]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[extractor/SovietsCloset] Fix extractor (#4688)
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
6e634cbe 1import base64
d92f5d5a 2import calendar
109dd3b2 3import copy
fe93e2c4 4import datetime
a5c56234 5import hashlib
0ca96d48 6import itertools
c5e8d7af 7import json
720c3099 8import math
c4417ddb 9import os.path
d77ab8e2 10import random
c5e8d7af 11import re
46383212 12import sys
f8271158 13import threading
8a784c74 14import time
e0df6211 15import traceback
14f25df2 16import urllib.error
ac668111 17import urllib.parse
c5e8d7af 18
b05654f0 19from .common import InfoExtractor, SearchInfoExtractor
14f25df2 20from ..compat import functools
545cc85d 21from ..jsinterp import JSInterpreter
4bb4a188 22from ..utils import (
f8271158 23 NO_DEFAULT,
24 ExtractorError,
693f0600 25 UserNotLive,
720c3099 26 bug_reports_message,
82d02080 27 classproperty,
c5e8d7af 28 clean_html,
d92f5d5a 29 datetime_from_str,
11f9be09 30 dict_get,
2d30521a 31 float_or_none,
11f9be09 32 format_field,
ff91cf74 33 get_first,
dd27fd17 34 int_or_none,
641ad5d8 35 is_html,
34921b43 36 join_nonempty,
48416bc4 37 js_to_json,
94278f72 38 mimetype2ext,
9c0d7f49 39 network_exceptions,
11f9be09 40 orderedSet,
6310acf5 41 parse_codecs,
49bd8c66 42 parse_count,
7c80519c 43 parse_duration,
7ea65411 44 parse_iso8601,
4dfbf869 45 parse_qs,
dca3ff4a 46 qualities,
3995d37d 47 remove_start,
cf7e015f 48 smuggle_url,
dbdaaa23 49 str_or_none,
c93d53f5 50 str_to_int,
f3aa3c3f 51 strftime_or_none,
7c365c21 52 traverse_obj,
556dbe7f 53 try_get,
c5e8d7af
PH
54 unescapeHTML,
55 unified_strdate,
f0d785d3 56 unified_timestamp,
cf7e015f 57 unsmuggle_url,
8bdd16b4 58 update_url_query,
21c340b8 59 url_or_none,
fe93e2c4 60 urljoin,
7c365c21 61 variadic,
c5e8d7af
PH
62)
63
962ffcf8 64# any clients starting with _ cannot be explicitly requested by the user
000c15a4 65INNERTUBE_CLIENTS = {
66 'web': {
67 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
68 'INNERTUBE_CONTEXT': {
69 'client': {
70 'clientName': 'WEB',
a0c830f4 71 'clientVersion': '2.20220801.00.00',
000c15a4 72 }
73 },
74 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
75 },
76 'web_embedded': {
77 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
78 'INNERTUBE_CONTEXT': {
79 'client': {
80 'clientName': 'WEB_EMBEDDED_PLAYER',
a0c830f4 81 'clientVersion': '1.20220731.00.00',
000c15a4 82 },
83 },
84 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
85 },
86 'web_music': {
87 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
88 'INNERTUBE_HOST': 'music.youtube.com',
89 'INNERTUBE_CONTEXT': {
90 'client': {
91 'clientName': 'WEB_REMIX',
a0c830f4 92 'clientVersion': '1.20220727.01.00',
000c15a4 93 }
94 },
95 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
96 },
e7e94f2a 97 'web_creator': {
18c7683d 98 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
99 'INNERTUBE_CONTEXT': {
100 'client': {
101 'clientName': 'WEB_CREATOR',
a0c830f4 102 'clientVersion': '1.20220726.00.00',
e7e94f2a
D
103 }
104 },
105 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
106 },
000c15a4 107 'android': {
18c7683d 108 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 109 'INNERTUBE_CONTEXT': {
110 'client': {
111 'clientName': 'ANDROID',
c7dcf0b3 112 'clientVersion': '17.29.34',
113 'androidSdkVersion': 30
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',
c7dcf0b3 124 'clientVersion': '17.29.34',
125 'androidSdkVersion': 30
000c15a4 126 },
127 },
b6de707d 128 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
129 'REQUIRE_JS_PLAYER': False
000c15a4 130 },
131 'android_music': {
18c7683d 132 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 133 'INNERTUBE_CONTEXT': {
134 'client': {
135 'clientName': 'ANDROID_MUSIC',
a0c830f4 136 'clientVersion': '5.16.51',
c7dcf0b3 137 'androidSdkVersion': 30
000c15a4 138 }
139 },
140 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 141 'REQUIRE_JS_PLAYER': False
000c15a4 142 },
e7e94f2a 143 'android_creator': {
18c7683d 144 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
145 'INNERTUBE_CONTEXT': {
146 'client': {
147 'clientName': 'ANDROID_CREATOR',
a0c830f4 148 'clientVersion': '22.28.100',
c7dcf0b3 149 'androidSdkVersion': 30
e7e94f2a
D
150 },
151 },
b6de707d 152 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
153 'REQUIRE_JS_PLAYER': False
e7e94f2a 154 },
18c7683d 155 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
156 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 157 'ios': {
18c7683d 158 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 159 'INNERTUBE_CONTEXT': {
160 'client': {
161 'clientName': 'IOS',
a0c830f4 162 'clientVersion': '17.30.1',
18c7683d 163 'deviceModel': 'iPhone14,3',
000c15a4 164 }
165 },
b6de707d 166 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
167 'REQUIRE_JS_PLAYER': False
000c15a4 168 },
169 'ios_embedded': {
000c15a4 170 'INNERTUBE_CONTEXT': {
171 'client': {
172 'clientName': 'IOS_MESSAGES_EXTENSION',
a0c830f4 173 'clientVersion': '17.30.1',
18c7683d 174 'deviceModel': 'iPhone14,3',
000c15a4 175 },
176 },
b6de707d 177 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
178 'REQUIRE_JS_PLAYER': False
000c15a4 179 },
180 'ios_music': {
18c7683d 181 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 182 'INNERTUBE_CONTEXT': {
183 'client': {
184 'clientName': 'IOS_MUSIC',
a0c830f4 185 'clientVersion': '5.18',
000c15a4 186 },
187 },
b6de707d 188 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
189 'REQUIRE_JS_PLAYER': False
000c15a4 190 },
e7e94f2a
D
191 'ios_creator': {
192 'INNERTUBE_CONTEXT': {
193 'client': {
194 'clientName': 'IOS_CREATOR',
a0c830f4 195 'clientVersion': '22.29.101',
e7e94f2a
D
196 },
197 },
b6de707d 198 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
199 'REQUIRE_JS_PLAYER': False
e7e94f2a 200 },
3619f78d 201 # mweb has 'ultralow' formats
202 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 203 'mweb': {
18c7683d 204 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 205 'INNERTUBE_CONTEXT': {
206 'client': {
207 'clientName': 'MWEB',
a0c830f4 208 'clientVersion': '2.20220801.00.00',
000c15a4 209 }
210 },
211 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
212 },
213 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
214 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
215 'tv_embedded': {
216 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
217 'INNERTUBE_CONTEXT': {
218 'client': {
219 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
220 'clientVersion': '2.0',
221 },
222 },
223 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
224 },
000c15a4 225}
226
227
e7870111
D
228def _split_innertube_client(client_name):
229 variant, *base = client_name.rsplit('.', 1)
230 if base:
231 return variant, base[0], variant
232 base, *variant = client_name.split('_', 1)
233 return client_name, base, variant[0] if variant else None
234
235
000c15a4 236def build_innertube_clients():
2e4cacd0 237 THIRD_PARTY = {
e7870111 238 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 239 }
e7870111 240 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 241 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 242
243 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 244 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 245 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 246 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 247 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 248
e7870111 249 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 250 ytcfg['priority'] = 10 * priority(base_client)
251
e48b3875 252 if not variant:
e7870111
D
253 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
254 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
255 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
256 embedscreen['priority'] -= 3
257 elif variant == 'embedded':
e48b3875 258 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 259 ytcfg['priority'] -= 2
e48b3875 260 else:
000c15a4 261 ytcfg['priority'] -= 3
262
263
264build_innertube_clients()
265
266
de7f3446 267class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 268 """Provide base functions for Youtube extractors"""
e00eb564 269
3462ffa8 270 _RESERVED_NAMES = (
3cd786db 271 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 272 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 273 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 274 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 275
3619f78d 276 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
277
52efa4b3 278 # _NETRC_MACHINE = 'youtube'
3619f78d 279
b2e8bc1b
JMF
280 # If True it will raise an error if no login info is provided
281 _LOGIN_REQUIRED = False
282
d9190e44
RH
283 _INVIDIOUS_SITES = (
284 # invidious-redirect websites
285 r'(?:www\.)?redirect\.invidious\.io',
286 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 287 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
288 r'(?:www\.)?invidious\.pussthecat\.org',
289 r'(?:www\.)?invidious\.zee\.li',
290 r'(?:www\.)?invidious\.ethibox\.fr',
291 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
292 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
293 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
294 # youtube-dl invidious instances list
295 r'(?:(?:www|no)\.)?invidiou\.sh',
296 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
297 r'(?:www\.)?invidious\.kabi\.tk',
298 r'(?:www\.)?invidious\.mastodon\.host',
299 r'(?:www\.)?invidious\.zapashcanon\.fr',
300 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
301 r'(?:www\.)?invidious\.tinfoil-hat\.net',
302 r'(?:www\.)?invidious\.himiko\.cloud',
303 r'(?:www\.)?invidious\.reallyancient\.tech',
304 r'(?:www\.)?invidious\.tube',
305 r'(?:www\.)?invidiou\.site',
306 r'(?:www\.)?invidious\.site',
307 r'(?:www\.)?invidious\.xyz',
308 r'(?:www\.)?invidious\.nixnet\.xyz',
309 r'(?:www\.)?invidious\.048596\.xyz',
310 r'(?:www\.)?invidious\.drycat\.fr',
311 r'(?:www\.)?inv\.skyn3t\.in',
312 r'(?:www\.)?tube\.poal\.co',
313 r'(?:www\.)?tube\.connect\.cafe',
314 r'(?:www\.)?vid\.wxzm\.sx',
315 r'(?:www\.)?vid\.mint\.lgbt',
316 r'(?:www\.)?vid\.puffyan\.us',
317 r'(?:www\.)?yewtu\.be',
318 r'(?:www\.)?yt\.elukerio\.org',
319 r'(?:www\.)?yt\.lelux\.fi',
320 r'(?:www\.)?invidious\.ggc-project\.de',
321 r'(?:www\.)?yt\.maisputain\.ovh',
322 r'(?:www\.)?ytprivate\.com',
323 r'(?:www\.)?invidious\.13ad\.de',
324 r'(?:www\.)?invidious\.toot\.koeln',
325 r'(?:www\.)?invidious\.fdn\.fr',
326 r'(?:www\.)?watch\.nettohikari\.com',
327 r'(?:www\.)?invidious\.namazso\.eu',
328 r'(?:www\.)?invidious\.silkky\.cloud',
329 r'(?:www\.)?invidious\.exonip\.de',
330 r'(?:www\.)?invidious\.riverside\.rocks',
331 r'(?:www\.)?invidious\.blamefran\.net',
332 r'(?:www\.)?invidious\.moomoo\.de',
333 r'(?:www\.)?ytb\.trom\.tf',
334 r'(?:www\.)?yt\.cyberhost\.uk',
335 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
336 r'(?:www\.)?qklhadlycap4cnod\.onion',
337 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
338 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
339 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
340 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
341 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
342 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
343 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
344 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
345 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
346 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
347 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
348 r'(?:www\.)?piped\.kavin\.rocks',
349 r'(?:www\.)?piped\.silkky\.cloud',
350 r'(?:www\.)?piped\.tokhmi\.xyz',
351 r'(?:www\.)?piped\.moomoo\.me',
352 r'(?:www\.)?il\.ax',
353 r'(?:www\.)?piped\.syncpundit\.com',
354 r'(?:www\.)?piped\.mha\.fi',
355 r'(?:www\.)?piped\.mint\.lgbt',
356 r'(?:www\.)?piped\.privacy\.com\.de',
d9190e44
RH
357 )
358
cce889b9 359 def _initialize_consent(self):
360 cookies = self._get_cookies('https://www.youtube.com/')
361 if cookies.get('__Secure-3PSID'):
362 return
363 consent_id = None
364 consent = cookies.get('CONSENT')
365 if consent:
366 if 'YES' in consent.value:
367 return
368 consent_id = self._search_regex(
369 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
370 if not consent_id:
371 consent_id = random.randint(100, 999)
372 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 373
f3aa3c3f 374 def _initialize_pref(self):
375 cookies = self._get_cookies('https://www.youtube.com/')
376 pref_cookie = cookies.get('PREF')
377 pref = {}
378 if pref_cookie:
379 try:
14f25df2 380 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 381 except ValueError:
382 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 383 pref.update({'hl': 'en', 'tz': 'UTC'})
14f25df2 384 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 385
b2e8bc1b 386 def _real_initialize(self):
f3aa3c3f 387 self._initialize_pref()
cce889b9 388 self._initialize_consent()
a25bca9f 389 self._check_login_required()
390
391 def _check_login_required(self):
24146491 392 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 393 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 394
b7c47b74 395 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
396 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 397
000c15a4 398 def _get_default_ytcfg(self, client='web'):
399 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 400
000c15a4 401 def _get_innertube_host(self, client='web'):
402 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 403
000c15a4 404 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 405 # try_get but with fallback to default ytcfg client values when present
406 _func = lambda y: try_get(y, getter, expected_type)
407 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
408
000c15a4 409 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 410 return self._ytcfg_get_safe(
411 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 412 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 413
000c15a4 414 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 415 return self._ytcfg_get_safe(
416 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 417 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 418
2ae778b8 419 def _select_api_hostname(self, req_api_hostname, default_client=None):
420 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
421 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
422
000c15a4 423 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 424 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 425
000c15a4 426 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 427 context = get_first(
428 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 429 # Enforce language and tz for extraction
430 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
431 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 432 return context
433
cf87314d 434 _SAPISID = None
435
109dd3b2 436 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 437 time_now = round(time.time())
cf87314d 438 if self._SAPISID is None:
439 yt_cookies = self._get_cookies('https://www.youtube.com')
440 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
441 # See: https://github.com/yt-dlp/yt-dlp/issues/393
442 sapisid_cookie = dict_get(
443 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
444 if sapisid_cookie and sapisid_cookie.value:
445 self._SAPISID = sapisid_cookie.value
446 self.write_debug('Extracted SAPISID cookie')
447 # SAPISID cookie is required if not already present
448 if not yt_cookies.get('SAPISID'):
449 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
450 self._set_cookie(
451 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
452 else:
453 self._SAPISID = False
454 if not self._SAPISID:
455 return None
1974e99f 456 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
457 sapisidhash = hashlib.sha1(
86e5f3ed 458 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 459 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
460
461 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 462 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 463 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 464
109dd3b2 465 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 466 data.update(query)
11f9be09 467 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 468 real_headers.update({'content-type': 'application/json'})
469 if headers:
470 real_headers.update(headers)
2ae778b8 471 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
472 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 473 return self._download_json(
2ae778b8 474 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 475 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 476 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 477 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 478
65141660 479 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
480 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 481
99e9e001 482 @staticmethod
483 def _extract_session_index(*data):
484 """
485 Index of current account in account list.
486 See: https://github.com/yt-dlp/yt-dlp/pull/519
487 """
488 for ytcfg in data:
489 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
490 if session_index is not None:
491 return session_index
492
493 # Deprecated?
494 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 495 if ytcfg:
14f25df2 496 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
497 if token:
498 return token
99e9e001 499 if webpage:
500 return self._search_regex(
501 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
502 'identity token', default=None, fatal=False)
a1c5d2ca
M
503
504 @staticmethod
fe93e2c4 505 def _extract_account_syncid(*args):
8ea3f7b9 506 """
507 Extract syncId required to download private playlists of secondary channels
fe93e2c4 508 @params response and/or ytcfg
8ea3f7b9 509 """
fe93e2c4 510 for data in args:
511 # ytcfg includes channel_syncid if on secondary channel
14f25df2 512 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 513 if delegated_sid:
514 return delegated_sid
515 sync_ids = (try_get(
516 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 517 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 518 if len(sync_ids) >= 2 and sync_ids[1]:
519 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
520 # and just "user_syncid||" for primary channel. We only want the channel_syncid
521 return sync_ids[0]
a1c5d2ca 522
ac56cf38 523 @staticmethod
524 def _extract_visitor_data(*args):
525 """
526 Extracts visitorData from an API response or ytcfg
527 Appears to be used to track session state
528 """
9222c381 529 return get_first(
6c73052c 530 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 531 expected_type=str)
ac56cf38 532
2762dbb1 533 @functools.cached_property
99e9e001 534 def is_authenticated(self):
535 return bool(self._generate_sapisidhash_header())
536
11f9be09 537 def extract_ytcfg(self, video_id, webpage):
8c54a305 538 if not webpage:
539 return {}
29f7c58a 540 return self._parse_json(
541 self._search_regex(
542 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 543 default='{}'), video_id, fatal=False) or {}
544
11f9be09 545 def generate_api_headers(
99e9e001 546 self, *, ytcfg=None, account_syncid=None, session_index=None,
547 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
548
2ae778b8 549 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 550 headers = {
14f25df2 551 'X-YouTube-Client-Name': str(
11f9be09 552 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
553 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 554 'Origin': origin,
555 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
556 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 557 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 558 }
559 if session_index is None:
314ee305 560 session_index = self._extract_session_index(ytcfg)
561 if account_syncid or session_index is not None:
562 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 563
109dd3b2 564 auth = self._generate_sapisidhash_header(origin)
f4f751af 565 if auth is not None:
566 headers['Authorization'] = auth
109dd3b2 567 headers['X-Origin'] = origin
99e9e001 568 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 569
a25bca9f 570 def _download_ytcfg(self, client, video_id):
571 url = {
572 'web': 'https://www.youtube.com',
573 'web_music': 'https://music.youtube.com',
574 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
575 }.get(client)
576 if not url:
577 return {}
578 webpage = self._download_webpage(
579 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
580 return self.extract_ytcfg(video_id, webpage) or {}
581
2d6659b9 582 @staticmethod
583 def _build_api_continuation_query(continuation, ctp=None):
584 query = {
585 'continuation': continuation
586 }
587 # TODO: Inconsistency with clickTrackingParams.
588 # Currently we have a fixed ctp contained within context (from ytcfg)
589 # and a ctp in root query for continuation.
