]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[phantomjs] Add function to execute JS without a DOM
[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}')
580ce007 2515 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 2516
580ce007 2517 if not cache_spec:
2518 code = self._load_player(video_id, player_url)
404f611f 2519 if code:
109dd3b2 2520 res = self._parse_sig_js(code)
ac668111 2521 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 2522 cache_spec = [ord(c) for c in res(test_string)]
9809740b 2523 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 2524
2525 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2526
60064c53 2527 def _print_sig_code(self, func, example_sig):
404f611f 2528 if not self.get_param('youtube_print_sig_code'):
2529 return
2530
edf3e38e
PH
2531 def gen_sig_code(idxs):
2532 def _genslice(start, end, step):
78caa52a 2533 starts = '' if start == 0 else str(start)
8bcc8756 2534 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2535 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2536 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2537
2538 step = None
7af808a5
PH
2539 # Quelch pyflakes warnings - start will be set when step is set
2540 start = '(Never used)'
edf3e38e
PH
2541 for i, prev in zip(idxs[1:], idxs[:-1]):
2542 if step is not None:
2543 if i - prev == step:
2544 continue
2545 yield _genslice(start, prev, step)
2546 step = None
2547 continue
2548 if i - prev in [-1, 1]:
2549 step = i - prev
2550 start = prev
2551 continue
2552 else:
78caa52a 2553 yield 's[%d]' % prev
edf3e38e 2554 if step is None:
78caa52a 2555 yield 's[%d]' % i
edf3e38e
PH
2556 else:
2557 yield _genslice(start, i, step)
2558
ac668111 2559 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2560 cache_res = func(test_string)
edf3e38e 2561 cache_spec = [ord(c) for c in cache_res]
78caa52a 2562 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2563 signature_id_tuple = '(%s)' % (
14f25df2 2564 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2565 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2566 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2567 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2568
e0df6211
PH
2569 def _parse_sig_js(self, jscode):
2570 funcname = self._search_regex(
abefc03f
S
2571 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2572 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
2573 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2574 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2575 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}\(a,\d+\)',
2576 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 2577 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2578 # Obsolete patterns
2579 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2580 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2581 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2582 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2583 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2584 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2585 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2586 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2587 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2588
2589 jsi = JSInterpreter(jscode)
2590 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2591 return lambda s: initial_function([s])
2592
580ce007 2593 def _cached(self, func, *cache_id):
2594 def inner(*args, **kwargs):
2595 if cache_id not in self._player_cache:
2596 try:
2597 self._player_cache[cache_id] = func(*args, **kwargs)
2598 except ExtractorError as e:
2599 self._player_cache[cache_id] = e
2600 except Exception as e:
2601 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
2602
2603 ret = self._player_cache[cache_id]
2604 if isinstance(ret, Exception):
2605 raise ret
2606 return ret
2607 return inner
2608
545cc85d 2609 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2610 """Turn the encrypted s field into a working signature"""
580ce007 2611 extract_sig = self._cached(
2612 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
2613 func = extract_sig(video_id, player_url, s)
2614 self._print_sig_code(func, s)
2615 return func(s)
404f611f 2616
2617 def _decrypt_nsig(self, s, video_id, player_url):
2618 """Turn the encrypted n field into a working signature"""
2619 if player_url is None:
2620 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2621 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2622
580ce007 2623 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
2624 if self.get_param('youtube_print_sig_code'):
2625 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 2626
580ce007 2627 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
2628 ret = extract_nsig(jsi, func_code)(s)
2629
2630 self.write_debug(f'Decrypted nsig {s} => {ret}')
2631 return ret
2632
2633 def _extract_n_function_code(self, video_id, player_url):
404f611f 2634 player_id = self._extract_player_info(player_url)
9809740b 2635 func_code = self.cache.load('youtube-nsig', player_id)
580ce007 2636 jscode = func_code or self._load_player(video_id, player_url)
2637 jsi = JSInterpreter(jscode)
404f611f 2638
2639 if func_code:
580ce007 2640 return jsi, player_id, func_code
404f611f 2641
580ce007 2642 funcname, idx = self._search_regex(
2643 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2644 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2645 if idx:
2646 funcname = json.loads(js_to_json(self._search_regex(
2647 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
2648 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
2649
2650 func_code = jsi.extract_function_code(funcname)
2651 self.cache.store('youtube-nsig', player_id, func_code)
2652 return jsi, player_id, func_code
2653
2654 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 2655 func = jsi.extract_function_from_code(*func_code)
f6ca640b 2656
580ce007 2657 def extract_nsig(s):
f6ca640b 2658 ret = func([s])
2659 if ret.startswith('enhanced_except_'):
2660 raise ExtractorError('Signature function returned an exception')
2661 return ret
580ce007 2662
2663 return extract_nsig
e0df6211 2664
109dd3b2 2665 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2666 """
2667 Extract signatureTimestamp (sts)
2668 Required to tell API what sig/player version is in use.
2669 """
2670 sts = None
2671 if isinstance(ytcfg, dict):
2672 sts = int_or_none(ytcfg.get('STS'))
2673
2674 if not sts:
2675 # Attempt to extract from player
2676 if player_url is None:
2677 error_msg = 'Cannot extract signature timestamp without player_url.'
2678 if fatal:
2679 raise ExtractorError(error_msg)
2680 self.report_warning(error_msg)
2681 return
404f611f 2682 code = self._load_player(video_id, player_url, fatal=fatal)
2683 if code:
109dd3b2 2684 sts = int_or_none(self._search_regex(
2685 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2686 'JS player signature timestamp', group='sts', fatal=fatal))
2687 return sts
2688
11f9be09 2689 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
2690 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2691 label = 'fully ' if is_full else ''
2692 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2693 expected_type=url_or_none)
2694 if not url:
2695 self.report_warning(f'Unable to mark {label}watched')
2696 return
14f25df2 2697 parsed_url = urllib.parse.urlparse(url)
2698 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
2699
2700 # cpn generation algorithm is reverse engineered from base.js.
2701 # In fact it works even with dummy cpn.
2702 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2703 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2704
2705 # # more consistent results setting it to right before the end
2706 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2707
2708 qs.update({
2709 'ver': ['2'],
2710 'cpn': [cpn],
2711 'cmt': video_length,
2712 'el': 'detailpage', # otherwise defaults to "shorts"
2713 })
2714
2715 if is_full:
2716 # these seem to mark watchtime "history" in the real world
2717 # they're required, so send in a single value
2718 qs.update({
2719 'st': video_length,
2720 'et': video_length,
2721 })
2722
14f25df2 2723 url = urllib.parse.urlunparse(
2724 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
2725
2726 self._download_webpage(
2727 url, video_id, f'Marking {label}watched',
2728 'Unable to mark watched', fatal=False)
d77ab8e2 2729
bfd973ec 2730 @classmethod
2731 def _extract_from_webpage(cls, url, webpage):
2732 # Invidious Instances
2733 # https://github.com/yt-dlp/yt-dlp/issues/195
2734 # https://github.com/iv-org/invidious/pull/1730
2735 mobj = re.search(
2736 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2737 webpage)
2738 if mobj:
2739 yield cls.url_result(mobj.group('url'), cls)
2740 raise cls.StopExtraction()
2741
2742 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
2743
2744 # lazyYT YouTube embed
bfd973ec 2745 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
2746 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
2747
2748 # Wordpress "YouTube Video Importer" plugin
bfd973ec 2749 for m in re.findall(r'''(?x)<div[^>]+
2750 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2751 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
2752 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 2753
97665381
PH
2754 @classmethod
2755 def extract_id(cls, url):
ae61d108 2756 video_id = cls.get_temp_id(url)
2757 if not video_id:
2758 raise ExtractorError(f'Invalid URL: {url}')
2759 return video_id
c5e8d7af 2760
7c365c21 2761 def _extract_chapters_from_json(self, data, duration):
2762 chapter_list = traverse_obj(
2763 data, (
2764 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2765 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2766 ), expected_type=list)
2767
2768 return self._extract_chapters(
2769 chapter_list,
2770 chapter_time=lambda chapter: float_or_none(
2771 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2772 chapter_title=lambda chapter: traverse_obj(
2773 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2774 duration=duration)
2775
2776 def _extract_chapters_from_engagement_panel(self, data, duration):
2777 content_list = traverse_obj(
8bdd16b4 2778 data,
7c365c21 2779 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2780 expected_type=list, default=[])
052e1350 2781 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2782 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2783
1890fc63 2784 return next(filter(None, (
2785 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2786 chapter_time, chapter_title, duration)
2787 for contents in content_list)), [])
7c365c21 2788
1890fc63 2789 def _extract_chapters_from_description(self, description, duration):
2790 return self._extract_chapters(
2791 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2792 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2793 duration=duration, strict=False)
84213ea8 2794
1890fc63 2795 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2796 if not duration:
2797 return
2798 chapter_list = [{
2799 'start_time': chapter_time(chapter),
2800 'title': chapter_title(chapter),
2801 } for chapter in chapter_list or []]
2802 if not strict:
2803 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2804
a3976e07 2805 chapters = [{'start_time': 0}]
1890fc63 2806 for idx, chapter in enumerate(chapter_list):
a3976e07 2807 if chapter['start_time'] is None:
1890fc63 2808 self.report_warning(f'Incomplete chapter {idx}')
2809 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
1890fc63 2810 chapters.append(chapter)
2811 else:
2812 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}"')
a3976e07 2813 return chapters[1:]
84213ea8 2814
a1c5d2ca
M
2815 def _extract_comment(self, comment_renderer, parent=None):
2816 comment_id = comment_renderer.get('commentId')
2817 if not comment_id:
2818 return
fe93e2c4 2819
052e1350 2820 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2821
49bd8c66 2822 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2823 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2824 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca 2825 author_id = try_get(comment_renderer,
14f25df2 2826 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
fe93e2c4 2827
49bd8c66 2828 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
14f25df2 2829 lambda x: x['likeCount']), str)) or 0
a1c5d2ca 2830 author_thumbnail = try_get(comment_renderer,
14f25df2 2831 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
a1c5d2ca
M
2832
2833 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2834 is_favorited = 'creatorHeart' in (try_get(
2835 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2836 return {
2837 'id': comment_id,
2838 'text': text,
d92f5d5a 2839 'timestamp': timestamp,
a1c5d2ca
M
2840 'time_text': time_text,
2841 'like_count': votes,
97524332 2842 'is_favorited': is_favorited,
a1c5d2ca
M
2843 'author': author,
2844 'author_id': author_id,
2845 'author_thumbnail': author_thumbnail,
2846 'author_is_uploader': author_is_uploader,
2847 'parent': parent or 'root'
2848 }
2849
46383212 2850 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2851
2852 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2853
2854 def extract_header(contents):
2d6659b9 2855 _continuation = None
2856 for content in contents:
46383212 2857 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2858 expected_comment_count = self._get_count(
2859 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2860
2d6659b9 2861 if expected_comment_count:
46383212 2862 tracker['est_total'] = expected_comment_count
2863 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2864 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2865
2866 sort_menu_item = try_get(
2867 comments_header_renderer,
2868 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2869 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2870
2871 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2872 if not _continuation:
2873 continue
2874
46383212 2875 sort_text = str_or_none(sort_menu_item.get('title'))
2876 if not sort_text:
2d6659b9 2877 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2878 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2879 break
a2160aa4 2880 return _continuation
a1c5d2ca 2881
2d6659b9 2882 def extract_thread(contents):
a1c5d2ca 2883 if not parent:
46383212 2884 tracker['current_page_thread'] = 0
a1c5d2ca 2885 for content in contents:
46383212 2886 if not parent and tracker['total_parent_comments'] >= max_parents:
2887 yield
a1c5d2ca 2888 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2889 comment_renderer = get_first(
2890 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2891 expected_type=dict, default={})
a1c5d2ca 2892
a1c5d2ca
M
2893 comment = self._extract_comment(comment_renderer, parent)
2894 if not comment:
2895 continue
46383212 2896
2897 tracker['running_total'] += 1
2898 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2899 yield comment
46383212 2900
a1c5d2ca
M
2901 # Attempt to get the replies
2902 comment_replies_renderer = try_get(
2903 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2904
2905 if comment_replies_renderer:
46383212 2906 tracker['current_page_thread'] += 1
a1c5d2ca 2907 comment_entries_iter = self._comment_entries(
99e9e001 2908 comment_replies_renderer, ytcfg, video_id,
46383212 2909 parent=comment.get('id'), tracker=tracker)
86e5f3ed 2910 yield from itertools.islice(comment_entries_iter, min(
2911 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 2912
46383212 2913 # Keeps track of counts across recursive calls
2914 if not tracker:
2915 tracker = dict(
2916 running_total=0,
2917 est_total=0,
2918 current_page_thread=0,
2919 total_parent_comments=0,
2920 total_reply_comments=0)
2921
2922 # TODO: Deprecated
2d6659b9 2923 # YouTube comments have a max depth of 2
46383212 2924 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2925 if max_depth:
2926 self._downloader.deprecation_warning(
2927 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2928 if max_depth == 1 and parent:
2929 return
a1c5d2ca 2930
46383212 2931 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2932 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2933
46383212 2934 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2935
46383212 2936 response = None
6e634cbe 2937 is_forced_continuation = False
2d6659b9 2938 is_first_continuation = parent is None
6e634cbe 2939 if is_first_continuation and not continuation:
2940 # Sometimes you can get comments by generating the continuation yourself,
2941 # even if YouTube initially reports them being disabled - e.g. stories comments.
2942 # Note: if the comment section is actually disabled, YouTube may return a response with
2943 # required check_get_keys missing. So we will disable that check initially in this case.
