]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[extractor/generic] Remove HEAD request
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
6e634cbe 1import base64
d92f5d5a 2import calendar
109dd3b2 3import copy
fe93e2c4 4import datetime
a5c56234 5import hashlib
0ca96d48 6import itertools
c5e8d7af 7import json
720c3099 8import math
c4417ddb 9import os.path
d77ab8e2 10import random
c5e8d7af 11import re
46383212 12import sys
f8271158 13import threading
8a784c74 14import time
e0df6211 15import traceback
14f25df2 16import urllib.error
ac668111 17import urllib.parse
c5e8d7af 18
b05654f0 19from .common import InfoExtractor, SearchInfoExtractor
14f25df2 20from ..compat import functools
545cc85d 21from ..jsinterp import JSInterpreter
4bb4a188 22from ..utils import (
f8271158 23 NO_DEFAULT,
24 ExtractorError,
720c3099 25 bug_reports_message,
82d02080 26 classproperty,
c5e8d7af 27 clean_html,
d92f5d5a 28 datetime_from_str,
11f9be09 29 dict_get,
358de58c 30 error_to_compat_str,
2d30521a 31 float_or_none,
11f9be09 32 format_field,
ff91cf74 33 get_first,
dd27fd17 34 int_or_none,
641ad5d8 35 is_html,
34921b43 36 join_nonempty,
48416bc4 37 js_to_json,
94278f72 38 mimetype2ext,
9c0d7f49 39 network_exceptions,
11f9be09 40 orderedSet,
6310acf5 41 parse_codecs,
49bd8c66 42 parse_count,
7c80519c 43 parse_duration,
7ea65411 44 parse_iso8601,
4dfbf869 45 parse_qs,
dca3ff4a 46 qualities,
c0ac49bc 47 remove_end,
3995d37d 48 remove_start,
cf7e015f 49 smuggle_url,
dbdaaa23 50 str_or_none,
c93d53f5 51 str_to_int,
f3aa3c3f 52 strftime_or_none,
7c365c21 53 traverse_obj,
556dbe7f 54 try_get,
c5e8d7af
PH
55 unescapeHTML,
56 unified_strdate,
f0d785d3 57 unified_timestamp,
cf7e015f 58 unsmuggle_url,
8bdd16b4 59 update_url_query,
21c340b8 60 url_or_none,
fe93e2c4 61 urljoin,
7c365c21 62 variadic,
c5e8d7af
PH
63)
64
962ffcf8 65# any clients starting with _ cannot be explicitly requested by the user
000c15a4 66INNERTUBE_CLIENTS = {
67 'web': {
68 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
69 'INNERTUBE_CONTEXT': {
70 'client': {
71 'clientName': 'WEB',
18c7683d 72 'clientVersion': '2.20211221.00.00',
000c15a4 73 }
74 },
75 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
76 },
77 'web_embedded': {
78 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
79 'INNERTUBE_CONTEXT': {
80 'client': {
81 'clientName': 'WEB_EMBEDDED_PLAYER',
18c7683d 82 'clientVersion': '1.20211215.00.01',
000c15a4 83 },
84 },
85 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
86 },
87 'web_music': {
88 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
89 'INNERTUBE_HOST': 'music.youtube.com',
90 'INNERTUBE_CONTEXT': {
91 'client': {
92 'clientName': 'WEB_REMIX',
18c7683d 93 'clientVersion': '1.20211213.00.00',
000c15a4 94 }
95 },
96 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
97 },
e7e94f2a 98 'web_creator': {
18c7683d 99 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
100 'INNERTUBE_CONTEXT': {
101 'client': {
102 'clientName': 'WEB_CREATOR',
18c7683d 103 'clientVersion': '1.20211220.02.00',
e7e94f2a
D
104 }
105 },
106 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
107 },
000c15a4 108 'android': {
18c7683d 109 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 110 'INNERTUBE_CONTEXT': {
111 'client': {
112 'clientName': 'ANDROID',
18c7683d 113 'clientVersion': '16.49',
000c15a4 114 }
115 },
116 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 117 'REQUIRE_JS_PLAYER': False
000c15a4 118 },
119 'android_embedded': {
18c7683d 120 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 121 'INNERTUBE_CONTEXT': {
122 'client': {
123 'clientName': 'ANDROID_EMBEDDED_PLAYER',
18c7683d 124 'clientVersion': '16.49',
000c15a4 125 },
126 },
b6de707d 127 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
128 'REQUIRE_JS_PLAYER': False
000c15a4 129 },
130 'android_music': {
18c7683d 131 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 132 'INNERTUBE_CONTEXT': {
133 'client': {
134 'clientName': 'ANDROID_MUSIC',
18c7683d 135 'clientVersion': '4.57',
000c15a4 136 }
137 },
138 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 139 'REQUIRE_JS_PLAYER': False
000c15a4 140 },
e7e94f2a 141 'android_creator': {
18c7683d 142 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
143 'INNERTUBE_CONTEXT': {
144 'client': {
145 'clientName': 'ANDROID_CREATOR',
18c7683d 146 'clientVersion': '21.47',
e7e94f2a
D
147 },
148 },
b6de707d 149 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
150 'REQUIRE_JS_PLAYER': False
e7e94f2a 151 },
18c7683d 152 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
153 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 154 'ios': {
18c7683d 155 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 156 'INNERTUBE_CONTEXT': {
157 'client': {
158 'clientName': 'IOS',
18c7683d 159 'clientVersion': '16.46',
160 'deviceModel': 'iPhone14,3',
000c15a4 161 }
162 },
b6de707d 163 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
164 'REQUIRE_JS_PLAYER': False
000c15a4 165 },
166 'ios_embedded': {
000c15a4 167 'INNERTUBE_CONTEXT': {
168 'client': {
169 'clientName': 'IOS_MESSAGES_EXTENSION',
18c7683d 170 'clientVersion': '16.46',
171 'deviceModel': 'iPhone14,3',
000c15a4 172 },
173 },
b6de707d 174 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
175 'REQUIRE_JS_PLAYER': False
000c15a4 176 },
177 'ios_music': {
18c7683d 178 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 179 'INNERTUBE_CONTEXT': {
180 'client': {
181 'clientName': 'IOS_MUSIC',
18c7683d 182 'clientVersion': '4.57',
000c15a4 183 },
184 },
b6de707d 185 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
186 'REQUIRE_JS_PLAYER': False
000c15a4 187 },
e7e94f2a
D
188 'ios_creator': {
189 'INNERTUBE_CONTEXT': {
190 'client': {
191 'clientName': 'IOS_CREATOR',
18c7683d 192 'clientVersion': '21.47',
e7e94f2a
D
193 },
194 },
b6de707d 195 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
196 'REQUIRE_JS_PLAYER': False
e7e94f2a 197 },
3619f78d 198 # mweb has 'ultralow' formats
199 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 200 'mweb': {
18c7683d 201 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 202 'INNERTUBE_CONTEXT': {
203 'client': {
204 'clientName': 'MWEB',
18c7683d 205 'clientVersion': '2.20211221.01.00',
000c15a4 206 }
207 },
208 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
209 },
210 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
211 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
212 'tv_embedded': {
213 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
214 'INNERTUBE_CONTEXT': {
215 'client': {
216 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
217 'clientVersion': '2.0',
218 },
219 },
220 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
221 },
000c15a4 222}
223
224
e7870111
D
225def _split_innertube_client(client_name):
226 variant, *base = client_name.rsplit('.', 1)
227 if base:
228 return variant, base[0], variant
229 base, *variant = client_name.split('_', 1)
230 return client_name, base, variant[0] if variant else None
231
232
000c15a4 233def build_innertube_clients():
2e4cacd0 234 THIRD_PARTY = {
e7870111 235 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 236 }
e7870111 237 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 238 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 239
240 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 241 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 242 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 243 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 244 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 245
e7870111 246 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 247 ytcfg['priority'] = 10 * priority(base_client)
248
e48b3875 249 if not variant:
e7870111
D
250 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
251 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
252 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
253 embedscreen['priority'] -= 3
254 elif variant == 'embedded':
e48b3875 255 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 256 ytcfg['priority'] -= 2
e48b3875 257 else:
000c15a4 258 ytcfg['priority'] -= 3
259
260
261build_innertube_clients()
262
263
de7f3446 264class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 265 """Provide base functions for Youtube extractors"""
e00eb564 266
3462ffa8 267 _RESERVED_NAMES = (
3cd786db 268 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 269 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 270 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 271 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 272
3619f78d 273 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
274
52efa4b3 275 # _NETRC_MACHINE = 'youtube'
3619f78d 276
b2e8bc1b
JMF
277 # If True it will raise an error if no login info is provided
278 _LOGIN_REQUIRED = False
279
d9190e44
RH
280 _INVIDIOUS_SITES = (
281 # invidious-redirect websites
282 r'(?:www\.)?redirect\.invidious\.io',
283 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 284 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
285 r'(?:www\.)?invidious\.pussthecat\.org',
286 r'(?:www\.)?invidious\.zee\.li',
287 r'(?:www\.)?invidious\.ethibox\.fr',
288 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
289 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
290 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
291 # youtube-dl invidious instances list
292 r'(?:(?:www|no)\.)?invidiou\.sh',
293 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
294 r'(?:www\.)?invidious\.kabi\.tk',
295 r'(?:www\.)?invidious\.mastodon\.host',
296 r'(?:www\.)?invidious\.zapashcanon\.fr',
297 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
298 r'(?:www\.)?invidious\.tinfoil-hat\.net',
299 r'(?:www\.)?invidious\.himiko\.cloud',
300 r'(?:www\.)?invidious\.reallyancient\.tech',
301 r'(?:www\.)?invidious\.tube',
302 r'(?:www\.)?invidiou\.site',
303 r'(?:www\.)?invidious\.site',
304 r'(?:www\.)?invidious\.xyz',
305 r'(?:www\.)?invidious\.nixnet\.xyz',
306 r'(?:www\.)?invidious\.048596\.xyz',
307 r'(?:www\.)?invidious\.drycat\.fr',
308 r'(?:www\.)?inv\.skyn3t\.in',
309 r'(?:www\.)?tube\.poal\.co',
310 r'(?:www\.)?tube\.connect\.cafe',
311 r'(?:www\.)?vid\.wxzm\.sx',
312 r'(?:www\.)?vid\.mint\.lgbt',
313 r'(?:www\.)?vid\.puffyan\.us',
314 r'(?:www\.)?yewtu\.be',
315 r'(?:www\.)?yt\.elukerio\.org',
316 r'(?:www\.)?yt\.lelux\.fi',
317 r'(?:www\.)?invidious\.ggc-project\.de',
318 r'(?:www\.)?yt\.maisputain\.ovh',
319 r'(?:www\.)?ytprivate\.com',
320 r'(?:www\.)?invidious\.13ad\.de',
321 r'(?:www\.)?invidious\.toot\.koeln',
322 r'(?:www\.)?invidious\.fdn\.fr',
323 r'(?:www\.)?watch\.nettohikari\.com',
324 r'(?:www\.)?invidious\.namazso\.eu',
325 r'(?:www\.)?invidious\.silkky\.cloud',
326 r'(?:www\.)?invidious\.exonip\.de',
327 r'(?:www\.)?invidious\.riverside\.rocks',
328 r'(?:www\.)?invidious\.blamefran\.net',
329 r'(?:www\.)?invidious\.moomoo\.de',
330 r'(?:www\.)?ytb\.trom\.tf',
331 r'(?:www\.)?yt\.cyberhost\.uk',
332 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
333 r'(?:www\.)?qklhadlycap4cnod\.onion',
334 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
335 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
336 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
337 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
338 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
339 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
340 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
341 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
342 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
343 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
344 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
345 r'(?:www\.)?piped\.kavin\.rocks',
346 r'(?:www\.)?piped\.silkky\.cloud',
347 r'(?:www\.)?piped\.tokhmi\.xyz',
348 r'(?:www\.)?piped\.moomoo\.me',
349 r'(?:www\.)?il\.ax',
350 r'(?:www\.)?piped\.syncpundit\.com',
351 r'(?:www\.)?piped\.mha\.fi',
352 r'(?:www\.)?piped\.mint\.lgbt',
353 r'(?:www\.)?piped\.privacy\.com\.de',
d9190e44
RH
354 )
355
cce889b9 356 def _initialize_consent(self):
357 cookies = self._get_cookies('https://www.youtube.com/')
358 if cookies.get('__Secure-3PSID'):
359 return
360 consent_id = None
361 consent = cookies.get('CONSENT')
362 if consent:
363 if 'YES' in consent.value:
364 return
365 consent_id = self._search_regex(
366 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
367 if not consent_id:
368 consent_id = random.randint(100, 999)
369 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 370
f3aa3c3f 371 def _initialize_pref(self):
372 cookies = self._get_cookies('https://www.youtube.com/')
373 pref_cookie = cookies.get('PREF')
374 pref = {}
375 if pref_cookie:
376 try:
14f25df2 377 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 378 except ValueError:
379 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 380 pref.update({'hl': 'en', 'tz': 'UTC'})
14f25df2 381 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 382
b2e8bc1b 383 def _real_initialize(self):
f3aa3c3f 384 self._initialize_pref()
cce889b9 385 self._initialize_consent()
a25bca9f 386 self._check_login_required()
387
388 def _check_login_required(self):
24146491 389 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 390 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 391
b7c47b74 392 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
393 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 394
000c15a4 395 def _get_default_ytcfg(self, client='web'):
396 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 397
000c15a4 398 def _get_innertube_host(self, client='web'):
399 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 400
000c15a4 401 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 402 # try_get but with fallback to default ytcfg client values when present
403 _func = lambda y: try_get(y, getter, expected_type)
404 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
405
000c15a4 406 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 407 return self._ytcfg_get_safe(
408 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 409 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 410
000c15a4 411 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 412 return self._ytcfg_get_safe(
413 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 414 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 415
2ae778b8 416 def _select_api_hostname(self, req_api_hostname, default_client=None):
417 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
418 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
419
000c15a4 420 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 421 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 422
000c15a4 423 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 424 context = get_first(
425 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 426 # Enforce language and tz for extraction
427 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
428 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 429 return context
430
cf87314d 431 _SAPISID = None
432
109dd3b2 433 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 434 time_now = round(time.time())
cf87314d 435 if self._SAPISID is None:
436 yt_cookies = self._get_cookies('https://www.youtube.com')
437 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
438 # See: https://github.com/yt-dlp/yt-dlp/issues/393
439 sapisid_cookie = dict_get(
440 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
441 if sapisid_cookie and sapisid_cookie.value:
442 self._SAPISID = sapisid_cookie.value
443 self.write_debug('Extracted SAPISID cookie')
444 # SAPISID cookie is required if not already present
445 if not yt_cookies.get('SAPISID'):
446 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
447 self._set_cookie(
448 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
449 else:
450 self._SAPISID = False
451 if not self._SAPISID:
452 return None
1974e99f 453 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
454 sapisidhash = hashlib.sha1(
86e5f3ed 455 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 456 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
457
458 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 459 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 460 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 461
109dd3b2 462 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 463 data.update(query)
11f9be09 464 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 465 real_headers.update({'content-type': 'application/json'})
466 if headers:
467 real_headers.update(headers)
2ae778b8 468 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
469 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 470 return self._download_json(
2ae778b8 471 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 472 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 473 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 474 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 475
65141660 476 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
477 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 478
99e9e001 479 @staticmethod
480 def _extract_session_index(*data):
481 """
482 Index of current account in account list.
483 See: https://github.com/yt-dlp/yt-dlp/pull/519
484 """
485 for ytcfg in data:
486 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
487 if session_index is not None:
488 return session_index
489
490 # Deprecated?
491 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 492 if ytcfg:
14f25df2 493 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
494 if token:
495 return token
99e9e001 496 if webpage:
497 return self._search_regex(
498 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
499 'identity token', default=None, fatal=False)
a1c5d2ca
M
500
501 @staticmethod
fe93e2c4 502 def _extract_account_syncid(*args):
8ea3f7b9 503 """
504 Extract syncId required to download private playlists of secondary channels
fe93e2c4 505 @params response and/or ytcfg
8ea3f7b9 506 """
fe93e2c4 507 for data in args:
508 # ytcfg includes channel_syncid if on secondary channel
14f25df2 509 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 510 if delegated_sid:
511 return delegated_sid
512 sync_ids = (try_get(
513 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 514 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 515 if len(sync_ids) >= 2 and sync_ids[1]:
516 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
517 # and just "user_syncid||" for primary channel. We only want the channel_syncid
518 return sync_ids[0]
a1c5d2ca 519
ac56cf38 520 @staticmethod
521 def _extract_visitor_data(*args):
522 """
523 Extracts visitorData from an API response or ytcfg
524 Appears to be used to track session state
525 """
9222c381 526 return get_first(
6c73052c 527 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 528 expected_type=str)
ac56cf38 529
2762dbb1 530 @functools.cached_property
99e9e001 531 def is_authenticated(self):
532 return bool(self._generate_sapisidhash_header())
533
11f9be09 534 def extract_ytcfg(self, video_id, webpage):
8c54a305 535 if not webpage:
536 return {}
29f7c58a 537 return self._parse_json(
538 self._search_regex(
539 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 540 default='{}'), video_id, fatal=False) or {}
541
11f9be09 542 def generate_api_headers(
99e9e001 543 self, *, ytcfg=None, account_syncid=None, session_index=None,
544 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
545
2ae778b8 546 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 547 headers = {
14f25df2 548 'X-YouTube-Client-Name': str(
11f9be09 549 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
550 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 551 'Origin': origin,
552 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
553 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 554 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 555 }
556 if session_index is None:
314ee305 557 session_index = self._extract_session_index(ytcfg)
558 if account_syncid or session_index is not None:
559 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 560
109dd3b2 561 auth = self._generate_sapisidhash_header(origin)
f4f751af 562 if auth is not None:
563 headers['Authorization'] = auth
109dd3b2 564 headers['X-Origin'] = origin
99e9e001 565 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 566
a25bca9f 567 def _download_ytcfg(self, client, video_id):
568 url = {
569 'web': 'https://www.youtube.com',
570 'web_music': 'https://music.youtube.com',
571 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
572 }.get(client)
573 if not url:
574 return {}
575 webpage = self._download_webpage(
576 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
577 return self.extract_ytcfg(video_id, webpage) or {}
578
2d6659b9 579 @staticmethod
580 def _build_api_continuation_query(continuation, ctp=None):
581 query = {
582 'continuation': continuation
583 }
584 # TODO: Inconsistency with clickTrackingParams.
585 # Currently we have a fixed ctp contained within context (from ytcfg)
586 # and a ctp in root query for continuation.