590 if ctp:
591 query['clickTracking'] = {'clickTrackingParams': ctp}
592 return query
593
2d6659b9 594 @classmethod
595 def _extract_next_continuation_data(cls, renderer):
596 next_continuation = try_get(
597 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
598 lambda x: x['continuation']['reloadContinuationData']), dict)
599 if not next_continuation:
600 return
601 continuation = next_continuation.get('continuation')
602 if not continuation:
603 return
604 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 605 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 606
607 @classmethod
608 def _extract_continuation_ep_data(cls, continuation_ep: dict):
609 if isinstance(continuation_ep, dict):
610 continuation = try_get(
14f25df2 611 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 612 if not continuation:
613 return
614 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 615 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 616
617 @classmethod
618 def _extract_continuation(cls, renderer):
619 next_continuation = cls._extract_next_continuation_data(renderer)
620 if next_continuation:
621 return next_continuation
fe93e2c4 622
2d6659b9 623 contents = []
624 for key in ('contents', 'items'):
625 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 626
2d6659b9 627 for content in contents:
628 if not isinstance(content, dict):
629 continue
630 continuation_ep = try_get(
631 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
632 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
633 dict)
634 continuation = cls._extract_continuation_ep_data(continuation_ep)
635 if continuation:
636 return continuation
637
fe93e2c4 638 @classmethod
639 def _extract_alerts(cls, data):
109dd3b2 640 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
641 if not isinstance(alert_dict, dict):
642 continue
643 for alert in alert_dict.values():
644 alert_type = alert.get('type')
645 if not alert_type:
646 continue
052e1350 647 message = cls._get_text(alert, 'text')
109dd3b2 648 if message:
649 yield alert_type, message
650
c0ac49bc 651 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 652 errors = []
653 warnings = []
654 for alert_type, alert_message in alerts:
641ad5d8 655 if alert_type.lower() == 'error' and fatal:
109dd3b2 656 errors.append([alert_type, alert_message])
657 else:
658 warnings.append([alert_type, alert_message])
659
660 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 661 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 662 if errors:
663 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
664
665 def _extract_and_report_alerts(self, data, *args, **kwargs):
666 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
667
47193e02 668 def _extract_badges(self, renderer: dict):
669 badges = set()
670 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
14f25df2 671 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], str)
47193e02 672 if label:
673 badges.add(label.lower())
674 return badges
675
676 @staticmethod
052e1350 677 def _get_text(data, *path_list, max_runs=None):
678 for path in path_list or [None]:
679 if path is None:
680 obj = [data]
681 else:
682 obj = traverse_obj(data, path, default=[])
683 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
684 obj = [obj]
685 for item in obj:
14f25df2 686 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 687 if text:
688 return text
689 runs = try_get(item, lambda x: x['runs'], list) or []
690 if not runs and isinstance(item, list):
691 runs = item
692
693 runs = runs[:min(len(runs), max_runs or len(runs))]
694 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
695 if text:
696 return text
47193e02 697
f0d785d3 698 def _get_count(self, data, *path_list):
699 count_text = self._get_text(data, *path_list) or ''
700 count = parse_count(count_text)
701 if count is None:
702 count = str_to_int(
703 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
704 return count
705
a709d873 706 @staticmethod
707 def _extract_thumbnails(data, *path_list):
708 """
709 Extract thumbnails from thumbnails dict
710 @param path_list: path list to level that contains 'thumbnails' key
711 """
712 thumbnails = []
713 for path in path_list or [()]:
714 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
715 thumbnail_url = url_or_none(thumbnail.get('url'))
716 if not thumbnail_url:
717 continue
718 # Sometimes youtube gives a wrong thumbnail URL. See:
719 # https://github.com/yt-dlp/yt-dlp/issues/233
720 # https://github.com/ytdl-org/youtube-dl/issues/28023
721 if 'maxresdefault' in thumbnail_url:
722 thumbnail_url = thumbnail_url.split('?')[0]
723 thumbnails.append({
724 'url': thumbnail_url,
725 'height': int_or_none(thumbnail.get('height')),
726 'width': int_or_none(thumbnail.get('width')),
727 })
728 return thumbnails
729
f3aa3c3f 730 @staticmethod
731 def extract_relative_time(relative_time_text):
732 """
733 Extracts a relative time from string and converts to dt object
f0d785d3 734 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 735 """
f0d785d3 736 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 737 if mobj:
f0d785d3 738 start = mobj.group('start')
739 if start:
740 return datetime_from_str(start)
f3aa3c3f 741 try:
f0d785d3 742 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 743 except ValueError:
744 return None
745
746 def _extract_time_text(self, renderer, *path_list):
a25bca9f 747 """@returns (timestamp, time_text)"""
f3aa3c3f 748 text = self._get_text(renderer, *path_list) or ''
749 dt = self.extract_relative_time(text)
750 timestamp = None
751 if isinstance(dt, datetime.datetime):
752 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 753
754 if timestamp is None:
755 timestamp = (
756 unified_timestamp(text) or unified_timestamp(
757 self._search_regex(
17322130 758 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 759 text.lower(), 'time text', default=None)))
f0d785d3 760
f3aa3c3f 761 if text and timestamp is None:
17322130 762 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
f3aa3c3f 763 return timestamp, text
764
109dd3b2 765 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
766 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 767 default_client='web'):
be5c1ae8 768 for retry in self.RetryManager():
109dd3b2 769 try:
770 response = self._call_api(
771 ep=ep, fatal=True, headers=headers,
be5c1ae8 772 video_id=item_id, query=query, note=note,
109dd3b2 773 context=self._extract_context(ytcfg, default_client),
774 api_key=self._extract_api_key(ytcfg, default_client),
be5c1ae8 775 api_hostname=api_hostname, default_client=default_client)
109dd3b2 776 except ExtractorError as e:
be5c1ae8 777 if not isinstance(e.cause, network_exceptions):
778 return self._error_or_warning(e, fatal=fatal)
779 elif not isinstance(e.cause, urllib.error.HTTPError):
780 retry.error = e
781 continue
109dd3b2 782
be5c1ae8 783 first_bytes = e.cause.read(512)
784 if not is_html(first_bytes):
785 yt_error = try_get(
786 self._parse_json(
787 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
788 lambda x: x['error']['message'], str)
789 if yt_error:
790 self._report_alerts([('ERROR', yt_error)], fatal=False)
791 # Downloading page may result in intermittent 5xx HTTP error
792 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
793 # We also want to catch all other network exceptions since errors in later pages can be troublesome
794 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
795 if e.cause.code not in (403, 429):
796 retry.error = e
797 continue
798 return self._error_or_warning(e, fatal=fatal)
799
800 try:
801 self._extract_and_report_alerts(response, only_once=True)
802 except ExtractorError as e:
803 # YouTube servers may return errors we want to retry on in a 200 OK response
804 # See: https://github.com/yt-dlp/yt-dlp/issues/839
805 if 'unknown error' in e.msg.lower():
806 retry.error = e
807 continue
808 return self._error_or_warning(e, fatal=fatal)
809 # Youtube sometimes sends incomplete data
810 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
811 if not traverse_obj(response, *variadic(check_get_keys)):
3ce29336 812 retry.error = ExtractorError('Incomplete data received', expected=True)
be5c1ae8 813 continue
814
815 return response
109dd3b2 816
9297939e 817 @staticmethod
818 def is_music_url(url):
819 return re.match(r'https?://music\.youtube\.com/', url) is not None
820
30a074c2 821 def _extract_video(self, renderer):
822 video_id = renderer.get('videoId')
052e1350 823 title = self._get_text(renderer, 'title')
824 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 825 duration = parse_duration(self._get_text(
826 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 827 if duration is None:
828 duration = parse_duration(self._search_regex(
829 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
830 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
831 video_id, default=None, group='duration'))
832
f0d785d3 833 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 834
052e1350 835 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 836 channel_id = traverse_obj(
a44ca5a4 837 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
838 expected_type=str, get_all=False)
f3aa3c3f 839 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
840 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
841 overlay_style = traverse_obj(
a44ca5a4 842 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
843 get_all=False, expected_type=str)
f3aa3c3f 844 badges = self._extract_badges(renderer)
a709d873 845 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
fd2ad7cb 846 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 847 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
848 expected_type=str)) or ''
fd2ad7cb 849 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 850 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 851 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 852
30a074c2 853 return {
39ed931e 854 '_type': 'url',
30a074c2 855 'ie_key': YoutubeIE.ie_key(),
856 'id': video_id,
fd2ad7cb 857 'url': url,
30a074c2 858 'title': title,
859 'description': description,
860 'duration': duration,
861 'view_count': view_count,
862 'uploader': uploader,
f3aa3c3f 863 'channel_id': channel_id,
a709d873 864 'thumbnails': thumbnails,
a44ca5a4 865 'upload_date': (strftime_or_none(timestamp, '%Y%m%d')
866 if self._configuration_arg('approximate_date', ie_key='youtubetab')
867 else None),
f3aa3c3f 868 'live_status': ('is_upcoming' if scheduled_timestamp is not None
869 else 'was_live' if 'streamed' in time_text.lower()
870 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
871 else None),
872 'release_timestamp': scheduled_timestamp,
873 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 874 }
875
0c148415 876
360e1ca5 877class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 878 IE_DESC = 'YouTube'
cb7dfeea 879 _VALID_URL = r"""(?x)^
c5e8d7af 880 (
edb53e2d 881 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 882 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
883 (?:www\.)?deturl\.com/www\.youtube\.com|
884 (?:www\.)?pwnyoutube\.com|
885 (?:www\.)?hooktube\.com|
886 (?:www\.)?yourepeat\.com|
887 tube\.majestyc\.net|
888 %(invidious)s|
889 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
890 (?:.*?\#/)? # handle anchor (#/) redirect urls
891 (?: # the various things that can precede the ID:
b6ce9bb0 892 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 893 |(?: # or the v= param in all its forms
f7000f3a 894 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 895 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 896 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
897 v=
898 )
f4b05232 899 ))
cbaed4bb
S
900 |(?:
901 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
902 vid\.plus| # or vid.plus/xxxx
903 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 904 %(invidious)s
cbaed4bb 905 )/
edb53e2d 906 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 907 )
c5e8d7af 908 )? # all until now is optional -> you can pass the naked ID
201c1459 909 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 910 (?(1).+)? # if we found the ID, everything can follow
9297939e 911 (?:\#|$)""" % {
d9190e44 912 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 913 }
bfd973ec 914 _EMBED_REGEX = [r'''(?x)
915 (?:
916 <iframe[^>]+?src=|
917 data-video-url=|
918 <embed[^>]+?src=|
919 embedSWF\(?:\s*|
920 <object[^>]+data=|
921 new\s+SWFObject\(
922 )
923 (["\'])
924 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
925 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
926 \1''']
e40c758c 927 _PLAYER_INFO_RE = (
cc2db878 928 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
929 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$',
545cc85d 930 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 931 )
2c62dc26 932 _formats = {
c2d3cb4c 933 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
934 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
935 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
936 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
937 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
938 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
939 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
940 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 941 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 942 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
943 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
944 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
945 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
946 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
947 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 948 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 949 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
950 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 951
952
953 # 3D videos
c2d3cb4c 954 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
955 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
956 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
957 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 958 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
959 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
960 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 961
96fb5605 962 # Apple HTTP Live Streaming
11f12195 963 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 964 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
965 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
966 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
967 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
968 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 969 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
970 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
971
972 # DASH mp4 video
d23028a8
S
973 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
974 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
975 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
976 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
977 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 978 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
979 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
980 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
981 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
982 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
983 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
984 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 985
f6f1fc92 986 # Dash mp4 audio
d23028a8
S
987 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
988 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
989 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
990 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
991 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
992 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
993 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
994
995 # Dash webm
d23028a8
S
996 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
997 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
998 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
999 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1000 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1001 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1002 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1003 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1004 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1005 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1006 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1007 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1008 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1009 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1010 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1011 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1012 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1013 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1014 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1015 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1016 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1017 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1018
1019 # Dash webm audio
d23028a8
S
1020 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1021 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1022
0857baad 1023 # Dash webm audio with opus inside
d23028a8
S
1024 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1025 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1026 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1027
ce6b9a2d
PH
1028 # RTMP (unnamed)
1029 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1030
1031 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1032 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1033 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1034 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1035 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1036 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1037 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1038 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1039 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1040 }
29f7c58a 1041 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1042
fd5c4aab
S
1043 _GEO_BYPASS = False
1044
78caa52a 1045 IE_NAME = 'youtube'
2eb88d95
PH
1046 _TESTS = [
1047 {
2d3d2997 1048 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1049 'info_dict': {
1050 'id': 'BaW_jenozKc',
1051 'ext': 'mp4',
3867038a 1052 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1053 'uploader': 'Philipp Hagemeister',
1054 'uploader_id': 'phihag',
ec85ded8 1055 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1056 'channel': 'Philipp Hagemeister',
dd4c4492
S
1057 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1058 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1059 'upload_date': '20121002',
ff9f925b 1060 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1061 'categories': ['Science & Technology'],
3867038a 1062 'tags': ['youtube-dl'],
556dbe7f 1063 'duration': 10,
dbdaaa23 1064 'view_count': int,
3e7c1224 1065 'like_count': int,
ff9f925b 1066 'availability': 'public',
1067 'playable_in_embed': True,
1068 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1069 'live_status': 'not_live',
1070 'age_limit': 0,
7c80519c 1071 'start_time': 1,
297a564b 1072 'end_time': 9,
12a1b225 1073 'comment_count': int,
6c73052c 1074 'channel_follower_count': int
2eb88d95 1075 }
0e853ca4 1076 },
fccd3771 1077 {
4bc3a23e
PH
1078 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1079 'note': 'Embed-only video (#1746)',
1080 'info_dict': {
1081 'id': 'yZIXLfi8CZQ',
1082 'ext': 'mp4',
1083 'upload_date': '20120608',
1084 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1085 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1086 'uploader': 'SET India',
94bfcd23 1087 'uploader_id': 'setindia',
ec85ded8 1088 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1089 'age_limit': 18,
545cc85d 1090 },
1091 'skip': 'Private video',
fccd3771 1092 },
11b56058 1093 {
8bdd16b4 1094 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1095 'note': 'Use the first video ID in the URL',
1096 'info_dict': {
1097 'id': 'BaW_jenozKc',
1098 'ext': 'mp4',
3867038a 1099 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1100 'uploader': 'Philipp Hagemeister',
1101 'uploader_id': 'phihag',
ec85ded8 1102 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1103 'channel': 'Philipp Hagemeister',
1104 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1105 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1106 'upload_date': '20121002',
976ae3ea 1107 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1108 'categories': ['Science & Technology'],
3867038a 1109 'tags': ['youtube-dl'],
556dbe7f 1110 'duration': 10,
dbdaaa23 1111 'view_count': int,
11b56058 1112 'like_count': int,
976ae3ea 1113 'availability': 'public',
1114 'playable_in_embed': True,
1115 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1116 'live_status': 'not_live',
1117 'age_limit': 0,
12a1b225 1118 'comment_count': int,
6c73052c 1119 'channel_follower_count': int
34a7de29
S
1120 },
1121 'params': {
1122 'skip_download': True,
1123 },
11b56058 1124 },
dd27fd17 1125 {
2d3d2997 1126 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1127 'note': '256k DASH audio (format 141) via DASH manifest',
1128 'info_dict': {
1129 'id': 'a9LDPn-MO4I',
1130 'ext': 'm4a',
1131 'upload_date': '20121002',
1132 'uploader_id': '8KVIDEO',
ec85ded8 1133 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1134 'description': '',
1135 'uploader': '8KVIDEO',
1136 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1137 },
4bc3a23e
PH
1138 'params': {
1139 'youtube_include_dash_manifest': True,
1140 'format': '141',
4919603f 1141 },
de3c7fe0 1142 'skip': 'format 141 not served anymore',
dd27fd17 1143 },
8bdd16b4 1144 # DASH manifest with encrypted signature
1145 {
1146 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1147 'info_dict': {
1148 'id': 'IB3lcPjvWLA',
1149 'ext': 'm4a',
1150 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1151 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1152 'duration': 244,
1153 'uploader': 'AfrojackVEVO',
1154 'uploader_id': 'AfrojackVEVO',
1155 'upload_date': '20131011',
cc2db878 1156 'abr': 129.495,
976ae3ea 1157 'like_count': int,
1158 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1159 'playable_in_embed': True,
1160 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1161 'view_count': int,
1162 'track': 'The Spark',
1163 'live_status': 'not_live',
1164 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1165 'channel': 'Afrojack',
1166 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1167 'tags': 'count:19',
1168 'availability': 'public',
1169 'categories': ['Music'],
1170 'age_limit': 0,
1171 'alt_title': 'The Spark',
6c73052c 1172 'channel_follower_count': int
8bdd16b4 1173 },
1174 'params': {
1175 'youtube_include_dash_manifest': True,
1176 'format': '141/bestaudio[ext=m4a]',
1177 },
1178 },
65c2fde2 1179 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1180 {
65c2fde2 1181 'note': 'Embed allowed age-gate video',
2d3d2997 1182 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1183 'info_dict': {
1184 'id': 'HtVdAasjOgU',
1185 'ext': 'mp4',
1186 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1187 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1188 'duration': 142,
c522adb1
JMF
1189 'uploader': 'The Witcher',
1190 'uploader_id': 'WitcherGame',
ec85ded8 1191 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1192 'upload_date': '20140605',
34952f09 1193 'age_limit': 18,
976ae3ea 1194 'categories': ['Gaming'],
1195 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1196 'availability': 'needs_auth',
1197 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1198 'like_count': int,
1199 'channel': 'The Witcher',
1200 'live_status': 'not_live',
1201 'tags': 'count:17',
1202 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1203 'playable_in_embed': True,
1204 'view_count': int,
6c73052c 1205 'channel_follower_count': int
c522adb1
JMF
1206 },
1207 },
65c2fde2 1208 {
1209 'note': 'Age-gate video with embed allowed in public site',
1210 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1211 'info_dict': {
1212 'id': 'HsUATh_Nc2U',
1213 'ext': 'mp4',
1214 'title': 'Godzilla 2 (Official Video)',
1215 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1216 'upload_date': '20200408',
1217 'uploader_id': 'FlyingKitty900',
1218 'uploader': 'FlyingKitty',
1219 'age_limit': 18,
976ae3ea 1220 'availability': 'needs_auth',
1221 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1222 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1223 'channel': 'FlyingKitty',
1224 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1225 'view_count': int,
1226 'categories': ['Entertainment'],
1227 'live_status': 'not_live',
1228 'tags': ['Flyingkitty', 'godzilla 2'],
1229 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1230 'like_count': int,
1231 'duration': 177,
1232 'playable_in_embed': True,
6c73052c 1233 'channel_follower_count': int
65c2fde2 1234 },
1235 },
1236 {
1237 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1238 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1239 'info_dict': {
1240 'id': 'Tq92D6wQ1mg',
1241 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1242 'ext': 'mp4',
17322130 1243 'upload_date': '20191228',
65c2fde2 1244 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1245 'uploader': 'Projekt Melody',
1246 'description': 'md5:17eccca93a786d51bc67646756894066',
1247 'age_limit': 18,
976ae3ea 1248 'like_count': int,
1249 'availability': 'needs_auth',
1250 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1251 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1252 'view_count': int,
1253 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1254 'channel': 'Projekt Melody',
1255 'live_status': 'not_live',
1256 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1257 'playable_in_embed': True,
1258 'categories': ['Entertainment'],
1259 'duration': 106,
1260 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1261 'comment_count': int,
6c73052c 1262 'channel_follower_count': int
65c2fde2 1263 },
1264 },
1265 {
1266 'note': 'Non-Agegated non-embeddable video',
1267 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1268 'info_dict': {
1269 'id': 'MeJVWBSsPAY',
1270 'ext': 'mp4',
1271 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1272 'uploader': 'Herr Lurik',
1273 'uploader_id': 'st3in234',
1274 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1275 'upload_date': '20130730',
976ae3ea 1276 'track': 'Such mich find mich',
1277 'age_limit': 0,
1278 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1279 'like_count': int,
1280 'playable_in_embed': False,
1281 'creator': 'OOMPH!',
1282 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1283 'view_count': int,
1284 'alt_title': 'Such mich find mich',
1285 'duration': 210,
1286 'channel': 'Herr Lurik',
1287 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1288 'categories': ['Music'],
1289 'availability': 'public',
1290 'uploader_url': 'http://www.youtube.com/user/st3in234',
1291 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1292 'live_status': 'not_live',
1293 'artist': 'OOMPH!',
6c73052c 1294 'channel_follower_count': int
65c2fde2 1295 },
1296 },
1297 {
1298 'note': 'Non-bypassable age-gated video',
1299 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1300 'only_matching': True,
1301 },
8bdd16b4 1302 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1303 # YouTube Red ad is not captured for creator
1304 {
1305 'url': '__2ABJjxzNo',
1306 'info_dict': {
1307 'id': '__2ABJjxzNo',
1308 'ext': 'mp4',
1309 'duration': 266,
1310 'upload_date': '20100430',
1311 'uploader_id': 'deadmau5',
1312 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1313 'creator': 'deadmau5',
1314 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1315 'uploader': 'deadmau5',
1316 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1317 'alt_title': 'Some Chords',
976ae3ea 1318 'availability': 'public',
1319 'tags': 'count:14',
1320 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1321 'view_count': int,
1322 'live_status': 'not_live',
1323 'channel': 'deadmau5',
1324 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1325 'like_count': int,
1326 'track': 'Some Chords',
1327 'artist': 'deadmau5',
1328 'playable_in_embed': True,
1329 'age_limit': 0,
1330 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1331 'categories': ['Music'],
1332 'album': 'Some Chords',
6c73052c 1333 'channel_follower_count': int
8bdd16b4 1334 },
1335 'expected_warnings': [
1336 'DASH manifest missing',
1337 ]
1338 },
067aa17e 1339 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1340 {
1341 'url': 'lqQg6PlCWgI',
1342 'info_dict': {
1343 'id': 'lqQg6PlCWgI',
1344 'ext': 'mp4',
556dbe7f 1345 'duration': 6085,
90227264 1346 'upload_date': '20150827',
cbe2bd91 1347 'uploader_id': 'olympic',
ec85ded8 1348 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
12a1b225 1349 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
11f9be09 1350 'uploader': 'Olympics',
cbe2bd91 1351 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1352 'like_count': int,
1353 'release_timestamp': 1343767800,
1354 'playable_in_embed': True,
1355 'categories': ['Sports'],
1356 'release_date': '20120731',
1357 'channel': 'Olympics',
1358 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1359 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1360 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1361 'age_limit': 0,
1362 'availability': 'public',
1363 'live_status': 'was_live',
1364 'view_count': int,
1365 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1366 'channel_follower_count': int
cbe2bd91
PH
1367 },
1368 'params': {
1369 'skip_download': 'requires avconv',
e52a40ab 1370 }
cbe2bd91 1371 },
6271f1ca
PH
1372 # Non-square pixels
1373 {
1374 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1375 'info_dict': {
1376 'id': '_b-2C3KPAM0',
1377 'ext': 'mp4',
1378 'stretched_ratio': 16 / 9.,
556dbe7f 1379 'duration': 85,
6271f1ca
PH
1380 'upload_date': '20110310',
1381 'uploader_id': 'AllenMeow',
ec85ded8 1382 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1383 '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 1384 'uploader': '孫ᄋᄅ',
6271f1ca 1385 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1386 'playable_in_embed': True,
1387 'channel': '孫ᄋᄅ',
1388 'age_limit': 0,
1389 'tags': 'count:11',
1390 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1391 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1392 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1393 'view_count': int,
1394 'categories': ['People & Blogs'],
1395 'like_count': int,
1396 'live_status': 'not_live',
1397 'availability': 'unlisted',
12a1b225 1398 'comment_count': int,
6c73052c 1399 'channel_follower_count': int
6271f1ca 1400 },
06b491eb
S
1401 },
1402 # url_encoded_fmt_stream_map is empty string
1403 {
1404 'url': 'qEJwOuvDf7I',
1405 'info_dict': {
1406 'id': 'qEJwOuvDf7I',
f57b7835 1407 'ext': 'webm',
06b491eb
S
1408 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1409 'description': '',
1410 'upload_date': '20150404',
1411 'uploader_id': 'spbelect',
1412 'uploader': 'Наблюдатели Петербурга',
1413 },
1414 'params': {
1415 'skip_download': 'requires avconv',
e323cf3f
S
1416 },
1417 'skip': 'This live event has ended.',
06b491eb 1418 },
067aa17e 1419 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1420 {
1421 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1422 'info_dict': {
1423 'id': 'FIl7x6_3R5Y',
eb6793ba 1424 'ext': 'webm',
da77d856
S
1425 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1426 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1427 'duration': 220,
da77d856
S
1428 'upload_date': '20150625',
1429 'uploader_id': 'dorappi2000',
ec85ded8 1430 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1431 'uploader': 'dorappi2000',
eb6793ba 1432 'formats': 'mincount:31',
da77d856 1433 },
eb6793ba 1434 'skip': 'not actual anymore',
2ee8f5d8 1435 },
8a1a26ce
YCH
1436 # DASH manifest with segment_list
1437 {
1438 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1439 'md5': '8ce563a1d667b599d21064e982ab9e31',
1440 'info_dict': {
1441 'id': 'CsmdDsKjzN8',
1442 'ext': 'mp4',
17ee98e1 1443 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1444 'uploader': 'Airtek',
1445 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1446 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1447 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1448 },
1449 'params': {
1450 'youtube_include_dash_manifest': True,
1451 'format': '135', # bestvideo
be49068d
S
1452 },
1453 'skip': 'This live event has ended.',
2ee8f5d8 1454 },
cf7e015f
S
1455 {
1456 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1457 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1458 'info_dict': {
545cc85d 1459 'id': 'jvGDaLqkpTg',
1460 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1461 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1462 },
1463 'playlist': [{
1464 'info_dict': {
545cc85d 1465 'id': 'jvGDaLqkpTg',
cf7e015f 1466 'ext': 'mp4',
545cc85d 1467 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1468 'description': 'md5:e03b909557865076822aa169218d6a5d',
1469 'duration': 10643,
1470 'upload_date': '20161111',
1471 'uploader': 'Team PGP',
1472 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1473 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1474 },
1475 }, {
1476 'info_dict': {
545cc85d 1477 'id': '3AKt1R1aDnw',
cf7e015f 1478 'ext': 'mp4',
545cc85d 1479 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1480 'description': 'md5:e03b909557865076822aa169218d6a5d',
1481 'duration': 10991,
1482 'upload_date': '20161111',
1483 'uploader': 'Team PGP',
1484 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1485 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1486 },
1487 }, {
1488 'info_dict': {
545cc85d 1489 'id': 'RtAMM00gpVc',
cf7e015f 1490 'ext': 'mp4',
545cc85d 1491 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1492 'description': 'md5:e03b909557865076822aa169218d6a5d',
1493 'duration': 10995,
1494 'upload_date': '20161111',
1495 'uploader': 'Team PGP',
1496 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1497 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1498 },
1499 }, {
1500 'info_dict': {
545cc85d 1501 'id': '6N2fdlP3C5U',
cf7e015f 1502 'ext': 'mp4',
545cc85d 1503 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1504 'description': 'md5:e03b909557865076822aa169218d6a5d',
1505 'duration': 10990,
1506 'upload_date': '20161111',
1507 'uploader': 'Team PGP',
1508 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1509 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1510 },
1511 }],
1512 'params': {
1513 'skip_download': True,
1514 },
65c2fde2 1515 'skip': 'Not multifeed anymore',
cbaed4bb 1516 },
f9f49d87 1517 {
067aa17e 1518 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1519 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1520 'info_dict': {
1521 'id': 'gVfLd0zydlo',
1522 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1523 },
1524 'playlist_count': 2,
be49068d 1525 'skip': 'Not multifeed anymore',
f9f49d87 1526 },
cbaed4bb 1527 {
2d3d2997 1528 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1529 'only_matching': True,
0e49d9a6 1530 },
6d4fc66b 1531 {
2d3d2997 1532 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1533 'only_matching': True,
1534 },
0e49d9a6 1535 {
067aa17e 1536 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1537 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1538 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1539 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1540 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1541 'info_dict': {
1542 'id': 'lsguqyKfVQg',
1543 'ext': 'mp4',
1544 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1545 'alt_title': 'Dark Walk',
0e49d9a6 1546 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1547 'duration': 133,
0e49d9a6
LL
1548 'upload_date': '20151119',
1549 'uploader_id': 'IronSoulElf',
ec85ded8 1550 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1551 'uploader': 'IronSoulElf',
11f9be09 1552 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1553 'track': 'Dark Walk',
1554 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1555 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1556 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1557 'categories': ['Film & Animation'],
1558 'view_count': int,
1559 'live_status': 'not_live',
1560 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1561 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1562 'tags': 'count:13',
1563 'availability': 'public',
1564 'channel': 'IronSoulElf',
1565 'playable_in_embed': True,
1566 'like_count': int,
1567 'age_limit': 0,
6c73052c 1568 'channel_follower_count': int
0e49d9a6
LL
1569 },
1570 'params': {
1571 'skip_download': True,
1572 },
1573 },
61f92af1 1574 {
067aa17e 1575 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1576 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1577 'only_matching': True,
1578 },
313dfc45
LL
1579 {
1580 # Video with yt:stretch=17:0
1581 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1582 'info_dict': {
1583 'id': 'Q39EVAstoRM',
1584 'ext': 'mp4',
1585 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1586 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1587 'upload_date': '20151107',
1588 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1589 'uploader': 'CH GAMER DROID',
1590 },
1591 'params': {
1592 'skip_download': True,
1593 },
be49068d 1594 'skip': 'This video does not exist.',
313dfc45 1595 },
201c1459 1596 {
1597 # Video with incomplete 'yt:stretch=16:'
1598 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1599 'only_matching': True,
1600 },
7caf9830
S
1601 {
1602 # Video licensed under Creative Commons
1603 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1604 'info_dict': {
1605 'id': 'M4gD1WSo5mA',
1606 'ext': 'mp4',
1607 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1608 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1609 'duration': 721,
17322130 1610 'upload_date': '20150128',
7caf9830 1611 'uploader_id': 'BerkmanCenter',
ec85ded8 1612 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1613 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1614 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1615 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1616 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1617 'like_count': int,
1618 'age_limit': 0,
1619 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1620 'channel': 'The Berkman Klein Center for Internet & Society',
1621 'availability': 'public',
1622 'view_count': int,
1623 'categories': ['Education'],
1624 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1625 'live_status': 'not_live',
1626 'playable_in_embed': True,
12a1b225 1627 'comment_count': int,
6c73052c 1628 'channel_follower_count': int
7caf9830
S
1629 },
1630 'params': {
1631 'skip_download': True,
1632 },
1633 },
fd050249
S
1634 {
1635 # Channel-like uploader_url
1636 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1637 'info_dict': {
1638 'id': 'eQcmzGIKrzg',
1639 'ext': 'mp4',
1640 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1641 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1642 'duration': 4060,
17322130 1643 'upload_date': '20151120',
eb6793ba 1644 'uploader': 'Bernie Sanders',
fd050249 1645 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1646 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1647 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1648 'playable_in_embed': True,
1649 'tags': 'count:12',
1650 'like_count': int,
1651 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1652 'age_limit': 0,
1653 'availability': 'public',
1654 'categories': ['News & Politics'],
1655 'channel': 'Bernie Sanders',
1656 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1657 'view_count': int,
1658 'live_status': 'not_live',
1659 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1660 'comment_count': int,
6c73052c 1661 'channel_follower_count': int
fd050249
S
1662 },
1663 'params': {
1664 'skip_download': True,
1665 },
1666 },
040ac686
S
1667 {
1668 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1669 'only_matching': True,
7f29cf54
S
1670 },
1671 {
067aa17e 1672 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1673 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1674 'only_matching': True,
6496ccb4
S
1675 },
1676 {
1677 # Rental video preview
1678 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1679 'info_dict': {
1680 'id': 'uGpuVWrhIzE',
1681 'ext': 'mp4',
1682 'title': 'Piku - Trailer',
1683 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1684 'upload_date': '20150811',
1685 'uploader': 'FlixMatrix',
1686 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1687 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1688 'license': 'Standard YouTube License',
1689 },
1690 'params': {
1691 'skip_download': True,
1692 },
eb6793ba 1693 'skip': 'This video is not available.',
022a5d66 1694 },
12afdc2a
S
1695 {
1696 # YouTube Red video with episode data
1697 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1698 'info_dict': {
1699 'id': 'iqKdEhx-dD4',
1700 'ext': 'mp4',
1701 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1702 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1703 'duration': 2085,
12afdc2a
S
1704 'upload_date': '20170118',
1705 'uploader': 'Vsauce',
1706 'uploader_id': 'Vsauce',
1707 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1708 'series': 'Mind Field',
1709 'season_number': 1,
1710 'episode_number': 1,
976ae3ea 1711 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1712 'tags': 'count:12',
1713 'view_count': int,
1714 'availability': 'public',
1715 'age_limit': 0,
1716 'channel': 'Vsauce',
1717 'episode': 'Episode 1',
1718 'categories': ['Entertainment'],
1719 'season': 'Season 1',
1720 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1721 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1722 'like_count': int,
1723 'playable_in_embed': True,
1724 'live_status': 'not_live',
6c73052c 1725 'channel_follower_count': int
12afdc2a
S
1726 },
1727 'params': {
1728 'skip_download': True,
1729 },
1730 'expected_warnings': [
1731 'Skipping DASH manifest',
1732 ],
1733 },
c7121fa7
S
1734 {
1735 # The following content has been identified by the YouTube community
1736 # as inappropriate or offensive to some audiences.