2944 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2945 is_forced_continuation = True
a1c5d2ca
M
2946
2947 for page_num in itertools.count(0):
2948 if not continuation:
2949 break
46383212 2950 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2951 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2952 if page_num == 0:
2953 if is_first_continuation:
2954 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2955 else:
2d6659b9 2956 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2957 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2958 else:
2959 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2960 ' ' if parent else '', ' replies' if parent else '',
2961 page_num, comment_prog_str)
2962
2963 response = self._extract_response(
fe93e2c4 2964 item_id=None, query=continuation,
2d6659b9 2965 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
6e634cbe 2966 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2967 is_forced_continuation = False
46383212 2968 continuation_contents = traverse_obj(
2969 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2970
2d6659b9 2971 continuation = None
46383212 2972 for continuation_section in continuation_contents:
2973 continuation_items = traverse_obj(
2974 continuation_section,
2975 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2976 get_all=False, expected_type=list) or []
2977 if is_first_continuation:
2978 continuation = extract_header(continuation_items)
2979 is_first_continuation = False
2d6659b9 2980 if continuation:
a1c5d2ca 2981 break
46383212 2982 continue
a1c5d2ca 2983
46383212 2984 for entry in extract_thread(continuation_items):
2985 if not entry:
2986 return
2987 yield entry
2988 continuation = self._extract_continuation({'contents': continuation_items})
2989 if continuation:
2d6659b9 2990 break
a1c5d2ca 2991
6e634cbe 2992 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2993 if message and not parent and tracker['running_total'] == 0:
2994 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
2995
2996 @staticmethod
2997 def _generate_comment_continuation(video_id):
2998 """
2999 Generates initial comment section continuation token from given video id
3000 """
3001 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3002 return base64.b64encode(token.encode()).decode()
3003
a2160aa4 3004 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3005 """Entry for comment extraction"""
2d6659b9 3006 def _real_comment_extract(contents):
aae16f6e 3007 renderer = next((
3008 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3009 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3010 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3011
a2160aa4 3012 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3013 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3014
109dd3b2 3015 @staticmethod
99e9e001 3016 def _get_checkok_params():
3017 return {'contentCheckOk': True, 'racyCheckOk': True}
3018
3019 @classmethod
3020 def _generate_player_context(cls, sts=None):
109dd3b2 3021 context = {
3022 'html5Preference': 'HTML5_PREF_WANTS',
3023 }
3024 if sts is not None:
3025 context['signatureTimestamp'] = sts
3026 return {
3027 'playbackContext': {
3028 'contentPlaybackContext': context
a1a7907b 3029 },
99e9e001 3030 **cls._get_checkok_params()
109dd3b2 3031 }
3032
e7e94f2a
D
3033 @staticmethod
3034 def _is_agegated(player_response):
3035 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3036 return True
e7e94f2a
D
3037
3038 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3039 AGE_GATE_REASONS = (
3040 'confirm your age', 'age-restricted', 'inappropriate', # reason
3041 'age_verification_required', 'age_check_required', # status
3042 )
3043 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3044
3045 @staticmethod
3046 def _is_unplayable(player_response):
3047 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3048
99e9e001 3049 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 3050
11f9be09 3051 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3052 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3053 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3054 headers = self.generate_api_headers(
99e9e001 3055 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3056
6e634cbe 3057 yt_query = {
3058 'videoId': video_id,
3059 'params': '8AEB' # enable stories
3060 }
11f9be09 3061 yt_query.update(self._generate_player_context(sts))
3062 return self._extract_response(
3063 item_id=video_id, ep='player', query=yt_query,
379e44ed 3064 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3065 default_client=client,
11f9be09 3066 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3067 ) or None
3068
11f9be09 3069 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3070 requested_clients = []
d0d012d4 3071 default = ['android', 'web']
000c15a4 3072 allowed_clients = sorted(
86e5f3ed 3073 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3074 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3075 for client in self._configuration_arg('player_client'):
3076 if client in allowed_clients:
3077 requested_clients.append(client)
d0d012d4 3078 elif client == 'default':
3079 requested_clients.extend(default)
b4c055ba 3080 elif client == 'all':
3081 requested_clients.extend(allowed_clients)
3082 else:
3083 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3084 if not requested_clients:
d0d012d4 3085 requested_clients = default
cf7e015f 3086
11f9be09 3087 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3088 requested_clients.extend(
e7e94f2a 3089 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3090
11f9be09 3091 return orderedSet(requested_clients)
cf7e015f 3092
99e9e001 3093 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 3094 initial_pr = None
3095 if webpage:
b7c47b74 3096 initial_pr = self._search_json(
3097 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3098
ae729626 3099 all_clients = set(clients)
c0bc527b 3100 clients = clients[::-1]
b6de707d 3101 prs = []
e7e94f2a 3102
ae729626 3103 def append_client(*client_names):
e7870111 3104 """ Append the first client name that exists but not already used """
ae729626 3105 for client_name in client_names:
e7870111
D
3106 actual_client = _split_innertube_client(client_name)[0]
3107 if actual_client in INNERTUBE_CLIENTS:
3108 if actual_client not in all_clients:
ae729626 3109 clients.append(client_name)
e7870111
D
3110 all_clients.add(actual_client)
3111 return
e7e94f2a 3112
379e44ed 3113 # Android player_response does not have microFormats which are needed for
3114 # extraction of some data. So we return the initial_pr with formats
3115 # stripped out even if not requested by the user
3116 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3117 if initial_pr:
3118 pr = dict(initial_pr)
3119 pr['streamingData'] = None
b6de707d 3120 prs.append(pr)
379e44ed 3121
3122 last_error = None
b6de707d 3123 tried_iframe_fallback = False
3124 player_url = None
c0bc527b 3125 while clients:
e7870111 3126 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3127 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3128 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3129 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3130
b6de707d 3131 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3132 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3133 if 'js' in self._configuration_arg('player_skip'):
3134 require_js_player = False
3135 player_url = None
3136
3137 if not player_url and not tried_iframe_fallback and require_js_player:
3138 player_url = self._download_player_url(video_id)
3139 tried_iframe_fallback = True
3140
379e44ed 3141 try:
3142 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 3143 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 3144 except ExtractorError as e:
3145 if last_error:
3146 self.report_warning(last_error)
3147 last_error = e
3148 continue
3149
11f9be09 3150 if pr:
a3e96421 3151 # YouTube may return a different video player response than expected.
3152 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3153 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3154 if pr_video_id and pr_video_id != video_id:
3155 self.report_warning(
c7dcf0b3 3156 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3157 else:
3158 prs.append(pr)
c0bc527b 3159
e7e94f2a 3160 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3161 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3162 append_client(f'{base_client}_creator')
e7e94f2a 3163 elif self._is_agegated(pr):
e7870111
D
3164 if variant == 'tv_embedded':
3165 append_client(f'{base_client}_embedded')
3166 elif not variant:
3167 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3168
379e44ed 3169 if last_error:
b6de707d 3170 if not len(prs):
379e44ed 3171 raise last_error
3172 self.report_warning(last_error)
b6de707d 3173 return prs, player_url
11f9be09 3174
c646d76f 3175 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3176 itags, stream_ids = {}, []
5c6d2ef9 3177 itag_qualities, res_qualities = {}, {0: -1}
d3fc8074 3178 q = qualities([
2a9c6dcd 3179 # Normally tiny is the smallest video-only formats. But
3180 # audio-only formats with unknown quality may get tagged as tiny
3181 'tiny',
3182 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3183 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3184 ])
11f9be09 3185 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3186
545cc85d 3187 for fmt in streaming_formats:
727029c5 3188 if fmt.get('targetDurationSec'):
545cc85d 3189 continue
321bf820 3190
cc2db878 3191 itag = str_or_none(fmt.get('itag'))
9297939e 3192 audio_track = fmt.get('audioTrack') or {}
3193 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3194 if stream_id in stream_ids:
3195 continue
3196
cc2db878 3197 quality = fmt.get('quality')
2a9c6dcd 3198 height = int_or_none(fmt.get('height'))
d3fc8074 3199 if quality == 'tiny' or not quality:
3200 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3201 # The 3gp format (17) in android client has a quality of "small",
3202 # but is actually worse than other formats
3203 if itag == '17':
3204 quality = 'tiny'
3205 if quality:
3206 if itag:
3207 itag_qualities[itag] = quality
3208 if height:
3209 res_qualities[height] = quality
cc2db878 3210 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3211 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3212 # number of fragment that would subsequently requested with (`&sq=N`)
3213 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3214 continue
3215
545cc85d 3216 fmt_url = fmt.get('url')
3217 if not fmt_url:
14f25df2 3218 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3219 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3220 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3221 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3222 continue
52023f12 3223 try:
3224 fmt_url += '&%s=%s' % (
3225 traverse_obj(sc, ('sp', -1)) or 'signature',
3226 self._decrypt_signature(encrypted_sig, video_id, player_url)
3227 )
3228 except ExtractorError as e:
580ce007 3229 self.report_warning('Signature extraction failed: Some formats may be missing',
3230 video_id=video_id, only_once=True)
52023f12 3231 self.write_debug(e, only_once=True)
201e9eaa 3232 continue
545cc85d 3233
404f611f 3234 query = parse_qs(fmt_url)
3235 throttled = False
b2916526 3236 if query.get('n'):
404f611f 3237 try:
580ce007 3238 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3239 fmt_url = update_url_query(fmt_url, {
580ce007 3240 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3241 })
404f611f 3242 except ExtractorError as e:
aa9369a2 3243 self.report_warning(
1d485a1a 3244 'nsig extraction failed: You may experience throttling for some formats\n'
580ce007 3245 f'n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
52023f12 3246 self.write_debug(e, only_once=True)
404f611f 3247 throttled = True
3248
545cc85d 3249 if itag:
a0bb6ce5 3250 itags[itag] = 'https'
9297939e 3251 stream_ids.append(stream_id)
3252
0ad92dfb 3253 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3254 language_preference = (
3255 10 if audio_track.get('audioIsDefault') and 10
3256 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3257 else -1)
0ad92dfb 3258 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3259 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3260 # Make sure to avoid false positives with small duration differences.