587 if ctp:
588 query['clickTracking'] = {'clickTrackingParams': ctp}
589 return query
590
2d6659b9 591 @classmethod
592 def _extract_next_continuation_data(cls, renderer):
593 next_continuation = try_get(
594 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
595 lambda x: x['continuation']['reloadContinuationData']), dict)
596 if not next_continuation:
597 return
598 continuation = next_continuation.get('continuation')
599 if not continuation:
600 return
601 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 602 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 603
604 @classmethod
605 def _extract_continuation_ep_data(cls, continuation_ep: dict):
606 if isinstance(continuation_ep, dict):
607 continuation = try_get(
14f25df2 608 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 609 if not continuation:
610 return
611 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 612 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 613
614 @classmethod
615 def _extract_continuation(cls, renderer):
616 next_continuation = cls._extract_next_continuation_data(renderer)
617 if next_continuation:
618 return next_continuation
fe93e2c4 619
2d6659b9 620 contents = []
621 for key in ('contents', 'items'):
622 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 623
2d6659b9 624 for content in contents:
625 if not isinstance(content, dict):
626 continue
627 continuation_ep = try_get(
628 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
629 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
630 dict)
631 continuation = cls._extract_continuation_ep_data(continuation_ep)
632 if continuation:
633 return continuation
634
fe93e2c4 635 @classmethod
636 def _extract_alerts(cls, data):
109dd3b2 637 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
638 if not isinstance(alert_dict, dict):
639 continue
640 for alert in alert_dict.values():
641 alert_type = alert.get('type')
642 if not alert_type:
643 continue
052e1350 644 message = cls._get_text(alert, 'text')
109dd3b2 645 if message:
646 yield alert_type, message
647
c0ac49bc 648 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 649 errors = []
650 warnings = []
651 for alert_type, alert_message in alerts:
641ad5d8 652 if alert_type.lower() == 'error' and fatal:
109dd3b2 653 errors.append([alert_type, alert_message])
654 else:
655 warnings.append([alert_type, alert_message])
656
657 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 658 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 659 if errors:
660 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
661
662 def _extract_and_report_alerts(self, data, *args, **kwargs):
663 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
664
47193e02 665 def _extract_badges(self, renderer: dict):
666 badges = set()
667 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
14f25df2 668 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], str)
47193e02 669 if label:
670 badges.add(label.lower())
671 return badges
672
673 @staticmethod
052e1350 674 def _get_text(data, *path_list, max_runs=None):
675 for path in path_list or [None]:
676 if path is None:
677 obj = [data]
678 else:
679 obj = traverse_obj(data, path, default=[])
680 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
681 obj = [obj]
682 for item in obj:
14f25df2 683 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 684 if text:
685 return text
686 runs = try_get(item, lambda x: x['runs'], list) or []
687 if not runs and isinstance(item, list):
688 runs = item
689
690 runs = runs[:min(len(runs), max_runs or len(runs))]
691 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
692 if text:
693 return text
47193e02 694
f0d785d3 695 def _get_count(self, data, *path_list):
696 count_text = self._get_text(data, *path_list) or ''
697 count = parse_count(count_text)
698 if count is None:
699 count = str_to_int(
700 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
701 return count
702
a709d873 703 @staticmethod
704 def _extract_thumbnails(data, *path_list):
705 """
706 Extract thumbnails from thumbnails dict
707 @param path_list: path list to level that contains 'thumbnails' key
708 """
709 thumbnails = []
710 for path in path_list or [()]:
711 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
712 thumbnail_url = url_or_none(thumbnail.get('url'))
713 if not thumbnail_url:
714 continue
715 # Sometimes youtube gives a wrong thumbnail URL. See:
716 # https://github.com/yt-dlp/yt-dlp/issues/233
717 # https://github.com/ytdl-org/youtube-dl/issues/28023
718 if 'maxresdefault' in thumbnail_url:
719 thumbnail_url = thumbnail_url.split('?')[0]
720 thumbnails.append({
721 'url': thumbnail_url,
722 'height': int_or_none(thumbnail.get('height')),
723 'width': int_or_none(thumbnail.get('width')),
724 })
725 return thumbnails
726
f3aa3c3f 727 @staticmethod
728 def extract_relative_time(relative_time_text):
729 """
730 Extracts a relative time from string and converts to dt object
f0d785d3 731 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 732 """
f0d785d3 733 mobj = re.search(r'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>microsecond|second|minute|hour|day|week|month|year)s?\s*ago', relative_time_text)
f3aa3c3f 734 if mobj:
f0d785d3 735 start = mobj.group('start')
736 if start:
737 return datetime_from_str(start)
f3aa3c3f 738 try:
f0d785d3 739 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 740 except ValueError:
741 return None
742
743 def _extract_time_text(self, renderer, *path_list):
a25bca9f 744 """@returns (timestamp, time_text)"""
f3aa3c3f 745 text = self._get_text(renderer, *path_list) or ''
746 dt = self.extract_relative_time(text)
747 timestamp = None
748 if isinstance(dt, datetime.datetime):
749 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 750
751 if timestamp is None:
752 timestamp = (
753 unified_timestamp(text) or unified_timestamp(
754 self._search_regex(
17322130 755 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 756 text.lower(), 'time text', default=None)))
f0d785d3 757
f3aa3c3f 758 if text and timestamp is None:
17322130 759 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
f3aa3c3f 760 return timestamp, text
761
109dd3b2 762 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
763 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 764 default_client='web'):
109dd3b2 765 response = None
766 last_error = None
767 count = -1
768 retries = self.get_param('extractor_retries', 3)
769 if check_get_keys is None:
770 check_get_keys = []
771 while count < retries:
772 count += 1
773 if last_error:
c0ac49bc 774 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
109dd3b2 775 try:
776 response = self._call_api(
777 ep=ep, fatal=True, headers=headers,
778 video_id=item_id, query=query,
779 context=self._extract_context(ytcfg, default_client),
780 api_key=self._extract_api_key(ytcfg, default_client),
781 api_hostname=api_hostname, default_client=default_client,
782 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
783 except ExtractorError as e:
9c0d7f49 784 if isinstance(e.cause, network_exceptions):
14f25df2 785 if isinstance(e.cause, urllib.error.HTTPError):
87e8e8a7 786 first_bytes = e.cause.read(512)
787 if not is_html(first_bytes):
788 yt_error = try_get(
789 self._parse_json(
790 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
14f25df2 791 lambda x: x['error']['message'], str)
87e8e8a7 792 if yt_error:
793 self._report_alerts([('ERROR', yt_error)], fatal=False)
109dd3b2 794 # Downloading page may result in intermittent 5xx HTTP error
962ffcf8 795 # Sometimes a 404 is also received. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 796 # We also want to catch all other network exceptions since errors in later pages can be troublesome
797 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
14f25df2 798 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
526d74ec 799 last_error = error_to_compat_str(e.cause or e.msg)
9c0d7f49 800 if count < retries:
801 continue
109dd3b2 802 if fatal:
803 raise
804 else:
805 self.report_warning(error_to_compat_str(e))
806 return
807
808 else:
109dd3b2 809 try:
ac56cf38 810 self._extract_and_report_alerts(response, only_once=True)
109dd3b2 811 except ExtractorError as e:
c0ac49bc 812 # YouTube servers may return errors we want to retry on in a 200 OK response
813 # See: https://github.com/yt-dlp/yt-dlp/issues/839
814 if 'unknown error' in e.msg.lower():
815 last_error = e.msg
816 continue
109dd3b2 817 if fatal:
818 raise
819 self.report_warning(error_to_compat_str(e))
820 return
821 if not check_get_keys or dict_get(response, check_get_keys):
822 break
823 # Youtube sometimes sends incomplete data
824 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
825 last_error = 'Incomplete data received'
826 if count >= retries:
827 if fatal:
828 raise ExtractorError(last_error)
829 else:
830 self.report_warning(last_error)
831 return
832 return response
833
9297939e 834 @staticmethod
835 def is_music_url(url):
836 return re.match(r'https?://music\.youtube\.com/', url) is not None
837
30a074c2 838 def _extract_video(self, renderer):
839 video_id = renderer.get('videoId')
052e1350 840 title = self._get_text(renderer, 'title')
841 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 842 duration = parse_duration(self._get_text(
843 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 844 if duration is None:
845 duration = parse_duration(self._search_regex(
846 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
847 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
848 video_id, default=None, group='duration'))
849
f0d785d3 850 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 851
052e1350 852 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 853 channel_id = traverse_obj(
a44ca5a4 854 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
855 expected_type=str, get_all=False)
f3aa3c3f 856 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
857 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
858 overlay_style = traverse_obj(
a44ca5a4 859 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
860 get_all=False, expected_type=str)
f3aa3c3f 861 badges = self._extract_badges(renderer)
a709d873 862 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
fd2ad7cb 863 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 864 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
865 expected_type=str)) or ''
fd2ad7cb 866 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 867 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 868 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 869
30a074c2 870 return {
39ed931e 871 '_type': 'url',
30a074c2 872 'ie_key': YoutubeIE.ie_key(),
873 'id': video_id,
fd2ad7cb 874 'url': url,
30a074c2 875 'title': title,
876 'description': description,
877 'duration': duration,
878 'view_count': view_count,
879 'uploader': uploader,
f3aa3c3f 880 'channel_id': channel_id,
a709d873 881 'thumbnails': thumbnails,
a44ca5a4 882 'upload_date': (strftime_or_none(timestamp, '%Y%m%d')
883 if self._configuration_arg('approximate_date', ie_key='youtubetab')
884 else None),
f3aa3c3f 885 'live_status': ('is_upcoming' if scheduled_timestamp is not None
886 else 'was_live' if 'streamed' in time_text.lower()
887 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
888 else None),
889 'release_timestamp': scheduled_timestamp,
890 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 891 }
892
0c148415 893
360e1ca5 894class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 895 IE_DESC = 'YouTube'
cb7dfeea 896 _VALID_URL = r"""(?x)^
c5e8d7af 897 (
edb53e2d 898 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 899 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
900 (?:www\.)?deturl\.com/www\.youtube\.com|
901 (?:www\.)?pwnyoutube\.com|
902 (?:www\.)?hooktube\.com|
903 (?:www\.)?yourepeat\.com|
904 tube\.majestyc\.net|
905 %(invidious)s|
906 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
907 (?:.*?\#/)? # handle anchor (#/) redirect urls
908 (?: # the various things that can precede the ID:
b6ce9bb0 909 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 910 |(?: # or the v= param in all its forms
f7000f3a 911 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 912 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 913 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
914 v=
915 )
f4b05232 916 ))
cbaed4bb
S
917 |(?:
918 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
919 vid\.plus| # or vid.plus/xxxx
920 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 921 %(invidious)s
cbaed4bb 922 )/
edb53e2d 923 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 924 )
c5e8d7af 925 )? # all until now is optional -> you can pass the naked ID
201c1459 926 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 927 (?(1).+)? # if we found the ID, everything can follow
9297939e 928 (?:\#|$)""" % {
d9190e44 929 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 930 }
e40c758c 931 _PLAYER_INFO_RE = (
cc2db878 932 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
933 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
545cc85d 934 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 935 )
2c62dc26 936 _formats = {
c2d3cb4c 937 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
938 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
939 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
940 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
941 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
942 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
943 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
944 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 945 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 946 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
947 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
948 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
949 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
950 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
951 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 952 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 953 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
954 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 955
956
957 # 3D videos
c2d3cb4c 958 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
959 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
960 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
961 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 962 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
963 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
964 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 965
96fb5605 966 # Apple HTTP Live Streaming
11f12195 967 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 968 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
969 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
970 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
971 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
972 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 973 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
974 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
975
976 # DASH mp4 video
d23028a8
S
977 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
978 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
979 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
980 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
981 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 982 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
983 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
984 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
985 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
986 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
987 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
988 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 989
f6f1fc92 990 # Dash mp4 audio
d23028a8
S
991 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
992 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
993 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
994 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
995 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
996 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
997 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
998
999 # Dash webm
d23028a8
S
1000 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1001 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1002 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1003 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1004 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1005 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1006 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1007 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1008 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1009 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1010 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1011 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1012 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1013 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1014 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1015 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1016 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1017 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1018 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1019 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1020 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1021 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1022
1023 # Dash webm audio
d23028a8
S
1024 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1025 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1026
0857baad 1027 # Dash webm audio with opus inside
d23028a8
S
1028 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1029 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1030 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1031
ce6b9a2d
PH
1032 # RTMP (unnamed)
1033 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1034
1035 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1036 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1037 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1038 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1039 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1040 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1041 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1042 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1043 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1044 }
29f7c58a 1045 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1046
fd5c4aab
S
1047 _GEO_BYPASS = False
1048
78caa52a 1049 IE_NAME = 'youtube'
2eb88d95
PH
1050 _TESTS = [
1051 {
2d3d2997 1052 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1053 'info_dict': {
1054 'id': 'BaW_jenozKc',
1055 'ext': 'mp4',
3867038a 1056 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1057 'uploader': 'Philipp Hagemeister',
1058 'uploader_id': 'phihag',
ec85ded8 1059 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1060 'channel': 'Philipp Hagemeister',
dd4c4492
S
1061 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1062 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1063 'upload_date': '20121002',
ff9f925b 1064 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1065 'categories': ['Science & Technology'],
3867038a 1066 'tags': ['youtube-dl'],
556dbe7f 1067 'duration': 10,
dbdaaa23 1068 'view_count': int,
3e7c1224 1069 'like_count': int,
ff9f925b 1070 'availability': 'public',
1071 'playable_in_embed': True,
1072 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1073 'live_status': 'not_live',
1074 'age_limit': 0,
7c80519c 1075 'start_time': 1,
297a564b 1076 'end_time': 9,
6c73052c 1077 'channel_follower_count': int
2eb88d95 1078 }
0e853ca4 1079 },
fccd3771 1080 {
4bc3a23e
PH
1081 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1082 'note': 'Embed-only video (#1746)',
1083 'info_dict': {
1084 'id': 'yZIXLfi8CZQ',
1085 'ext': 'mp4',
1086 'upload_date': '20120608',
1087 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1088 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1089 'uploader': 'SET India',
94bfcd23 1090 'uploader_id': 'setindia',
ec85ded8 1091 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1092 'age_limit': 18,
545cc85d 1093 },
1094 'skip': 'Private video',
fccd3771 1095 },
11b56058 1096 {
8bdd16b4 1097 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1098 'note': 'Use the first video ID in the URL',
1099 'info_dict': {
1100 'id': 'BaW_jenozKc',
1101 'ext': 'mp4',
3867038a 1102 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1103 'uploader': 'Philipp Hagemeister',
1104 'uploader_id': 'phihag',
ec85ded8 1105 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1106 'channel': 'Philipp Hagemeister',
1107 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1108 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1109 'upload_date': '20121002',
976ae3ea 1110 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1111 'categories': ['Science & Technology'],
3867038a 1112 'tags': ['youtube-dl'],
556dbe7f 1113 'duration': 10,
dbdaaa23 1114 'view_count': int,
11b56058 1115 'like_count': int,
976ae3ea 1116 'availability': 'public',
1117 'playable_in_embed': True,
1118 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1119 'live_status': 'not_live',
1120 'age_limit': 0,
6c73052c 1121 'channel_follower_count': int
34a7de29
S
1122 },
1123 'params': {
1124 'skip_download': True,
1125 },
11b56058 1126 },
dd27fd17 1127 {
2d3d2997 1128 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1129 'note': '256k DASH audio (format 141) via DASH manifest',
1130 'info_dict': {
1131 'id': 'a9LDPn-MO4I',
1132 'ext': 'm4a',
1133 'upload_date': '20121002',
1134 'uploader_id': '8KVIDEO',
ec85ded8 1135 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1136 'description': '',
1137 'uploader': '8KVIDEO',
1138 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1139 },
4bc3a23e
PH
1140 'params': {
1141 'youtube_include_dash_manifest': True,
1142 'format': '141',
4919603f 1143 },
de3c7fe0 1144 'skip': 'format 141 not served anymore',
dd27fd17 1145 },
8bdd16b4 1146 # DASH manifest with encrypted signature
1147 {
1148 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1149 'info_dict': {
1150 'id': 'IB3lcPjvWLA',
1151 'ext': 'm4a',
1152 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1153 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1154 'duration': 244,
1155 'uploader': 'AfrojackVEVO',
1156 'uploader_id': 'AfrojackVEVO',
1157 'upload_date': '20131011',
cc2db878 1158 'abr': 129.495,
976ae3ea 1159 'like_count': int,
1160 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1161 'playable_in_embed': True,
1162 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1163 'view_count': int,
1164 'track': 'The Spark',
1165 'live_status': 'not_live',
1166 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1167 'channel': 'Afrojack',
1168 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1169 'tags': 'count:19',
1170 'availability': 'public',
1171 'categories': ['Music'],
1172 'age_limit': 0,
1173 'alt_title': 'The Spark',
6c73052c 1174 'channel_follower_count': int
8bdd16b4 1175 },
1176 'params': {
1177 'youtube_include_dash_manifest': True,
1178 'format': '141/bestaudio[ext=m4a]',
1179 },
1180 },
65c2fde2 1181 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1182 {
65c2fde2 1183 'note': 'Embed allowed age-gate video',
2d3d2997 1184 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1185 'info_dict': {
1186 'id': 'HtVdAasjOgU',
1187 'ext': 'mp4',
1188 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1189 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1190 'duration': 142,
c522adb1
JMF
1191 'uploader': 'The Witcher',
1192 'uploader_id': 'WitcherGame',
ec85ded8 1193 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1194 'upload_date': '20140605',
34952f09 1195 'age_limit': 18,
976ae3ea 1196 'categories': ['Gaming'],
1197 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1198 'availability': 'needs_auth',
1199 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1200 'like_count': int,
1201 'channel': 'The Witcher',
1202 'live_status': 'not_live',
1203 'tags': 'count:17',
1204 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1205 'playable_in_embed': True,
1206 'view_count': int,
6c73052c 1207 'channel_follower_count': int
c522adb1
JMF
1208 },
1209 },
65c2fde2 1210 {
1211 'note': 'Age-gate video with embed allowed in public site',
1212 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1213 'info_dict': {
1214 'id': 'HsUATh_Nc2U',
1215 'ext': 'mp4',
1216 'title': 'Godzilla 2 (Official Video)',
1217 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1218 'upload_date': '20200408',
1219 'uploader_id': 'FlyingKitty900',
1220 'uploader': 'FlyingKitty',
1221 'age_limit': 18,
976ae3ea 1222 'availability': 'needs_auth',
1223 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1224 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1225 'channel': 'FlyingKitty',
1226 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1227 'view_count': int,
1228 'categories': ['Entertainment'],
1229 'live_status': 'not_live',
1230 'tags': ['Flyingkitty', 'godzilla 2'],
1231 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1232 'like_count': int,
1233 'duration': 177,
1234 'playable_in_embed': True,
6c73052c 1235 'channel_follower_count': int
65c2fde2 1236 },
1237 },
1238 {
1239 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1240 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1241 'info_dict': {
1242 'id': 'Tq92D6wQ1mg',
1243 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1244 'ext': 'mp4',
17322130 1245 'upload_date': '20191228',
65c2fde2 1246 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1247 'uploader': 'Projekt Melody',
1248 'description': 'md5:17eccca93a786d51bc67646756894066',
1249 'age_limit': 18,
976ae3ea 1250 'like_count': int,
1251 'availability': 'needs_auth',
1252 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1253 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1254 'view_count': int,
1255 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1256 'channel': 'Projekt Melody',
1257 'live_status': 'not_live',
1258 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1259 'playable_in_embed': True,
1260 'categories': ['Entertainment'],
1261 'duration': 106,
1262 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
6c73052c 1263 'channel_follower_count': int
65c2fde2 1264 },
1265 },
1266 {
1267 'note': 'Non-Agegated non-embeddable video',
1268 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1269 'info_dict': {
1270 'id': 'MeJVWBSsPAY',
1271 'ext': 'mp4',
1272 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1273 'uploader': 'Herr Lurik',
1274 'uploader_id': 'st3in234',
1275 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1276 'upload_date': '20130730',
976ae3ea 1277 'track': 'Such mich find mich',
1278 'age_limit': 0,
1279 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1280 'like_count': int,
1281 'playable_in_embed': False,
1282 'creator': 'OOMPH!',
1283 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1284 'view_count': int,
1285 'alt_title': 'Such mich find mich',
1286 'duration': 210,
1287 'channel': 'Herr Lurik',
1288 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1289 'categories': ['Music'],
1290 'availability': 'public',
1291 'uploader_url': 'http://www.youtube.com/user/st3in234',
1292 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1293 'live_status': 'not_live',
1294 'artist': 'OOMPH!',
6c73052c 1295 'channel_follower_count': int
65c2fde2 1296 },
1297 },
1298 {
1299 'note': 'Non-bypassable age-gated video',
1300 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1301 'only_matching': True,
1302 },
8bdd16b4 1303 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1304 # YouTube Red ad is not captured for creator
1305 {
1306 'url': '__2ABJjxzNo',
1307 'info_dict': {
1308 'id': '__2ABJjxzNo',
1309 'ext': 'mp4',
1310 'duration': 266,
1311 'upload_date': '20100430',
1312 'uploader_id': 'deadmau5',
1313 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1314 'creator': 'deadmau5',
1315 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1316 'uploader': 'deadmau5',
1317 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1318 'alt_title': 'Some Chords',
976ae3ea 1319 'availability': 'public',
1320 'tags': 'count:14',
1321 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1322 'view_count': int,
1323 'live_status': 'not_live',
1324 'channel': 'deadmau5',
1325 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1326 'like_count': int,
1327 'track': 'Some Chords',
1328 'artist': 'deadmau5',
1329 'playable_in_embed': True,
1330 'age_limit': 0,
1331 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1332 'categories': ['Music'],
1333 'album': 'Some Chords',
6c73052c 1334 'channel_follower_count': int
8bdd16b4 1335 },
1336 'expected_warnings': [
1337 'DASH manifest missing',
1338 ]
1339 },
067aa17e 1340 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1341 {
1342 'url': 'lqQg6PlCWgI',
1343 'info_dict': {
1344 'id': 'lqQg6PlCWgI',
1345 'ext': 'mp4',
556dbe7f 1346 'duration': 6085,
90227264 1347 'upload_date': '20150827',
cbe2bd91 1348 'uploader_id': 'olympic',
ec85ded8 1349 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1350 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1351 'uploader': 'Olympics',
cbe2bd91 1352 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1353 'like_count': int,
1354 'release_timestamp': 1343767800,
1355 'playable_in_embed': True,
1356 'categories': ['Sports'],
1357 'release_date': '20120731',
1358 'channel': 'Olympics',
1359 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1360 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1361 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1362 'age_limit': 0,
1363 'availability': 'public',
1364 'live_status': 'was_live',
1365 'view_count': int,
1366 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1367 'channel_follower_count': int
cbe2bd91
PH
1368 },
1369 'params': {
1370 'skip_download': 'requires avconv',
e52a40ab 1371 }
cbe2bd91 1372 },
6271f1ca
PH
1373 # Non-square pixels
1374 {
1375 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1376 'info_dict': {
1377 'id': '_b-2C3KPAM0',
1378 'ext': 'mp4',
1379 'stretched_ratio': 16 / 9.,
556dbe7f 1380 'duration': 85,
6271f1ca
PH
1381 'upload_date': '20110310',
1382 'uploader_id': 'AllenMeow',
ec85ded8 1383 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1384 '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 1385 'uploader': '孫ᄋᄅ',
6271f1ca 1386 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1387 'playable_in_embed': True,
1388 'channel': '孫ᄋᄅ',
1389 'age_limit': 0,
1390 'tags': 'count:11',
1391 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1392 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1393 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1394 'view_count': int,
1395 'categories': ['People & Blogs'],
1396 'like_count': int,
1397 'live_status': 'not_live',
1398 'availability': 'unlisted',
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,
6c73052c 1627 'channel_follower_count': int
7caf9830
S
1628 },
1629 'params': {
1630 'skip_download': True,
1631 },
1632 },
fd050249
S
1633 {
1634 # Channel-like uploader_url
1635 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1636 'info_dict': {
1637 'id': 'eQcmzGIKrzg',
1638 'ext': 'mp4',
1639 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1640 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1641 'duration': 4060,
17322130 1642 'upload_date': '20151120',
eb6793ba 1643 'uploader': 'Bernie Sanders',
fd050249 1644 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1645 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1646 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1647 'playable_in_embed': True,
1648 'tags': 'count:12',
1649 'like_count': int,
1650 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1651 'age_limit': 0,
1652 'availability': 'public',
1653 'categories': ['News & Politics'],
1654 'channel': 'Bernie Sanders',
1655 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1656 'view_count': int,
1657 'live_status': 'not_live',
1658 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
6c73052c 1659 'channel_follower_count': int
fd050249
S
1660 },
1661 'params': {
1662 'skip_download': True,
1663 },
1664 },
040ac686
S
1665 {
1666 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1667 'only_matching': True,
7f29cf54
S
1668 },
1669 {
067aa17e 1670 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1671 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1672 'only_matching': True,
6496ccb4
S
1673 },
1674 {
1675 # Rental video preview
1676 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1677 'info_dict': {
1678 'id': 'uGpuVWrhIzE',
1679 'ext': 'mp4',
1680 'title': 'Piku - Trailer',
1681 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1682 'upload_date': '20150811',
1683 'uploader': 'FlixMatrix',
1684 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1685 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1686 'license': 'Standard YouTube License',
1687 },
1688 'params': {
1689 'skip_download': True,
1690 },
eb6793ba 1691 'skip': 'This video is not available.',
022a5d66 1692 },
12afdc2a
S
1693 {
1694 # YouTube Red video with episode data
1695 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1696 'info_dict': {
1697 'id': 'iqKdEhx-dD4',
1698 'ext': 'mp4',
1699 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1700 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1701 'duration': 2085,
12afdc2a
S
1702 'upload_date': '20170118',
1703 'uploader': 'Vsauce',
1704 'uploader_id': 'Vsauce',
1705 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1706 'series': 'Mind Field',
1707 'season_number': 1,
1708 'episode_number': 1,
976ae3ea 1709 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1710 'tags': 'count:12',
1711 'view_count': int,
1712 'availability': 'public',
1713 'age_limit': 0,
1714 'channel': 'Vsauce',
1715 'episode': 'Episode 1',
1716 'categories': ['Entertainment'],
1717 'season': 'Season 1',
1718 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1719 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1720 'like_count': int,
1721 'playable_in_embed': True,
1722 'live_status': 'not_live',
6c73052c 1723 'channel_follower_count': int
12afdc2a
S
1724 },
1725 'params': {
1726 'skip_download': True,
1727 },
1728 'expected_warnings': [
1729 'Skipping DASH manifest',
1730 ],
1731 },
c7121fa7
S
1732 {
1733 # The following content has been identified by the YouTube community
1734 # as inappropriate or offensive to some audiences.
