta('uploadDate')))
3820 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
6e634cbe 3821 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date
17322130 3822 info['upload_date'] = upload_date
992f9a73 3823
545cc85d 3824 for to, frm in fallbacks.items():
3825 if not info.get(to):
3826 info[to] = info.get(frm)
3827
3828 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3829 v = info.get(s_k)
3830 if v:
3831 info[d_k] = v
b84071c0 3832
11f9be09 3833 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3834 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3835 is_membersonly = None
b28f8d24 3836 is_premium = None
c224251a
M
3837 if initial_data and is_private is not None:
3838 is_membersonly = False
b28f8d24 3839 is_premium = False
47193e02 3840 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3841 badge_labels = set()
3842 for content in contents:
3843 if not isinstance(content, dict):
3844 continue
3845 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3846 for badge_label in badge_labels:
3847 if badge_label.lower() == 'members only':
3848 is_membersonly = True
3849 elif badge_label.lower() == 'premium':
3850 is_premium = True
3851 elif badge_label.lower() == 'unlisted':
3852 is_unlisted = True
c224251a 3853
c224251a
M
3854 info['availability'] = self._availability(
3855 is_private=is_private,
b28f8d24 3856 needs_premium=is_premium,
c224251a
M
3857 needs_subscription=is_membersonly,
3858 needs_auth=info['age_limit'] >= 18,
3859 is_unlisted=None if is_private is None else is_unlisted)
3860
a2160aa4 3861 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3862
11f9be09 3863 self.mark_watched(video_id, player_responses)
d77ab8e2 3864
545cc85d 3865 return info
c5e8d7af 3866
a61fd4cf 3867
a6213a49 3868class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3869
182bda88 3870 @staticmethod
3871 def passthrough_smuggled_data(func):
3872 def _smuggle(entries, smuggled_data):
3873 for entry in entries:
3874 # TODO: Convert URL to music.youtube instead.
3875 # Do we need to passthrough any other smuggled_data?
3876 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3877 yield entry
3878
3879 @functools.wraps(func)
3880 def wrapper(self, url):
3881 url, smuggled_data = unsmuggle_url(url, {})
3882 if self.is_music_url(url):
3883 smuggled_data['is_music_url'] = True
3884 info_dict = func(self, url, smuggled_data)
3885 if smuggled_data and info_dict.get('entries'):
3886 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3887 return info_dict
3888 return wrapper
3889
a6213a49 3890 def _extract_channel_id(self, webpage):
3891 channel_id = self._html_search_meta(
3892 'channelId', webpage, 'channel id', default=None)
3893 if channel_id:
3894 return channel_id
3895 channel_url = self._html_search_meta(
3896 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3897 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3898 'twitter:app:url:googleplay'), webpage, 'channel url')
3899 return self._search_regex(
3900 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3901 channel_url, 'channel id')
15f6397c 3902
8bdd16b4 3903 @staticmethod
cd7c66cf 3904 def _extract_basic_item_renderer(item):
3905 # Modified from _extract_grid_item_renderer
201c1459 3906 known_basic_renderers = (
a17526e4 3907 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 3908 )
3909 for key, renderer in item.items():
201c1459 3910 if not isinstance(renderer, dict):
cd7c66cf 3911 continue
201c1459 3912 elif key in known_basic_renderers:
3913 return renderer
3914 elif key.startswith('grid') and key.endswith('Renderer'):
3915 return renderer
8bdd16b4 3916
8bdd16b4 3917 def _grid_entries(self, grid_renderer):
3918 for item in grid_renderer['items']:
3919 if not isinstance(item, dict):
39b62db1 3920 continue
cd7c66cf 3921 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3922 if not isinstance(renderer, dict):
3923 continue
052e1350 3924 title = self._get_text(renderer, 'title')
fe93e2c4 3925
8bdd16b4 3926 # playlist
3927 playlist_id = renderer.get('playlistId')
3928 if playlist_id:
3929 yield self.url_result(
3930 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3931 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3932 video_title=title)
201c1459 3933 continue
8bdd16b4 3934 # video
3935 video_id = renderer.get('videoId')
3936 if video_id:
3937 yield self._extract_video(renderer)
201c1459 3938 continue
8bdd16b4 3939 # channel
3940 channel_id = renderer.get('channelId')
3941 if channel_id:
8bdd16b4 3942 yield self.url_result(
3943 'https://www.youtube.com/channel/%s' % channel_id,
3944 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3945 continue
3946 # generic endpoint URL support
3947 ep_url = urljoin('https://www.youtube.com/', try_get(
3948 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 3949 str))
201c1459 3950 if ep_url:
3951 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3952 if ie.suitable(ep_url):
3953 yield self.url_result(
3954 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3955 break
8bdd16b4 3956
16aa9ea4 3957 def _music_reponsive_list_entry(self, renderer):
3958 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3959 if video_id:
3960 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3961 ie=YoutubeIE.ie_key(), video_id=video_id)
3962 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3963 if playlist_id:
3964 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3965 if video_id:
3966 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3967 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3968 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3969 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3970 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3971 if browse_id:
3972 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3973 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3974
3d3dddc9 3975 def _shelf_entries_from_content(self, shelf_renderer):
3976 content = shelf_renderer.get('content')
3977 if not isinstance(content, dict):
8bdd16b4 3978 return
cd7c66cf 3979 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3980 if renderer:
3981 # TODO: add support for nested playlists so each shelf is processed
3982 # as separate playlist
3983 # TODO: this includes only first N items
86e5f3ed 3984 yield from self._grid_entries(renderer)
3d3dddc9 3985 renderer = content.get('horizontalListRenderer')
3986 if renderer:
3987 # TODO
3988 pass
8bdd16b4 3989
29f7c58a 3990 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3991 ep = try_get(
3992 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 3993 str)
8bdd16b4 3994 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3995 if shelf_url:
29f7c58a 3996 # Skipping links to another channels, note that checking for
3997 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3998 # will not work
3999 if skip_channels and '/channels?' in shelf_url:
4000 return
052e1350 4001 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4002 yield self.url_result(shelf_url, video_title=title)
4003 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4004 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4005
8bdd16b4 4006 def _playlist_entries(self, video_list_renderer):
4007 for content in video_list_renderer['contents']:
4008 if not isinstance(content, dict):
4009 continue
4010 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4011 if not isinstance(renderer, dict):
4012 continue
4013 video_id = renderer.get('videoId')
4014 if not video_id:
4015 continue
4016 yield self._extract_video(renderer)
07aeced6 4017
3462ffa8 4018 def _rich_entries(self, rich_grid_renderer):
4019 renderer = try_get(
70d5c17b 4020 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 4021 video_id = renderer.get('videoId')
4022 if not video_id:
4023 return
4024 yield self._extract_video(renderer)
4025
8bdd16b4 4026 def _video_entry(self, video_renderer):
4027 video_id = video_renderer.get('videoId')
4028 if video_id:
4029 return self._extract_video(video_renderer)
dacb3a86 4030
ad210f4f 4031 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4032 url = urljoin('https://youtube.com', traverse_obj(
4033 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4034 if url:
4035 return self.url_result(
4036 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4037
8bdd16b4 4038 def _post_thread_entries(self, post_thread_renderer):
4039 post_renderer = try_get(
4040 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4041 if not post_renderer:
4042 return
4043 # video attachment
4044 video_renderer = try_get(
895b0931 4045 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4046 video_id = video_renderer.get('videoId')
4047 if video_id:
4048 entry = self._extract_video(video_renderer)
8bdd16b4 4049 if entry:
4050 yield entry
895b0931 4051 # playlist attachment
4052 playlist_id = try_get(
14f25df2 4053 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4054 if playlist_id:
4055 yield self.url_result(
e28f1c0a 4056 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4057 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4058 # inline video links
4059 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4060 for run in runs:
4061 if not isinstance(run, dict):
4062 continue
4063 ep_url = try_get(
14f25df2 4064 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4065 if not ep_url:
4066 continue
4067 if not YoutubeIE.suitable(ep_url):
4068 continue
4069 ep_video_id = YoutubeIE._match_id(ep_url)
4070 if video_id == ep_video_id:
4071 continue
895b0931 4072 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4073
8bdd16b4 4074 def _post_thread_continuation_entries(self, post_thread_continuation):
4075 contents = post_thread_continuation.get('contents')
4076 if not isinstance(contents, list):
4077 return
4078 for content in contents:
4079 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4080 if isinstance(renderer, dict):
4081 yield from self._post_thread_entries(renderer)
8bdd16b4 4082 continue
6b0b0a28 4083 renderer = content.get('videoRenderer')
4084 if isinstance(renderer, dict):
4085 yield self._video_entry(renderer)
07aeced6 4086
39ed931e 4087 r''' # unused
4088 def _rich_grid_entries(self, contents):
4089 for content in contents:
4090 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4091 if video_renderer:
4092 entry = self._video_entry(video_renderer)
4093 if entry:
4094 yield entry
4095 '''
52efa4b3 4096
a6213a49 4097 def _extract_entries(self, parent_renderer, continuation_list):
4098 # continuation_list is modified in-place with continuation_list = [continuation_token]
4099 continuation_list[:] = [None]
4100 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4101 for content in contents:
4102 if not isinstance(content, dict):
4103 continue
16aa9ea4 4104 is_renderer = traverse_obj(
4105 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4106 expected_type=dict)
a6213a49 4107 if not is_renderer:
4108 renderer = content.get('richItemRenderer')
4109 if renderer:
4110 for entry in self._rich_entries(renderer):
4111 yield entry
4112 continuation_list[0] = self._extract_continuation(parent_renderer)
4113 continue
4114 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4115 for isr_content in isr_contents:
4116 if not isinstance(isr_content, dict):
