]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[cleanup] Consistent style for file heads
[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
ac668111 16import urllib.parse
c5e8d7af 17
b05654f0 18from .common import InfoExtractor, SearchInfoExtractor
1890fc63 19from ..compat import functools # isort: split
4bb4a188 20from ..compat import (
29f7c58a 21 compat_HTTPError,
c5e8d7af 22 compat_parse_qs,
545cc85d 23 compat_str,
15707c7e 24 compat_urllib_parse_urlencode,
7c80519c 25 compat_urllib_parse_urlparse,
7c61bd36 26 compat_urlparse,
4bb4a188 27)
545cc85d 28from ..jsinterp import JSInterpreter
4bb4a188 29from ..utils import (
f8271158 30 NO_DEFAULT,
31 ExtractorError,
720c3099 32 bug_reports_message,
82d02080 33 classproperty,
c5e8d7af 34 clean_html,
d92f5d5a 35 datetime_from_str,
11f9be09 36 dict_get,
358de58c 37 error_to_compat_str,
2d30521a 38 float_or_none,
11f9be09 39 format_field,
ff91cf74 40 get_first,
dd27fd17 41 int_or_none,
641ad5d8 42 is_html,
34921b43 43 join_nonempty,
48416bc4 44 js_to_json,
94278f72 45 mimetype2ext,
9c0d7f49 46 network_exceptions,
11f9be09 47 orderedSet,
6310acf5 48 parse_codecs,
49bd8c66 49 parse_count,
7c80519c 50 parse_duration,
7ea65411 51 parse_iso8601,
4dfbf869 52 parse_qs,
dca3ff4a 53 qualities,
c0ac49bc 54 remove_end,
3995d37d 55 remove_start,
cf7e015f 56 smuggle_url,
dbdaaa23 57 str_or_none,
c93d53f5 58 str_to_int,
f3aa3c3f 59 strftime_or_none,
7c365c21 60 traverse_obj,
556dbe7f 61 try_get,
c5e8d7af
PH
62 unescapeHTML,
63 unified_strdate,
f0d785d3 64 unified_timestamp,
cf7e015f 65 unsmuggle_url,
8bdd16b4 66 update_url_query,
21c340b8 67 url_or_none,
fe93e2c4 68 urljoin,
7c365c21 69 variadic,
c5e8d7af
PH
70)
71
000c15a4 72# any clients starting with _ cannot be explicity requested by the user
73INNERTUBE_CLIENTS = {
74 'web': {
75 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
76 'INNERTUBE_CONTEXT': {
77 'client': {
78 'clientName': 'WEB',
18c7683d 79 'clientVersion': '2.20211221.00.00',
000c15a4 80 }
81 },
82 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
83 },
84 'web_embedded': {
85 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
86 'INNERTUBE_CONTEXT': {
87 'client': {
88 'clientName': 'WEB_EMBEDDED_PLAYER',
18c7683d 89 'clientVersion': '1.20211215.00.01',
000c15a4 90 },
91 },
92 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
93 },
94 'web_music': {
95 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
96 'INNERTUBE_HOST': 'music.youtube.com',
97 'INNERTUBE_CONTEXT': {
98 'client': {
99 'clientName': 'WEB_REMIX',
18c7683d 100 'clientVersion': '1.20211213.00.00',
000c15a4 101 }
102 },
103 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
104 },
e7e94f2a 105 'web_creator': {
18c7683d 106 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
107 'INNERTUBE_CONTEXT': {
108 'client': {
109 'clientName': 'WEB_CREATOR',
18c7683d 110 'clientVersion': '1.20211220.02.00',
e7e94f2a
D
111 }
112 },
113 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
114 },
000c15a4 115 'android': {
18c7683d 116 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 117 'INNERTUBE_CONTEXT': {
118 'client': {
119 'clientName': 'ANDROID',
18c7683d 120 'clientVersion': '16.49',
000c15a4 121 }
122 },
123 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 124 'REQUIRE_JS_PLAYER': False
000c15a4 125 },
126 'android_embedded': {
18c7683d 127 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 128 'INNERTUBE_CONTEXT': {
129 'client': {
130 'clientName': 'ANDROID_EMBEDDED_PLAYER',
18c7683d 131 'clientVersion': '16.49',
000c15a4 132 },
133 },
b6de707d 134 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
135 'REQUIRE_JS_PLAYER': False
000c15a4 136 },
137 'android_music': {
18c7683d 138 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 139 'INNERTUBE_CONTEXT': {
140 'client': {
141 'clientName': 'ANDROID_MUSIC',
18c7683d 142 'clientVersion': '4.57',
000c15a4 143 }
144 },
145 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 146 'REQUIRE_JS_PLAYER': False
000c15a4 147 },
e7e94f2a 148 'android_creator': {
18c7683d 149 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
150 'INNERTUBE_CONTEXT': {
151 'client': {
152 'clientName': 'ANDROID_CREATOR',
18c7683d 153 'clientVersion': '21.47',
e7e94f2a
D
154 },
155 },
b6de707d 156 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
157 'REQUIRE_JS_PLAYER': False
e7e94f2a 158 },
18c7683d 159 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
160 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 161 'ios': {
18c7683d 162 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 163 'INNERTUBE_CONTEXT': {
164 'client': {
165 'clientName': 'IOS',
18c7683d 166 'clientVersion': '16.46',
167 'deviceModel': 'iPhone14,3',
000c15a4 168 }
169 },
b6de707d 170 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
171 'REQUIRE_JS_PLAYER': False
000c15a4 172 },
173 'ios_embedded': {
000c15a4 174 'INNERTUBE_CONTEXT': {
175 'client': {
176 'clientName': 'IOS_MESSAGES_EXTENSION',
18c7683d 177 'clientVersion': '16.46',
178 'deviceModel': 'iPhone14,3',
000c15a4 179 },
180 },
b6de707d 181 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
182 'REQUIRE_JS_PLAYER': False
000c15a4 183 },
184 'ios_music': {
18c7683d 185 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 186 'INNERTUBE_CONTEXT': {
187 'client': {
188 'clientName': 'IOS_MUSIC',
18c7683d 189 'clientVersion': '4.57',
000c15a4 190 },
191 },
b6de707d 192 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
193 'REQUIRE_JS_PLAYER': False
000c15a4 194 },
e7e94f2a
D
195 'ios_creator': {
196 'INNERTUBE_CONTEXT': {
197 'client': {
198 'clientName': 'IOS_CREATOR',
18c7683d 199 'clientVersion': '21.47',
e7e94f2a
D
200 },
201 },
b6de707d 202 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
203 'REQUIRE_JS_PLAYER': False
e7e94f2a 204 },
3619f78d 205 # mweb has 'ultralow' formats
206 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 207 'mweb': {
18c7683d 208 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 209 'INNERTUBE_CONTEXT': {
210 'client': {
211 'clientName': 'MWEB',
18c7683d 212 'clientVersion': '2.20211221.01.00',
000c15a4 213 }
214 },
215 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
216 },
217 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
218 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
219 'tv_embedded': {
220 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
221 'INNERTUBE_CONTEXT': {
222 'client': {
223 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
224 'clientVersion': '2.0',
225 },
226 },
227 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
228 },
000c15a4 229}
230
231
e7870111
D
232def _split_innertube_client(client_name):
233 variant, *base = client_name.rsplit('.', 1)
234 if base:
235 return variant, base[0], variant
236 base, *variant = client_name.split('_', 1)
237 return client_name, base, variant[0] if variant else None
238
239
000c15a4 240def build_innertube_clients():
2e4cacd0 241 THIRD_PARTY = {
e7870111 242 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 243 }
e7870111 244 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 245 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 246
247 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 248 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 249 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 250 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 251 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 252
e7870111 253 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 254 ytcfg['priority'] = 10 * priority(base_client)
255
e48b3875 256 if not variant:
e7870111
D
257 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
258 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
259 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
260 embedscreen['priority'] -= 3
261 elif variant == 'embedded':
e48b3875 262 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 263 ytcfg['priority'] -= 2
e48b3875 264 else:
000c15a4 265 ytcfg['priority'] -= 3
266
267
268build_innertube_clients()
269
270
de7f3446 271class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 272 """Provide base functions for Youtube extractors"""
e00eb564 273
3462ffa8 274 _RESERVED_NAMES = (
3cd786db 275 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 276 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 277 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 278 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 279
3619f78d 280 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
281
52efa4b3 282 # _NETRC_MACHINE = 'youtube'
3619f78d 283
b2e8bc1b
JMF
284 # If True it will raise an error if no login info is provided
285 _LOGIN_REQUIRED = False
286
d9190e44
RH
287 _INVIDIOUS_SITES = (
288 # invidious-redirect websites
289 r'(?:www\.)?redirect\.invidious\.io',
290 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 291 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
292 r'(?:www\.)?invidious\.pussthecat\.org',
293 r'(?:www\.)?invidious\.zee\.li',
294 r'(?:www\.)?invidious\.ethibox\.fr',
295 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
296 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
297 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
298 # youtube-dl invidious instances list
299 r'(?:(?:www|no)\.)?invidiou\.sh',
300 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
301 r'(?:www\.)?invidious\.kabi\.tk',
302 r'(?:www\.)?invidious\.mastodon\.host',
303 r'(?:www\.)?invidious\.zapashcanon\.fr',
304 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
305 r'(?:www\.)?invidious\.tinfoil-hat\.net',
306 r'(?:www\.)?invidious\.himiko\.cloud',
307 r'(?:www\.)?invidious\.reallyancient\.tech',
308 r'(?:www\.)?invidious\.tube',
309 r'(?:www\.)?invidiou\.site',
310 r'(?:www\.)?invidious\.site',
311 r'(?:www\.)?invidious\.xyz',
312 r'(?:www\.)?invidious\.nixnet\.xyz',
313 r'(?:www\.)?invidious\.048596\.xyz',
314 r'(?:www\.)?invidious\.drycat\.fr',
315 r'(?:www\.)?inv\.skyn3t\.in',
316 r'(?:www\.)?tube\.poal\.co',
317 r'(?:www\.)?tube\.connect\.cafe',
318 r'(?:www\.)?vid\.wxzm\.sx',
319 r'(?:www\.)?vid\.mint\.lgbt',
320 r'(?:www\.)?vid\.puffyan\.us',
321 r'(?:www\.)?yewtu\.be',
322 r'(?:www\.)?yt\.elukerio\.org',
323 r'(?:www\.)?yt\.lelux\.fi',
324 r'(?:www\.)?invidious\.ggc-project\.de',
325 r'(?:www\.)?yt\.maisputain\.ovh',
326 r'(?:www\.)?ytprivate\.com',
327 r'(?:www\.)?invidious\.13ad\.de',
328 r'(?:www\.)?invidious\.toot\.koeln',
329 r'(?:www\.)?invidious\.fdn\.fr',
330 r'(?:www\.)?watch\.nettohikari\.com',
331 r'(?:www\.)?invidious\.namazso\.eu',
332 r'(?:www\.)?invidious\.silkky\.cloud',
333 r'(?:www\.)?invidious\.exonip\.de',
334 r'(?:www\.)?invidious\.riverside\.rocks',
335 r'(?:www\.)?invidious\.blamefran\.net',
336 r'(?:www\.)?invidious\.moomoo\.de',
337 r'(?:www\.)?ytb\.trom\.tf',
338 r'(?:www\.)?yt\.cyberhost\.uk',
339 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
340 r'(?:www\.)?qklhadlycap4cnod\.onion',
341 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
342 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
343 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
344 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
345 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
346 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
347 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
348 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
349 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
350 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
351 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
352 r'(?:www\.)?piped\.kavin\.rocks',
353 r'(?:www\.)?piped\.silkky\.cloud',
354 r'(?:www\.)?piped\.tokhmi\.xyz',
355 r'(?:www\.)?piped\.moomoo\.me',
356 r'(?:www\.)?il\.ax',
357 r'(?:www\.)?piped\.syncpundit\.com',
358 r'(?:www\.)?piped\.mha\.fi',
359 r'(?:www\.)?piped\.mint\.lgbt',
360 r'(?:www\.)?piped\.privacy\.com\.de',
d9190e44
RH
361 )
362
cce889b9 363 def _initialize_consent(self):
364 cookies = self._get_cookies('https://www.youtube.com/')
365 if cookies.get('__Secure-3PSID'):
366 return
367 consent_id = None
368 consent = cookies.get('CONSENT')
369 if consent:
370 if 'YES' in consent.value:
371 return
372 consent_id = self._search_regex(
373 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
374 if not consent_id:
375 consent_id = random.randint(100, 999)
376 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 377
f3aa3c3f 378 def _initialize_pref(self):
379 cookies = self._get_cookies('https://www.youtube.com/')
380 pref_cookie = cookies.get('PREF')
381 pref = {}
382 if pref_cookie:
383 try:
384 pref = dict(compat_urlparse.parse_qsl(pref_cookie.value))
385 except ValueError:
386 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 387 pref.update({'hl': 'en', 'tz': 'UTC'})
f3aa3c3f 388 self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref))
389
b2e8bc1b 390 def _real_initialize(self):
f3aa3c3f 391 self._initialize_pref()
cce889b9 392 self._initialize_consent()
a25bca9f 393 self._check_login_required()
394
395 def _check_login_required(self):
24146491 396 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 397 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 398
b7c47b74 399 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
400 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 401
000c15a4 402 def _get_default_ytcfg(self, client='web'):
403 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 404
000c15a4 405 def _get_innertube_host(self, client='web'):
406 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 407
000c15a4 408 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 409 # try_get but with fallback to default ytcfg client values when present
410 _func = lambda y: try_get(y, getter, expected_type)
411 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
412
000c15a4 413 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 414 return self._ytcfg_get_safe(
415 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
416 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
109dd3b2 417
000c15a4 418 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 419 return self._ytcfg_get_safe(
420 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
421 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
109dd3b2 422
2ae778b8 423 def _select_api_hostname(self, req_api_hostname, default_client=None):
424 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
425 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
426
000c15a4 427 def _extract_api_key(self, ytcfg=None, default_client='web'):
109dd3b2 428 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
429
000c15a4 430 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 431 context = get_first(
432 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 433 # Enforce language and tz for extraction
434 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
435 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 436 return context
437
cf87314d 438 _SAPISID = None
439
109dd3b2 440 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 441 time_now = round(time.time())
cf87314d 442 if self._SAPISID is None:
443 yt_cookies = self._get_cookies('https://www.youtube.com')
444 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
445 # See: https://github.com/yt-dlp/yt-dlp/issues/393
446 sapisid_cookie = dict_get(
447 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
448 if sapisid_cookie and sapisid_cookie.value:
449 self._SAPISID = sapisid_cookie.value
450 self.write_debug('Extracted SAPISID cookie')
451 # SAPISID cookie is required if not already present
452 if not yt_cookies.get('SAPISID'):
453 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
454 self._set_cookie(
455 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
456 else:
457 self._SAPISID = False
458 if not self._SAPISID:
459 return None
1974e99f 460 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
461 sapisidhash = hashlib.sha1(
86e5f3ed 462 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 463 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
464
465 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 466 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 467 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 468
109dd3b2 469 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 470 data.update(query)
11f9be09 471 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 472 real_headers.update({'content-type': 'application/json'})
473 if headers:
474 real_headers.update(headers)
2ae778b8 475 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
476 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 477 return self._download_json(
2ae778b8 478 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 479 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 480 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 481 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 482
65141660 483 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
484 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 485
99e9e001 486 @staticmethod
487 def _extract_session_index(*data):
488 """
489 Index of current account in account list.
490 See: https://github.com/yt-dlp/yt-dlp/pull/519
491 """
492 for ytcfg in data:
493 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
494 if session_index is not None:
495 return session_index
496
497 # Deprecated?
498 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca
M
499 if ytcfg:
500 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
501 if token:
502 return token
99e9e001 503 if webpage:
504 return self._search_regex(
505 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
506 'identity token', default=None, fatal=False)
a1c5d2ca
M
507
508 @staticmethod
fe93e2c4 509 def _extract_account_syncid(*args):
8ea3f7b9 510 """
511 Extract syncId required to download private playlists of secondary channels
fe93e2c4 512 @params response and/or ytcfg
8ea3f7b9 513 """
fe93e2c4 514 for data in args:
515 # ytcfg includes channel_syncid if on secondary channel
516 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
517 if delegated_sid:
518 return delegated_sid
519 sync_ids = (try_get(
520 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
e6f21b3d 521 lambda x: x['DATASYNC_ID']), compat_str) or '').split('||')
fe93e2c4 522 if len(sync_ids) >= 2 and sync_ids[1]:
523 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
524 # and just "user_syncid||" for primary channel. We only want the channel_syncid
525 return sync_ids[0]
a1c5d2ca 526
ac56cf38 527 @staticmethod
528 def _extract_visitor_data(*args):
529 """
530 Extracts visitorData from an API response or ytcfg
531 Appears to be used to track session state
532 """
9222c381 533 return get_first(
6c73052c 534 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 535 expected_type=str)
ac56cf38 536
2762dbb1 537 @functools.cached_property
99e9e001 538 def is_authenticated(self):
539 return bool(self._generate_sapisidhash_header())
540
11f9be09 541 def extract_ytcfg(self, video_id, webpage):
8c54a305 542 if not webpage:
543 return {}
29f7c58a 544 return self._parse_json(
545 self._search_regex(
546 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 547 default='{}'), video_id, fatal=False) or {}
548
11f9be09 549 def generate_api_headers(
99e9e001 550 self, *, ytcfg=None, account_syncid=None, session_index=None,
551 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
552
2ae778b8 553 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 554 headers = {
109dd3b2 555 'X-YouTube-Client-Name': compat_str(
11f9be09 556 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
557 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 558 'Origin': origin,
559 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
560 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 561 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 562 }
563 if session_index is None:
314ee305 564 session_index = self._extract_session_index(ytcfg)
565 if account_syncid or session_index is not None:
566 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 567
109dd3b2 568 auth = self._generate_sapisidhash_header(origin)
f4f751af 569 if auth is not None:
570 headers['Authorization'] = auth
109dd3b2 571 headers['X-Origin'] = origin
99e9e001 572 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 573
a25bca9f 574 def _download_ytcfg(self, client, video_id):
575 url = {
576 'web': 'https://www.youtube.com',
577 'web_music': 'https://music.youtube.com',
578 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
579 }.get(client)
580 if not url:
581 return {}
582 webpage = self._download_webpage(
583 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
584 return self.extract_ytcfg(video_id, webpage) or {}
585
2d6659b9 586 @staticmethod
587 def _build_api_continuation_query(continuation, ctp=None):
588 query = {
589 'continuation': continuation
590 }
591 # TODO: Inconsistency with clickTrackingParams.
592 # Currently we have a fixed ctp contained within context (from ytcfg)
593 # and a ctp in root query for continuation.