62b58c09 3261 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3262 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3263 if is_damaged:
0f06bcd7 3264 self.report_warning(
3265 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3266 dct = {
3267 'asr': int_or_none(fmt.get('audioSampleRate')),
3268 'filesize': int_or_none(fmt.get('contentLength')),
3269 'format_id': itag,
34921b43 3270 'format_note': join_nonempty(
26e8e044 3271 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3272 ' (default)' if language_preference > 0 else ''),
404f611f 3273 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
a4166234 3274 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3275 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
0ad92dfb 3276 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3277 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3278 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3279 'fps': int_or_none(fmt.get('fps')) or None,
a4166234 3280 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3281 'height': height,
dca3ff4a 3282 'quality': q(quality),
727029c5 3283 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3284 'tbr': tbr,
545cc85d 3285 'url': fmt_url,
2a9c6dcd 3286 'width': int_or_none(fmt.get('width')),
ab6df717 3287 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3288 'desc' if language_preference < -1 else ''),
3289 'language_preference': language_preference,
a405b38f 3290 # Strictly de-prioritize damaged and 3gp formats
3291 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3292 }
60bdb7bd 3293 mime_mobj = re.match(
3294 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3295 if mime_mobj:
3296 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3297 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3298 no_audio = dct.get('acodec') == 'none'
3299 no_video = dct.get('vcodec') == 'none'
3300 if no_audio:
3301 dct['vbr'] = tbr
3302 if no_video:
3303 dct['abr'] = tbr
3304 if no_audio or no_video:
545cc85d 3305 dct['downloader_options'] = {
3306 # Youtube throttles chunks >~10M
3307 'http_chunk_size': 10485760,
bf1317d2 3308 }
7c60c33e 3309 if dct.get('ext'):
3310 dct['container'] = dct['ext'] + '_dash'
11f9be09 3311 yield dct
545cc85d 3312
adbc4ec4 3313 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3314 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3315 if not self.get_param('youtube_include_hls_manifest', True):
3316 skip_manifests.append('hls')
0f06bcd7 3317 if not self.get_param('youtube_include_dash_manifest', True):
3318 skip_manifests.append('dash')
adbc4ec4
THD
3319 get_dash = 'dash' not in skip_manifests and (
3320 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3321 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3322
a0bb6ce5 3323 def process_manifest_format(f, proto, itag):
3324 if itag in itags:
3325 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3326 return False
3327 itag = f'{itag}-{proto}'
3328 if itag:
3329 f['format_id'] = itag
3330 itags[itag] = proto
3331
5c6d2ef9 3332 f['quality'] = itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1)
3333 if f['quality'] == -1 and f.get('height'):
3334 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
a0bb6ce5 3335 return True
2a9c6dcd 3336
c646d76f 3337 subtitles = {}
11f9be09 3338 for sd in streaming_data:
5d3a0e79 3339 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3340 if hls_manifest_url:
c646d76f 3341 fmts, subs = self._extract_m3u8_formats_and_subtitles(hls_manifest_url, video_id, 'mp4', fatal=False, live=is_live)
3342 subtitles = self._merge_subtitles(subs, subtitles)
3343 for f in fmts:
a0bb6ce5 3344 if process_manifest_format(f, 'hls', self._search_regex(
3345 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3346 yield f
545cc85d 3347
5d3a0e79 3348 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3349 if dash_manifest_url:
c646d76f 3350 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3351 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3352 for f in formats:
a0bb6ce5 3353 if process_manifest_format(f, 'dash', f['format_id']):
3354 f['filesize'] = int_or_none(self._search_regex(
3355 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3356 if live_from_start:
3357 f['is_from_start'] = True
3358
a0bb6ce5 3359 yield f
c646d76f 3360 yield subtitles
11f9be09 3361
720c3099 3362 def _extract_storyboard(self, player_responses, duration):
3363 spec = get_first(
3364 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3365 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3366 if not base_url:
720c3099 3367 return
720c3099 3368 L = len(spec) - 1
3369 for i, args in enumerate(spec):
3370 args = args.split('#')
3371 counts = list(map(int_or_none, args[:5]))
3372 if len(args) != 8 or not all(counts):
3373 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3374 continue
3375 width, height, frame_count, cols, rows = counts
3376 N, sigh = args[6:]
3377
3378 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3379 fragment_count = frame_count / (cols * rows)
3380 fragment_duration = duration / fragment_count
3381 yield {
3382 'format_id': f'sb{i}',
3383 'format_note': 'storyboard',
3384 'ext': 'mhtml',
3385 'protocol': 'mhtml',
3386 'acodec': 'none',
3387 'vcodec': 'none',
3388 'url': url,
3389 'width': width,
3390 'height': height,
45e8a04e 3391 'fps': frame_count / duration,
3392 'rows': rows,
3393 'columns': cols,
720c3099 3394 'fragments': [{
b3edc806 3395 'url': url.replace('$M', str(j)),
720c3099 3396 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3397 } for j in range(math.ceil(fragment_count))],
3398 }
3399
adbc4ec4 3400 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3401 webpage = None
3402 if 'webpage' not in self._configuration_arg('player_skip'):
3403 webpage = self._download_webpage(
6e634cbe 3404 webpage_url + '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id, fatal=False)
11f9be09 3405
3406 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3407
b6de707d 3408 player_responses, player_url = self._extract_player_responses(
11f9be09 3409 self._get_requested_clients(url, smuggled_data),
99e9e001 3410 video_id, webpage, master_ytcfg)
11f9be09 3411
adbc4ec4
THD
3412 return webpage, master_ytcfg, player_responses, player_url
3413
a1b2d843 3414 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3415 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3416 is_live = get_first(video_details, 'isLive')
3417 if is_live is None:
3418 is_live = get_first(live_broadcast_details, 'isLiveNow')
3419
3420 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
c646d76f 3421 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, is_live, duration)
adbc4ec4 3422
c646d76f 3423 return live_broadcast_details, is_live, streaming_data, formats, subtitles
adbc4ec4
THD
3424
3425 def _real_extract(self, url):
3426 url, smuggled_data = unsmuggle_url(url, {})
3427 video_id = self._match_id(url)
3428
3429 base_url = self.http_scheme() + '//www.youtube.com/'
3430 webpage_url = base_url + 'watch?v=' + video_id
3431
3432 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3433
11f9be09 3434 playability_statuses = traverse_obj(
3435 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3436
3437 trailer_video_id = get_first(
3438 playability_statuses,
3439 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3440 expected_type=str)
3441 if trailer_video_id:
3442 return self.url_result(
3443 trailer_video_id, self.ie_key(), trailer_video_id)
3444
3445 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3446 if webpage else (lambda x: None))
3447
3448 video_details = traverse_obj(
3449 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3450 microformats = traverse_obj(
3451 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3452 expected_type=dict, default=[])
3453 video_title = (
3454 get_first(video_details, 'title')
3455 or self._get_text(microformats, (..., 'title'))
3456 or search_meta(['og:title', 'twitter:title', 'title']))
3457 video_description = get_first(video_details, 'shortDescription')
3458
d89257f3 3459 multifeed_metadata_list = get_first(
3460 player_responses,
3461 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3462 expected_type=str)
3463 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3464 if self.get_param('noplaylist'):
11f9be09 3465 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3466 else:
3467 entries = []
3468 feed_ids = []
3469 for feed in multifeed_metadata_list.split(','):
3470 # Unquote should take place before split on comma (,) since textual
3471 # fields may contain comma as well (see
3472 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3473 feed_data = urllib.parse.parse_qs(
ac668111 3474 urllib.parse.unquote_plus(feed))
d89257f3 3475
3476 def feed_entry(name):
3477 return try_get(
14f25df2 3478 feed_data, lambda x: x[name][0], str)
d89257f3 3479
3480 feed_id = feed_entry('id')
3481 if not feed_id:
3482 continue
3483 feed_title = feed_entry('title')
3484 title = video_title
3485 if feed_title:
3486 title += ' (%s)' % feed_title
3487 entries.append({
3488 '_type': 'url_transparent',
3489 'ie_key': 'Youtube',
3490 'url': smuggle_url(
3491 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3492 {'force_singlefeed': True}),
3493 'title': title,
3494 })
3495 feed_ids.append(feed_id)
3496 self.to_screen(
3497 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3498 % (', '.join(feed_ids), video_id))
3499 return self.playlist_result(
3500 entries, video_id, video_title, video_description)
11f9be09 3501
a1b2d843 3502 duration = int_or_none(
3503 get_first(video_details, 'lengthSeconds')
3504 or get_first(microformats, 'lengthSeconds')
3505 or parse_duration(search_meta('duration'))) or None
3506
c646d76f 3507 live_broadcast_details, is_live, streaming_data, formats, automatic_captions = \
3508 self._list_formats(video_id, microformats, video_details, player_responses, player_url)
bf1317d2 3509
545cc85d 3510 if not formats:
11f9be09 3511 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3512 self.report_drm(video_id)
11f9be09 3513 pemr = get_first(
3514 playability_statuses,
3515 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3516 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3517 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3518 if subreason:
545cc85d 3519 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3520 countries = get_first(microformats, 'availableCountries')
545cc85d 3521 if not countries:
3522 regions_allowed = search_meta('regionsAllowed')
3523 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3524 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3525 reason += f'. {subreason}'
545cc85d 3526 if reason:
b7da73eb 3527 self.raise_no_formats(reason, expected=True)
bf1317d2 3528
11f9be09 3529 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3530 if not keywords and webpage:
3531 keywords = [
3532 unescapeHTML(m.group('content'))
3533 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3534 for keyword in keywords:
3535 if keyword.startswith('yt:stretch='):
201c1459 3536 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3537 if mobj:
3538 # NB: float is intentional for forcing float division
3539 w, h = (float(v) for v in mobj.groups())
3540 if w > 0 and h > 0:
3541 ratio = w / h
3542 for f in formats:
3543 if f.get('vcodec') != 'none':
3544 f['stretched_ratio'] = ratio
3545 break
a709d873 3546 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3547 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3548 if thumbnail_url:
3549 thumbnails.append({
3550 'url': thumbnail_url,
ff2751ac 3551 })
fccf5021 3552 original_thumbnails = thumbnails.copy()
3553
0ba692ac 3554 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3555 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3556 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3557 thumbnail_names = [
962ffcf8 3558 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 3559 # in resolution, these are not the custom thumbnail. So de-prioritize them
3560 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3561 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3562 ]
cca80fe6 3563 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3564 thumbnails.extend({
3565 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3566 video_id=video_id, name=name, ext=ext,
3567 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3568 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3569 for thumb in thumbnails:
cca80fe6 3570 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3571 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3572 self._remove_duplicate_formats(thumbnails)
fccf5021 3573 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3574
7ea65411 3575 category = get_first(microformats, 'category') or search_meta('genre')
3576 channel_id = str_or_none(
3577 get_first(video_details, 'channelId')
3578 or get_first(microformats, 'externalChannelId')
3579 or search_meta('channelId'))
7ea65411 3580 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3581
3582 live_content = get_first(video_details, 'isLiveContent')
3583 is_upcoming = get_first(video_details, 'isUpcoming')
3584 if is_live is None:
3585 if is_upcoming or live_content is False:
3586 is_live = False
3587 if is_upcoming is None and (live_content or is_live):
3588 is_upcoming = False
adbc4ec4
THD
3589 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3590 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3591 if not duration and live_end_time and live_start_time:
3592 duration = live_end_time - live_start_time
3593
3594 if is_live and self.get_param('live_from_start'):
3595 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3596
720c3099 3597 formats.extend(self._extract_storyboard(player_responses, duration))
3598
31b532a1 3599 # source_preference is lower for throttled/potentially damaged formats
7e798d72 3600 self._sort_formats(formats, (
3601 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'))
720c3099 3602
545cc85d 3603 info = {
3604 'id': video_id,
39ca3b5c 3605 'title': video_title,
545cc85d 3606 'formats': formats,
3607 'thumbnails': thumbnails,
fccf5021 3608 # The best thumbnail that we are sure exists. Prevents unnecessary
3609 # URL checking if user don't care about getting the best possible thumbnail
3610 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3611 'description': video_description,
11f9be09 3612 'uploader': get_first(video_details, 'author'),
545cc85d 3613 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3614 'uploader_url': owner_profile_url,
3615 'channel_id': channel_id,
a70635b8 3616 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3617 'duration': duration,
3618 'view_count': int_or_none(
11f9be09 3619 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3620 or search_meta('interactionCount')),
11f9be09 3621 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3622 'age_limit': 18 if (
11f9be09 3623 get_first(microformats, 'isFamilySafe') is False
545cc85d 3624 or search_meta('isFamilyFriendly') == 'false'
3625 or search_meta('og:restrictions:age') == '18+') else 0,
3626 'webpage_url': webpage_url,
3627 'categories': [category] if category else None,
3628 'tags': keywords,
11f9be09 3629 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3630 'is_live': is_live,
3631 'was_live': (False if is_live or is_upcoming or live_content is False
3632 else None if is_live is None or is_upcoming is None
3633 else live_content),
3634 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3635 'release_timestamp': live_start_time,
545cc85d 3636 }
b477fc13 3637
e325a21a 3638 if get_first(video_details, 'isPostLiveDvr'):
3639 self.write_debug('Video is in Post-Live Manifestless mode')
3640 info['live_status'] = 'post_live'
3641 if (duration or 0) > 4 * 3600:
3642 self.report_warning(
3643 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3644 'This is a known issue and patches are welcome')
3645
c646d76f 3646 subtitles = {}
3944e7af 3647 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3648 if pctr:
ecdc9049 3649 def get_lang_code(track):
3650 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3651 or track.get('languageCode'))
3652
3653 # Converted into dicts to remove duplicates
3654 captions = {
3655 get_lang_code(sub): sub
3656 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3657 translation_languages = {
3658 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3659 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3660
774d79cc 3661 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3662 lang_subs = container.setdefault(lang_code, [])
545cc85d 3663 for fmt in self._SUBTITLE_FORMATS:
3664 query.update({
3665 'fmt': fmt,
3666 })
3667 lang_subs.append({
3668 'ext': fmt,
60f393e4 3669 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3670 'name': sub_name,
545cc85d 3671 })
7e72694b 3672
07b47084 3673 # NB: Constructing the full subtitle dictionary is slow
3674 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
3675 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 3676 for lang_code, caption_track in captions.items():
3677 base_url = caption_track.get('baseUrl')
1235d333 3678 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3679 if not base_url:
3680 continue
ecdc9049 3681 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3682 if caption_track.get('kind') != 'asr':
545cc85d 3683 if not lang_code:
3684 continue
3685 process_language(
ecdc9049 3686 subtitles, base_url, lang_code, lang_name, {})
3687 if not caption_track.get('isTranslatable'):
3688 continue
3944e7af 3689 for trans_code, trans_name in translation_languages.items():
3690 if not trans_code:
545cc85d 3691 continue
1235d333 3692 orig_trans_code = trans_code
ecdc9049 3693 if caption_track.get('kind') != 'asr':
07b47084 3694 if not get_translated_subs:
18e49408 3695 continue
ecdc9049 3696 trans_code += f'-{lang_code}'
a70635b8 3697 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 3698 # Add an "-orig" label to the original language so that it can be distinguished.
3699 # The subs are returned without "-orig" as well for compatibility
1235d333 3700 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3701 process_language(
d49669ac 3702 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3703 # Setting tlang=lang returns damaged subtitles.