8bdd16b4 4117 continue
69184e41 4118
a6213a49 4119 known_renderers = {
4120 'playlistVideoListRenderer': self._playlist_entries,
4121 'gridRenderer': self._grid_entries,
a17526e4 4122 'reelShelfRenderer': self._grid_entries,
4123 'shelfRenderer': self._shelf_entries,
16aa9ea4 4124 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4125 'backstagePostThreadRenderer': self._post_thread_entries,
4126 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4127 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4128 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4129 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4130 }
4131 for key, renderer in isr_content.items():
4132 if key not in known_renderers:
4133 continue
4134 for entry in known_renderers[key](renderer):
4135 if entry:
4136 yield entry
4137 continuation_list[0] = self._extract_continuation(renderer)
4138 break
70d5c17b 4139
4140 if not continuation_list[0]:
a6213a49 4141 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4142
a6213a49 4143 if not continuation_list[0]:
4144 continuation_list[0] = self._extract_continuation(parent_renderer)
4145
4146 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4147 continuation_list = [None]
4148 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4149 tab_content = try_get(tab, lambda x: x['content'], dict)
4150 if not tab_content:
4151 return
3462ffa8 4152 parent_renderer = (
29f7c58a 4153 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4154 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4155 yield from extract_entries(parent_renderer)
3462ffa8 4156 continuation = continuation_list[0]
d069eca7 4157
8bdd16b4 4158 for page_num in itertools.count(1):
4159 if not continuation:
4160 break
99e9e001 4161 headers = self.generate_api_headers(
4162 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4163 response = self._extract_response(
86e5f3ed 4164 item_id=f'{item_id} page {page_num}',
fe93e2c4 4165 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4166 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4167
4168 if not response:
8bdd16b4 4169 break
ac56cf38 4170 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4171 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4172 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4173
69184e41 4174 known_continuation_renderers = {
4175 'playlistVideoListContinuation': self._playlist_entries,
4176 'gridContinuation': self._grid_entries,
4177 'itemSectionContinuation': self._post_thread_continuation_entries,
4178 'sectionListContinuation': extract_entries, # for feeds
4179 }
8bdd16b4 4180 continuation_contents = try_get(
69184e41 4181 response, lambda x: x['continuationContents'], dict) or {}
4182 continuation_renderer = None
4183 for key, value in continuation_contents.items():
4184 if key not in known_continuation_renderers:
3462ffa8 4185 continue
69184e41 4186 continuation_renderer = value
4187 continuation_list = [None]
86e5f3ed 4188 yield from known_continuation_renderers[key](continuation_renderer)
69184e41 4189 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4190 break
4191 if continuation_renderer:
4192 continue
c5e8d7af 4193
a1b535bd 4194 known_renderers = {
e4b98809 4195 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4196 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4197 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4198 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4199 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4200 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4201 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4202 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4203 }
cce889b9 4204 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4205 continuation_items = try_get(
cce889b9 4206 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4207 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4208 video_items_renderer = None
4209 for key, value in continuation_item.items():
4210 if key not in known_renderers:
8bdd16b4 4211 continue
a1b535bd 4212 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4213 continuation_list = [None]
86e5f3ed 4214 yield from known_renderers[key][0](video_items_renderer)
9ba5705a 4215 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4216 break
4217 if video_items_renderer:
4218 continue
8bdd16b4 4219 break
9558dcec 4220
8bdd16b4 4221 @staticmethod
7c219ea6 4222 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4223 for tab in tabs:
cd684175 4224 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4225 if renderer.get('selected') is True:
4226 return renderer
2b3c2546 4227 else:
7c219ea6 4228 if fatal:
4229 raise ExtractorError('Unable to find selected tab')
b82f815f 4230
61d3665d 4231 def _extract_uploader(self, data):
8bdd16b4 4232 uploader = {}
61d3665d 4233 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
47193e02 4234 owner = try_get(
4235 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4236 if owner:
61d3665d 4237 owner_text = owner.get('text')
4238 uploader['uploader'] = self._search_regex(
4239 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
47193e02 4240 uploader['uploader_id'] = try_get(
14f25df2 4241 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], str)
47193e02 4242 uploader['uploader_url'] = urljoin(
4243 'https://www.youtube.com/',
14f25df2 4244 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
9c3fe2ef 4245 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4246
ac56cf38 4247 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4248 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4249 tags = []
b60419c5 4250
8bdd16b4 4251 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4252 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4253 renderer = try_get(
4254 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4255 if renderer:
b60419c5 4256 channel_name = renderer.get('title')
4257 channel_url = renderer.get('channelUrl')
4258 channel_id = renderer.get('externalId')
39ed931e 4259 else:
64c0d954 4260 renderer = try_get(
4261 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4262
8bdd16b4 4263 if renderer:
4264 title = renderer.get('title')
ecc97af3 4265 description = renderer.get('description', '')
b60419c5 4266 playlist_id = channel_id
4267 tags = renderer.get('keywords', '').split()
b60419c5 4268
301d07fc 4269 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4270 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4271 def _get_uncropped(url):
4272 return url_or_none((url or '').split('=')[0] + '=s0')
4273
4274 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4275 if avatar_thumbnails:
4276 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4277 if uncropped_avatar:
4278 avatar_thumbnails.append({
4279 'url': uncropped_avatar,
4280 'id': 'avatar_uncropped',
4281 'preference': 1
4282 })
4283
4284 channel_banners = self._extract_thumbnails(
4285 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4286 for banner in channel_banners:
4287 banner['preference'] = -10
4288
4289 if channel_banners:
4290 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4291 if uncropped_banner:
4292 channel_banners.append({
4293 'url': uncropped_banner,
4294 'id': 'banner_uncropped',
4295 'preference': -5
4296 })
4297
4298 primary_thumbnails = self._extract_thumbnails(
a17526e4 4299 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4300
3462ffa8 4301 if playlist_id is None:
70d5c17b 4302 playlist_id = item_id
f0d785d3 4303
4304 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4305 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4306 if title is None:
f0d785d3 4307 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4308 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4309 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4310
b60419c5 4311 metadata = {
4312 'playlist_id': playlist_id,
4313 'playlist_title': title,
4314 'playlist_description': description,
4315 'uploader': channel_name,
4316 'uploader_id': channel_id,
4317 'uploader_url': channel_url,
301d07fc 4318 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4319 'tags': tags,
f0d785d3 4320 'view_count': self._get_count(playlist_stats, 1),
4321 'availability': self._extract_availability(data),
4322 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4323 'playlist_count': self._get_count(playlist_stats, 0),
4324 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4325 }
4326 if not channel_id:
4327 metadata.update(self._extract_uploader(data))
4328 metadata.update({
4329 'channel': metadata['uploader'],
4330 'channel_id': metadata['uploader_id'],
4331 'channel_url': metadata['uploader_url']})
4332 return self.playlist_result(
d069eca7 4333 self._entries(
ac56cf38 4334 selected_tab, playlist_id, ytcfg,
4335 self._extract_account_syncid(ytcfg, data),
4336 self._extract_visitor_data(data, ytcfg)),
b60419c5 4337 **metadata)
73c4ac2c 4338
6e634cbe 4339 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4340 first_id = last_id = response = None
2be71994 4341 for page_num in itertools.count(1):
cd7c66cf 4342 videos = list(self._playlist_entries(playlist))
4343 if not videos:
4344 return
2be71994 4345 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4346 if start >= len(videos):
4347 return
24146491 4348 yield from videos[start:]
2be71994 4349 first_id = first_id or videos[0]['id']
4350 last_id = videos[-1]['id']
79360d99 4351 watch_endpoint = try_get(
4352 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4353 headers = self.generate_api_headers(
4354 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4355 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4356 query = {
4357 'playlistId': playlist_id,
4358 'videoId': watch_endpoint.get('videoId') or last_id,
4359 'index': watch_endpoint.get('index') or len(videos),
4360 'params': watch_endpoint.get('params') or 'OAE%3D'
4361 }
4362 response = self._extract_response(
4363 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4364 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4365 check_get_keys='contents'
4366 )
cd7c66cf 4367 playlist = try_get(
79360d99 4368 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4369
ac56cf38 4370 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4371 title = playlist.get('title') or try_get(
14f25df2 4372 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4373 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4374
4375 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4376 playlist_url = urljoin(url, try_get(
4377 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4378 str))
6e634cbe 4379
4380 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4381 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4382 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4383
4384 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4385 return self.url_result(
4386 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4387 video_title=title)
cd7c66cf 4388
8bdd16b4 4389 return self.playlist_result(
6e634cbe 4390 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4391 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4392
47193e02 4393 def _extract_availability(self, data):
4394 """