594 if ctp:
595 query['clickTracking'] = {'clickTrackingParams': ctp}
596 return query
597
2d6659b9 598 @classmethod
599 def _extract_next_continuation_data(cls, renderer):
600 next_continuation = try_get(
601 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
602 lambda x: x['continuation']['reloadContinuationData']), dict)
603 if not next_continuation:
604 return
605 continuation = next_continuation.get('continuation')
606 if not continuation:
607 return
608 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 609 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 610
611 @classmethod
612 def _extract_continuation_ep_data(cls, continuation_ep: dict):
613 if isinstance(continuation_ep, dict):
614 continuation = try_get(
615 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
616 if not continuation:
617 return
618 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 619 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 620
621 @classmethod
622 def _extract_continuation(cls, renderer):
623 next_continuation = cls._extract_next_continuation_data(renderer)
624 if next_continuation:
625 return next_continuation
fe93e2c4 626
2d6659b9 627 contents = []
628 for key in ('contents', 'items'):
629 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 630
2d6659b9 631 for content in contents:
632 if not isinstance(content, dict):
633 continue
634 continuation_ep = try_get(
635 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
636 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
637 dict)
638 continuation = cls._extract_continuation_ep_data(continuation_ep)
639 if continuation:
640 return continuation
641
fe93e2c4 642 @classmethod
643 def _extract_alerts(cls, data):
109dd3b2 644 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
645 if not isinstance(alert_dict, dict):
646 continue
647 for alert in alert_dict.values():
648 alert_type = alert.get('type')
649 if not alert_type:
650 continue
052e1350 651 message = cls._get_text(alert, 'text')
109dd3b2 652 if message:
653 yield alert_type, message
654
c0ac49bc 655 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 656 errors = []
657 warnings = []
658 for alert_type, alert_message in alerts:
641ad5d8 659 if alert_type.lower() == 'error' and fatal:
109dd3b2 660 errors.append([alert_type, alert_message])
661 else:
662 warnings.append([alert_type, alert_message])
663
664 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 665 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 666 if errors:
667 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
668
669 def _extract_and_report_alerts(self, data, *args, **kwargs):
670 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
671
47193e02 672 def _extract_badges(self, renderer: dict):
673 badges = set()
674 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
675 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
676 if label:
677 badges.add(label.lower())
678 return badges
679
680 @staticmethod
052e1350 681 def _get_text(data, *path_list, max_runs=None):
682 for path in path_list or [None]:
683 if path is None:
684 obj = [data]
685 else:
686 obj = traverse_obj(data, path, default=[])
687 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
688 obj = [obj]
689 for item in obj:
690 text = try_get(item, lambda x: x['simpleText'], compat_str)
691 if text:
692 return text
693 runs = try_get(item, lambda x: x['runs'], list) or []
694 if not runs and isinstance(item, list):
695 runs = item
696
697 runs = runs[:min(len(runs), max_runs or len(runs))]
698 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
699 if text:
700 return text
47193e02 701
f0d785d3 702 def _get_count(self, data, *path_list):
703 count_text = self._get_text(data, *path_list) or ''
704 count = parse_count(count_text)
705 if count is None:
706 count = str_to_int(
707 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
708 return count
709
a709d873 710 @staticmethod
711 def _extract_thumbnails(data, *path_list):
712 """
713 Extract thumbnails from thumbnails dict
714 @param path_list: path list to level that contains 'thumbnails' key
715 """
716 thumbnails = []
717 for path in path_list or [()]:
718 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
719 thumbnail_url = url_or_none(thumbnail.get('url'))
720 if not thumbnail_url:
721 continue
722 # Sometimes youtube gives a wrong thumbnail URL. See:
723 # https://github.com/yt-dlp/yt-dlp/issues/233
724 # https://github.com/ytdl-org/youtube-dl/issues/28023
725 if 'maxresdefault' in thumbnail_url:
726 thumbnail_url = thumbnail_url.split('?')[0]
727 thumbnails.append({
728 'url': thumbnail_url,
729 'height': int_or_none(thumbnail.get('height')),
730 'width': int_or_none(thumbnail.get('width')),
731 })
732 return thumbnails
733
f3aa3c3f 734 @staticmethod
735 def extract_relative_time(relative_time_text):
736 """
737 Extracts a relative time from string and converts to dt object
f0d785d3 738 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 739 """
f0d785d3 740 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 741 if mobj:
f0d785d3 742 start = mobj.group('start')
743 if start:
744 return datetime_from_str(start)
f3aa3c3f 745 try:
f0d785d3 746 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 747 except ValueError:
748 return None
749
750 def _extract_time_text(self, renderer, *path_list):
a25bca9f 751 """@returns (timestamp, time_text)"""
f3aa3c3f 752 text = self._get_text(renderer, *path_list) or ''
753 dt = self.extract_relative_time(text)
754 timestamp = None
755 if isinstance(dt, datetime.datetime):
756 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 757
758 if timestamp is None:
759 timestamp = (
760 unified_timestamp(text) or unified_timestamp(
761 self._search_regex(
17322130 762 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 763 text.lower(), 'time text', default=None)))
f0d785d3 764
f3aa3c3f 765 if text and timestamp is None:
17322130 766 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
f3aa3c3f 767 return timestamp, text
768
109dd3b2 769 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
770 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 771 default_client='web'):
109dd3b2 772 response = None
773 last_error = None
774 count = -1
775 retries = self.get_param('extractor_retries', 3)
776 if check_get_keys is None:
777 check_get_keys = []
778 while count < retries:
779 count += 1
780 if last_error:
c0ac49bc 781 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
109dd3b2 782 try:
783 response = self._call_api(
784 ep=ep, fatal=True, headers=headers,
785 video_id=item_id, query=query,
786 context=self._extract_context(ytcfg, default_client),
787 api_key=self._extract_api_key(ytcfg, default_client),
788 api_hostname=api_hostname, default_client=default_client,
789 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
790 except ExtractorError as e:
9c0d7f49 791 if isinstance(e.cause, network_exceptions):
87e8e8a7 792 if isinstance(e.cause, compat_HTTPError):
793 first_bytes = e.cause.read(512)
794 if not is_html(first_bytes):
795 yt_error = try_get(
796 self._parse_json(
797 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
798 lambda x: x['error']['message'], compat_str)
799 if yt_error:
800 self._report_alerts([('ERROR', yt_error)], fatal=False)
109dd3b2 801 # Downloading page may result in intermittent 5xx HTTP error
802 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 803 # We also want to catch all other network exceptions since errors in later pages can be troublesome
804 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
805 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
526d74ec 806 last_error = error_to_compat_str(e.cause or e.msg)
9c0d7f49 807 if count < retries:
808 continue
109dd3b2 809 if fatal:
810 raise
811 else:
812 self.report_warning(error_to_compat_str(e))
813 return
814
815 else:
109dd3b2 816 try:
ac56cf38 817 self._extract_and_report_alerts(response, only_once=True)
109dd3b2 818 except ExtractorError as e:
c0ac49bc 819 # YouTube servers may return errors we want to retry on in a 200 OK response
820 # See: https://github.com/yt-dlp/yt-dlp/issues/839
821 if 'unknown error' in e.msg.lower():
822 last_error = e.msg
823 continue
109dd3b2 824 if fatal:
825 raise
826 self.report_warning(error_to_compat_str(e))
827 return
828 if not check_get_keys or dict_get(response, check_get_keys):
829 break
830 # Youtube sometimes sends incomplete data
831 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
832 last_error = 'Incomplete data received'
833 if count >= retries:
834 if fatal:
835 raise ExtractorError(last_error)
836 else:
837 self.report_warning(last_error)
838 return
839 return response
840
9297939e 841 @staticmethod
842 def is_music_url(url):
843 return re.match(r'https?://music\.youtube\.com/', url) is not None
844
30a074c2 845 def _extract_video(self, renderer):
846 video_id = renderer.get('videoId')
052e1350 847 title = self._get_text(renderer, 'title')
848 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 849 duration = parse_duration(self._get_text(
850 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 851 if duration is None:
852 duration = parse_duration(self._search_regex(
853 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
854 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
855 video_id, default=None, group='duration'))
856
f0d785d3 857 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 858
052e1350 859 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 860 channel_id = traverse_obj(
a44ca5a4 861 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
862 expected_type=str, get_all=False)
f3aa3c3f 863 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
864 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
865 overlay_style = traverse_obj(
a44ca5a4 866 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
867 get_all=False, expected_type=str)
f3aa3c3f 868 badges = self._extract_badges(renderer)
a709d873 869 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
fd2ad7cb 870 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 871 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
872 expected_type=str)) or ''
fd2ad7cb 873 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 874 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 875 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 876
30a074c2 877 return {
39ed931e 878 '_type': 'url',
30a074c2 879 'ie_key': YoutubeIE.ie_key(),
880 'id': video_id,
fd2ad7cb 881 'url': url,
30a074c2 882 'title': title,
883 'description': description,
884 'duration': duration,
885 'view_count': view_count,
886 'uploader': uploader,
f3aa3c3f 887 'channel_id': channel_id,
a709d873 888 'thumbnails': thumbnails,
a44ca5a4 889 'upload_date': (strftime_or_none(timestamp, '%Y%m%d')
890 if self._configuration_arg('approximate_date', ie_key='youtubetab')
891 else None),
f3aa3c3f 892 'live_status': ('is_upcoming' if scheduled_timestamp is not None
893 else 'was_live' if 'streamed' in time_text.lower()
894 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
895 else None),
896 'release_timestamp': scheduled_timestamp,
897 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 898 }
899
0c148415 900
360e1ca5 901class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 902 IE_DESC = 'YouTube'
cb7dfeea 903 _VALID_URL = r"""(?x)^
c5e8d7af 904 (
edb53e2d 905 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 906 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
907 (?:www\.)?deturl\.com/www\.youtube\.com|
908 (?:www\.)?pwnyoutube\.com|
909 (?:www\.)?hooktube\.com|
910 (?:www\.)?yourepeat\.com|
911 tube\.majestyc\.net|
912 %(invidious)s|
913 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
914 (?:.*?\#/)? # handle anchor (#/) redirect urls
915 (?: # the various things that can precede the ID:
b6ce9bb0 916 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 917 |(?: # or the v= param in all its forms
f7000f3a 918 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 919 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 920 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
921 v=
922 )
f4b05232 923 ))
cbaed4bb
S
924 |(?:
925 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
926 vid\.plus| # or vid.plus/xxxx
927 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 928 %(invidious)s
cbaed4bb 929 )/
edb53e2d 930 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 931 )
c5e8d7af 932 )? # all until now is optional -> you can pass the naked ID
201c1459 933 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 934 (?(1).+)? # if we found the ID, everything can follow
9297939e 935 (?:\#|$)""" % {
d9190e44 936 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 937 }
e40c758c 938 _PLAYER_INFO_RE = (
cc2db878 939 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
940 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$',
545cc85d 941 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 942 )
2c62dc26 943 _formats = {
c2d3cb4c 944 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
945 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
946 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
947 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
948 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
949 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
950 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
951 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 952 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 953 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
954 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
955 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
956 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
957 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
958 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 959 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 960 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
961 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 962
963
964 # 3D videos
c2d3cb4c 965 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
966 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
967 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
968 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 969 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
970 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
971 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 972
96fb5605 973 # Apple HTTP Live Streaming
11f12195 974 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 975 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
976 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
977 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
978 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
979 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 980 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
981 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
982
983 # DASH mp4 video
d23028a8
S
984 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
985 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
986 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
987 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
988 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 989 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
990 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
991 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
992 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
993 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
994 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
995 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 996
f6f1fc92 997 # Dash mp4 audio
d23028a8
S
998 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
999 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1000 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1001 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1002 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1003 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1004 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1005
1006 # Dash webm
d23028a8
S
1007 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1008 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1009 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1010 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1011 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1012 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1013 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1014 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1015 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1016 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1017 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1018 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1019 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1020 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1021 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1022 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1023 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1024 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1025 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1026 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1027 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1028 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1029
1030 # Dash webm audio
d23028a8
S
1031 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1032 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1033
0857baad 1034 # Dash webm audio with opus inside
d23028a8
S
1035 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1036 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1037 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1038
ce6b9a2d
PH
1039 # RTMP (unnamed)
1040 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1041
1042 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1043 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1044 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1045 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1046 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1047 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1048 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1049 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1050 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1051 }
29f7c58a 1052 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1053
fd5c4aab
S
1054 _GEO_BYPASS = False
1055
78caa52a 1056 IE_NAME = 'youtube'
2eb88d95
PH
1057 _TESTS = [
1058 {
2d3d2997 1059 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1060 'info_dict': {
1061 'id': 'BaW_jenozKc',
1062 'ext': 'mp4',
3867038a 1063 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1064 'uploader': 'Philipp Hagemeister',
1065 'uploader_id': 'phihag',
ec85ded8 1066 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1067 'channel': 'Philipp Hagemeister',
dd4c4492
S
1068 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1069 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1070 'upload_date': '20121002',
ff9f925b 1071 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1072 'categories': ['Science & Technology'],
3867038a 1073 'tags': ['youtube-dl'],
556dbe7f 1074 'duration': 10,
dbdaaa23 1075 'view_count': int,
3e7c1224 1076 'like_count': int,
ff9f925b 1077 'availability': 'public',
1078 'playable_in_embed': True,
1079 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1080 'live_status': 'not_live',
1081 'age_limit': 0,
7c80519c 1082 'start_time': 1,
297a564b 1083 'end_time': 9,
6c73052c 1084 'channel_follower_count': int
2eb88d95 1085 }
0e853ca4 1086 },
fccd3771 1087 {
4bc3a23e
PH
1088 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1089 'note': 'Embed-only video (#1746)',
1090 'info_dict': {
1091 'id': 'yZIXLfi8CZQ',
1092 'ext': 'mp4',
1093 'upload_date': '20120608',
1094 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1095 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1096 'uploader': 'SET India',
94bfcd23 1097 'uploader_id': 'setindia',
ec85ded8 1098 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1099 'age_limit': 18,
545cc85d 1100 },
1101 'skip': 'Private video',
fccd3771 1102 },
11b56058 1103 {
8bdd16b4 1104 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1105 'note': 'Use the first video ID in the URL',
1106 'info_dict': {
1107 'id': 'BaW_jenozKc',
1108 'ext': 'mp4',
3867038a 1109 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1110 'uploader': 'Philipp Hagemeister',
1111 'uploader_id': 'phihag',
ec85ded8 1112 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1113 'channel': 'Philipp Hagemeister',
1114 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1115 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1116 'upload_date': '20121002',
976ae3ea 1117 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1118 'categories': ['Science & Technology'],
3867038a 1119 'tags': ['youtube-dl'],
556dbe7f 1120 'duration': 10,
dbdaaa23 1121 'view_count': int,
11b56058 1122 'like_count': int,
976ae3ea 1123 'availability': 'public',
1124 'playable_in_embed': True,
1125 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1126 'live_status': 'not_live',
1127 'age_limit': 0,
6c73052c 1128 'channel_follower_count': int
34a7de29
S
1129 },