d49669ac 3704 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3705 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 3706
3707 info['automatic_captions'] = automatic_captions
3708 info['subtitles'] = subtitles
7e72694b 3709
14f25df2 3710 parsed_url = urllib.parse.urlparse(url)
545cc85d 3711 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 3712 query = urllib.parse.parse_qs(component)
545cc85d 3713 for k, v in query.items():
3714 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3715 d_k += '_time'
3716 if d_k not in info and k in s_ks:
3717 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3718
3719 # Youtube Music Auto-generated description
822b9d9c 3720 if video_description:
1890fc63 3721 mobj = re.search(
3722 r'''(?xs)
3723 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3724 (?P<album>[^\n]+)
3725 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3726 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3727 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3728 .+\nAuto-generated\ by\ YouTube\.\s*$
3729 ''', video_description)
822b9d9c 3730 if mobj:
822b9d9c
RA
3731 release_year = mobj.group('release_year')
3732 release_date = mobj.group('release_date')
3733 if release_date:
3734 release_date = release_date.replace('-', '')
3735 if not release_year:
545cc85d 3736 release_year = release_date[:4]
3737 info.update({
3738 'album': mobj.group('album'.strip()),
3739 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3740 'track': mobj.group('track').strip(),
3741 'release_date': release_date,
cc2db878 3742 'release_year': int_or_none(release_year),
545cc85d 3743 })
7e72694b 3744
545cc85d 3745 initial_data = None
3746 if webpage:
56ba69e4 3747 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 3748 if not initial_data:
99e9e001 3749 query = {'videoId': video_id}
3750 query.update(self._get_checkok_params())
109dd3b2 3751 initial_data = self._extract_response(
3752 item_id=video_id, ep='next', fatal=False,
99e9e001 3753 ytcfg=master_ytcfg, query=query,
3754 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3755 note='Downloading initial data API JSON')
545cc85d 3756
0df111a3 3757 info['comment_count'] = traverse_obj(initial_data, (
3758 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3759 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3760 ), (
3761 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3762 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3763 ), expected_type=int_or_none, get_all=False)
3764
19a03940 3765 try: # This will error if there is no livechat
c60ee3a2 3766 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 3767 except (KeyError, IndexError, TypeError):
3768 pass
3769 else:
ecdc9049 3770 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 3771 # url is needed to set cookies
3772 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 3773 'video_id': video_id,
3774 'ext': 'json',
f6745c49 3775 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3776 }]
545cc85d 3777
3778 if initial_data:
7c365c21 3779 info['chapters'] = (
3780 self._extract_chapters_from_json(initial_data, duration)
3781 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 3782 or self._extract_chapters_from_description(video_description, duration)
7c365c21 3783 or None)
545cc85d 3784
17322130 3785 contents = traverse_obj(
3786 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3787 expected_type=list, default=[])
3788
3789 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3790 if vpir:
3791 stl = vpir.get('superTitleLink')
3792 if stl:
3793 stl = self._get_text(stl)
3794 if try_get(
3795 vpir,
3796 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3797 info['location'] = stl
3798 else:
affc4fef 3799 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 3800 if mobj:
545cc85d 3801 info.update({
17322130 3802 'series': mobj.group(1),
3803 'season_number': int(mobj.group(2)),
3804 'episode_number': int(mobj.group(3)),
545cc85d 3805 })
17322130 3806 for tlb in (try_get(
3807 vpir,
3808 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3809 list) or []):
3810 tbr = tlb.get('toggleButtonRenderer') or {}
3811 for getter, regex in [(
3812 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3813 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3814 lambda x: x['accessibility'],
3815 lambda x: x['accessibilityData']['accessibilityData'],
3816 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3817 label = (try_get(tbr, getter, dict) or {}).get('label')
3818 if label:
3819 mobj = re.match(regex, label)
3820 if mobj:
3821 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3822 break
17322130 3823 sbr_tooltip = try_get(
3824 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3825 if sbr_tooltip:
3826 like_count, dislike_count = sbr_tooltip.split(' / ')
3827 info.update({
3828 'like_count': str_to_int(like_count),
3829 'dislike_count': str_to_int(dislike_count),
3830 })
3831 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3832 if vsir:
3833 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3834 info.update({
3835 'channel': self._get_text(vor, 'title'),
3836 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3837
3838 rows = try_get(
3839 vsir,
3840 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3841 list) or []
3842 multiple_songs = False
3843 for row in rows:
3844 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3845 multiple_songs = True
3846 break
3847 for row in rows:
3848 mrr = row.get('metadataRowRenderer') or {}
3849 mrr_title = mrr.get('title')
3850 if not mrr_title:
3851 continue
3852 mrr_title = self._get_text(mrr, 'title')
3853 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3854 if mrr_title == 'License':
3855 info['license'] = mrr_contents_text
3856 elif not multiple_songs:
3857 if mrr_title == 'Album':
3858 info['album'] = mrr_contents_text
3859 elif mrr_title == 'Artist':
3860 info['artist'] = mrr_contents_text
3861 elif mrr_title == 'Song':
3862 info['track'] = mrr_contents_text
545cc85d 3863
3864 fallbacks = {
3865 'channel': 'uploader',
3866 'channel_id': 'uploader_id',
3867 'channel_url': 'uploader_url',
3868 }
992f9a73 3869
17322130 3870 # The upload date for scheduled, live and past live streams / premieres in microformats
3871 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3872 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3873 upload_date = (
3874 unified_strdate(get_first(microformats, 'uploadDate'))
3875 or unified_strdate(search_meta('uploadDate')))
3876 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
6e634cbe 3877 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date
17322130 3878 info['upload_date'] = upload_date
992f9a73 3879
545cc85d 3880 for to, frm in fallbacks.items():
3881 if not info.get(to):
3882 info[to] = info.get(frm)
3883
3884 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3885 v = info.get(s_k)
3886 if v:
3887 info[d_k] = v
b84071c0 3888
11f9be09 3889 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3890 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3891 is_membersonly = None
b28f8d24 3892 is_premium = None
c224251a
M
3893 if initial_data and is_private is not None:
3894 is_membersonly = False
b28f8d24 3895 is_premium = False
47193e02 3896 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3897 badge_labels = set()
3898 for content in contents:
3899 if not isinstance(content, dict):
3900 continue
3901 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3902 for badge_label in badge_labels:
3903 if badge_label.lower() == 'members only':
3904 is_membersonly = True
3905 elif badge_label.lower() == 'premium':
3906 is_premium = True
3907 elif badge_label.lower() == 'unlisted':
3908 is_unlisted = True
c224251a 3909
c224251a
M
3910 info['availability'] = self._availability(
3911 is_private=is_private,
b28f8d24 3912 needs_premium=is_premium,
c224251a
M
3913 needs_subscription=is_membersonly,
3914 needs_auth=info['age_limit'] >= 18,
3915 is_unlisted=None if is_private is None else is_unlisted)
3916
a2160aa4 3917 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3918
11f9be09 3919 self.mark_watched(video_id, player_responses)
d77ab8e2 3920
545cc85d 3921 return info
c5e8d7af 3922
a61fd4cf 3923
a6213a49 3924class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3925
182bda88 3926 @staticmethod
3927 def passthrough_smuggled_data(func):
3928 def _smuggle(entries, smuggled_data):
3929 for entry in entries:
3930 # TODO: Convert URL to music.youtube instead.
3931 # Do we need to passthrough any other smuggled_data?
3932 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3933 yield entry
3934
3935 @functools.wraps(func)
3936 def wrapper(self, url):
3937 url, smuggled_data = unsmuggle_url(url, {})
3938 if self.is_music_url(url):
3939 smuggled_data['is_music_url'] = True
3940 info_dict = func(self, url, smuggled_data)
3941 if smuggled_data and info_dict.get('entries'):
3942 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3943 return info_dict
3944 return wrapper
3945
a6213a49 3946 def _extract_channel_id(self, webpage):
3947 channel_id = self._html_search_meta(
3948 'channelId', webpage, 'channel id', default=None)
3949 if channel_id:
3950 return channel_id
3951 channel_url = self._html_search_meta(
3952 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3953 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3954 'twitter:app:url:googleplay'), webpage, 'channel url')
3955 return self._search_regex(
3956 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3957 channel_url, 'channel id')
15f6397c 3958
8bdd16b4 3959 @staticmethod
cd7c66cf 3960 def _extract_basic_item_renderer(item):
3961 # Modified from _extract_grid_item_renderer
201c1459 3962 known_basic_renderers = (
a17526e4 3963 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 3964 )
3965 for key, renderer in item.items():
201c1459 3966 if not isinstance(renderer, dict):
cd7c66cf 3967 continue
201c1459 3968 elif key in known_basic_renderers:
3969 return renderer
3970 elif key.startswith('grid') and key.endswith('Renderer'):
3971 return renderer
8bdd16b4 3972
8bdd16b4 3973 def _grid_entries(self, grid_renderer):
3974 for item in grid_renderer['items']:
3975 if not isinstance(item, dict):
39b62db1 3976 continue
cd7c66cf 3977 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3978 if not isinstance(renderer, dict):
3979 continue
052e1350 3980 title = self._get_text(renderer, 'title')
fe93e2c4 3981
8bdd16b4 3982 # playlist
3983 playlist_id = renderer.get('playlistId')
3984 if playlist_id:
3985 yield self.url_result(
3986 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3987 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3988 video_title=title)
201c1459 3989 continue
8bdd16b4 3990 # video
3991 video_id = renderer.get('videoId')
3992 if video_id:
3993 yield self._extract_video(renderer)
201c1459 3994 continue
8bdd16b4 3995 # channel
3996 channel_id = renderer.get('channelId')
3997 if channel_id:
8bdd16b4 3998 yield self.url_result(
3999 'https://www.youtube.com/channel/%s' % channel_id,
4000 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 4001 continue
4002 # generic endpoint URL support
4003 ep_url = urljoin('https://www.youtube.com/', try_get(
4004 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4005 str))
201c1459 4006 if ep_url:
4007 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4008 if ie.suitable(ep_url):
4009 yield self.url_result(
4010 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4011 break
8bdd16b4 4012
16aa9ea4 4013 def _music_reponsive_list_entry(self, renderer):
4014 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4015 if video_id:
4016 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4017 ie=YoutubeIE.ie_key(), video_id=video_id)
4018 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4019 if playlist_id:
4020 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4021 if video_id:
4022 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4023 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4024 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4025 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4026 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4027 if browse_id:
4028 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4029 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4030
3d3dddc9 4031 def _shelf_entries_from_content(self, shelf_renderer):
4032 content = shelf_renderer.get('content')
4033 if not isinstance(content, dict):
8bdd16b4 4034 return
cd7c66cf 4035 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4036 if renderer:
4037 # TODO: add support for nested playlists so each shelf is processed
4038 # as separate playlist
4039 # TODO: this includes only first N items
86e5f3ed 4040 yield from self._grid_entries(renderer)
3d3dddc9 4041 renderer = content.get('horizontalListRenderer')
4042 if renderer:
4043 # TODO
4044 pass
8bdd16b4 4045
29f7c58a 4046 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4047 ep = try_get(
4048 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4049 str)
8bdd16b4 4050 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4051 if shelf_url:
29f7c58a 4052 # Skipping links to another channels, note that checking for
4053 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4054 # will not work
4055 if skip_channels and '/channels?' in shelf_url:
4056 return
052e1350 4057 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4058 yield self.url_result(shelf_url, video_title=title)
4059 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4060 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4061
8bdd16b4 4062 def _playlist_entries(self, video_list_renderer):
4063 for content in video_list_renderer['contents']:
4064 if not isinstance(content, dict):
4065 continue
4066 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4067 if not isinstance(renderer, dict):
4068 continue
4069 video_id = renderer.get('videoId')
4070 if not video_id:
4071 continue
4072 yield self._extract_video(renderer)
07aeced6 4073
3462ffa8 4074 def _rich_entries(self, rich_grid_renderer):
4075 renderer = try_get(
70d5c17b 4076 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 4077 video_id = renderer.get('videoId')
4078 if not video_id:
4079 return
4080 yield self._extract_video(renderer)
4081
8bdd16b4 4082 def _video_entry(self, video_renderer):
4083 video_id = video_renderer.get('videoId')
4084 if video_id:
4085 return self._extract_video(video_renderer)
dacb3a86 4086
ad210f4f 4087 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4088 url = urljoin('https://youtube.com', traverse_obj(
4089 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4090 if url:
4091 return self.url_result(
4092 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4093
8bdd16b4 4094 def _post_thread_entries(self, post_thread_renderer):
4095 post_renderer = try_get(
4096 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4097 if not post_renderer:
4098 return
4099 # video attachment
4100 video_renderer = try_get(
895b0931 4101 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4102 video_id = video_renderer.get('videoId')
4103 if video_id:
4104 entry = self._extract_video(video_renderer)
8bdd16b4 4105 if entry:
4106 yield entry
895b0931 4107 # playlist attachment
4108 playlist_id = try_get(
14f25df2 4109 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4110 if playlist_id:
4111 yield self.url_result(
e28f1c0a 4112 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4113 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4114 # inline video links
4115 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4116 for run in runs:
4117 if not isinstance(run, dict):
4118 continue
4119 ep_url = try_get(
14f25df2 4120 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4121 if not ep_url:
4122 continue
4123 if not YoutubeIE.suitable(ep_url):
4124 continue
4125 ep_video_id = YoutubeIE._match_id(ep_url)
4126 if video_id == ep_video_id:
4127 continue
895b0931 4128 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4129
8bdd16b4 4130 def _post_thread_continuation_entries(self, post_thread_continuation):
4131 contents = post_thread_continuation.get('contents')
4132 if not isinstance(contents, list):
4133 return
4134 for content in contents:
4135 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4136 if isinstance(renderer, dict):
4137 yield from self._post_thread_entries(renderer)
8bdd16b4 4138 continue
6b0b0a28 4139 renderer = content.get('videoRenderer')
4140 if isinstance(renderer, dict):
4141 yield self._video_entry(renderer)
07aeced6 4142
39ed931e 4143 r''' # unused
4144 def _rich_grid_entries(self, contents):
4145 for content in contents:
4146 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4147 if video_renderer:
4148 entry = self._video_entry(video_renderer)
4149 if entry:
4150 yield entry
4151 '''
52efa4b3 4152
a6213a49 4153 def _extract_entries(self, parent_renderer, continuation_list):
4154 # continuation_list is modified in-place with continuation_list = [continuation_token]
4155 continuation_list[:] = [None]
4156 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4157 for content in contents:
4158 if not isinstance(content, dict):
4159 continue
16aa9ea4 4160 is_renderer = traverse_obj(
4161 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4162 expected_type=dict)
a6213a49 4163 if not is_renderer:
4164 renderer = content.get('richItemRenderer')
4165 if renderer:
4166 for entry in self._rich_entries(renderer):
4167 yield entry
4168 continuation_list[0] = self._extract_continuation(parent_renderer)
4169 continue
4170 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4171 for isr_content in isr_contents:
4172 if not isinstance(isr_content, dict):
8bdd16b4 4173 continue
69184e41 4174
a6213a49 4175 known_renderers = {
4176 'playlistVideoListRenderer': self._playlist_entries,
4177 'gridRenderer': self._grid_entries,
a17526e4 4178 'reelShelfRenderer': self._grid_entries,
4179 'shelfRenderer': self._shelf_entries,
16aa9ea4 4180 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4181 'backstagePostThreadRenderer': self._post_thread_entries,
4182 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4183 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4184 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4185 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4186 }
4187 for key, renderer in isr_content.items():
4188 if key not in known_renderers:
4189 continue