4395 Gets the availability of a given playlist/tab.
4396 Note: Unless YouTube tells us explicitly, we do not assume it is public
4397 @param data: response
4398 """
4399 is_private = is_unlisted = None
4400 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4401 badge_labels = self._extract_badges(renderer)
4402
4403 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4404 privacy_dropdown_entries = try_get(
4405 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4406 for renderer_dict in privacy_dropdown_entries:
4407 is_selected = try_get(
4408 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4409 if not is_selected:
4410 continue
052e1350 4411 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4412 if label:
4413 badge_labels.add(label.lower())
4414 break
4415
4416 for badge_label in badge_labels:
4417 if badge_label == 'unlisted':
4418 is_unlisted = True
4419 elif badge_label == 'private':
4420 is_private = True
4421 elif badge_label == 'public':
4422 is_unlisted = is_private = False
4423 return self._availability(is_private, False, False, False, is_unlisted)
4424
4425 @staticmethod
4426 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4427 sidebar_renderer = try_get(
4428 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4429 for item in sidebar_renderer:
4430 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4431 if renderer:
4432 return renderer
4433
ac56cf38 4434 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4435 """
4436 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4437 """
5d342002 4438 browse_id = params = None
47193e02 4439 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4440 if not renderer:
4441 return
4442 menu_renderer = try_get(
4443 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4444 for menu_item in menu_renderer:
4445 if not isinstance(menu_item, dict):
358de58c 4446 continue
47193e02 4447 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4448 text = try_get(
14f25df2 4449 nav_item_renderer, lambda x: x['text']['simpleText'], str)
47193e02 4450 if not text or text.lower() != 'show unavailable videos':
4451 continue
4452 browse_endpoint = try_get(
4453 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4454 browse_id = browse_endpoint.get('browseId')
4455 params = browse_endpoint.get('params')
4456 break
5d342002 4457
11f9be09 4458 headers = self.generate_api_headers(
99e9e001 4459 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4460 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4461 query = {
4462 'params': params or 'wgYCCAA=',
4463 'browseId': browse_id or 'VL%s' % item_id
4464 }
4465 return self._extract_response(
4466 item_id=item_id, headers=headers, query=query,
fe93e2c4 4467 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4468 note='Downloading API JSON with unavailable videos')
358de58c 4469
2762dbb1 4470 @functools.cached_property
a25bca9f 4471 def skip_webpage(self):
4472 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4473
ac56cf38 4474 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4475 retries = self.get_param('extractor_retries', 3)
62bff2c1 4476 count = -1
ac56cf38 4477 webpage = data = last_error = None
14fdfea9 4478 while count < retries:
62bff2c1 4479 count += 1
14fdfea9 4480 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4481 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4482 if last_error:
c705177d 4483 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4484 try:
4485 webpage = self._download_webpage(
4486 url, item_id,
4487 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4488 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4489 except ExtractorError as e:
4490 if isinstance(e.cause, network_exceptions):
14f25df2 4491 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
ac56cf38 4492 last_error = error_to_compat_str(e.cause or e.msg)
4493 if count < retries:
4494 continue
4495 if fatal:
4496 raise
4497 self.report_warning(error_to_compat_str(e))
14fdfea9 4498 break
ac56cf38 4499 else:
4500 try:
4501 self._extract_and_report_alerts(data)
4502 except ExtractorError as e:
4503 if fatal:
4504 raise
4505 self.report_warning(error_to_compat_str(e))
4506 break
4507
7c219ea6 4508 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
ac56cf38 4509 break
4510
4511 last_error = 'Incomplete yt initial data received'
4512 if count >= retries:
4513 if fatal:
4514 raise ExtractorError(last_error)
4515 self.report_warning(last_error)
4516 break
4517
cd7c66cf 4518 return webpage, data
4519
a25bca9f 4520 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4521 """Use if failed to extract ytcfg (and data) from initial webpage"""
4522 if not ytcfg and self.is_authenticated:
4523 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4524 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4525 raise ExtractorError(
4526 f'{msg}. If you are not downloading private content, or '
4527 'your cookies are only for the first account and channel,'
4528 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4529 expected=True)
4530 self.report_warning(msg, only_once=True)
4531
ac56cf38 4532 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4533 data = None
a25bca9f 4534 if not self.skip_webpage:
ac56cf38 4535 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4536 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4537 # Reject webpage data if redirected to home page without explicitly requesting
4538 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4539 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4540 if (url != 'https://www.youtube.com/feed/recommended'
4541 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4542 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4543 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4544 if fatal:
4545 raise ExtractorError(msg, expected=True)
4546 self.report_warning(msg, only_once=True)
ac56cf38 4547 if not data:
a25bca9f 4548 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4549 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4550 return data, ytcfg
4551
4552 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4553 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4554 resolve_response = self._extract_response(
4555 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4556 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4557 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4558 for ep_key, ep in endpoints.items():
4559 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4560 if params:
4561 return self._extract_response(
4562 item_id=item_id, query=params, ep=ep, headers=headers,
4563 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4564 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4565 err_note = 'Failed to resolve url (does the playlist exist?)'
4566 if fatal:
4567 raise ExtractorError(err_note, expected=True)
4568 self.report_warning(err_note, item_id)
4569
a6213a49 4570 _SEARCH_PARAMS = None
4571
af5c1c55 4572 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4573 data = {'query': query}
4574 if params is NO_DEFAULT:
4575 params = self._SEARCH_PARAMS
4576 if params:
4577 data['params'] = params
16aa9ea4 4578
4579 content_keys = (
4580 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4581 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4582 # ytmusic search
4583 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4584 ('continuationContents', ),
4585 )
a25bca9f 4586 display_id = f'query "{query}"'
86e5f3ed 4587 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4588 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4589 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4590
a61fd4cf 4591 continuation_list = [None]
a25bca9f 4592 search = None
a6213a49 4593 for page_num in itertools.count(1):
a61fd4cf 4594 data.update(continuation_list[0] or {})
a25bca9f 4595 headers = self.generate_api_headers(
4596 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4597 search = self._extract_response(
a25bca9f 4598 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4599 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4600 slr_contents = traverse_obj(search, *content_keys)
4601 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4602 if not continuation_list[0]:
a6213a49 4603 break
4604
4605
4606class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4607 IE_DESC = 'YouTube Tabs'
4608 _VALID_URL = r'''(?x:
4609 https?://
4610 (?:\w+\.)?