1735 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1736 'info_dict': {
1737 'id': '6SJNVb0GnPI',
1738 'ext': 'mp4',
1739 'title': 'Race Differences in Intelligence',
1740 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1741 'duration': 965,
1742 'upload_date': '20140124',
1743 'uploader': 'New Century Foundation',
1744 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1745 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1746 },
1747 'params': {
1748 'skip_download': True,
1749 },
545cc85d 1750 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1751 },
022a5d66
S
1752 {
1753 # itag 212
1754 'url': '1t24XAntNCY',
1755 'only_matching': True,
fd5c4aab
S
1756 },
1757 {
1758 # geo restricted to JP
1759 'url': 'sJL6WA-aGkQ',
1760 'only_matching': True,
1761 },
cd5a74a2
S
1762 {
1763 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1764 'only_matching': True,
1765 },
bc2ca1bb 1766 {
1767 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1768 'only_matching': True,
1769 },
1770 {
1771 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1772 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1773 'only_matching': True,
1774 },
825cd268
RA
1775 {
1776 # DRM protected
1777 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1778 'only_matching': True,
4fe54c12
S
1779 },
1780 {
1781 # Video with unsupported adaptive stream type formats
1782 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1783 'info_dict': {
1784 'id': 'Z4Vy8R84T1U',
1785 'ext': 'mp4',
1786 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1787 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1788 'duration': 433,
1789 'upload_date': '20130923',
1790 'uploader': 'Amelia Putri Harwita',
1791 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1792 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1793 'formats': 'maxcount:10',
1794 },
1795 'params': {
1796 'skip_download': True,
1797 'youtube_include_dash_manifest': False,
1798 },
5429d6a9 1799 'skip': 'not actual anymore',
5caabd3c 1800 },
1801 {
822b9d9c 1802 # Youtube Music Auto-generated description
5caabd3c 1803 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1804 'info_dict': {
1805 'id': 'MgNrAu2pzNs',
1806 'ext': 'mp4',
1807 'title': 'Voyeur Girl',
1808 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1809 'upload_date': '20190312',
5429d6a9
S
1810 'uploader': 'Stephen - Topic',
1811 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1812 'artist': 'Stephen',
1813 'track': 'Voyeur Girl',
1814 'album': 'it\'s too much love to know my dear',
1815 'release_date': '20190313',
1816 'release_year': 2019,
976ae3ea 1817 'alt_title': 'Voyeur Girl',
1818 'view_count': int,
1819 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1820 'playable_in_embed': True,
1821 'like_count': int,
1822 'categories': ['Music'],
1823 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1824 'channel': 'Stephen',
1825 'availability': 'public',
1826 'creator': 'Stephen',
1827 'duration': 169,
1828 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1829 'age_limit': 0,
1830 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1831 'tags': 'count:11',
1832 'live_status': 'not_live',
6c73052c 1833 'channel_follower_count': int
5caabd3c 1834 },
1835 'params': {
1836 'skip_download': True,
1837 },
1838 },
66b48727
RA
1839 {
1840 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1841 'only_matching': True,
1842 },
011e75e6
S
1843 {
1844 # invalid -> valid video id redirection
1845 'url': 'DJztXj2GPfl',
1846 'info_dict': {
1847 'id': 'DJztXj2GPfk',
1848 'ext': 'mp4',
1849 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1850 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1851 'upload_date': '20090125',
1852 'uploader': 'Prochorowka',
1853 'uploader_id': 'Prochorowka',
1854 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1855 'artist': 'Panjabi MC',
1856 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1857 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1858 },
1859 'params': {
1860 'skip_download': True,
1861 },
545cc85d 1862 'skip': 'Video unavailable',
ea74e00b
DP
1863 },
1864 {
1865 # empty description results in an empty string
1866 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1867 'info_dict': {
1868 'id': 'x41yOUIvK2k',
1869 'ext': 'mp4',
1870 'title': 'IMG 3456',
1871 'description': '',
1872 'upload_date': '20170613',
1873 'uploader_id': 'ElevageOrVert',
1874 'uploader': 'ElevageOrVert',
976ae3ea 1875 'view_count': int,
1876 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1877 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1878 'like_count': int,
1879 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1880 'tags': [],
1881 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1882 'availability': 'public',
1883 'age_limit': 0,
1884 'categories': ['Pets & Animals'],
1885 'duration': 7,
1886 'playable_in_embed': True,
1887 'live_status': 'not_live',
1888 'channel': 'ElevageOrVert',
6c73052c 1889 'channel_follower_count': int
ea74e00b
DP
1890 },
1891 'params': {
1892 'skip_download': True,
1893 },
1894 },
a0566bbf 1895 {
29f7c58a 1896 # with '};' inside yt initial data (see [1])
1897 # see [2] for an example with '};' inside ytInitialPlayerResponse
1898 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1899 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1900 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1901 'info_dict': {
1902 'id': 'CHqg6qOn4no',
1903 'ext': 'mp4',
1904 'title': 'Part 77 Sort a list of simple types in c#',
1905 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1906 'upload_date': '20130831',
1907 'uploader_id': 'kudvenkat',
1908 'uploader': 'kudvenkat',
976ae3ea 1909 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1910 'like_count': int,
1911 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1912 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1913 'live_status': 'not_live',
1914 'categories': ['Education'],
1915 'availability': 'public',
1916 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1917 'tags': 'count:12',
1918 'playable_in_embed': True,
1919 'age_limit': 0,
1920 'view_count': int,
1921 'duration': 522,
1922 'channel': 'kudvenkat',
6c73052c 1923 'channel_follower_count': int
a0566bbf 1924 },
1925 'params': {
1926 'skip_download': True,
1927 },
1928 },
29f7c58a 1929 {
1930 # another example of '};' in ytInitialData
1931 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1932 'only_matching': True,
1933 },
1934 {
1935 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1936 'only_matching': True,
1937 },
545cc85d 1938 {
cc2db878 1939 # https://github.com/ytdl-org/youtube-dl/pull/28094
1940 'url': 'OtqTfy26tG0',
1941 'info_dict': {
1942 'id': 'OtqTfy26tG0',
1943 'ext': 'mp4',
1944 'title': 'Burn Out',
1945 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1946 'upload_date': '20141120',
1947 'uploader': 'The Cinematic Orchestra - Topic',
1948 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1949 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1950 'artist': 'The Cinematic Orchestra',
1951 'track': 'Burn Out',
1952 'album': 'Every Day',
976ae3ea 1953 'like_count': int,
1954 'live_status': 'not_live',
1955 'alt_title': 'Burn Out',
1956 'duration': 614,
1957 'age_limit': 0,
1958 'view_count': int,
1959 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1960 'creator': 'The Cinematic Orchestra',
1961 'channel': 'The Cinematic Orchestra',
1962 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1963 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1964 'availability': 'public',
1965 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1966 'categories': ['Music'],
1967 'playable_in_embed': True,
6c73052c 1968 'channel_follower_count': int
cc2db878 1969 },
1970 'params': {
1971 'skip_download': True,
1972 },
545cc85d 1973 },
bc2ca1bb 1974 {
1975 # controversial video, only works with bpctr when authenticated with cookies
1976 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1977 'only_matching': True,
1978 },
a1a7907b 1979 {
1980 # controversial video, requires bpctr/contentCheckOk
1981 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1982 'info_dict': {
1983 'id': 'SZJvDhaSDnc',
1984 'ext': 'mp4',
1985 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1986 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1987 'uploader': 'CBS Mornings',
11f9be09 1988 'uploader_id': 'CBSThisMorning',
a1a7907b 1989 'upload_date': '20140716',
976ae3ea 1990 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1991 'duration': 170,
1992 'categories': ['News & Politics'],
1993 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1994 'view_count': int,
1995 'channel': 'CBS Mornings',
1996 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1997 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1998 'age_limit': 18,
1999 'availability': 'needs_auth',
2000 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2001 'like_count': int,
2002 'live_status': 'not_live',
2003 'playable_in_embed': True,
6c73052c 2004 'channel_follower_count': int
a1a7907b 2005 }
2006 },
f7ad7160 2007 {
2008 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2009 'url': 'cBvYw8_A0vQ',
2010 'info_dict': {
2011 'id': 'cBvYw8_A0vQ',
2012 'ext': 'mp4',
2013 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2014 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2015 'upload_date': '20201120',
2016 'uploader': 'Walk around Japan',
2017 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2018 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2019 'duration': 1456,
2020 'categories': ['Travel & Events'],
2021 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2022 'view_count': int,
2023 'channel': 'Walk around Japan',
2024 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2025 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2026 'age_limit': 0,
2027 'availability': 'public',
2028 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2029 'live_status': 'not_live',
2030 'playable_in_embed': True,
6c73052c 2031 'channel_follower_count': int
f7ad7160 2032 },
2033 'params': {
2034 'skip_download': True,
2035 },
0fb983f6 2036 }, {
2037 # Has multiple audio streams
2038 'url': 'WaOKSUlf4TM',
2039 'only_matching': True
9297939e 2040 }, {
2041 # Requires Premium: has format 141 when requested using YTM url
2042 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2043 'only_matching': True
2044 }, {
120916da 2045 # multiple subtitles with same lang_code
2046 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2047 'only_matching': True,
109dd3b2 2048 }, {
2049 # Force use android client fallback
2050 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2051 'info_dict': {
2052 'id': 'YOelRv7fMxY',
11f9be09 2053 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2054 'ext': '3gp',
2055 'upload_date': '20210624',
2056 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2057 'uploader': 'colinfurze',
11f9be09 2058 'uploader_id': 'colinfurze',
109dd3b2 2059 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2060 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2061 'duration': 596,
2062 'categories': ['Entertainment'],
2063 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2064 'view_count': int,
2065 'channel': 'colinfurze',
2066 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2067 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2068 'age_limit': 0,
2069 'availability': 'public',
2070 'like_count': int,
2071 'live_status': 'not_live',
2072 'playable_in_embed': True,
6c73052c 2073 'channel_follower_count': int
109dd3b2 2074 },
2075 'params': {
2076 'format': '17', # 3gp format available on android
2077 'extractor_args': {'youtube': {'player_client': ['android']}},
2078 },
120916da 2079 },
109dd3b2 2080 {
2081 # Skip download of additional client configs (remix client config in this case)
2082 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2083 'only_matching': True,
2084 'params': {
2085 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2086 },
8fc54b12 2087 }, {
2088 # shorts
2089 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2090 'only_matching': True,
9222c381 2091 }, {
2092 'note': 'Storyboards',
2093 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2094 'info_dict': {
2095 'id': '5KLPxDtMqe8',
2096 'ext': 'mhtml',
2097 'format_id': 'sb0',
2098 'title': 'Your Brain is Plastic',
2099 'uploader_id': 'scishow',
2100 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2101 'upload_date': '20140324',
2102 'uploader': 'SciShow',
976ae3ea 2103 'like_count': int,
2104 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2105 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2106 'view_count': int,
2107 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2108 'playable_in_embed': True,
2109 'tags': 'count:12',
2110 'uploader_url': 'http://www.youtube.com/user/scishow',
2111 'availability': 'public',
2112 'channel': 'SciShow',
2113 'live_status': 'not_live',
2114 'duration': 248,
2115 'categories': ['Education'],
2116 'age_limit': 0,
6c73052c 2117 'channel_follower_count': int
9222c381 2118 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2119 }, {
2120 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2121 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2122 'info_dict': {
2123 'id': '2NUZ8W2llS4',
2124 'ext': 'mp4',
2125 'title': 'The NP that test your phone performance 🙂',
2126 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2127 'uploader': 'Leon Nguyen',
2128 'uploader_id': 'VNSXIII',
2129 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2130 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2131 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2132 'duration': 21,
2133 'view_count': int,
2134 'age_limit': 0,
2135 'categories': ['Gaming'],
2136 'tags': 'count:23',
2137 'playable_in_embed': True,
2138 'live_status': 'not_live',
2139 'upload_date': '20220103',
2140 'like_count': int,
2141 'availability': 'public',
2142 'channel': 'Leon Nguyen',
2143 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2144 'channel_follower_count': int
2145 }
2146 }, {
2147 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2148 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2149 'info_dict': {
2150 'id': 'mzZzzBU6lrM',
2151 'ext': 'mp4',
2152 'title': 'I Met GeorgeNotFound In Real Life...',
2153 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2154 'uploader': 'Quackity',
2155 'uploader_id': 'QuackityHQ',
2156 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2157 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2158 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2159 'duration': 955,
2160 'view_count': int,
2161 'age_limit': 0,
2162 'categories': ['Entertainment'],
2163 'tags': 'count:26',
2164 'playable_in_embed': True,
2165 'live_status': 'not_live',
2166 'release_timestamp': 1641172509,
2167 'release_date': '20220103',
2168 'upload_date': '20220103',
2169 'like_count': int,
2170 'availability': 'public',
2171 'channel': 'Quackity',
2172 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2173 'channel_follower_count': int
2174 }
2175 },
2176 { # continuous livestream. Microformat upload date should be preferred.
2177 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2178 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2179 'info_dict': {
2180 'id': 'kgx4WGK0oNU',
2181 'title': r're:jazz\/lofi hip hop radio🌱chill beats to relax\/study to \[LIVE 24\/7\] \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
2182 'ext': 'mp4',
2183 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2184 'availability': 'public',
2185 'age_limit': 0,
2186 'release_timestamp': 1637975704,
2187 'upload_date': '20210619',
2188 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2189 'live_status': 'is_live',
2190 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2191 'uploader': '阿鲍Abao',
2192 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2193 'channel': 'Abao in Tokyo',
2194 'channel_follower_count': int,
2195 'release_date': '20211127',
2196 'tags': 'count:39',
2197 'categories': ['People & Blogs'],
2198 'like_count': int,
2199 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2200 'view_count': int,
2201 'playable_in_embed': True,
2202 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2203 },
2204 'params': {'skip_download': True}
6e634cbe 2205 }, {
2206 # Story. Requires specific player params to work.
2207 # Note: stories get removed after some period of time
ee27297f 2208 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2209 'info_dict': {
ee27297f 2210 'id': 'vv8qTUWmulI',
6e634cbe 2211 'ext': 'mp4',
ee27297f 2212 'availability': 'unlisted',
2213 'view_count': int,
2214 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2215 'upload_date': '20220526',
2216 'categories': ['Education'],
2217 'title': 'Story',
2218 'channel': 'IT\'S HISTORY',
2219 'description': '',
2220 'uploader_id': 'BlastfromthePast',
2221 'duration': 12,
2222 'uploader': 'IT\'S HISTORY',
6e634cbe 2223 'playable_in_embed': True,
6e634cbe 2224 'age_limit': 0,
6e634cbe 2225 'live_status': 'not_live',
ee27297f 2226 'tags': [],
2227 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2228 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2229 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2230 }
2231 }, {
2232 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2233 'info_dict': {
2234 'id': 'tjjjtzRLHvA',
2235 'ext': 'mp4',
2236 'title': 'ハッシュタグ無し };if window.ytcsi',
2237 'upload_date': '20220323',
2238 'like_count': int,
2239 'availability': 'unlisted',
2240 'channel': 'nao20010128nao',
2241 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2242 'age_limit': 0,
2243 'uploader': 'nao20010128nao',
2244 'uploader_id': 'nao20010128nao',
2245 'categories': ['Music'],
6e634cbe 2246 'view_count': int,
2247 'description': '',
ee27297f 2248 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2249 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2250 'live_status': 'not_live',
2251 'playable_in_embed': True,
2252 'channel_follower_count': int,
2253 'duration': 6,
2254 'tags': [],
2255 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2256 }
2257 }
2eb88d95
PH
2258 ]
2259
201c1459 2260 @classmethod
2261 def suitable(cls, url):
4dfbf869 2262 from ..utils import parse_qs
2263
201c1459 2264 qs = parse_qs(url)
2265 if qs.get('list', [None])[0]:
2266 return False
86e5f3ed 2267 return super().suitable(url)
201c1459 2268
e0df6211 2269 def __init__(self, *args, **kwargs):
86e5f3ed 2270 super().__init__(*args, **kwargs)
545cc85d 2271 self._code_cache = {}
83799698 2272 self._player_cache = {}
e0df6211 2273
adbc4ec4 2274 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2275 lock = threading.Lock()
2276
2277 is_live = True
185bf310 2278 start_time = time.time()
adbc4ec4
THD
2279 formats = [f for f in formats if f.get('is_from_start')]
2280
185bf310 2281 def refetch_manifest(format_id, delay):
2282 nonlocal formats, start_time, is_live
2283 if time.time() <= start_time + delay:
adbc4ec4
THD
2284 return
2285
2286 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2287 video_details = traverse_obj(
2288 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2289 microformats = traverse_obj(
2290 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2291 expected_type=dict, default=[])
2292 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2293 start_time = time.time()
adbc4ec4 2294
185bf310 2295 def mpd_feed(format_id, delay):
adbc4ec4
THD
2296 """
2297 @returns (manifest_url, manifest_stream_number, is_live) or None
2298 """
2299 with lock:
185bf310 2300 refetch_manifest(format_id, delay)
adbc4ec4
THD
2301
2302 f = next((f for f in formats if f['format_id'] == format_id), None)
2303 if not f:
185bf310 2304 if not is_live:
2305 self.to_screen(f'{video_id}: Video is no longer live')
2306 else:
2307 self.report_warning(
2308 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2309 return None
2310 return f['manifest_url'], f['manifest_stream_number'], is_live
2311
2312 for f in formats:
a539f065 2313 f['is_live'] = True
adbc4ec4
THD
2314 f['protocol'] = 'http_dash_segments_generator'
2315 f['fragments'] = functools.partial(
2316 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2317
2318 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2319 FETCH_SPAN, MAX_DURATION = 5, 432000
2320
2321 mpd_url, stream_number, is_live = None, None, True
2322
2323 begin_index = 0
2324 download_start_time = ctx.get('start') or time.time()
2325
2326 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2327 if lack_early_segments:
2328 self.report_warning(bug_reports_message(
2329 'Starting download from the last 120 hours of the live stream since '
2330 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2331 lack_early_segments = True
2332
2333 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2334 fragments, fragment_base_url = None, None
2335
a539f065 2336 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2337 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2338 # Obtain from MPD's maximum seq value
2339 old_mpd_url = mpd_url
185bf310 2340 last_error = ctx.pop('last_error', None)
14f25df2 2341 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2342 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2343 or (mpd_url, stream_number, False))
2344 if not refresh_sequence:
2345 if expire_fast and not is_live:
2346 return False, last_seq
2347 elif old_mpd_url == mpd_url:
2348 return True, last_seq
adbc4ec4
THD
2349 try:
2350 fmts, _ = self._extract_mpd_formats_and_subtitles(
2351 mpd_url, None, note=False, errnote=False, fatal=False)
2352 except ExtractorError:
2353 fmts = None
2354 if not fmts:
a539f065 2355 no_fragment_score += 2
adbc4ec4
THD
2356 return False, last_seq
2357 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2358 fragments = fmt_info['fragments']
2359 fragment_base_url = fmt_info['fragment_base_url']
2360 assert fragment_base_url
2361
2362 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2363 return True, _last_seq
2364
2365 while is_live:
2366 fetch_time = time.time()
2367 if no_fragment_score > 30:
2368 return
2369 if last_segment_url:
2370 # Obtain from "X-Head-Seqnum" header value from each segment
2371 try:
2372 urlh = self._request_webpage(
2373 last_segment_url, None, note=False, errnote=False, fatal=False)
2374 except ExtractorError:
2375 urlh = None
2376 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2377 if last_seq is None:
a539f065 2378 no_fragment_score += 2
adbc4ec4
THD
2379 last_segment_url = None
2380 continue
2381 else:
a539f065
LNO
2382 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2383 no_fragment_score += 2
185bf310 2384 if not should_continue:
adbc4ec4
THD
2385 continue
2386
2387 if known_idx > last_seq:
2388 last_segment_url = None
2389 continue
2390
2391 last_seq += 1
2392
2393 if begin_index < 0 and known_idx < 0:
2394 # skip from the start when it's negative value
2395 known_idx = last_seq + begin_index
2396 if lack_early_segments:
2397 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2398 try:
2399 for idx in range(known_idx, last_seq):
2400 # do not update sequence here or you'll get skipped some part of it
a539f065 2401 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2402 if not should_continue:
adbc4ec4
THD
2403 known_idx = idx - 1
2404 raise ExtractorError('breaking out of outer loop')
2405 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2406 yield {
2407 'url': last_segment_url,
36195c44 2408 'fragment_count': last_seq,
adbc4ec4
THD
2409 }
2410 if known_idx == last_seq:
2411 no_fragment_score += 5
2412 else:
2413 no_fragment_score = 0
2414 known_idx = last_seq
2415 except ExtractorError:
2416 continue
2417
2418 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2419
b6de707d 2420 def _extract_player_url(self, *ytcfgs, webpage=None):
2421 player_url = traverse_obj(
2422 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2423 get_all=False, expected_type=str)
11f9be09 2424 if not player_url:
b6de707d 2425 return
60f393e4 2426 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2427
b6de707d 2428 def _download_player_url(self, video_id, fatal=False):
2429 res = self._download_webpage(
2430 'https://www.youtube.com/iframe_api',
2431 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2432 if res:
2433 player_version = self._search_regex(
2434 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2435 if player_version:
2436 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2437
60064c53
PH
2438 def _signature_cache_id(self, example_sig):
2439 """ Return a string representation of a signature """
14f25df2 2440 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2441
e40c758c
S
2442 @classmethod
2443 def _extract_player_info(cls, player_url):
2444 for player_re in cls._PLAYER_INFO_RE:
2445 id_m = re.search(player_re, player_url)
2446 if id_m:
2447 break
2448 else:
c081b35c 2449 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2450 return id_m.group('id')
e40c758c 2451
404f611f 2452 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2453 player_id = self._extract_player_info(player_url)
2454 if player_id not in self._code_cache:
1276a43a 2455 code = self._download_webpage(
109dd3b2 2456 player_url, video_id, fatal=fatal,
2457 note='Downloading player ' + player_id,
2458 errnote='Download of %s failed' % player_url)
1276a43a 2459 if code:
2460 self._code_cache[player_id] = code
404f611f 2461 return self._code_cache.get(player_id)
109dd3b2 2462
e40c758c 2463 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2464 player_id = self._extract_player_info(player_url)
e0df6211 2465
c4417ddb 2466 # Read from filesystem cache
86e5f3ed 2467 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2468 assert os.path.basename(func_id) == func_id
a0e07d31 2469
ae61d108 2470 self.write_debug(f'Extracting signature function {func_id}')
9809740b 2471 cache_spec = self.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2472 if cache_spec is not None:
78caa52a 2473 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2474
404f611f 2475 code = self._load_player(video_id, player_url)
2476 if code:
109dd3b2 2477 res = self._parse_sig_js(code)
e0df6211 2478
ac668111 2479 test_string = ''.join(map(chr, range(len(example_sig))))
109dd3b2 2480 cache_res = res(test_string)
2481 cache_spec = [ord(c) for c in cache_res]
83799698 2482
9809740b 2483 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
109dd3b2 2484 return res
83799698 2485
60064c53 2486 def _print_sig_code(self, func, example_sig):
404f611f 2487 if not self.get_param('youtube_print_sig_code'):
2488 return
2489
edf3e38e
PH
2490 def gen_sig_code(idxs):
2491 def _genslice(start, end, step):
78caa52a 2492 starts = '' if start == 0 else str(start)
8bcc8756 2493 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2494 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2495 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2496
2497 step = None
7af808a5
PH
2498 # Quelch pyflakes warnings - start will be set when step is set
2499 start = '(Never used)'
edf3e38e
PH
2500 for i, prev in zip(idxs[1:], idxs[:-1]):
2501 if step is not None:
2502 if i - prev == step:
2503 continue
2504 yield _genslice(start, prev, step)
2505 step = None
2506 continue
2507 if i - prev in [-1, 1]:
2508 step = i - prev
2509 start = prev
2510 continue
2511 else:
78caa52a 2512 yield 's[%d]' % prev
edf3e38e 2513 if step is None:
78caa52a 2514 yield 's[%d]' % i
edf3e38e
PH
2515 else:
2516 yield _genslice(start, i, step)
2517
ac668111 2518 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2519 cache_res = func(test_string)
edf3e38e 2520 cache_spec = [ord(c) for c in cache_res]
78caa52a 2521 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2522 signature_id_tuple = '(%s)' % (
14f25df2 2523 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2524 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2525 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2526 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2527
e0df6211
PH
2528 def _parse_sig_js(self, jscode):
2529 funcname = self._search_regex(
abefc03f
S
2530 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2531 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
2532 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2533 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2534 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}\(a,\d+\)',
2535 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 2536 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2537 # Obsolete patterns
2538 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2539 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2540 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2541 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2542 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2543 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2544 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2545 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2546 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2547
2548 jsi = JSInterpreter(jscode)
2549 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2550 return lambda s: initial_function([s])
2551
545cc85d 2552 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2553 """Turn the encrypted s field into a working signature"""
c8bf86d5 2554 try:
62af3a0e 2555 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5 2556 if player_id not in self._player_cache:
52023f12 2557 func = self._extract_signature_function(video_id, player_url, s)
c8bf86d5
PH
2558 self._player_cache[player_id] = func
2559 func = self._player_cache[player_id]
404f611f 2560 self._print_sig_code(func, s)
c8bf86d5
PH
2561 return func(s)
2562 except Exception as e:
52023f12 2563 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2564
2565 def _decrypt_nsig(self, s, video_id, player_url):
2566 """Turn the encrypted n field into a working signature"""
2567 if player_url is None:
2568 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2569 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2570
2571 sig_id = ('nsig_value', s)
2572 if sig_id in self._player_cache:
2573 return self._player_cache[sig_id]
2574
2575 try:
2576 player_id = ('nsig', player_url)
2577 if player_id not in self._player_cache:
2578 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2579 func = self._player_cache[player_id]
2580 self._player_cache[sig_id] = func(s)
2581 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2582 return self._player_cache[sig_id]
2583 except Exception as e:
aa9369a2 2584 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2585
2586 def _extract_n_function_name(self, jscode):
48416bc4 2587 nfunc, idx = self._search_regex(
c571b3a6 2588 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2589 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2590 if not idx:
2591 return nfunc
2592 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2593 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2594 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2595
2596 def _extract_n_function(self, video_id, player_url):
2597 player_id = self._extract_player_info(player_url)
9809740b 2598 func_code = self.cache.load('youtube-nsig', player_id)
404f611f 2599
2600 if func_code:
2601 jsi = JSInterpreter(func_code)
2602 else:
2603 jscode = self._load_player(video_id, player_url)
2604 funcname = self._extract_n_function_name(jscode)
2605 jsi = JSInterpreter(jscode)
2606 func_code = jsi.extract_function_code(funcname)
9809740b 2607 self.cache.store('youtube-nsig', player_id, func_code)
404f611f 2608
2609 if self.get_param('youtube_print_sig_code'):
2610 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2611
2612 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2613
109dd3b2 2614 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2615 """