4190 for entry in known_renderers[key](renderer):
4191 if entry:
4192 yield entry
4193 continuation_list[0] = self._extract_continuation(renderer)
4194 break
70d5c17b 4195
4196 if not continuation_list[0]:
a6213a49 4197 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4198
a6213a49 4199 if not continuation_list[0]:
4200 continuation_list[0] = self._extract_continuation(parent_renderer)
4201
4202 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4203 continuation_list = [None]
4204 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4205 tab_content = try_get(tab, lambda x: x['content'], dict)
4206 if not tab_content:
4207 return
3462ffa8 4208 parent_renderer = (
29f7c58a 4209 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4210 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4211 yield from extract_entries(parent_renderer)
3462ffa8 4212 continuation = continuation_list[0]
d069eca7 4213
8bdd16b4 4214 for page_num in itertools.count(1):
4215 if not continuation:
4216 break
99e9e001 4217 headers = self.generate_api_headers(
4218 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4219 response = self._extract_response(
86e5f3ed 4220 item_id=f'{item_id} page {page_num}',
fe93e2c4 4221 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4222 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4223
4224 if not response:
8bdd16b4 4225 break
ac56cf38 4226 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4227 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4228 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4229
69184e41 4230 known_continuation_renderers = {
4231 'playlistVideoListContinuation': self._playlist_entries,
4232 'gridContinuation': self._grid_entries,
4233 'itemSectionContinuation': self._post_thread_continuation_entries,
4234 'sectionListContinuation': extract_entries, # for feeds
4235 }
8bdd16b4 4236 continuation_contents = try_get(
69184e41 4237 response, lambda x: x['continuationContents'], dict) or {}
4238 continuation_renderer = None
4239 for key, value in continuation_contents.items():
4240 if key not in known_continuation_renderers:
3462ffa8 4241 continue
69184e41 4242 continuation_renderer = value
4243 continuation_list = [None]
86e5f3ed 4244 yield from known_continuation_renderers[key](continuation_renderer)
69184e41 4245 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4246 break
4247 if continuation_renderer:
4248 continue
c5e8d7af 4249
a1b535bd 4250 known_renderers = {
e4b98809 4251 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4252 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4253 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4254 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4255 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4256 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4257 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4258 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4259 }
cce889b9 4260 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4261 continuation_items = try_get(
cce889b9 4262 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4263 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4264 video_items_renderer = None
4265 for key, value in continuation_item.items():
4266 if key not in known_renderers:
8bdd16b4 4267 continue
a1b535bd 4268 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4269 continuation_list = [None]
86e5f3ed 4270 yield from known_renderers[key][0](video_items_renderer)
9ba5705a 4271 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4272 break
4273 if video_items_renderer:
4274 continue
8bdd16b4 4275 break
9558dcec 4276
8bdd16b4 4277 @staticmethod
7c219ea6 4278 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4279 for tab in tabs:
cd684175 4280 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4281 if renderer.get('selected') is True:
4282 return renderer
2b3c2546 4283 else:
7c219ea6 4284 if fatal:
4285 raise ExtractorError('Unable to find selected tab')
b82f815f 4286
61d3665d 4287 def _extract_uploader(self, data):
8bdd16b4 4288 uploader = {}
61d3665d 4289 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
47193e02 4290 owner = try_get(
4291 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4292 if owner:
61d3665d 4293 owner_text = owner.get('text')
4294 uploader['uploader'] = self._search_regex(
4295 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
47193e02 4296 uploader['uploader_id'] = try_get(
14f25df2 4297 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], str)
47193e02 4298 uploader['uploader_url'] = urljoin(
4299 'https://www.youtube.com/',
14f25df2 4300 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
9c3fe2ef 4301 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4302
ac56cf38 4303 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4304 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4305 tags = []
b60419c5 4306
8bdd16b4 4307 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4308 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4309 renderer = try_get(
4310 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4311 if renderer:
b60419c5 4312 channel_name = renderer.get('title')
4313 channel_url = renderer.get('channelUrl')
4314 channel_id = renderer.get('externalId')
39ed931e 4315 else:
64c0d954 4316 renderer = try_get(
4317 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4318
8bdd16b4 4319 if renderer:
4320 title = renderer.get('title')
ecc97af3 4321 description = renderer.get('description', '')
b60419c5 4322 playlist_id = channel_id
4323 tags = renderer.get('keywords', '').split()
b60419c5 4324
301d07fc 4325 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4326 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4327 def _get_uncropped(url):
4328 return url_or_none((url or '').split('=')[0] + '=s0')
4329
4330 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4331 if avatar_thumbnails:
4332 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4333 if uncropped_avatar:
4334 avatar_thumbnails.append({
4335 'url': uncropped_avatar,
4336 'id': 'avatar_uncropped',
4337 'preference': 1
4338 })
4339
4340 channel_banners = self._extract_thumbnails(
4341 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4342 for banner in channel_banners:
4343 banner['preference'] = -10
4344
4345 if channel_banners:
4346 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4347 if uncropped_banner:
4348 channel_banners.append({
4349 'url': uncropped_banner,
4350 'id': 'banner_uncropped',
4351 'preference': -5
4352 })
4353
4354 primary_thumbnails = self._extract_thumbnails(
a17526e4 4355 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4356
3462ffa8 4357 if playlist_id is None:
70d5c17b 4358 playlist_id = item_id
f0d785d3 4359
4360 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4361 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4362 if title is None:
f0d785d3 4363 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4364 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4365 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4366
b60419c5 4367 metadata = {
4368 'playlist_id': playlist_id,
4369 'playlist_title': title,
4370 'playlist_description': description,
4371 'uploader': channel_name,
4372 'uploader_id': channel_id,
4373 'uploader_url': channel_url,
301d07fc 4374 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4375 'tags': tags,
f0d785d3 4376 'view_count': self._get_count(playlist_stats, 1),
4377 'availability': self._extract_availability(data),
4378 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4379 'playlist_count': self._get_count(playlist_stats, 0),
4380 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4381 }
4382 if not channel_id:
4383 metadata.update(self._extract_uploader(data))
4384 metadata.update({
4385 'channel': metadata['uploader'],
4386 'channel_id': metadata['uploader_id'],
4387 'channel_url': metadata['uploader_url']})
4388 return self.playlist_result(
d069eca7 4389 self._entries(
ac56cf38 4390 selected_tab, playlist_id, ytcfg,
4391 self._extract_account_syncid(ytcfg, data),
4392 self._extract_visitor_data(data, ytcfg)),
b60419c5 4393 **metadata)
73c4ac2c 4394
6e634cbe 4395 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4396 first_id = last_id = response = None
2be71994 4397 for page_num in itertools.count(1):
cd7c66cf 4398 videos = list(self._playlist_entries(playlist))
4399 if not videos:
4400 return
2be71994 4401 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4402 if start >= len(videos):
4403 return
24146491 4404 yield from videos[start:]
2be71994 4405 first_id = first_id or videos[0]['id']
4406 last_id = videos[-1]['id']
79360d99 4407 watch_endpoint = try_get(
4408 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4409 headers = self.generate_api_headers(
4410 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4411 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4412 query = {
4413 'playlistId': playlist_id,
4414 'videoId': watch_endpoint.get('videoId') or last_id,
4415 'index': watch_endpoint.get('index') or len(videos),
4416 'params': watch_endpoint.get('params') or 'OAE%3D'
4417 }
4418 response = self._extract_response(
4419 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4420 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4421 check_get_keys='contents'
4422 )
cd7c66cf 4423 playlist = try_get(
79360d99 4424 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4425
ac56cf38 4426 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4427 title = playlist.get('title') or try_get(
14f25df2 4428 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4429 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4430
4431 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4432 playlist_url = urljoin(url, try_get(
4433 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4434 str))
6e634cbe 4435
4436 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4437 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4438 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4439
4440 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4441 return self.url_result(
4442 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4443 video_title=title)
cd7c66cf 4444
8bdd16b4 4445 return self.playlist_result(
6e634cbe 4446 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4447 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4448
47193e02 4449 def _extract_availability(self, data):
4450 """
4451 Gets the availability of a given playlist/tab.
4452 Note: Unless YouTube tells us explicitly, we do not assume it is public
4453 @param data: response
4454 """
4455 is_private = is_unlisted = None
4456 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4457 badge_labels = self._extract_badges(renderer)
4458
4459 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4460 privacy_dropdown_entries = try_get(
4461 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4462 for renderer_dict in privacy_dropdown_entries:
4463 is_selected = try_get(
4464 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4465 if not is_selected:
4466 continue
052e1350 4467 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4468 if label:
4469 badge_labels.add(label.lower())
4470 break
4471
4472 for badge_label in badge_labels:
4473 if badge_label == 'unlisted':
4474 is_unlisted = True
4475 elif badge_label == 'private':
4476 is_private = True
4477 elif badge_label == 'public':
4478 is_unlisted = is_private = False
4479 return self._availability(is_private, False, False, False, is_unlisted)
4480
4481 @staticmethod
4482 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4483 sidebar_renderer = try_get(
4484 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4485 for item in sidebar_renderer:
4486 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4487 if renderer:
4488 return renderer
4489
ac56cf38 4490 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4491 """
4492 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4493 """
5d342002 4494 browse_id = params = None
47193e02 4495 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4496 if not renderer:
4497 return
4498 menu_renderer = try_get(
4499 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4500 for menu_item in menu_renderer:
4501 if not isinstance(menu_item, dict):
358de58c 4502 continue
47193e02 4503 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4504 text = try_get(
14f25df2 4505 nav_item_renderer, lambda x: x['text']['simpleText'], str)
47193e02 4506 if not text or text.lower() != 'show unavailable videos':
4507 continue
4508 browse_endpoint = try_get(
4509 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4510 browse_id = browse_endpoint.get('browseId')
4511 params = browse_endpoint.get('params')
4512 break
5d342002 4513
11f9be09 4514 headers = self.generate_api_headers(
99e9e001 4515 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4516 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4517 query = {
4518 'params': params or 'wgYCCAA=',
4519 'browseId': browse_id or 'VL%s' % item_id
4520 }
4521 return self._extract_response(
4522 item_id=item_id, headers=headers, query=query,
fe93e2c4 4523 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4524 note='Downloading API JSON with unavailable videos')
358de58c 4525
2762dbb1 4526 @functools.cached_property
a25bca9f 4527 def skip_webpage(self):
4528 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4529
ac56cf38 4530 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 4531 webpage, data = None, None
4532 for retry in self.RetryManager(fatal=fatal):
ac56cf38 4533 try:
be5c1ae8 4534 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 4535 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4536 except ExtractorError as e:
4537 if isinstance(e.cause, network_exceptions):
14f25df2 4538 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 4539 retry.error = e
4540 continue
4541 self._error_or_warning(e, fatal=fatal)
14fdfea9 4542 break
ac56cf38 4543
be5c1ae8 4544 try:
4545 self._extract_and_report_alerts(data)
4546 except ExtractorError as e:
4547 self._error_or_warning(e, fatal=fatal)
4548 break
ac56cf38 4549
be5c1ae8 4550 # Sometimes youtube returns a webpage with incomplete ytInitialData
4551 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4552 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4553 retry.error = ExtractorError('Incomplete yt initial data received')
4554 continue
ac56cf38 4555
cd7c66cf 4556 return webpage, data
4557
a25bca9f 4558 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4559 """Use if failed to extract ytcfg (and data) from initial webpage"""
4560 if not ytcfg and self.is_authenticated:
4561 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4562 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4563 raise ExtractorError(
4564 f'{msg}. If you are not downloading private content, or '
4565 'your cookies are only for the first account and channel,'
4566 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4567 expected=True)
4568 self.report_warning(msg, only_once=True)
4569
ac56cf38 4570 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4571 data = None
a25bca9f 4572 if not self.skip_webpage:
ac56cf38 4573 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4574 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4575 # Reject webpage data if redirected to home page without explicitly requesting
4576 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4577 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4578 if (url != 'https://www.youtube.com/feed/recommended'
4579 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4580 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4581 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4582 if fatal:
4583 raise ExtractorError(msg, expected=True)
4584 self.report_warning(msg, only_once=True)
ac56cf38 4585 if not data:
a25bca9f 4586 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4587 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4588 return data, ytcfg
4589
4590 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4591 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4592 resolve_response = self._extract_response(
4593 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4594 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4595 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4596 for ep_key, ep in endpoints.items():
4597 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4598 if params:
4599 return self._extract_response(
4600 item_id=item_id, query=params, ep=ep, headers=headers,
4601 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4602 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4603 err_note = 'Failed to resolve url (does the playlist exist?)'
4604 if fatal:
4605 raise ExtractorError(err_note, expected=True)
4606 self.report_warning(err_note, item_id)
4607
a6213a49 4608 _SEARCH_PARAMS = None
4609
af5c1c55 4610 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4611 data = {'query': query}
4612 if params is NO_DEFAULT:
4613 params = self._SEARCH_PARAMS
4614 if params:
4615 data['params'] = params
16aa9ea4 4616
4617 content_keys = (
4618 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4619 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4620 # ytmusic search
4621 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4622 ('continuationContents', ),
4623 )
a25bca9f 4624 display_id = f'query "{query}"'
86e5f3ed 4625 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4626 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4627 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4628
a61fd4cf 4629 continuation_list = [None]
a25bca9f 4630 search = None
a6213a49 4631 for page_num in itertools.count(1):
a61fd4cf 4632 data.update(continuation_list[0] or {})
a25bca9f 4633 headers = self.generate_api_headers(
4634 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4635 search = self._extract_response(
a25bca9f 4636 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4637 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4638 slr_contents = traverse_obj(search, *content_keys)
4639 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4640 if not continuation_list[0]:
a6213a49 4641 break
4642
4643
4644class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4645 IE_DESC = 'YouTube Tabs'
4646 _VALID_URL = r'''(?x:
4647 https?://
4648 (?:\w+\.)?