4611 (?:
4612 youtube(?:kids)?\.com|
4613 %(invidious)s
4614 )/
4615 (?:
4616 (?P<channel_type>channel|c|user|browse)/|
4617 (?P<not_channel>
4618 feed/|hashtag/|
4619 (?:playlist|watch)\?.*?\blist=
4620 )|
4621 (?!(?:%(reserved_names)s)\b) # Direct URLs
4622 )
4623 (?P<id>[^/?\#&]+)
4624 )''' % {
4625 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4626 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4627 }
4628 IE_NAME = 'youtube:tab'
4629
4630 _TESTS = [{
4631 'note': 'playlists, multipage',
4632 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4633 'playlist_mincount': 94,
4634 'info_dict': {
4635 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4636 'title': 'Igor Kleiner - Playlists',
a6213a49 4637 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4638 'uploader': 'Igor Kleiner',
a6213a49 4639 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4640 'channel': 'Igor Kleiner',
4641 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4642 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4643 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4644 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4645 'channel_follower_count': int
a6213a49 4646 },
4647 }, {
4648 'note': 'playlists, multipage, different order',
4649 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4650 'playlist_mincount': 94,
4651 'info_dict': {
4652 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4653 'title': 'Igor Kleiner - Playlists',
a6213a49 4654 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4655 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4656 'uploader': 'Igor Kleiner',
4657 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4658 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4659 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4660 'channel': 'Igor Kleiner',
4661 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4662 'channel_follower_count': int
a6213a49 4663 },
4664 }, {
4665 'note': 'playlists, series',
4666 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4667 'playlist_mincount': 5,
4668 'info_dict': {
4669 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4670 'title': '3Blue1Brown - Playlists',
4671 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4672 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4673 'uploader': '3Blue1Brown',
976ae3ea 4674 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4675 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4676 'channel': '3Blue1Brown',
4677 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4678 'tags': ['Mathematics'],
6c73052c 4679 'channel_follower_count': int
a6213a49 4680 },
4681 }, {
4682 'note': 'playlists, singlepage',
4683 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4684 'playlist_mincount': 4,
4685 'info_dict': {
4686 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4687 'title': 'ThirstForScience - Playlists',
4688 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4689 'uploader': 'ThirstForScience',
4690 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4691 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4692 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4693 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4694 'tags': 'count:13',
4695 'channel': 'ThirstForScience',
6c73052c 4696 'channel_follower_count': int
a6213a49 4697 }
4698 }, {
4699 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4700 'only_matching': True,
4701 }, {
4702 'note': 'basic, single video playlist',
4703 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4704 'info_dict': {
4705 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4706 'uploader': 'Sergey M.',
4707 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4708 'title': 'youtube-dl public playlist',
976ae3ea 4709 'description': '',
4710 'tags': [],
4711 'view_count': int,
4712 'modified_date': '20201130',
4713 'channel': 'Sergey M.',
4714 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4715 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4716 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4717 },
4718 'playlist_count': 1,
4719 }, {
4720 'note': 'empty playlist',
4721 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4722 'info_dict': {
4723 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4724 'uploader': 'Sergey M.',
4725 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4726 'title': 'youtube-dl empty playlist',
976ae3ea 4727 'tags': [],
4728 'channel': 'Sergey M.',
4729 'description': '',
4730 'modified_date': '20160902',
4731 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4732 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4733 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4734 },
4735 'playlist_count': 0,
4736 }, {
4737 'note': 'Home tab',
4738 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4739 'info_dict': {
4740 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4741 'title': 'lex will - Home',
4742 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4743 'uploader': 'lex will',
4744 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4745 'channel': 'lex will',
4746 'tags': ['bible', 'history', 'prophesy'],
4747 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4748 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4749 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4750 'channel_follower_count': int
a6213a49 4751 },
4752 'playlist_mincount': 2,
4753 }, {
4754 'note': 'Videos tab',
4755 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4756 'info_dict': {
4757 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4758 'title': 'lex will - Videos',
4759 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4760 'uploader': 'lex will',
4761 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4762 'tags': ['bible', 'history', 'prophesy'],
4763 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4764 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4765 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4766 'channel': 'lex will',
6c73052c 4767 'channel_follower_count': int
a6213a49 4768 },
4769 'playlist_mincount': 975,
4770 }, {
4771 'note': 'Videos tab, sorted by popular',
4772 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4773 'info_dict': {
4774 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4775 'title': 'lex will - Videos',
4776 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4777 'uploader': 'lex will',
4778 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4779 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4780 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4781 'channel': 'lex will',
4782 'tags': ['bible', 'history', 'prophesy'],
4783 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4784 'channel_follower_count': int
a6213a49 4785 },
4786 'playlist_mincount': 199,
4787 }, {
4788 'note': 'Playlists tab',
4789 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4790 'info_dict': {
4791 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4792 'title': 'lex will - Playlists',
4793 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4794 'uploader': 'lex will',
4795 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4796 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4797 'channel': 'lex will',
4798 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4799 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4800 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4801 'channel_follower_count': int
a6213a49 4802 },
4803 'playlist_mincount': 17,
4804 }, {
4805 'note': 'Community tab',
4806 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4807 'info_dict': {
4808 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4809 'title': 'lex will - Community',
4810 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4811 'uploader': 'lex will',
4812 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4813 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4814 'channel': 'lex will',
4815 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4816 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4817 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4818 'channel_follower_count': int
a6213a49 4819 },
4820 'playlist_mincount': 18,
4821 }, {
4822 'note': 'Channels tab',
4823 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4824 'info_dict': {
4825 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4826 'title': 'lex will - Channels',
4827 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4828 'uploader': 'lex will',
4829 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4830 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4831 'channel': 'lex will',
4832 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4833 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4834 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4835 'channel_follower_count': int
a6213a49 4836 },
4837 'playlist_mincount': 12,
4838 }, {
4839 'note': 'Search tab',
4840 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4841 'playlist_mincount': 40,
4842 'info_dict': {
4843 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4844 'title': '3Blue1Brown - Search - linear algebra',
4845 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4846 'uploader': '3Blue1Brown',
4847 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4848 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4849 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4850 'tags': ['Mathematics'],
4851 'channel': '3Blue1Brown',
4852 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4853 'channel_follower_count': int
a6213a49 4854 },
4855 }, {
4856 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4857 'only_matching': True,
4858 }, {
4859 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4860 'only_matching': True,
4861 }, {
4862 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4863 'only_matching': True,
4864 }, {
4865 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4866 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4867 'info_dict': {
4868 'title': '29C3: Not my department',
4869 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4870 'uploader': 'Christiaan008',
4871 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4872 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4873 'tags': [],
4874 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4875 'view_count': int,
4876 'modified_date': '20150605',
4877 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4878 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4879 'channel': 'Christiaan008',
a6213a49 4880 },
4881 'playlist_count': 96,
4882 }, {
4883 'note': 'Large playlist',
4884 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4885 'info_dict': {