2616 Extract signatureTimestamp (sts)
2617 Required to tell API what sig/player version is in use.
2618 """
2619 sts = None
2620 if isinstance(ytcfg, dict):
2621 sts = int_or_none(ytcfg.get('STS'))
2622
2623 if not sts:
2624 # Attempt to extract from player
2625 if player_url is None:
2626 error_msg = 'Cannot extract signature timestamp without player_url.'
2627 if fatal:
2628 raise ExtractorError(error_msg)
2629 self.report_warning(error_msg)
2630 return
404f611f 2631 code = self._load_player(video_id, player_url, fatal=fatal)
2632 if code:
109dd3b2 2633 sts = int_or_none(self._search_regex(
2634 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2635 'JS player signature timestamp', group='sts', fatal=fatal))
2636 return sts
2637
11f9be09 2638 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
2639 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2640 label = 'fully ' if is_full else ''
2641 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2642 expected_type=url_or_none)
2643 if not url:
2644 self.report_warning(f'Unable to mark {label}watched')
2645 return
14f25df2 2646 parsed_url = urllib.parse.urlparse(url)
2647 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
2648
2649 # cpn generation algorithm is reverse engineered from base.js.
2650 # In fact it works even with dummy cpn.
2651 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2652 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2653
2654 # # more consistent results setting it to right before the end
2655 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2656
2657 qs.update({
2658 'ver': ['2'],
2659 'cpn': [cpn],
2660 'cmt': video_length,
2661 'el': 'detailpage', # otherwise defaults to "shorts"
2662 })
2663
2664 if is_full:
2665 # these seem to mark watchtime "history" in the real world
2666 # they're required, so send in a single value
2667 qs.update({
2668 'st': video_length,
2669 'et': video_length,
2670 })
2671
14f25df2 2672 url = urllib.parse.urlunparse(
2673 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
2674
2675 self._download_webpage(
2676 url, video_id, f'Marking {label}watched',
2677 'Unable to mark watched', fatal=False)
d77ab8e2 2678
66c9fa36
S
2679 @staticmethod
2680 def _extract_urls(webpage):
2681 # Embedded YouTube player
2682 entries = [
2683 unescapeHTML(mobj.group('url'))
2684 for mobj in re.finditer(r'''(?x)
2685 (?:
2686 <iframe[^>]+?src=|
2687 data-video-url=|
2688 <embed[^>]+?src=|
2689 embedSWF\(?:\s*|
2690 <object[^>]+data=|
2691 new\s+SWFObject\(
2692 )
2693 (["\'])
2694 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2695 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2696 \1''', webpage)]
2697
2698 # lazyYT YouTube embed
2699 entries.extend(list(map(
2700 unescapeHTML,
2701 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2702
2703 # Wordpress "YouTube Video Importer" plugin
2704 matches = re.findall(r'''(?x)<div[^>]+
2705 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2706 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2707 entries.extend(m[-1] for m in matches)
2708
2709 return entries
2710
2711 @staticmethod
2712 def _extract_url(webpage):
2713 urls = YoutubeIE._extract_urls(webpage)
2714 return urls[0] if urls else None
2715
97665381
PH
2716 @classmethod
2717 def extract_id(cls, url):
ae61d108 2718 video_id = cls.get_temp_id(url)
2719 if not video_id:
2720 raise ExtractorError(f'Invalid URL: {url}')
2721 return video_id
c5e8d7af 2722
7c365c21 2723 def _extract_chapters_from_json(self, data, duration):
2724 chapter_list = traverse_obj(
2725 data, (
2726 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2727 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2728 ), expected_type=list)
2729
2730 return self._extract_chapters(
2731 chapter_list,
2732 chapter_time=lambda chapter: float_or_none(
2733 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2734 chapter_title=lambda chapter: traverse_obj(
2735 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2736 duration=duration)
2737
2738 def _extract_chapters_from_engagement_panel(self, data, duration):
2739 content_list = traverse_obj(
8bdd16b4 2740 data,
7c365c21 2741 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2742 expected_type=list, default=[])
052e1350 2743 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2744 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2745
1890fc63 2746 return next(filter(None, (
2747 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2748 chapter_time, chapter_title, duration)
2749 for contents in content_list)), [])
7c365c21 2750
1890fc63 2751 def _extract_chapters_from_description(self, description, duration):
2752 return self._extract_chapters(
2753 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2754 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2755 duration=duration, strict=False)
84213ea8 2756
1890fc63 2757 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2758 if not duration:
2759 return
2760 chapter_list = [{
2761 'start_time': chapter_time(chapter),
2762 'title': chapter_title(chapter),
2763 } for chapter in chapter_list or []]
2764 if not strict:
2765 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2766
a3976e07 2767 chapters = [{'start_time': 0}]
1890fc63 2768 for idx, chapter in enumerate(chapter_list):
a3976e07 2769 if chapter['start_time'] is None:
1890fc63 2770 self.report_warning(f'Incomplete chapter {idx}')
2771 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
1890fc63 2772 chapters.append(chapter)
2773 else:
2774 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}"')
a3976e07 2775 return chapters[1:]
84213ea8 2776
a1c5d2ca
M
2777 def _extract_comment(self, comment_renderer, parent=None):
2778 comment_id = comment_renderer.get('commentId')
2779 if not comment_id:
2780 return
fe93e2c4 2781
052e1350 2782 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2783
49bd8c66 2784 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2785 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2786 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca 2787 author_id = try_get(comment_renderer,
14f25df2 2788 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
fe93e2c4 2789
49bd8c66 2790 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
14f25df2 2791 lambda x: x['likeCount']), str)) or 0
a1c5d2ca 2792 author_thumbnail = try_get(comment_renderer,
14f25df2 2793 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
a1c5d2ca
M
2794
2795 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2796 is_favorited = 'creatorHeart' in (try_get(
2797 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2798 return {
2799 'id': comment_id,
2800 'text': text,
d92f5d5a 2801 'timestamp': timestamp,
a1c5d2ca
M
2802 'time_text': time_text,
2803 'like_count': votes,
97524332 2804 'is_favorited': is_favorited,
a1c5d2ca
M
2805 'author': author,
2806 'author_id': author_id,
2807 'author_thumbnail': author_thumbnail,
2808 'author_is_uploader': author_is_uploader,
2809 'parent': parent or 'root'
2810 }
2811
46383212 2812 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2813
2814 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2815
2816 def extract_header(contents):
2d6659b9 2817 _continuation = None
2818 for content in contents:
46383212 2819 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2820 expected_comment_count = self._get_count(
2821 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2822
2d6659b9 2823 if expected_comment_count:
46383212 2824 tracker['est_total'] = expected_comment_count
2825 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2826 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2827
2828 sort_menu_item = try_get(
2829 comments_header_renderer,
2830 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2831 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2832
2833 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2834 if not _continuation:
2835 continue
2836
46383212 2837 sort_text = str_or_none(sort_menu_item.get('title'))
2838 if not sort_text:
2d6659b9 2839 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2840 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2841 break
a2160aa4 2842 return _continuation
a1c5d2ca 2843
2d6659b9 2844 def extract_thread(contents):
a1c5d2ca 2845 if not parent:
46383212 2846 tracker['current_page_thread'] = 0
a1c5d2ca 2847 for content in contents:
46383212 2848 if not parent and tracker['total_parent_comments'] >= max_parents:
2849 yield
a1c5d2ca 2850 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2851 comment_renderer = get_first(
2852 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2853 expected_type=dict, default={})
a1c5d2ca 2854
a1c5d2ca
M
2855 comment = self._extract_comment(comment_renderer, parent)
2856 if not comment:
2857 continue
46383212 2858
2859 tracker['running_total'] += 1
2860 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2861 yield comment
46383212 2862
a1c5d2ca
M
2863 # Attempt to get the replies
2864 comment_replies_renderer = try_get(
2865 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2866
2867 if comment_replies_renderer:
46383212 2868 tracker['current_page_thread'] += 1
a1c5d2ca 2869 comment_entries_iter = self._comment_entries(
99e9e001 2870 comment_replies_renderer, ytcfg, video_id,
46383212 2871 parent=comment.get('id'), tracker=tracker)
86e5f3ed 2872 yield from itertools.islice(comment_entries_iter, min(
2873 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 2874
46383212 2875 # Keeps track of counts across recursive calls
2876 if not tracker:
2877 tracker = dict(
2878 running_total=0,
2879 est_total=0,
2880 current_page_thread=0,
2881 total_parent_comments=0,
2882 total_reply_comments=0)
2883
2884 # TODO: Deprecated
2d6659b9 2885 # YouTube comments have a max depth of 2
46383212 2886 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2887 if max_depth:
2888 self._downloader.deprecation_warning(
2889 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2890 if max_depth == 1 and parent:
2891 return
a1c5d2ca 2892
46383212 2893 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2894 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2895
46383212 2896 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2897
46383212 2898 response = None
6e634cbe 2899 is_forced_continuation = False
2d6659b9 2900 is_first_continuation = parent is None
6e634cbe 2901 if is_first_continuation and not continuation:
2902 # Sometimes you can get comments by generating the continuation yourself,
2903 # even if YouTube initially reports them being disabled - e.g. stories comments.
2904 # Note: if the comment section is actually disabled, YouTube may return a response with
2905 # required check_get_keys missing. So we will disable that check initially in this case.
2906 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2907 is_forced_continuation = True
a1c5d2ca
M
2908
2909 for page_num in itertools.count(0):
2910 if not continuation:
2911 break
46383212 2912 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2913 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2914 if page_num == 0:
2915 if is_first_continuation:
2916 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2917 else:
2d6659b9 2918 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2919 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2920 else:
2921 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2922 ' ' if parent else '', ' replies' if parent else '',
2923 page_num, comment_prog_str)
2924
2925 response = self._extract_response(
fe93e2c4 2926 item_id=None, query=continuation,
2d6659b9 2927 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
6e634cbe 2928 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2929 is_forced_continuation = False
46383212 2930 continuation_contents = traverse_obj(
2931 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2932
2d6659b9 2933 continuation = None
46383212 2934 for continuation_section in continuation_contents:
2935 continuation_items = traverse_obj(
2936 continuation_section,
2937 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2938 get_all=False, expected_type=list) or []
2939 if is_first_continuation:
2940 continuation = extract_header(continuation_items)
2941 is_first_continuation = False
2d6659b9 2942 if continuation:
a1c5d2ca 2943 break
46383212 2944 continue
a1c5d2ca 2945
46383212 2946 for entry in extract_thread(continuation_items):
2947 if not entry:
2948 return
2949 yield entry
2950 continuation = self._extract_continuation({'contents': continuation_items})
2951 if continuation:
2d6659b9 2952 break
a1c5d2ca 2953
6e634cbe 2954 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2955 if message and not parent and tracker['running_total'] == 0:
2956 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
2957
2958 @staticmethod
2959 def _generate_comment_continuation(video_id):
2960 """
2961 Generates initial comment section continuation token from given video id
2962 """
2963 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
2964 return base64.b64encode(token.encode()).decode()
2965
a2160aa4 2966 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2967 """Entry for comment extraction"""
2d6659b9 2968 def _real_comment_extract(contents):
aae16f6e 2969 renderer = next((
2970 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2971 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2972 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2973
a2160aa4 2974 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2975 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2976
109dd3b2 2977 @staticmethod
99e9e001 2978 def _get_checkok_params():
2979 return {'contentCheckOk': True, 'racyCheckOk': True}
2980
2981 @classmethod
2982 def _generate_player_context(cls, sts=None):
109dd3b2 2983 context = {
2984 'html5Preference': 'HTML5_PREF_WANTS',
2985 }
2986 if sts is not None:
2987 context['signatureTimestamp'] = sts
2988 return {
2989 'playbackContext': {
2990 'contentPlaybackContext': context
a1a7907b 2991 },
99e9e001 2992 **cls._get_checkok_params()
109dd3b2 2993 }
2994
e7e94f2a
D
2995 @staticmethod
2996 def _is_agegated(player_response):
2997 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 2998 return True
e7e94f2a
D
2999
3000 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3001 AGE_GATE_REASONS = (
3002 'confirm your age', 'age-restricted', 'inappropriate', # reason
3003 'age_verification_required', 'age_check_required', # status
3004 )
3005 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3006
3007 @staticmethod
3008 def _is_unplayable(player_response):
3009 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3010
99e9e001 3011 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 3012
11f9be09 3013 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3014 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3015 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3016 headers = self.generate_api_headers(
99e9e001 3017 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3018
6e634cbe 3019 yt_query = {
3020 'videoId': video_id,
3021 'params': '8AEB' # enable stories
3022 }
11f9be09 3023 yt_query.update(self._generate_player_context(sts))
3024 return self._extract_response(
3025 item_id=video_id, ep='player', query=yt_query,
379e44ed 3026 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3027 default_client=client,
11f9be09 3028 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3029 ) or None
3030
11f9be09 3031 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3032 requested_clients = []
d0d012d4 3033 default = ['android', 'web']
000c15a4 3034 allowed_clients = sorted(
86e5f3ed 3035 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3036 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3037 for client in self._configuration_arg('player_client'):
3038 if client in allowed_clients:
3039 requested_clients.append(client)
d0d012d4 3040 elif client == 'default':
3041 requested_clients.extend(default)
b4c055ba 3042 elif client == 'all':
3043 requested_clients.extend(allowed_clients)
3044 else:
3045 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3046 if not requested_clients:
d0d012d4 3047 requested_clients = default
cf7e015f 3048
11f9be09 3049 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3050 requested_clients.extend(
e7e94f2a 3051 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3052
11f9be09 3053 return orderedSet(requested_clients)
cf7e015f 3054
99e9e001 3055 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 3056 initial_pr = None
3057 if webpage:
b7c47b74 3058 initial_pr = self._search_json(
3059 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3060
ae729626 3061 all_clients = set(clients)
c0bc527b 3062 clients = clients[::-1]
b6de707d 3063 prs = []
e7e94f2a 3064
ae729626 3065 def append_client(*client_names):
e7870111 3066 """ Append the first client name that exists but not already used """
ae729626 3067 for client_name in client_names:
e7870111
D
3068 actual_client = _split_innertube_client(client_name)[0]
3069 if actual_client in INNERTUBE_CLIENTS:
3070 if actual_client not in all_clients:
ae729626 3071 clients.append(client_name)
e7870111
D
3072 all_clients.add(actual_client)
3073 return
e7e94f2a 3074
379e44ed 3075 # Android player_response does not have microFormats which are needed for
3076 # extraction of some data. So we return the initial_pr with formats
3077 # stripped out even if not requested by the user
3078 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3079 if initial_pr:
3080 pr = dict(initial_pr)
3081 pr['streamingData'] = None
b6de707d 3082 prs.append(pr)
379e44ed 3083
3084 last_error = None
b6de707d 3085 tried_iframe_fallback = False
3086 player_url = None
c0bc527b 3087 while clients:
e7870111 3088 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3089 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3090 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3091 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3092
b6de707d 3093 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3094 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3095 if 'js' in self._configuration_arg('player_skip'):
3096 require_js_player = False
3097 player_url = None
3098
3099 if not player_url and not tried_iframe_fallback and require_js_player:
3100 player_url = self._download_player_url(video_id)
3101 tried_iframe_fallback = True
3102
379e44ed 3103 try:
3104 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 3105 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 3106 except ExtractorError as e:
3107 if last_error:
3108 self.report_warning(last_error)
3109 last_error = e
3110 continue
3111
11f9be09 3112 if pr:
b6de707d 3113 prs.append(pr)
c0bc527b 3114
e7e94f2a 3115 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3116 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3117 append_client(f'{base_client}_creator')
e7e94f2a 3118 elif self._is_agegated(pr):
e7870111
D
3119 if variant == 'tv_embedded':
3120 append_client(f'{base_client}_embedded')
3121 elif not variant:
3122 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3123
379e44ed 3124 if last_error:
b6de707d 3125 if not len(prs):
379e44ed 3126 raise last_error
3127 self.report_warning(last_error)
b6de707d 3128 return prs, player_url
11f9be09 3129
a1b2d843 3130 def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3131 itags, stream_ids = {}, []
2a9c6dcd 3132 itag_qualities, res_qualities = {}, {}
d3fc8074 3133 q = qualities([
2a9c6dcd 3134 # Normally tiny is the smallest video-only formats. But
3135 # audio-only formats with unknown quality may get tagged as tiny
3136 'tiny',
3137 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3138 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3139 ])
11f9be09 3140 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3141
545cc85d 3142 for fmt in streaming_formats:
727029c5 3143 if fmt.get('targetDurationSec'):
545cc85d 3144 continue
321bf820 3145
cc2db878 3146 itag = str_or_none(fmt.get('itag'))
9297939e 3147 audio_track = fmt.get('audioTrack') or {}
3148 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3149 if stream_id in stream_ids:
3150 continue
3151
cc2db878 3152 quality = fmt.get('quality')
2a9c6dcd 3153 height = int_or_none(fmt.get('height'))
d3fc8074 3154 if quality == 'tiny' or not quality:
3155 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3156 # The 3gp format (17) in android client has a quality of "small",
3157 # but is actually worse than other formats
3158 if itag == '17':
3159 quality = 'tiny'
3160 if quality:
3161 if itag:
3162 itag_qualities[itag] = quality
3163 if height:
3164 res_qualities[height] = quality
cc2db878 3165 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3166 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3167 # number of fragment that would subsequently requested with (`&sq=N`)
3168 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3169 continue
3170
545cc85d 3171 fmt_url = fmt.get('url')
3172 if not fmt_url:
14f25df2 3173 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3174 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3175 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3176 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3177 continue
52023f12 3178 try:
3179 fmt_url += '&%s=%s' % (
3180 traverse_obj(sc, ('sp', -1)) or 'signature',
3181 self._decrypt_signature(encrypted_sig, video_id, player_url)
3182 )
3183 except ExtractorError as e:
3184 self.report_warning('Signature extraction failed: Some formats may be missing', only_once=True)
3185 self.write_debug(e, only_once=True)
201e9eaa 3186 continue
545cc85d 3187
404f611f 3188 query = parse_qs(fmt_url)
3189 throttled = False
b2916526 3190 if query.get('n'):
404f611f 3191 try:
3192 fmt_url = update_url_query(fmt_url, {
3193 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3194 except ExtractorError as e:
aa9369a2 3195 self.report_warning(
1d485a1a 3196 'nsig extraction failed: You may experience throttling for some formats\n'
52023f12 3197 f'n = {query["n"][0]} ; player = {player_url}', only_once=True)
3198 self.write_debug(e, only_once=True)
404f611f 3199 throttled = True
3200
545cc85d 3201 if itag:
a0bb6ce5 3202 itags[itag] = 'https'
9297939e 3203 stream_ids.append(stream_id)
3204
0ad92dfb 3205 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3206 language_preference = (
3207 10 if audio_track.get('audioIsDefault') and 10
3208 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3209 else -1)
0ad92dfb 3210 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3211 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3212 # Make sure to avoid false positives with small duration differences.