1130 'params': {
1131 'skip_download': True,
1132 },
11b56058 1133 },
dd27fd17 1134 {
2d3d2997 1135 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1136 'note': '256k DASH audio (format 141) via DASH manifest',
1137 'info_dict': {
1138 'id': 'a9LDPn-MO4I',
1139 'ext': 'm4a',
1140 'upload_date': '20121002',
1141 'uploader_id': '8KVIDEO',
ec85ded8 1142 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1143 'description': '',
1144 'uploader': '8KVIDEO',
1145 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1146 },
4bc3a23e
PH
1147 'params': {
1148 'youtube_include_dash_manifest': True,
1149 'format': '141',
4919603f 1150 },
de3c7fe0 1151 'skip': 'format 141 not served anymore',
dd27fd17 1152 },
8bdd16b4 1153 # DASH manifest with encrypted signature
1154 {
1155 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1156 'info_dict': {
1157 'id': 'IB3lcPjvWLA',
1158 'ext': 'm4a',
1159 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1160 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1161 'duration': 244,
1162 'uploader': 'AfrojackVEVO',
1163 'uploader_id': 'AfrojackVEVO',
1164 'upload_date': '20131011',
cc2db878 1165 'abr': 129.495,
976ae3ea 1166 'like_count': int,
1167 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1168 'playable_in_embed': True,
1169 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1170 'view_count': int,
1171 'track': 'The Spark',
1172 'live_status': 'not_live',
1173 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1174 'channel': 'Afrojack',
1175 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1176 'tags': 'count:19',
1177 'availability': 'public',
1178 'categories': ['Music'],
1179 'age_limit': 0,
1180 'alt_title': 'The Spark',
6c73052c 1181 'channel_follower_count': int
8bdd16b4 1182 },
1183 'params': {
1184 'youtube_include_dash_manifest': True,
1185 'format': '141/bestaudio[ext=m4a]',
1186 },
1187 },
65c2fde2 1188 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1189 {
65c2fde2 1190 'note': 'Embed allowed age-gate video',
2d3d2997 1191 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1192 'info_dict': {
1193 'id': 'HtVdAasjOgU',
1194 'ext': 'mp4',
1195 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1196 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1197 'duration': 142,
c522adb1
JMF
1198 'uploader': 'The Witcher',
1199 'uploader_id': 'WitcherGame',
ec85ded8 1200 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1201 'upload_date': '20140605',
34952f09 1202 'age_limit': 18,
976ae3ea 1203 'categories': ['Gaming'],
1204 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1205 'availability': 'needs_auth',
1206 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1207 'like_count': int,
1208 'channel': 'The Witcher',
1209 'live_status': 'not_live',
1210 'tags': 'count:17',
1211 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1212 'playable_in_embed': True,
1213 'view_count': int,
6c73052c 1214 'channel_follower_count': int
c522adb1
JMF
1215 },
1216 },
65c2fde2 1217 {
1218 'note': 'Age-gate video with embed allowed in public site',
1219 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1220 'info_dict': {
1221 'id': 'HsUATh_Nc2U',
1222 'ext': 'mp4',
1223 'title': 'Godzilla 2 (Official Video)',
1224 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1225 'upload_date': '20200408',
1226 'uploader_id': 'FlyingKitty900',
1227 'uploader': 'FlyingKitty',
1228 'age_limit': 18,
976ae3ea 1229 'availability': 'needs_auth',
1230 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1231 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1232 'channel': 'FlyingKitty',
1233 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1234 'view_count': int,
1235 'categories': ['Entertainment'],
1236 'live_status': 'not_live',
1237 'tags': ['Flyingkitty', 'godzilla 2'],
1238 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1239 'like_count': int,
1240 'duration': 177,
1241 'playable_in_embed': True,
6c73052c 1242 'channel_follower_count': int
65c2fde2 1243 },
1244 },
1245 {
1246 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1247 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1248 'info_dict': {
1249 'id': 'Tq92D6wQ1mg',
1250 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1251 'ext': 'mp4',
17322130 1252 'upload_date': '20191228',
65c2fde2 1253 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1254 'uploader': 'Projekt Melody',
1255 'description': 'md5:17eccca93a786d51bc67646756894066',
1256 'age_limit': 18,
976ae3ea 1257 'like_count': int,
1258 'availability': 'needs_auth',
1259 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1260 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1261 'view_count': int,
1262 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1263 'channel': 'Projekt Melody',
1264 'live_status': 'not_live',
1265 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1266 'playable_in_embed': True,
1267 'categories': ['Entertainment'],
1268 'duration': 106,
1269 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
6c73052c 1270 'channel_follower_count': int
65c2fde2 1271 },
1272 },
1273 {
1274 'note': 'Non-Agegated non-embeddable video',
1275 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1276 'info_dict': {
1277 'id': 'MeJVWBSsPAY',
1278 'ext': 'mp4',
1279 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1280 'uploader': 'Herr Lurik',
1281 'uploader_id': 'st3in234',
1282 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1283 'upload_date': '20130730',
976ae3ea 1284 'track': 'Such mich find mich',
1285 'age_limit': 0,
1286 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1287 'like_count': int,
1288 'playable_in_embed': False,
1289 'creator': 'OOMPH!',
1290 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1291 'view_count': int,
1292 'alt_title': 'Such mich find mich',
1293 'duration': 210,
1294 'channel': 'Herr Lurik',
1295 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1296 'categories': ['Music'],
1297 'availability': 'public',
1298 'uploader_url': 'http://www.youtube.com/user/st3in234',
1299 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1300 'live_status': 'not_live',
1301 'artist': 'OOMPH!',
6c73052c 1302 'channel_follower_count': int
65c2fde2 1303 },
1304 },
1305 {
1306 'note': 'Non-bypassable age-gated video',
1307 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1308 'only_matching': True,
1309 },
8bdd16b4 1310 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1311 # YouTube Red ad is not captured for creator
1312 {
1313 'url': '__2ABJjxzNo',
1314 'info_dict': {
1315 'id': '__2ABJjxzNo',
1316 'ext': 'mp4',
1317 'duration': 266,
1318 'upload_date': '20100430',
1319 'uploader_id': 'deadmau5',
1320 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1321 'creator': 'deadmau5',
1322 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1323 'uploader': 'deadmau5',
1324 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1325 'alt_title': 'Some Chords',
976ae3ea 1326 'availability': 'public',
1327 'tags': 'count:14',
1328 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1329 'view_count': int,
1330 'live_status': 'not_live',
1331 'channel': 'deadmau5',
1332 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1333 'like_count': int,
1334 'track': 'Some Chords',
1335 'artist': 'deadmau5',
1336 'playable_in_embed': True,
1337 'age_limit': 0,
1338 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1339 'categories': ['Music'],
1340 'album': 'Some Chords',
6c73052c 1341 'channel_follower_count': int
8bdd16b4 1342 },
1343 'expected_warnings': [
1344 'DASH manifest missing',
1345 ]
1346 },
067aa17e 1347 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1348 {
1349 'url': 'lqQg6PlCWgI',
1350 'info_dict': {
1351 'id': 'lqQg6PlCWgI',
1352 'ext': 'mp4',
556dbe7f 1353 'duration': 6085,
90227264 1354 'upload_date': '20150827',
cbe2bd91 1355 'uploader_id': 'olympic',
ec85ded8 1356 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1357 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1358 'uploader': 'Olympics',
cbe2bd91 1359 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1360 'like_count': int,
1361 'release_timestamp': 1343767800,
1362 'playable_in_embed': True,
1363 'categories': ['Sports'],
1364 'release_date': '20120731',
1365 'channel': 'Olympics',
1366 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1367 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1368 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1369 'age_limit': 0,
1370 'availability': 'public',
1371 'live_status': 'was_live',
1372 'view_count': int,
1373 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1374 'channel_follower_count': int
cbe2bd91
PH
1375 },
1376 'params': {
1377 'skip_download': 'requires avconv',
e52a40ab 1378 }
cbe2bd91 1379 },
6271f1ca
PH
1380 # Non-square pixels
1381 {
1382 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1383 'info_dict': {
1384 'id': '_b-2C3KPAM0',
1385 'ext': 'mp4',
1386 'stretched_ratio': 16 / 9.,
556dbe7f 1387 'duration': 85,
6271f1ca
PH
1388 'upload_date': '20110310',
1389 'uploader_id': 'AllenMeow',
ec85ded8 1390 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1391 '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 1392 'uploader': '孫ᄋᄅ',
6271f1ca 1393 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1394 'playable_in_embed': True,
1395 'channel': '孫ᄋᄅ',
1396 'age_limit': 0,
1397 'tags': 'count:11',
1398 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1399 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1400 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1401 'view_count': int,
1402 'categories': ['People & Blogs'],
1403 'like_count': int,
1404 'live_status': 'not_live',
1405 'availability': 'unlisted',
6c73052c 1406 'channel_follower_count': int
6271f1ca 1407 },
06b491eb
S
1408 },
1409 # url_encoded_fmt_stream_map is empty string
1410 {
1411 'url': 'qEJwOuvDf7I',
1412 'info_dict': {
1413 'id': 'qEJwOuvDf7I',
f57b7835 1414 'ext': 'webm',
06b491eb
S
1415 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1416 'description': '',
1417 'upload_date': '20150404',
1418 'uploader_id': 'spbelect',
1419 'uploader': 'Наблюдатели Петербурга',
1420 },
1421 'params': {
1422 'skip_download': 'requires avconv',
e323cf3f
S
1423 },
1424 'skip': 'This live event has ended.',
06b491eb 1425 },
067aa17e 1426 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1427 {
1428 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1429 'info_dict': {
1430 'id': 'FIl7x6_3R5Y',
eb6793ba 1431 'ext': 'webm',
da77d856
S
1432 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1433 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1434 'duration': 220,
da77d856
S
1435 'upload_date': '20150625',
1436 'uploader_id': 'dorappi2000',
ec85ded8 1437 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1438 'uploader': 'dorappi2000',
eb6793ba 1439 'formats': 'mincount:31',
da77d856 1440 },
eb6793ba 1441 'skip': 'not actual anymore',
2ee8f5d8 1442 },
8a1a26ce
YCH
1443 # DASH manifest with segment_list
1444 {
1445 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1446 'md5': '8ce563a1d667b599d21064e982ab9e31',
1447 'info_dict': {
1448 'id': 'CsmdDsKjzN8',
1449 'ext': 'mp4',
17ee98e1 1450 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1451 'uploader': 'Airtek',
1452 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1453 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1454 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1455 },
1456 'params': {
1457 'youtube_include_dash_manifest': True,
1458 'format': '135', # bestvideo
be49068d
S
1459 },
1460 'skip': 'This live event has ended.',
2ee8f5d8 1461 },
cf7e015f
S
1462 {
1463 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1464 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1465 'info_dict': {
545cc85d 1466 'id': 'jvGDaLqkpTg',
1467 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1468 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1469 },
1470 'playlist': [{
1471 'info_dict': {
545cc85d 1472 'id': 'jvGDaLqkpTg',
cf7e015f 1473 'ext': 'mp4',
545cc85d 1474 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1475 'description': 'md5:e03b909557865076822aa169218d6a5d',
1476 'duration': 10643,
1477 'upload_date': '20161111',
1478 'uploader': 'Team PGP',
1479 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1480 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1481 },
1482 }, {
1483 'info_dict': {
545cc85d 1484 'id': '3AKt1R1aDnw',
cf7e015f 1485 'ext': 'mp4',
545cc85d 1486 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1487 'description': 'md5:e03b909557865076822aa169218d6a5d',
1488 'duration': 10991,
1489 'upload_date': '20161111',
1490 'uploader': 'Team PGP',
1491 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1492 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1493 },
1494 }, {
1495 'info_dict': {
545cc85d 1496 'id': 'RtAMM00gpVc',
cf7e015f 1497 'ext': 'mp4',
545cc85d 1498 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1499 'description': 'md5:e03b909557865076822aa169218d6a5d',
1500 'duration': 10995,
1501 'upload_date': '20161111',
1502 'uploader': 'Team PGP',
1503 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1504 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1505 },
1506 }, {
1507 'info_dict': {
545cc85d 1508 'id': '6N2fdlP3C5U',
cf7e015f 1509 'ext': 'mp4',
545cc85d 1510 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1511 'description': 'md5:e03b909557865076822aa169218d6a5d',
1512 'duration': 10990,
1513 'upload_date': '20161111',
1514 'uploader': 'Team PGP',
1515 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1516 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1517 },
1518 }],
1519 'params': {
1520 'skip_download': True,
1521 },
65c2fde2 1522 'skip': 'Not multifeed anymore',
cbaed4bb 1523 },
f9f49d87 1524 {
067aa17e 1525 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1526 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1527 'info_dict': {
1528 'id': 'gVfLd0zydlo',
1529 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1530 },
1531 'playlist_count': 2,
be49068d 1532 'skip': 'Not multifeed anymore',
f9f49d87 1533 },
cbaed4bb 1534 {
2d3d2997 1535 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1536 'only_matching': True,
0e49d9a6 1537 },
6d4fc66b 1538 {
2d3d2997 1539 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1540 'only_matching': True,
1541 },
0e49d9a6 1542 {
067aa17e 1543 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1544 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1545 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1546 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1547 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1548 'info_dict': {
1549 'id': 'lsguqyKfVQg',
1550 'ext': 'mp4',
1551 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1552 'alt_title': 'Dark Walk',
0e49d9a6 1553 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1554 'duration': 133,
0e49d9a6
LL
1555 'upload_date': '20151119',
1556 'uploader_id': 'IronSoulElf',
ec85ded8 1557 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1558 'uploader': 'IronSoulElf',
11f9be09 1559 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1560 'track': 'Dark Walk',
1561 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1562 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1563 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1564 'categories': ['Film & Animation'],
1565 'view_count': int,
1566 'live_status': 'not_live',
1567 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1568 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1569 'tags': 'count:13',
1570 'availability': 'public',
1571 'channel': 'IronSoulElf',
1572 'playable_in_embed': True,
1573 'like_count': int,
1574 'age_limit': 0,
6c73052c 1575 'channel_follower_count': int
0e49d9a6
LL
1576 },
1577 'params': {
1578 'skip_download': True,
1579 },
1580 },
61f92af1 1581 {
067aa17e 1582 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1583 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1584 'only_matching': True,
1585 },
313dfc45
LL
1586 {
1587 # Video with yt:stretch=17:0
1588 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1589 'info_dict': {
1590 'id': 'Q39EVAstoRM',
1591 'ext': 'mp4',
1592 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1593 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1594 'upload_date': '20151107',
1595 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1596 'uploader': 'CH GAMER DROID',
1597 },
1598 'params': {
1599 'skip_download': True,
1600 },
be49068d 1601 'skip': 'This video does not exist.',
313dfc45 1602 },
201c1459 1603 {
1604 # Video with incomplete 'yt:stretch=16:'
1605 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1606 'only_matching': True,
1607 },
7caf9830
S
1608 {
1609 # Video licensed under Creative Commons
1610 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1611 'info_dict': {
1612 'id': 'M4gD1WSo5mA',
1613 'ext': 'mp4',
1614 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1615 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1616 'duration': 721,
17322130 1617 'upload_date': '20150128',
7caf9830 1618 'uploader_id': 'BerkmanCenter',
ec85ded8 1619 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1620 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1621 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1622 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1623 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1624 'like_count': int,
1625 'age_limit': 0,
1626 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1627 'channel': 'The Berkman Klein Center for Internet & Society',
1628 'availability': 'public',
1629 'view_count': int,
1630 'categories': ['Education'],
1631 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1632 'live_status': 'not_live',
1633 'playable_in_embed': True,
6c73052c 1634 'channel_follower_count': int
7caf9830
S
1635 },
1636 'params': {
1637 'skip_download': True,
1638 },
1639 },
fd050249
S
1640 {
1641 # Channel-like uploader_url
1642 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1643 'info_dict': {
1644 'id': 'eQcmzGIKrzg',
1645 'ext': 'mp4',
1646 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1647 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1648 'duration': 4060,
17322130 1649 'upload_date': '20151120',
eb6793ba 1650 'uploader': 'Bernie Sanders',
fd050249 1651 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1652 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1653 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1654 'playable_in_embed': True,
1655 'tags': 'count:12',
1656 'like_count': int,
1657 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1658 'age_limit': 0,
1659 'availability': 'public',
1660 'categories': ['News & Politics'],
1661 'channel': 'Bernie Sanders',
1662 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1663 'view_count': int,
1664 'live_status': 'not_live',
1665 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
6c73052c 1666 'channel_follower_count': int
fd050249
S
1667 },
1668 'params': {
1669 'skip_download': True,
1670 },
1671 },
040ac686
S
1672 {
1673 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1674 'only_matching': True,
7f29cf54
S
1675 },
1676 {
067aa17e 1677 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1678 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1679 'only_matching': True,
6496ccb4
S
1680 },
1681 {
1682 # Rental video preview
1683 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1684 'info_dict': {
1685 'id': 'uGpuVWrhIzE',
1686 'ext': 'mp4',
1687 'title': 'Piku - Trailer',
1688 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1689 'upload_date': '20150811',
1690 'uploader': 'FlixMatrix',
1691 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1692 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1693 'license': 'Standard YouTube License',
1694 },
1695 'params': {
1696 'skip_download': True,
1697 },
eb6793ba 1698 'skip': 'This video is not available.',
022a5d66 1699 },
12afdc2a
S
1700 {
1701 # YouTube Red video with episode data
1702 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1703 'info_dict': {
1704 'id': 'iqKdEhx-dD4',
1705 'ext': 'mp4',
1706 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1707 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1708 'duration': 2085,
12afdc2a
S
1709 'upload_date': '20170118',
1710 'uploader': 'Vsauce',
1711 'uploader_id': 'Vsauce',
1712 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1713 'series': 'Mind Field',
1714 'season_number': 1,
1715 'episode_number': 1,
976ae3ea 1716 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1717 'tags': 'count:12',
1718 'view_count': int,
1719 'availability': 'public',
1720 'age_limit': 0,
1721 'channel': 'Vsauce',
1722 'episode': 'Episode 1',
1723 'categories': ['Entertainment'],
1724 'season': 'Season 1',
1725 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1726 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1727 'like_count': int,
1728 'playable_in_embed': True,
1729 'live_status': 'not_live',
6c73052c 1730 'channel_follower_count': int
12afdc2a
S
1731 },
1732 'params': {
1733 'skip_download': True,
1734 },
1735 'expected_warnings': [
1736 'Skipping DASH manifest',
1737 ],
1738 },
c7121fa7
S
1739 {
1740 # The following content has been identified by the YouTube community
1741 # as inappropriate or offensive to some audiences.