4886 'title': 'Uploads from Cauchemar',
4887 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4888 'uploader': 'Cauchemar',
4889 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4890 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4891 'tags': [],
4892 'modified_date': r're:\d{8}',
4893 'channel': 'Cauchemar',
4894 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4895 'view_count': int,
4896 'description': '',
4897 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4898 },
4899 'playlist_mincount': 1123,
976ae3ea 4900 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4901 }, {
4902 'note': 'even larger playlist, 8832 videos',
4903 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4904 'only_matching': True,
4905 }, {
4906 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4907 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4908 'info_dict': {
4909 'title': 'Uploads from Interstellar Movie',
4910 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4911 'uploader': 'Interstellar Movie',
4912 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4913 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4914 'tags': [],
4915 'view_count': int,
4916 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4917 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4918 'channel': 'Interstellar Movie',
4919 'description': '',
4920 'modified_date': r're:\d{8}',
a6213a49 4921 },
4922 'playlist_mincount': 21,
4923 }, {
4924 'note': 'Playlist with "show unavailable videos" button',
4925 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4926 'info_dict': {
4927 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4928 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4929 'uploader': 'Phim Siêu Nhân Nhật Bản',
4930 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4931 'view_count': int,
4932 'channel': 'Phim Siêu Nhân Nhật Bản',
4933 'tags': [],
4934 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4935 'description': '',
4936 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4937 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4938 'modified_date': r're:\d{8}',
a6213a49 4939 },
4940 'playlist_mincount': 200,
976ae3ea 4941 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4942 }, {
4943 'note': 'Playlist with unavailable videos in page 7',
4944 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4945 'info_dict': {
4946 'title': 'Uploads from BlankTV',
4947 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4948 'uploader': 'BlankTV',
4949 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4950 'channel': 'BlankTV',
4951 'channel_url': 'https://www.youtube.com/c/blanktv',
4952 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4953 'view_count': int,
4954 'tags': [],
4955 'uploader_url': 'https://www.youtube.com/c/blanktv',
4956 'modified_date': r're:\d{8}',
4957 'description': '',
a6213a49 4958 },
4959 'playlist_mincount': 1000,
976ae3ea 4960 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4961 }, {
4962 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4963 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4964 'info_dict': {
4965 'title': 'Data Analysis with Dr Mike Pound',
4966 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4967 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4968 'uploader': 'Computerphile',
4969 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4970 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4971 'tags': [],
4972 'view_count': int,
4973 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4974 'channel_url': 'https://www.youtube.com/user/Computerphile',
4975 'channel': 'Computerphile',
a6213a49 4976 },
4977 'playlist_mincount': 11,
4978 }, {
4979 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4980 'only_matching': True,
4981 }, {
4982 'note': 'Playlist URL that does not actually serve a playlist',
4983 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4984 'info_dict': {
4985 'id': 'FqZTN594JQw',
4986 'ext': 'webm',
4987 'title': "Smiley's People 01 detective, Adventure Series, Action",
4988 'uploader': 'STREEM',
4989 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4990 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4991 'upload_date': '20150526',
4992 'license': 'Standard YouTube License',
4993 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4994 'categories': ['People & Blogs'],
4995 'tags': list,
4996 'view_count': int,
4997 'like_count': int,
a6213a49 4998 },
4999 'params': {
5000 'skip_download': True,
5001 },
5002 'skip': 'This video is not available.',
5003 'add_ie': [YoutubeIE.ie_key()],
5004 }, {
5005 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5006 'only_matching': True,
5007 }, {
5008 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5009 'only_matching': True,
5010 }, {
5011 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5012 'info_dict': {
12a1b225 5013 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5014 'ext': 'mp4',
976ae3ea 5015 'title': str,
a6213a49 5016 'uploader': 'Sky News',
5017 'uploader_id': 'skynews',
5018 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5019 'upload_date': r're:\d{8}',
976ae3ea 5020 'description': str,
a6213a49 5021 'categories': ['News & Politics'],
5022 'tags': list,
5023 'like_count': int,
6c73052c 5024 'release_timestamp': 1642502819,
976ae3ea 5025 'channel': 'Sky News',
5026 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5027 'age_limit': 0,
5028 'view_count': int,
6c73052c 5029 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 5030 'playable_in_embed': True,
6c73052c 5031 'release_date': '20220118',
976ae3ea 5032 'availability': 'public',
5033 'live_status': 'is_live',
5034 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 5035 'channel_follower_count': int
a6213a49 5036 },
5037 'params': {
5038 'skip_download': True,
5039 },
976ae3ea 5040 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5041 }, {
5042 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5043 'info_dict': {
5044 'id': 'a48o2S1cPoo',
5045 'ext': 'mp4',
5046 'title': 'The Young Turks - Live Main Show',
5047 'uploader': 'The Young Turks',
5048 'uploader_id': 'TheYoungTurks',
5049 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5050 'upload_date': '20150715',
5051 'license': 'Standard YouTube License',
5052 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5053 'categories': ['News & Politics'],
5054 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5055 'like_count': int,
a6213a49 5056 },
5057 'params': {
5058 'skip_download': True,
5059 },
5060 'only_matching': True,
5061 }, {
5062 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5063 'only_matching': True,
5064 }, {
5065 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5066 'only_matching': True,
5067 }, {
5068 'note': 'A channel that is not live. Should raise error',
5069 'url': 'https://www.youtube.com/user/numberphile/live',
5070 'only_matching': True,
5071 }, {
5072 'url': 'https://www.youtube.com/feed/trending',
5073 'only_matching': True,
5074 }, {
5075 'url': 'https://www.youtube.com/feed/library',
5076 'only_matching': True,
5077 }, {
5078 'url': 'https://www.youtube.com/feed/history',
5079 'only_matching': True,
5080 }, {
5081 'url': 'https://www.youtube.com/feed/subscriptions',
5082 'only_matching': True,
5083 }, {
5084 'url': 'https://www.youtube.com/feed/watch_later',
5085 'only_matching': True,
5086 }, {
5087 'note': 'Recommended - redirects to home page.',
5088 'url': 'https://www.youtube.com/feed/recommended',
5089 'only_matching': True,
5090 }, {
5091 'note': 'inline playlist with not always working continuations',
5092 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5093 'only_matching': True,
5094 }, {
5095 'url': 'https://www.youtube.com/course',
5096 'only_matching': True,
5097 }, {
5098 'url': 'https://www.youtube.com/zsecurity',
5099 'only_matching': True,
5100 }, {
5101 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5102 'only_matching': True,
5103 }, {
5104 'url': 'https://www.youtube.com/TheYoungTurks/live',
5105 'only_matching': True,
5106 }, {
5107 'url': 'https://www.youtube.com/hashtag/cctv9',
5108 'info_dict': {
5109 'id': 'cctv9',
5110 'title': '#cctv9',
976ae3ea 5111 'tags': [],
a6213a49 5112 },
5113 'playlist_mincount': 350,
5114 }, {
5115 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5116 'only_matching': True,
5117 }, {
5118 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5119 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5120 'only_matching': True
5121 }, {
5122 'note': '/browse/ should redirect to /channel/',
5123 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5124 'only_matching': True
5125 }, {
5126 'note': 'VLPL, should redirect to playlist?list=PL...',
5127 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5128 'info_dict': {
5129 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5130 'uploader': 'NoCopyrightSounds',
5131 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5132 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5133 'title': 'NCS : All Releases 💿',
976ae3ea 5134 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5135 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5136 'modified_date': r're:\d{8}',
5137 'view_count': int,
5138 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5139 'tags': [],
5140 'channel': 'NoCopyrightSounds',
a6213a49 5141 },
5142 'playlist_mincount': 166,
976ae3ea 5143 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5144 }, {
5145 'note': 'Topic, should redirect to playlist?list=UU...',
5146 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5147 'info_dict': {
5148 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5149 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5150 'title': 'Uploads from Royalty Free Music - Topic',
5151 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5152 'tags': [],
5153 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5154 'channel': 'Royalty Free Music - Topic',
5155 'view_count': int,
5156 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5157 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5158 'modified_date': r're:\d{8}',
5159 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5160 'description': '',
a6213a49 5161 },
5162 'expected_warnings': [
a6213a49 5163 'The URL does not have a videos tab',
976ae3ea 5164 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5165 ],
5166 'playlist_mincount': 101,
5167 }, {
5168 'note': 'Topic without a UU playlist',
5169 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5170 'info_dict': {
5171 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5172 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5173 'tags': [],
a6213a49 5174 },
5175 'expected_warnings': [