1737 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1738 'info_dict': {
1739 'id': '6SJNVb0GnPI',
1740 'ext': 'mp4',
1741 'title': 'Race Differences in Intelligence',
1742 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1743 'duration': 965,
1744 'upload_date': '20140124',
1745 'uploader': 'New Century Foundation',
1746 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1747 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1748 },
1749 'params': {
1750 'skip_download': True,
1751 },
545cc85d 1752 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1753 },
022a5d66
S
1754 {
1755 # itag 212
1756 'url': '1t24XAntNCY',
1757 'only_matching': True,
fd5c4aab
S
1758 },
1759 {
1760 # geo restricted to JP
1761 'url': 'sJL6WA-aGkQ',
1762 'only_matching': True,
1763 },
cd5a74a2
S
1764 {
1765 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1766 'only_matching': True,
1767 },
bc2ca1bb 1768 {
1769 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1770 'only_matching': True,
1771 },
1772 {
1773 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1774 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1775 'only_matching': True,
1776 },
825cd268
RA
1777 {
1778 # DRM protected
1779 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1780 'only_matching': True,
4fe54c12
S
1781 },
1782 {
1783 # Video with unsupported adaptive stream type formats
1784 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1785 'info_dict': {
1786 'id': 'Z4Vy8R84T1U',
1787 'ext': 'mp4',
1788 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1789 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1790 'duration': 433,
1791 'upload_date': '20130923',
1792 'uploader': 'Amelia Putri Harwita',
1793 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1794 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1795 'formats': 'maxcount:10',
1796 },
1797 'params': {
1798 'skip_download': True,
1799 'youtube_include_dash_manifest': False,
1800 },
5429d6a9 1801 'skip': 'not actual anymore',
5caabd3c 1802 },
1803 {
822b9d9c 1804 # Youtube Music Auto-generated description
5caabd3c 1805 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1806 'info_dict': {
1807 'id': 'MgNrAu2pzNs',
1808 'ext': 'mp4',
1809 'title': 'Voyeur Girl',
1810 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1811 'upload_date': '20190312',
5429d6a9
S
1812 'uploader': 'Stephen - Topic',
1813 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1814 'artist': 'Stephen',
1815 'track': 'Voyeur Girl',
1816 'album': 'it\'s too much love to know my dear',
1817 'release_date': '20190313',
1818 'release_year': 2019,
976ae3ea 1819 'alt_title': 'Voyeur Girl',
1820 'view_count': int,
1821 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1822 'playable_in_embed': True,
1823 'like_count': int,
1824 'categories': ['Music'],
1825 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1826 'channel': 'Stephen',
1827 'availability': 'public',
1828 'creator': 'Stephen',
1829 'duration': 169,
1830 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1831 'age_limit': 0,
1832 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1833 'tags': 'count:11',
1834 'live_status': 'not_live',
6c73052c 1835 'channel_follower_count': int
5caabd3c 1836 },
1837 'params': {
1838 'skip_download': True,
1839 },
1840 },
66b48727
RA
1841 {
1842 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1843 'only_matching': True,
1844 },
011e75e6
S
1845 {
1846 # invalid -> valid video id redirection
1847 'url': 'DJztXj2GPfl',
1848 'info_dict': {
1849 'id': 'DJztXj2GPfk',
1850 'ext': 'mp4',
1851 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1852 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1853 'upload_date': '20090125',
1854 'uploader': 'Prochorowka',
1855 'uploader_id': 'Prochorowka',
1856 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1857 'artist': 'Panjabi MC',
1858 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1859 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1860 },
1861 'params': {
1862 'skip_download': True,
1863 },
545cc85d 1864 'skip': 'Video unavailable',
ea74e00b
DP
1865 },
1866 {
1867 # empty description results in an empty string
1868 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1869 'info_dict': {
1870 'id': 'x41yOUIvK2k',
1871 'ext': 'mp4',
1872 'title': 'IMG 3456',
1873 'description': '',
1874 'upload_date': '20170613',
1875 'uploader_id': 'ElevageOrVert',
1876 'uploader': 'ElevageOrVert',
976ae3ea 1877 'view_count': int,
1878 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1879 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1880 'like_count': int,
1881 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1882 'tags': [],
1883 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1884 'availability': 'public',
1885 'age_limit': 0,
1886 'categories': ['Pets & Animals'],
1887 'duration': 7,
1888 'playable_in_embed': True,
1889 'live_status': 'not_live',
1890 'channel': 'ElevageOrVert',
6c73052c 1891 'channel_follower_count': int
ea74e00b
DP
1892 },
1893 'params': {
1894 'skip_download': True,
1895 },
1896 },
a0566bbf 1897 {
29f7c58a 1898 # with '};' inside yt initial data (see [1])
1899 # see [2] for an example with '};' inside ytInitialPlayerResponse
1900 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1901 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1902 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1903 'info_dict': {
1904 'id': 'CHqg6qOn4no',
1905 'ext': 'mp4',
1906 'title': 'Part 77 Sort a list of simple types in c#',
1907 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1908 'upload_date': '20130831',
1909 'uploader_id': 'kudvenkat',
1910 'uploader': 'kudvenkat',
976ae3ea 1911 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1912 'like_count': int,
1913 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1914 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1915 'live_status': 'not_live',
1916 'categories': ['Education'],
1917 'availability': 'public',
1918 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1919 'tags': 'count:12',
1920 'playable_in_embed': True,
1921 'age_limit': 0,
1922 'view_count': int,
1923 'duration': 522,
1924 'channel': 'kudvenkat',
12a1b225 1925 'comment_count': int,
6c73052c 1926 'channel_follower_count': int
a0566bbf 1927 },
1928 'params': {
1929 'skip_download': True,
1930 },
1931 },
29f7c58a 1932 {
1933 # another example of '};' in ytInitialData
1934 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1935 'only_matching': True,
1936 },
1937 {
1938 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1939 'only_matching': True,
1940 },
545cc85d 1941 {
cc2db878 1942 # https://github.com/ytdl-org/youtube-dl/pull/28094
1943 'url': 'OtqTfy26tG0',
1944 'info_dict': {
1945 'id': 'OtqTfy26tG0',
1946 'ext': 'mp4',
1947 'title': 'Burn Out',
1948 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1949 'upload_date': '20141120',
1950 'uploader': 'The Cinematic Orchestra - Topic',
1951 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1952 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1953 'artist': 'The Cinematic Orchestra',
1954 'track': 'Burn Out',
1955 'album': 'Every Day',
976ae3ea 1956 'like_count': int,
1957 'live_status': 'not_live',
1958 'alt_title': 'Burn Out',
1959 'duration': 614,
1960 'age_limit': 0,
1961 'view_count': int,
1962 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1963 'creator': 'The Cinematic Orchestra',
1964 'channel': 'The Cinematic Orchestra',
1965 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1966 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1967 'availability': 'public',
1968 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1969 'categories': ['Music'],
1970 'playable_in_embed': True,
6c73052c 1971 'channel_follower_count': int
cc2db878 1972 },
1973 'params': {
1974 'skip_download': True,
1975 },
545cc85d 1976 },
bc2ca1bb 1977 {
1978 # controversial video, only works with bpctr when authenticated with cookies
1979 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1980 'only_matching': True,
1981 },
a1a7907b 1982 {
1983 # controversial video, requires bpctr/contentCheckOk
1984 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1985 'info_dict': {
1986 'id': 'SZJvDhaSDnc',
1987 'ext': 'mp4',
1988 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1989 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1990 'uploader': 'CBS Mornings',
11f9be09 1991 'uploader_id': 'CBSThisMorning',
a1a7907b 1992 'upload_date': '20140716',
976ae3ea 1993 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1994 'duration': 170,
1995 'categories': ['News & Politics'],
1996 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1997 'view_count': int,
1998 'channel': 'CBS Mornings',
1999 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2000 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2001 'age_limit': 18,
2002 'availability': 'needs_auth',
2003 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2004 'like_count': int,
2005 'live_status': 'not_live',
2006 'playable_in_embed': True,
6c73052c 2007 'channel_follower_count': int
a1a7907b 2008 }
2009 },
f7ad7160 2010 {
2011 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2012 'url': 'cBvYw8_A0vQ',
2013 'info_dict': {
2014 'id': 'cBvYw8_A0vQ',
2015 'ext': 'mp4',
2016 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2017 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2018 'upload_date': '20201120',
2019 'uploader': 'Walk around Japan',
2020 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2021 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2022 'duration': 1456,
2023 'categories': ['Travel & Events'],
2024 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2025 'view_count': int,
2026 'channel': 'Walk around Japan',
2027 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2028 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2029 'age_limit': 0,
2030 'availability': 'public',
2031 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2032 'live_status': 'not_live',
2033 'playable_in_embed': True,
6c73052c 2034 'channel_follower_count': int
f7ad7160 2035 },
2036 'params': {
2037 'skip_download': True,
2038 },
0fb983f6 2039 }, {
2040 # Has multiple audio streams
2041 'url': 'WaOKSUlf4TM',
2042 'only_matching': True
9297939e 2043 }, {
2044 # Requires Premium: has format 141 when requested using YTM url
2045 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2046 'only_matching': True
2047 }, {
120916da 2048 # multiple subtitles with same lang_code
2049 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2050 'only_matching': True,
109dd3b2 2051 }, {
2052 # Force use android client fallback
2053 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2054 'info_dict': {
2055 'id': 'YOelRv7fMxY',
11f9be09 2056 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2057 'ext': '3gp',
2058 'upload_date': '20210624',
2059 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2060 'uploader': 'colinfurze',
11f9be09 2061 'uploader_id': 'colinfurze',
109dd3b2 2062 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2063 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2064 'duration': 596,
2065 'categories': ['Entertainment'],
2066 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2067 'view_count': int,
2068 'channel': 'colinfurze',
2069 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2070 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2071 'age_limit': 0,
2072 'availability': 'public',
2073 'like_count': int,
2074 'live_status': 'not_live',
2075 'playable_in_embed': True,
6c73052c 2076 'channel_follower_count': int
109dd3b2 2077 },
2078 'params': {
2079 'format': '17', # 3gp format available on android
2080 'extractor_args': {'youtube': {'player_client': ['android']}},
2081 },
120916da 2082 },
109dd3b2 2083 {
2084 # Skip download of additional client configs (remix client config in this case)
2085 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2086 'only_matching': True,
2087 'params': {
2088 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2089 },
8fc54b12 2090 }, {
2091 # shorts
2092 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2093 'only_matching': True,
9222c381 2094 }, {
2095 'note': 'Storyboards',
2096 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2097 'info_dict': {
2098 'id': '5KLPxDtMqe8',
2099 'ext': 'mhtml',
2100 'format_id': 'sb0',
2101 'title': 'Your Brain is Plastic',
2102 'uploader_id': 'scishow',
2103 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2104 'upload_date': '20140324',
2105 'uploader': 'SciShow',
976ae3ea 2106 'like_count': int,
2107 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2108 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2109 'view_count': int,
2110 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2111 'playable_in_embed': True,
2112 'tags': 'count:12',
2113 'uploader_url': 'http://www.youtube.com/user/scishow',
2114 'availability': 'public',
2115 'channel': 'SciShow',
2116 'live_status': 'not_live',
2117 'duration': 248,
2118 'categories': ['Education'],
2119 'age_limit': 0,
6c73052c 2120 'channel_follower_count': int
9222c381 2121 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2122 }, {
2123 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2124 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2125 'info_dict': {
2126 'id': '2NUZ8W2llS4',
2127 'ext': 'mp4',
2128 'title': 'The NP that test your phone performance 🙂',
2129 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2130 'uploader': 'Leon Nguyen',
2131 'uploader_id': 'VNSXIII',
2132 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2133 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2134 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2135 'duration': 21,
2136 'view_count': int,
2137 'age_limit': 0,
2138 'categories': ['Gaming'],
2139 'tags': 'count:23',
2140 'playable_in_embed': True,
2141 'live_status': 'not_live',
2142 'upload_date': '20220103',
2143 'like_count': int,
2144 'availability': 'public',
2145 'channel': 'Leon Nguyen',
2146 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2147 'comment_count': int,
992f9a73 2148 'channel_follower_count': int
2149 }
2150 }, {
2151 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2152 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2153 'info_dict': {
2154 'id': 'mzZzzBU6lrM',
2155 'ext': 'mp4',
2156 'title': 'I Met GeorgeNotFound In Real Life...',
2157 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2158 'uploader': 'Quackity',
2159 'uploader_id': 'QuackityHQ',
2160 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2161 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2162 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2163 'duration': 955,
2164 'view_count': int,
2165 'age_limit': 0,
2166 'categories': ['Entertainment'],
2167 'tags': 'count:26',
2168 'playable_in_embed': True,
2169 'live_status': 'not_live',
2170 'release_timestamp': 1641172509,
2171 'release_date': '20220103',
2172 'upload_date': '20220103',
2173 'like_count': int,
2174 'availability': 'public',
2175 'channel': 'Quackity',
2176 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2177 'channel_follower_count': int
2178 }
2179 },
2180 { # continuous livestream. Microformat upload date should be preferred.
2181 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2182 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2183 'info_dict': {
2184 'id': 'kgx4WGK0oNU',
2185 '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}',
2186 'ext': 'mp4',
2187 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2188 'availability': 'public',
2189 'age_limit': 0,
2190 'release_timestamp': 1637975704,
2191 'upload_date': '20210619',
2192 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2193 'live_status': 'is_live',
2194 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2195 'uploader': '阿鲍Abao',
2196 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2197 'channel': 'Abao in Tokyo',
2198 'channel_follower_count': int,
2199 'release_date': '20211127',
2200 'tags': 'count:39',
2201 'categories': ['People & Blogs'],
2202 'like_count': int,
2203 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2204 'view_count': int,
2205 'playable_in_embed': True,
2206 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2207 },
2208 'params': {'skip_download': True}
6e634cbe 2209 }, {
2210 # Story. Requires specific player params to work.