1742 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1743 'info_dict': {
1744 'id': '6SJNVb0GnPI',
1745 'ext': 'mp4',
1746 'title': 'Race Differences in Intelligence',
1747 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1748 'duration': 965,
1749 'upload_date': '20140124',
1750 'uploader': 'New Century Foundation',
1751 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1752 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1753 },
1754 'params': {
1755 'skip_download': True,
1756 },
545cc85d 1757 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1758 },
022a5d66
S
1759 {
1760 # itag 212
1761 'url': '1t24XAntNCY',
1762 'only_matching': True,
fd5c4aab
S
1763 },
1764 {
1765 # geo restricted to JP
1766 'url': 'sJL6WA-aGkQ',
1767 'only_matching': True,
1768 },
cd5a74a2
S
1769 {
1770 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1771 'only_matching': True,
1772 },
bc2ca1bb 1773 {
1774 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1775 'only_matching': True,
1776 },
1777 {
1778 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1779 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1780 'only_matching': True,
1781 },
825cd268
RA
1782 {
1783 # DRM protected
1784 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1785 'only_matching': True,
4fe54c12
S
1786 },
1787 {
1788 # Video with unsupported adaptive stream type formats
1789 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1790 'info_dict': {
1791 'id': 'Z4Vy8R84T1U',
1792 'ext': 'mp4',
1793 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1794 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1795 'duration': 433,
1796 'upload_date': '20130923',
1797 'uploader': 'Amelia Putri Harwita',
1798 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1799 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1800 'formats': 'maxcount:10',
1801 },
1802 'params': {
1803 'skip_download': True,
1804 'youtube_include_dash_manifest': False,
1805 },
5429d6a9 1806 'skip': 'not actual anymore',
5caabd3c 1807 },
1808 {
822b9d9c 1809 # Youtube Music Auto-generated description
5caabd3c 1810 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1811 'info_dict': {
1812 'id': 'MgNrAu2pzNs',
1813 'ext': 'mp4',
1814 'title': 'Voyeur Girl',
1815 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1816 'upload_date': '20190312',
5429d6a9
S
1817 'uploader': 'Stephen - Topic',
1818 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1819 'artist': 'Stephen',
1820 'track': 'Voyeur Girl',
1821 'album': 'it\'s too much love to know my dear',
1822 'release_date': '20190313',
1823 'release_year': 2019,
976ae3ea 1824 'alt_title': 'Voyeur Girl',
1825 'view_count': int,
1826 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1827 'playable_in_embed': True,
1828 'like_count': int,
1829 'categories': ['Music'],
1830 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1831 'channel': 'Stephen',
1832 'availability': 'public',
1833 'creator': 'Stephen',
1834 'duration': 169,
1835 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1836 'age_limit': 0,
1837 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1838 'tags': 'count:11',
1839 'live_status': 'not_live',
6c73052c 1840 'channel_follower_count': int
5caabd3c 1841 },
1842 'params': {
1843 'skip_download': True,
1844 },
1845 },
66b48727
RA
1846 {
1847 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1848 'only_matching': True,
1849 },
011e75e6
S
1850 {
1851 # invalid -> valid video id redirection
1852 'url': 'DJztXj2GPfl',
1853 'info_dict': {
1854 'id': 'DJztXj2GPfk',
1855 'ext': 'mp4',
1856 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1857 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1858 'upload_date': '20090125',
1859 'uploader': 'Prochorowka',
1860 'uploader_id': 'Prochorowka',
1861 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1862 'artist': 'Panjabi MC',
1863 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1864 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1865 },
1866 'params': {
1867 'skip_download': True,
1868 },
545cc85d 1869 'skip': 'Video unavailable',
ea74e00b
DP
1870 },
1871 {
1872 # empty description results in an empty string
1873 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1874 'info_dict': {
1875 'id': 'x41yOUIvK2k',
1876 'ext': 'mp4',
1877 'title': 'IMG 3456',
1878 'description': '',
1879 'upload_date': '20170613',
1880 'uploader_id': 'ElevageOrVert',
1881 'uploader': 'ElevageOrVert',
976ae3ea 1882 'view_count': int,
1883 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1884 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1885 'like_count': int,
1886 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1887 'tags': [],
1888 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1889 'availability': 'public',
1890 'age_limit': 0,
1891 'categories': ['Pets & Animals'],
1892 'duration': 7,
1893 'playable_in_embed': True,
1894 'live_status': 'not_live',
1895 'channel': 'ElevageOrVert',
6c73052c 1896 'channel_follower_count': int
ea74e00b
DP
1897 },
1898 'params': {
1899 'skip_download': True,
1900 },
1901 },
a0566bbf 1902 {
29f7c58a 1903 # with '};' inside yt initial data (see [1])
1904 # see [2] for an example with '};' inside ytInitialPlayerResponse
1905 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1906 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1907 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1908 'info_dict': {
1909 'id': 'CHqg6qOn4no',
1910 'ext': 'mp4',
1911 'title': 'Part 77 Sort a list of simple types in c#',
1912 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1913 'upload_date': '20130831',
1914 'uploader_id': 'kudvenkat',
1915 'uploader': 'kudvenkat',
976ae3ea 1916 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1917 'like_count': int,
1918 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1919 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1920 'live_status': 'not_live',
1921 'categories': ['Education'],
1922 'availability': 'public',
1923 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1924 'tags': 'count:12',
1925 'playable_in_embed': True,
1926 'age_limit': 0,
1927 'view_count': int,
1928 'duration': 522,
1929 'channel': 'kudvenkat',
6c73052c 1930 'channel_follower_count': int
a0566bbf 1931 },
1932 'params': {
1933 'skip_download': True,
1934 },
1935 },
29f7c58a 1936 {
1937 # another example of '};' in ytInitialData
1938 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1939 'only_matching': True,
1940 },
1941 {
1942 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1943 'only_matching': True,
1944 },
545cc85d 1945 {
cc2db878 1946 # https://github.com/ytdl-org/youtube-dl/pull/28094
1947 'url': 'OtqTfy26tG0',
1948 'info_dict': {
1949 'id': 'OtqTfy26tG0',
1950 'ext': 'mp4',
1951 'title': 'Burn Out',
1952 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1953 'upload_date': '20141120',
1954 'uploader': 'The Cinematic Orchestra - Topic',
1955 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1956 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1957 'artist': 'The Cinematic Orchestra',
1958 'track': 'Burn Out',
1959 'album': 'Every Day',
976ae3ea 1960 'like_count': int,
1961 'live_status': 'not_live',
1962 'alt_title': 'Burn Out',
1963 'duration': 614,
1964 'age_limit': 0,
1965 'view_count': int,
1966 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1967 'creator': 'The Cinematic Orchestra',
1968 'channel': 'The Cinematic Orchestra',
1969 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1970 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1971 'availability': 'public',
1972 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1973 'categories': ['Music'],
1974 'playable_in_embed': True,
6c73052c 1975 'channel_follower_count': int
cc2db878 1976 },
1977 'params': {
1978 'skip_download': True,
1979 },
545cc85d 1980 },
bc2ca1bb 1981 {
1982 # controversial video, only works with bpctr when authenticated with cookies
1983 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1984 'only_matching': True,
1985 },
a1a7907b 1986 {
1987 # controversial video, requires bpctr/contentCheckOk
1988 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1989 'info_dict': {
1990 'id': 'SZJvDhaSDnc',
1991 'ext': 'mp4',
1992 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1993 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1994 'uploader': 'CBS Mornings',
11f9be09 1995 'uploader_id': 'CBSThisMorning',
a1a7907b 1996 'upload_date': '20140716',
976ae3ea 1997 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1998 'duration': 170,
1999 'categories': ['News & Politics'],
2000 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2001 'view_count': int,
2002 'channel': 'CBS Mornings',
2003 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2004 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2005 'age_limit': 18,
2006 'availability': 'needs_auth',
2007 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2008 'like_count': int,
2009 'live_status': 'not_live',
2010 'playable_in_embed': True,
6c73052c 2011 'channel_follower_count': int
a1a7907b 2012 }
2013 },
f7ad7160 2014 {
2015 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2016 'url': 'cBvYw8_A0vQ',
2017 'info_dict': {
2018 'id': 'cBvYw8_A0vQ',
2019 'ext': 'mp4',
2020 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2021 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2022 'upload_date': '20201120',
2023 'uploader': 'Walk around Japan',
2024 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2025 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2026 'duration': 1456,
2027 'categories': ['Travel & Events'],
2028 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2029 'view_count': int,
2030 'channel': 'Walk around Japan',
2031 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2032 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2033 'age_limit': 0,
2034 'availability': 'public',
2035 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2036 'live_status': 'not_live',
2037 'playable_in_embed': True,
6c73052c 2038 'channel_follower_count': int
f7ad7160 2039 },
2040 'params': {
2041 'skip_download': True,
2042 },
0fb983f6 2043 }, {
2044 # Has multiple audio streams
2045 'url': 'WaOKSUlf4TM',
2046 'only_matching': True
9297939e 2047 }, {
2048 # Requires Premium: has format 141 when requested using YTM url
2049 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2050 'only_matching': True
2051 }, {
120916da 2052 # multiple subtitles with same lang_code
2053 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2054 'only_matching': True,
109dd3b2 2055 }, {
2056 # Force use android client fallback
2057 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2058 'info_dict': {
2059 'id': 'YOelRv7fMxY',
11f9be09 2060 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2061 'ext': '3gp',
2062 'upload_date': '20210624',
2063 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2064 'uploader': 'colinfurze',
11f9be09 2065 'uploader_id': 'colinfurze',
109dd3b2 2066 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2067 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2068 'duration': 596,
2069 'categories': ['Entertainment'],
2070 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2071 'view_count': int,
2072 'channel': 'colinfurze',
2073 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2074 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2075 'age_limit': 0,
2076 'availability': 'public',
2077 'like_count': int,
2078 'live_status': 'not_live',
2079 'playable_in_embed': True,
6c73052c 2080 'channel_follower_count': int
109dd3b2 2081 },
2082 'params': {
2083 'format': '17', # 3gp format available on android
2084 'extractor_args': {'youtube': {'player_client': ['android']}},
2085 },
120916da 2086 },
109dd3b2 2087 {
2088 # Skip download of additional client configs (remix client config in this case)
2089 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2090 'only_matching': True,
2091 'params': {
2092 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2093 },
8fc54b12 2094 }, {
2095 # shorts
2096 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2097 'only_matching': True,
9222c381 2098 }, {
2099 'note': 'Storyboards',
2100 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2101 'info_dict': {
2102 'id': '5KLPxDtMqe8',
2103 'ext': 'mhtml',
2104 'format_id': 'sb0',
2105 'title': 'Your Brain is Plastic',
2106 'uploader_id': 'scishow',
2107 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2108 'upload_date': '20140324',
2109 'uploader': 'SciShow',
976ae3ea 2110 'like_count': int,
2111 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2112 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2113 'view_count': int,
2114 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2115 'playable_in_embed': True,
2116 'tags': 'count:12',
2117 'uploader_url': 'http://www.youtube.com/user/scishow',
2118 'availability': 'public',
2119 'channel': 'SciShow',
2120 'live_status': 'not_live',
2121 'duration': 248,
2122 'categories': ['Education'],
2123 'age_limit': 0,
6c73052c 2124 'channel_follower_count': int
9222c381 2125 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2126 }, {
2127 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2128 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2129 'info_dict': {
2130 'id': '2NUZ8W2llS4',
2131 'ext': 'mp4',
2132 'title': 'The NP that test your phone performance 🙂',
2133 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2134 'uploader': 'Leon Nguyen',
2135 'uploader_id': 'VNSXIII',
2136 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2137 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2138 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2139 'duration': 21,
2140 'view_count': int,
2141 'age_limit': 0,
2142 'categories': ['Gaming'],
2143 'tags': 'count:23',
2144 'playable_in_embed': True,
2145 'live_status': 'not_live',
2146 'upload_date': '20220103',
2147 'like_count': int,
2148 'availability': 'public',
2149 'channel': 'Leon Nguyen',
2150 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2151 'channel_follower_count': int
2152 }
2153 }, {
2154 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2155 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2156 'info_dict': {
2157 'id': 'mzZzzBU6lrM',
2158 'ext': 'mp4',
2159 'title': 'I Met GeorgeNotFound In Real Life...',
2160 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2161 'uploader': 'Quackity',
2162 'uploader_id': 'QuackityHQ',
2163 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2164 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2165 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2166 'duration': 955,
2167 'view_count': int,
2168 'age_limit': 0,
2169 'categories': ['Entertainment'],
2170 'tags': 'count:26',
2171 'playable_in_embed': True,
2172 'live_status': 'not_live',
2173 'release_timestamp': 1641172509,
2174 'release_date': '20220103',
2175 'upload_date': '20220103',
2176 'like_count': int,
2177 'availability': 'public',
2178 'channel': 'Quackity',
2179 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2180 'channel_follower_count': int
2181 }
2182 },
2183 { # continuous livestream. Microformat upload date should be preferred.
2184 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2185 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2186 'info_dict': {
2187 'id': 'kgx4WGK0oNU',
2188 '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}',
2189 'ext': 'mp4',
2190 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2191 'availability': 'public',
2192 'age_limit': 0,
2193 'release_timestamp': 1637975704,
2194 'upload_date': '20210619',
2195 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2196 'live_status': 'is_live',
2197 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2198 'uploader': '阿鲍Abao',
2199 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2200 'channel': 'Abao in Tokyo',
2201 'channel_follower_count': int,
2202 'release_date': '20211127',
2203 'tags': 'count:39',
2204 'categories': ['People & Blogs'],
2205 'like_count': int,
2206 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2207 'view_count': int,
2208 'playable_in_embed': True,
2209 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2210 },
2211 'params': {'skip_download': True}
6e634cbe 2212 }, {
2213 # Story. Requires specific player params to work.
2214 # Note: stories get removed after some period of time
ee27297f 2215 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2216 'info_dict': {
ee27297f 2217 'id': 'vv8qTUWmulI',
6e634cbe 2218 'ext': 'mp4',
ee27297f 2219 'availability': 'unlisted',
2220 'view_count': int,
2221 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2222 'upload_date': '20220526',
2223 'categories': ['Education'],
2224 'title': 'Story',
2225 'channel': 'IT\'S HISTORY',
2226 'description': '',
2227 'uploader_id': 'BlastfromthePast',
2228 'duration': 12,
2229 'uploader': 'IT\'S HISTORY',
6e634cbe 2230 'playable_in_embed': True,
6e634cbe 2231 'age_limit': 0,
6e634cbe 2232 'live_status': 'not_live',
ee27297f 2233 'tags': [],
2234 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2235 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2236 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2237 }
2238 }, {
2239 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2240 'info_dict': {
2241 'id': 'tjjjtzRLHvA',
2242 'ext': 'mp4',
2243 'title': 'ハッシュタグ無し };if window.ytcsi',
2244 'upload_date': '20220323',
2245 'like_count': int,
2246 'availability': 'unlisted',
2247 'channel': 'nao20010128nao',
2248 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2249 'age_limit': 0,
2250 'uploader': 'nao20010128nao',
2251 'uploader_id': 'nao20010128nao',
2252 'categories': ['Music'],
6e634cbe 2253 'view_count': int,
2254 'description': '',
ee27297f 2255 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2256 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2257 'live_status': 'not_live',
2258 'playable_in_embed': True,
2259 'channel_follower_count': int,
2260 'duration': 6,
2261 'tags': [],
2262 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2263 }
2264 }
2eb88d95
PH
2265 ]
2266
201c1459 2267 @classmethod
2268 def suitable(cls, url):
4dfbf869 2269 from ..utils import parse_qs
2270
201c1459 2271 qs = parse_qs(url)
2272 if qs.get('list', [None])[0]:
2273 return False
86e5f3ed 2274 return super().suitable(url)
201c1459 2275
e0df6211 2276 def __init__(self, *args, **kwargs):
86e5f3ed 2277 super().__init__(*args, **kwargs)
545cc85d 2278 self._code_cache = {}
83799698 2279 self._player_cache = {}
e0df6211 2280
adbc4ec4 2281 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2282 lock = threading.Lock()
2283
2284 is_live = True
185bf310 2285 start_time = time.time()
adbc4ec4
THD
2286 formats = [f for f in formats if f.get('is_from_start')]
2287
185bf310 2288 def refetch_manifest(format_id, delay):
2289 nonlocal formats, start_time, is_live
2290 if time.time() <= start_time + delay:
adbc4ec4
THD
2291 return
2292
2293 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2294 video_details = traverse_obj(
2295 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2296 microformats = traverse_obj(
2297 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2298 expected_type=dict, default=[])
2299 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2300 start_time = time.time()
adbc4ec4 2301
185bf310 2302 def mpd_feed(format_id, delay):
adbc4ec4
THD
2303 """
2304 @returns (manifest_url, manifest_stream_number, is_live) or None
2305 """
2306 with lock:
185bf310 2307 refetch_manifest(format_id, delay)
adbc4ec4
THD
2308
2309 f = next((f for f in formats if f['format_id'] == format_id), None)
2310 if not f:
185bf310 2311 if not is_live:
2312 self.to_screen(f'{video_id}: Video is no longer live')
2313 else:
2314 self.report_warning(
2315 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2316 return None
2317 return f['manifest_url'], f['manifest_stream_number'], is_live
2318
2319 for f in formats:
a539f065 2320 f['is_live'] = True
adbc4ec4
THD
2321 f['protocol'] = 'http_dash_segments_generator'
2322 f['fragments'] = functools.partial(
2323 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2324
2325 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2326 FETCH_SPAN, MAX_DURATION = 5, 432000
2327
2328 mpd_url, stream_number, is_live = None, None, True
2329
2330 begin_index = 0
2331 download_start_time = ctx.get('start') or time.time()
2332
2333 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2334 if lack_early_segments:
2335 self.report_warning(bug_reports_message(
2336 'Starting download from the last 120 hours of the live stream since '
2337 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2338 lack_early_segments = True
2339
2340 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2341 fragments, fragment_base_url = None, None
2342
a539f065 2343 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2344 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2345 # Obtain from MPD's maximum seq value
2346 old_mpd_url = mpd_url
185bf310 2347 last_error = ctx.pop('last_error', None)
a539f065 2348 expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
185bf310 2349 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2350 or (mpd_url, stream_number, False))
2351 if not refresh_sequence:
2352 if expire_fast and not is_live:
2353 return False, last_seq
2354 elif old_mpd_url == mpd_url:
2355 return True, last_seq
adbc4ec4
THD
2356 try:
2357 fmts, _ = self._extract_mpd_formats_and_subtitles(
2358 mpd_url, None, note=False, errnote=False, fatal=False)
2359 except ExtractorError:
2360 fmts = None
2361 if not fmts:
a539f065 2362 no_fragment_score += 2
adbc4ec4
THD
2363 return False, last_seq
2364 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2365 fragments = fmt_info['fragments']
2366 fragment_base_url = fmt_info['fragment_base_url']
2367 assert fragment_base_url
2368
2369 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2370 return True, _last_seq
2371
2372 while is_live:
2373 fetch_time = time.time()
2374 if no_fragment_score > 30:
2375 return
2376 if last_segment_url:
2377 # Obtain from "X-Head-Seqnum" header value from each segment
2378 try:
2379 urlh = self._request_webpage(
2380 last_segment_url, None, note=False, errnote=False, fatal=False)
2381 except ExtractorError:
2382 urlh = None
2383 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2384 if last_seq is None:
a539f065 2385 no_fragment_score += 2
adbc4ec4
THD
2386 last_segment_url = None
2387 continue
2388 else:
a539f065
LNO
2389 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2390 no_fragment_score += 2
185bf310 2391 if not should_continue:
adbc4ec4
THD
2392 continue
2393
2394 if known_idx > last_seq:
2395 last_segment_url = None
2396 continue
2397
2398 last_seq += 1
2399
2400 if begin_index < 0 and known_idx < 0:
2401 # skip from the start when it's negative value
2402 known_idx = last_seq + begin_index
2403 if lack_early_segments:
2404 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2405 try:
2406 for idx in range(known_idx, last_seq):
2407 # do not update sequence here or you'll get skipped some part of it
a539f065 2408 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2409 if not should_continue:
adbc4ec4
THD
2410 known_idx = idx - 1
2411 raise ExtractorError('breaking out of outer loop')
2412 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2413 yield {
2414 'url': last_segment_url,
36195c44 2415 'fragment_count': last_seq,
adbc4ec4
THD
2416 }
2417 if known_idx == last_seq:
2418 no_fragment_score += 5
2419 else:
2420 no_fragment_score = 0
2421 known_idx = last_seq
2422 except ExtractorError:
2423 continue
2424
2425 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2426
b6de707d 2427 def _extract_player_url(self, *ytcfgs, webpage=None):
2428 player_url = traverse_obj(
2429 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2430 get_all=False, expected_type=compat_str)
11f9be09 2431 if not player_url:
b6de707d 2432 return
60f393e4 2433 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2434
b6de707d 2435 def _download_player_url(self, video_id, fatal=False):
2436 res = self._download_webpage(
2437 'https://www.youtube.com/iframe_api',
2438 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2439 if res:
2440 player_version = self._search_regex(
2441 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2442 if player_version:
2443 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2444
60064c53
PH
2445 def _signature_cache_id(self, example_sig):
2446 """ Return a string representation of a signature """
78caa52a 2447 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 2448
e40c758c
S
2449 @classmethod
2450 def _extract_player_info(cls, player_url):
2451 for player_re in cls._PLAYER_INFO_RE:
2452 id_m = re.search(player_re, player_url)
2453 if id_m:
2454 break
2455 else:
c081b35c 2456 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2457 return id_m.group('id')
e40c758c 2458
404f611f 2459 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2460 player_id = self._extract_player_info(player_url)
2461 if player_id not in self._code_cache:
1276a43a 2462 code = self._download_webpage(
109dd3b2 2463 player_url, video_id, fatal=fatal,
2464 note='Downloading player ' + player_id,
2465 errnote='Download of %s failed' % player_url)
1276a43a 2466 if code:
2467 self._code_cache[player_id] = code
404f611f 2468 return self._code_cache.get(player_id)
109dd3b2 2469
e40c758c 2470 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2471 player_id = self._extract_player_info(player_url)
e0df6211 2472
c4417ddb 2473 # Read from filesystem cache
86e5f3ed 2474 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2475 assert os.path.basename(func_id) == func_id
a0e07d31 2476
9809740b 2477 cache_spec = self.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2478 if cache_spec is not None:
78caa52a 2479 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2480
404f611f 2481 code = self._load_player(video_id, player_url)
2482 if code:
109dd3b2 2483 res = self._parse_sig_js(code)
e0df6211 2484
ac668111 2485 test_string = ''.join(map(chr, range(len(example_sig))))
109dd3b2 2486 cache_res = res(test_string)
2487 cache_spec = [ord(c) for c in cache_res]
83799698 2488
9809740b 2489 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
109dd3b2 2490 return res
83799698 2491
60064c53 2492 def _print_sig_code(self, func, example_sig):
404f611f 2493 if not self.get_param('youtube_print_sig_code'):
2494 return
2495
edf3e38e
PH
2496 def gen_sig_code(idxs):
2497 def _genslice(start, end, step):
78caa52a 2498 starts = '' if start == 0 else str(start)
8bcc8756 2499 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2500 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2501 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2502
2503 step = None
7af808a5
PH
2504 # Quelch pyflakes warnings - start will be set when step is set
2505 start = '(Never used)'
edf3e38e
PH
2506 for i, prev in zip(idxs[1:], idxs[:-1]):
2507 if step is not None:
2508 if i - prev == step:
2509 continue
2510 yield _genslice(start, prev, step)
2511 step = None
2512 continue
2513 if i - prev in [-1, 1]:
2514 step = i - prev
2515 start = prev
2516 continue
2517 else:
78caa52a 2518 yield 's[%d]' % prev
edf3e38e 2519 if step is None:
78caa52a 2520 yield 's[%d]' % i
edf3e38e
PH
2521 else:
2522 yield _genslice(start, i, step)
2523
ac668111 2524 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2525 cache_res = func(test_string)
edf3e38e 2526 cache_spec = [ord(c) for c in cache_res]
78caa52a 2527 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
2528 signature_id_tuple = '(%s)' % (
2529 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2530 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2531 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2532 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2533
e0df6211
PH
2534 def _parse_sig_js(self, jscode):
2535 funcname = self._search_regex(
abefc03f
S
2536 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2537 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
2538 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2539 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2540 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}\(a,\d+\)',
2541 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 2542 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2543 # Obsolete patterns
2544 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2545 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2546 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2547 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2548 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2549 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2550 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2551 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2552 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2553
2554 jsi = JSInterpreter(jscode)
2555 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2556 return lambda s: initial_function([s])
2557
545cc85d 2558 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2559 """Turn the encrypted s field into a working signature"""
c8bf86d5 2560 try:
62af3a0e 2561 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5 2562 if player_id not in self._player_cache:
52023f12 2563 func = self._extract_signature_function(video_id, player_url, s)
c8bf86d5
PH
2564 self._player_cache[player_id] = func
2565 func = self._player_cache[player_id]
404f611f 2566 self._print_sig_code(func, s)
c8bf86d5
PH
2567 return func(s)
2568 except Exception as e:
52023f12 2569 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2570
2571 def _decrypt_nsig(self, s, video_id, player_url):
2572 """Turn the encrypted n field into a working signature"""
2573 if player_url is None:
2574 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2575 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2576
2577 sig_id = ('nsig_value', s)
2578 if sig_id in self._player_cache:
2579 return self._player_cache[sig_id]
2580
2581 try:
2582 player_id = ('nsig', player_url)
2583 if player_id not in self._player_cache:
2584 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2585 func = self._player_cache[player_id]
2586 self._player_cache[sig_id] = func(s)
2587 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2588 return self._player_cache[sig_id]
2589 except Exception as e:
aa9369a2 2590 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2591
2592 def _extract_n_function_name(self, jscode):
48416bc4 2593 nfunc, idx = self._search_regex(
c571b3a6 2594 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2595 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2596 if not idx:
2597 return nfunc
2598 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2599 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2600 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2601
2602 def _extract_n_function(self, video_id, player_url):
2603 player_id = self._extract_player_info(player_url)
9809740b 2604 func_code = self.cache.load('youtube-nsig', player_id)
404f611f 2605
2606 if func_code:
2607 jsi = JSInterpreter(func_code)
2608 else:
2609 jscode = self._load_player(video_id, player_url)
2610 funcname = self._extract_n_function_name(jscode)
2611 jsi = JSInterpreter(jscode)
2612 func_code = jsi.extract_function_code(funcname)
9809740b 2613 self.cache.store('youtube-nsig', player_id, func_code)
404f611f 2614
2615 if self.get_param('youtube_print_sig_code'):
2616 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2617
2618 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2619
109dd3b2 2620 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2621 """
2622 Extract signatureTimestamp (sts)
2623 Required to tell API what sig/player version is in use.
2624 """
2625 sts = None
2626 if isinstance(ytcfg, dict):
2627 sts = int_or_none(ytcfg.get('STS'))
2628
2629 if not sts:
2630 # Attempt to extract from player
2631 if player_url is None:
2632 error_msg = 'Cannot extract signature timestamp without player_url.'