976ae3ea 5176 'the playlist redirect gave error',
a6213a49 5177 ],
5178 'playlist_mincount': 9,
5179 }, {
5180 'note': 'Youtube music Album',
5181 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5182 'info_dict': {
5183 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5184 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5185 'tags': [],
5186 'view_count': int,
5187 'description': '',
5188 'availability': 'unlisted',
5189 'modified_date': r're:\d{8}',
a6213a49 5190 },
5191 'playlist_count': 50,
5192 }, {
5193 'note': 'unlisted single video playlist',
5194 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5195 'info_dict': {
5196 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5197 'uploader': 'colethedj',
5198 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5199 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5200 'availability': 'unlisted',
5201 'tags': [],
12a1b225 5202 'modified_date': '20220418',
976ae3ea 5203 'channel': 'colethedj',
5204 'view_count': int,
5205 'description': '',
5206 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5207 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5208 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5209 },
5210 'playlist_count': 1,
5211 }, {
5212 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5213 'url': 'https://www.youtube.com/feed/recommended',
5214 'info_dict': {
5215 'id': 'recommended',
5216 'title': 'recommended',
6c73052c 5217 'tags': [],
a6213a49 5218 },
5219 'playlist_mincount': 50,
5220 'params': {
5221 'skip_download': True,
5222 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5223 },
5224 }, {
5225 'note': 'API Fallback: /videos tab, sorted by oldest first',
5226 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5227 'info_dict': {
5228 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5229 'title': 'Cody\'sLab - Videos',
5230 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5231 'uploader': 'Cody\'sLab',
5232 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5233 'channel': 'Cody\'sLab',
5234 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5235 'tags': [],
5236 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5237 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5238 'channel_follower_count': int
a6213a49 5239 },
5240 'playlist_mincount': 650,
5241 'params': {
5242 'skip_download': True,
5243 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5244 },
5245 }, {
5246 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5247 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5248 'info_dict': {
5249 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5250 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5251 'title': 'Uploads from Royalty Free Music - Topic',
5252 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5253 'modified_date': r're:\d{8}',
5254 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5255 'description': '',
5256 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5257 'tags': [],
5258 'channel': 'Royalty Free Music - Topic',
5259 'view_count': int,
5260 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5261 },
5262 'expected_warnings': [
976ae3ea 5263 'does not have a videos tab',
5264 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5265 ],
5266 'playlist_mincount': 101,
5267 'params': {
5268 'skip_download': True,
5269 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5270 },
7c219ea6 5271 }, {
5272 'note': 'non-standard redirect to regional channel',
5273 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5274 'only_matching': True
61d3665d 5275 }, {
5276 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5277 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5278 'info_dict': {
5279 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5280 'modified_date': '20220407',
5281 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5282 'tags': [],
5283 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5284 'uploader': 'pukkandan',
5285 'availability': 'unlisted',
5286 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5287 'channel': 'pukkandan',
5288 'description': 'Test for collaborative playlist',
5289 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5290 'view_count': int,
61d3665d 5291 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5292 },
5293 'playlist_mincount': 2
a6213a49 5294 }]
5295
5296 @classmethod
5297 def suitable(cls, url):
86e5f3ed 5298 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5299
64f36541 5300 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5301
182bda88 5302 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5303 def _real_extract(self, url, smuggled_data):
cd7c66cf 5304 item_id = self._match_id(url)
14f25df2 5305 url = urllib.parse.urlunparse(
5306 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5307 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5308
fe03a6cd 5309 def get_mobj(url):
37e57a9f 5310 mobj = self._URL_RE.match(url).groupdict()
07cce701 5311 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5312 return mobj
5313
37e57a9f 5314 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5315 # Youtube returns incomplete data if tabname is not lower case
5316 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5317 if is_channel:
5318 if smuggled_data.get('is_music_url'):
37e57a9f 5319 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5320 item_id = item_id[2:]
37e57a9f 5321 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5322 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5323 mdata = self._extract_tab_endpoint(
37e57a9f 5324 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5325 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
14f25df2 5326 get_all=False, expected_type=str)
ac56cf38 5327 if not murl:
37e57a9f 5328 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5329 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5330 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5331 pre = f'https://www.youtube.com/channel/{item_id}'
5332
64f36541 5333 original_tab_name = tab
fe03a6cd 5334 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5335 # Home URLs should redirect to /videos/
37e57a9f 5336 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5337 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5338 tab = '/videos'
5339
5340 url = ''.join((pre, tab, post))
5341 mobj = get_mobj(url)
cd7c66cf 5342
5343 # Handle both video/playlist URLs
201c1459 5344 qs = parse_qs(url)
86e5f3ed 5345 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5346
fe03a6cd 5347 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5348 if not playlist_id:
fe03a6cd 5349 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5350 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5351 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5352 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5353 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5354 mobj = get_mobj(url)
cd7c66cf 5355
5356 if video_id and playlist_id:
a06916d9 5357 if self.get_param('noplaylist'):
37e57a9f 5358 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5359 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5360 ie=YoutubeIE.ie_key(), video_id=video_id)
5361 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5362
ac56cf38 5363 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5364
7c219ea6 5365 # YouTube may provide a non-standard redirect to the regional channel
5366 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5367 redirect_url = traverse_obj(
5368 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5369 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5370 redirect_url = ''.join((
5371 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5372 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5373 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5374
37e57a9f 5375 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5376 if tabs:
5377 selected_tab = self._extract_selected_tab(tabs)
64f36541 5378 selected_tab_name = selected_tab.get('title', '').lower()
5379 if selected_tab_name == 'home':
5380 selected_tab_name = 'featured'
5381 requested_tab_name = mobj['tab'][1:]
09f1580e 5382 if 'no-youtube-channel-redirect' not in compat_opts:
64f36541 5383 if requested_tab_name == 'live':
09f1580e 5384 # Live tab should have redirected to the video
5385 raise ExtractorError('The channel is not currently live', expected=True)
64f36541 5386 if requested_tab_name not in ('', selected_tab_name):
5387 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5388 if not original_tab_name:
5389 if item_id[:2] == 'UC':
5390 # Topic channels don't have /videos. Use the equivalent playlist instead
5391 pl_id = f'UU{item_id[2:]}'
5392 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5393 try:
5394 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5395 except ExtractorError:
5396 redirect_warning += ' and the playlist redirect gave error'
5397 else:
5398 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5399 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5400 if selected_tab_name and selected_tab_name != requested_tab_name:
5401 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5402 else:
5403 raise ExtractorError(redirect_warning, expected=True)
18db7548 5404
37e57a9f 5405 if redirect_warning:
64f36541 5406 self.to_screen(redirect_warning)
37e57a9f 5407 self.write_debug(f'Final URL: {url}')
18db7548 5408
358de58c 5409 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5410 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5411 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5412 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5413 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5414 if tabs:
ac56cf38 5415 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5416
37e57a9f 5417 playlist = traverse_obj(
5418 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5419 if playlist:
ac56cf38 5420 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5421
37e57a9f 5422 video_id = traverse_obj(
5423 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5424 if video_id:
09f1580e 5425 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5426 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5427 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5428 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5429
8bdd16b4 5430 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5431
c5e8d7af 5432
8bdd16b4 5433class YoutubePlaylistIE(InfoExtractor):
96565c7e 5434 IE_DESC = 'YouTube playlists'
8bdd16b4 5435 _VALID_URL = r'''(?x)(?:
5436 (?:https?://)?
5437 (?:\w+\.)?
5438 (?:
5439 (?:
5440 youtube(?:kids)?\.com|
d9190e44 5441 %(invidious)s
8bdd16b4 5442 )
5443 /.*?\?.*?\blist=
5444 )?