4649 (?:
4650 youtube(?:kids)?\.com|
4651 %(invidious)s
4652 )/
4653 (?:
4654 (?P<channel_type>channel|c|user|browse)/|
4655 (?P<not_channel>
4656 feed/|hashtag/|
4657 (?:playlist|watch)\?.*?\blist=
4658 )|
4659 (?!(?:%(reserved_names)s)\b) # Direct URLs
4660 )
4661 (?P<id>[^/?\#&]+)
4662 )''' % {
4663 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4664 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4665 }
4666 IE_NAME = 'youtube:tab'
4667
4668 _TESTS = [{
4669 'note': 'playlists, multipage',
4670 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4671 'playlist_mincount': 94,
4672 'info_dict': {
4673 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4674 'title': 'Igor Kleiner - Playlists',
a6213a49 4675 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4676 'uploader': 'Igor Kleiner',
a6213a49 4677 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4678 'channel': 'Igor Kleiner',
4679 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4680 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4681 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4682 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4683 'channel_follower_count': int
a6213a49 4684 },
4685 }, {
4686 'note': 'playlists, multipage, different order',
4687 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4688 'playlist_mincount': 94,
4689 'info_dict': {
4690 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4691 'title': 'Igor Kleiner - Playlists',
a6213a49 4692 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4693 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4694 'uploader': 'Igor Kleiner',
4695 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4696 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4697 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4698 'channel': 'Igor Kleiner',
4699 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4700 'channel_follower_count': int
a6213a49 4701 },
4702 }, {
4703 'note': 'playlists, series',
4704 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4705 'playlist_mincount': 5,
4706 'info_dict': {
4707 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4708 'title': '3Blue1Brown - Playlists',
4709 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4710 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4711 'uploader': '3Blue1Brown',
976ae3ea 4712 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4713 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4714 'channel': '3Blue1Brown',
4715 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4716 'tags': ['Mathematics'],
6c73052c 4717 'channel_follower_count': int
a6213a49 4718 },
4719 }, {
4720 'note': 'playlists, singlepage',
4721 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4722 'playlist_mincount': 4,
4723 'info_dict': {
4724 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4725 'title': 'ThirstForScience - Playlists',
4726 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4727 'uploader': 'ThirstForScience',
4728 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4729 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4730 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4731 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4732 'tags': 'count:13',
4733 'channel': 'ThirstForScience',
6c73052c 4734 'channel_follower_count': int
a6213a49 4735 }
4736 }, {
4737 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4738 'only_matching': True,
4739 }, {
4740 'note': 'basic, single video playlist',
4741 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4742 'info_dict': {
4743 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4744 'uploader': 'Sergey M.',
4745 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4746 'title': 'youtube-dl public playlist',
976ae3ea 4747 'description': '',
4748 'tags': [],
4749 'view_count': int,
4750 'modified_date': '20201130',
4751 'channel': 'Sergey M.',
4752 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4753 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4754 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4755 },
4756 'playlist_count': 1,
4757 }, {
4758 'note': 'empty playlist',
4759 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4760 'info_dict': {
4761 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4762 'uploader': 'Sergey M.',
4763 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4764 'title': 'youtube-dl empty playlist',
976ae3ea 4765 'tags': [],
4766 'channel': 'Sergey M.',
4767 'description': '',
4768 'modified_date': '20160902',
4769 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4770 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4771 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4772 },
4773 'playlist_count': 0,
4774 }, {
4775 'note': 'Home tab',
4776 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4777 'info_dict': {
4778 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4779 'title': 'lex will - Home',
4780 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4781 'uploader': 'lex will',
4782 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4783 'channel': 'lex will',
4784 'tags': ['bible', 'history', 'prophesy'],
4785 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4786 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4787 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4788 'channel_follower_count': int
a6213a49 4789 },
4790 'playlist_mincount': 2,
4791 }, {
4792 'note': 'Videos tab',
4793 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4794 'info_dict': {
4795 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4796 'title': 'lex will - Videos',
4797 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4798 'uploader': 'lex will',
4799 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4800 'tags': ['bible', 'history', 'prophesy'],
4801 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4802 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4803 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4804 'channel': 'lex will',
6c73052c 4805 'channel_follower_count': int
a6213a49 4806 },
4807 'playlist_mincount': 975,
4808 }, {
4809 'note': 'Videos tab, sorted by popular',
4810 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4811 'info_dict': {
4812 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4813 'title': 'lex will - Videos',
4814 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4815 'uploader': 'lex will',
4816 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4817 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4818 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4819 'channel': 'lex will',
4820 'tags': ['bible', 'history', 'prophesy'],
4821 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4822 'channel_follower_count': int
a6213a49 4823 },
4824 'playlist_mincount': 199,
4825 }, {
4826 'note': 'Playlists tab',
4827 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4828 'info_dict': {
4829 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4830 'title': 'lex will - Playlists',
4831 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4832 'uploader': 'lex will',
4833 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4834 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4835 'channel': 'lex will',
4836 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4837 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4838 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4839 'channel_follower_count': int
a6213a49 4840 },
4841 'playlist_mincount': 17,
4842 }, {
4843 'note': 'Community tab',
4844 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4845 'info_dict': {
4846 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4847 'title': 'lex will - Community',
4848 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4849 'uploader': 'lex will',
4850 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4851 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4852 'channel': 'lex will',
4853 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4854 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4855 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4856 'channel_follower_count': int
a6213a49 4857 },
4858 'playlist_mincount': 18,
4859 }, {
4860 'note': 'Channels tab',
4861 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4862 'info_dict': {
4863 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4864 'title': 'lex will - Channels',
4865 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4866 'uploader': 'lex will',
4867 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4868 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4869 'channel': 'lex will',
4870 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4871 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4872 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4873 'channel_follower_count': int
a6213a49 4874 },
4875 'playlist_mincount': 12,
4876 }, {
4877 'note': 'Search tab',
4878 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4879 'playlist_mincount': 40,
4880 'info_dict': {
4881 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4882 'title': '3Blue1Brown - Search - linear algebra',
4883 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4884 'uploader': '3Blue1Brown',
4885 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4886 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4887 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4888 'tags': ['Mathematics'],
4889 'channel': '3Blue1Brown',
4890 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4891 'channel_follower_count': int
a6213a49 4892 },
4893 }, {
4894 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4895 'only_matching': True,
4896 }, {
4897 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4898 'only_matching': True,
4899 }, {
4900 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4901 'only_matching': True,
4902 }, {
4903 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4904 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4905 'info_dict': {
4906 'title': '29C3: Not my department',
4907 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4908 'uploader': 'Christiaan008',
4909 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4910 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4911 'tags': [],
4912 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4913 'view_count': int,
4914 'modified_date': '20150605',
4915 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4916 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4917 'channel': 'Christiaan008',
a6213a49 4918 },
4919 'playlist_count': 96,
4920 }, {
4921 'note': 'Large playlist',
4922 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4923 'info_dict': {
4924 'title': 'Uploads from Cauchemar',
4925 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4926 'uploader': 'Cauchemar',
4927 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4928 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4929 'tags': [],
4930 'modified_date': r're:\d{8}',
4931 'channel': 'Cauchemar',
4932 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4933 'view_count': int,
4934 'description': '',
4935 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4936 },
4937 'playlist_mincount': 1123,
976ae3ea 4938 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4939 }, {
4940 'note': 'even larger playlist, 8832 videos',
4941 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4942 'only_matching': True,
4943 }, {
4944 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4945 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4946 'info_dict': {
4947 'title': 'Uploads from Interstellar Movie',
4948 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4949 'uploader': 'Interstellar Movie',
4950 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4951 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4952 'tags': [],
4953 'view_count': int,
4954 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4955 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4956 'channel': 'Interstellar Movie',
4957 'description': '',
4958 'modified_date': r're:\d{8}',
a6213a49 4959 },
4960 'playlist_mincount': 21,
4961 }, {
4962 'note': 'Playlist with "show unavailable videos" button',
4963 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4964 'info_dict': {
4965 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4966 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4967 'uploader': 'Phim Siêu Nhân Nhật Bản',
4968 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4969 'view_count': int,
4970 'channel': 'Phim Siêu Nhân Nhật Bản',
4971 'tags': [],
4972 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4973 'description': '',
4974 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4975 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4976 'modified_date': r're:\d{8}',
a6213a49 4977 },
4978 'playlist_mincount': 200,
976ae3ea 4979 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4980 }, {
4981 'note': 'Playlist with unavailable videos in page 7',
4982 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4983 'info_dict': {
4984 'title': 'Uploads from BlankTV',
4985 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4986 'uploader': 'BlankTV',
4987 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4988 'channel': 'BlankTV',
4989 'channel_url': 'https://www.youtube.com/c/blanktv',
4990 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4991 'view_count': int,
4992 'tags': [],
4993 'uploader_url': 'https://www.youtube.com/c/blanktv',
4994 'modified_date': r're:\d{8}',
4995 'description': '',
a6213a49 4996 },
4997 'playlist_mincount': 1000,
976ae3ea 4998 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4999 }, {
5000 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5001 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5002 'info_dict': {
5003 'title': 'Data Analysis with Dr Mike Pound',
5004 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5005 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5006 'uploader': 'Computerphile',
5007 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5008 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5009 'tags': [],
5010 'view_count': int,
5011 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5012 'channel_url': 'https://www.youtube.com/user/Computerphile',
5013 'channel': 'Computerphile',
a6213a49 5014 },
5015 'playlist_mincount': 11,
5016 }, {
5017 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5018 'only_matching': True,
5019 }, {
5020 'note': 'Playlist URL that does not actually serve a playlist',
5021 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5022 'info_dict': {
5023 'id': 'FqZTN594JQw',
5024 'ext': 'webm',
5025 'title': "Smiley's People 01 detective, Adventure Series, Action",
5026 'uploader': 'STREEM',
5027 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5028 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5029 'upload_date': '20150526',
5030 'license': 'Standard YouTube License',
5031 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5032 'categories': ['People & Blogs'],
5033 'tags': list,
5034 'view_count': int,
5035 'like_count': int,
a6213a49 5036 },
5037 'params': {
5038 'skip_download': True,
5039 },
5040 'skip': 'This video is not available.',
5041 'add_ie': [YoutubeIE.ie_key()],
5042 }, {
5043 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5044 'only_matching': True,
5045 }, {
5046 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5047 'only_matching': True,
5048 }, {
5049 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5050 'info_dict': {
12a1b225 5051 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5052 'ext': 'mp4',
976ae3ea 5053 'title': str,
a6213a49 5054 'uploader': 'Sky News',
5055 'uploader_id': 'skynews',
5056 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5057 'upload_date': r're:\d{8}',
976ae3ea 5058 'description': str,
a6213a49 5059 'categories': ['News & Politics'],
5060 'tags': list,
5061 'like_count': int,
6c73052c 5062 'release_timestamp': 1642502819,
976ae3ea 5063 'channel': 'Sky News',
5064 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5065 'age_limit': 0,
5066 'view_count': int,
6c73052c 5067 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 5068 'playable_in_embed': True,
6c73052c 5069 'release_date': '20220118',
976ae3ea 5070 'availability': 'public',
5071 'live_status': 'is_live',
5072 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 5073 'channel_follower_count': int
a6213a49 5074 },
5075 'params': {
5076 'skip_download': True,
5077 },
976ae3ea 5078 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5079 }, {
5080 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5081 'info_dict': {
5082 'id': 'a48o2S1cPoo',
5083 'ext': 'mp4',
5084 'title': 'The Young Turks - Live Main Show',
5085 'uploader': 'The Young Turks',
5086 'uploader_id': 'TheYoungTurks',
5087 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5088 'upload_date': '20150715',
5089 'license': 'Standard YouTube License',
5090 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5091 'categories': ['News & Politics'],
5092 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5093 'like_count': int,
a6213a49 5094 },
5095 'params': {
5096 'skip_download': True,
5097 },
5098 'only_matching': True,
5099 }, {
5100 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5101 'only_matching': True,
5102 }, {
5103 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5104 'only_matching': True,
5105 }, {
5106 'note': 'A channel that is not live. Should raise error',
5107 'url': 'https://www.youtube.com/user/numberphile/live',
5108 'only_matching': True,
5109 }, {
5110 'url': 'https://www.youtube.com/feed/trending',
5111 'only_matching': True,
5112 }, {
5113 'url': 'https://www.youtube.com/feed/library',
5114 'only_matching': True,
5115 }, {
5116 'url': 'https://www.youtube.com/feed/history',
5117 'only_matching': True,
5118 }, {
5119 'url': 'https://www.youtube.com/feed/subscriptions',
5120 'only_matching': True,
5121 }, {
5122 'url': 'https://www.youtube.com/feed/watch_later',
5123 'only_matching': True,
5124 }, {
5125 'note': 'Recommended - redirects to home page.',
5126 'url': 'https://www.youtube.com/feed/recommended',
5127 'only_matching': True,
5128 }, {
5129 'note': 'inline playlist with not always working continuations',
5130 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5131 'only_matching': True,
5132 }, {
5133 'url': 'https://www.youtube.com/course',
5134 'only_matching': True,
5135 }, {
5136 'url': 'https://www.youtube.com/zsecurity',
5137 'only_matching': True,
5138 }, {
5139 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5140 'only_matching': True,
5141 }, {
5142 'url': 'https://www.youtube.com/TheYoungTurks/live',
5143 'only_matching': True,
5144 }, {
5145 'url': 'https://www.youtube.com/hashtag/cctv9',
5146 'info_dict': {
5147 'id': 'cctv9',
5148 'title': '#cctv9',
976ae3ea 5149 'tags': [],
a6213a49 5150 },
5151 'playlist_mincount': 350,
5152 }, {
5153 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5154 'only_matching': True,
5155 }, {
5156 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5157 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5158 'only_matching': True
5159 }, {
5160 'note': '/browse/ should redirect to /channel/',
5161 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5162 'only_matching': True
5163 }, {
5164 'note': 'VLPL, should redirect to playlist?list=PL...',
5165 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5166 'info_dict': {
5167 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5168 'uploader': 'NoCopyrightSounds',