ee27297f 2211 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2212 'info_dict': {
ee27297f 2213 'id': 'vv8qTUWmulI',
6e634cbe 2214 'ext': 'mp4',
ee27297f 2215 'availability': 'unlisted',
2216 'view_count': int,
2217 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2218 'upload_date': '20220526',
2219 'categories': ['Education'],
2220 'title': 'Story',
2221 'channel': 'IT\'S HISTORY',
2222 'description': '',
2223 'uploader_id': 'BlastfromthePast',
2224 'duration': 12,
2225 'uploader': 'IT\'S HISTORY',
6e634cbe 2226 'playable_in_embed': True,
6e634cbe 2227 'age_limit': 0,
6e634cbe 2228 'live_status': 'not_live',
ee27297f 2229 'tags': [],
2230 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2231 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2232 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
12a1b225
A
2233 },
2234 'skip': 'stories get removed after some period of time',
ee27297f 2235 }, {
2236 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2237 'info_dict': {
2238 'id': 'tjjjtzRLHvA',
2239 'ext': 'mp4',
2240 'title': 'ハッシュタグ無し };if window.ytcsi',
2241 'upload_date': '20220323',
2242 'like_count': int,
2243 'availability': 'unlisted',
2244 'channel': 'nao20010128nao',
2245 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2246 'age_limit': 0,
2247 'uploader': 'nao20010128nao',
2248 'uploader_id': 'nao20010128nao',
2249 'categories': ['Music'],
6e634cbe 2250 'view_count': int,
2251 'description': '',
ee27297f 2252 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2253 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2254 'live_status': 'not_live',
2255 'playable_in_embed': True,
2256 'channel_follower_count': int,
2257 'duration': 6,
2258 'tags': [],
2259 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2260 }
a4166234 2261 }, {
2262 'note': '6 channel audio',
2263 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2264 'only_matching': True,
6e634cbe 2265 }
2eb88d95
PH
2266 ]
2267
f2e8dbcc 2268 _WEBPAGE_TESTS = [
2269 # YouTube <object> embed
2270 {
2271 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2272 'md5': '873c81d308b979f0e23ee7e620b312a3',
2273 'info_dict': {
2274 'id': 'msN87y-iEx0',
2275 'ext': 'mp4',
2276 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2277 'upload_date': '20080526',
2278 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2279 'uploader': 'Christopher Sykes',
2280 'uploader_id': 'ChristopherJSykes',
2281 'age_limit': 0,
2282 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2283 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2284 'playable_in_embed': True,
2285 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2286 'like_count': int,
2287 'comment_count': int,
2288 'channel': 'Christopher Sykes',
2289 'live_status': 'not_live',
2290 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2291 'availability': 'public',
2292 'duration': 195,
2293 'view_count': int,
2294 'categories': ['Science & Technology'],
2295 'channel_follower_count': int,
2296 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2297 },
2298 'params': {
2299 'skip_download': True,
2300 }
2301 },
2302 ]
2303
201c1459 2304 @classmethod
2305 def suitable(cls, url):
4dfbf869 2306 from ..utils import parse_qs
2307
201c1459 2308 qs = parse_qs(url)
2309 if qs.get('list', [None])[0]:
2310 return False
86e5f3ed 2311 return super().suitable(url)
201c1459 2312
e0df6211 2313 def __init__(self, *args, **kwargs):
86e5f3ed 2314 super().__init__(*args, **kwargs)
545cc85d 2315 self._code_cache = {}
83799698 2316 self._player_cache = {}
e0df6211 2317
adbc4ec4 2318 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2319 lock = threading.Lock()
2320
2321 is_live = True
185bf310 2322 start_time = time.time()
adbc4ec4
THD
2323 formats = [f for f in formats if f.get('is_from_start')]
2324
185bf310 2325 def refetch_manifest(format_id, delay):
2326 nonlocal formats, start_time, is_live
2327 if time.time() <= start_time + delay:
adbc4ec4
THD
2328 return
2329
2330 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2331 video_details = traverse_obj(
2332 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2333 microformats = traverse_obj(
2334 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2335 expected_type=dict, default=[])
c646d76f 2336 _, is_live, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2337 start_time = time.time()
adbc4ec4 2338
185bf310 2339 def mpd_feed(format_id, delay):
adbc4ec4
THD
2340 """
2341 @returns (manifest_url, manifest_stream_number, is_live) or None
2342 """
2343 with lock:
185bf310 2344 refetch_manifest(format_id, delay)
adbc4ec4
THD
2345
2346 f = next((f for f in formats if f['format_id'] == format_id), None)
2347 if not f:
185bf310 2348 if not is_live:
2349 self.to_screen(f'{video_id}: Video is no longer live')
2350 else:
2351 self.report_warning(
2352 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2353 return None
2354 return f['manifest_url'], f['manifest_stream_number'], is_live
2355
2356 for f in formats:
a539f065 2357 f['is_live'] = True
adbc4ec4
THD
2358 f['protocol'] = 'http_dash_segments_generator'
2359 f['fragments'] = functools.partial(
2360 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2361
2362 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2363 FETCH_SPAN, MAX_DURATION = 5, 432000
2364
2365 mpd_url, stream_number, is_live = None, None, True
2366
2367 begin_index = 0
2368 download_start_time = ctx.get('start') or time.time()
2369
2370 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2371 if lack_early_segments:
2372 self.report_warning(bug_reports_message(
2373 'Starting download from the last 120 hours of the live stream since '
2374 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2375 lack_early_segments = True
2376
2377 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2378 fragments, fragment_base_url = None, None
2379
a539f065 2380 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2381 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2382 # Obtain from MPD's maximum seq value
2383 old_mpd_url = mpd_url
185bf310 2384 last_error = ctx.pop('last_error', None)
14f25df2 2385 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2386 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2387 or (mpd_url, stream_number, False))
2388 if not refresh_sequence:
2389 if expire_fast and not is_live:
2390 return False, last_seq
2391 elif old_mpd_url == mpd_url:
2392 return True, last_seq
adbc4ec4
THD
2393 try:
2394 fmts, _ = self._extract_mpd_formats_and_subtitles(
2395 mpd_url, None, note=False, errnote=False, fatal=False)
2396 except ExtractorError:
2397 fmts = None
2398 if not fmts:
a539f065 2399 no_fragment_score += 2
adbc4ec4
THD
2400 return False, last_seq
2401 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2402 fragments = fmt_info['fragments']
2403 fragment_base_url = fmt_info['fragment_base_url']
2404 assert fragment_base_url
2405
2406 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2407 return True, _last_seq
2408
2409 while is_live:
2410 fetch_time = time.time()
2411 if no_fragment_score > 30:
2412 return
2413 if last_segment_url:
2414 # Obtain from "X-Head-Seqnum" header value from each segment
2415 try:
2416 urlh = self._request_webpage(
2417 last_segment_url, None, note=False, errnote=False, fatal=False)
2418 except ExtractorError:
2419 urlh = None
2420 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2421 if last_seq is None:
a539f065 2422 no_fragment_score += 2
adbc4ec4
THD
2423 last_segment_url = None
2424 continue
2425 else:
a539f065
LNO
2426 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2427 no_fragment_score += 2
185bf310 2428 if not should_continue:
adbc4ec4
THD
2429 continue
2430
2431 if known_idx > last_seq:
2432 last_segment_url = None
2433 continue
2434
2435 last_seq += 1
2436
2437 if begin_index < 0 and known_idx < 0:
2438 # skip from the start when it's negative value
2439 known_idx = last_seq + begin_index
2440 if lack_early_segments:
2441 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2442 try:
2443 for idx in range(known_idx, last_seq):
2444 # do not update sequence here or you'll get skipped some part of it
a539f065 2445 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2446 if not should_continue:
adbc4ec4
THD
2447 known_idx = idx - 1
2448 raise ExtractorError('breaking out of outer loop')
2449 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2450 yield {
2451 'url': last_segment_url,
36195c44 2452 'fragment_count': last_seq,
adbc4ec4
THD
2453 }
2454 if known_idx == last_seq:
2455 no_fragment_score += 5
2456 else:
2457 no_fragment_score = 0
2458 known_idx = last_seq
2459 except ExtractorError:
2460 continue
2461
2462 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2463
b6de707d 2464 def _extract_player_url(self, *ytcfgs, webpage=None):
2465 player_url = traverse_obj(
2466 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2467 get_all=False, expected_type=str)
11f9be09 2468 if not player_url:
b6de707d 2469 return
60f393e4 2470 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2471
b6de707d 2472 def _download_player_url(self, video_id, fatal=False):
2473 res = self._download_webpage(
2474 'https://www.youtube.com/iframe_api',
2475 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2476 if res:
2477 player_version = self._search_regex(
2478 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2479 if player_version:
2480 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2481
60064c53
PH
2482 def _signature_cache_id(self, example_sig):
2483 """ Return a string representation of a signature """
14f25df2 2484 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2485
e40c758c
S
2486 @classmethod
2487 def _extract_player_info(cls, player_url):
2488 for player_re in cls._PLAYER_INFO_RE:
2489 id_m = re.search(player_re, player_url)
2490 if id_m:
2491 break
2492 else:
c081b35c 2493 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2494 return id_m.group('id')
e40c758c 2495
404f611f 2496 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2497 player_id = self._extract_player_info(player_url)
2498 if player_id not in self._code_cache:
1276a43a 2499 code = self._download_webpage(
109dd3b2 2500 player_url, video_id, fatal=fatal,
2501 note='Downloading player ' + player_id,
2502 errnote='Download of %s failed' % player_url)
1276a43a 2503 if code:
2504 self._code_cache[player_id] = code
404f611f 2505 return self._code_cache.get(player_id)
109dd3b2 2506
e40c758c 2507 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2508 player_id = self._extract_player_info(player_url)
e0df6211 2509
c4417ddb 2510 # Read from filesystem cache
86e5f3ed 2511 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2512 assert os.path.basename(func_id) == func_id
a0e07d31 2513
ae61d108 2514 self.write_debug(f'Extracting signature function {func_id}')
9809740b 2515 cache_spec = self.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2516 if cache_spec is not None:
78caa52a 2517 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2518
404f611f 2519 code = self._load_player(video_id, player_url)
2520 if code:
109dd3b2 2521 res = self._parse_sig_js(code)
e0df6211 2522
ac668111 2523 test_string = ''.join(map(chr, range(len(example_sig))))
109dd3b2 2524 cache_res = res(test_string)
2525 cache_spec = [ord(c) for c in cache_res]
83799698 2526
9809740b 2527 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
109dd3b2 2528 return res
83799698 2529
60064c53 2530 def _print_sig_code(self, func, example_sig):
404f611f 2531 if not self.get_param('youtube_print_sig_code'):
2532 return
2533
edf3e38e
PH
2534 def gen_sig_code(idxs):
2535 def _genslice(start, end, step):
78caa52a 2536 starts = '' if start == 0 else str(start)
8bcc8756 2537 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2538 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2539 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2540
2541 step = None
7af808a5
PH
2542 # Quelch pyflakes warnings - start will be set when step is set
2543 start = '(Never used)'
edf3e38e
PH
2544 for i, prev in zip(idxs[1:], idxs[:-1]):
2545 if step is not None:
2546 if i - prev == step:
2547 continue
2548 yield _genslice(start, prev, step)
2549 step = None
2550 continue
2551 if i - prev in [-1, 1]:
2552 step = i - prev
2553 start = prev
2554 continue
2555 else:
78caa52a 2556 yield 's[%d]' % prev
edf3e38e 2557 if step is None:
78caa52a 2558 yield 's[%d]' % i
edf3e38e
PH
2559 else:
2560 yield _genslice(start, i, step)
2561
ac668111 2562 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2563 cache_res = func(test_string)
edf3e38e 2564 cache_spec = [ord(c) for c in cache_res]
78caa52a 2565 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2566 signature_id_tuple = '(%s)' % (
14f25df2 2567 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2568 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2569 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2570 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2571
e0df6211
PH
2572 def _parse_sig_js(self, jscode):
2573 funcname = self._search_regex(
abefc03f
S
2574 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2575 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
2576 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2577 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2578 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}\(a,\d+\)',
2579 r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
31ce6e99 2580 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2581 # Obsolete patterns
2582 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2583 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2584 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2585 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2586 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2587 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2588 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2589 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2590 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2591
2592 jsi = JSInterpreter(jscode)
2593 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2594 return lambda s: initial_function([s])
2595
545cc85d 2596 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2597 """Turn the encrypted s field into a working signature"""
c8bf86d5 2598 try:
62af3a0e 2599 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5 2600 if player_id not in self._player_cache:
52023f12 2601 func = self._extract_signature_function(video_id, player_url, s)
c8bf86d5
PH
2602 self._player_cache[player_id] = func
2603 func = self._player_cache[player_id]
404f611f 2604 self._print_sig_code(func, s)
c8bf86d5
PH
2605 return func(s)
2606 except Exception as e:
52023f12 2607 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2608
2609 def _decrypt_nsig(self, s, video_id, player_url):
2610 """Turn the encrypted n field into a working signature"""
2611 if player_url is None:
2612 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2613 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2614
2615 sig_id = ('nsig_value', s)
2616 if sig_id in self._player_cache:
2617 return self._player_cache[sig_id]
2618
2619 try:
2620 player_id = ('nsig', player_url)
2621 if player_id not in self._player_cache:
2622 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2623 func = self._player_cache[player_id]
2624 self._player_cache[sig_id] = func(s)
2625 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2626 return self._player_cache[sig_id]
2627 except Exception as e:
aa9369a2 2628 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2629
2630 def _extract_n_function_name(self, jscode):
48416bc4 2631 nfunc, idx = self._search_regex(
c571b3a6 2632 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2633 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2634 if not idx:
2635 return nfunc
2636 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2637 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2638 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2639
2640 def _extract_n_function(self, video_id, player_url):
2641 player_id = self._extract_player_info(player_url)
9809740b 2642 func_code = self.cache.load('youtube-nsig', player_id)
404f611f 2643
2644 if func_code:
2645 jsi = JSInterpreter(func_code)
2646 else:
2647 jscode = self._load_player(video_id, player_url)
2648 funcname = self._extract_n_function_name(jscode)
2649 jsi = JSInterpreter(jscode)
2650 func_code = jsi.extract_function_code(funcname)
9809740b 2651 self.cache.store('youtube-nsig', player_id, func_code)
404f611f 2652
2653 if self.get_param('youtube_print_sig_code'):
2654 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
8f53dc44 2655 func = jsi.extract_function_from_code(*func_code)
f6ca640b 2656
2657 def inner(s):
2658 ret = func([s])
2659 if ret.startswith('enhanced_except_'):
2660 raise ExtractorError('Signature function returned an exception')
2661 return ret
2662 return inner
e0df6211 2663
109dd3b2 2664 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2665 """
2666 Extract signatureTimestamp (sts)
2667 Required to tell API what sig/player version is in use.
2668 """
2669 sts = None
2670 if isinstance(ytcfg, dict):
2671 sts = int_or_none(ytcfg.get('STS'))
2672
2673 if not sts:
2674 # Attempt to extract from player
2675 if player_url is None:
2676 error_msg = 'Cannot extract signature timestamp without player_url.'
2677 if fatal:
2678 raise ExtractorError(error_msg)
2679 self.report_warning(error_msg)
2680 return
404f611f 2681 code = self._load_player(video_id, player_url, fatal=fatal)
2682 if code:
109dd3b2 2683 sts = int_or_none(self._search_regex(
2684 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2685 'JS player signature timestamp', group='sts', fatal=fatal))
2686 return sts
2687
11f9be09 2688 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
2689 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2690 label = 'fully ' if is_full else ''
2691 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2692 expected_type=url_or_none)
2693 if not url:
2694 self.report_warning(f'Unable to mark {label}watched')
2695 return
14f25df2 2696 parsed_url = urllib.parse.urlparse(url)
2697 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
2698
2699 # cpn generation algorithm is reverse engineered from base.js.
2700 # In fact it works even with dummy cpn.
2701 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2702 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2703
2704 # # more consistent results setting it to right before the end
2705 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2706
2707 qs.update({
2708 'ver': ['2'],
2709 'cpn': [cpn],
2710 'cmt': video_length,
2711 'el': 'detailpage', # otherwise defaults to "shorts"
2712 })
2713
2714 if is_full:
2715 # these seem to mark watchtime "history" in the real world
2716 # they're required, so send in a single value
2717 qs.update({
2718 'st': video_length,
2719 'et': video_length,
2720 })
2721
14f25df2 2722 url = urllib.parse.urlunparse(
2723 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
2724
2725 self._download_webpage(
2726 url, video_id, f'Marking {label}watched',
2727 'Unable to mark watched', fatal=False)
d77ab8e2 2728
bfd973ec 2729 @classmethod
2730 def _extract_from_webpage(cls, url, webpage):
2731 # Invidious Instances
2732 # https://github.com/yt-dlp/yt-dlp/issues/195
2733 # https://github.com/iv-org/invidious/pull/1730
2734 mobj = re.search(
2735 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2736 webpage)
2737 if mobj:
2738 yield cls.url_result(mobj.group('url'), cls)
2739 raise cls.StopExtraction()
2740
2741 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
2742
2743 # lazyYT YouTube embed
bfd973ec 2744 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
2745 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
2746
2747 # Wordpress "YouTube Video Importer" plugin
bfd973ec 2748 for m in re.findall(r'''(?x)<div[^>]+
2749 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2750 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
2751 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 2752
97665381
PH
2753 @classmethod
2754 def extract_id(cls, url):
ae61d108 2755 video_id = cls.get_temp_id(url)
2756 if not video_id:
2757 raise ExtractorError(f'Invalid URL: {url}')
2758 return video_id
c5e8d7af 2759
7c365c21 2760 def _extract_chapters_from_json(self, data, duration):
2761 chapter_list = traverse_obj(
2762 data, (
2763 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2764 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2765 ), expected_type=list)
2766
2767 return self._extract_chapters(
2768 chapter_list,
2769 chapter_time=lambda chapter: float_or_none(
2770 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2771 chapter_title=lambda chapter: traverse_obj(
2772 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2773 duration=duration)
2774
2775 def _extract_chapters_from_engagement_panel(self, data, duration):
2776 content_list = traverse_obj(
8bdd16b4 2777 data,
7c365c21 2778 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2779 expected_type=list, default=[])
052e1350 2780 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2781 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2782
1890fc63 2783 return next(filter(None, (
2784 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2785 chapter_time, chapter_title, duration)
2786 for contents in content_list)), [])
7c365c21 2787
1890fc63 2788 def _extract_chapters_from_description(self, description, duration):
2789 return self._extract_chapters(
2790 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2791 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2792 duration=duration, strict=False)
84213ea8 2793
1890fc63 2794 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2795 if not duration:
2796 return
2797 chapter_list = [{
2798 'start_time': chapter_time(chapter),
2799 'title': chapter_title(chapter),
2800 } for chapter in chapter_list or []]
2801 if not strict:
2802 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2803
a3976e07 2804 chapters = [{'start_time': 0}]
1890fc63 2805 for idx, chapter in enumerate(chapter_list):
a3976e07 2806 if chapter['start_time'] is None:
1890fc63 2807 self.report_warning(f'Incomplete chapter {idx}')
2808 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
1890fc63 2809 chapters.append(chapter)
2810 else:
2811 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}"')
a3976e07 2812 return chapters[1:]
84213ea8 2813
a1c5d2ca
M
2814 def _extract_comment(self, comment_renderer, parent=None):
2815 comment_id = comment_renderer.get('commentId')
2816 if not comment_id:
2817 return
fe93e2c4 2818
052e1350 2819 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2820
49bd8c66 2821 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2822 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2823 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca 2824 author_id = try_get(comment_renderer,
14f25df2 2825 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
fe93e2c4 2826
49bd8c66 2827 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
14f25df2 2828 lambda x: x['likeCount']), str)) or 0
a1c5d2ca 2829 author_thumbnail = try_get(comment_renderer,
14f25df2 2830 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
a1c5d2ca
M
2831
2832 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2833 is_favorited = 'creatorHeart' in (try_get(
2834 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2835 return {
2836 'id': comment_id,
2837 'text': text,
d92f5d5a 2838 'timestamp': timestamp,
a1c5d2ca
M
2839 'time_text': time_text,
2840 'like_count': votes,
97524332 2841 'is_favorited': is_favorited,
a1c5d2ca
M
2842 'author': author,
2843 'author_id': author_id,
2844 'author_thumbnail': author_thumbnail,
2845 'author_is_uploader': author_is_uploader,
2846 'parent': parent or 'root'
2847 }
2848
46383212 2849 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2850
2851 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2852
2853 def extract_header(contents):
2d6659b9 2854 _continuation = None
2855 for content in contents:
46383212 2856 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2857 expected_comment_count = self._get_count(
2858 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2859
2d6659b9 2860 if expected_comment_count:
46383212 2861 tracker['est_total'] = expected_comment_count
2862 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2863 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2864
2865 sort_menu_item = try_get(
2866 comments_header_renderer,
2867 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2868 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2869
2870 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2871 if not _continuation:
2872 continue
2873
46383212 2874 sort_text = str_or_none(sort_menu_item.get('title'))
2875 if not sort_text:
2d6659b9 2876 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2877 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2878 break
a2160aa4 2879 return _continuation
a1c5d2ca 2880
2d6659b9 2881 def extract_thread(contents):
a1c5d2ca 2882 if not parent:
46383212 2883 tracker['current_page_thread'] = 0
a1c5d2ca 2884 for content in contents:
46383212 2885 if not parent and tracker['total_parent_comments'] >= max_parents:
2886 yield
a1c5d2ca 2887 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2888 comment_renderer = get_first(
2889 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2890 expected_type=dict, default={})
a1c5d2ca 2891
a1c5d2ca
M
2892 comment = self._extract_comment(comment_renderer, parent)
2893 if not comment:
2894 continue
46383212 2895
2896 tracker['running_total'] += 1
2897 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2898 yield comment
46383212 2899
a1c5d2ca
M
2900 # Attempt to get the replies
2901 comment_replies_renderer = try_get(
2902 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2903
2904 if comment_replies_renderer:
46383212 2905 tracker['current_page_thread'] += 1
a1c5d2ca 2906 comment_entries_iter = self._comment_entries(
99e9e001 2907 comment_replies_renderer, ytcfg, video_id,
46383212 2908 parent=comment.get('id'), tracker=tracker)
86e5f3ed 2909 yield from itertools.islice(comment_entries_iter, min(
2910 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 2911
46383212 2912 # Keeps track of counts across recursive calls
2913 if not tracker:
2914 tracker = dict(
2915 running_total=0,
2916 est_total=0,
2917 current_page_thread=0,
2918 total_parent_comments=0,
2919 total_reply_comments=0)
2920
2921 # TODO: Deprecated
2d6659b9 2922 # YouTube comments have a max depth of 2
46383212 2923 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2924 if max_depth:
2925 self._downloader.deprecation_warning(
2926 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2927 if max_depth == 1 and parent:
2928 return
a1c5d2ca 2929
46383212 2930 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2931 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2932
46383212 2933 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2934
46383212 2935 response = None
6e634cbe 2936 is_forced_continuation = False
2d6659b9 2937 is_first_continuation = parent is None
6e634cbe 2938 if is_first_continuation and not continuation:
2939 # Sometimes you can get comments by generating the continuation yourself,
2940 # even if YouTube initially reports them being disabled - e.g. stories comments.
2941 # Note: if the comment section is actually disabled, YouTube may return a response with
2942 # required check_get_keys missing. So we will disable that check initially in this case.