2633 if fatal:
2634 raise ExtractorError(error_msg)
2635 self.report_warning(error_msg)
2636 return
404f611f 2637 code = self._load_player(video_id, player_url, fatal=fatal)
2638 if code:
109dd3b2 2639 sts = int_or_none(self._search_regex(
2640 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2641 'JS player signature timestamp', group='sts', fatal=fatal))
2642 return sts
2643
11f9be09 2644 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
2645 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2646 label = 'fully ' if is_full else ''
2647 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2648 expected_type=url_or_none)
2649 if not url:
2650 self.report_warning(f'Unable to mark {label}watched')
2651 return
2652 parsed_url = compat_urlparse.urlparse(url)
2653 qs = compat_urlparse.parse_qs(parsed_url.query)
2654
2655 # cpn generation algorithm is reverse engineered from base.js.
2656 # In fact it works even with dummy cpn.
2657 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2658 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2659
2660 # # more consistent results setting it to right before the end
2661 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2662
2663 qs.update({
2664 'ver': ['2'],
2665 'cpn': [cpn],
2666 'cmt': video_length,
2667 'el': 'detailpage', # otherwise defaults to "shorts"
2668 })
2669
2670 if is_full:
2671 # these seem to mark watchtime "history" in the real world
2672 # they're required, so send in a single value
2673 qs.update({
2674 'st': video_length,
2675 'et': video_length,
2676 })
2677
2678 url = compat_urlparse.urlunparse(
2679 parsed_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
2680
2681 self._download_webpage(
2682 url, video_id, f'Marking {label}watched',
2683 'Unable to mark watched', fatal=False)
d77ab8e2 2684
66c9fa36
S
2685 @staticmethod
2686 def _extract_urls(webpage):
2687 # Embedded YouTube player
2688 entries = [
2689 unescapeHTML(mobj.group('url'))
2690 for mobj in re.finditer(r'''(?x)
2691 (?:
2692 <iframe[^>]+?src=|
2693 data-video-url=|
2694 <embed[^>]+?src=|
2695 embedSWF\(?:\s*|
2696 <object[^>]+data=|
2697 new\s+SWFObject\(
2698 )
2699 (["\'])
2700 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2701 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2702 \1''', webpage)]
2703
2704 # lazyYT YouTube embed
2705 entries.extend(list(map(
2706 unescapeHTML,
2707 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2708
2709 # Wordpress "YouTube Video Importer" plugin
2710 matches = re.findall(r'''(?x)<div[^>]+
2711 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2712 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2713 entries.extend(m[-1] for m in matches)
2714
2715 return entries
2716
2717 @staticmethod
2718 def _extract_url(webpage):
2719 urls = YoutubeIE._extract_urls(webpage)
2720 return urls[0] if urls else None
2721
97665381
PH
2722 @classmethod
2723 def extract_id(cls, url):
2724 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 2725 if mobj is None:
69ea8ca4 2726 raise ExtractorError('Invalid URL: %s' % url)
5ad28e7f 2727 return mobj.group('id')
c5e8d7af 2728
7c365c21 2729 def _extract_chapters_from_json(self, data, duration):
2730 chapter_list = traverse_obj(
2731 data, (
2732 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2733 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2734 ), expected_type=list)
2735
2736 return self._extract_chapters(
2737 chapter_list,
2738 chapter_time=lambda chapter: float_or_none(
2739 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2740 chapter_title=lambda chapter: traverse_obj(
2741 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2742 duration=duration)
2743
2744 def _extract_chapters_from_engagement_panel(self, data, duration):
2745 content_list = traverse_obj(
8bdd16b4 2746 data,
7c365c21 2747 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2748 expected_type=list, default=[])
052e1350 2749 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2750 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2751
1890fc63 2752 return next(filter(None, (
2753 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2754 chapter_time, chapter_title, duration)
2755 for contents in content_list)), [])
7c365c21 2756
1890fc63 2757 def _extract_chapters_from_description(self, description, duration):
2758 return self._extract_chapters(
2759 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2760 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2761 duration=duration, strict=False)
84213ea8 2762
1890fc63 2763 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2764 if not duration:
2765 return
2766 chapter_list = [{
2767 'start_time': chapter_time(chapter),
2768 'title': chapter_title(chapter),
2769 } for chapter in chapter_list or []]
2770 if not strict:
2771 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2772
2773 chapters = [{'start_time': 0, 'title': '<Untitled>'}]
2774 for idx, chapter in enumerate(chapter_list):
2775 if chapter['start_time'] is None or not chapter['title']:
2776 self.report_warning(f'Incomplete chapter {idx}')
2777 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
2778 chapters[-1]['end_time'] = chapter['start_time']
2779 chapters.append(chapter)
2780 else:
2781 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}"')
2782 chapters[-1]['end_time'] = duration
2783 return chapters if len(chapters) > 1 and chapters[1]['start_time'] else chapters[1:]
84213ea8 2784
a1c5d2ca
M
2785 def _extract_comment(self, comment_renderer, parent=None):
2786 comment_id = comment_renderer.get('commentId')
2787 if not comment_id:
2788 return
fe93e2c4 2789
052e1350 2790 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2791
49bd8c66 2792 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2793 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2794 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2795 author_id = try_get(comment_renderer,
2796 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2797
49bd8c66 2798 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2799 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2800 author_thumbnail = try_get(comment_renderer,
2801 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2802
2803 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2804 is_favorited = 'creatorHeart' in (try_get(
2805 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2806 return {
2807 'id': comment_id,
2808 'text': text,
d92f5d5a 2809 'timestamp': timestamp,
a1c5d2ca
M
2810 'time_text': time_text,
2811 'like_count': votes,
97524332 2812 'is_favorited': is_favorited,
a1c5d2ca
M
2813 'author': author,
2814 'author_id': author_id,
2815 'author_thumbnail': author_thumbnail,
2816 'author_is_uploader': author_is_uploader,
2817 'parent': parent or 'root'
2818 }
2819
46383212 2820 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2821
2822 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2823
2824 def extract_header(contents):
2d6659b9 2825 _continuation = None
2826 for content in contents:
46383212 2827 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2828 expected_comment_count = self._get_count(
2829 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2830
2d6659b9 2831 if expected_comment_count:
46383212 2832 tracker['est_total'] = expected_comment_count
2833 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2834 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2835
2836 sort_menu_item = try_get(
2837 comments_header_renderer,
2838 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2839 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2840
2841 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2842 if not _continuation:
2843 continue
2844
46383212 2845 sort_text = str_or_none(sort_menu_item.get('title'))
2846 if not sort_text:
2d6659b9 2847 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2848 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2849 break
a2160aa4 2850 return _continuation
a1c5d2ca 2851
2d6659b9 2852 def extract_thread(contents):
a1c5d2ca 2853 if not parent:
46383212 2854 tracker['current_page_thread'] = 0
a1c5d2ca 2855 for content in contents:
46383212 2856 if not parent and tracker['total_parent_comments'] >= max_parents:
2857 yield
a1c5d2ca 2858 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2859 comment_renderer = get_first(
2860 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2861 expected_type=dict, default={})
a1c5d2ca 2862
a1c5d2ca
M
2863 comment = self._extract_comment(comment_renderer, parent)
2864 if not comment:
2865 continue
46383212 2866
2867 tracker['running_total'] += 1
2868 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2869 yield comment
46383212 2870
a1c5d2ca
M
2871 # Attempt to get the replies
2872 comment_replies_renderer = try_get(
2873 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2874
2875 if comment_replies_renderer:
46383212 2876 tracker['current_page_thread'] += 1
a1c5d2ca 2877 comment_entries_iter = self._comment_entries(
99e9e001 2878 comment_replies_renderer, ytcfg, video_id,
46383212 2879 parent=comment.get('id'), tracker=tracker)
86e5f3ed 2880 yield from itertools.islice(comment_entries_iter, min(
2881 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 2882
46383212 2883 # Keeps track of counts across recursive calls
2884 if not tracker:
2885 tracker = dict(
2886 running_total=0,
2887 est_total=0,
2888 current_page_thread=0,
2889 total_parent_comments=0,
2890 total_reply_comments=0)
2891
2892 # TODO: Deprecated
2d6659b9 2893 # YouTube comments have a max depth of 2
46383212 2894 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2895 if max_depth:
2896 self._downloader.deprecation_warning(
2897 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2898 if max_depth == 1 and parent:
2899 return
a1c5d2ca 2900
46383212 2901 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2902 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2903
46383212 2904 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2905
46383212 2906 response = None
6e634cbe 2907 is_forced_continuation = False
2d6659b9 2908 is_first_continuation = parent is None
6e634cbe 2909 if is_first_continuation and not continuation:
2910 # Sometimes you can get comments by generating the continuation yourself,
2911 # even if YouTube initially reports them being disabled - e.g. stories comments.
2912 # Note: if the comment section is actually disabled, YouTube may return a response with
2913 # required check_get_keys missing. So we will disable that check initially in this case.
2914 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2915 is_forced_continuation = True
a1c5d2ca
M
2916
2917 for page_num in itertools.count(0):
2918 if not continuation:
2919 break
46383212 2920 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2921 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2922 if page_num == 0:
2923 if is_first_continuation:
2924 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2925 else:
2d6659b9 2926 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2927 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2928 else:
2929 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2930 ' ' if parent else '', ' replies' if parent else '',
2931 page_num, comment_prog_str)
2932
2933 response = self._extract_response(
fe93e2c4 2934 item_id=None, query=continuation,
2d6659b9 2935 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
6e634cbe 2936 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2937 is_forced_continuation = False
46383212 2938 continuation_contents = traverse_obj(
2939 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2940
2d6659b9 2941 continuation = None
46383212 2942 for continuation_section in continuation_contents:
2943 continuation_items = traverse_obj(
2944 continuation_section,
2945 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2946 get_all=False, expected_type=list) or []
2947 if is_first_continuation:
2948 continuation = extract_header(continuation_items)
2949 is_first_continuation = False
2d6659b9 2950 if continuation:
a1c5d2ca 2951 break
46383212 2952 continue
a1c5d2ca 2953
46383212 2954 for entry in extract_thread(continuation_items):
2955 if not entry:
2956 return
2957 yield entry
2958 continuation = self._extract_continuation({'contents': continuation_items})
2959 if continuation:
2d6659b9 2960 break
a1c5d2ca 2961
6e634cbe 2962 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2963 if message and not parent and tracker['running_total'] == 0:
2964 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
2965
2966 @staticmethod
2967 def _generate_comment_continuation(video_id):
2968 """
2969 Generates initial comment section continuation token from given video id
2970 """
2971 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
2972 return base64.b64encode(token.encode()).decode()
2973
a2160aa4 2974 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2975 """Entry for comment extraction"""
2d6659b9 2976 def _real_comment_extract(contents):
aae16f6e 2977 renderer = next((
2978 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2979 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2980 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2981
a2160aa4 2982 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2983 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2984
109dd3b2 2985 @staticmethod
99e9e001 2986 def _get_checkok_params():
2987 return {'contentCheckOk': True, 'racyCheckOk': True}
2988
2989 @classmethod
2990 def _generate_player_context(cls, sts=None):
109dd3b2 2991 context = {
2992 'html5Preference': 'HTML5_PREF_WANTS',
2993 }
2994 if sts is not None:
2995 context['signatureTimestamp'] = sts
2996 return {
2997 'playbackContext': {
2998 'contentPlaybackContext': context
a1a7907b 2999 },
99e9e001 3000 **cls._get_checkok_params()
109dd3b2 3001 }
3002
e7e94f2a
D
3003 @staticmethod
3004 def _is_agegated(player_response):
3005 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3006 return True
e7e94f2a
D
3007
3008 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3009 AGE_GATE_REASONS = (
3010 'confirm your age', 'age-restricted', 'inappropriate', # reason
3011 'age_verification_required', 'age_check_required', # status
3012 )
3013 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3014
3015 @staticmethod
3016 def _is_unplayable(player_response):
3017 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3018
99e9e001 3019 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 3020
11f9be09 3021 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3022 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3023 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3024 headers = self.generate_api_headers(
99e9e001 3025 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3026
6e634cbe 3027 yt_query = {
3028 'videoId': video_id,
3029 'params': '8AEB' # enable stories
3030 }
11f9be09 3031 yt_query.update(self._generate_player_context(sts))
3032 return self._extract_response(
3033 item_id=video_id, ep='player', query=yt_query,
379e44ed 3034 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3035 default_client=client,
11f9be09 3036 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3037 ) or None
3038
11f9be09 3039 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3040 requested_clients = []
d0d012d4 3041 default = ['android', 'web']
000c15a4 3042 allowed_clients = sorted(
86e5f3ed 3043 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3044 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3045 for client in self._configuration_arg('player_client'):
3046 if client in allowed_clients:
3047 requested_clients.append(client)
d0d012d4 3048 elif client == 'default':
3049 requested_clients.extend(default)
b4c055ba 3050 elif client == 'all':
3051 requested_clients.extend(allowed_clients)
3052 else:
3053 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3054 if not requested_clients:
d0d012d4 3055 requested_clients = default
cf7e015f 3056
11f9be09 3057 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3058 requested_clients.extend(
e7e94f2a 3059 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3060
11f9be09 3061 return orderedSet(requested_clients)
cf7e015f 3062
99e9e001 3063 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 3064 initial_pr = None
3065 if webpage:
b7c47b74 3066 initial_pr = self._search_json(
3067 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3068
ae729626 3069 all_clients = set(clients)
c0bc527b 3070 clients = clients[::-1]
b6de707d 3071 prs = []
e7e94f2a 3072
ae729626 3073 def append_client(*client_names):
e7870111 3074 """ Append the first client name that exists but not already used """
ae729626 3075 for client_name in client_names:
e7870111
D
3076 actual_client = _split_innertube_client(client_name)[0]
3077 if actual_client in INNERTUBE_CLIENTS:
3078 if actual_client not in all_clients:
ae729626 3079 clients.append(client_name)
e7870111
D
3080 all_clients.add(actual_client)
3081 return
e7e94f2a 3082
379e44ed 3083 # Android player_response does not have microFormats which are needed for
3084 # extraction of some data. So we return the initial_pr with formats
3085 # stripped out even if not requested by the user
3086 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3087 if initial_pr:
3088 pr = dict(initial_pr)
3089 pr['streamingData'] = None
b6de707d 3090 prs.append(pr)
379e44ed 3091
3092 last_error = None
b6de707d 3093 tried_iframe_fallback = False
3094 player_url = None
c0bc527b 3095 while clients:
e7870111 3096 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3097 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3098 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3099 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3100
b6de707d 3101 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3102 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3103 if 'js' in self._configuration_arg('player_skip'):
3104 require_js_player = False
3105 player_url = None
3106
3107 if not player_url and not tried_iframe_fallback and require_js_player:
3108 player_url = self._download_player_url(video_id)
3109 tried_iframe_fallback = True
3110
379e44ed 3111 try:
3112 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 3113 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 3114 except ExtractorError as e:
3115 if last_error:
3116 self.report_warning(last_error)
3117 last_error = e
3118 continue
3119
11f9be09 3120 if pr:
b6de707d 3121 prs.append(pr)
c0bc527b 3122
e7e94f2a 3123 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3124 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3125 append_client(f'{base_client}_creator')
e7e94f2a 3126 elif self._is_agegated(pr):
e7870111
D
3127 if variant == 'tv_embedded':
3128 append_client(f'{base_client}_embedded')
3129 elif not variant:
3130 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3131
379e44ed 3132 if last_error:
b6de707d 3133 if not len(prs):
379e44ed 3134 raise last_error
3135 self.report_warning(last_error)
b6de707d 3136 return prs, player_url
11f9be09 3137
a1b2d843 3138 def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3139 itags, stream_ids = {}, []
2a9c6dcd 3140 itag_qualities, res_qualities = {}, {}
d3fc8074 3141 q = qualities([
2a9c6dcd 3142 # Normally tiny is the smallest video-only formats. But
3143 # audio-only formats with unknown quality may get tagged as tiny
3144 'tiny',
3145 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3146 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3147 ])
11f9be09 3148 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3149
545cc85d 3150 for fmt in streaming_formats:
727029c5 3151 if fmt.get('targetDurationSec'):
545cc85d 3152 continue
321bf820 3153
cc2db878 3154 itag = str_or_none(fmt.get('itag'))
9297939e 3155 audio_track = fmt.get('audioTrack') or {}
3156 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3157 if stream_id in stream_ids:
3158 continue
3159
cc2db878 3160 quality = fmt.get('quality')
2a9c6dcd 3161 height = int_or_none(fmt.get('height'))
d3fc8074 3162 if quality == 'tiny' or not quality:
3163 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3164 # The 3gp format (17) in android client has a quality of "small",
3165 # but is actually worse than other formats
3166 if itag == '17':
3167 quality = 'tiny'
3168 if quality:
3169 if itag:
3170 itag_qualities[itag] = quality
3171 if height:
3172 res_qualities[height] = quality
cc2db878 3173 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3174 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3175 # number of fragment that would subsequently requested with (`&sq=N`)
3176 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3177 continue
3178
545cc85d 3179 fmt_url = fmt.get('url')
3180 if not fmt_url:
3181 sc = compat_parse_qs(fmt.get('signatureCipher'))
3182 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3183 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3184 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3185 continue
52023f12 3186 try:
3187 fmt_url += '&%s=%s' % (
3188 traverse_obj(sc, ('sp', -1)) or 'signature',
3189 self._decrypt_signature(encrypted_sig, video_id, player_url)
3190 )
3191 except ExtractorError as e:
3192 self.report_warning('Signature extraction failed: Some formats may be missing', only_once=True)
3193 self.write_debug(e, only_once=True)
201e9eaa 3194 continue
545cc85d 3195
404f611f 3196 query = parse_qs(fmt_url)
3197 throttled = False
b2916526 3198 if query.get('n'):
404f611f 3199 try:
3200 fmt_url = update_url_query(fmt_url, {
3201 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3202 except ExtractorError as e:
aa9369a2 3203 self.report_warning(
1d485a1a 3204 'nsig extraction failed: You may experience throttling for some formats\n'
52023f12 3205 f'n = {query["n"][0]} ; player = {player_url}', only_once=True)
3206 self.write_debug(e, only_once=True)
404f611f 3207 throttled = True
3208
545cc85d 3209 if itag:
a0bb6ce5 3210 itags[itag] = 'https'
9297939e 3211 stream_ids.append(stream_id)
3212
0ad92dfb 3213 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3214 language_preference = (
3215 10 if audio_track.get('audioIsDefault') and 10
3216 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3217 else -1)
0ad92dfb 3218 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3219 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3220 # Make sure to avoid false positives with small duration differences.