3213 # Eg: __2ABJjxzNo, ySuUZEjARPY
3214 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3215 if is_damaged:
0f06bcd7 3216 self.report_warning(
3217 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3218 dct = {
3219 'asr': int_or_none(fmt.get('audioSampleRate')),
3220 'filesize': int_or_none(fmt.get('contentLength')),
3221 'format_id': itag,
34921b43 3222 'format_note': join_nonempty(
26e8e044 3223 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3224 ' (default)' if language_preference > 0 else ''),
404f611f 3225 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
0ad92dfb 3226 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3227 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3228 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3229 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3230 'height': height,
dca3ff4a 3231 'quality': q(quality),
727029c5 3232 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3233 'tbr': tbr,
545cc85d 3234 'url': fmt_url,
2a9c6dcd 3235 'width': int_or_none(fmt.get('width')),
ab6df717 3236 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3237 'desc' if language_preference < -1 else ''),
3238 'language_preference': language_preference,
a405b38f 3239 # Strictly de-prioritize damaged and 3gp formats
3240 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3241 }
60bdb7bd 3242 mime_mobj = re.match(
3243 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3244 if mime_mobj:
3245 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3246 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3247 no_audio = dct.get('acodec') == 'none'
3248 no_video = dct.get('vcodec') == 'none'
3249 if no_audio:
3250 dct['vbr'] = tbr
3251 if no_video:
3252 dct['abr'] = tbr
3253 if no_audio or no_video:
545cc85d 3254 dct['downloader_options'] = {
3255 # Youtube throttles chunks >~10M
3256 'http_chunk_size': 10485760,
bf1317d2 3257 }
7c60c33e 3258 if dct.get('ext'):
3259 dct['container'] = dct['ext'] + '_dash'
11f9be09 3260 yield dct
545cc85d 3261
adbc4ec4 3262 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3263 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3264 if not self.get_param('youtube_include_hls_manifest', True):
3265 skip_manifests.append('hls')
0f06bcd7 3266 if not self.get_param('youtube_include_dash_manifest', True):
3267 skip_manifests.append('dash')
adbc4ec4
THD
3268 get_dash = 'dash' not in skip_manifests and (
3269 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3270 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3271
a0bb6ce5 3272 def process_manifest_format(f, proto, itag):
3273 if itag in itags:
3274 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3275 return False
3276 itag = f'{itag}-{proto}'
3277 if itag:
3278 f['format_id'] = itag
3279 itags[itag] = proto
3280
3281 f['quality'] = next((
3282 q(qdict[val])
e339d25a 3283 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3284 if val in qdict), -1)
3285 return True
2a9c6dcd 3286
11f9be09 3287 for sd in streaming_data:
5d3a0e79 3288 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3289 if hls_manifest_url:
2a9c6dcd 3290 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 3291 if process_manifest_format(f, 'hls', self._search_regex(
3292 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3293 yield f
545cc85d 3294
5d3a0e79 3295 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3296 if dash_manifest_url:
2a9c6dcd 3297 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 3298 if process_manifest_format(f, 'dash', f['format_id']):
3299 f['filesize'] = int_or_none(self._search_regex(
3300 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3301 if live_from_start:
3302 f['is_from_start'] = True
3303
a0bb6ce5 3304 yield f
11f9be09 3305
720c3099 3306 def _extract_storyboard(self, player_responses, duration):
3307 spec = get_first(
3308 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3309 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3310 if not base_url:
720c3099 3311 return
720c3099 3312 L = len(spec) - 1
3313 for i, args in enumerate(spec):
3314 args = args.split('#')
3315 counts = list(map(int_or_none, args[:5]))
3316 if len(args) != 8 or not all(counts):
3317 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3318 continue
3319 width, height, frame_count, cols, rows = counts
3320 N, sigh = args[6:]
3321
3322 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3323 fragment_count = frame_count / (cols * rows)
3324 fragment_duration = duration / fragment_count
3325 yield {
3326 'format_id': f'sb{i}',
3327 'format_note': 'storyboard',
3328 'ext': 'mhtml',
3329 'protocol': 'mhtml',
3330 'acodec': 'none',
3331 'vcodec': 'none',
3332 'url': url,
3333 'width': width,
3334 'height': height,
3335 'fragments': [{
b3edc806 3336 'url': url.replace('$M', str(j)),
720c3099 3337 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3338 } for j in range(math.ceil(fragment_count))],
3339 }
3340
adbc4ec4 3341 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3342 webpage = None
3343 if 'webpage' not in self._configuration_arg('player_skip'):
3344 webpage = self._download_webpage(
6e634cbe 3345 webpage_url + '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id, fatal=False)
11f9be09 3346
3347 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3348
b6de707d 3349 player_responses, player_url = self._extract_player_responses(
11f9be09 3350 self._get_requested_clients(url, smuggled_data),
99e9e001 3351 video_id, webpage, master_ytcfg)
11f9be09 3352
adbc4ec4
THD
3353 return webpage, master_ytcfg, player_responses, player_url
3354
a1b2d843 3355 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3356 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3357 is_live = get_first(video_details, 'isLive')
3358 if is_live is None:
3359 is_live = get_first(live_broadcast_details, 'isLiveNow')
3360
3361 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
a1b2d843 3362 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration))
adbc4ec4
THD
3363
3364 return live_broadcast_details, is_live, streaming_data, formats
3365
3366 def _real_extract(self, url):
3367 url, smuggled_data = unsmuggle_url(url, {})
3368 video_id = self._match_id(url)
3369
3370 base_url = self.http_scheme() + '//www.youtube.com/'
3371 webpage_url = base_url + 'watch?v=' + video_id
3372
3373 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3374
11f9be09 3375 playability_statuses = traverse_obj(
3376 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3377
3378 trailer_video_id = get_first(
3379 playability_statuses,
3380 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3381 expected_type=str)
3382 if trailer_video_id:
3383 return self.url_result(
3384 trailer_video_id, self.ie_key(), trailer_video_id)
3385
3386 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3387 if webpage else (lambda x: None))
3388
3389 video_details = traverse_obj(
3390 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3391 microformats = traverse_obj(
3392 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3393 expected_type=dict, default=[])
3394 video_title = (
3395 get_first(video_details, 'title')
3396 or self._get_text(microformats, (..., 'title'))
3397 or search_meta(['og:title', 'twitter:title', 'title']))
3398 video_description = get_first(video_details, 'shortDescription')
3399
d89257f3 3400 multifeed_metadata_list = get_first(
3401 player_responses,
3402 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3403 expected_type=str)
3404 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3405 if self.get_param('noplaylist'):
11f9be09 3406 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3407 else:
3408 entries = []
3409 feed_ids = []
3410 for feed in multifeed_metadata_list.split(','):
3411 # Unquote should take place before split on comma (,) since textual
3412 # fields may contain comma as well (see
3413 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3414 feed_data = urllib.parse.parse_qs(
ac668111 3415 urllib.parse.unquote_plus(feed))
d89257f3 3416
3417 def feed_entry(name):
3418 return try_get(
14f25df2 3419 feed_data, lambda x: x[name][0], str)
d89257f3 3420
3421 feed_id = feed_entry('id')
3422 if not feed_id:
3423 continue
3424 feed_title = feed_entry('title')
3425 title = video_title
3426 if feed_title:
3427 title += ' (%s)' % feed_title
3428 entries.append({
3429 '_type': 'url_transparent',
3430 'ie_key': 'Youtube',
3431 'url': smuggle_url(
3432 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3433 {'force_singlefeed': True}),
3434 'title': title,
3435 })
3436 feed_ids.append(feed_id)
3437 self.to_screen(
3438 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3439 % (', '.join(feed_ids), video_id))
3440 return self.playlist_result(
3441 entries, video_id, video_title, video_description)
11f9be09 3442
a1b2d843 3443 duration = int_or_none(
3444 get_first(video_details, 'lengthSeconds')
3445 or get_first(microformats, 'lengthSeconds')
3446 or parse_duration(search_meta('duration'))) or None
3447
829bbd1d 3448 if get_first(video_details, 'isPostLiveDvr'):
3449 self.write_debug('Video is in Post-Live Manifestless mode')
3450 if duration or 0 > 4 * 3600:
3451 self.report_warning(
3452 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3453 'This is a known issue and patches are welcome')
3454
a1b2d843 3455 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(
3456 video_id, microformats, video_details, player_responses, player_url, duration)
bf1317d2 3457
545cc85d 3458 if not formats:
11f9be09 3459 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3460 self.report_drm(video_id)
11f9be09 3461 pemr = get_first(
3462 playability_statuses,
3463 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3464 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3465 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3466 if subreason:
545cc85d 3467 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3468 countries = get_first(microformats, 'availableCountries')
545cc85d 3469 if not countries:
3470 regions_allowed = search_meta('regionsAllowed')
3471 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3472 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3473 reason += f'. {subreason}'
545cc85d 3474 if reason:
b7da73eb 3475 self.raise_no_formats(reason, expected=True)
bf1317d2 3476
11f9be09 3477 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3478 if not keywords and webpage:
3479 keywords = [
3480 unescapeHTML(m.group('content'))
3481 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3482 for keyword in keywords:
3483 if keyword.startswith('yt:stretch='):
201c1459 3484 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3485 if mobj:
3486 # NB: float is intentional for forcing float division
3487 w, h = (float(v) for v in mobj.groups())
3488 if w > 0 and h > 0:
3489 ratio = w / h
3490 for f in formats:
3491 if f.get('vcodec') != 'none':
3492 f['stretched_ratio'] = ratio
3493 break
a709d873 3494 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3495 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3496 if thumbnail_url:
3497 thumbnails.append({
3498 'url': thumbnail_url,
ff2751ac 3499 })
fccf5021 3500 original_thumbnails = thumbnails.copy()
3501
0ba692ac 3502 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3503 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3504 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3505 thumbnail_names = [
962ffcf8 3506 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 3507 # in resolution, these are not the custom thumbnail. So de-prioritize them
3508 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3509 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3510 ]
cca80fe6 3511 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3512 thumbnails.extend({
3513 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3514 video_id=video_id, name=name, ext=ext,
3515 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3516 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3517 for thumb in thumbnails:
cca80fe6 3518 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3519 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3520 self._remove_duplicate_formats(thumbnails)
fccf5021 3521 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3522
7ea65411 3523 category = get_first(microformats, 'category') or search_meta('genre')
3524 channel_id = str_or_none(
3525 get_first(video_details, 'channelId')
3526 or get_first(microformats, 'externalChannelId')
3527 or search_meta('channelId'))
7ea65411 3528 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3529
3530 live_content = get_first(video_details, 'isLiveContent')
3531 is_upcoming = get_first(video_details, 'isUpcoming')
3532 if is_live is None:
3533 if is_upcoming or live_content is False:
3534 is_live = False
3535 if is_upcoming is None and (live_content or is_live):
3536 is_upcoming = False
adbc4ec4
THD
3537 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3538 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3539 if not duration and live_end_time and live_start_time:
3540 duration = live_end_time - live_start_time
3541
3542 if is_live and self.get_param('live_from_start'):
3543 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3544
720c3099 3545 formats.extend(self._extract_storyboard(player_responses, duration))
3546
3547 # Source is given priority since formats that throttle are given lower source_preference
3548 # When throttling issue is fully fixed, remove this
3549 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3550
545cc85d 3551 info = {
3552 'id': video_id,
39ca3b5c 3553 'title': video_title,
545cc85d 3554 'formats': formats,
3555 'thumbnails': thumbnails,
fccf5021 3556 # The best thumbnail that we are sure exists. Prevents unnecessary
3557 # URL checking if user don't care about getting the best possible thumbnail
3558 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3559 'description': video_description,
11f9be09 3560 'uploader': get_first(video_details, 'author'),
545cc85d 3561 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3562 'uploader_url': owner_profile_url,
3563 'channel_id': channel_id,
a70635b8 3564 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3565 'duration': duration,
3566 'view_count': int_or_none(
11f9be09 3567 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3568 or search_meta('interactionCount')),
11f9be09 3569 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3570 'age_limit': 18 if (
11f9be09 3571 get_first(microformats, 'isFamilySafe') is False
545cc85d 3572 or search_meta('isFamilyFriendly') == 'false'
3573 or search_meta('og:restrictions:age') == '18+') else 0,
3574 'webpage_url': webpage_url,
3575 'categories': [category] if category else None,
3576 'tags': keywords,
11f9be09 3577 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3578 'is_live': is_live,
3579 'was_live': (False if is_live or is_upcoming or live_content is False
3580 else None if is_live is None or is_upcoming is None
3581 else live_content),
3582 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3583 'release_timestamp': live_start_time,
545cc85d 3584 }
b477fc13 3585
3944e7af 3586 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3587 if pctr:
ecdc9049 3588 def get_lang_code(track):
3589 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3590 or track.get('languageCode'))
3591
3592 # Converted into dicts to remove duplicates
3593 captions = {
3594 get_lang_code(sub): sub
3595 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3596 translation_languages = {
3597 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3598 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3599
774d79cc 3600 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3601 lang_subs = container.setdefault(lang_code, [])
545cc85d 3602 for fmt in self._SUBTITLE_FORMATS:
3603 query.update({
3604 'fmt': fmt,
3605 })
3606 lang_subs.append({
3607 'ext': fmt,
60f393e4 3608 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3609 'name': sub_name,
545cc85d 3610 })
7e72694b 3611
ecdc9049 3612 subtitles, automatic_captions = {}, {}
3613 for lang_code, caption_track in captions.items():
3614 base_url = caption_track.get('baseUrl')
1235d333 3615 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3616 if not base_url:
3617 continue
ecdc9049 3618 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3619 if caption_track.get('kind') != 'asr':
545cc85d 3620 if not lang_code:
3621 continue
3622 process_language(
ecdc9049 3623 subtitles, base_url, lang_code, lang_name, {})
3624 if not caption_track.get('isTranslatable'):
3625 continue
3944e7af 3626 for trans_code, trans_name in translation_languages.items():
3627 if not trans_code:
545cc85d 3628 continue
1235d333 3629 orig_trans_code = trans_code
ecdc9049 3630 if caption_track.get('kind') != 'asr':
18e49408 3631 if 'translated_subs' in self._configuration_arg('skip'):
3632 continue
ecdc9049 3633 trans_code += f'-{lang_code}'
a70635b8 3634 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 3635 # Add an "-orig" label to the original language so that it can be distinguished.
3636 # The subs are returned without "-orig" as well for compatibility
1235d333 3637 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3638 process_language(
d49669ac 3639 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3640 # Setting tlang=lang returns damaged subtitles.
d49669ac 3641 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3642 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
ecdc9049 3643 info['automatic_captions'] = automatic_captions
3644 info['subtitles'] = subtitles
7e72694b 3645
14f25df2 3646 parsed_url = urllib.parse.urlparse(url)
545cc85d 3647 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 3648 query = urllib.parse.parse_qs(component)
545cc85d 3649 for k, v in query.items():
3650 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3651 d_k += '_time'
3652 if d_k not in info and k in s_ks:
3653 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3654
3655 # Youtube Music Auto-generated description
822b9d9c 3656 if video_description:
1890fc63 3657 mobj = re.search(
3658 r'''(?xs)
3659 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3660 (?P<album>[^\n]+)
3661 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3662 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3663 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3664 .+\nAuto-generated\ by\ YouTube\.\s*$
3665 ''', video_description)
822b9d9c 3666 if mobj:
822b9d9c
RA
3667 release_year = mobj.group('release_year')
3668 release_date = mobj.group('release_date')
3669 if release_date:
3670 release_date = release_date.replace('-', '')
3671 if not release_year:
545cc85d 3672 release_year = release_date[:4]
3673 info.update({
3674 'album': mobj.group('album'.strip()),
3675 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3676 'track': mobj.group('track').strip(),
3677 'release_date': release_date,
cc2db878 3678 'release_year': int_or_none(release_year),
545cc85d 3679 })
7e72694b 3680
545cc85d 3681 initial_data = None
3682 if webpage:
56ba69e4 3683 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 3684 if not initial_data:
99e9e001 3685 query = {'videoId': video_id}
3686 query.update(self._get_checkok_params())
109dd3b2 3687 initial_data = self._extract_response(
3688 item_id=video_id, ep='next', fatal=False,
99e9e001 3689 ytcfg=master_ytcfg, query=query,
3690 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3691 note='Downloading initial data API JSON')
545cc85d 3692
0df111a3 3693 info['comment_count'] = traverse_obj(initial_data, (
3694 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3695 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3696 ), (
3697 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3698 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3699 ), expected_type=int_or_none, get_all=False)
3700
19a03940 3701 try: # This will error if there is no livechat
c60ee3a2 3702 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 3703 except (KeyError, IndexError, TypeError):
3704 pass
3705 else:
ecdc9049 3706 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 3707 # url is needed to set cookies
3708 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 3709 'video_id': video_id,
3710 'ext': 'json',
f6745c49 3711 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3712 }]
545cc85d 3713
3714 if initial_data:
7c365c21 3715 info['chapters'] = (
3716 self._extract_chapters_from_json(initial_data, duration)
3717 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 3718 or self._extract_chapters_from_description(video_description, duration)
7c365c21 3719 or None)
545cc85d 3720
17322130 3721 contents = traverse_obj(
3722 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3723 expected_type=list, default=[])
3724
3725 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3726 if vpir:
3727 stl = vpir.get('superTitleLink')
3728 if stl:
3729 stl = self._get_text(stl)
3730 if try_get(
3731 vpir,
3732 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3733 info['location'] = stl
3734 else:
affc4fef 3735 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 3736 if mobj:
545cc85d 3737 info.update({
17322130 3738 'series': mobj.group(1),
3739 'season_number': int(mobj.group(2)),
3740 'episode_number': int(mobj.group(3)),
545cc85d 3741 })
17322130 3742 for tlb in (try_get(
3743 vpir,
3744 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3745 list) or []):
3746 tbr = tlb.get('toggleButtonRenderer') or {}
3747 for getter, regex in [(
3748 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3749 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3750 lambda x: x['accessibility'],
3751 lambda x: x['accessibilityData']['accessibilityData'],
3752 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3753 label = (try_get(tbr, getter, dict) or {}).get('label')
3754 if label:
3755 mobj = re.match(regex, label)
3756 if mobj:
3757 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3758 break
17322130 3759 sbr_tooltip = try_get(
3760 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3761 if sbr_tooltip:
3762 like_count, dislike_count = sbr_tooltip.split(' / ')
3763 info.update({
3764 'like_count': str_to_int(like_count),
3765 'dislike_count': str_to_int(dislike_count),
3766 })
3767 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3768 if vsir:
3769 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3770 info.update({
3771 'channel': self._get_text(vor, 'title'),
3772 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3773
3774 rows = try_get(
3775 vsir,
3776 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3777 list) or []
3778 multiple_songs = False
3779 for row in rows:
3780 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3781 multiple_songs = True
3782 break
3783 for row in rows:
3784 mrr = row.get('metadataRowRenderer') or {}
3785 mrr_title = mrr.get('title')
3786 if not mrr_title:
3787 continue
3788 mrr_title = self._get_text(mrr, 'title')
3789 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3790 if mrr_title == 'License':
3791 info['license'] = mrr_contents_text
3792 elif not multiple_songs:
3793 if mrr_title == 'Album':
3794 info['album'] = mrr_contents_text
3795 elif mrr_title == 'Artist':
3796 info['artist'] = mrr_contents_text
3797 elif mrr_title == 'Song':
3798 info['track'] = mrr_contents_text
545cc85d 3799
3800 fallbacks = {
3801 'channel': 'uploader',
3802 'channel_id': 'uploader_id',
3803 'channel_url': 'uploader_url',
3804 }
992f9a73 3805
17322130 3806 # The upload date for scheduled, live and past live streams / premieres in microformats
3807 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3808 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3809 upload_date = (
3810 unified_strdate(get_first(microformats, 'uploadDate'))
3811 or unified_strdate(search_meta('uploadDate')))
3812 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
6e634cbe 3813 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date
17322130 3814 info['upload_date'] = upload_date
992f9a73 3815
545cc85d 3816 for to, frm in fallbacks.items():
3817 if not info.get(to):
3818 info[to] = info.get(frm)
3819
3820 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3821 v = info.get(s_k)
3822 if v:
3823 info[d_k] = v
b84071c0 3824
11f9be09 3825 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3826 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3827 is_membersonly = None
b28f8d24 3828 is_premium = None
c224251a
M
3829 if initial_data and is_private is not None:
3830 is_membersonly = False
b28f8d24 3831 is_premium = False
47193e02 3832 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3833 badge_labels = set()
3834 for content in contents:
3835 if not isinstance(content, dict):
3836 continue
3837 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3838 for badge_label in badge_labels:
3839 if badge_label.lower() == 'members only':
3840 is_membersonly = True
3841 elif badge_label.lower() == 'premium':
3842 is_premium = True
3843 elif badge_label.lower() == 'unlisted':
3844 is_unlisted = True
c224251a 3845
c224251a
M
3846 info['availability'] = self._availability(
3847 is_private=is_private,
b28f8d24 3848 needs_premium=is_premium,
c224251a
M
3849 needs_subscription=is_membersonly,
3850 needs_auth=info['age_limit'] >= 18,
3851 is_unlisted=None if is_private is None else is_unlisted)
3852
a2160aa4 3853 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3854
11f9be09 3855 self.mark_watched(video_id, player_responses)
d77ab8e2 3856
545cc85d 3857 return info
c5e8d7af 3858
a61fd4cf 3859
a6213a49 3860class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3861
182bda88 3862 @staticmethod
3863 def passthrough_smuggled_data(func):
3864 def _smuggle(entries, smuggled_data):
3865 for entry in entries:
3866 # TODO: Convert URL to music.youtube instead.