2943 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2944 is_forced_continuation = True
a1c5d2ca
M
2945
2946 for page_num in itertools.count(0):
2947 if not continuation:
2948 break
46383212 2949 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2950 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2951 if page_num == 0:
2952 if is_first_continuation:
2953 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2954 else:
2d6659b9 2955 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2956 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2957 else:
2958 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2959 ' ' if parent else '', ' replies' if parent else '',
2960 page_num, comment_prog_str)
2961
2962 response = self._extract_response(
fe93e2c4 2963 item_id=None, query=continuation,
2d6659b9 2964 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
6e634cbe 2965 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2966 is_forced_continuation = False
46383212 2967 continuation_contents = traverse_obj(
2968 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2969
2d6659b9 2970 continuation = None
46383212 2971 for continuation_section in continuation_contents:
2972 continuation_items = traverse_obj(
2973 continuation_section,
2974 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2975 get_all=False, expected_type=list) or []
2976 if is_first_continuation:
2977 continuation = extract_header(continuation_items)
2978 is_first_continuation = False
2d6659b9 2979 if continuation:
a1c5d2ca 2980 break
46383212 2981 continue
a1c5d2ca 2982
46383212 2983 for entry in extract_thread(continuation_items):
2984 if not entry:
2985 return
2986 yield entry
2987 continuation = self._extract_continuation({'contents': continuation_items})
2988 if continuation:
2d6659b9 2989 break
a1c5d2ca 2990
6e634cbe 2991 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2992 if message and not parent and tracker['running_total'] == 0:
2993 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
2994
2995 @staticmethod
2996 def _generate_comment_continuation(video_id):
2997 """
2998 Generates initial comment section continuation token from given video id
2999 """
3000 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3001 return base64.b64encode(token.encode()).decode()
3002
a2160aa4 3003 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3004 """Entry for comment extraction"""
2d6659b9 3005 def _real_comment_extract(contents):
aae16f6e 3006 renderer = next((
3007 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3008 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3009 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3010
a2160aa4 3011 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3012 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3013
109dd3b2 3014 @staticmethod
99e9e001 3015 def _get_checkok_params():
3016 return {'contentCheckOk': True, 'racyCheckOk': True}
3017
3018 @classmethod
3019 def _generate_player_context(cls, sts=None):
109dd3b2 3020 context = {
3021 'html5Preference': 'HTML5_PREF_WANTS',
3022 }
3023 if sts is not None:
3024 context['signatureTimestamp'] = sts
3025 return {
3026 'playbackContext': {
3027 'contentPlaybackContext': context
a1a7907b 3028 },
99e9e001 3029 **cls._get_checkok_params()
109dd3b2 3030 }
3031
e7e94f2a
D
3032 @staticmethod
3033 def _is_agegated(player_response):
3034 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3035 return True
e7e94f2a
D
3036
3037 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3038 AGE_GATE_REASONS = (
3039 'confirm your age', 'age-restricted', 'inappropriate', # reason
3040 'age_verification_required', 'age_check_required', # status
3041 )
3042 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3043
3044 @staticmethod
3045 def _is_unplayable(player_response):
3046 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3047
99e9e001 3048 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 3049
11f9be09 3050 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3051 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3052 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3053 headers = self.generate_api_headers(
99e9e001 3054 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3055
6e634cbe 3056 yt_query = {
3057 'videoId': video_id,
3058 'params': '8AEB' # enable stories
3059 }
11f9be09 3060 yt_query.update(self._generate_player_context(sts))
3061 return self._extract_response(
3062 item_id=video_id, ep='player', query=yt_query,
379e44ed 3063 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3064 default_client=client,
11f9be09 3065 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3066 ) or None
3067
11f9be09 3068 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3069 requested_clients = []
d0d012d4 3070 default = ['android', 'web']
000c15a4 3071 allowed_clients = sorted(
86e5f3ed 3072 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3073 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3074 for client in self._configuration_arg('player_client'):
3075 if client in allowed_clients:
3076 requested_clients.append(client)
d0d012d4 3077 elif client == 'default':
3078 requested_clients.extend(default)
b4c055ba 3079 elif client == 'all':
3080 requested_clients.extend(allowed_clients)
3081 else:
3082 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3083 if not requested_clients:
d0d012d4 3084 requested_clients = default
cf7e015f 3085
11f9be09 3086 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3087 requested_clients.extend(
e7e94f2a 3088 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3089
11f9be09 3090 return orderedSet(requested_clients)
cf7e015f 3091
99e9e001 3092 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 3093 initial_pr = None
3094 if webpage:
b7c47b74 3095 initial_pr = self._search_json(
3096 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3097
ae729626 3098 all_clients = set(clients)
c0bc527b 3099 clients = clients[::-1]
b6de707d 3100 prs = []
e7e94f2a 3101
ae729626 3102 def append_client(*client_names):
e7870111 3103 """ Append the first client name that exists but not already used """
ae729626 3104 for client_name in client_names:
e7870111
D
3105 actual_client = _split_innertube_client(client_name)[0]
3106 if actual_client in INNERTUBE_CLIENTS:
3107 if actual_client not in all_clients:
ae729626 3108 clients.append(client_name)
e7870111
D
3109 all_clients.add(actual_client)
3110 return
e7e94f2a 3111
379e44ed 3112 # Android player_response does not have microFormats which are needed for
3113 # extraction of some data. So we return the initial_pr with formats
3114 # stripped out even if not requested by the user
3115 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3116 if initial_pr:
3117 pr = dict(initial_pr)
3118 pr['streamingData'] = None
b6de707d 3119 prs.append(pr)
379e44ed 3120
3121 last_error = None
b6de707d 3122 tried_iframe_fallback = False
3123 player_url = None
c0bc527b 3124 while clients:
e7870111 3125 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3126 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3127 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3128 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3129
b6de707d 3130 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3131 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3132 if 'js' in self._configuration_arg('player_skip'):
3133 require_js_player = False
3134 player_url = None
3135
3136 if not player_url and not tried_iframe_fallback and require_js_player:
3137 player_url = self._download_player_url(video_id)
3138 tried_iframe_fallback = True
3139
379e44ed 3140 try:
3141 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 3142 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 3143 except ExtractorError as e:
3144 if last_error:
3145 self.report_warning(last_error)
3146 last_error = e
3147 continue
3148
11f9be09 3149 if pr:
a3e96421 3150 # YouTube may return a different video player response than expected.
3151 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3152 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3153 if pr_video_id and pr_video_id != video_id:
3154 self.report_warning(
c7dcf0b3 3155 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3156 else:
3157 prs.append(pr)
c0bc527b 3158
e7e94f2a 3159 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3160 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3161 append_client(f'{base_client}_creator')
e7e94f2a 3162 elif self._is_agegated(pr):
e7870111
D
3163 if variant == 'tv_embedded':
3164 append_client(f'{base_client}_embedded')
3165 elif not variant:
3166 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3167
379e44ed 3168 if last_error:
b6de707d 3169 if not len(prs):
379e44ed 3170 raise last_error
3171 self.report_warning(last_error)
b6de707d 3172 return prs, player_url
11f9be09 3173
c646d76f 3174 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3175 itags, stream_ids = {}, []
5c6d2ef9 3176 itag_qualities, res_qualities = {}, {0: -1}
d3fc8074 3177 q = qualities([
2a9c6dcd 3178 # Normally tiny is the smallest video-only formats. But
3179 # audio-only formats with unknown quality may get tagged as tiny
3180 'tiny',
3181 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3182 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3183 ])
11f9be09 3184 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3185
545cc85d 3186 for fmt in streaming_formats:
727029c5 3187 if fmt.get('targetDurationSec'):
545cc85d 3188 continue
321bf820 3189
cc2db878 3190 itag = str_or_none(fmt.get('itag'))
9297939e 3191 audio_track = fmt.get('audioTrack') or {}
3192 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3193 if stream_id in stream_ids:
3194 continue
3195
cc2db878 3196 quality = fmt.get('quality')
2a9c6dcd 3197 height = int_or_none(fmt.get('height'))
d3fc8074 3198 if quality == 'tiny' or not quality:
3199 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3200 # The 3gp format (17) in android client has a quality of "small",
3201 # but is actually worse than other formats
3202 if itag == '17':
3203 quality = 'tiny'
3204 if quality:
3205 if itag:
3206 itag_qualities[itag] = quality
3207 if height:
3208 res_qualities[height] = quality
cc2db878 3209 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3210 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3211 # number of fragment that would subsequently requested with (`&sq=N`)
3212 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3213 continue
3214
545cc85d 3215 fmt_url = fmt.get('url')
3216 if not fmt_url:
14f25df2 3217 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3218 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3219 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3220 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3221 continue
52023f12 3222 try:
3223 fmt_url += '&%s=%s' % (
3224 traverse_obj(sc, ('sp', -1)) or 'signature',
3225 self._decrypt_signature(encrypted_sig, video_id, player_url)
3226 )
3227 except ExtractorError as e:
3228 self.report_warning('Signature extraction failed: Some formats may be missing', only_once=True)
3229 self.write_debug(e, only_once=True)
201e9eaa 3230 continue
545cc85d 3231
404f611f 3232 query = parse_qs(fmt_url)
3233 throttled = False
b2916526 3234 if query.get('n'):
404f611f 3235 try:
3236 fmt_url = update_url_query(fmt_url, {
3237 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3238 except ExtractorError as e:
aa9369a2 3239 self.report_warning(
1d485a1a 3240 'nsig extraction failed: You may experience throttling for some formats\n'
52023f12 3241 f'n = {query["n"][0]} ; player = {player_url}', only_once=True)
3242 self.write_debug(e, only_once=True)
404f611f 3243 throttled = True
3244
545cc85d 3245 if itag:
a0bb6ce5 3246 itags[itag] = 'https'
9297939e 3247 stream_ids.append(stream_id)
3248
0ad92dfb 3249 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3250 language_preference = (
3251 10 if audio_track.get('audioIsDefault') and 10
3252 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3253 else -1)
0ad92dfb 3254 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3255 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3256 # Make sure to avoid false positives with small duration differences.
62b58c09 3257 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3258 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3259 if is_damaged:
0f06bcd7 3260 self.report_warning(
3261 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3262 dct = {
3263 'asr': int_or_none(fmt.get('audioSampleRate')),
3264 'filesize': int_or_none(fmt.get('contentLength')),
3265 'format_id': itag,
34921b43 3266 'format_note': join_nonempty(
26e8e044 3267 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3268 ' (default)' if language_preference > 0 else ''),
404f611f 3269 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
a4166234 3270 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3271 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
0ad92dfb 3272 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3273 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3274 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3275 'fps': int_or_none(fmt.get('fps')) or None,
a4166234 3276 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3277 'height': height,
dca3ff4a 3278 'quality': q(quality),
727029c5 3279 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3280 'tbr': tbr,
545cc85d 3281 'url': fmt_url,
2a9c6dcd 3282 'width': int_or_none(fmt.get('width')),
ab6df717 3283 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3284 'desc' if language_preference < -1 else ''),
3285 'language_preference': language_preference,
a405b38f 3286 # Strictly de-prioritize damaged and 3gp formats
3287 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3288 }
60bdb7bd 3289 mime_mobj = re.match(
3290 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3291 if mime_mobj:
3292 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3293 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3294 no_audio = dct.get('acodec') == 'none'
3295 no_video = dct.get('vcodec') == 'none'
3296 if no_audio:
3297 dct['vbr'] = tbr
3298 if no_video:
3299 dct['abr'] = tbr
3300 if no_audio or no_video:
545cc85d 3301 dct['downloader_options'] = {
3302 # Youtube throttles chunks >~10M
3303 'http_chunk_size': 10485760,
bf1317d2 3304 }
7c60c33e 3305 if dct.get('ext'):
3306 dct['container'] = dct['ext'] + '_dash'
11f9be09 3307 yield dct
545cc85d 3308
adbc4ec4 3309 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3310 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3311 if not self.get_param('youtube_include_hls_manifest', True):
3312 skip_manifests.append('hls')
0f06bcd7 3313 if not self.get_param('youtube_include_dash_manifest', True):
3314 skip_manifests.append('dash')
adbc4ec4
THD
3315 get_dash = 'dash' not in skip_manifests and (
3316 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3317 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3318
a0bb6ce5 3319 def process_manifest_format(f, proto, itag):
3320 if itag in itags:
3321 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3322 return False
3323 itag = f'{itag}-{proto}'
3324 if itag:
3325 f['format_id'] = itag
3326 itags[itag] = proto
3327
5c6d2ef9 3328 f['quality'] = itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1)
3329 if f['quality'] == -1 and f.get('height'):
3330 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
a0bb6ce5 3331 return True
2a9c6dcd 3332
c646d76f 3333 subtitles = {}
11f9be09 3334 for sd in streaming_data:
5d3a0e79 3335 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3336 if hls_manifest_url:
c646d76f 3337 fmts, subs = self._extract_m3u8_formats_and_subtitles(hls_manifest_url, video_id, 'mp4', fatal=False, live=is_live)
3338 subtitles = self._merge_subtitles(subs, subtitles)
3339 for f in fmts:
a0bb6ce5 3340 if process_manifest_format(f, 'hls', self._search_regex(
3341 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3342 yield f
545cc85d 3343
5d3a0e79 3344 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3345 if dash_manifest_url:
c646d76f 3346 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3347 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3348 for f in formats:
a0bb6ce5 3349 if process_manifest_format(f, 'dash', f['format_id']):
3350 f['filesize'] = int_or_none(self._search_regex(
3351 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3352 if live_from_start:
3353 f['is_from_start'] = True
3354
a0bb6ce5 3355 yield f
c646d76f 3356 yield subtitles
11f9be09 3357
720c3099 3358 def _extract_storyboard(self, player_responses, duration):
3359 spec = get_first(
3360 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3361 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3362 if not base_url:
720c3099 3363 return
720c3099 3364 L = len(spec) - 1
3365 for i, args in enumerate(spec):
3366 args = args.split('#')
3367 counts = list(map(int_or_none, args[:5]))
3368 if len(args) != 8 or not all(counts):
3369 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3370 continue
3371 width, height, frame_count, cols, rows = counts
3372 N, sigh = args[6:]
3373
3374 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3375 fragment_count = frame_count / (cols * rows)
3376 fragment_duration = duration / fragment_count
3377 yield {
3378 'format_id': f'sb{i}',
3379 'format_note': 'storyboard',
3380 'ext': 'mhtml',
3381 'protocol': 'mhtml',
3382 'acodec': 'none',
3383 'vcodec': 'none',
3384 'url': url,
3385 'width': width,
3386 'height': height,
45e8a04e 3387 'fps': frame_count / duration,
3388 'rows': rows,
3389 'columns': cols,
720c3099 3390 'fragments': [{
b3edc806 3391 'url': url.replace('$M', str(j)),
720c3099 3392 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3393 } for j in range(math.ceil(fragment_count))],
3394 }
3395
adbc4ec4 3396 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3397 webpage = None
3398 if 'webpage' not in self._configuration_arg('player_skip'):
3399 webpage = self._download_webpage(
6e634cbe 3400 webpage_url + '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id, fatal=False)
11f9be09 3401
3402 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3403
b6de707d 3404 player_responses, player_url = self._extract_player_responses(
11f9be09 3405 self._get_requested_clients(url, smuggled_data),
99e9e001 3406 video_id, webpage, master_ytcfg)
11f9be09 3407
adbc4ec4
THD
3408 return webpage, master_ytcfg, player_responses, player_url
3409
a1b2d843 3410 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3411 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3412 is_live = get_first(video_details, 'isLive')
3413 if is_live is None:
3414 is_live = get_first(live_broadcast_details, 'isLiveNow')
3415
3416 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
c646d76f 3417 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, is_live, duration)
adbc4ec4 3418
c646d76f 3419 return live_broadcast_details, is_live, streaming_data, formats, subtitles
adbc4ec4
THD
3420
3421 def _real_extract(self, url):
3422 url, smuggled_data = unsmuggle_url(url, {})
3423 video_id = self._match_id(url)
3424
3425 base_url = self.http_scheme() + '//www.youtube.com/'
3426 webpage_url = base_url + 'watch?v=' + video_id
3427
3428 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3429
11f9be09 3430 playability_statuses = traverse_obj(
3431 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3432
3433 trailer_video_id = get_first(
3434 playability_statuses,
3435 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3436 expected_type=str)
3437 if trailer_video_id:
3438 return self.url_result(
3439 trailer_video_id, self.ie_key(), trailer_video_id)
3440
3441 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3442 if webpage else (lambda x: None))
3443
3444 video_details = traverse_obj(
3445 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3446 microformats = traverse_obj(
3447 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3448 expected_type=dict, default=[])
3449 video_title = (
3450 get_first(video_details, 'title')
3451 or self._get_text(microformats, (..., 'title'))
3452 or search_meta(['og:title', 'twitter:title', 'title']))
3453 video_description = get_first(video_details, 'shortDescription')
3454
d89257f3 3455 multifeed_metadata_list = get_first(
3456 player_responses,
3457 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3458 expected_type=str)
3459 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3460 if self.get_param('noplaylist'):
11f9be09 3461 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3462 else:
3463 entries = []
3464 feed_ids = []
3465 for feed in multifeed_metadata_list.split(','):
3466 # Unquote should take place before split on comma (,) since textual
3467 # fields may contain comma as well (see
3468 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3469 feed_data = urllib.parse.parse_qs(
ac668111 3470 urllib.parse.unquote_plus(feed))
d89257f3 3471
3472 def feed_entry(name):
3473 return try_get(
14f25df2 3474 feed_data, lambda x: x[name][0], str)
d89257f3 3475
3476 feed_id = feed_entry('id')
3477 if not feed_id:
3478 continue
3479 feed_title = feed_entry('title')
3480 title = video_title
3481 if feed_title:
3482 title += ' (%s)' % feed_title
3483 entries.append({
3484 '_type': 'url_transparent',
3485 'ie_key': 'Youtube',
3486 'url': smuggle_url(
3487 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3488 {'force_singlefeed': True}),
3489 'title': title,
3490 })
3491 feed_ids.append(feed_id)
3492 self.to_screen(
3493 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3494 % (', '.join(feed_ids), video_id))
3495 return self.playlist_result(
3496 entries, video_id, video_title, video_description)
11f9be09 3497
a1b2d843 3498 duration = int_or_none(
3499 get_first(video_details, 'lengthSeconds')
3500 or get_first(microformats, 'lengthSeconds')
3501 or parse_duration(search_meta('duration'))) or None
3502
c646d76f 3503 live_broadcast_details, is_live, streaming_data, formats, automatic_captions = \
3504 self._list_formats(video_id, microformats, video_details, player_responses, player_url)
bf1317d2 3505
545cc85d 3506 if not formats:
11f9be09 3507 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3508 self.report_drm(video_id)
11f9be09 3509 pemr = get_first(
3510 playability_statuses,
3511 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3512 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3513 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3514 if subreason:
545cc85d 3515 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3516 countries = get_first(microformats, 'availableCountries')
545cc85d 3517 if not countries:
3518 regions_allowed = search_meta('regionsAllowed')
3519 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3520 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3521 reason += f'. {subreason}'
545cc85d 3522 if reason:
b7da73eb 3523 self.raise_no_formats(reason, expected=True)
bf1317d2 3524
11f9be09 3525 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3526 if not keywords and webpage:
3527 keywords = [
3528 unescapeHTML(m.group('content'))
3529 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3530 for keyword in keywords:
3531 if keyword.startswith('yt:stretch='):
201c1459 3532 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3533 if mobj:
3534 # NB: float is intentional for forcing float division
3535 w, h = (float(v) for v in mobj.groups())
3536 if w > 0 and h > 0:
3537 ratio = w / h
3538 for f in formats:
3539 if f.get('vcodec') != 'none':
3540 f['stretched_ratio'] = ratio
3541 break
a709d873 3542 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3543 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3544 if thumbnail_url:
3545 thumbnails.append({
3546 'url': thumbnail_url,
ff2751ac 3547 })
fccf5021 3548 original_thumbnails = thumbnails.copy()
3549
0ba692ac 3550 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3551 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3552 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3553 thumbnail_names = [
962ffcf8 3554 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 3555 # in resolution, these are not the custom thumbnail. So de-prioritize them
3556 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3557 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3558 ]
cca80fe6 3559 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3560 thumbnails.extend({
3561 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3562 video_id=video_id, name=name, ext=ext,
3563 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3564 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3565 for thumb in thumbnails:
cca80fe6 3566 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3567 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3568 self._remove_duplicate_formats(thumbnails)
fccf5021 3569 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3570
7ea65411 3571 category = get_first(microformats, 'category') or search_meta('genre')
3572 channel_id = str_or_none(
3573 get_first(video_details, 'channelId')
3574 or get_first(microformats, 'externalChannelId')
3575 or search_meta('channelId'))
7ea65411 3576 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3577
3578 live_content = get_first(video_details, 'isLiveContent')
3579 is_upcoming = get_first(video_details, 'isUpcoming')
3580 if is_live is None:
3581 if is_upcoming or live_content is False:
3582 is_live = False
3583 if is_upcoming is None and (live_content or is_live):
3584 is_upcoming = False
adbc4ec4
THD
3585 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3586 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3587 if not duration and live_end_time and live_start_time:
3588 duration = live_end_time - live_start_time
3589
3590 if is_live and self.get_param('live_from_start'):
3591 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3592
720c3099 3593 formats.extend(self._extract_storyboard(player_responses, duration))
3594
31b532a1 3595 # source_preference is lower for throttled/potentially damaged formats
7e798d72 3596 self._sort_formats(formats, (
3597 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'))
720c3099 3598
545cc85d 3599 info = {
3600 'id': video_id,
39ca3b5c 3601 'title': video_title,
545cc85d 3602 'formats': formats,
3603 'thumbnails': thumbnails,
fccf5021 3604 # The best thumbnail that we are sure exists. Prevents unnecessary
3605 # URL checking if user don't care about getting the best possible thumbnail
3606 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3607 'description': video_description,
11f9be09 3608 'uploader': get_first(video_details, 'author'),
545cc85d 3609 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3610 'uploader_url': owner_profile_url,
3611 'channel_id': channel_id,
a70635b8 3612 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3613 'duration': duration,
3614 'view_count': int_or_none(
11f9be09 3615 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3616 or search_meta('interactionCount')),
11f9be09 3617 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3618 'age_limit': 18 if (
11f9be09 3619 get_first(microformats, 'isFamilySafe') is False
545cc85d 3620 or search_meta('isFamilyFriendly') == 'false'
3621 or search_meta('og:restrictions:age') == '18+') else 0,
3622 'webpage_url': webpage_url,
3623 'categories': [category] if category else None,
3624 'tags': keywords,
11f9be09 3625 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3626 'is_live': is_live,
3627 'was_live': (False if is_live or is_upcoming or live_content is False
3628 else None if is_live is None or is_upcoming is None
3629 else live_content),
3630 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3631 'release_timestamp': live_start_time,
545cc85d 3632 }
b477fc13 3633
e325a21a 3634 if get_first(video_details, 'isPostLiveDvr'):
3635 self.write_debug('Video is in Post-Live Manifestless mode')
3636 info['live_status'] = 'post_live'
3637 if (duration or 0) > 4 * 3600:
3638 self.report_warning(
3639 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3640 'This is a known issue and patches are welcome')
3641
c646d76f 3642 subtitles = {}
3944e7af 3643 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3644 if pctr:
ecdc9049 3645 def get_lang_code(track):
3646 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3647 or track.get('languageCode'))
3648
3649 # Converted into dicts to remove duplicates
3650 captions = {
3651 get_lang_code(sub): sub
3652 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3653 translation_languages = {
3654 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3655 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3656
774d79cc 3657 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3658 lang_subs = container.setdefault(lang_code, [])
545cc85d 3659 for fmt in self._SUBTITLE_FORMATS:
3660 query.update({
3661 'fmt': fmt,
3662 })
3663 lang_subs.append({
3664 'ext': fmt,
60f393e4 3665 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3666 'name': sub_name,
545cc85d 3667 })
7e72694b 3668
07b47084 3669 # NB: Constructing the full subtitle dictionary is slow
3670 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
3671 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 3672 for lang_code, caption_track in captions.items():
3673 base_url = caption_track.get('baseUrl')
1235d333 3674 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3675 if not base_url:
3676 continue
ecdc9049 3677 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3678 if caption_track.get('kind') != 'asr':
545cc85d 3679 if not lang_code:
3680 continue
3681 process_language(
ecdc9049 3682 subtitles, base_url, lang_code, lang_name, {})
3683 if not caption_track.get('isTranslatable'):
3684 continue
3944e7af 3685 for trans_code, trans_name in translation_languages.items():
3686 if not trans_code:
545cc85d 3687 continue
1235d333 3688 orig_trans_code = trans_code
ecdc9049 3689 if caption_track.get('kind') != 'asr':
07b47084 3690 if not get_translated_subs:
18e49408 3691 continue
ecdc9049 3692 trans_code += f'-{lang_code}'
a70635b8 3693 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 3694 # Add an "-orig" label to the original language so that it can be distinguished.