3221 # Eg: __2ABJjxzNo, ySuUZEjARPY
3222 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3223 if is_damaged:
0f06bcd7 3224 self.report_warning(
3225 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3226 dct = {
3227 'asr': int_or_none(fmt.get('audioSampleRate')),
3228 'filesize': int_or_none(fmt.get('contentLength')),
3229 'format_id': itag,
34921b43 3230 'format_note': join_nonempty(
26e8e044 3231 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3232 ' (default)' if language_preference > 0 else ''),
404f611f 3233 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
0ad92dfb 3234 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3235 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3236 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3237 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3238 'height': height,
dca3ff4a 3239 'quality': q(quality),
727029c5 3240 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3241 'tbr': tbr,
545cc85d 3242 'url': fmt_url,
2a9c6dcd 3243 'width': int_or_none(fmt.get('width')),
ab6df717 3244 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3245 'desc' if language_preference < -1 else ''),
3246 'language_preference': language_preference,
a405b38f 3247 # Strictly de-prioritize damaged and 3gp formats
3248 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3249 }
60bdb7bd 3250 mime_mobj = re.match(
3251 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3252 if mime_mobj:
3253 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3254 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3255 no_audio = dct.get('acodec') == 'none'
3256 no_video = dct.get('vcodec') == 'none'
3257 if no_audio:
3258 dct['vbr'] = tbr
3259 if no_video:
3260 dct['abr'] = tbr
3261 if no_audio or no_video:
545cc85d 3262 dct['downloader_options'] = {
3263 # Youtube throttles chunks >~10M
3264 'http_chunk_size': 10485760,
bf1317d2 3265 }
7c60c33e 3266 if dct.get('ext'):
3267 dct['container'] = dct['ext'] + '_dash'
11f9be09 3268 yield dct
545cc85d 3269
adbc4ec4 3270 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3271 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3272 if not self.get_param('youtube_include_hls_manifest', True):
3273 skip_manifests.append('hls')
0f06bcd7 3274 if not self.get_param('youtube_include_dash_manifest', True):
3275 skip_manifests.append('dash')
adbc4ec4
THD
3276 get_dash = 'dash' not in skip_manifests and (
3277 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3278 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3279
a0bb6ce5 3280 def process_manifest_format(f, proto, itag):
3281 if itag in itags:
3282 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3283 return False
3284 itag = f'{itag}-{proto}'
3285 if itag:
3286 f['format_id'] = itag
3287 itags[itag] = proto
3288
3289 f['quality'] = next((
3290 q(qdict[val])
e339d25a 3291 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3292 if val in qdict), -1)
3293 return True
2a9c6dcd 3294
11f9be09 3295 for sd in streaming_data:
5d3a0e79 3296 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3297 if hls_manifest_url:
2a9c6dcd 3298 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 3299 if process_manifest_format(f, 'hls', self._search_regex(
3300 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3301 yield f
545cc85d 3302
5d3a0e79 3303 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3304 if dash_manifest_url:
2a9c6dcd 3305 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 3306 if process_manifest_format(f, 'dash', f['format_id']):
3307 f['filesize'] = int_or_none(self._search_regex(
3308 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3309 if live_from_start:
3310 f['is_from_start'] = True
3311
a0bb6ce5 3312 yield f
11f9be09 3313
720c3099 3314 def _extract_storyboard(self, player_responses, duration):
3315 spec = get_first(
3316 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3317 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3318 if not base_url:
720c3099 3319 return
720c3099 3320 L = len(spec) - 1
3321 for i, args in enumerate(spec):
3322 args = args.split('#')
3323 counts = list(map(int_or_none, args[:5]))
3324 if len(args) != 8 or not all(counts):
3325 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3326 continue
3327 width, height, frame_count, cols, rows = counts
3328 N, sigh = args[6:]
3329
3330 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3331 fragment_count = frame_count / (cols * rows)
3332 fragment_duration = duration / fragment_count
3333 yield {
3334 'format_id': f'sb{i}',
3335 'format_note': 'storyboard',
3336 'ext': 'mhtml',
3337 'protocol': 'mhtml',
3338 'acodec': 'none',
3339 'vcodec': 'none',
3340 'url': url,
3341 'width': width,
3342 'height': height,
3343 'fragments': [{
b3edc806 3344 'url': url.replace('$M', str(j)),
720c3099 3345 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3346 } for j in range(math.ceil(fragment_count))],
3347 }
3348
adbc4ec4 3349 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3350 webpage = None
3351 if 'webpage' not in self._configuration_arg('player_skip'):
3352 webpage = self._download_webpage(
6e634cbe 3353 webpage_url + '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id, fatal=False)
11f9be09 3354
3355 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3356
b6de707d 3357 player_responses, player_url = self._extract_player_responses(
11f9be09 3358 self._get_requested_clients(url, smuggled_data),
99e9e001 3359 video_id, webpage, master_ytcfg)
11f9be09 3360
adbc4ec4
THD
3361 return webpage, master_ytcfg, player_responses, player_url
3362
a1b2d843 3363 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3364 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3365 is_live = get_first(video_details, 'isLive')
3366 if is_live is None:
3367 is_live = get_first(live_broadcast_details, 'isLiveNow')
3368
3369 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
a1b2d843 3370 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration))
adbc4ec4
THD
3371
3372 return live_broadcast_details, is_live, streaming_data, formats
3373
3374 def _real_extract(self, url):
3375 url, smuggled_data = unsmuggle_url(url, {})
3376 video_id = self._match_id(url)
3377
3378 base_url = self.http_scheme() + '//www.youtube.com/'
3379 webpage_url = base_url + 'watch?v=' + video_id
3380
3381 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3382
11f9be09 3383 playability_statuses = traverse_obj(
3384 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3385
3386 trailer_video_id = get_first(
3387 playability_statuses,
3388 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3389 expected_type=str)
3390 if trailer_video_id:
3391 return self.url_result(
3392 trailer_video_id, self.ie_key(), trailer_video_id)
3393
3394 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3395 if webpage else (lambda x: None))
3396
3397 video_details = traverse_obj(
3398 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3399 microformats = traverse_obj(
3400 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3401 expected_type=dict, default=[])
3402 video_title = (
3403 get_first(video_details, 'title')
3404 or self._get_text(microformats, (..., 'title'))
3405 or search_meta(['og:title', 'twitter:title', 'title']))
3406 video_description = get_first(video_details, 'shortDescription')
3407
d89257f3 3408 multifeed_metadata_list = get_first(
3409 player_responses,
3410 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3411 expected_type=str)
3412 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3413 if self.get_param('noplaylist'):
11f9be09 3414 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3415 else:
3416 entries = []
3417 feed_ids = []
3418 for feed in multifeed_metadata_list.split(','):
3419 # Unquote should take place before split on comma (,) since textual
3420 # fields may contain comma as well (see
3421 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3422 feed_data = compat_parse_qs(
ac668111 3423 urllib.parse.unquote_plus(feed))
d89257f3 3424
3425 def feed_entry(name):
3426 return try_get(
3427 feed_data, lambda x: x[name][0], compat_str)
3428
3429 feed_id = feed_entry('id')
3430 if not feed_id:
3431 continue
3432 feed_title = feed_entry('title')
3433 title = video_title
3434 if feed_title:
3435 title += ' (%s)' % feed_title
3436 entries.append({
3437 '_type': 'url_transparent',
3438 'ie_key': 'Youtube',
3439 'url': smuggle_url(
3440 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3441 {'force_singlefeed': True}),
3442 'title': title,
3443 })
3444 feed_ids.append(feed_id)
3445 self.to_screen(
3446 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3447 % (', '.join(feed_ids), video_id))
3448 return self.playlist_result(
3449 entries, video_id, video_title, video_description)
11f9be09 3450
a1b2d843 3451 duration = int_or_none(
3452 get_first(video_details, 'lengthSeconds')
3453 or get_first(microformats, 'lengthSeconds')
3454 or parse_duration(search_meta('duration'))) or None
3455
829bbd1d 3456 if get_first(video_details, 'isPostLiveDvr'):
3457 self.write_debug('Video is in Post-Live Manifestless mode')
3458 if duration or 0 > 4 * 3600:
3459 self.report_warning(
3460 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3461 'This is a known issue and patches are welcome')
3462
a1b2d843 3463 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(
3464 video_id, microformats, video_details, player_responses, player_url, duration)
bf1317d2 3465
545cc85d 3466 if not formats:
11f9be09 3467 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3468 self.report_drm(video_id)
11f9be09 3469 pemr = get_first(
3470 playability_statuses,
3471 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3472 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3473 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3474 if subreason:
545cc85d 3475 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3476 countries = get_first(microformats, 'availableCountries')
545cc85d 3477 if not countries:
3478 regions_allowed = search_meta('regionsAllowed')
3479 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3480 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3481 reason += f'. {subreason}'
545cc85d 3482 if reason:
b7da73eb 3483 self.raise_no_formats(reason, expected=True)
bf1317d2 3484
11f9be09 3485 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3486 if not keywords and webpage:
3487 keywords = [
3488 unescapeHTML(m.group('content'))
3489 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3490 for keyword in keywords:
3491 if keyword.startswith('yt:stretch='):
201c1459 3492 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3493 if mobj:
3494 # NB: float is intentional for forcing float division
3495 w, h = (float(v) for v in mobj.groups())
3496 if w > 0 and h > 0:
3497 ratio = w / h
3498 for f in formats:
3499 if f.get('vcodec') != 'none':
3500 f['stretched_ratio'] = ratio
3501 break
a709d873 3502 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3503 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3504 if thumbnail_url:
3505 thumbnails.append({
3506 'url': thumbnail_url,
ff2751ac 3507 })
fccf5021 3508 original_thumbnails = thumbnails.copy()
3509
0ba692ac 3510 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3511 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3512 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3513 thumbnail_names = [
bfec31be 3514 # While the *1,*2,*3 thumbnails are just below their correspnding "*default" variants
3515 # in resolution, these are not the custom thumbnail. So de-prioritize them
3516 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3517 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3518 ]
cca80fe6 3519 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3520 thumbnails.extend({
3521 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3522 video_id=video_id, name=name, ext=ext,
3523 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3524 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3525 for thumb in thumbnails:
cca80fe6 3526 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3527 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3528 self._remove_duplicate_formats(thumbnails)
fccf5021 3529 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3530
7ea65411 3531 category = get_first(microformats, 'category') or search_meta('genre')
3532 channel_id = str_or_none(
3533 get_first(video_details, 'channelId')
3534 or get_first(microformats, 'externalChannelId')
3535 or search_meta('channelId'))
7ea65411 3536 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3537
3538 live_content = get_first(video_details, 'isLiveContent')
3539 is_upcoming = get_first(video_details, 'isUpcoming')
3540 if is_live is None:
3541 if is_upcoming or live_content is False:
3542 is_live = False
3543 if is_upcoming is None and (live_content or is_live):
3544 is_upcoming = False
adbc4ec4
THD
3545 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3546 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3547 if not duration and live_end_time and live_start_time:
3548 duration = live_end_time - live_start_time
3549
3550 if is_live and self.get_param('live_from_start'):
3551 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3552
720c3099 3553 formats.extend(self._extract_storyboard(player_responses, duration))
3554
3555 # Source is given priority since formats that throttle are given lower source_preference
3556 # When throttling issue is fully fixed, remove this
3557 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3558
545cc85d 3559 info = {
3560 'id': video_id,
39ca3b5c 3561 'title': video_title,
545cc85d 3562 'formats': formats,
3563 'thumbnails': thumbnails,
fccf5021 3564 # The best thumbnail that we are sure exists. Prevents unnecessary
3565 # URL checking if user don't care about getting the best possible thumbnail
3566 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3567 'description': video_description,
11f9be09 3568 'uploader': get_first(video_details, 'author'),
545cc85d 3569 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3570 'uploader_url': owner_profile_url,
3571 'channel_id': channel_id,
a70635b8 3572 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3573 'duration': duration,
3574 'view_count': int_or_none(
11f9be09 3575 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3576 or search_meta('interactionCount')),
11f9be09 3577 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3578 'age_limit': 18 if (
11f9be09 3579 get_first(microformats, 'isFamilySafe') is False
545cc85d 3580 or search_meta('isFamilyFriendly') == 'false'
3581 or search_meta('og:restrictions:age') == '18+') else 0,
3582 'webpage_url': webpage_url,
3583 'categories': [category] if category else None,
3584 'tags': keywords,
11f9be09 3585 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3586 'is_live': is_live,
3587 'was_live': (False if is_live or is_upcoming or live_content is False
3588 else None if is_live is None or is_upcoming is None
3589 else live_content),
3590 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3591 'release_timestamp': live_start_time,
545cc85d 3592 }
b477fc13 3593
3944e7af 3594 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3595 if pctr:
ecdc9049 3596 def get_lang_code(track):
3597 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3598 or track.get('languageCode'))
3599
3600 # Converted into dicts to remove duplicates
3601 captions = {
3602 get_lang_code(sub): sub
3603 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3604 translation_languages = {
3605 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3606 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3607
774d79cc 3608 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3609 lang_subs = container.setdefault(lang_code, [])
545cc85d 3610 for fmt in self._SUBTITLE_FORMATS:
3611 query.update({
3612 'fmt': fmt,
3613 })
3614 lang_subs.append({
3615 'ext': fmt,
60f393e4 3616 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3617 'name': sub_name,
545cc85d 3618 })
7e72694b 3619
ecdc9049 3620 subtitles, automatic_captions = {}, {}
3621 for lang_code, caption_track in captions.items():
3622 base_url = caption_track.get('baseUrl')
1235d333 3623 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3624 if not base_url:
3625 continue
ecdc9049 3626 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3627 if caption_track.get('kind') != 'asr':
545cc85d 3628 if not lang_code:
3629 continue
3630 process_language(
ecdc9049 3631 subtitles, base_url, lang_code, lang_name, {})
3632 if not caption_track.get('isTranslatable'):
3633 continue
3944e7af 3634 for trans_code, trans_name in translation_languages.items():
3635 if not trans_code:
545cc85d 3636 continue
1235d333 3637 orig_trans_code = trans_code
ecdc9049 3638 if caption_track.get('kind') != 'asr':
18e49408 3639 if 'translated_subs' in self._configuration_arg('skip'):
3640 continue
ecdc9049 3641 trans_code += f'-{lang_code}'
a70635b8 3642 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 3643 # Add an "-orig" label to the original language so that it can be distinguished.
3644 # The subs are returned without "-orig" as well for compatibility
1235d333 3645 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3646 process_language(
d49669ac 3647 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3648 # Setting tlang=lang returns damaged subtitles.