3867 # Do we need to passthrough any other smuggled_data?
3868 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3869 yield entry
3870
3871 @functools.wraps(func)
3872 def wrapper(self, url):
3873 url, smuggled_data = unsmuggle_url(url, {})
3874 if self.is_music_url(url):
3875 smuggled_data['is_music_url'] = True
3876 info_dict = func(self, url, smuggled_data)
3877 if smuggled_data and info_dict.get('entries'):
3878 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3879 return info_dict
3880 return wrapper
3881
a6213a49 3882 def _extract_channel_id(self, webpage):
3883 channel_id = self._html_search_meta(
3884 'channelId', webpage, 'channel id', default=None)
3885 if channel_id:
3886 return channel_id
3887 channel_url = self._html_search_meta(
3888 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3889 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3890 'twitter:app:url:googleplay'), webpage, 'channel url')
3891 return self._search_regex(
3892 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3893 channel_url, 'channel id')
15f6397c 3894
8bdd16b4 3895 @staticmethod
cd7c66cf 3896 def _extract_basic_item_renderer(item):
3897 # Modified from _extract_grid_item_renderer
201c1459 3898 known_basic_renderers = (
a17526e4 3899 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 3900 )
3901 for key, renderer in item.items():
201c1459 3902 if not isinstance(renderer, dict):
cd7c66cf 3903 continue
201c1459 3904 elif key in known_basic_renderers:
3905 return renderer
3906 elif key.startswith('grid') and key.endswith('Renderer'):
3907 return renderer
8bdd16b4 3908
8bdd16b4 3909 def _grid_entries(self, grid_renderer):
3910 for item in grid_renderer['items']:
3911 if not isinstance(item, dict):
39b62db1 3912 continue
cd7c66cf 3913 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3914 if not isinstance(renderer, dict):
3915 continue
052e1350 3916 title = self._get_text(renderer, 'title')
fe93e2c4 3917
8bdd16b4 3918 # playlist
3919 playlist_id = renderer.get('playlistId')
3920 if playlist_id:
3921 yield self.url_result(
3922 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3923 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3924 video_title=title)
201c1459 3925 continue
8bdd16b4 3926 # video
3927 video_id = renderer.get('videoId')
3928 if video_id:
3929 yield self._extract_video(renderer)
201c1459 3930 continue
8bdd16b4 3931 # channel
3932 channel_id = renderer.get('channelId')
3933 if channel_id:
8bdd16b4 3934 yield self.url_result(
3935 'https://www.youtube.com/channel/%s' % channel_id,
3936 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3937 continue
3938 # generic endpoint URL support
3939 ep_url = urljoin('https://www.youtube.com/', try_get(
3940 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 3941 str))
201c1459 3942 if ep_url:
3943 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3944 if ie.suitable(ep_url):
3945 yield self.url_result(
3946 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3947 break
8bdd16b4 3948
16aa9ea4 3949 def _music_reponsive_list_entry(self, renderer):
3950 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3951 if video_id:
3952 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3953 ie=YoutubeIE.ie_key(), video_id=video_id)
3954 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3955 if playlist_id:
3956 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3957 if video_id:
3958 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3959 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3960 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3961 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3962 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3963 if browse_id:
3964 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3965 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3966
3d3dddc9 3967 def _shelf_entries_from_content(self, shelf_renderer):
3968 content = shelf_renderer.get('content')
3969 if not isinstance(content, dict):
8bdd16b4 3970 return
cd7c66cf 3971 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3972 if renderer:
3973 # TODO: add support for nested playlists so each shelf is processed
3974 # as separate playlist
3975 # TODO: this includes only first N items
86e5f3ed 3976 yield from self._grid_entries(renderer)
3d3dddc9 3977 renderer = content.get('horizontalListRenderer')
3978 if renderer:
3979 # TODO
3980 pass
8bdd16b4 3981
29f7c58a 3982 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3983 ep = try_get(
3984 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 3985 str)
8bdd16b4 3986 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3987 if shelf_url:
29f7c58a 3988 # Skipping links to another channels, note that checking for
3989 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3990 # will not work
3991 if skip_channels and '/channels?' in shelf_url:
3992 return
052e1350 3993 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 3994 yield self.url_result(shelf_url, video_title=title)
3995 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 3996 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 3997
8bdd16b4 3998 def _playlist_entries(self, video_list_renderer):
3999 for content in video_list_renderer['contents']:
4000 if not isinstance(content, dict):
4001 continue
4002 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4003 if not isinstance(renderer, dict):
4004 continue
4005 video_id = renderer.get('videoId')
4006 if not video_id:
4007 continue
4008 yield self._extract_video(renderer)
07aeced6 4009
3462ffa8 4010 def _rich_entries(self, rich_grid_renderer):
4011 renderer = try_get(
70d5c17b 4012 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 4013 video_id = renderer.get('videoId')
4014 if not video_id:
4015 return
4016 yield self._extract_video(renderer)
4017
8bdd16b4 4018 def _video_entry(self, video_renderer):
4019 video_id = video_renderer.get('videoId')
4020 if video_id:
4021 return self._extract_video(video_renderer)
dacb3a86 4022
ad210f4f 4023 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4024 url = urljoin('https://youtube.com', traverse_obj(
4025 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4026 if url:
4027 return self.url_result(
4028 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4029
8bdd16b4 4030 def _post_thread_entries(self, post_thread_renderer):
4031 post_renderer = try_get(
4032 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4033 if not post_renderer:
4034 return
4035 # video attachment
4036 video_renderer = try_get(
895b0931 4037 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4038 video_id = video_renderer.get('videoId')
4039 if video_id:
4040 entry = self._extract_video(video_renderer)
8bdd16b4 4041 if entry:
4042 yield entry
895b0931 4043 # playlist attachment
4044 playlist_id = try_get(
14f25df2 4045 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4046 if playlist_id:
4047 yield self.url_result(
e28f1c0a 4048 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4049 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4050 # inline video links
4051 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4052 for run in runs:
4053 if not isinstance(run, dict):
4054 continue
4055 ep_url = try_get(
14f25df2 4056 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4057 if not ep_url:
4058 continue
4059 if not YoutubeIE.suitable(ep_url):
4060 continue
4061 ep_video_id = YoutubeIE._match_id(ep_url)
4062 if video_id == ep_video_id:
4063 continue
895b0931 4064 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4065
8bdd16b4 4066 def _post_thread_continuation_entries(self, post_thread_continuation):
4067 contents = post_thread_continuation.get('contents')
4068 if not isinstance(contents, list):
4069 return
4070 for content in contents:
4071 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4072 if isinstance(renderer, dict):
4073 yield from self._post_thread_entries(renderer)
8bdd16b4 4074 continue
6b0b0a28 4075 renderer = content.get('videoRenderer')
4076 if isinstance(renderer, dict):
4077 yield self._video_entry(renderer)
07aeced6 4078
39ed931e 4079 r''' # unused
4080 def _rich_grid_entries(self, contents):
4081 for content in contents:
4082 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4083 if video_renderer:
4084 entry = self._video_entry(video_renderer)
4085 if entry:
4086 yield entry
4087 '''
52efa4b3 4088
a6213a49 4089 def _extract_entries(self, parent_renderer, continuation_list):
4090 # continuation_list is modified in-place with continuation_list = [continuation_token]
4091 continuation_list[:] = [None]
4092 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4093 for content in contents:
4094 if not isinstance(content, dict):
4095 continue
16aa9ea4 4096 is_renderer = traverse_obj(
4097 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4098 expected_type=dict)
a6213a49 4099 if not is_renderer:
4100 renderer = content.get('richItemRenderer')
4101 if renderer:
4102 for entry in self._rich_entries(renderer):
4103 yield entry
4104 continuation_list[0] = self._extract_continuation(parent_renderer)
4105 continue
4106 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4107 for isr_content in isr_contents:
4108 if not isinstance(isr_content, dict):
8bdd16b4 4109 continue
69184e41 4110
a6213a49 4111 known_renderers = {
4112 'playlistVideoListRenderer': self._playlist_entries,
4113 'gridRenderer': self._grid_entries,
a17526e4 4114 'reelShelfRenderer': self._grid_entries,
4115 'shelfRenderer': self._shelf_entries,
16aa9ea4 4116 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4117 'backstagePostThreadRenderer': self._post_thread_entries,
4118 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4119 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4120 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4121 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4122 }
4123 for key, renderer in isr_content.items():
4124 if key not in known_renderers:
4125 continue
4126 for entry in known_renderers[key](renderer):
4127 if entry:
4128 yield entry
4129 continuation_list[0] = self._extract_continuation(renderer)
4130 break
70d5c17b 4131
4132 if not continuation_list[0]:
a6213a49 4133 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4134
a6213a49 4135 if not continuation_list[0]:
4136 continuation_list[0] = self._extract_continuation(parent_renderer)
4137
4138 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4139 continuation_list = [None]
4140 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4141 tab_content = try_get(tab, lambda x: x['content'], dict)
4142 if not tab_content:
4143 return
3462ffa8 4144 parent_renderer = (
29f7c58a 4145 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4146 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4147 yield from extract_entries(parent_renderer)
3462ffa8 4148 continuation = continuation_list[0]
d069eca7 4149
8bdd16b4 4150 for page_num in itertools.count(1):
4151 if not continuation:
4152 break
99e9e001 4153 headers = self.generate_api_headers(
4154 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4155 response = self._extract_response(
86e5f3ed 4156 item_id=f'{item_id} page {page_num}',
fe93e2c4 4157 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4158 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4159
4160 if not response:
8bdd16b4 4161 break
ac56cf38 4162 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4163 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4164 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4165
69184e41 4166 known_continuation_renderers = {
4167 'playlistVideoListContinuation': self._playlist_entries,
4168 'gridContinuation': self._grid_entries,
4169 'itemSectionContinuation': self._post_thread_continuation_entries,
4170 'sectionListContinuation': extract_entries, # for feeds
4171 }
8bdd16b4 4172 continuation_contents = try_get(
69184e41 4173 response, lambda x: x['continuationContents'], dict) or {}
4174 continuation_renderer = None
4175 for key, value in continuation_contents.items():
4176 if key not in known_continuation_renderers:
3462ffa8 4177 continue
69184e41 4178 continuation_renderer = value
4179 continuation_list = [None]
86e5f3ed 4180 yield from known_continuation_renderers[key](continuation_renderer)
69184e41 4181 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4182 break
4183 if continuation_renderer:
4184 continue
c5e8d7af 4185
a1b535bd 4186 known_renderers = {
e4b98809 4187 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4188 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4189 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4190 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4191 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4192 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4193 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4194 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4195 }
cce889b9 4196 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4197 continuation_items = try_get(
cce889b9 4198 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4199 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4200 video_items_renderer = None
4201 for key, value in continuation_item.items():
4202 if key not in known_renderers:
8bdd16b4 4203 continue
a1b535bd 4204 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4205 continuation_list = [None]
86e5f3ed 4206 yield from known_renderers[key][0](video_items_renderer)
9ba5705a 4207 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4208 break
4209 if video_items_renderer:
4210 continue
8bdd16b4 4211 break
9558dcec 4212
8bdd16b4 4213 @staticmethod
7c219ea6 4214 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4215 for tab in tabs:
cd684175 4216 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4217 if renderer.get('selected') is True:
4218 return renderer
2b3c2546 4219 else:
7c219ea6 4220 if fatal:
4221 raise ExtractorError('Unable to find selected tab')
b82f815f 4222
61d3665d 4223 def _extract_uploader(self, data):
8bdd16b4 4224 uploader = {}
61d3665d 4225 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
47193e02 4226 owner = try_get(
4227 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4228 if owner:
61d3665d 4229 owner_text = owner.get('text')
4230 uploader['uploader'] = self._search_regex(
4231 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
47193e02 4232 uploader['uploader_id'] = try_get(
14f25df2 4233 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], str)
47193e02 4234 uploader['uploader_url'] = urljoin(
4235 'https://www.youtube.com/',
14f25df2 4236 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
9c3fe2ef 4237 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4238
ac56cf38 4239 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4240 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4241 tags = []
b60419c5 4242
8bdd16b4 4243 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4244 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4245 renderer = try_get(
4246 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4247 if renderer:
b60419c5 4248 channel_name = renderer.get('title')
4249 channel_url = renderer.get('channelUrl')
4250 channel_id = renderer.get('externalId')
39ed931e 4251 else:
64c0d954 4252 renderer = try_get(
4253 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4254
8bdd16b4 4255 if renderer:
4256 title = renderer.get('title')
ecc97af3 4257 description = renderer.get('description', '')
b60419c5 4258 playlist_id = channel_id
4259 tags = renderer.get('keywords', '').split()
b60419c5 4260
301d07fc 4261 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4262 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4263 def _get_uncropped(url):
4264 return url_or_none((url or '').split('=')[0] + '=s0')
4265
4266 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4267 if avatar_thumbnails:
4268 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4269 if uncropped_avatar:
4270 avatar_thumbnails.append({
4271 'url': uncropped_avatar,
4272 'id': 'avatar_uncropped',
4273 'preference': 1
4274 })
4275
4276 channel_banners = self._extract_thumbnails(
4277 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4278 for banner in channel_banners:
4279 banner['preference'] = -10
4280
4281 if channel_banners:
4282 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4283 if uncropped_banner:
4284 channel_banners.append({
4285 'url': uncropped_banner,
4286 'id': 'banner_uncropped',
4287 'preference': -5
4288 })
4289
4290 primary_thumbnails = self._extract_thumbnails(
a17526e4 4291 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4292
3462ffa8 4293 if playlist_id is None:
70d5c17b 4294 playlist_id = item_id
f0d785d3 4295
4296 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4297 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4298 if title is None:
f0d785d3 4299 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4300 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4301 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4302
b60419c5 4303 metadata = {
4304 'playlist_id': playlist_id,
4305 'playlist_title': title,
4306 'playlist_description': description,
4307 'uploader': channel_name,
4308 'uploader_id': channel_id,
4309 'uploader_url': channel_url,
301d07fc 4310 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4311 'tags': tags,
f0d785d3 4312 'view_count': self._get_count(playlist_stats, 1),
4313 'availability': self._extract_availability(data),
4314 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4315 'playlist_count': self._get_count(playlist_stats, 0),
4316 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4317 }
4318 if not channel_id:
4319 metadata.update(self._extract_uploader(data))
4320 metadata.update({
4321 'channel': metadata['uploader'],
4322 'channel_id': metadata['uploader_id'],
4323 'channel_url': metadata['uploader_url']})
4324 return self.playlist_result(
d069eca7 4325 self._entries(
ac56cf38 4326 selected_tab, playlist_id, ytcfg,
4327 self._extract_account_syncid(ytcfg, data),
4328 self._extract_visitor_data(data, ytcfg)),
b60419c5 4329 **metadata)
73c4ac2c 4330
6e634cbe 4331 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4332 first_id = last_id = response = None
2be71994 4333 for page_num in itertools.count(1):
cd7c66cf 4334 videos = list(self._playlist_entries(playlist))
4335 if not videos:
4336 return
2be71994 4337 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4338 if start >= len(videos):
4339 return
24146491 4340 yield from videos[start:]
2be71994 4341 first_id = first_id or videos[0]['id']
4342 last_id = videos[-1]['id']
79360d99 4343 watch_endpoint = try_get(
4344 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4345 headers = self.generate_api_headers(
4346 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4347 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4348 query = {
4349 'playlistId': playlist_id,
4350 'videoId': watch_endpoint.get('videoId') or last_id,
4351 'index': watch_endpoint.get('index') or len(videos),
4352 'params': watch_endpoint.get('params') or 'OAE%3D'
4353 }
4354 response = self._extract_response(
4355 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4356 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4357 check_get_keys='contents'
4358 )
cd7c66cf 4359 playlist = try_get(
79360d99 4360 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4361
ac56cf38 4362 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4363 title = playlist.get('title') or try_get(
14f25df2 4364 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4365 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4366
4367 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4368 playlist_url = urljoin(url, try_get(
4369 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4370 str))
6e634cbe 4371
4372 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4373 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4374 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4375
4376 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4377 return self.url_result(
4378 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4379 video_title=title)
cd7c66cf 4380
8bdd16b4 4381 return self.playlist_result(
6e634cbe 4382 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4383 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4384
47193e02 4385 def _extract_availability(self, data):
4386 """
4387 Gets the availability of a given playlist/tab.
4388 Note: Unless YouTube tells us explicitly, we do not assume it is public
4389 @param data: response
4390 """
4391 is_private = is_unlisted = None
4392 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4393 badge_labels = self._extract_badges(renderer)
4394
4395 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4396 privacy_dropdown_entries = try_get(
4397 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4398 for renderer_dict in privacy_dropdown_entries:
4399 is_selected = try_get(
4400 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4401 if not is_selected:
4402 continue
052e1350 4403 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4404 if label:
4405 badge_labels.add(label.lower())
4406 break
4407
4408 for badge_label in badge_labels:
4409 if badge_label == 'unlisted':
4410 is_unlisted = True
4411 elif badge_label == 'private':
4412 is_private = True
4413 elif badge_label == 'public':
4414 is_unlisted = is_private = False
4415 return self._availability(is_private, False, False, False, is_unlisted)
4416
4417 @staticmethod
4418 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4419 sidebar_renderer = try_get(
4420 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4421 for item in sidebar_renderer:
4422 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4423 if renderer:
4424 return renderer
4425
ac56cf38 4426 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4427 """
4428 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4429 """
5d342002 4430 browse_id = params = None
47193e02 4431 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4432 if not renderer:
4433 return
4434 menu_renderer = try_get(
4435 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4436 for menu_item in menu_renderer:
4437 if not isinstance(menu_item, dict):
358de58c 4438 continue
47193e02 4439 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4440 text = try_get(
14f25df2 4441 nav_item_renderer, lambda x: x['text']['simpleText'], str)
47193e02 4442 if not text or text.lower() != 'show unavailable videos':
4443 continue
4444 browse_endpoint = try_get(
4445 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4446 browse_id = browse_endpoint.get('browseId')
4447 params = browse_endpoint.get('params')
4448 break
5d342002 4449
11f9be09 4450 headers = self.generate_api_headers(
99e9e001 4451 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4452 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4453 query = {
4454 'params': params or 'wgYCCAA=',
4455 'browseId': browse_id or 'VL%s' % item_id
4456 }
4457 return self._extract_response(
4458 item_id=item_id, headers=headers, query=query,
fe93e2c4 4459 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4460 note='Downloading API JSON with unavailable videos')
358de58c 4461
2762dbb1 4462 @functools.cached_property
a25bca9f 4463 def skip_webpage(self):
4464 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4465
ac56cf38 4466 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4467 retries = self.get_param('extractor_retries', 3)
62bff2c1 4468 count = -1
ac56cf38 4469 webpage = data = last_error = None
14fdfea9 4470 while count < retries:
62bff2c1 4471 count += 1
14fdfea9 4472 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4473 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4474 if last_error:
c705177d 4475 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4476 try:
4477 webpage = self._download_webpage(
4478 url, item_id,
4479 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4480 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4481 except ExtractorError as e:
4482 if isinstance(e.cause, network_exceptions):
14f25df2 4483 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
ac56cf38 4484 last_error = error_to_compat_str(e.cause or e.msg)
4485 if count < retries:
4486 continue
4487 if fatal:
4488 raise
4489 self.report_warning(error_to_compat_str(e))
14fdfea9 4490 break
ac56cf38 4491 else:
4492 try:
4493 self._extract_and_report_alerts(data)
4494 except ExtractorError as e:
4495 if fatal:
4496 raise
4497 self.report_warning(error_to_compat_str(e))
4498 break
4499
7c219ea6 4500 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
ac56cf38 4501 break
4502
4503 last_error = 'Incomplete yt initial data received'
4504 if count >= retries:
4505 if fatal:
4506 raise ExtractorError(last_error)
4507 self.report_warning(last_error)
4508 break
4509
cd7c66cf 4510 return webpage, data
4511
a25bca9f 4512 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4513 """Use if failed to extract ytcfg (and data) from initial webpage"""
4514 if not ytcfg and self.is_authenticated:
4515 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4516 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4517 raise ExtractorError(
4518 f'{msg}. If you are not downloading private content, or '
4519 'your cookies are only for the first account and channel,'
4520 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4521 expected=True)
4522 self.report_warning(msg, only_once=True)
4523
ac56cf38 4524 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4525 data = None
a25bca9f 4526 if not self.skip_webpage:
ac56cf38 4527 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4528 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4529 # Reject webpage data if redirected to home page without explicitly requesting
4530 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4531 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4532 if (url != 'https://www.youtube.com/feed/recommended'
4533 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4534 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4535 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4536 if fatal:
4537 raise ExtractorError(msg, expected=True)
4538 self.report_warning(msg, only_once=True)
ac56cf38 4539 if not data:
a25bca9f 4540 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4541 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4542 return data, ytcfg
4543
4544 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4545 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4546 resolve_response = self._extract_response(
4547 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4548 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4549 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4550 for ep_key, ep in endpoints.items():
4551 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4552 if params:
4553 return self._extract_response(
4554 item_id=item_id, query=params, ep=ep, headers=headers,
4555 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4556 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4557 err_note = 'Failed to resolve url (does the playlist exist?)'