3695 # The subs are returned without "-orig" as well for compatibility
1235d333 3696 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3697 process_language(
d49669ac 3698 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3699 # Setting tlang=lang returns damaged subtitles.
d49669ac 3700 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3701 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 3702
3703 info['automatic_captions'] = automatic_captions
3704 info['subtitles'] = subtitles
7e72694b 3705
14f25df2 3706 parsed_url = urllib.parse.urlparse(url)
545cc85d 3707 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 3708 query = urllib.parse.parse_qs(component)
545cc85d 3709 for k, v in query.items():
3710 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3711 d_k += '_time'
3712 if d_k not in info and k in s_ks:
3713 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3714
3715 # Youtube Music Auto-generated description
822b9d9c 3716 if video_description:
1890fc63 3717 mobj = re.search(
3718 r'''(?xs)
3719 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3720 (?P<album>[^\n]+)
3721 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3722 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3723 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3724 .+\nAuto-generated\ by\ YouTube\.\s*$
3725 ''', video_description)
822b9d9c 3726 if mobj:
822b9d9c
RA
3727 release_year = mobj.group('release_year')
3728 release_date = mobj.group('release_date')
3729 if release_date:
3730 release_date = release_date.replace('-', '')
3731 if not release_year:
545cc85d 3732 release_year = release_date[:4]
3733 info.update({
3734 'album': mobj.group('album'.strip()),
3735 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3736 'track': mobj.group('track').strip(),
3737 'release_date': release_date,
cc2db878 3738 'release_year': int_or_none(release_year),
545cc85d 3739 })
7e72694b 3740
545cc85d 3741 initial_data = None
3742 if webpage:
56ba69e4 3743 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 3744 if not initial_data:
99e9e001 3745 query = {'videoId': video_id}
3746 query.update(self._get_checkok_params())
109dd3b2 3747 initial_data = self._extract_response(
3748 item_id=video_id, ep='next', fatal=False,
99e9e001 3749 ytcfg=master_ytcfg, query=query,
3750 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3751 note='Downloading initial data API JSON')
545cc85d 3752
0df111a3 3753 info['comment_count'] = traverse_obj(initial_data, (
3754 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3755 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3756 ), (
3757 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3758 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3759 ), expected_type=int_or_none, get_all=False)
3760
19a03940 3761 try: # This will error if there is no livechat
c60ee3a2 3762 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 3763 except (KeyError, IndexError, TypeError):
3764 pass
3765 else:
ecdc9049 3766 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 3767 # url is needed to set cookies
3768 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 3769 'video_id': video_id,
3770 'ext': 'json',
f6745c49 3771 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3772 }]
545cc85d 3773
3774 if initial_data:
7c365c21 3775 info['chapters'] = (
3776 self._extract_chapters_from_json(initial_data, duration)
3777 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 3778 or self._extract_chapters_from_description(video_description, duration)
7c365c21 3779 or None)
545cc85d 3780
17322130 3781 contents = traverse_obj(
3782 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3783 expected_type=list, default=[])
3784
3785 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3786 if vpir:
3787 stl = vpir.get('superTitleLink')
3788 if stl:
3789 stl = self._get_text(stl)
3790 if try_get(
3791 vpir,
3792 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3793 info['location'] = stl
3794 else:
affc4fef 3795 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 3796 if mobj:
545cc85d 3797 info.update({
17322130 3798 'series': mobj.group(1),
3799 'season_number': int(mobj.group(2)),
3800 'episode_number': int(mobj.group(3)),
545cc85d 3801 })
17322130 3802 for tlb in (try_get(
3803 vpir,
3804 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3805 list) or []):
3806 tbr = tlb.get('toggleButtonRenderer') or {}
3807 for getter, regex in [(
3808 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3809 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3810 lambda x: x['accessibility'],
3811 lambda x: x['accessibilityData']['accessibilityData'],
3812 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3813 label = (try_get(tbr, getter, dict) or {}).get('label')
3814 if label:
3815 mobj = re.match(regex, label)
3816 if mobj:
3817 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3818 break
17322130 3819 sbr_tooltip = try_get(
3820 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3821 if sbr_tooltip:
3822 like_count, dislike_count = sbr_tooltip.split(' / ')
3823 info.update({
3824 'like_count': str_to_int(like_count),
3825 'dislike_count': str_to_int(dislike_count),
3826 })
3827 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3828 if vsir:
3829 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3830 info.update({
3831 'channel': self._get_text(vor, 'title'),
3832 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3833
3834 rows = try_get(
3835 vsir,
3836 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3837 list) or []
3838 multiple_songs = False
3839 for row in rows:
3840 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3841 multiple_songs = True
3842 break
3843 for row in rows:
3844 mrr = row.get('metadataRowRenderer') or {}
3845 mrr_title = mrr.get('title')
3846 if not mrr_title:
3847 continue
3848 mrr_title = self._get_text(mrr, 'title')
3849 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3850 if mrr_title == 'License':
3851 info['license'] = mrr_contents_text
3852 elif not multiple_songs:
3853 if mrr_title == 'Album':
3854 info['album'] = mrr_contents_text
3855 elif mrr_title == 'Artist':
3856 info['artist'] = mrr_contents_text
3857 elif mrr_title == 'Song':
3858 info['track'] = mrr_contents_text
545cc85d 3859
3860 fallbacks = {
3861 'channel': 'uploader',
3862 'channel_id': 'uploader_id',
3863 'channel_url': 'uploader_url',
3864 }
992f9a73 3865
17322130 3866 # The upload date for scheduled, live and past live streams / premieres in microformats
3867 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3868 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3869 upload_date = (
3870 unified_strdate(get_first(microformats, 'uploadDate'))
3871 or unified_strdate(search_meta('uploadDate')))
3872 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
6e634cbe 3873 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date
17322130 3874 info['upload_date'] = upload_date
992f9a73 3875
545cc85d 3876 for to, frm in fallbacks.items():
3877 if not info.get(to):
3878 info[to] = info.get(frm)
3879
3880 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3881 v = info.get(s_k)
3882 if v:
3883 info[d_k] = v
b84071c0 3884
11f9be09 3885 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3886 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3887 is_membersonly = None
b28f8d24 3888 is_premium = None
c224251a
M
3889 if initial_data and is_private is not None:
3890 is_membersonly = False
b28f8d24 3891 is_premium = False
47193e02 3892 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3893 badge_labels = set()
3894 for content in contents:
3895 if not isinstance(content, dict):
3896 continue
3897 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3898 for badge_label in badge_labels:
3899 if badge_label.lower() == 'members only':
3900 is_membersonly = True
3901 elif badge_label.lower() == 'premium':
3902 is_premium = True
3903 elif badge_label.lower() == 'unlisted':
3904 is_unlisted = True
c224251a 3905
c224251a
M
3906 info['availability'] = self._availability(
3907 is_private=is_private,
b28f8d24 3908 needs_premium=is_premium,
c224251a
M
3909 needs_subscription=is_membersonly,
3910 needs_auth=info['age_limit'] >= 18,
3911 is_unlisted=None if is_private is None else is_unlisted)
3912
a2160aa4 3913 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3914
11f9be09 3915 self.mark_watched(video_id, player_responses)
d77ab8e2 3916
545cc85d 3917 return info
c5e8d7af 3918
a61fd4cf 3919
a6213a49 3920class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3921
182bda88 3922 @staticmethod
3923 def passthrough_smuggled_data(func):
3924 def _smuggle(entries, smuggled_data):
3925 for entry in entries:
3926 # TODO: Convert URL to music.youtube instead.
3927 # Do we need to passthrough any other smuggled_data?
3928 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3929 yield entry
3930
3931 @functools.wraps(func)
3932 def wrapper(self, url):
3933 url, smuggled_data = unsmuggle_url(url, {})
3934 if self.is_music_url(url):
3935 smuggled_data['is_music_url'] = True
3936 info_dict = func(self, url, smuggled_data)
3937 if smuggled_data and info_dict.get('entries'):
3938 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3939 return info_dict
3940 return wrapper
3941
a6213a49 3942 def _extract_channel_id(self, webpage):
3943 channel_id = self._html_search_meta(
3944 'channelId', webpage, 'channel id', default=None)
3945 if channel_id:
3946 return channel_id
3947 channel_url = self._html_search_meta(
3948 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3949 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3950 'twitter:app:url:googleplay'), webpage, 'channel url')
3951 return self._search_regex(
3952 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3953 channel_url, 'channel id')
15f6397c 3954
8bdd16b4 3955 @staticmethod
cd7c66cf 3956 def _extract_basic_item_renderer(item):
3957 # Modified from _extract_grid_item_renderer
201c1459 3958 known_basic_renderers = (
a17526e4 3959 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 3960 )
3961 for key, renderer in item.items():
201c1459 3962 if not isinstance(renderer, dict):
cd7c66cf 3963 continue
201c1459 3964 elif key in known_basic_renderers:
3965 return renderer
3966 elif key.startswith('grid') and key.endswith('Renderer'):
3967 return renderer
8bdd16b4 3968
8bdd16b4 3969 def _grid_entries(self, grid_renderer):
3970 for item in grid_renderer['items']:
3971 if not isinstance(item, dict):
39b62db1 3972 continue
cd7c66cf 3973 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3974 if not isinstance(renderer, dict):
3975 continue
052e1350 3976 title = self._get_text(renderer, 'title')
fe93e2c4 3977
8bdd16b4 3978 # playlist
3979 playlist_id = renderer.get('playlistId')
3980 if playlist_id:
3981 yield self.url_result(
3982 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3983 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3984 video_title=title)
201c1459 3985 continue
8bdd16b4 3986 # video
3987 video_id = renderer.get('videoId')
3988 if video_id:
3989 yield self._extract_video(renderer)
201c1459 3990 continue
8bdd16b4 3991 # channel
3992 channel_id = renderer.get('channelId')
3993 if channel_id:
8bdd16b4 3994 yield self.url_result(
3995 'https://www.youtube.com/channel/%s' % channel_id,
3996 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3997 continue
3998 # generic endpoint URL support
3999 ep_url = urljoin('https://www.youtube.com/', try_get(
4000 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4001 str))
201c1459 4002 if ep_url:
4003 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4004 if ie.suitable(ep_url):
4005 yield self.url_result(
4006 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4007 break
8bdd16b4 4008
16aa9ea4 4009 def _music_reponsive_list_entry(self, renderer):
4010 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4011 if video_id:
4012 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4013 ie=YoutubeIE.ie_key(), video_id=video_id)
4014 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4015 if playlist_id:
4016 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4017 if video_id:
4018 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4019 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4020 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4021 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4022 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4023 if browse_id:
4024 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4025 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4026
3d3dddc9 4027 def _shelf_entries_from_content(self, shelf_renderer):
4028 content = shelf_renderer.get('content')
4029 if not isinstance(content, dict):
8bdd16b4 4030 return
cd7c66cf 4031 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4032 if renderer:
4033 # TODO: add support for nested playlists so each shelf is processed
4034 # as separate playlist
4035 # TODO: this includes only first N items
86e5f3ed 4036 yield from self._grid_entries(renderer)
3d3dddc9 4037 renderer = content.get('horizontalListRenderer')
4038 if renderer:
4039 # TODO
4040 pass
8bdd16b4 4041
29f7c58a 4042 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4043 ep = try_get(
4044 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4045 str)
8bdd16b4 4046 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4047 if shelf_url:
29f7c58a 4048 # Skipping links to another channels, note that checking for
4049 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4050 # will not work
4051 if skip_channels and '/channels?' in shelf_url:
4052 return
052e1350 4053 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4054 yield self.url_result(shelf_url, video_title=title)
4055 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4056 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4057
8bdd16b4 4058 def _playlist_entries(self, video_list_renderer):
4059 for content in video_list_renderer['contents']:
4060 if not isinstance(content, dict):
4061 continue
4062 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4063 if not isinstance(renderer, dict):
4064 continue
4065 video_id = renderer.get('videoId')
4066 if not video_id:
4067 continue
4068 yield self._extract_video(renderer)
07aeced6 4069
3462ffa8 4070 def _rich_entries(self, rich_grid_renderer):
4071 renderer = try_get(
70d5c17b 4072 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 4073 video_id = renderer.get('videoId')
4074 if not video_id:
4075 return
4076 yield self._extract_video(renderer)
4077
8bdd16b4 4078 def _video_entry(self, video_renderer):
4079 video_id = video_renderer.get('videoId')
4080 if video_id:
4081 return self._extract_video(video_renderer)
dacb3a86 4082
ad210f4f 4083 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4084 url = urljoin('https://youtube.com', traverse_obj(
4085 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4086 if url:
4087 return self.url_result(
4088 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4089
8bdd16b4 4090 def _post_thread_entries(self, post_thread_renderer):
4091 post_renderer = try_get(
4092 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4093 if not post_renderer:
4094 return
4095 # video attachment
4096 video_renderer = try_get(
895b0931 4097 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4098 video_id = video_renderer.get('videoId')
4099 if video_id:
4100 entry = self._extract_video(video_renderer)
8bdd16b4 4101 if entry:
4102 yield entry
895b0931 4103 # playlist attachment
4104 playlist_id = try_get(
14f25df2 4105 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4106 if playlist_id:
4107 yield self.url_result(
e28f1c0a 4108 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4109 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4110 # inline video links
4111 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4112 for run in runs:
4113 if not isinstance(run, dict):
4114 continue
4115 ep_url = try_get(
14f25df2 4116 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4117 if not ep_url:
4118 continue
4119 if not YoutubeIE.suitable(ep_url):
4120 continue
4121 ep_video_id = YoutubeIE._match_id(ep_url)
4122 if video_id == ep_video_id:
4123 continue
895b0931 4124 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4125
8bdd16b4 4126 def _post_thread_continuation_entries(self, post_thread_continuation):
4127 contents = post_thread_continuation.get('contents')
4128 if not isinstance(contents, list):
4129 return
4130 for content in contents:
4131 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4132 if isinstance(renderer, dict):
4133 yield from self._post_thread_entries(renderer)
8bdd16b4 4134 continue
6b0b0a28 4135 renderer = content.get('videoRenderer')
4136 if isinstance(renderer, dict):
4137 yield self._video_entry(renderer)
07aeced6 4138
39ed931e 4139 r''' # unused
4140 def _rich_grid_entries(self, contents):
4141 for content in contents:
4142 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4143 if video_renderer:
4144 entry = self._video_entry(video_renderer)
4145 if entry:
4146 yield entry
4147 '''
52efa4b3 4148
a6213a49 4149 def _extract_entries(self, parent_renderer, continuation_list):
4150 # continuation_list is modified in-place with continuation_list = [continuation_token]
4151 continuation_list[:] = [None]
4152 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4153 for content in contents:
4154 if not isinstance(content, dict):
4155 continue
16aa9ea4 4156 is_renderer = traverse_obj(
4157 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4158 expected_type=dict)
a6213a49 4159 if not is_renderer:
4160 renderer = content.get('richItemRenderer')
4161 if renderer:
4162 for entry in self._rich_entries(renderer):
4163 yield entry
4164 continuation_list[0] = self._extract_continuation(parent_renderer)
4165 continue
4166 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4167 for isr_content in isr_contents:
4168 if not isinstance(isr_content, dict):
8bdd16b4 4169 continue
69184e41 4170
a6213a49 4171 known_renderers = {
4172 'playlistVideoListRenderer': self._playlist_entries,
4173 'gridRenderer': self._grid_entries,
a17526e4 4174 'reelShelfRenderer': self._grid_entries,
4175 'shelfRenderer': self._shelf_entries,
16aa9ea4 4176 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4177 'backstagePostThreadRenderer': self._post_thread_entries,
4178 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4179 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4180 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4181 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4182 }
4183 for key, renderer in isr_content.items():
4184 if key not in known_renderers:
4185 continue
4186 for entry in known_renderers[key](renderer):
4187 if entry:
4188 yield entry
4189 continuation_list[0] = self._extract_continuation(renderer)
4190 break
70d5c17b 4191
4192 if not continuation_list[0]:
a6213a49 4193 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4194
a6213a49 4195 if not continuation_list[0]:
4196 continuation_list[0] = self._extract_continuation(parent_renderer)
4197
4198 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4199 continuation_list = [None]
4200 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4201 tab_content = try_get(tab, lambda x: x['content'], dict)
4202 if not tab_content:
4203 return
3462ffa8 4204 parent_renderer = (
29f7c58a 4205 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4206 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4207 yield from extract_entries(parent_renderer)
3462ffa8 4208 continuation = continuation_list[0]
d069eca7 4209
8bdd16b4 4210 for page_num in itertools.count(1):
4211 if not continuation:
4212 break
99e9e001 4213 headers = self.generate_api_headers(
4214 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4215 response = self._extract_response(
86e5f3ed 4216 item_id=f'{item_id} page {page_num}',
fe93e2c4 4217 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4218 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4219
4220 if not response:
8bdd16b4 4221 break
ac56cf38 4222 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4223 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4224 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4225
69184e41 4226 known_continuation_renderers = {
4227 'playlistVideoListContinuation': self._playlist_entries,
4228 'gridContinuation': self._grid_entries,
4229 'itemSectionContinuation': self._post_thread_continuation_entries,
4230 'sectionListContinuation': extract_entries, # for feeds
4231 }
8bdd16b4 4232 continuation_contents = try_get(
69184e41 4233 response, lambda x: x['continuationContents'], dict) or {}
4234 continuation_renderer = None
4235 for key, value in continuation_contents.items():
4236 if key not in known_continuation_renderers:
3462ffa8 4237 continue
69184e41 4238 continuation_renderer = value
4239 continuation_list = [None]
86e5f3ed 4240 yield from known_continuation_renderers[key](continuation_renderer)
69184e41 4241 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4242 break
4243 if continuation_renderer:
4244 continue
c5e8d7af 4245
a1b535bd 4246 known_renderers = {
e4b98809 4247 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4248 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4249 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4250 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4251 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4252 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4253 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4254 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4255 }
cce889b9 4256 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4257 continuation_items = try_get(
cce889b9 4258 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4259 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4260 video_items_renderer = None
4261 for key, value in continuation_item.items():
4262 if key not in known_renderers:
8bdd16b4 4263 continue
a1b535bd 4264 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4265 continuation_list = [None]
86e5f3ed 4266 yield from known_renderers[key][0](video_items_renderer)
9ba5705a 4267 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4268 break
4269 if video_items_renderer:
4270 continue
8bdd16b4 4271 break
9558dcec 4272
8bdd16b4 4273 @staticmethod
7c219ea6 4274 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4275 for tab in tabs:
cd684175 4276 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4277 if renderer.get('selected') is True:
4278 return renderer
2b3c2546 4279 else:
7c219ea6 4280 if fatal:
4281 raise ExtractorError('Unable to find selected tab')
b82f815f 4282
61d3665d 4283 def _extract_uploader(self, data):
8bdd16b4 4284 uploader = {}
61d3665d 4285 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
47193e02 4286 owner = try_get(
4287 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4288 if owner:
61d3665d 4289 owner_text = owner.get('text')
4290 uploader['uploader'] = self._search_regex(
4291 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
47193e02 4292 uploader['uploader_id'] = try_get(
14f25df2 4293 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], str)
47193e02 4294 uploader['uploader_url'] = urljoin(
4295 'https://www.youtube.com/',
14f25df2 4296 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
9c3fe2ef 4297 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4298
ac56cf38 4299 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4300 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4301 tags = []
b60419c5 4302
8bdd16b4 4303 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4304 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4305 renderer = try_get(
4306 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4307 if renderer:
b60419c5 4308 channel_name = renderer.get('title')
4309 channel_url = renderer.get('channelUrl')
4310 channel_id = renderer.get('externalId')
39ed931e 4311 else:
64c0d954 4312 renderer = try_get(
4313 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4314
8bdd16b4 4315 if renderer:
4316 title = renderer.get('title')
ecc97af3 4317 description = renderer.get('description', '')
b60419c5 4318 playlist_id = channel_id
4319 tags = renderer.get('keywords', '').split()
b60419c5 4320
301d07fc 4321 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4322 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4323 def _get_uncropped(url):
4324 return url_or_none((url or '').split('=')[0] + '=s0')
4325
4326 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4327 if avatar_thumbnails:
4328 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4329 if uncropped_avatar:
4330 avatar_thumbnails.append({
4331 'url': uncropped_avatar,
4332 'id': 'avatar_uncropped',
4333 'preference': 1
4334 })
4335
4336 channel_banners = self._extract_thumbnails(
4337 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4338 for banner in channel_banners:
4339 banner['preference'] = -10
4340
4341 if channel_banners:
4342 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4343 if uncropped_banner:
4344 channel_banners.append({
4345 'url': uncropped_banner,
4346 'id': 'banner_uncropped',
4347 'preference': -5
4348 })
4349
4350 primary_thumbnails = self._extract_thumbnails(
a17526e4 4351 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4352
3462ffa8 4353 if playlist_id is None:
70d5c17b 4354 playlist_id = item_id
f0d785d3 4355
4356 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4357 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4358 if title is None:
f0d785d3 4359 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4360 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4361 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4362
b60419c5 4363 metadata = {
4364 'playlist_id': playlist_id,
4365 'playlist_title': title,
4366 'playlist_description': description,
4367 'uploader': channel_name,
4368 'uploader_id': channel_id,
4369 'uploader_url': channel_url,
301d07fc 4370 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4371 'tags': tags,
f0d785d3 4372 'view_count': self._get_count(playlist_stats, 1),
4373 'availability': self._extract_availability(data),
4374 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4375 'playlist_count': self._get_count(playlist_stats, 0),
4376 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4377 }
4378 if not channel_id:
4379 metadata.update(self._extract_uploader(data))
4380 metadata.update({
4381 'channel': metadata['uploader'],
4382 'channel_id': metadata['uploader_id'],
4383 'channel_url': metadata['uploader_url']})
4384 return self.playlist_result(
d069eca7 4385 self._entries(
ac56cf38 4386 selected_tab, playlist_id, ytcfg,
4387 self._extract_account_syncid(ytcfg, data),
4388 self._extract_visitor_data(data, ytcfg)),
b60419c5 4389 **metadata)
73c4ac2c 4390
6e634cbe 4391 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4392 first_id = last_id = response = None
2be71994 4393 for page_num in itertools.count(1):
cd7c66cf 4394 videos = list(self._playlist_entries(playlist))
4395 if not videos:
4396 return
2be71994 4397 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4398 if start >= len(videos):
4399 return
24146491 4400 yield from videos[start:]
2be71994 4401 first_id = first_id or videos[0]['id']
4402 last_id = videos[-1]['id']
79360d99 4403 watch_endpoint = try_get(
4404 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4405 headers = self.generate_api_headers(
4406 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4407 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4408 query = {
4409 'playlistId': playlist_id,
4410 'videoId': watch_endpoint.get('videoId') or last_id,
4411 'index': watch_endpoint.get('index') or len(videos),
4412 'params': watch_endpoint.get('params') or 'OAE%3D'
4413 }
4414 response = self._extract_response(
4415 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4416 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4417 check_get_keys='contents'
4418 )
cd7c66cf 4419 playlist = try_get(
79360d99 4420 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4421
ac56cf38 4422 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4423 title = playlist.get('title') or try_get(
14f25df2 4424 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4425 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4426
4427 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4428 playlist_url = urljoin(url, try_get(
4429 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4430 str))
6e634cbe 4431
4432 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4433 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4434 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4435
4436 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4437 return self.url_result(
4438 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4439 video_title=title)
cd7c66cf 4440
8bdd16b4 4441 return self.playlist_result(
6e634cbe 4442 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4443 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4444
47193e02 4445 def _extract_availability(self, data):
4446 """