5169 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5170 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5171 'title': 'NCS : All Releases 💿',
976ae3ea 5172 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5173 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5174 'modified_date': r're:\d{8}',
5175 'view_count': int,
5176 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5177 'tags': [],
5178 'channel': 'NoCopyrightSounds',
a6213a49 5179 },
5180 'playlist_mincount': 166,
976ae3ea 5181 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5182 }, {
5183 'note': 'Topic, should redirect to playlist?list=UU...',
5184 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5185 'info_dict': {
5186 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5187 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5188 'title': 'Uploads from Royalty Free Music - Topic',
5189 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5190 'tags': [],
5191 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5192 'channel': 'Royalty Free Music - Topic',
5193 'view_count': int,
5194 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5195 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5196 'modified_date': r're:\d{8}',
5197 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5198 'description': '',
a6213a49 5199 },
5200 'expected_warnings': [
a6213a49 5201 'The URL does not have a videos tab',
976ae3ea 5202 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5203 ],
5204 'playlist_mincount': 101,
5205 }, {
5206 'note': 'Topic without a UU playlist',
5207 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5208 'info_dict': {
5209 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5210 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5211 'tags': [],
a6213a49 5212 },
5213 'expected_warnings': [
976ae3ea 5214 'the playlist redirect gave error',
a6213a49 5215 ],
5216 'playlist_mincount': 9,
5217 }, {
5218 'note': 'Youtube music Album',
5219 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5220 'info_dict': {
5221 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5222 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5223 'tags': [],
5224 'view_count': int,
5225 'description': '',
5226 'availability': 'unlisted',
5227 'modified_date': r're:\d{8}',
a6213a49 5228 },
5229 'playlist_count': 50,
5230 }, {
5231 'note': 'unlisted single video playlist',
5232 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5233 'info_dict': {
5234 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5235 'uploader': 'colethedj',
5236 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5237 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5238 'availability': 'unlisted',
5239 'tags': [],
12a1b225 5240 'modified_date': '20220418',
976ae3ea 5241 'channel': 'colethedj',
5242 'view_count': int,
5243 'description': '',
5244 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5245 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5246 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5247 },
5248 'playlist_count': 1,
5249 }, {
5250 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5251 'url': 'https://www.youtube.com/feed/recommended',
5252 'info_dict': {
5253 'id': 'recommended',
5254 'title': 'recommended',
6c73052c 5255 'tags': [],
a6213a49 5256 },
5257 'playlist_mincount': 50,
5258 'params': {
5259 'skip_download': True,
5260 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5261 },
5262 }, {
5263 'note': 'API Fallback: /videos tab, sorted by oldest first',
5264 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5265 'info_dict': {
5266 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5267 'title': 'Cody\'sLab - Videos',
5268 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5269 'uploader': 'Cody\'sLab',
5270 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5271 'channel': 'Cody\'sLab',
5272 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5273 'tags': [],
5274 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5275 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5276 'channel_follower_count': int
a6213a49 5277 },
5278 'playlist_mincount': 650,
5279 'params': {
5280 'skip_download': True,
5281 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5282 },
5283 }, {
5284 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5285 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5286 'info_dict': {
5287 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5288 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5289 'title': 'Uploads from Royalty Free Music - Topic',
5290 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5291 'modified_date': r're:\d{8}',
5292 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5293 'description': '',
5294 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5295 'tags': [],
5296 'channel': 'Royalty Free Music - Topic',
5297 'view_count': int,
5298 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5299 },
5300 'expected_warnings': [
976ae3ea 5301 'does not have a videos tab',
5302 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5303 ],
5304 'playlist_mincount': 101,
5305 'params': {
5306 'skip_download': True,
5307 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5308 },
7c219ea6 5309 }, {
5310 'note': 'non-standard redirect to regional channel',
5311 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5312 'only_matching': True
61d3665d 5313 }, {
5314 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5315 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5316 'info_dict': {
5317 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5318 'modified_date': '20220407',
5319 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5320 'tags': [],
5321 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5322 'uploader': 'pukkandan',
5323 'availability': 'unlisted',
5324 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5325 'channel': 'pukkandan',
5326 'description': 'Test for collaborative playlist',
5327 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5328 'view_count': int,
61d3665d 5329 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5330 },
5331 'playlist_mincount': 2
a6213a49 5332 }]
5333
5334 @classmethod
5335 def suitable(cls, url):
86e5f3ed 5336 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5337
64f36541 5338 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5339
182bda88 5340 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5341 def _real_extract(self, url, smuggled_data):
cd7c66cf 5342 item_id = self._match_id(url)
14f25df2 5343 url = urllib.parse.urlunparse(
5344 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5345 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5346
fe03a6cd 5347 def get_mobj(url):
37e57a9f 5348 mobj = self._URL_RE.match(url).groupdict()
07cce701 5349 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5350 return mobj
5351
37e57a9f 5352 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5353 # Youtube returns incomplete data if tabname is not lower case
5354 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5355 if is_channel:
5356 if smuggled_data.get('is_music_url'):
37e57a9f 5357 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5358 item_id = item_id[2:]
37e57a9f 5359 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5360 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5361 mdata = self._extract_tab_endpoint(
37e57a9f 5362 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5363 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
14f25df2 5364 get_all=False, expected_type=str)
ac56cf38 5365 if not murl:
37e57a9f 5366 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5367 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5368 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5369 pre = f'https://www.youtube.com/channel/{item_id}'
5370
64f36541 5371 original_tab_name = tab
fe03a6cd 5372 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5373 # Home URLs should redirect to /videos/
37e57a9f 5374 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5375 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5376 tab = '/videos'
5377
5378 url = ''.join((pre, tab, post))
5379 mobj = get_mobj(url)
cd7c66cf 5380
5381 # Handle both video/playlist URLs
201c1459 5382 qs = parse_qs(url)
86e5f3ed 5383 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5384
fe03a6cd 5385 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5386 if not playlist_id:
fe03a6cd 5387 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5388 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5389 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5390 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5391 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5392 mobj = get_mobj(url)
cd7c66cf 5393
5394 if video_id and playlist_id:
a06916d9 5395 if self.get_param('noplaylist'):
37e57a9f 5396 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5397 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5398 ie=YoutubeIE.ie_key(), video_id=video_id)
5399 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5400
ac56cf38 5401 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5402
7c219ea6 5403 # YouTube may provide a non-standard redirect to the regional channel
5404 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5405 redirect_url = traverse_obj(
5406 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5407 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5408 redirect_url = ''.join((
5409 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5410 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5411 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5412
37e57a9f 5413 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5414 if tabs:
5415 selected_tab = self._extract_selected_tab(tabs)
64f36541 5416 selected_tab_name = selected_tab.get('title', '').lower()
5417 if selected_tab_name == 'home':
5418 selected_tab_name = 'featured'
5419 requested_tab_name = mobj['tab'][1:]
09f1580e 5420 if 'no-youtube-channel-redirect' not in compat_opts:
693f0600 5421 if requested_tab_name == 'live': # Live tab should have redirected to the video
5422 raise UserNotLive(video_id=mobj['id'])
64f36541 5423 if requested_tab_name not in ('', selected_tab_name):
5424 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5425 if not original_tab_name:
5426 if item_id[:2] == 'UC':
5427 # Topic channels don't have /videos. Use the equivalent playlist instead
5428 pl_id = f'UU{item_id[2:]}'
5429 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5430 try:
5431 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5432 except ExtractorError:
5433 redirect_warning += ' and the playlist redirect gave error'
5434 else:
5435 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5436 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5437 if selected_tab_name and selected_tab_name != requested_tab_name:
5438 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5439 else:
5440 raise ExtractorError(redirect_warning, expected=True)
18db7548 5441
37e57a9f 5442 if redirect_warning:
64f36541 5443 self.to_screen(redirect_warning)
37e57a9f 5444 self.write_debug(f'Final URL: {url}')
18db7548 5445
358de58c 5446 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5447 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5448 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5449 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5450 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5451 if tabs:
ac56cf38 5452 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5453
37e57a9f 5454 playlist = traverse_obj(
5455 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5456 if playlist:
ac56cf38 5457 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5458
37e57a9f 5459 video_id = traverse_obj(
5460 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5461 if video_id:
09f1580e 5462 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5463 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5464 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5465 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5466
8bdd16b4 5467 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5468
c5e8d7af 5469
8bdd16b4 5470class YoutubePlaylistIE(InfoExtractor):
96565c7e 5471 IE_DESC = 'YouTube playlists'
8bdd16b4 5472 _VALID_URL = r'''(?x)(?:
5473 (?:https?://)?
5474 (?:\w+\.)?
5475 (?:
5476 (?:
5477 youtube(?:kids)?\.com|
d9190e44 5478 %(invidious)s
8bdd16b4 5479 )
5480 /.*?\?.*?\blist=
5481 )?
5482 (?P<id>%(playlist_id)s)
d9190e44
RH
5483 )''' % {
5484 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5485 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5486 }
8bdd16b4 5487 IE_NAME = 'youtube:playlist'
cdc628a4 5488 _TESTS = [{
8bdd16b4 5489 'note': 'issue #673',
5490 'url': 'PLBB231211A4F62143',
cdc628a4 5491 'info_dict': {
8bdd16b4 5492 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5493 'id': 'PLBB231211A4F62143',
976ae3ea 5494 'uploader': 'Wickman',
8bdd16b4 5495 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5496 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5497 'view_count': int,
5498 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5499 'modified_date': r're:\d{8}',
5500 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5501 'channel': 'Wickman',
5502 'tags': [],
5503 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5504 },
5505 'playlist_mincount': 29,
5506 }, {
5507 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5508 'info_dict': {
5509 'title': 'YDL_safe_search',
5510 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5511 },
5512 'playlist_count': 2,
5513 'skip': 'This playlist is private',
9558dcec 5514 }, {
8bdd16b4 5515 'note': 'embedded',
5516 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5517 'playlist_count': 4,
9558dcec 5518 'info_dict': {
8bdd16b4 5519 'title': 'JODA15',
5520 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5521 'uploader': 'milan',
5522 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5523 'description': '',
5524 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5525 'tags': [],
5526 'modified_date': '20140919',
5527 'view_count': int,
5528 'channel': 'milan',
5529 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5530 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5531 },
5532 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5533 }, {
8bdd16b4 5534 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 5535 'playlist_mincount': 455,
8bdd16b4 5536 'info_dict': {
5537 'title': '2018 Chinese New Singles (11/6 updated)',
5538 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5539 'uploader': 'LBK',
5540 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5541 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5542 'channel': 'LBK',
5543 'view_count': int,
5544 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5545 'tags': [],
5546 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5547 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5548 'modified_date': r're:\d{8}',
5549 },
5550 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5551 }, {
29f7c58a 5552 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5553 'only_matching': True,
5554 }, {
5555 # music album playlist
5556 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5557 'only_matching': True,
5558 }]
5559
5560 @classmethod
5561 def suitable(cls, url):
201c1459 5562 if YoutubeTabIE.suitable(url):
5563 return False
49a57e70 5564 from ..utils import parse_qs
201c1459 5565 qs = parse_qs(url)
5566 if qs.get('v', [None])[0]:
5567 return False
86e5f3ed 5568 return super().suitable(url)
29f7c58a 5569
5570 def _real_extract(self, url):
5571 playlist_id = self._match_id(url)
46953e7e 5572 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5573 url = update_url_query(
5574 'https://www.youtube.com/playlist',
5575 parse_qs(url) or {'list': playlist_id})
5576 if is_music_url:
5577 url = smuggle_url(url, {'is_music_url': True})
5578 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5579
5580
5581class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5582 IE_DESC = 'youtu.be'
29f7c58a 5583 _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}
5584 _TESTS = [{
8bdd16b4 5585 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5586 'info_dict': {
5587 'id': 'yeWKywCrFtk',
5588 'ext': 'mp4',
5589 'title': 'Small Scale Baler and Braiding Rugs',
5590 'uploader': 'Backus-Page House Museum',
5591 'uploader_id': 'backuspagemuseum',
5592 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5593 'upload_date': '20161008',
5594 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5595 'categories': ['Nonprofits & Activism'],
5596 'tags': list,
5597 'like_count': int,
976ae3ea 5598 'age_limit': 0,
5599 'playable_in_embed': True,
5600 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5601 'channel': 'Backus-Page House Museum',
5602 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5603 'live_status': 'not_live',
5604 'view_count': int,
5605 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5606 'availability': 'public',
5607 'duration': 59,
12a1b225
A
5608 'comment_count': int,
5609 'channel_follower_count': int
8bdd16b4 5610 },
5611 'params': {
5612 'noplaylist': True,
5613 'skip_download': True,
5614 },
39e7107d 5615 }, {
8bdd16b4 5616 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5617 'only_matching': True,
cdc628a4
PH
5618 }]
5619
8bdd16b4 5620 def _real_extract(self, url):
5ad28e7f 5621 mobj = self._match_valid_url(url)
29f7c58a 5622 video_id = mobj.group('id')
5623 playlist_id = mobj.group('playlist_id')
8bdd16b4 5624 return self.url_result(
29f7c58a 5625 update_url_query('https://www.youtube.com/watch', {
5626 'v': video_id,
5627 'list': playlist_id,
5628 'feature': 'youtu.be',
5629 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5630
5631
b6ce9bb0 5632class YoutubeLivestreamEmbedIE(InfoExtractor):
5633 IE_DESC = 'YouTube livestream embeds'
5634 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5635 _TESTS = [{
5636 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5637 'only_matching': True,
5638 }]
5639
5640 def _real_extract(self, url):
5641 channel_id = self._match_id(url)
5642 return self.url_result(
5643 f'https://www.youtube.com/channel/{channel_id}/live',
5644 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5645
5646
8bdd16b4 5647class YoutubeYtUserIE(InfoExtractor):
96565c7e 5648 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5649 IE_NAME = 'youtube:user'
8bdd16b4 5650 _VALID_URL = r'ytuser:(?P<id>.+)'
5651 _TESTS = [{
5652 'url': 'ytuser:phihag',
5653 'only_matching': True,
5654 }]
5655
5656 def _real_extract(self, url):
5657 user_id = self._match_id(url)
5658 return self.url_result(
c586f9e8 5659 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5660 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5661
b05654f0 5662
3d3dddc9 5663class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5664 IE_NAME = 'youtube:favorites'
96565c7e 5665 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5666 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5667 _LOGIN_REQUIRED = True
5668 _TESTS = [{
5669 'url': ':ytfav',
5670 'only_matching': True,
5671 }, {
5672 'url': ':ytfavorites',
5673 'only_matching': True,
5674 }]
5675
5676 def _real_extract(self, url):
5677 return self.url_result(
5678 'https://www.youtube.com/playlist?list=LL',
5679 ie=YoutubeTabIE.ie_key())
5680
5681
ca5300c7 5682class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
5683 IE_NAME = 'youtube:notif'
5684 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5685 _VALID_URL = r':ytnotif(?:ication)?s?'