4558 if fatal:
4559 raise ExtractorError(err_note, expected=True)
4560 self.report_warning(err_note, item_id)
4561
a6213a49 4562 _SEARCH_PARAMS = None
4563
af5c1c55 4564 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4565 data = {'query': query}
4566 if params is NO_DEFAULT:
4567 params = self._SEARCH_PARAMS
4568 if params:
4569 data['params'] = params
16aa9ea4 4570
4571 content_keys = (
4572 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4573 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4574 # ytmusic search
4575 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4576 ('continuationContents', ),
4577 )
a25bca9f 4578 display_id = f'query "{query}"'
86e5f3ed 4579 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4580 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4581 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4582
a61fd4cf 4583 continuation_list = [None]
a25bca9f 4584 search = None
a6213a49 4585 for page_num in itertools.count(1):
a61fd4cf 4586 data.update(continuation_list[0] or {})
a25bca9f 4587 headers = self.generate_api_headers(
4588 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4589 search = self._extract_response(
a25bca9f 4590 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4591 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4592 slr_contents = traverse_obj(search, *content_keys)
4593 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4594 if not continuation_list[0]:
a6213a49 4595 break
4596
4597
4598class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4599 IE_DESC = 'YouTube Tabs'
4600 _VALID_URL = r'''(?x:
4601 https?://
4602 (?:\w+\.)?
4603 (?:
4604 youtube(?:kids)?\.com|
4605 %(invidious)s
4606 )/
4607 (?:
4608 (?P<channel_type>channel|c|user|browse)/|
4609 (?P<not_channel>
4610 feed/|hashtag/|
4611 (?:playlist|watch)\?.*?\blist=
4612 )|
4613 (?!(?:%(reserved_names)s)\b) # Direct URLs
4614 )
4615 (?P<id>[^/?\#&]+)
4616 )''' % {
4617 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4618 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4619 }
4620 IE_NAME = 'youtube:tab'
4621
4622 _TESTS = [{
4623 'note': 'playlists, multipage',
4624 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4625 'playlist_mincount': 94,
4626 'info_dict': {
4627 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4628 'title': 'Igor Kleiner - Playlists',
a6213a49 4629 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4630 'uploader': 'Igor Kleiner',
a6213a49 4631 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4632 'channel': 'Igor Kleiner',
4633 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4634 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4635 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4636 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4637 'channel_follower_count': int
a6213a49 4638 },
4639 }, {
4640 'note': 'playlists, multipage, different order',
4641 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4642 'playlist_mincount': 94,
4643 'info_dict': {
4644 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4645 'title': 'Igor Kleiner - Playlists',
a6213a49 4646 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4647 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4648 'uploader': 'Igor Kleiner',
4649 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4650 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4651 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4652 'channel': 'Igor Kleiner',
4653 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4654 'channel_follower_count': int
a6213a49 4655 },
4656 }, {
4657 'note': 'playlists, series',
4658 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4659 'playlist_mincount': 5,
4660 'info_dict': {
4661 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4662 'title': '3Blue1Brown - Playlists',
4663 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4664 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4665 'uploader': '3Blue1Brown',
976ae3ea 4666 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4667 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4668 'channel': '3Blue1Brown',
4669 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4670 'tags': ['Mathematics'],
6c73052c 4671 'channel_follower_count': int
a6213a49 4672 },
4673 }, {
4674 'note': 'playlists, singlepage',
4675 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4676 'playlist_mincount': 4,
4677 'info_dict': {
4678 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4679 'title': 'ThirstForScience - Playlists',
4680 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4681 'uploader': 'ThirstForScience',
4682 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4683 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4684 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4685 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4686 'tags': 'count:13',
4687 'channel': 'ThirstForScience',
6c73052c 4688 'channel_follower_count': int
a6213a49 4689 }
4690 }, {
4691 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4692 'only_matching': True,
4693 }, {
4694 'note': 'basic, single video playlist',
4695 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4696 'info_dict': {
4697 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4698 'uploader': 'Sergey M.',
4699 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4700 'title': 'youtube-dl public playlist',
976ae3ea 4701 'description': '',
4702 'tags': [],
4703 'view_count': int,
4704 'modified_date': '20201130',
4705 'channel': 'Sergey M.',
4706 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4707 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4708 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4709 },
4710 'playlist_count': 1,
4711 }, {
4712 'note': 'empty playlist',
4713 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4714 'info_dict': {
4715 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4716 'uploader': 'Sergey M.',
4717 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4718 'title': 'youtube-dl empty playlist',
976ae3ea 4719 'tags': [],
4720 'channel': 'Sergey M.',
4721 'description': '',
4722 'modified_date': '20160902',
4723 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4724 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4725 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4726 },
4727 'playlist_count': 0,
4728 }, {
4729 'note': 'Home tab',
4730 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4731 'info_dict': {
4732 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4733 'title': 'lex will - Home',
4734 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4735 'uploader': 'lex will',
4736 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4737 'channel': 'lex will',
4738 'tags': ['bible', 'history', 'prophesy'],
4739 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4740 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4741 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4742 'channel_follower_count': int
a6213a49 4743 },
4744 'playlist_mincount': 2,
4745 }, {
4746 'note': 'Videos tab',
4747 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4748 'info_dict': {
4749 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4750 'title': 'lex will - Videos',
4751 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4752 'uploader': 'lex will',
4753 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4754 'tags': ['bible', 'history', 'prophesy'],
4755 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4756 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4757 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4758 'channel': 'lex will',
6c73052c 4759 'channel_follower_count': int
a6213a49 4760 },
4761 'playlist_mincount': 975,
4762 }, {
4763 'note': 'Videos tab, sorted by popular',
4764 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4765 'info_dict': {
4766 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4767 'title': 'lex will - Videos',
4768 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4769 'uploader': 'lex will',
4770 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4771 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4772 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4773 'channel': 'lex will',
4774 'tags': ['bible', 'history', 'prophesy'],
4775 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4776 'channel_follower_count': int
a6213a49 4777 },
4778 'playlist_mincount': 199,
4779 }, {
4780 'note': 'Playlists tab',
4781 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4782 'info_dict': {
4783 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4784 'title': 'lex will - Playlists',
4785 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4786 'uploader': 'lex will',
4787 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4788 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4789 'channel': 'lex will',
4790 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4791 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4792 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4793 'channel_follower_count': int
a6213a49 4794 },
4795 'playlist_mincount': 17,
4796 }, {
4797 'note': 'Community tab',
4798 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4799 'info_dict': {
4800 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4801 'title': 'lex will - Community',
4802 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4803 'uploader': 'lex will',
4804 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4805 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4806 'channel': 'lex will',
4807 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4808 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4809 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4810 'channel_follower_count': int
a6213a49 4811 },
4812 'playlist_mincount': 18,
4813 }, {
4814 'note': 'Channels tab',
4815 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4816 'info_dict': {
4817 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4818 'title': 'lex will - Channels',
4819 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4820 'uploader': 'lex will',
4821 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4822 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4823 'channel': 'lex will',
4824 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4825 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4826 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4827 'channel_follower_count': int
a6213a49 4828 },
4829 'playlist_mincount': 12,
4830 }, {
4831 'note': 'Search tab',
4832 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4833 'playlist_mincount': 40,
4834 'info_dict': {
4835 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4836 'title': '3Blue1Brown - Search - linear algebra',
4837 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4838 'uploader': '3Blue1Brown',
4839 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4840 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4841 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4842 'tags': ['Mathematics'],
4843 'channel': '3Blue1Brown',
4844 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4845 'channel_follower_count': int
a6213a49 4846 },
4847 }, {
4848 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4849 'only_matching': True,
4850 }, {
4851 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4852 'only_matching': True,
4853 }, {
4854 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4855 'only_matching': True,
4856 }, {
4857 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4858 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4859 'info_dict': {
4860 'title': '29C3: Not my department',
4861 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4862 'uploader': 'Christiaan008',
4863 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4864 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4865 'tags': [],
4866 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4867 'view_count': int,
4868 'modified_date': '20150605',
4869 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4870 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4871 'channel': 'Christiaan008',
a6213a49 4872 },
4873 'playlist_count': 96,
4874 }, {
4875 'note': 'Large playlist',
4876 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4877 'info_dict': {
4878 'title': 'Uploads from Cauchemar',
4879 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4880 'uploader': 'Cauchemar',
4881 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4882 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4883 'tags': [],
4884 'modified_date': r're:\d{8}',
4885 'channel': 'Cauchemar',
4886 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4887 'view_count': int,
4888 'description': '',
4889 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4890 },
4891 'playlist_mincount': 1123,
976ae3ea 4892 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4893 }, {
4894 'note': 'even larger playlist, 8832 videos',
4895 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4896 'only_matching': True,
4897 }, {
4898 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4899 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4900 'info_dict': {
4901 'title': 'Uploads from Interstellar Movie',
4902 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4903 'uploader': 'Interstellar Movie',
4904 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4905 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4906 'tags': [],
4907 'view_count': int,
4908 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4909 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4910 'channel': 'Interstellar Movie',
4911 'description': '',
4912 'modified_date': r're:\d{8}',
a6213a49 4913 },
4914 'playlist_mincount': 21,
4915 }, {
4916 'note': 'Playlist with "show unavailable videos" button',
4917 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4918 'info_dict': {
4919 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4920 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4921 'uploader': 'Phim Siêu Nhân Nhật Bản',
4922 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4923 'view_count': int,
4924 'channel': 'Phim Siêu Nhân Nhật Bản',
4925 'tags': [],
4926 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4927 'description': '',
4928 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4929 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4930 'modified_date': r're:\d{8}',
a6213a49 4931 },
4932 'playlist_mincount': 200,
976ae3ea 4933 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4934 }, {
4935 'note': 'Playlist with unavailable videos in page 7',
4936 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4937 'info_dict': {
4938 'title': 'Uploads from BlankTV',
4939 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4940 'uploader': 'BlankTV',
4941 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4942 'channel': 'BlankTV',
4943 'channel_url': 'https://www.youtube.com/c/blanktv',
4944 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4945 'view_count': int,
4946 'tags': [],
4947 'uploader_url': 'https://www.youtube.com/c/blanktv',
4948 'modified_date': r're:\d{8}',
4949 'description': '',
a6213a49 4950 },
4951 'playlist_mincount': 1000,
976ae3ea 4952 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4953 }, {
4954 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4955 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4956 'info_dict': {
4957 'title': 'Data Analysis with Dr Mike Pound',
4958 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4959 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4960 'uploader': 'Computerphile',
4961 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4962 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4963 'tags': [],
4964 'view_count': int,
4965 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4966 'channel_url': 'https://www.youtube.com/user/Computerphile',
4967 'channel': 'Computerphile',
a6213a49 4968 },
4969 'playlist_mincount': 11,
4970 }, {
4971 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4972 'only_matching': True,
4973 }, {
4974 'note': 'Playlist URL that does not actually serve a playlist',
4975 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4976 'info_dict': {
4977 'id': 'FqZTN594JQw',
4978 'ext': 'webm',
4979 'title': "Smiley's People 01 detective, Adventure Series, Action",
4980 'uploader': 'STREEM',
4981 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4982 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4983 'upload_date': '20150526',
4984 'license': 'Standard YouTube License',
4985 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4986 'categories': ['People & Blogs'],
4987 'tags': list,
4988 'view_count': int,
4989 'like_count': int,
a6213a49 4990 },
4991 'params': {
4992 'skip_download': True,
4993 },
4994 'skip': 'This video is not available.',
4995 'add_ie': [YoutubeIE.ie_key()],
4996 }, {
4997 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4998 'only_matching': True,
4999 }, {
5000 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5001 'only_matching': True,
5002 }, {
5003 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5004 'info_dict': {
6c73052c 5005 'id': 'GgL890LIznQ', # This will keep changing
a6213a49 5006 'ext': 'mp4',
976ae3ea 5007 'title': str,
a6213a49 5008 'uploader': 'Sky News',
5009 'uploader_id': 'skynews',
5010 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5011 'upload_date': r're:\d{8}',
976ae3ea 5012 'description': str,
a6213a49 5013 'categories': ['News & Politics'],
5014 'tags': list,
5015 'like_count': int,
6c73052c 5016 'release_timestamp': 1642502819,
976ae3ea 5017 'channel': 'Sky News',
5018 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5019 'age_limit': 0,
5020 'view_count': int,
6c73052c 5021 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 5022 'playable_in_embed': True,
6c73052c 5023 'release_date': '20220118',
976ae3ea 5024 'availability': 'public',
5025 'live_status': 'is_live',
5026 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 5027 'channel_follower_count': int
a6213a49 5028 },
5029 'params': {
5030 'skip_download': True,
5031 },
976ae3ea 5032 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5033 }, {
5034 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5035 'info_dict': {
5036 'id': 'a48o2S1cPoo',
5037 'ext': 'mp4',
5038 'title': 'The Young Turks - Live Main Show',
5039 'uploader': 'The Young Turks',
5040 'uploader_id': 'TheYoungTurks',
5041 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5042 'upload_date': '20150715',
5043 'license': 'Standard YouTube License',
5044 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5045 'categories': ['News & Politics'],
5046 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5047 'like_count': int,
a6213a49 5048 },
5049 'params': {
5050 'skip_download': True,
5051 },
5052 'only_matching': True,
5053 }, {
5054 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5055 'only_matching': True,
5056 }, {
5057 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5058 'only_matching': True,
5059 }, {
5060 'note': 'A channel that is not live. Should raise error',
5061 'url': 'https://www.youtube.com/user/numberphile/live',
5062 'only_matching': True,
5063 }, {
5064 'url': 'https://www.youtube.com/feed/trending',
5065 'only_matching': True,
5066 }, {
5067 'url': 'https://www.youtube.com/feed/library',
5068 'only_matching': True,
5069 }, {
5070 'url': 'https://www.youtube.com/feed/history',
5071 'only_matching': True,
5072 }, {
5073 'url': 'https://www.youtube.com/feed/subscriptions',
5074 'only_matching': True,
5075 }, {
5076 'url': 'https://www.youtube.com/feed/watch_later',
5077 'only_matching': True,
5078 }, {
5079 'note': 'Recommended - redirects to home page.',
5080 'url': 'https://www.youtube.com/feed/recommended',
5081 'only_matching': True,
5082 }, {
5083 'note': 'inline playlist with not always working continuations',
5084 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5085 'only_matching': True,
5086 }, {
5087 'url': 'https://www.youtube.com/course',
5088 'only_matching': True,
5089 }, {
5090 'url': 'https://www.youtube.com/zsecurity',
5091 'only_matching': True,
5092 }, {
5093 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5094 'only_matching': True,
5095 }, {
5096 'url': 'https://www.youtube.com/TheYoungTurks/live',
5097 'only_matching': True,
5098 }, {
5099 'url': 'https://www.youtube.com/hashtag/cctv9',
5100 'info_dict': {
5101 'id': 'cctv9',
5102 'title': '#cctv9',
976ae3ea 5103 'tags': [],
a6213a49 5104 },
5105 'playlist_mincount': 350,
5106 }, {
5107 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5108 'only_matching': True,
5109 }, {
5110 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5111 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5112 'only_matching': True
5113 }, {
5114 'note': '/browse/ should redirect to /channel/',
5115 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5116 'only_matching': True
5117 }, {
5118 'note': 'VLPL, should redirect to playlist?list=PL...',
5119 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5120 'info_dict': {
5121 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5122 'uploader': 'NoCopyrightSounds',
5123 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5124 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5125 'title': 'NCS Releases',
976ae3ea 5126 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5127 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5128 'modified_date': r're:\d{8}',
5129 'view_count': int,
5130 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5131 'tags': [],
5132 'channel': 'NoCopyrightSounds',
a6213a49 5133 },
5134 'playlist_mincount': 166,
976ae3ea 5135 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5136 }, {
5137 'note': 'Topic, should redirect to playlist?list=UU...',
5138 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5139 'info_dict': {
5140 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5141 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5142 'title': 'Uploads from Royalty Free Music - Topic',
5143 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5144 'tags': [],
5145 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5146 'channel': 'Royalty Free Music - Topic',
5147 'view_count': int,
5148 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5149 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5150 'modified_date': r're:\d{8}',
5151 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5152 'description': '',
a6213a49 5153 },
5154 'expected_warnings': [
a6213a49 5155 'The URL does not have a videos tab',
976ae3ea 5156 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5157 ],
5158 'playlist_mincount': 101,
5159 }, {
5160 'note': 'Topic without a UU playlist',
5161 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5162 'info_dict': {
5163 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5164 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5165 'tags': [],
a6213a49 5166 },
5167 'expected_warnings': [
976ae3ea 5168 'the playlist redirect gave error',
a6213a49 5169 ],
5170 'playlist_mincount': 9,
5171 }, {
5172 'note': 'Youtube music Album',
5173 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5174 'info_dict': {
5175 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5176 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5177 'tags': [],
5178 'view_count': int,
5179 'description': '',
5180 'availability': 'unlisted',
5181 'modified_date': r're:\d{8}',
a6213a49 5182 },
5183 'playlist_count': 50,
5184 }, {
5185 'note': 'unlisted single video playlist',
5186 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5187 'info_dict': {
5188 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5189 'uploader': 'colethedj',
5190 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5191 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5192 'availability': 'unlisted',
5193 'tags': [],
5194 'modified_date': '20211208',
5195 'channel': 'colethedj',
5196 'view_count': int,
5197 'description': '',
5198 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5199 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5200 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5201 },
5202 'playlist_count': 1,
5203 }, {
5204 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5205 'url': 'https://www.youtube.com/feed/recommended',
5206 'info_dict': {
5207 'id': 'recommended',
5208 'title': 'recommended',
6c73052c 5209 'tags': [],
a6213a49 5210 },
5211 'playlist_mincount': 50,
5212 'params': {
5213 'skip_download': True,
5214 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5215 },
5216 }, {
5217 'note': 'API Fallback: /videos tab, sorted by oldest first',
5218 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5219 'info_dict': {
5220 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5221 'title': 'Cody\'sLab - Videos',
5222 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5223 'uploader': 'Cody\'sLab',
5224 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5225 'channel': 'Cody\'sLab',
5226 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5227 'tags': [],
5228 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5229 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5230 'channel_follower_count': int
a6213a49 5231 },
5232 'playlist_mincount': 650,
5233 'params': {
5234 'skip_download': True,
5235 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5236 },
5237 }, {
5238 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5239 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5240 'info_dict': {
5241 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5242 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5243 'title': 'Uploads from Royalty Free Music - Topic',
5244 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5245 'modified_date': r're:\d{8}',
5246 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5247 'description': '',
5248 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5249 'tags': [],
5250 'channel': 'Royalty Free Music - Topic',
5251 'view_count': int,
5252 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5253 },
5254 'expected_warnings': [
976ae3ea 5255 'does not have a videos tab',
5256 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5257 ],
5258 'playlist_mincount': 101,
5259 'params': {
5260 'skip_download': True,
5261 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5262 },
7c219ea6 5263 }, {
5264 'note': 'non-standard redirect to regional channel',
5265 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5266 'only_matching': True
61d3665d 5267 }, {
5268 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5269 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5270 'info_dict': {
5271 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5272 'modified_date': '20220407',
5273 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5274 'tags': [],
5275 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5276 'uploader': 'pukkandan',
5277 'availability': 'unlisted',
5278 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5279 'channel': 'pukkandan',
5280 'description': 'Test for collaborative playlist',
5281 'title': 'yt-dlp test - collaborative playlist',
5282 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5283 },
5284 'playlist_mincount': 2
a6213a49 5285 }]
5286
5287 @classmethod
5288 def suitable(cls, url):
86e5f3ed 5289 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5290
64f36541 5291 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5292
182bda88 5293 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5294 def _real_extract(self, url, smuggled_data):
cd7c66cf 5295 item_id = self._match_id(url)
14f25df2 5296 url = urllib.parse.urlunparse(
5297 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5298 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5299
fe03a6cd 5300 def get_mobj(url):
37e57a9f 5301 mobj = self._URL_RE.match(url).groupdict()
07cce701 5302 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5303 return mobj
5304
37e57a9f 5305 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5306 # Youtube returns incomplete data if tabname is not lower case
5307 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5308 if is_channel:
5309 if smuggled_data.get('is_music_url'):
37e57a9f 5310 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5311 item_id = item_id[2:]
37e57a9f 5312 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5313 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5314 mdata = self._extract_tab_endpoint(
37e57a9f 5315 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5316 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
14f25df2 5317 get_all=False, expected_type=str)
ac56cf38 5318 if not murl:
37e57a9f 5319 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5320 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5321 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5322 pre = f'https://www.youtube.com/channel/{item_id}'
5323
64f36541 5324 original_tab_name = tab
fe03a6cd 5325 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5326 # Home URLs should redirect to /videos/
37e57a9f 5327 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5328 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5329 tab = '/videos'
5330
5331 url = ''.join((pre, tab, post))
5332 mobj = get_mobj(url)
cd7c66cf 5333
5334 # Handle both video/playlist URLs
201c1459 5335 qs = parse_qs(url)
86e5f3ed 5336 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5337
fe03a6cd 5338 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5339 if not playlist_id:
fe03a6cd 5340 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5341 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5342 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5343 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5344 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5345 mobj = get_mobj(url)
cd7c66cf 5346
5347 if video_id and playlist_id:
a06916d9 5348 if self.get_param('noplaylist'):
37e57a9f 5349 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5350 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5351 ie=YoutubeIE.ie_key(), video_id=video_id)
5352 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5353
ac56cf38 5354 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5355
7c219ea6 5356 # YouTube may provide a non-standard redirect to the regional channel
5357 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5358 redirect_url = traverse_obj(
5359 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5360 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5361 redirect_url = ''.join((
5362 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5363 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5364 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5365
37e57a9f 5366 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5367 if tabs:
5368 selected_tab = self._extract_selected_tab(tabs)
64f36541 5369 selected_tab_name = selected_tab.get('title', '').lower()
5370 if selected_tab_name == 'home':
5371 selected_tab_name = 'featured'
5372 requested_tab_name = mobj['tab'][1:]
09f1580e 5373 if 'no-youtube-channel-redirect' not in compat_opts:
64f36541 5374 if requested_tab_name == 'live':
09f1580e 5375 # Live tab should have redirected to the video
5376 raise ExtractorError('The channel is not currently live', expected=True)
64f36541 5377 if requested_tab_name not in ('', selected_tab_name):
5378 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5379 if not original_tab_name:
5380 if item_id[:2] == 'UC':
5381 # Topic channels don't have /videos. Use the equivalent playlist instead
5382 pl_id = f'UU{item_id[2:]}'
5383 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5384 try:
5385 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5386 except ExtractorError:
5387 redirect_warning += ' and the playlist redirect gave error'
5388 else:
5389 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5390 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5391 if selected_tab_name and selected_tab_name != requested_tab_name:
5392 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5393 else:
5394 raise ExtractorError(redirect_warning, expected=True)
18db7548 5395
37e57a9f 5396 if redirect_warning:
64f36541 5397 self.to_screen(redirect_warning)
37e57a9f 5398 self.write_debug(f'Final URL: {url}')
18db7548 5399
358de58c 5400 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5401 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5402 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5403 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5404 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5405 if tabs:
ac56cf38 5406 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5407
37e57a9f 5408 playlist = traverse_obj(
5409 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5410 if playlist:
ac56cf38 5411 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5412
37e57a9f 5413 video_id = traverse_obj(
5414 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5415 if video_id:
09f1580e 5416 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5417 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5418 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5419 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5420
8bdd16b4 5421 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5422
c5e8d7af 5423
8bdd16b4 5424class YoutubePlaylistIE(InfoExtractor):
96565c7e 5425 IE_DESC = 'YouTube playlists'
8bdd16b4 5426 _VALID_URL = r'''(?x)(?:
5427 (?:https?://)?