4447 Gets the availability of a given playlist/tab.
4448 Note: Unless YouTube tells us explicitly, we do not assume it is public
4449 @param data: response
4450 """
4451 is_private = is_unlisted = None
4452 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4453 badge_labels = self._extract_badges(renderer)
4454
4455 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4456 privacy_dropdown_entries = try_get(
4457 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4458 for renderer_dict in privacy_dropdown_entries:
4459 is_selected = try_get(
4460 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4461 if not is_selected:
4462 continue
052e1350 4463 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4464 if label:
4465 badge_labels.add(label.lower())
4466 break
4467
4468 for badge_label in badge_labels:
4469 if badge_label == 'unlisted':
4470 is_unlisted = True
4471 elif badge_label == 'private':
4472 is_private = True
4473 elif badge_label == 'public':
4474 is_unlisted = is_private = False
4475 return self._availability(is_private, False, False, False, is_unlisted)
4476
4477 @staticmethod
4478 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4479 sidebar_renderer = try_get(
4480 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4481 for item in sidebar_renderer:
4482 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4483 if renderer:
4484 return renderer
4485
ac56cf38 4486 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4487 """
4488 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4489 """
5d342002 4490 browse_id = params = None
47193e02 4491 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4492 if not renderer:
4493 return
4494 menu_renderer = try_get(
4495 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4496 for menu_item in menu_renderer:
4497 if not isinstance(menu_item, dict):
358de58c 4498 continue
47193e02 4499 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4500 text = try_get(
14f25df2 4501 nav_item_renderer, lambda x: x['text']['simpleText'], str)
47193e02 4502 if not text or text.lower() != 'show unavailable videos':
4503 continue
4504 browse_endpoint = try_get(
4505 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4506 browse_id = browse_endpoint.get('browseId')
4507 params = browse_endpoint.get('params')
4508 break
5d342002 4509
11f9be09 4510 headers = self.generate_api_headers(
99e9e001 4511 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4512 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4513 query = {
4514 'params': params or 'wgYCCAA=',
4515 'browseId': browse_id or 'VL%s' % item_id
4516 }
4517 return self._extract_response(
4518 item_id=item_id, headers=headers, query=query,
fe93e2c4 4519 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4520 note='Downloading API JSON with unavailable videos')
358de58c 4521
2762dbb1 4522 @functools.cached_property
a25bca9f 4523 def skip_webpage(self):
4524 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4525
ac56cf38 4526 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 4527 webpage, data = None, None
4528 for retry in self.RetryManager(fatal=fatal):
ac56cf38 4529 try:
be5c1ae8 4530 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 4531 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4532 except ExtractorError as e:
4533 if isinstance(e.cause, network_exceptions):
14f25df2 4534 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 4535 retry.error = e
4536 continue
4537 self._error_or_warning(e, fatal=fatal)
14fdfea9 4538 break
ac56cf38 4539
be5c1ae8 4540 try:
4541 self._extract_and_report_alerts(data)
4542 except ExtractorError as e:
4543 self._error_or_warning(e, fatal=fatal)
4544 break
ac56cf38 4545
be5c1ae8 4546 # Sometimes youtube returns a webpage with incomplete ytInitialData
4547 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4548 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4549 retry.error = ExtractorError('Incomplete yt initial data received')
4550 continue
ac56cf38 4551
cd7c66cf 4552 return webpage, data
4553
a25bca9f 4554 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4555 """Use if failed to extract ytcfg (and data) from initial webpage"""
4556 if not ytcfg and self.is_authenticated:
4557 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4558 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4559 raise ExtractorError(
4560 f'{msg}. If you are not downloading private content, or '
4561 'your cookies are only for the first account and channel,'
4562 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4563 expected=True)
4564 self.report_warning(msg, only_once=True)
4565
ac56cf38 4566 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4567 data = None
a25bca9f 4568 if not self.skip_webpage:
ac56cf38 4569 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4570 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4571 # Reject webpage data if redirected to home page without explicitly requesting
4572 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4573 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4574 if (url != 'https://www.youtube.com/feed/recommended'
4575 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4576 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4577 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4578 if fatal:
4579 raise ExtractorError(msg, expected=True)
4580 self.report_warning(msg, only_once=True)
ac56cf38 4581 if not data:
a25bca9f 4582 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4583 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4584 return data, ytcfg
4585
4586 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4587 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4588 resolve_response = self._extract_response(
4589 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4590 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4591 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4592 for ep_key, ep in endpoints.items():
4593 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4594 if params:
4595 return self._extract_response(
4596 item_id=item_id, query=params, ep=ep, headers=headers,
4597 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4598 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4599 err_note = 'Failed to resolve url (does the playlist exist?)'
4600 if fatal:
4601 raise ExtractorError(err_note, expected=True)
4602 self.report_warning(err_note, item_id)
4603
a6213a49 4604 _SEARCH_PARAMS = None
4605
af5c1c55 4606 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4607 data = {'query': query}
4608 if params is NO_DEFAULT:
4609 params = self._SEARCH_PARAMS
4610 if params:
4611 data['params'] = params
16aa9ea4 4612
4613 content_keys = (
4614 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4615 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4616 # ytmusic search
4617 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4618 ('continuationContents', ),
4619 )
a25bca9f 4620 display_id = f'query "{query}"'
86e5f3ed 4621 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4622 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4623 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4624
a61fd4cf 4625 continuation_list = [None]
a25bca9f 4626 search = None
a6213a49 4627 for page_num in itertools.count(1):
a61fd4cf 4628 data.update(continuation_list[0] or {})
a25bca9f 4629 headers = self.generate_api_headers(
4630 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4631 search = self._extract_response(
a25bca9f 4632 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4633 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4634 slr_contents = traverse_obj(search, *content_keys)
4635 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4636 if not continuation_list[0]:
a6213a49 4637 break
4638
4639
4640class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4641 IE_DESC = 'YouTube Tabs'
4642 _VALID_URL = r'''(?x:
4643 https?://
4644 (?:\w+\.)?
4645 (?:
4646 youtube(?:kids)?\.com|
4647 %(invidious)s
4648 )/
4649 (?:
4650 (?P<channel_type>channel|c|user|browse)/|
4651 (?P<not_channel>
4652 feed/|hashtag/|
4653 (?:playlist|watch)\?.*?\blist=
4654 )|
4655 (?!(?:%(reserved_names)s)\b) # Direct URLs
4656 )
4657 (?P<id>[^/?\#&]+)
4658 )''' % {
4659 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4660 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4661 }
4662 IE_NAME = 'youtube:tab'
4663
4664 _TESTS = [{
4665 'note': 'playlists, multipage',
4666 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4667 'playlist_mincount': 94,
4668 'info_dict': {
4669 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4670 'title': 'Igor Kleiner - Playlists',
a6213a49 4671 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4672 'uploader': 'Igor Kleiner',
a6213a49 4673 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4674 'channel': 'Igor Kleiner',
4675 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4676 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4677 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4678 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4679 'channel_follower_count': int
a6213a49 4680 },
4681 }, {
4682 'note': 'playlists, multipage, different order',
4683 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4684 'playlist_mincount': 94,
4685 'info_dict': {
4686 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4687 'title': 'Igor Kleiner - Playlists',
a6213a49 4688 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4689 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4690 'uploader': 'Igor Kleiner',
4691 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4692 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4693 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4694 'channel': 'Igor Kleiner',
4695 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4696 'channel_follower_count': int
a6213a49 4697 },
4698 }, {
4699 'note': 'playlists, series',
4700 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4701 'playlist_mincount': 5,
4702 'info_dict': {
4703 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4704 'title': '3Blue1Brown - Playlists',
4705 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4706 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4707 'uploader': '3Blue1Brown',
976ae3ea 4708 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4709 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4710 'channel': '3Blue1Brown',
4711 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4712 'tags': ['Mathematics'],
6c73052c 4713 'channel_follower_count': int
a6213a49 4714 },
4715 }, {
4716 'note': 'playlists, singlepage',
4717 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4718 'playlist_mincount': 4,
4719 'info_dict': {
4720 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4721 'title': 'ThirstForScience - Playlists',
4722 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4723 'uploader': 'ThirstForScience',
4724 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4725 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4726 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4727 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4728 'tags': 'count:13',
4729 'channel': 'ThirstForScience',
6c73052c 4730 'channel_follower_count': int
a6213a49 4731 }
4732 }, {
4733 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4734 'only_matching': True,
4735 }, {
4736 'note': 'basic, single video playlist',
4737 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4738 'info_dict': {
4739 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4740 'uploader': 'Sergey M.',
4741 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4742 'title': 'youtube-dl public playlist',
976ae3ea 4743 'description': '',
4744 'tags': [],
4745 'view_count': int,
4746 'modified_date': '20201130',
4747 'channel': 'Sergey M.',
4748 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4749 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4750 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4751 },
4752 'playlist_count': 1,
4753 }, {
4754 'note': 'empty playlist',
4755 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4756 'info_dict': {
4757 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4758 'uploader': 'Sergey M.',
4759 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4760 'title': 'youtube-dl empty playlist',
976ae3ea 4761 'tags': [],
4762 'channel': 'Sergey M.',
4763 'description': '',
4764 'modified_date': '20160902',
4765 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4766 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4767 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4768 },
4769 'playlist_count': 0,
4770 }, {
4771 'note': 'Home tab',
4772 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4773 'info_dict': {
4774 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4775 'title': 'lex will - Home',
4776 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4777 'uploader': 'lex will',
4778 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4779 'channel': 'lex will',
4780 'tags': ['bible', 'history', 'prophesy'],
4781 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4782 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4783 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4784 'channel_follower_count': int
a6213a49 4785 },
4786 'playlist_mincount': 2,
4787 }, {
4788 'note': 'Videos tab',
4789 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4790 'info_dict': {
4791 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4792 'title': 'lex will - Videos',
4793 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4794 'uploader': 'lex will',
4795 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4796 'tags': ['bible', 'history', 'prophesy'],
4797 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4798 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4799 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4800 'channel': 'lex will',
6c73052c 4801 'channel_follower_count': int
a6213a49 4802 },
4803 'playlist_mincount': 975,
4804 }, {
4805 'note': 'Videos tab, sorted by popular',
4806 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4807 'info_dict': {
4808 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4809 'title': 'lex will - Videos',
4810 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4811 'uploader': 'lex will',
4812 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4813 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4814 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4815 'channel': 'lex will',
4816 'tags': ['bible', 'history', 'prophesy'],
4817 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4818 'channel_follower_count': int
a6213a49 4819 },
4820 'playlist_mincount': 199,
4821 }, {
4822 'note': 'Playlists tab',
4823 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4824 'info_dict': {
4825 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4826 'title': 'lex will - Playlists',
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': 17,
4838 }, {
4839 'note': 'Community tab',
4840 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4841 'info_dict': {
4842 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4843 'title': 'lex will - Community',
4844 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4845 'uploader': 'lex will',
4846 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4847 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4848 'channel': 'lex will',
4849 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4850 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4851 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4852 'channel_follower_count': int
a6213a49 4853 },
4854 'playlist_mincount': 18,
4855 }, {
4856 'note': 'Channels tab',
4857 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4858 'info_dict': {
4859 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4860 'title': 'lex will - Channels',
4861 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4862 'uploader': 'lex will',
4863 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4864 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4865 'channel': 'lex will',
4866 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4867 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4868 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4869 'channel_follower_count': int
a6213a49 4870 },
4871 'playlist_mincount': 12,
4872 }, {
4873 'note': 'Search tab',
4874 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4875 'playlist_mincount': 40,
4876 'info_dict': {
4877 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4878 'title': '3Blue1Brown - Search - linear algebra',
4879 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4880 'uploader': '3Blue1Brown',
4881 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4882 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4883 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4884 'tags': ['Mathematics'],
4885 'channel': '3Blue1Brown',
4886 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4887 'channel_follower_count': int
a6213a49 4888 },
4889 }, {
4890 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4891 'only_matching': True,
4892 }, {
4893 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4894 'only_matching': True,
4895 }, {
4896 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4897 'only_matching': True,
4898 }, {
4899 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4900 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4901 'info_dict': {
4902 'title': '29C3: Not my department',
4903 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4904 'uploader': 'Christiaan008',
4905 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4906 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4907 'tags': [],
4908 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4909 'view_count': int,
4910 'modified_date': '20150605',
4911 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4912 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4913 'channel': 'Christiaan008',
a6213a49 4914 },
4915 'playlist_count': 96,
4916 }, {
4917 'note': 'Large playlist',
4918 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4919 'info_dict': {
4920 'title': 'Uploads from Cauchemar',
4921 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4922 'uploader': 'Cauchemar',
4923 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4924 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4925 'tags': [],
4926 'modified_date': r're:\d{8}',
4927 'channel': 'Cauchemar',
4928 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4929 'view_count': int,
4930 'description': '',
4931 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4932 },
4933 'playlist_mincount': 1123,
976ae3ea 4934 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4935 }, {
4936 'note': 'even larger playlist, 8832 videos',
4937 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4938 'only_matching': True,
4939 }, {
4940 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4941 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4942 'info_dict': {
4943 'title': 'Uploads from Interstellar Movie',
4944 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4945 'uploader': 'Interstellar Movie',
4946 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4947 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4948 'tags': [],
4949 'view_count': int,
4950 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4951 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4952 'channel': 'Interstellar Movie',
4953 'description': '',
4954 'modified_date': r're:\d{8}',
a6213a49 4955 },
4956 'playlist_mincount': 21,
4957 }, {
4958 'note': 'Playlist with "show unavailable videos" button',
4959 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4960 'info_dict': {
4961 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4962 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4963 'uploader': 'Phim Siêu Nhân Nhật Bản',
4964 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4965 'view_count': int,
4966 'channel': 'Phim Siêu Nhân Nhật Bản',
4967 'tags': [],
4968 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4969 'description': '',
4970 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4971 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4972 'modified_date': r're:\d{8}',
a6213a49 4973 },
4974 'playlist_mincount': 200,
976ae3ea 4975 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4976 }, {
4977 'note': 'Playlist with unavailable videos in page 7',
4978 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4979 'info_dict': {
4980 'title': 'Uploads from BlankTV',
4981 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4982 'uploader': 'BlankTV',
4983 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4984 'channel': 'BlankTV',
4985 'channel_url': 'https://www.youtube.com/c/blanktv',
4986 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4987 'view_count': int,
4988 'tags': [],
4989 'uploader_url': 'https://www.youtube.com/c/blanktv',
4990 'modified_date': r're:\d{8}',
4991 'description': '',
a6213a49 4992 },
4993 'playlist_mincount': 1000,
976ae3ea 4994 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4995 }, {
4996 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4997 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4998 'info_dict': {
4999 'title': 'Data Analysis with Dr Mike Pound',
5000 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5001 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5002 'uploader': 'Computerphile',
5003 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5004 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5005 'tags': [],
5006 'view_count': int,
5007 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5008 'channel_url': 'https://www.youtube.com/user/Computerphile',
5009 'channel': 'Computerphile',
a6213a49 5010 },
5011 'playlist_mincount': 11,
5012 }, {
5013 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5014 'only_matching': True,
5015 }, {
5016 'note': 'Playlist URL that does not actually serve a playlist',
5017 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5018 'info_dict': {
5019 'id': 'FqZTN594JQw',
5020 'ext': 'webm',
5021 'title': "Smiley's People 01 detective, Adventure Series, Action",
5022 'uploader': 'STREEM',
5023 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5024 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5025 'upload_date': '20150526',
5026 'license': 'Standard YouTube License',
5027 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5028 'categories': ['People & Blogs'],
5029 'tags': list,
5030 'view_count': int,
5031 'like_count': int,
a6213a49 5032 },
5033 'params': {
5034 'skip_download': True,
5035 },
5036 'skip': 'This video is not available.',
5037 'add_ie': [YoutubeIE.ie_key()],
5038 }, {
5039 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5040 'only_matching': True,
5041 }, {
5042 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5043 'only_matching': True,
5044 }, {
5045 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5046 'info_dict': {
12a1b225 5047 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5048 'ext': 'mp4',
976ae3ea 5049 'title': str,
a6213a49 5050 'uploader': 'Sky News',
5051 'uploader_id': 'skynews',
5052 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5053 'upload_date': r're:\d{8}',
976ae3ea 5054 'description': str,
a6213a49 5055 'categories': ['News & Politics'],
5056 'tags': list,
5057 'like_count': int,
6c73052c 5058 'release_timestamp': 1642502819,
976ae3ea 5059 'channel': 'Sky News',
5060 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5061 'age_limit': 0,
5062 'view_count': int,
6c73052c 5063 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 5064 'playable_in_embed': True,
6c73052c 5065 'release_date': '20220118',
976ae3ea 5066 'availability': 'public',
5067 'live_status': 'is_live',
5068 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 5069 'channel_follower_count': int
a6213a49 5070 },
5071 'params': {
5072 'skip_download': True,
5073 },
976ae3ea 5074 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5075 }, {
5076 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5077 'info_dict': {
5078 'id': 'a48o2S1cPoo',
5079 'ext': 'mp4',
5080 'title': 'The Young Turks - Live Main Show',
5081 'uploader': 'The Young Turks',
5082 'uploader_id': 'TheYoungTurks',
5083 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5084 'upload_date': '20150715',
5085 'license': 'Standard YouTube License',
5086 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5087 'categories': ['News & Politics'],
5088 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5089 'like_count': int,
a6213a49 5090 },
5091 'params': {
5092 'skip_download': True,
5093 },
5094 'only_matching': True,
5095 }, {
5096 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5097 'only_matching': True,
5098 }, {
5099 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5100 'only_matching': True,
5101 }, {
5102 'note': 'A channel that is not live. Should raise error',
5103 'url': 'https://www.youtube.com/user/numberphile/live',
5104 'only_matching': True,
5105 }, {
5106 'url': 'https://www.youtube.com/feed/trending',
5107 'only_matching': True,
5108 }, {
5109 'url': 'https://www.youtube.com/feed/library',
5110 'only_matching': True,
5111 }, {
5112 'url': 'https://www.youtube.com/feed/history',
5113 'only_matching': True,
5114 }, {
5115 'url': 'https://www.youtube.com/feed/subscriptions',
5116 'only_matching': True,
5117 }, {
5118 'url': 'https://www.youtube.com/feed/watch_later',
5119 'only_matching': True,
5120 }, {
5121 'note': 'Recommended - redirects to home page.',
5122 'url': 'https://www.youtube.com/feed/recommended',
5123 'only_matching': True,
5124 }, {
5125 'note': 'inline playlist with not always working continuations',
5126 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5127 'only_matching': True,
5128 }, {
5129 'url': 'https://www.youtube.com/course',
5130 'only_matching': True,
5131 }, {
5132 'url': 'https://www.youtube.com/zsecurity',
5133 'only_matching': True,
5134 }, {
5135 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5136 'only_matching': True,
5137 }, {
5138 'url': 'https://www.youtube.com/TheYoungTurks/live',
5139 'only_matching': True,
5140 }, {
5141 'url': 'https://www.youtube.com/hashtag/cctv9',
5142 'info_dict': {
5143 'id': 'cctv9',
5144 'title': '#cctv9',
976ae3ea 5145 'tags': [],
a6213a49 5146 },
5147 'playlist_mincount': 350,
5148 }, {
5149 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5150 'only_matching': True,
5151 }, {
5152 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5153 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5154 'only_matching': True
5155 }, {
5156 'note': '/browse/ should redirect to /channel/',
5157 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5158 'only_matching': True
5159 }, {
5160 'note': 'VLPL, should redirect to playlist?list=PL...',
5161 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5162 'info_dict': {
5163 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5164 'uploader': 'NoCopyrightSounds',
5165 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5166 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5167 'title': 'NCS : All Releases 💿',
976ae3ea 5168 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5169 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5170 'modified_date': r're:\d{8}',
5171 'view_count': int,
5172 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5173 'tags': [],
5174 'channel': 'NoCopyrightSounds',
a6213a49 5175 },
5176 'playlist_mincount': 166,
976ae3ea 5177 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5178 }, {
5179 'note': 'Topic, should redirect to playlist?list=UU...',
5180 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5181 'info_dict': {
5182 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5183 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5184 'title': 'Uploads from Royalty Free Music - Topic',
5185 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5186 'tags': [],
5187 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5188 'channel': 'Royalty Free Music - Topic',
5189 'view_count': int,
5190 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5191 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5192 'modified_date': r're:\d{8}',
5193 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5194 'description': '',
a6213a49 5195 },
5196 'expected_warnings': [
a6213a49 5197 'The URL does not have a videos tab',
976ae3ea 5198 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5199 ],
5200 'playlist_mincount': 101,
5201 }, {
5202 'note': 'Topic without a UU playlist',
5203 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5204 'info_dict': {
5205 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5206 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5207 'tags': [],
a6213a49 5208 },
5209 'expected_warnings': [
976ae3ea 5210 'the playlist redirect gave error',
a6213a49 5211 ],
5212 'playlist_mincount': 9,
5213 }, {
5214 'note': 'Youtube music Album',
5215 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5216 'info_dict': {
5217 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5218 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5219 'tags': [],
5220 'view_count': int,
5221 'description': '',
5222 'availability': 'unlisted',
5223 'modified_date': r're:\d{8}',
a6213a49 5224 },
5225 'playlist_count': 50,
5226 }, {
5227 'note': 'unlisted single video playlist',
5228 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5229 'info_dict': {
5230 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5231 'uploader': 'colethedj',
5232 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5233 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5234 'availability': 'unlisted',
5235 'tags': [],
12a1b225 5236 'modified_date': '20220418',
976ae3ea 5237 'channel': 'colethedj',
5238 'view_count': int,
5239 'description': '',
5240 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5241 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5242 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5243 },
5244 'playlist_count': 1,
5245 }, {
5246 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5247 'url': 'https://www.youtube.com/feed/recommended',
5248 'info_dict': {
5249 'id': 'recommended',
5250 'title': 'recommended',
6c73052c 5251 'tags': [],
a6213a49 5252 },
5253 'playlist_mincount': 50,
5254 'params': {
5255 'skip_download': True,
5256 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5257 },
5258 }, {
5259 'note': 'API Fallback: /videos tab, sorted by oldest first',
5260 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5261 'info_dict': {
5262 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5263 'title': 'Cody\'sLab - Videos',
5264 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5265 'uploader': 'Cody\'sLab',
5266 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5267 'channel': 'Cody\'sLab',
5268 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5269 'tags': [],
5270 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5271 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5272 'channel_follower_count': int
a6213a49 5273 },
5274 'playlist_mincount': 650,
5275 'params': {
5276 'skip_download': True,
5277 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5278 },
5279 }, {
5280 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5281 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5282 'info_dict': {
5283 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5284 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5285 'title': 'Uploads from Royalty Free Music - Topic',
5286 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5287 'modified_date': r're:\d{8}',
5288 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5289 'description': '',
5290 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5291 'tags': [],
5292 'channel': 'Royalty Free Music - Topic',
5293 'view_count': int,
5294 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5295 },
5296 'expected_warnings': [
976ae3ea 5297 'does not have a videos tab',
5298 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5299 ],
5300 'playlist_mincount': 101,
5301 'params': {
5302 'skip_download': True,
5303 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5304 },
7c219ea6 5305 }, {
5306 'note': 'non-standard redirect to regional channel',
5307 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5308 'only_matching': True
61d3665d 5309 }, {
5310 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5311 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5312 'info_dict': {
5313 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5314 'modified_date': '20220407',
5315 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5316 'tags': [],
5317 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5318 'uploader': 'pukkandan',
5319 'availability': 'unlisted',
5320 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5321 'channel': 'pukkandan',
5322 'description': 'Test for collaborative playlist',
5323 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5324 'view_count': int,
61d3665d 5325 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5326 },
5327 'playlist_mincount': 2
a6213a49 5328 }]
5329
5330 @classmethod
5331 def suitable(cls, url):
86e5f3ed 5332 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5333
64f36541 5334 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5335
182bda88 5336 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5337 def _real_extract(self, url, smuggled_data):
cd7c66cf 5338 item_id = self._match_id(url)
14f25df2 5339 url = urllib.parse.urlunparse(
5340 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5341 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5342
fe03a6cd 5343 def get_mobj(url):
37e57a9f 5344 mobj = self._URL_RE.match(url).groupdict()
07cce701 5345 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5346 return mobj
5347
37e57a9f 5348 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5349 # Youtube returns incomplete data if tabname is not lower case
5350 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5351 if is_channel:
5352 if smuggled_data.get('is_music_url'):
37e57a9f 5353 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5354 item_id = item_id[2:]
37e57a9f 5355 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5356 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5357 mdata = self._extract_tab_endpoint(
37e57a9f 5358 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5359 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
14f25df2 5360 get_all=False, expected_type=str)
ac56cf38 5361 if not murl:
37e57a9f 5362 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5363 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5364 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5365 pre = f'https://www.youtube.com/channel/{item_id}'
5366
64f36541 5367 original_tab_name = tab
fe03a6cd 5368 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5369 # Home URLs should redirect to /videos/
37e57a9f 5370 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5371 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5372 tab = '/videos'
5373
5374 url = ''.join((pre, tab, post))
5375 mobj = get_mobj(url)
cd7c66cf 5376
5377 # Handle both video/playlist URLs
201c1459 5378 qs = parse_qs(url)
86e5f3ed 5379 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5380
fe03a6cd 5381 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5382 if not playlist_id:
fe03a6cd 5383 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5384 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5385 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5386 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5387 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5388 mobj = get_mobj(url)
cd7c66cf 5389
5390 if video_id and playlist_id:
a06916d9 5391 if self.get_param('noplaylist'):
37e57a9f 5392 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5393 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5394 ie=YoutubeIE.ie_key(), video_id=video_id)
5395 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5396
ac56cf38 5397 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5398
7c219ea6 5399 # YouTube may provide a non-standard redirect to the regional channel
5400 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5401 redirect_url = traverse_obj(
5402 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5403 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5404 redirect_url = ''.join((
5405 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5406 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5407 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5408
37e57a9f 5409 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5410 if tabs:
5411 selected_tab = self._extract_selected_tab(tabs)
64f36541 5412 selected_tab_name = selected_tab.get('title', '').lower()
5413 if selected_tab_name == 'home':
5414 selected_tab_name = 'featured'
5415 requested_tab_name = mobj['tab'][1:]
09f1580e 5416 if 'no-youtube-channel-redirect' not in compat_opts:
693f0600 5417 if requested_tab_name == 'live': # Live tab should have redirected to the video
5418 raise UserNotLive(video_id=mobj['id'])
64f36541 5419 if requested_tab_name not in ('', selected_tab_name):
5420 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5421 if not original_tab_name:
5422 if item_id[:2] == 'UC':
5423 # Topic channels don't have /videos. Use the equivalent playlist instead
5424 pl_id = f'UU{item_id[2:]}'
5425 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5426 try:
5427 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5428 except ExtractorError:
5429 redirect_warning += ' and the playlist redirect gave error'
5430 else:
5431 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5432 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5433 if selected_tab_name and selected_tab_name != requested_tab_name:
5434 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5435 else:
5436 raise ExtractorError(redirect_warning, expected=True)
18db7548 5437
37e57a9f 5438 if redirect_warning:
64f36541 5439 self.to_screen(redirect_warning)
37e57a9f 5440 self.write_debug(f'Final URL: {url}')
18db7548 5441
358de58c 5442 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5443 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5444 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5445 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5446 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5447 if tabs:
ac56cf38 5448 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5449
37e57a9f 5450 playlist = traverse_obj(
5451 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5452 if playlist:
ac56cf38 5453 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5454
37e57a9f 5455 video_id = traverse_obj(
5456 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5457 if video_id:
09f1580e 5458 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5459 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5460 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5461 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5462
8bdd16b4 5463 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5464
c5e8d7af 5465
8bdd16b4 5466class YoutubePlaylistIE(InfoExtractor):
96565c7e 5467 IE_DESC = 'YouTube playlists'
8bdd16b4 5468 _VALID_URL = r'''(?x)(?:
5469 (?:https?://)?