d49669ac 3649 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3650 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
ecdc9049 3651 info['automatic_captions'] = automatic_captions
3652 info['subtitles'] = subtitles
7e72694b 3653
545cc85d 3654 parsed_url = compat_urllib_parse_urlparse(url)
3655 for component in [parsed_url.fragment, parsed_url.query]:
3656 query = compat_parse_qs(component)
3657 for k, v in query.items():
3658 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3659 d_k += '_time'
3660 if d_k not in info and k in s_ks:
3661 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3662
3663 # Youtube Music Auto-generated description
822b9d9c 3664 if video_description:
1890fc63 3665 mobj = re.search(
3666 r'''(?xs)
3667 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3668 (?P<album>[^\n]+)
3669 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3670 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3671 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3672 .+\nAuto-generated\ by\ YouTube\.\s*$
3673 ''', video_description)
822b9d9c 3674 if mobj:
822b9d9c
RA
3675 release_year = mobj.group('release_year')
3676 release_date = mobj.group('release_date')
3677 if release_date:
3678 release_date = release_date.replace('-', '')
3679 if not release_year:
545cc85d 3680 release_year = release_date[:4]
3681 info.update({
3682 'album': mobj.group('album'.strip()),
3683 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3684 'track': mobj.group('track').strip(),
3685 'release_date': release_date,
cc2db878 3686 'release_year': int_or_none(release_year),
545cc85d 3687 })
7e72694b 3688
545cc85d 3689 initial_data = None
3690 if webpage:
56ba69e4 3691 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 3692 if not initial_data:
99e9e001 3693 query = {'videoId': video_id}
3694 query.update(self._get_checkok_params())
109dd3b2 3695 initial_data = self._extract_response(
3696 item_id=video_id, ep='next', fatal=False,
99e9e001 3697 ytcfg=master_ytcfg, query=query,
3698 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3699 note='Downloading initial data API JSON')
545cc85d 3700
0df111a3 3701 info['comment_count'] = traverse_obj(initial_data, (
3702 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3703 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3704 ), (
3705 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3706 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3707 ), expected_type=int_or_none, get_all=False)
3708
19a03940 3709 try: # This will error if there is no livechat
c60ee3a2 3710 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 3711 except (KeyError, IndexError, TypeError):
3712 pass
3713 else:
ecdc9049 3714 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 3715 # url is needed to set cookies
3716 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 3717 'video_id': video_id,
3718 'ext': 'json',
f6745c49 3719 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3720 }]
545cc85d 3721
3722 if initial_data:
7c365c21 3723 info['chapters'] = (
3724 self._extract_chapters_from_json(initial_data, duration)
3725 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 3726 or self._extract_chapters_from_description(video_description, duration)
7c365c21 3727 or None)
545cc85d 3728
17322130 3729 contents = traverse_obj(
3730 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3731 expected_type=list, default=[])
3732
3733 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3734 if vpir:
3735 stl = vpir.get('superTitleLink')
3736 if stl:
3737 stl = self._get_text(stl)
3738 if try_get(
3739 vpir,
3740 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3741 info['location'] = stl
3742 else:
affc4fef 3743 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 3744 if mobj:
545cc85d 3745 info.update({
17322130 3746 'series': mobj.group(1),
3747 'season_number': int(mobj.group(2)),
3748 'episode_number': int(mobj.group(3)),
545cc85d 3749 })
17322130 3750 for tlb in (try_get(
3751 vpir,
3752 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3753 list) or []):
3754 tbr = tlb.get('toggleButtonRenderer') or {}
3755 for getter, regex in [(
3756 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3757 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3758 lambda x: x['accessibility'],
3759 lambda x: x['accessibilityData']['accessibilityData'],
3760 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3761 label = (try_get(tbr, getter, dict) or {}).get('label')
3762 if label:
3763 mobj = re.match(regex, label)
3764 if mobj:
3765 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3766 break
17322130 3767 sbr_tooltip = try_get(
3768 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3769 if sbr_tooltip:
3770 like_count, dislike_count = sbr_tooltip.split(' / ')
3771 info.update({
3772 'like_count': str_to_int(like_count),
3773 'dislike_count': str_to_int(dislike_count),
3774 })
3775 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3776 if vsir:
3777 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3778 info.update({
3779 'channel': self._get_text(vor, 'title'),
3780 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3781
3782 rows = try_get(
3783 vsir,
3784 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3785 list) or []
3786 multiple_songs = False
3787 for row in rows:
3788 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3789 multiple_songs = True
3790 break
3791 for row in rows:
3792 mrr = row.get('metadataRowRenderer') or {}
3793 mrr_title = mrr.get('title')
3794 if not mrr_title:
3795 continue
3796 mrr_title = self._get_text(mrr, 'title')
3797 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3798 if mrr_title == 'License':
3799 info['license'] = mrr_contents_text
3800 elif not multiple_songs:
3801 if mrr_title == 'Album':
3802 info['album'] = mrr_contents_text
3803 elif mrr_title == 'Artist':
3804 info['artist'] = mrr_contents_text
3805 elif mrr_title == 'Song':
3806 info['track'] = mrr_contents_text
545cc85d 3807
3808 fallbacks = {
3809 'channel': 'uploader',
3810 'channel_id': 'uploader_id',
3811 'channel_url': 'uploader_url',
3812 }
992f9a73 3813
17322130 3814 # The upload date for scheduled, live and past live streams / premieres in microformats
3815 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3816 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3817 upload_date = (
3818 unified_strdate(get_first(microformats, 'uploadDate'))
3819 or unified_strdate(search_meta('uploadDate')))
3820 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
6e634cbe 3821 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date
17322130 3822 info['upload_date'] = upload_date
992f9a73 3823
545cc85d 3824 for to, frm in fallbacks.items():
3825 if not info.get(to):
3826 info[to] = info.get(frm)
3827
3828 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3829 v = info.get(s_k)
3830 if v:
3831 info[d_k] = v
b84071c0 3832
11f9be09 3833 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3834 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3835 is_membersonly = None
b28f8d24 3836 is_premium = None
c224251a
M
3837 if initial_data and is_private is not None:
3838 is_membersonly = False
b28f8d24 3839 is_premium = False
47193e02 3840 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3841 badge_labels = set()
3842 for content in contents:
3843 if not isinstance(content, dict):
3844 continue
3845 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3846 for badge_label in badge_labels:
3847 if badge_label.lower() == 'members only':
3848 is_membersonly = True
3849 elif badge_label.lower() == 'premium':
3850 is_premium = True
3851 elif badge_label.lower() == 'unlisted':
3852 is_unlisted = True
c224251a 3853
c224251a
M
3854 info['availability'] = self._availability(
3855 is_private=is_private,
b28f8d24 3856 needs_premium=is_premium,
c224251a
M
3857 needs_subscription=is_membersonly,
3858 needs_auth=info['age_limit'] >= 18,
3859 is_unlisted=None if is_private is None else is_unlisted)
3860
a2160aa4 3861 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3862
11f9be09 3863 self.mark_watched(video_id, player_responses)
d77ab8e2 3864
545cc85d 3865 return info
c5e8d7af 3866
a61fd4cf 3867
a6213a49 3868class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3869
182bda88 3870 @staticmethod
3871 def passthrough_smuggled_data(func):
3872 def _smuggle(entries, smuggled_data):
3873 for entry in entries:
3874 # TODO: Convert URL to music.youtube instead.
3875 # Do we need to passthrough any other smuggled_data?
3876 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3877 yield entry
3878
3879 @functools.wraps(func)
3880 def wrapper(self, url):
3881 url, smuggled_data = unsmuggle_url(url, {})
3882 if self.is_music_url(url):
3883 smuggled_data['is_music_url'] = True
3884 info_dict = func(self, url, smuggled_data)
3885 if smuggled_data and info_dict.get('entries'):
3886 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3887 return info_dict
3888 return wrapper
3889
a6213a49 3890 def _extract_channel_id(self, webpage):
3891 channel_id = self._html_search_meta(
3892 'channelId', webpage, 'channel id', default=None)
3893 if channel_id:
3894 return channel_id
3895 channel_url = self._html_search_meta(
3896 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3897 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3898 'twitter:app:url:googleplay'), webpage, 'channel url')
3899 return self._search_regex(
3900 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3901 channel_url, 'channel id')
15f6397c 3902
8bdd16b4 3903 @staticmethod
cd7c66cf 3904 def _extract_basic_item_renderer(item):
3905 # Modified from _extract_grid_item_renderer
201c1459 3906 known_basic_renderers = (
a17526e4 3907 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 3908 )
3909 for key, renderer in item.items():
201c1459 3910 if not isinstance(renderer, dict):
cd7c66cf 3911 continue
201c1459 3912 elif key in known_basic_renderers:
3913 return renderer
3914 elif key.startswith('grid') and key.endswith('Renderer'):
3915 return renderer
8bdd16b4 3916
8bdd16b4 3917 def _grid_entries(self, grid_renderer):
3918 for item in grid_renderer['items']:
3919 if not isinstance(item, dict):
39b62db1 3920 continue
cd7c66cf 3921 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3922 if not isinstance(renderer, dict):
3923 continue
052e1350 3924 title = self._get_text(renderer, 'title')
fe93e2c4 3925
8bdd16b4 3926 # playlist
3927 playlist_id = renderer.get('playlistId')
3928 if playlist_id:
3929 yield self.url_result(
3930 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3931 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3932 video_title=title)
201c1459 3933 continue
8bdd16b4 3934 # video
3935 video_id = renderer.get('videoId')
3936 if video_id:
3937 yield self._extract_video(renderer)
201c1459 3938 continue
8bdd16b4 3939 # channel
3940 channel_id = renderer.get('channelId')
3941 if channel_id:
8bdd16b4 3942 yield self.url_result(
3943 'https://www.youtube.com/channel/%s' % channel_id,
3944 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3945 continue
3946 # generic endpoint URL support
3947 ep_url = urljoin('https://www.youtube.com/', try_get(
3948 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3949 compat_str))
3950 if ep_url:
3951 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3952 if ie.suitable(ep_url):
3953 yield self.url_result(
3954 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3955 break
8bdd16b4 3956
16aa9ea4 3957 def _music_reponsive_list_entry(self, renderer):
3958 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3959 if video_id:
3960 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3961 ie=YoutubeIE.ie_key(), video_id=video_id)
3962 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3963 if playlist_id:
3964 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3965 if video_id:
3966 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3967 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3968 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3969 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3970 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3971 if browse_id:
3972 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3973 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3974
3d3dddc9 3975 def _shelf_entries_from_content(self, shelf_renderer):
3976 content = shelf_renderer.get('content')
3977 if not isinstance(content, dict):
8bdd16b4 3978 return
cd7c66cf 3979 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3980 if renderer:
3981 # TODO: add support for nested playlists so each shelf is processed
3982 # as separate playlist
3983 # TODO: this includes only first N items
86e5f3ed 3984 yield from self._grid_entries(renderer)
3d3dddc9 3985 renderer = content.get('horizontalListRenderer')
3986 if renderer:
3987 # TODO
3988 pass
8bdd16b4 3989
29f7c58a 3990 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3991 ep = try_get(
3992 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3993 compat_str)
3994 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3995 if shelf_url:
29f7c58a 3996 # Skipping links to another channels, note that checking for
3997 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3998 # will not work
3999 if skip_channels and '/channels?' in shelf_url:
4000 return
052e1350 4001 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4002 yield self.url_result(shelf_url, video_title=title)
4003 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4004 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4005
8bdd16b4 4006 def _playlist_entries(self, video_list_renderer):
4007 for content in video_list_renderer['contents']:
4008 if not isinstance(content, dict):
4009 continue
4010 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4011 if not isinstance(renderer, dict):
4012 continue
4013 video_id = renderer.get('videoId')
4014 if not video_id:
4015 continue
4016 yield self._extract_video(renderer)
07aeced6 4017
3462ffa8 4018 def _rich_entries(self, rich_grid_renderer):
4019 renderer = try_get(
70d5c17b 4020 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 4021 video_id = renderer.get('videoId')
4022 if not video_id:
4023 return
4024 yield self._extract_video(renderer)
4025
8bdd16b4 4026 def _video_entry(self, video_renderer):
4027 video_id = video_renderer.get('videoId')
4028 if video_id:
4029 return self._extract_video(video_renderer)
dacb3a86 4030
ad210f4f 4031 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4032 url = urljoin('https://youtube.com', traverse_obj(
4033 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4034 if url:
4035 return self.url_result(
4036 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4037
8bdd16b4 4038 def _post_thread_entries(self, post_thread_renderer):
4039 post_renderer = try_get(
4040 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4041 if not post_renderer:
4042 return
4043 # video attachment
4044 video_renderer = try_get(
895b0931 4045 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4046 video_id = video_renderer.get('videoId')
4047 if video_id:
4048 entry = self._extract_video(video_renderer)
8bdd16b4 4049 if entry:
4050 yield entry
895b0931 4051 # playlist attachment
4052 playlist_id = try_get(
4053 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
4054 if playlist_id:
4055 yield self.url_result(
e28f1c0a 4056 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4057 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4058 # inline video links
4059 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4060 for run in runs:
4061 if not isinstance(run, dict):
4062 continue
4063 ep_url = try_get(
4064 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
4065 if not ep_url:
4066 continue
4067 if not YoutubeIE.suitable(ep_url):
4068 continue
4069 ep_video_id = YoutubeIE._match_id(ep_url)
4070 if video_id == ep_video_id:
4071 continue
895b0931 4072 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4073
8bdd16b4 4074 def _post_thread_continuation_entries(self, post_thread_continuation):
4075 contents = post_thread_continuation.get('contents')
4076 if not isinstance(contents, list):
4077 return
4078 for content in contents:
4079 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4080 if isinstance(renderer, dict):
4081 yield from self._post_thread_entries(renderer)
8bdd16b4 4082 continue
6b0b0a28 4083 renderer = content.get('videoRenderer')
4084 if isinstance(renderer, dict):
4085 yield self._video_entry(renderer)
07aeced6 4086
39ed931e 4087 r''' # unused
4088 def _rich_grid_entries(self, contents):
4089 for content in contents:
4090 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4091 if video_renderer:
4092 entry = self._video_entry(video_renderer)
4093 if entry:
4094 yield entry
4095 '''
52efa4b3 4096
a6213a49 4097 def _extract_entries(self, parent_renderer, continuation_list):
4098 # continuation_list is modified in-place with continuation_list = [continuation_token]
4099 continuation_list[:] = [None]
4100 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4101 for content in contents:
4102 if not isinstance(content, dict):
4103 continue
16aa9ea4 4104 is_renderer = traverse_obj(
4105 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4106 expected_type=dict)
a6213a49 4107 if not is_renderer:
4108 renderer = content.get('richItemRenderer')
4109 if renderer:
4110 for entry in self._rich_entries(renderer):
4111 yield entry
4112 continuation_list[0] = self._extract_continuation(parent_renderer)
4113 continue
4114 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4115 for isr_content in isr_contents:
4116 if not isinstance(isr_content, dict):
8bdd16b4 4117 continue
69184e41 4118
a6213a49 4119 known_renderers = {
4120 'playlistVideoListRenderer': self._playlist_entries,
4121 'gridRenderer': self._grid_entries,
a17526e4 4122 'reelShelfRenderer': self._grid_entries,
4123 'shelfRenderer': self._shelf_entries,
16aa9ea4 4124 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4125 'backstagePostThreadRenderer': self._post_thread_entries,
4126 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4127 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4128 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4129 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4130 }
4131 for key, renderer in isr_content.items():
4132 if key not in known_renderers:
4133 continue
4134 for entry in known_renderers[key](renderer):
4135 if entry:
4136 yield entry
4137 continuation_list[0] = self._extract_continuation(renderer)
4138 break
70d5c17b 4139
4140 if not continuation_list[0]:
a6213a49 4141 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4142
a6213a49 4143 if not continuation_list[0]:
4144 continuation_list[0] = self._extract_continuation(parent_renderer)
4145
4146 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4147 continuation_list = [None]
4148 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4149 tab_content = try_get(tab, lambda x: x['content'], dict)
4150 if not tab_content:
4151 return
3462ffa8 4152 parent_renderer = (
29f7c58a 4153 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4154 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4155 yield from extract_entries(parent_renderer)
3462ffa8 4156 continuation = continuation_list[0]
d069eca7 4157
8bdd16b4 4158 for page_num in itertools.count(1):
4159 if not continuation:
4160 break
99e9e001 4161 headers = self.generate_api_headers(
4162 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4163 response = self._extract_response(
86e5f3ed 4164 item_id=f'{item_id} page {page_num}',
fe93e2c4 4165 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4166 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4167
4168 if not response:
8bdd16b4 4169 break
ac56cf38 4170 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4171 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4172 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4173
69184e41 4174 known_continuation_renderers = {
4175 'playlistVideoListContinuation': self._playlist_entries,
4176 'gridContinuation': self._grid_entries,
4177 'itemSectionContinuation': self._post_thread_continuation_entries,
4178 'sectionListContinuation': extract_entries, # for feeds
4179 }
8bdd16b4 4180 continuation_contents = try_get(
69184e41 4181 response, lambda x: x['continuationContents'], dict) or {}
4182 continuation_renderer = None
4183 for key, value in continuation_contents.items():
4184 if key not in known_continuation_renderers:
3462ffa8 4185 continue
69184e41 4186 continuation_renderer = value
4187 continuation_list = [None]
86e5f3ed 4188 yield from known_continuation_renderers[key](continuation_renderer)
69184e41 4189 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4190 break
4191 if continuation_renderer:
4192 continue
c5e8d7af 4193
a1b535bd 4194 known_renderers = {
e4b98809 4195 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4196 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4197 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4198 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4199 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4200 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4201 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4202 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4203 }
cce889b9 4204 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4205 continuation_items = try_get(
cce889b9 4206 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4207 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4208 video_items_renderer = None
4209 for key, value in continuation_item.items():
4210 if key not in known_renderers:
8bdd16b4 4211 continue
a1b535bd 4212 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4213 continuation_list = [None]
86e5f3ed 4214 yield from known_renderers[key][0](video_items_renderer)
9ba5705a 4215 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4216 break
4217 if video_items_renderer:
4218 continue
8bdd16b4 4219 break
9558dcec 4220
8bdd16b4 4221 @staticmethod
7c219ea6 4222 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4223 for tab in tabs:
cd684175 4224 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4225 if renderer.get('selected') is True:
4226 return renderer
2b3c2546 4227 else:
7c219ea6 4228 if fatal:
4229 raise ExtractorError('Unable to find selected tab')
b82f815f 4230
61d3665d 4231 def _extract_uploader(self, data):
8bdd16b4 4232 uploader = {}
61d3665d 4233 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
47193e02 4234 owner = try_get(
4235 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4236 if owner:
61d3665d 4237 owner_text = owner.get('text')
4238 uploader['uploader'] = self._search_regex(
4239 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
47193e02 4240 uploader['uploader_id'] = try_get(
4241 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
4242 uploader['uploader_url'] = urljoin(
4243 'https://www.youtube.com/',
4244 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 4245 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4246
ac56cf38 4247 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4248 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4249 tags = []
b60419c5 4250
8bdd16b4 4251 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4252 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4253 renderer = try_get(
4254 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4255 if renderer:
b60419c5 4256 channel_name = renderer.get('title')
4257 channel_url = renderer.get('channelUrl')
4258 channel_id = renderer.get('externalId')
39ed931e 4259 else:
64c0d954 4260 renderer = try_get(
4261 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4262
8bdd16b4 4263 if renderer:
4264 title = renderer.get('title')
ecc97af3 4265 description = renderer.get('description', '')
b60419c5 4266 playlist_id = channel_id
4267 tags = renderer.get('keywords', '').split()
b60419c5 4268
301d07fc 4269 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4270 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4271 def _get_uncropped(url):
4272 return url_or_none((url or '').split('=')[0] + '=s0')
4273
4274 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4275 if avatar_thumbnails:
4276 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4277 if uncropped_avatar:
4278 avatar_thumbnails.append({
4279 'url': uncropped_avatar,
4280 'id': 'avatar_uncropped',
4281 'preference': 1
4282 })
4283
4284 channel_banners = self._extract_thumbnails(
4285 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4286 for banner in channel_banners:
4287 banner['preference'] = -10
4288
4289 if channel_banners:
4290 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4291 if uncropped_banner:
4292 channel_banners.append({
4293 'url': uncropped_banner,
4294 'id': 'banner_uncropped',
4295 'preference': -5
4296 })
4297
4298 primary_thumbnails = self._extract_thumbnails(
a17526e4 4299 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4300
3462ffa8 4301 if playlist_id is None:
70d5c17b 4302 playlist_id = item_id
f0d785d3 4303
4304 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4305 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4306 if title is None:
f0d785d3 4307 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4308 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4309 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4310
b60419c5 4311 metadata = {
4312 'playlist_id': playlist_id,
4313 'playlist_title': title,
4314 'playlist_description': description,
4315 'uploader': channel_name,
4316 'uploader_id': channel_id,
4317 'uploader_url': channel_url,
301d07fc 4318 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4319 'tags': tags,
f0d785d3 4320 'view_count': self._get_count(playlist_stats, 1),
4321 'availability': self._extract_availability(data),
4322 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4323 'playlist_count': self._get_count(playlist_stats, 0),
4324 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4325 }
4326 if not channel_id:
4327 metadata.update(self._extract_uploader(data))
4328 metadata.update({
4329 'channel': metadata['uploader'],
4330 'channel_id': metadata['uploader_id'],
4331 'channel_url': metadata['uploader_url']})
4332 return self.playlist_result(
d069eca7 4333 self._entries(
ac56cf38 4334 selected_tab, playlist_id, ytcfg,
4335 self._extract_account_syncid(ytcfg, data),
4336 self._extract_visitor_data(data, ytcfg)),
b60419c5 4337 **metadata)
73c4ac2c 4338
6e634cbe 4339 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4340 first_id = last_id = response = None
2be71994 4341 for page_num in itertools.count(1):
cd7c66cf 4342 videos = list(self._playlist_entries(playlist))
4343 if not videos:
4344 return
2be71994 4345 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4346 if start >= len(videos):
4347 return
24146491 4348 yield from videos[start:]
2be71994 4349 first_id = first_id or videos[0]['id']
4350 last_id = videos[-1]['id']
79360d99 4351 watch_endpoint = try_get(
4352 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4353 headers = self.generate_api_headers(
4354 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4355 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4356 query = {
4357 'playlistId': playlist_id,
4358 'videoId': watch_endpoint.get('videoId') or last_id,
4359 'index': watch_endpoint.get('index') or len(videos),
4360 'params': watch_endpoint.get('params') or 'OAE%3D'
4361 }
4362 response = self._extract_response(
4363 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4364 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4365 check_get_keys='contents'
4366 )
cd7c66cf 4367 playlist = try_get(
79360d99 4368 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4369
ac56cf38 4370 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4371 title = playlist.get('title') or try_get(
4372 data, lambda x: x['titleText']['simpleText'], compat_str)
4373 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4374
4375 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4376 playlist_url = urljoin(url, try_get(
4377 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4378 compat_str))
6e634cbe 4379
4380 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4381 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4382 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4383
4384 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4385 return self.url_result(
4386 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4387 video_title=title)
cd7c66cf 4388
8bdd16b4 4389 return self.playlist_result(
6e634cbe 4390 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4391 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4392
47193e02 4393 def _extract_availability(self, data):
4394 """