5445 (?P<id>%(playlist_id)s)
d9190e44
RH
5446 )''' % {
5447 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5448 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5449 }
8bdd16b4 5450 IE_NAME = 'youtube:playlist'
cdc628a4 5451 _TESTS = [{
8bdd16b4 5452 'note': 'issue #673',
5453 'url': 'PLBB231211A4F62143',
cdc628a4 5454 'info_dict': {
8bdd16b4 5455 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5456 'id': 'PLBB231211A4F62143',
976ae3ea 5457 'uploader': 'Wickman',
8bdd16b4 5458 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5459 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5460 'view_count': int,
5461 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5462 'modified_date': r're:\d{8}',
5463 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5464 'channel': 'Wickman',
5465 'tags': [],
5466 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5467 },
5468 'playlist_mincount': 29,
5469 }, {
5470 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5471 'info_dict': {
5472 'title': 'YDL_safe_search',
5473 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5474 },
5475 'playlist_count': 2,
5476 'skip': 'This playlist is private',
9558dcec 5477 }, {
8bdd16b4 5478 'note': 'embedded',
5479 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5480 'playlist_count': 4,
9558dcec 5481 'info_dict': {
8bdd16b4 5482 'title': 'JODA15',
5483 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5484 'uploader': 'milan',
5485 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5486 'description': '',
5487 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5488 'tags': [],
5489 'modified_date': '20140919',
5490 'view_count': int,
5491 'channel': 'milan',
5492 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5493 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5494 },
5495 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5496 }, {
8bdd16b4 5497 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 5498 'playlist_mincount': 455,
8bdd16b4 5499 'info_dict': {
5500 'title': '2018 Chinese New Singles (11/6 updated)',
5501 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5502 'uploader': 'LBK',
5503 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5504 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5505 'channel': 'LBK',
5506 'view_count': int,
5507 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5508 'tags': [],
5509 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5510 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5511 'modified_date': r're:\d{8}',
5512 },
5513 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5514 }, {
29f7c58a 5515 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5516 'only_matching': True,
5517 }, {
5518 # music album playlist
5519 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5520 'only_matching': True,
5521 }]
5522
5523 @classmethod
5524 def suitable(cls, url):
201c1459 5525 if YoutubeTabIE.suitable(url):
5526 return False
49a57e70 5527 from ..utils import parse_qs
201c1459 5528 qs = parse_qs(url)
5529 if qs.get('v', [None])[0]:
5530 return False
86e5f3ed 5531 return super().suitable(url)
29f7c58a 5532
5533 def _real_extract(self, url):
5534 playlist_id = self._match_id(url)
46953e7e 5535 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5536 url = update_url_query(
5537 'https://www.youtube.com/playlist',
5538 parse_qs(url) or {'list': playlist_id})
5539 if is_music_url:
5540 url = smuggle_url(url, {'is_music_url': True})
5541 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5542
5543
5544class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5545 IE_DESC = 'youtu.be'
29f7c58a 5546 _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}
5547 _TESTS = [{
8bdd16b4 5548 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5549 'info_dict': {
5550 'id': 'yeWKywCrFtk',
5551 'ext': 'mp4',
5552 'title': 'Small Scale Baler and Braiding Rugs',
5553 'uploader': 'Backus-Page House Museum',
5554 'uploader_id': 'backuspagemuseum',
5555 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5556 'upload_date': '20161008',
5557 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5558 'categories': ['Nonprofits & Activism'],
5559 'tags': list,
5560 'like_count': int,
976ae3ea 5561 'age_limit': 0,
5562 'playable_in_embed': True,
5563 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5564 'channel': 'Backus-Page House Museum',
5565 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5566 'live_status': 'not_live',
5567 'view_count': int,
5568 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5569 'availability': 'public',
5570 'duration': 59,
12a1b225
A
5571 'comment_count': int,
5572 'channel_follower_count': int
8bdd16b4 5573 },
5574 'params': {
5575 'noplaylist': True,
5576 'skip_download': True,
5577 },
39e7107d 5578 }, {
8bdd16b4 5579 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5580 'only_matching': True,
cdc628a4
PH
5581 }]
5582
8bdd16b4 5583 def _real_extract(self, url):
5ad28e7f 5584 mobj = self._match_valid_url(url)
29f7c58a 5585 video_id = mobj.group('id')
5586 playlist_id = mobj.group('playlist_id')
8bdd16b4 5587 return self.url_result(
29f7c58a 5588 update_url_query('https://www.youtube.com/watch', {
5589 'v': video_id,
5590 'list': playlist_id,
5591 'feature': 'youtu.be',
5592 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5593
5594
b6ce9bb0 5595class YoutubeLivestreamEmbedIE(InfoExtractor):
5596 IE_DESC = 'YouTube livestream embeds'
5597 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5598 _TESTS = [{
5599 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5600 'only_matching': True,
5601 }]
5602
5603 def _real_extract(self, url):
5604 channel_id = self._match_id(url)
5605 return self.url_result(
5606 f'https://www.youtube.com/channel/{channel_id}/live',
5607 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5608
5609
8bdd16b4 5610class YoutubeYtUserIE(InfoExtractor):
96565c7e 5611 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5612 IE_NAME = 'youtube:user'
8bdd16b4 5613 _VALID_URL = r'ytuser:(?P<id>.+)'
5614 _TESTS = [{
5615 'url': 'ytuser:phihag',
5616 'only_matching': True,
5617 }]
5618
5619 def _real_extract(self, url):
5620 user_id = self._match_id(url)
5621 return self.url_result(
c586f9e8 5622 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5623 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5624
b05654f0 5625
3d3dddc9 5626class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5627 IE_NAME = 'youtube:favorites'
96565c7e 5628 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5629 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5630 _LOGIN_REQUIRED = True
5631 _TESTS = [{
5632 'url': ':ytfav',
5633 'only_matching': True,
5634 }, {
5635 'url': ':ytfavorites',
5636 'only_matching': True,
5637 }]
5638
5639 def _real_extract(self, url):
5640 return self.url_result(
5641 'https://www.youtube.com/playlist?list=LL',
5642 ie=YoutubeTabIE.ie_key())
5643
5644
ca5300c7 5645class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
5646 IE_NAME = 'youtube:notif'
5647 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5648 _VALID_URL = r':ytnotif(?:ication)?s?'
5649 _LOGIN_REQUIRED = True
5650 _TESTS = [{
5651 'url': ':ytnotif',
5652 'only_matching': True,
5653 }, {
5654 'url': ':ytnotifications',
5655 'only_matching': True,
5656 }]
5657
5658 def _extract_notification_menu(self, response, continuation_list):
5659 notification_list = traverse_obj(
5660 response,
5661 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5662 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5663 expected_type=list) or []
5664 continuation_list[0] = None
5665 for item in notification_list:
5666 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
5667 if entry:
5668 yield entry
5669 continuation = item.get('continuationItemRenderer')
5670 if continuation:
5671 continuation_list[0] = continuation
5672
5673 def _extract_notification_renderer(self, notification):
5674 video_id = traverse_obj(
5675 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
5676 url = f'https://www.youtube.com/watch?v={video_id}'
5677 channel_id = None
5678 if not video_id:
5679 browse_ep = traverse_obj(
5680 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
5681 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
5682 post_id = self._search_regex(
5683 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
5684 'post id', default=None)
5685 if not channel_id or not post_id:
5686 return
5687 # The direct /post url redirects to this in the browser
5688 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5689
5690 channel = traverse_obj(
5691 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5692 expected_type=str)
c7a7baaa 5693 notification_title = self._get_text(notification, 'shortMessage')
5694 if notification_title:
5695 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
5696 # TODO: handle recommended videos
ca5300c7 5697 title = self._search_regex(
c7a7baaa 5698 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 5699 'video title', default=None)
ca5300c7 5700 upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d')
5701 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
5702 else None)
5703 return {
5704 '_type': 'url',
5705 'url': url,
5706 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
5707 'video_id': video_id,
5708 'title': title,
5709 'channel_id': channel_id,
5710 'channel': channel,
5711 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5712 'upload_date': upload_date,
5713 }
5714
5715 def _notification_menu_entries(self, ytcfg):
5716 continuation_list = [None]
5717 response = None
5718 for page in itertools.count(1):
5719 ctoken = traverse_obj(
5720 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
5721 response = self._extract_response(
5722 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
5723 ep='notification/get_notification_menu', check_get_keys='actions',
5724 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
5725 yield from self._extract_notification_menu(response, continuation_list)
5726 if not continuation_list[0]:
5727 break
5728
5729 def _real_extract(self, url):
5730 display_id = 'notifications'
5731 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
5732 self._report_playlist_authcheck(ytcfg)
5733 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
5734
5735
a6213a49 5736class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5737 IE_DESC = 'YouTube search'
78caa52a 5738 IE_NAME = 'youtube:search'
b05654f0 5739 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5740 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5741 _TESTS = [{
5742 'url': 'ytsearch5:youtube-dl test video',
5743 'playlist_count': 5,
5744 'info_dict': {
5745 'id': 'youtube-dl test video',
5746 'title': 'youtube-dl test video',
5747 }
5748 }]
b05654f0 5749
a61fd4cf 5750
5f7cb91a 5751class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5752 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5753 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5754 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5755 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5756 _TESTS = [{
5757 'url': 'ytsearchdate5:youtube-dl test video',
5758 'playlist_count': 5,
5759 'info_dict': {
5760 'id': 'youtube-dl test video',
5761 'title': 'youtube-dl test video',
5762 }
5763 }]
75dff0ee 5764
c9ae7b95 5765
a6213a49 5766class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5767 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5768 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5769 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5770 _TESTS = [{
5771 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5772 'playlist_mincount': 5,
5773 'info_dict': {
11f9be09 5774 'id': 'youtube-dl test video',
3462ffa8 5775 'title': 'youtube-dl test video',
5776 }
a61fd4cf 5777 }, {
5778 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5779 'playlist_mincount': 5,
5780 'info_dict': {
5781 'id': 'python',
5782 'title': 'python',
5783 }
ad210f4f 5784 }, {
5785 'url': 'https://www.youtube.com/results?search_query=%23cats',
5786 'playlist_mincount': 1,
5787 'info_dict': {
5788 'id': '#cats',
5789 'title': '#cats',
12a1b225
A
5790 # The test suite does not have support for nested playlists
5791 # 'entries': [{
5792 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5793 # 'title': '#cats',
5794 # }],
ad210f4f 5795 },
3462ffa8 5796 }, {
5797 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5798 'only_matching': True,
5799 }]
5800
5801 def _real_extract(self, url):
4dfbf869 5802 qs = parse_qs(url)
386e1dd9 5803 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5804 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5805
5806
16aa9ea4 5807class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
455a15e2 5808 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
16aa9ea4 5809 IE_NAME = 'youtube:music:search_url'
5810 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5811 _TESTS = [{
5812 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5813 'playlist_count': 16,
5814 'info_dict': {
5815 'id': 'royalty free music',
5816 'title': 'royalty free music',
5817 }
5818 }, {
5819 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5820 'playlist_mincount': 30,
5821 'info_dict': {
5822 'id': 'royalty free music - songs',
5823 'title': 'royalty free music - songs',
5824 },
5825 'params': {'extract_flat': 'in_playlist'}
5826 }, {
5827 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5828 'playlist_mincount': 30,
5829 'info_dict': {
5830 'id': 'royalty free music - community playlists',
5831 'title': 'royalty free music - community playlists',
5832 },
5833 'params': {'extract_flat': 'in_playlist'}
5834 }]
5835
5836 _SECTIONS = {
5837 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5838 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5839 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5840 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5841 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5842 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5843 }
5844
5845 def _real_extract(self, url):
5846 qs = parse_qs(url)
5847 query = (qs.get('search_query') or qs.get('q'))[0]
5848 params = qs.get('sp', (None,))[0]
5849 if params:
5850 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5851 else:
ac668111 5852 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 5853 params = self._SECTIONS.get(section)
5854 if not params:
5855 section = None
5856 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5857 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5858
5859
182bda88 5860class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5861 """
25f14e9f 5862 Base class for feed extractors
82d02080 5863 Subclasses must re-define the _FEED_NAME property.