5470 (?:\w+\.)?
5471 (?:
5472 (?:
5473 youtube(?:kids)?\.com|
d9190e44 5474 %(invidious)s
8bdd16b4 5475 )
5476 /.*?\?.*?\blist=
5477 )?
5478 (?P<id>%(playlist_id)s)
d9190e44
RH
5479 )''' % {
5480 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5481 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5482 }
8bdd16b4 5483 IE_NAME = 'youtube:playlist'
cdc628a4 5484 _TESTS = [{
8bdd16b4 5485 'note': 'issue #673',
5486 'url': 'PLBB231211A4F62143',
cdc628a4 5487 'info_dict': {
8bdd16b4 5488 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5489 'id': 'PLBB231211A4F62143',
976ae3ea 5490 'uploader': 'Wickman',
8bdd16b4 5491 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5492 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5493 'view_count': int,
5494 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5495 'modified_date': r're:\d{8}',
5496 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5497 'channel': 'Wickman',
5498 'tags': [],
5499 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5500 },
5501 'playlist_mincount': 29,
5502 }, {
5503 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5504 'info_dict': {
5505 'title': 'YDL_safe_search',
5506 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5507 },
5508 'playlist_count': 2,
5509 'skip': 'This playlist is private',
9558dcec 5510 }, {
8bdd16b4 5511 'note': 'embedded',
5512 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5513 'playlist_count': 4,
9558dcec 5514 'info_dict': {
8bdd16b4 5515 'title': 'JODA15',
5516 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5517 'uploader': 'milan',
5518 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5519 'description': '',
5520 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5521 'tags': [],
5522 'modified_date': '20140919',
5523 'view_count': int,
5524 'channel': 'milan',
5525 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5526 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5527 },
5528 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5529 }, {
8bdd16b4 5530 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 5531 'playlist_mincount': 455,
8bdd16b4 5532 'info_dict': {
5533 'title': '2018 Chinese New Singles (11/6 updated)',
5534 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5535 'uploader': 'LBK',
5536 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5537 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5538 'channel': 'LBK',
5539 'view_count': int,
5540 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5541 'tags': [],
5542 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5543 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5544 'modified_date': r're:\d{8}',
5545 },
5546 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5547 }, {
29f7c58a 5548 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5549 'only_matching': True,
5550 }, {
5551 # music album playlist
5552 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5553 'only_matching': True,
5554 }]
5555
5556 @classmethod
5557 def suitable(cls, url):
201c1459 5558 if YoutubeTabIE.suitable(url):
5559 return False
49a57e70 5560 from ..utils import parse_qs
201c1459 5561 qs = parse_qs(url)
5562 if qs.get('v', [None])[0]:
5563 return False
86e5f3ed 5564 return super().suitable(url)
29f7c58a 5565
5566 def _real_extract(self, url):
5567 playlist_id = self._match_id(url)
46953e7e 5568 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5569 url = update_url_query(
5570 'https://www.youtube.com/playlist',
5571 parse_qs(url) or {'list': playlist_id})
5572 if is_music_url:
5573 url = smuggle_url(url, {'is_music_url': True})
5574 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5575
5576
5577class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5578 IE_DESC = 'youtu.be'
29f7c58a 5579 _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}
5580 _TESTS = [{
8bdd16b4 5581 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5582 'info_dict': {
5583 'id': 'yeWKywCrFtk',
5584 'ext': 'mp4',
5585 'title': 'Small Scale Baler and Braiding Rugs',
5586 'uploader': 'Backus-Page House Museum',
5587 'uploader_id': 'backuspagemuseum',
5588 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5589 'upload_date': '20161008',
5590 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5591 'categories': ['Nonprofits & Activism'],
5592 'tags': list,
5593 'like_count': int,
976ae3ea 5594 'age_limit': 0,
5595 'playable_in_embed': True,
5596 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5597 'channel': 'Backus-Page House Museum',
5598 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5599 'live_status': 'not_live',
5600 'view_count': int,
5601 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5602 'availability': 'public',
5603 'duration': 59,
12a1b225
A
5604 'comment_count': int,
5605 'channel_follower_count': int
8bdd16b4 5606 },
5607 'params': {
5608 'noplaylist': True,
5609 'skip_download': True,
5610 },
39e7107d 5611 }, {
8bdd16b4 5612 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5613 'only_matching': True,
cdc628a4
PH
5614 }]
5615
8bdd16b4 5616 def _real_extract(self, url):
5ad28e7f 5617 mobj = self._match_valid_url(url)
29f7c58a 5618 video_id = mobj.group('id')
5619 playlist_id = mobj.group('playlist_id')
8bdd16b4 5620 return self.url_result(
29f7c58a 5621 update_url_query('https://www.youtube.com/watch', {
5622 'v': video_id,
5623 'list': playlist_id,
5624 'feature': 'youtu.be',
5625 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5626
5627
b6ce9bb0 5628class YoutubeLivestreamEmbedIE(InfoExtractor):
5629 IE_DESC = 'YouTube livestream embeds'
5630 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5631 _TESTS = [{
5632 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5633 'only_matching': True,
5634 }]
5635
5636 def _real_extract(self, url):
5637 channel_id = self._match_id(url)
5638 return self.url_result(
5639 f'https://www.youtube.com/channel/{channel_id}/live',
5640 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5641
5642
8bdd16b4 5643class YoutubeYtUserIE(InfoExtractor):
96565c7e 5644 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5645 IE_NAME = 'youtube:user'
8bdd16b4 5646 _VALID_URL = r'ytuser:(?P<id>.+)'
5647 _TESTS = [{
5648 'url': 'ytuser:phihag',
5649 'only_matching': True,
5650 }]
5651
5652 def _real_extract(self, url):
5653 user_id = self._match_id(url)
5654 return self.url_result(
c586f9e8 5655 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5656 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5657
b05654f0 5658
3d3dddc9 5659class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5660 IE_NAME = 'youtube:favorites'
96565c7e 5661 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5662 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5663 _LOGIN_REQUIRED = True
5664 _TESTS = [{
5665 'url': ':ytfav',
5666 'only_matching': True,
5667 }, {
5668 'url': ':ytfavorites',
5669 'only_matching': True,
5670 }]
5671
5672 def _real_extract(self, url):
5673 return self.url_result(
5674 'https://www.youtube.com/playlist?list=LL',
5675 ie=YoutubeTabIE.ie_key())
5676
5677
ca5300c7 5678class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
5679 IE_NAME = 'youtube:notif'
5680 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5681 _VALID_URL = r':ytnotif(?:ication)?s?'
5682 _LOGIN_REQUIRED = True
5683 _TESTS = [{
5684 'url': ':ytnotif',
5685 'only_matching': True,
5686 }, {
5687 'url': ':ytnotifications',
5688 'only_matching': True,
5689 }]
5690
5691 def _extract_notification_menu(self, response, continuation_list):
5692 notification_list = traverse_obj(
5693 response,
5694 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5695 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5696 expected_type=list) or []
5697 continuation_list[0] = None
5698 for item in notification_list:
5699 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
5700 if entry:
5701 yield entry
5702 continuation = item.get('continuationItemRenderer')
5703 if continuation:
5704 continuation_list[0] = continuation
5705
5706 def _extract_notification_renderer(self, notification):
5707 video_id = traverse_obj(
5708 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
5709 url = f'https://www.youtube.com/watch?v={video_id}'
5710 channel_id = None
5711 if not video_id:
5712 browse_ep = traverse_obj(
5713 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
5714 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
5715 post_id = self._search_regex(
5716 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
5717 'post id', default=None)
5718 if not channel_id or not post_id:
5719 return
5720 # The direct /post url redirects to this in the browser
5721 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5722
5723 channel = traverse_obj(
5724 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5725 expected_type=str)
c7a7baaa 5726 notification_title = self._get_text(notification, 'shortMessage')
5727 if notification_title:
5728 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
5729 # TODO: handle recommended videos
ca5300c7 5730 title = self._search_regex(
c7a7baaa 5731 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 5732 'video title', default=None)
ca5300c7 5733 upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d')
5734 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
5735 else None)
5736 return {
5737 '_type': 'url',
5738 'url': url,
5739 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
5740 'video_id': video_id,
5741 'title': title,
5742 'channel_id': channel_id,
5743 'channel': channel,
5744 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5745 'upload_date': upload_date,
5746 }
5747
5748 def _notification_menu_entries(self, ytcfg):
5749 continuation_list = [None]
5750 response = None
5751 for page in itertools.count(1):
5752 ctoken = traverse_obj(
5753 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
5754 response = self._extract_response(
5755 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
5756 ep='notification/get_notification_menu', check_get_keys='actions',
5757 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
5758 yield from self._extract_notification_menu(response, continuation_list)
5759 if not continuation_list[0]:
5760 break
5761
5762 def _real_extract(self, url):
5763 display_id = 'notifications'
5764 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
5765 self._report_playlist_authcheck(ytcfg)
5766 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
5767
5768
a6213a49 5769class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5770 IE_DESC = 'YouTube search'
78caa52a 5771 IE_NAME = 'youtube:search'
b05654f0 5772 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5773 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5774 _TESTS = [{
5775 'url': 'ytsearch5:youtube-dl test video',
5776 'playlist_count': 5,
5777 'info_dict': {
5778 'id': 'youtube-dl test video',
5779 'title': 'youtube-dl test video',
5780 }
5781 }]
b05654f0 5782
a61fd4cf 5783
5f7cb91a 5784class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5785 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5786 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5787 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5788 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5789 _TESTS = [{
5790 'url': 'ytsearchdate5:youtube-dl test video',
5791 'playlist_count': 5,
5792 'info_dict': {
5793 'id': 'youtube-dl test video',
5794 'title': 'youtube-dl test video',
5795 }
5796 }]
75dff0ee 5797
c9ae7b95 5798
a6213a49 5799class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5800 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5801 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5802 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5803 _TESTS = [{
5804 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5805 'playlist_mincount': 5,
5806 'info_dict': {
11f9be09 5807 'id': 'youtube-dl test video',
3462ffa8 5808 'title': 'youtube-dl test video',
5809 }
a61fd4cf 5810 }, {
5811 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5812 'playlist_mincount': 5,
5813 'info_dict': {
5814 'id': 'python',
5815 'title': 'python',
5816 }
ad210f4f 5817 }, {
5818 'url': 'https://www.youtube.com/results?search_query=%23cats',
5819 'playlist_mincount': 1,
5820 'info_dict': {
5821 'id': '#cats',
5822 'title': '#cats',
12a1b225
A
5823 # The test suite does not have support for nested playlists
5824 # 'entries': [{
5825 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5826 # 'title': '#cats',
5827 # }],
ad210f4f 5828 },
3462ffa8 5829 }, {
5830 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5831 'only_matching': True,
5832 }]
5833
5834 def _real_extract(self, url):
4dfbf869 5835 qs = parse_qs(url)
386e1dd9 5836 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5837 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5838
5839
16aa9ea4 5840class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 5841 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 5842 IE_NAME = 'youtube:music:search_url'
5843 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5844 _TESTS = [{
5845 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5846 'playlist_count': 16,
5847 'info_dict': {
5848 'id': 'royalty free music',
5849 'title': 'royalty free music',
5850 }
5851 }, {
5852 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5853 'playlist_mincount': 30,
5854 'info_dict': {
5855 'id': 'royalty free music - songs',
5856 'title': 'royalty free music - songs',
5857 },
5858 'params': {'extract_flat': 'in_playlist'}
5859 }, {
5860 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5861 'playlist_mincount': 30,
5862 'info_dict': {
5863 'id': 'royalty free music - community playlists',
5864 'title': 'royalty free music - community playlists',
5865 },
5866 'params': {'extract_flat': 'in_playlist'}
5867 }]
5868
5869 _SECTIONS = {
5870 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5871 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5872 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5873 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5874 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5875 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5876 }
5877
5878 def _real_extract(self, url):
5879 qs = parse_qs(url)
5880 query = (qs.get('search_query') or qs.get('q'))[0]
5881 params = qs.get('sp', (None,))[0]
5882 if params:
5883 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5884 else:
ac668111 5885 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 5886 params = self._SECTIONS.get(section)
5887 if not params:
5888 section = None
5889 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5890 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5891
5892
182bda88 5893class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5894 """
25f14e9f 5895 Base class for feed extractors
82d02080 5896 Subclasses must re-define the _FEED_NAME property.
d7ae0639 5897 """
b2e8bc1b 5898 _LOGIN_REQUIRED = True
82d02080 5899 _FEED_NAME = 'feeds'
a25bca9f 5900
5901 def _real_initialize(self):
5902 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 5903
82d02080 5904 @classproperty
d7ae0639 5905 def IE_NAME(self):
82d02080 5906 return f'youtube:{self._FEED_NAME}'
04cc9617 5907
3853309f 5908 def _real_extract(self, url):
3d3dddc9 5909 return self.url_result(
182bda88 5910 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5911
5912
ef2f3c7f 5913class YoutubeWatchLaterIE(InfoExtractor):
5914 IE_NAME = 'youtube:watchlater'
96565c7e 5915 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5916 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5917 _TESTS = [{
8bdd16b4 5918 'url': ':ytwatchlater',
bc7a9cd8
S
5919 'only_matching': True,
5920 }]
25f14e9f
S
5921
5922 def _real_extract(self, url):
ef2f3c7f 5923 return self.url_result(
5924 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5925
5926
25f14e9f 5927class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5928 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5929 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5930 _FEED_NAME = 'recommended'
45db527f 5931 _LOGIN_REQUIRED = False
3d3dddc9 5932 _TESTS = [{
5933 'url': ':ytrec',
5934 'only_matching': True,
5935 }, {
5936 'url': ':ytrecommended',
5937 'only_matching': True,
5938 }, {
5939 'url': 'https://youtube.com',
5940 'only_matching': True,
5941 }]
1ed5b5c9 5942
1ed5b5c9 5943
25f14e9f 5944class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5945 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5946 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5947 _FEED_NAME = 'subscriptions'
3d3dddc9 5948 _TESTS = [{
5949 'url': ':ytsubs',
5950 'only_matching': True,
5951 }, {
5952 'url': ':ytsubscriptions',
5953 'only_matching': True,
5954 }]
1ed5b5c9 5955
1ed5b5c9 5956
25f14e9f 5957class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5958 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5959 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5960 _FEED_NAME = 'history'
3d3dddc9 5961 _TESTS = [{
5962 'url': ':ythistory',
5963 'only_matching': True,
5964 }]
1ed5b5c9
JMF
5965
5966
6e634cbe 5967class YoutubeStoriesIE(InfoExtractor):
5968 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
5969 IE_NAME = 'youtube:stories'
5970 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
5971 _TESTS = [{
5972 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
5973 'only_matching': True,
5974 }]
5975
5976 def _real_extract(self, url):
5977 playlist_id = f'RLTD{self._match_id(url)}'
5978 return self.url_result(
5979 f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
5980 ie=YoutubeTabIE, video_id=playlist_id)
5981
5982
15870e90
PH
5983class YoutubeTruncatedURLIE(InfoExtractor):
5984 IE_NAME = 'youtube:truncated_url'
5985 IE_DESC = False # Do not list
975d35db 5986 _VALID_URL = r'''(?x)
b95aab84
PH
5987 (?:https?://)?
5988 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5989 (?:watch\?(?:
c4808c60 5990 feature=[a-z_]+|
b95aab84
PH
5991 annotation_id=annotation_[^&]+|
5992 x-yt-cl=[0-9]+|
c1708b89 5993 hl=[^&]*|
287be8c6 5994 t=[0-9]+
b95aab84
PH
5995 )?
5996 |
5997 attribution_link\?a=[^&]+
5998 )
5999 $
975d35db 6000 '''
15870e90 6001
c4808c60 6002 _TESTS = [{
2d3d2997 6003 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 6004 'only_matching': True,
dc2fc736 6005 }, {
2d3d2997 6006 'url': 'https://www.youtube.com/watch?',
dc2fc736 6007 'only_matching': True,
b95aab84
PH
6008 }, {
6009 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6010 'only_matching': True,
6011 }, {
6012 'url': 'https://www.youtube.com/watch?feature=foo',
6013 'only_matching': True,
c1708b89
PH
6014 }, {
6015 'url': 'https://www.youtube.com/watch?hl=en-GB',
6016 'only_matching': True,
287be8c6
PH
6017 }, {
6018 'url': 'https://www.youtube.com/watch?t=2372',
6019 'only_matching': True,
c4808c60
PH
6020 }]
6021
15870e90
PH
6022 def _real_extract(self, url):
6023 raise ExtractorError(
78caa52a
PH
6024 'Did you forget to quote the URL? Remember that & is a meta '
6025 'character in most shells, so you want to put the URL in quotes, '
3867038a 6026 'like youtube-dl '
2d3d2997 6027 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 6028 ' or simply youtube-dl BaW_jenozKc .',
15870e90 6029 expected=True)
772fd5cc
PH
6030
6031
471d0367 6032class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6033 IE_NAME = 'youtube:clip'
471d0367 6034 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6035 _TESTS = [{
6036 # FIXME: Other metadata should be extracted from the clip, not from the base video
6037 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6038 'info_dict': {
6039 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6040 'ext': 'mp4',
6041 'section_start': 29.0,
6042 'section_end': 39.7,
6043 'duration': 10.7,
12a1b225
A
6044 'age_limit': 0,
6045 'availability': 'public',
6046 'categories': ['Gaming'],
6047 'channel': 'Scott The Woz',
6048 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6049 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6050 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6051 'like_count': int,
6052 'playable_in_embed': True,
6053 'tags': 'count:17',
6054 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6055 'title': 'Mobile Games on Console - Scott The Woz',
6056 'upload_date': '20210920',
6057 'uploader': 'Scott The Woz',
6058 'uploader_id': 'scottthewoz',
6059 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6060 'view_count': int,
6061 'live_status': 'not_live',
6062 'channel_follower_count': int
471d0367 6063 }
6064 }]
3cd786db 6065
6066 def _real_extract(self, url):
471d0367 6067 clip_id = self._match_id(url)
6068 _, data = self._extract_webpage(url, clip_id)
6069
6070 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6071 if not video_id:
6072 raise ExtractorError('Unable to find video ID')
6073
6074 clip_data = traverse_obj(data, (
6075 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6076 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6077 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6078 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6079
6080 return {
6081 '_type': 'url_transparent',
6082 'url': f'https://www.youtube.com/watch?v={video_id}',
6083 'ie_key': YoutubeIE.ie_key(),
6084 'id': clip_id,
6085 'section_start': int(clip_data['startTimeMs']) / 1000,
6086 'section_end': int(clip_data['endTimeMs']) / 1000,
6087 }
3cd786db 6088
6089
772fd5cc
PH
6090class YoutubeTruncatedIDIE(InfoExtractor):
6091 IE_NAME = 'youtube:truncated_id'
6092 IE_DESC = False # Do not list
b95aab84 6093 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6094
6095 _TESTS = [{
6096 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6097 'only_matching': True,
6098 }]
6099
6100 def _real_extract(self, url):
6101 video_id = self._match_id(url)
6102 raise ExtractorError(
86e5f3ed 6103 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6104 expected=True)