5686 _LOGIN_REQUIRED = True
5687 _TESTS = [{
5688 'url': ':ytnotif',
5689 'only_matching': True,
5690 }, {
5691 'url': ':ytnotifications',
5692 'only_matching': True,
5693 }]
5694
5695 def _extract_notification_menu(self, response, continuation_list):
5696 notification_list = traverse_obj(
5697 response,
5698 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5699 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5700 expected_type=list) or []
5701 continuation_list[0] = None
5702 for item in notification_list:
5703 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
5704 if entry:
5705 yield entry
5706 continuation = item.get('continuationItemRenderer')
5707 if continuation:
5708 continuation_list[0] = continuation
5709
5710 def _extract_notification_renderer(self, notification):
5711 video_id = traverse_obj(
5712 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
5713 url = f'https://www.youtube.com/watch?v={video_id}'
5714 channel_id = None
5715 if not video_id:
5716 browse_ep = traverse_obj(
5717 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
5718 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
5719 post_id = self._search_regex(
5720 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
5721 'post id', default=None)
5722 if not channel_id or not post_id:
5723 return
5724 # The direct /post url redirects to this in the browser
5725 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5726
5727 channel = traverse_obj(
5728 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5729 expected_type=str)
c7a7baaa 5730 notification_title = self._get_text(notification, 'shortMessage')
5731 if notification_title:
5732 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
5733 # TODO: handle recommended videos
ca5300c7 5734 title = self._search_regex(
c7a7baaa 5735 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 5736 'video title', default=None)
ca5300c7 5737 upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d')
5738 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
5739 else None)
5740 return {
5741 '_type': 'url',
5742 'url': url,
5743 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
5744 'video_id': video_id,
5745 'title': title,
5746 'channel_id': channel_id,
5747 'channel': channel,
5748 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5749 'upload_date': upload_date,
5750 }
5751
5752 def _notification_menu_entries(self, ytcfg):
5753 continuation_list = [None]
5754 response = None
5755 for page in itertools.count(1):
5756 ctoken = traverse_obj(
5757 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
5758 response = self._extract_response(
5759 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
5760 ep='notification/get_notification_menu', check_get_keys='actions',
5761 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
5762 yield from self._extract_notification_menu(response, continuation_list)
5763 if not continuation_list[0]:
5764 break
5765
5766 def _real_extract(self, url):
5767 display_id = 'notifications'
5768 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
5769 self._report_playlist_authcheck(ytcfg)
5770 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
5771
5772
a6213a49 5773class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5774 IE_DESC = 'YouTube search'
78caa52a 5775 IE_NAME = 'youtube:search'
b05654f0 5776 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5777 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5778 _TESTS = [{
5779 'url': 'ytsearch5:youtube-dl test video',
5780 'playlist_count': 5,
5781 'info_dict': {
5782 'id': 'youtube-dl test video',
5783 'title': 'youtube-dl test video',
5784 }
5785 }]
b05654f0 5786
a61fd4cf 5787
5f7cb91a 5788class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5789 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5790 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5791 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5792 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5793 _TESTS = [{
5794 'url': 'ytsearchdate5:youtube-dl test video',
5795 'playlist_count': 5,
5796 'info_dict': {
5797 'id': 'youtube-dl test video',
5798 'title': 'youtube-dl test video',
5799 }
5800 }]
75dff0ee 5801
c9ae7b95 5802
a6213a49 5803class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5804 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5805 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5806 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5807 _TESTS = [{
5808 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5809 'playlist_mincount': 5,
5810 'info_dict': {
11f9be09 5811 'id': 'youtube-dl test video',
3462ffa8 5812 'title': 'youtube-dl test video',
5813 }
a61fd4cf 5814 }, {
5815 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5816 'playlist_mincount': 5,
5817 'info_dict': {
5818 'id': 'python',
5819 'title': 'python',
5820 }
ad210f4f 5821 }, {
5822 'url': 'https://www.youtube.com/results?search_query=%23cats',
5823 'playlist_mincount': 1,
5824 'info_dict': {
5825 'id': '#cats',
5826 'title': '#cats',
12a1b225
A
5827 # The test suite does not have support for nested playlists
5828 # 'entries': [{
5829 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5830 # 'title': '#cats',
5831 # }],
ad210f4f 5832 },
3462ffa8 5833 }, {
5834 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5835 'only_matching': True,
5836 }]
5837
5838 def _real_extract(self, url):
4dfbf869 5839 qs = parse_qs(url)
386e1dd9 5840 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5841 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5842
5843
16aa9ea4 5844class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 5845 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 5846 IE_NAME = 'youtube:music:search_url'
5847 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5848 _TESTS = [{
5849 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5850 'playlist_count': 16,
5851 'info_dict': {
5852 'id': 'royalty free music',
5853 'title': 'royalty free music',
5854 }
5855 }, {
5856 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5857 'playlist_mincount': 30,
5858 'info_dict': {
5859 'id': 'royalty free music - songs',
5860 'title': 'royalty free music - songs',
5861 },
5862 'params': {'extract_flat': 'in_playlist'}
5863 }, {
5864 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5865 'playlist_mincount': 30,
5866 'info_dict': {
5867 'id': 'royalty free music - community playlists',
5868 'title': 'royalty free music - community playlists',
5869 },
5870 'params': {'extract_flat': 'in_playlist'}
5871 }]
5872
5873 _SECTIONS = {
5874 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5875 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5876 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5877 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5878 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5879 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5880 }
5881
5882 def _real_extract(self, url):
5883 qs = parse_qs(url)
5884 query = (qs.get('search_query') or qs.get('q'))[0]
5885 params = qs.get('sp', (None,))[0]
5886 if params:
5887 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5888 else:
ac668111 5889 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 5890 params = self._SECTIONS.get(section)
5891 if not params:
5892 section = None
5893 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5894 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5895
5896
182bda88 5897class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5898 """
25f14e9f 5899 Base class for feed extractors
82d02080 5900 Subclasses must re-define the _FEED_NAME property.
d7ae0639 5901 """
b2e8bc1b 5902 _LOGIN_REQUIRED = True
82d02080 5903 _FEED_NAME = 'feeds'
a25bca9f 5904
5905 def _real_initialize(self):
5906 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 5907
82d02080 5908 @classproperty
d7ae0639 5909 def IE_NAME(self):
82d02080 5910 return f'youtube:{self._FEED_NAME}'
04cc9617 5911
3853309f 5912 def _real_extract(self, url):
3d3dddc9 5913 return self.url_result(
182bda88 5914 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5915
5916
ef2f3c7f 5917class YoutubeWatchLaterIE(InfoExtractor):
5918 IE_NAME = 'youtube:watchlater'
96565c7e 5919 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5920 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5921 _TESTS = [{
8bdd16b4 5922 'url': ':ytwatchlater',
bc7a9cd8
S
5923 'only_matching': True,
5924 }]
25f14e9f
S
5925
5926 def _real_extract(self, url):
ef2f3c7f 5927 return self.url_result(
5928 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5929
5930
25f14e9f 5931class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5932 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5933 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5934 _FEED_NAME = 'recommended'
45db527f 5935 _LOGIN_REQUIRED = False
3d3dddc9 5936 _TESTS = [{
5937 'url': ':ytrec',
5938 'only_matching': True,
5939 }, {
5940 'url': ':ytrecommended',
5941 'only_matching': True,
5942 }, {
5943 'url': 'https://youtube.com',
5944 'only_matching': True,
5945 }]
1ed5b5c9 5946
1ed5b5c9 5947
25f14e9f 5948class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5949 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5950 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5951 _FEED_NAME = 'subscriptions'
3d3dddc9 5952 _TESTS = [{
5953 'url': ':ytsubs',
5954 'only_matching': True,
5955 }, {
5956 'url': ':ytsubscriptions',
5957 'only_matching': True,
5958 }]
1ed5b5c9 5959
1ed5b5c9 5960
25f14e9f 5961class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5962 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5963 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5964 _FEED_NAME = 'history'
3d3dddc9 5965 _TESTS = [{
5966 'url': ':ythistory',
5967 'only_matching': True,
5968 }]
1ed5b5c9
JMF
5969
5970
6e634cbe 5971class YoutubeStoriesIE(InfoExtractor):
5972 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
5973 IE_NAME = 'youtube:stories'
5974 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
5975 _TESTS = [{
5976 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
5977 'only_matching': True,
5978 }]
5979
5980 def _real_extract(self, url):
5981 playlist_id = f'RLTD{self._match_id(url)}'
5982 return self.url_result(
5983 f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
5984 ie=YoutubeTabIE, video_id=playlist_id)
5985
5986
15870e90
PH
5987class YoutubeTruncatedURLIE(InfoExtractor):
5988 IE_NAME = 'youtube:truncated_url'
5989 IE_DESC = False # Do not list
975d35db 5990 _VALID_URL = r'''(?x)
b95aab84
PH
5991 (?:https?://)?
5992 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5993 (?:watch\?(?:
c4808c60 5994 feature=[a-z_]+|
b95aab84
PH
5995 annotation_id=annotation_[^&]+|
5996 x-yt-cl=[0-9]+|
c1708b89 5997 hl=[^&]*|
287be8c6 5998 t=[0-9]+
b95aab84
PH
5999 )?
6000 |
6001 attribution_link\?a=[^&]+
6002 )
6003 $
975d35db 6004 '''
15870e90 6005
c4808c60 6006 _TESTS = [{
2d3d2997 6007 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 6008 'only_matching': True,
dc2fc736 6009 }, {
2d3d2997 6010 'url': 'https://www.youtube.com/watch?',
dc2fc736 6011 'only_matching': True,
b95aab84
PH
6012 }, {
6013 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6014 'only_matching': True,
6015 }, {
6016 'url': 'https://www.youtube.com/watch?feature=foo',
6017 'only_matching': True,
c1708b89
PH
6018 }, {
6019 'url': 'https://www.youtube.com/watch?hl=en-GB',
6020 'only_matching': True,
287be8c6
PH
6021 }, {
6022 'url': 'https://www.youtube.com/watch?t=2372',
6023 'only_matching': True,
c4808c60
PH
6024 }]
6025
15870e90
PH
6026 def _real_extract(self, url):
6027 raise ExtractorError(
78caa52a
PH
6028 'Did you forget to quote the URL? Remember that & is a meta '
6029 'character in most shells, so you want to put the URL in quotes, '
3867038a 6030 'like youtube-dl '
2d3d2997 6031 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 6032 ' or simply youtube-dl BaW_jenozKc .',
15870e90 6033 expected=True)
772fd5cc
PH
6034
6035
471d0367 6036class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6037 IE_NAME = 'youtube:clip'
471d0367 6038 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6039 _TESTS = [{
6040 # FIXME: Other metadata should be extracted from the clip, not from the base video
6041 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6042 'info_dict': {
6043 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6044 'ext': 'mp4',
6045 'section_start': 29.0,
6046 'section_end': 39.7,
6047 'duration': 10.7,
12a1b225
A
6048 'age_limit': 0,
6049 'availability': 'public',
6050 'categories': ['Gaming'],
6051 'channel': 'Scott The Woz',
6052 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6053 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6054 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6055 'like_count': int,
6056 'playable_in_embed': True,
6057 'tags': 'count:17',
6058 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6059 'title': 'Mobile Games on Console - Scott The Woz',
6060 'upload_date': '20210920',
6061 'uploader': 'Scott The Woz',
6062 'uploader_id': 'scottthewoz',
6063 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6064 'view_count': int,
6065 'live_status': 'not_live',
6066 'channel_follower_count': int
471d0367 6067 }
6068 }]
3cd786db 6069
6070 def _real_extract(self, url):
471d0367 6071 clip_id = self._match_id(url)
6072 _, data = self._extract_webpage(url, clip_id)
6073
6074 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6075 if not video_id:
6076 raise ExtractorError('Unable to find video ID')
6077
6078 clip_data = traverse_obj(data, (
6079 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6080 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6081 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6082 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6083
6084 return {
6085 '_type': 'url_transparent',
6086 'url': f'https://www.youtube.com/watch?v={video_id}',
6087 'ie_key': YoutubeIE.ie_key(),
6088 'id': clip_id,
6089 'section_start': int(clip_data['startTimeMs']) / 1000,
6090 'section_end': int(clip_data['endTimeMs']) / 1000,
6091 }
3cd786db 6092
6093
772fd5cc
PH
6094class YoutubeTruncatedIDIE(InfoExtractor):
6095 IE_NAME = 'youtube:truncated_id'
6096 IE_DESC = False # Do not list
b95aab84 6097 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6098
6099 _TESTS = [{
6100 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6101 'only_matching': True,
6102 }]
6103
6104 def _real_extract(self, url):
6105 video_id = self._match_id(url)
6106 raise ExtractorError(
86e5f3ed 6107 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6108 expected=True)