d7ae0639 5864 """
b2e8bc1b 5865 _LOGIN_REQUIRED = True
82d02080 5866 _FEED_NAME = 'feeds'
a25bca9f 5867
5868 def _real_initialize(self):
5869 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 5870
82d02080 5871 @classproperty
d7ae0639 5872 def IE_NAME(self):
82d02080 5873 return f'youtube:{self._FEED_NAME}'
04cc9617 5874
3853309f 5875 def _real_extract(self, url):
3d3dddc9 5876 return self.url_result(
182bda88 5877 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5878
5879
ef2f3c7f 5880class YoutubeWatchLaterIE(InfoExtractor):
5881 IE_NAME = 'youtube:watchlater'
96565c7e 5882 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5883 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5884 _TESTS = [{
8bdd16b4 5885 'url': ':ytwatchlater',
bc7a9cd8
S
5886 'only_matching': True,
5887 }]
25f14e9f
S
5888
5889 def _real_extract(self, url):
ef2f3c7f 5890 return self.url_result(
5891 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5892
5893
25f14e9f 5894class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5895 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5896 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5897 _FEED_NAME = 'recommended'
45db527f 5898 _LOGIN_REQUIRED = False
3d3dddc9 5899 _TESTS = [{
5900 'url': ':ytrec',
5901 'only_matching': True,
5902 }, {
5903 'url': ':ytrecommended',
5904 'only_matching': True,
5905 }, {
5906 'url': 'https://youtube.com',
5907 'only_matching': True,
5908 }]
1ed5b5c9 5909
1ed5b5c9 5910
25f14e9f 5911class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5912 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5913 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5914 _FEED_NAME = 'subscriptions'
3d3dddc9 5915 _TESTS = [{
5916 'url': ':ytsubs',
5917 'only_matching': True,
5918 }, {
5919 'url': ':ytsubscriptions',
5920 'only_matching': True,
5921 }]
1ed5b5c9 5922
1ed5b5c9 5923
25f14e9f 5924class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5925 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5926 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5927 _FEED_NAME = 'history'
3d3dddc9 5928 _TESTS = [{
5929 'url': ':ythistory',
5930 'only_matching': True,
5931 }]
1ed5b5c9
JMF
5932
5933
6e634cbe 5934class YoutubeStoriesIE(InfoExtractor):
5935 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
5936 IE_NAME = 'youtube:stories'
5937 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
5938 _TESTS = [{
5939 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
5940 'only_matching': True,
5941 }]
5942
5943 def _real_extract(self, url):
5944 playlist_id = f'RLTD{self._match_id(url)}'
5945 return self.url_result(
5946 f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
5947 ie=YoutubeTabIE, video_id=playlist_id)
5948
5949
15870e90
PH
5950class YoutubeTruncatedURLIE(InfoExtractor):
5951 IE_NAME = 'youtube:truncated_url'
5952 IE_DESC = False # Do not list
975d35db 5953 _VALID_URL = r'''(?x)
b95aab84
PH
5954 (?:https?://)?
5955 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5956 (?:watch\?(?:
c4808c60 5957 feature=[a-z_]+|
b95aab84
PH
5958 annotation_id=annotation_[^&]+|
5959 x-yt-cl=[0-9]+|
c1708b89 5960 hl=[^&]*|
287be8c6 5961 t=[0-9]+
b95aab84
PH
5962 )?
5963 |
5964 attribution_link\?a=[^&]+
5965 )
5966 $
975d35db 5967 '''
15870e90 5968
c4808c60 5969 _TESTS = [{
2d3d2997 5970 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5971 'only_matching': True,
dc2fc736 5972 }, {
2d3d2997 5973 'url': 'https://www.youtube.com/watch?',
dc2fc736 5974 'only_matching': True,
b95aab84
PH
5975 }, {
5976 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5977 'only_matching': True,
5978 }, {
5979 'url': 'https://www.youtube.com/watch?feature=foo',
5980 'only_matching': True,
c1708b89
PH
5981 }, {
5982 'url': 'https://www.youtube.com/watch?hl=en-GB',
5983 'only_matching': True,
287be8c6
PH
5984 }, {
5985 'url': 'https://www.youtube.com/watch?t=2372',
5986 'only_matching': True,
c4808c60
PH
5987 }]
5988
15870e90
PH
5989 def _real_extract(self, url):
5990 raise ExtractorError(
78caa52a
PH
5991 'Did you forget to quote the URL? Remember that & is a meta '
5992 'character in most shells, so you want to put the URL in quotes, '
3867038a 5993 'like youtube-dl '
2d3d2997 5994 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 5995 ' or simply youtube-dl BaW_jenozKc .',
15870e90 5996 expected=True)
772fd5cc
PH
5997
5998
471d0367 5999class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6000 IE_NAME = 'youtube:clip'
471d0367 6001 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6002 _TESTS = [{
6003 # FIXME: Other metadata should be extracted from the clip, not from the base video
6004 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6005 'info_dict': {
6006 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6007 'ext': 'mp4',
6008 'section_start': 29.0,
6009 'section_end': 39.7,
6010 'duration': 10.7,
12a1b225
A
6011 'age_limit': 0,
6012 'availability': 'public',
6013 'categories': ['Gaming'],
6014 'channel': 'Scott The Woz',
6015 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6016 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6017 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6018 'like_count': int,
6019 'playable_in_embed': True,
6020 'tags': 'count:17',
6021 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6022 'title': 'Mobile Games on Console - Scott The Woz',
6023 'upload_date': '20210920',
6024 'uploader': 'Scott The Woz',
6025 'uploader_id': 'scottthewoz',
6026 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6027 'view_count': int,
6028 'live_status': 'not_live',
6029 'channel_follower_count': int
471d0367 6030 }
6031 }]
3cd786db 6032
6033 def _real_extract(self, url):
471d0367 6034 clip_id = self._match_id(url)
6035 _, data = self._extract_webpage(url, clip_id)
6036
6037 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6038 if not video_id:
6039 raise ExtractorError('Unable to find video ID')
6040
6041 clip_data = traverse_obj(data, (
6042 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6043 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6044 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6045 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6046
6047 return {
6048 '_type': 'url_transparent',
6049 'url': f'https://www.youtube.com/watch?v={video_id}',
6050 'ie_key': YoutubeIE.ie_key(),
6051 'id': clip_id,
6052 'section_start': int(clip_data['startTimeMs']) / 1000,
6053 'section_end': int(clip_data['endTimeMs']) / 1000,
6054 }
3cd786db 6055
6056
772fd5cc
PH
6057class YoutubeTruncatedIDIE(InfoExtractor):
6058 IE_NAME = 'youtube:truncated_id'
6059 IE_DESC = False # Do not list
b95aab84 6060 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6061
6062 _TESTS = [{
6063 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6064 'only_matching': True,
6065 }]
6066
6067 def _real_extract(self, url):
6068 video_id = self._match_id(url)
6069 raise ExtractorError(
86e5f3ed 6070 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6071 expected=True)