5428 (?:\w+\.)?
5429 (?:
5430 (?:
5431 youtube(?:kids)?\.com|
d9190e44 5432 %(invidious)s
8bdd16b4 5433 )
5434 /.*?\?.*?\blist=
5435 )?
5436 (?P<id>%(playlist_id)s)
d9190e44
RH
5437 )''' % {
5438 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5439 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5440 }
8bdd16b4 5441 IE_NAME = 'youtube:playlist'
cdc628a4 5442 _TESTS = [{
8bdd16b4 5443 'note': 'issue #673',
5444 'url': 'PLBB231211A4F62143',
cdc628a4 5445 'info_dict': {
8bdd16b4 5446 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5447 'id': 'PLBB231211A4F62143',
976ae3ea 5448 'uploader': 'Wickman',
8bdd16b4 5449 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5450 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5451 'view_count': int,
5452 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5453 'modified_date': r're:\d{8}',
5454 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5455 'channel': 'Wickman',
5456 'tags': [],
5457 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5458 },
5459 'playlist_mincount': 29,
5460 }, {
5461 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5462 'info_dict': {
5463 'title': 'YDL_safe_search',
5464 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5465 },
5466 'playlist_count': 2,
5467 'skip': 'This playlist is private',
9558dcec 5468 }, {
8bdd16b4 5469 'note': 'embedded',
5470 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5471 'playlist_count': 4,
9558dcec 5472 'info_dict': {
8bdd16b4 5473 'title': 'JODA15',
5474 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5475 'uploader': 'milan',
5476 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5477 'description': '',
5478 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5479 'tags': [],
5480 'modified_date': '20140919',
5481 'view_count': int,
5482 'channel': 'milan',
5483 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5484 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5485 },
5486 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5487 }, {
8bdd16b4 5488 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 5489 'playlist_mincount': 654,
8bdd16b4 5490 'info_dict': {
5491 'title': '2018 Chinese New Singles (11/6 updated)',
5492 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5493 'uploader': 'LBK',
5494 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5495 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5496 'channel': 'LBK',
5497 'view_count': int,
5498 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5499 'tags': [],
5500 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5501 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5502 'modified_date': r're:\d{8}',
5503 },
5504 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5505 }, {
29f7c58a 5506 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5507 'only_matching': True,
5508 }, {
5509 # music album playlist
5510 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5511 'only_matching': True,
5512 }]
5513
5514 @classmethod
5515 def suitable(cls, url):
201c1459 5516 if YoutubeTabIE.suitable(url):
5517 return False
49a57e70 5518 from ..utils import parse_qs
201c1459 5519 qs = parse_qs(url)
5520 if qs.get('v', [None])[0]:
5521 return False
86e5f3ed 5522 return super().suitable(url)
29f7c58a 5523
5524 def _real_extract(self, url):
5525 playlist_id = self._match_id(url)
46953e7e 5526 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5527 url = update_url_query(
5528 'https://www.youtube.com/playlist',
5529 parse_qs(url) or {'list': playlist_id})
5530 if is_music_url:
5531 url = smuggle_url(url, {'is_music_url': True})
5532 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5533
5534
5535class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5536 IE_DESC = 'youtu.be'
29f7c58a 5537 _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}
5538 _TESTS = [{
8bdd16b4 5539 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5540 'info_dict': {
5541 'id': 'yeWKywCrFtk',
5542 'ext': 'mp4',
5543 'title': 'Small Scale Baler and Braiding Rugs',
5544 'uploader': 'Backus-Page House Museum',
5545 'uploader_id': 'backuspagemuseum',
5546 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5547 'upload_date': '20161008',
5548 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5549 'categories': ['Nonprofits & Activism'],
5550 'tags': list,
5551 'like_count': int,
976ae3ea 5552 'age_limit': 0,
5553 'playable_in_embed': True,
5554 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5555 'channel': 'Backus-Page House Museum',
5556 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5557 'live_status': 'not_live',
5558 'view_count': int,
5559 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5560 'availability': 'public',
5561 'duration': 59,
8bdd16b4 5562 },
5563 'params': {
5564 'noplaylist': True,
5565 'skip_download': True,
5566 },
39e7107d 5567 }, {
8bdd16b4 5568 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5569 'only_matching': True,
cdc628a4
PH
5570 }]
5571
8bdd16b4 5572 def _real_extract(self, url):
5ad28e7f 5573 mobj = self._match_valid_url(url)
29f7c58a 5574 video_id = mobj.group('id')
5575 playlist_id = mobj.group('playlist_id')
8bdd16b4 5576 return self.url_result(
29f7c58a 5577 update_url_query('https://www.youtube.com/watch', {
5578 'v': video_id,
5579 'list': playlist_id,
5580 'feature': 'youtu.be',
5581 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5582
5583
b6ce9bb0 5584class YoutubeLivestreamEmbedIE(InfoExtractor):
5585 IE_DESC = 'YouTube livestream embeds'
5586 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5587 _TESTS = [{
5588 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5589 'only_matching': True,
5590 }]
5591
5592 def _real_extract(self, url):
5593 channel_id = self._match_id(url)
5594 return self.url_result(
5595 f'https://www.youtube.com/channel/{channel_id}/live',
5596 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5597
5598
8bdd16b4 5599class YoutubeYtUserIE(InfoExtractor):
96565c7e 5600 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5601 IE_NAME = 'youtube:user'
8bdd16b4 5602 _VALID_URL = r'ytuser:(?P<id>.+)'
5603 _TESTS = [{
5604 'url': 'ytuser:phihag',
5605 'only_matching': True,
5606 }]
5607
5608 def _real_extract(self, url):
5609 user_id = self._match_id(url)
5610 return self.url_result(
c586f9e8 5611 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5612 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5613
b05654f0 5614
3d3dddc9 5615class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5616 IE_NAME = 'youtube:favorites'
96565c7e 5617 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5618 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5619 _LOGIN_REQUIRED = True
5620 _TESTS = [{
5621 'url': ':ytfav',
5622 'only_matching': True,
5623 }, {
5624 'url': ':ytfavorites',
5625 'only_matching': True,
5626 }]
5627
5628 def _real_extract(self, url):
5629 return self.url_result(
5630 'https://www.youtube.com/playlist?list=LL',
5631 ie=YoutubeTabIE.ie_key())
5632
5633
ca5300c7 5634class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
5635 IE_NAME = 'youtube:notif'
5636 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5637 _VALID_URL = r':ytnotif(?:ication)?s?'
5638 _LOGIN_REQUIRED = True
5639 _TESTS = [{
5640 'url': ':ytnotif',
5641 'only_matching': True,
5642 }, {
5643 'url': ':ytnotifications',
5644 'only_matching': True,
5645 }]
5646
5647 def _extract_notification_menu(self, response, continuation_list):
5648 notification_list = traverse_obj(
5649 response,
5650 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5651 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5652 expected_type=list) or []
5653 continuation_list[0] = None
5654 for item in notification_list:
5655 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
5656 if entry:
5657 yield entry
5658 continuation = item.get('continuationItemRenderer')
5659 if continuation:
5660 continuation_list[0] = continuation
5661
5662 def _extract_notification_renderer(self, notification):
5663 video_id = traverse_obj(
5664 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
5665 url = f'https://www.youtube.com/watch?v={video_id}'
5666 channel_id = None
5667 if not video_id:
5668 browse_ep = traverse_obj(
5669 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
5670 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
5671 post_id = self._search_regex(
5672 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
5673 'post id', default=None)
5674 if not channel_id or not post_id:
5675 return
5676 # The direct /post url redirects to this in the browser
5677 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5678
5679 channel = traverse_obj(
5680 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5681 expected_type=str)
c7a7baaa 5682 notification_title = self._get_text(notification, 'shortMessage')
5683 if notification_title:
5684 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
5685 # TODO: handle recommended videos
ca5300c7 5686 title = self._search_regex(
c7a7baaa 5687 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 5688 'video title', default=None)
ca5300c7 5689 upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d')
5690 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
5691 else None)
5692 return {
5693 '_type': 'url',
5694 'url': url,
5695 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
5696 'video_id': video_id,
5697 'title': title,
5698 'channel_id': channel_id,
5699 'channel': channel,
5700 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5701 'upload_date': upload_date,
5702 }
5703
5704 def _notification_menu_entries(self, ytcfg):
5705 continuation_list = [None]
5706 response = None
5707 for page in itertools.count(1):
5708 ctoken = traverse_obj(
5709 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
5710 response = self._extract_response(
5711 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
5712 ep='notification/get_notification_menu', check_get_keys='actions',
5713 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
5714 yield from self._extract_notification_menu(response, continuation_list)
5715 if not continuation_list[0]:
5716 break
5717
5718 def _real_extract(self, url):
5719 display_id = 'notifications'
5720 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
5721 self._report_playlist_authcheck(ytcfg)
5722 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
5723
5724
a6213a49 5725class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5726 IE_DESC = 'YouTube search'
78caa52a 5727 IE_NAME = 'youtube:search'
b05654f0 5728 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5729 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5730 _TESTS = [{
5731 'url': 'ytsearch5:youtube-dl test video',
5732 'playlist_count': 5,
5733 'info_dict': {
5734 'id': 'youtube-dl test video',
5735 'title': 'youtube-dl test video',
5736 }
5737 }]
b05654f0 5738
a61fd4cf 5739
5f7cb91a 5740class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5741 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5742 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5743 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5744 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5745 _TESTS = [{
5746 'url': 'ytsearchdate5:youtube-dl test video',
5747 'playlist_count': 5,
5748 'info_dict': {
5749 'id': 'youtube-dl test video',
5750 'title': 'youtube-dl test video',
5751 }
5752 }]
75dff0ee 5753
c9ae7b95 5754
a6213a49 5755class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5756 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5757 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5758 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5759 _TESTS = [{
5760 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5761 'playlist_mincount': 5,
5762 'info_dict': {
11f9be09 5763 'id': 'youtube-dl test video',
3462ffa8 5764 'title': 'youtube-dl test video',
5765 }
a61fd4cf 5766 }, {
5767 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5768 'playlist_mincount': 5,
5769 'info_dict': {
5770 'id': 'python',
5771 'title': 'python',
5772 }
ad210f4f 5773 }, {
5774 'url': 'https://www.youtube.com/results?search_query=%23cats',
5775 'playlist_mincount': 1,
5776 'info_dict': {
5777 'id': '#cats',
5778 'title': '#cats',
5779 'entries': [{
5780 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5781 'title': '#cats',
5782 }],
5783 },
3462ffa8 5784 }, {
5785 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5786 'only_matching': True,
5787 }]
5788
5789 def _real_extract(self, url):
4dfbf869 5790 qs = parse_qs(url)
386e1dd9 5791 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5792 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5793
5794
16aa9ea4 5795class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
455a15e2 5796 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
16aa9ea4 5797 IE_NAME = 'youtube:music:search_url'
5798 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5799 _TESTS = [{
5800 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5801 'playlist_count': 16,
5802 'info_dict': {
5803 'id': 'royalty free music',
5804 'title': 'royalty free music',
5805 }
5806 }, {
5807 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5808 'playlist_mincount': 30,
5809 'info_dict': {
5810 'id': 'royalty free music - songs',
5811 'title': 'royalty free music - songs',
5812 },
5813 'params': {'extract_flat': 'in_playlist'}
5814 }, {
5815 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5816 'playlist_mincount': 30,
5817 'info_dict': {
5818 'id': 'royalty free music - community playlists',
5819 'title': 'royalty free music - community playlists',
5820 },
5821 'params': {'extract_flat': 'in_playlist'}
5822 }]
5823
5824 _SECTIONS = {
5825 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5826 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5827 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5828 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5829 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5830 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5831 }
5832
5833 def _real_extract(self, url):
5834 qs = parse_qs(url)
5835 query = (qs.get('search_query') or qs.get('q'))[0]
5836 params = qs.get('sp', (None,))[0]
5837 if params:
5838 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5839 else:
ac668111 5840 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 5841 params = self._SECTIONS.get(section)
5842 if not params:
5843 section = None
5844 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5845 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5846
5847
182bda88 5848class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5849 """
25f14e9f 5850 Base class for feed extractors
82d02080 5851 Subclasses must re-define the _FEED_NAME property.
d7ae0639 5852 """
b2e8bc1b 5853 _LOGIN_REQUIRED = True
82d02080 5854 _FEED_NAME = 'feeds'
a25bca9f 5855
5856 def _real_initialize(self):
5857 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 5858
82d02080 5859 @classproperty
d7ae0639 5860 def IE_NAME(self):
82d02080 5861 return f'youtube:{self._FEED_NAME}'
04cc9617 5862
3853309f 5863 def _real_extract(self, url):
3d3dddc9 5864 return self.url_result(
182bda88 5865 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5866
5867
ef2f3c7f 5868class YoutubeWatchLaterIE(InfoExtractor):
5869 IE_NAME = 'youtube:watchlater'
96565c7e 5870 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5871 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5872 _TESTS = [{
8bdd16b4 5873 'url': ':ytwatchlater',
bc7a9cd8
S
5874 'only_matching': True,
5875 }]
25f14e9f
S
5876
5877 def _real_extract(self, url):
ef2f3c7f 5878 return self.url_result(
5879 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5880
5881
25f14e9f 5882class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5883 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5884 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5885 _FEED_NAME = 'recommended'
45db527f 5886 _LOGIN_REQUIRED = False
3d3dddc9 5887 _TESTS = [{
5888 'url': ':ytrec',
5889 'only_matching': True,
5890 }, {
5891 'url': ':ytrecommended',
5892 'only_matching': True,
5893 }, {
5894 'url': 'https://youtube.com',
5895 'only_matching': True,
5896 }]
1ed5b5c9 5897
1ed5b5c9 5898
25f14e9f 5899class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5900 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5901 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5902 _FEED_NAME = 'subscriptions'
3d3dddc9 5903 _TESTS = [{
5904 'url': ':ytsubs',
5905 'only_matching': True,
5906 }, {
5907 'url': ':ytsubscriptions',
5908 'only_matching': True,
5909 }]
1ed5b5c9 5910
1ed5b5c9 5911
25f14e9f 5912class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5913 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5914 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5915 _FEED_NAME = 'history'
3d3dddc9 5916 _TESTS = [{
5917 'url': ':ythistory',
5918 'only_matching': True,
5919 }]
1ed5b5c9
JMF
5920
5921
6e634cbe 5922class YoutubeStoriesIE(InfoExtractor):
5923 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
5924 IE_NAME = 'youtube:stories'
5925 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
5926 _TESTS = [{
5927 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
5928 'only_matching': True,
5929 }]
5930
5931 def _real_extract(self, url):
5932 playlist_id = f'RLTD{self._match_id(url)}'
5933 return self.url_result(
5934 f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
5935 ie=YoutubeTabIE, video_id=playlist_id)
5936
5937
15870e90
PH
5938class YoutubeTruncatedURLIE(InfoExtractor):
5939 IE_NAME = 'youtube:truncated_url'
5940 IE_DESC = False # Do not list
975d35db 5941 _VALID_URL = r'''(?x)
b95aab84
PH
5942 (?:https?://)?
5943 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5944 (?:watch\?(?:
c4808c60 5945 feature=[a-z_]+|
b95aab84
PH
5946 annotation_id=annotation_[^&]+|
5947 x-yt-cl=[0-9]+|
c1708b89 5948 hl=[^&]*|
287be8c6 5949 t=[0-9]+
b95aab84
PH
5950 )?
5951 |
5952 attribution_link\?a=[^&]+
5953 )
5954 $
975d35db 5955 '''
15870e90 5956
c4808c60 5957 _TESTS = [{
2d3d2997 5958 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5959 'only_matching': True,
dc2fc736 5960 }, {
2d3d2997 5961 'url': 'https://www.youtube.com/watch?',
dc2fc736 5962 'only_matching': True,
b95aab84
PH
5963 }, {
5964 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5965 'only_matching': True,
5966 }, {
5967 'url': 'https://www.youtube.com/watch?feature=foo',
5968 'only_matching': True,
c1708b89
PH
5969 }, {
5970 'url': 'https://www.youtube.com/watch?hl=en-GB',
5971 'only_matching': True,
287be8c6
PH
5972 }, {
5973 'url': 'https://www.youtube.com/watch?t=2372',
5974 'only_matching': True,
c4808c60
PH
5975 }]
5976
15870e90
PH
5977 def _real_extract(self, url):
5978 raise ExtractorError(
78caa52a
PH
5979 'Did you forget to quote the URL? Remember that & is a meta '
5980 'character in most shells, so you want to put the URL in quotes, '
3867038a 5981 'like youtube-dl '
2d3d2997 5982 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 5983 ' or simply youtube-dl BaW_jenozKc .',
15870e90 5984 expected=True)
772fd5cc
PH
5985
5986
471d0367 5987class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 5988 IE_NAME = 'youtube:clip'
471d0367 5989 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
5990 _TESTS = [{
5991 # FIXME: Other metadata should be extracted from the clip, not from the base video
5992 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
5993 'info_dict': {
5994 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
5995 'ext': 'mp4',
5996 'section_start': 29.0,
5997 'section_end': 39.7,
5998 'duration': 10.7,
5999 }
6000 }]
3cd786db 6001
6002 def _real_extract(self, url):
471d0367 6003 clip_id = self._match_id(url)
6004 _, data = self._extract_webpage(url, clip_id)
6005
6006 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6007 if not video_id:
6008 raise ExtractorError('Unable to find video ID')
6009
6010 clip_data = traverse_obj(data, (
6011 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6012 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6013 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6014 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6015
6016 return {
6017 '_type': 'url_transparent',
6018 'url': f'https://www.youtube.com/watch?v={video_id}',
6019 'ie_key': YoutubeIE.ie_key(),
6020 'id': clip_id,
6021 'section_start': int(clip_data['startTimeMs']) / 1000,
6022 'section_end': int(clip_data['endTimeMs']) / 1000,
6023 }
3cd786db 6024
6025
772fd5cc
PH
6026class YoutubeTruncatedIDIE(InfoExtractor):
6027 IE_NAME = 'youtube:truncated_id'
6028 IE_DESC = False # Do not list
b95aab84 6029 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6030
6031 _TESTS = [{
6032 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6033 'only_matching': True,
6034 }]
6035
6036 def _real_extract(self, url):
6037 video_id = self._match_id(url)
6038 raise ExtractorError(
86e5f3ed 6039 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6040 expected=True)