4395 Gets the availability of a given playlist/tab.
4396 Note: Unless YouTube tells us explicitly, we do not assume it is public
4397 @param data: response
4398 """
4399 is_private = is_unlisted = None
4400 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4401 badge_labels = self._extract_badges(renderer)
4402
4403 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4404 privacy_dropdown_entries = try_get(
4405 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4406 for renderer_dict in privacy_dropdown_entries:
4407 is_selected = try_get(
4408 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4409 if not is_selected:
4410 continue
052e1350 4411 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4412 if label:
4413 badge_labels.add(label.lower())
4414 break
4415
4416 for badge_label in badge_labels:
4417 if badge_label == 'unlisted':
4418 is_unlisted = True
4419 elif badge_label == 'private':
4420 is_private = True
4421 elif badge_label == 'public':
4422 is_unlisted = is_private = False
4423 return self._availability(is_private, False, False, False, is_unlisted)
4424
4425 @staticmethod
4426 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4427 sidebar_renderer = try_get(
4428 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4429 for item in sidebar_renderer:
4430 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4431 if renderer:
4432 return renderer
4433
ac56cf38 4434 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4435 """
4436 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4437 """
5d342002 4438 browse_id = params = None
47193e02 4439 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4440 if not renderer:
4441 return
4442 menu_renderer = try_get(
4443 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4444 for menu_item in menu_renderer:
4445 if not isinstance(menu_item, dict):
358de58c 4446 continue
47193e02 4447 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4448 text = try_get(
4449 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4450 if not text or text.lower() != 'show unavailable videos':
4451 continue
4452 browse_endpoint = try_get(
4453 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4454 browse_id = browse_endpoint.get('browseId')
4455 params = browse_endpoint.get('params')
4456 break
5d342002 4457
11f9be09 4458 headers = self.generate_api_headers(
99e9e001 4459 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4460 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4461 query = {
4462 'params': params or 'wgYCCAA=',
4463 'browseId': browse_id or 'VL%s' % item_id
4464 }
4465 return self._extract_response(
4466 item_id=item_id, headers=headers, query=query,
fe93e2c4 4467 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4468 note='Downloading API JSON with unavailable videos')
358de58c 4469
2762dbb1 4470 @functools.cached_property
a25bca9f 4471 def skip_webpage(self):
4472 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4473
ac56cf38 4474 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4475 retries = self.get_param('extractor_retries', 3)
62bff2c1 4476 count = -1
ac56cf38 4477 webpage = data = last_error = None
14fdfea9 4478 while count < retries:
62bff2c1 4479 count += 1
14fdfea9 4480 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4481 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4482 if last_error:
c705177d 4483 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4484 try:
4485 webpage = self._download_webpage(
4486 url, item_id,
4487 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4488 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4489 except ExtractorError as e:
4490 if isinstance(e.cause, network_exceptions):
4491 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4492 last_error = error_to_compat_str(e.cause or e.msg)
4493 if count < retries:
4494 continue
4495 if fatal:
4496 raise
4497 self.report_warning(error_to_compat_str(e))
14fdfea9 4498 break
ac56cf38 4499 else:
4500 try:
4501 self._extract_and_report_alerts(data)
4502 except ExtractorError as e:
4503 if fatal:
4504 raise
4505 self.report_warning(error_to_compat_str(e))
4506 break
4507
7c219ea6 4508 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
ac56cf38 4509 break
4510
4511 last_error = 'Incomplete yt initial data received'
4512 if count >= retries:
4513 if fatal:
4514 raise ExtractorError(last_error)
4515 self.report_warning(last_error)
4516 break
4517
cd7c66cf 4518 return webpage, data
4519
a25bca9f 4520 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4521 """Use if failed to extract ytcfg (and data) from initial webpage"""
4522 if not ytcfg and self.is_authenticated:
4523 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4524 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4525 raise ExtractorError(
4526 f'{msg}. If you are not downloading private content, or '
4527 'your cookies are only for the first account and channel,'
4528 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4529 expected=True)
4530 self.report_warning(msg, only_once=True)
4531
ac56cf38 4532 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4533 data = None
a25bca9f 4534 if not self.skip_webpage:
ac56cf38 4535 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4536 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4537 # Reject webpage data if redirected to home page without explicitly requesting
4538 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4539 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4540 if (url != 'https://www.youtube.com/feed/recommended'
4541 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4542 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4543 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4544 if fatal:
4545 raise ExtractorError(msg, expected=True)
4546 self.report_warning(msg, only_once=True)
ac56cf38 4547 if not data:
a25bca9f 4548 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4549 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4550 return data, ytcfg
4551
4552 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4553 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4554 resolve_response = self._extract_response(
4555 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4556 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4557 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4558 for ep_key, ep in endpoints.items():
4559 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4560 if params:
4561 return self._extract_response(
4562 item_id=item_id, query=params, ep=ep, headers=headers,
4563 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4564 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4565 err_note = 'Failed to resolve url (does the playlist exist?)'
4566 if fatal:
4567 raise ExtractorError(err_note, expected=True)
4568 self.report_warning(err_note, item_id)
4569
a6213a49 4570 _SEARCH_PARAMS = None
4571
af5c1c55 4572 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4573 data = {'query': query}
4574 if params is NO_DEFAULT:
4575 params = self._SEARCH_PARAMS
4576 if params:
4577 data['params'] = params
16aa9ea4 4578
4579 content_keys = (
4580 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4581 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4582 # ytmusic search
4583 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4584 ('continuationContents', ),
4585 )
a25bca9f 4586 display_id = f'query "{query}"'
86e5f3ed 4587 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4588 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4589 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4590
a61fd4cf 4591 continuation_list = [None]
a25bca9f 4592 search = None
a6213a49 4593 for page_num in itertools.count(1):
a61fd4cf 4594 data.update(continuation_list[0] or {})
a25bca9f 4595 headers = self.generate_api_headers(
4596 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4597 search = self._extract_response(
a25bca9f 4598 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4599 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4600 slr_contents = traverse_obj(search, *content_keys)
4601 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4602 if not continuation_list[0]:
a6213a49 4603 break
4604
4605
4606class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4607 IE_DESC = 'YouTube Tabs'
4608 _VALID_URL = r'''(?x:
4609 https?://
4610 (?:\w+\.)?
4611 (?:
4612 youtube(?:kids)?\.com|
4613 %(invidious)s
4614 )/
4615 (?:
4616 (?P<channel_type>channel|c|user|browse)/|
4617 (?P<not_channel>
4618 feed/|hashtag/|
4619 (?:playlist|watch)\?.*?\blist=
4620 )|
4621 (?!(?:%(reserved_names)s)\b) # Direct URLs
4622 )
4623 (?P<id>[^/?\#&]+)
4624 )''' % {
4625 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4626 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4627 }
4628 IE_NAME = 'youtube:tab'
4629
4630 _TESTS = [{
4631 'note': 'playlists, multipage',
4632 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4633 'playlist_mincount': 94,
4634 'info_dict': {
4635 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4636 'title': 'Igor Kleiner - Playlists',
a6213a49 4637 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4638 'uploader': 'Igor Kleiner',
a6213a49 4639 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4640 'channel': 'Igor Kleiner',
4641 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4642 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4643 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4644 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4645 'channel_follower_count': int
a6213a49 4646 },
4647 }, {
4648 'note': 'playlists, multipage, different order',
4649 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4650 'playlist_mincount': 94,
4651 'info_dict': {
4652 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4653 'title': 'Igor Kleiner - Playlists',
a6213a49 4654 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4655 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4656 'uploader': 'Igor Kleiner',
4657 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4658 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4659 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4660 'channel': 'Igor Kleiner',
4661 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4662 'channel_follower_count': int
a6213a49 4663 },
4664 }, {
4665 'note': 'playlists, series',
4666 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4667 'playlist_mincount': 5,
4668 'info_dict': {
4669 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4670 'title': '3Blue1Brown - Playlists',
4671 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4672 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4673 'uploader': '3Blue1Brown',
976ae3ea 4674 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4675 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4676 'channel': '3Blue1Brown',
4677 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4678 'tags': ['Mathematics'],
6c73052c 4679 'channel_follower_count': int
a6213a49 4680 },
4681 }, {
4682 'note': 'playlists, singlepage',
4683 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4684 'playlist_mincount': 4,
4685 'info_dict': {
4686 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4687 'title': 'ThirstForScience - Playlists',
4688 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4689 'uploader': 'ThirstForScience',
4690 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4691 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4692 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4693 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4694 'tags': 'count:13',
4695 'channel': 'ThirstForScience',
6c73052c 4696 'channel_follower_count': int
a6213a49 4697 }
4698 }, {
4699 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4700 'only_matching': True,
4701 }, {
4702 'note': 'basic, single video playlist',
4703 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4704 'info_dict': {
4705 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4706 'uploader': 'Sergey M.',
4707 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4708 'title': 'youtube-dl public playlist',
976ae3ea 4709 'description': '',
4710 'tags': [],
4711 'view_count': int,
4712 'modified_date': '20201130',
4713 'channel': 'Sergey M.',
4714 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4715 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4716 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4717 },
4718 'playlist_count': 1,
4719 }, {
4720 'note': 'empty playlist',
4721 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4722 'info_dict': {
4723 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4724 'uploader': 'Sergey M.',
4725 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4726 'title': 'youtube-dl empty playlist',
976ae3ea 4727 'tags': [],
4728 'channel': 'Sergey M.',
4729 'description': '',
4730 'modified_date': '20160902',
4731 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4732 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4733 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4734 },
4735 'playlist_count': 0,
4736 }, {
4737 'note': 'Home tab',
4738 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4739 'info_dict': {
4740 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4741 'title': 'lex will - Home',
4742 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4743 'uploader': 'lex will',
4744 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4745 'channel': 'lex will',
4746 'tags': ['bible', 'history', 'prophesy'],
4747 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4748 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4749 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4750 'channel_follower_count': int
a6213a49 4751 },
4752 'playlist_mincount': 2,
4753 }, {
4754 'note': 'Videos tab',
4755 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4756 'info_dict': {
4757 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4758 'title': 'lex will - Videos',
4759 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4760 'uploader': 'lex will',
4761 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4762 'tags': ['bible', 'history', 'prophesy'],
4763 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4764 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4765 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4766 'channel': 'lex will',
6c73052c 4767 'channel_follower_count': int
a6213a49 4768 },
4769 'playlist_mincount': 975,
4770 }, {
4771 'note': 'Videos tab, sorted by popular',
4772 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4773 'info_dict': {
4774 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4775 'title': 'lex will - Videos',
4776 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4777 'uploader': 'lex will',
4778 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4779 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4780 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4781 'channel': 'lex will',
4782 'tags': ['bible', 'history', 'prophesy'],
4783 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4784 'channel_follower_count': int
a6213a49 4785 },
4786 'playlist_mincount': 199,
4787 }, {
4788 'note': 'Playlists tab',
4789 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4790 'info_dict': {
4791 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4792 'title': 'lex will - Playlists',
4793 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4794 'uploader': 'lex will',
4795 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4796 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4797 'channel': 'lex will',
4798 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4799 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4800 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4801 'channel_follower_count': int
a6213a49 4802 },
4803 'playlist_mincount': 17,
4804 }, {
4805 'note': 'Community tab',
4806 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4807 'info_dict': {
4808 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4809 'title': 'lex will - Community',
4810 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4811 'uploader': 'lex will',
4812 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4813 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4814 'channel': 'lex will',
4815 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4816 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4817 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4818 'channel_follower_count': int
a6213a49 4819 },
4820 'playlist_mincount': 18,
4821 }, {
4822 'note': 'Channels tab',
4823 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4824 'info_dict': {
4825 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4826 'title': 'lex will - Channels',
4827 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4828 'uploader': 'lex will',
4829 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4830 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4831 'channel': 'lex will',
4832 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4833 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4834 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4835 'channel_follower_count': int
a6213a49 4836 },
4837 'playlist_mincount': 12,
4838 }, {
4839 'note': 'Search tab',
4840 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4841 'playlist_mincount': 40,
4842 'info_dict': {
4843 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4844 'title': '3Blue1Brown - Search - linear algebra',
4845 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4846 'uploader': '3Blue1Brown',
4847 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4848 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4849 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4850 'tags': ['Mathematics'],
4851 'channel': '3Blue1Brown',
4852 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4853 'channel_follower_count': int
a6213a49 4854 },
4855 }, {
4856 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4857 'only_matching': True,
4858 }, {
4859 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4860 'only_matching': True,
4861 }, {
4862 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4863 'only_matching': True,
4864 }, {
4865 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4866 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4867 'info_dict': {
4868 'title': '29C3: Not my department',
4869 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4870 'uploader': 'Christiaan008',
4871 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4872 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4873 'tags': [],
4874 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4875 'view_count': int,
4876 'modified_date': '20150605',
4877 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4878 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4879 'channel': 'Christiaan008',
a6213a49 4880 },
4881 'playlist_count': 96,
4882 }, {
4883 'note': 'Large playlist',
4884 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4885 'info_dict': {
4886 'title': 'Uploads from Cauchemar',
4887 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4888 'uploader': 'Cauchemar',
4889 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4890 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4891 'tags': [],
4892 'modified_date': r're:\d{8}',
4893 'channel': 'Cauchemar',
4894 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4895 'view_count': int,
4896 'description': '',
4897 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4898 },
4899 'playlist_mincount': 1123,
976ae3ea 4900 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4901 }, {
4902 'note': 'even larger playlist, 8832 videos',
4903 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4904 'only_matching': True,
4905 }, {
4906 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4907 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4908 'info_dict': {
4909 'title': 'Uploads from Interstellar Movie',
4910 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4911 'uploader': 'Interstellar Movie',
4912 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4913 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4914 'tags': [],
4915 'view_count': int,
4916 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4917 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4918 'channel': 'Interstellar Movie',
4919 'description': '',
4920 'modified_date': r're:\d{8}',
a6213a49 4921 },
4922 'playlist_mincount': 21,
4923 }, {
4924 'note': 'Playlist with "show unavailable videos" button',
4925 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4926 'info_dict': {
4927 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4928 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4929 'uploader': 'Phim Siêu Nhân Nhật Bản',
4930 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4931 'view_count': int,
4932 'channel': 'Phim Siêu Nhân Nhật Bản',
4933 'tags': [],
4934 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4935 'description': '',
4936 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4937 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4938 'modified_date': r're:\d{8}',
a6213a49 4939 },
4940 'playlist_mincount': 200,
976ae3ea 4941 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4942 }, {
4943 'note': 'Playlist with unavailable videos in page 7',
4944 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4945 'info_dict': {
4946 'title': 'Uploads from BlankTV',
4947 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4948 'uploader': 'BlankTV',
4949 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4950 'channel': 'BlankTV',
4951 'channel_url': 'https://www.youtube.com/c/blanktv',
4952 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4953 'view_count': int,
4954 'tags': [],
4955 'uploader_url': 'https://www.youtube.com/c/blanktv',
4956 'modified_date': r're:\d{8}',
4957 'description': '',
a6213a49 4958 },
4959 'playlist_mincount': 1000,
976ae3ea 4960 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4961 }, {
4962 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4963 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4964 'info_dict': {
4965 'title': 'Data Analysis with Dr Mike Pound',
4966 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4967 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4968 'uploader': 'Computerphile',
4969 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4970 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4971 'tags': [],
4972 'view_count': int,
4973 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4974 'channel_url': 'https://www.youtube.com/user/Computerphile',
4975 'channel': 'Computerphile',
a6213a49 4976 },
4977 'playlist_mincount': 11,
4978 }, {
4979 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4980 'only_matching': True,
4981 }, {
4982 'note': 'Playlist URL that does not actually serve a playlist',
4983 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4984 'info_dict': {
4985 'id': 'FqZTN594JQw',
4986 'ext': 'webm',
4987 'title': "Smiley's People 01 detective, Adventure Series, Action",
4988 'uploader': 'STREEM',
4989 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4990 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4991 'upload_date': '20150526',
4992 'license': 'Standard YouTube License',
4993 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4994 'categories': ['People & Blogs'],
4995 'tags': list,
4996 'view_count': int,
4997 'like_count': int,
a6213a49 4998 },
4999 'params': {
5000 'skip_download': True,
5001 },
5002 'skip': 'This video is not available.',
5003 'add_ie': [YoutubeIE.ie_key()],
5004 }, {
5005 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5006 'only_matching': True,
5007 }, {
5008 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5009 'only_matching': True,
5010 }, {
5011 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5012 'info_dict': {
6c73052c 5013 'id': 'GgL890LIznQ', # This will keep changing
a6213a49 5014 'ext': 'mp4',
976ae3ea 5015 'title': str,
a6213a49 5016 'uploader': 'Sky News',
5017 'uploader_id': 'skynews',
5018 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5019 'upload_date': r're:\d{8}',
976ae3ea 5020 'description': str,
a6213a49 5021 'categories': ['News & Politics'],
5022 'tags': list,
5023 'like_count': int,
6c73052c 5024 'release_timestamp': 1642502819,
976ae3ea 5025 'channel': 'Sky News',
5026 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5027 'age_limit': 0,
5028 'view_count': int,
6c73052c 5029 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 5030 'playable_in_embed': True,
6c73052c 5031 'release_date': '20220118',
976ae3ea 5032 'availability': 'public',
5033 'live_status': 'is_live',
5034 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 5035 'channel_follower_count': int
a6213a49 5036 },
5037 'params': {
5038 'skip_download': True,
5039 },
976ae3ea 5040 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5041 }, {
5042 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5043 'info_dict': {
5044 'id': 'a48o2S1cPoo',
5045 'ext': 'mp4',
5046 'title': 'The Young Turks - Live Main Show',
5047 'uploader': 'The Young Turks',
5048 'uploader_id': 'TheYoungTurks',
5049 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5050 'upload_date': '20150715',
5051 'license': 'Standard YouTube License',
5052 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5053 'categories': ['News & Politics'],
5054 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5055 'like_count': int,
a6213a49 5056 },
5057 'params': {
5058 'skip_download': True,
5059 },
5060 'only_matching': True,
5061 }, {
5062 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5063 'only_matching': True,
5064 }, {
5065 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5066 'only_matching': True,
5067 }, {
5068 'note': 'A channel that is not live. Should raise error',
5069 'url': 'https://www.youtube.com/user/numberphile/live',
5070 'only_matching': True,
5071 }, {
5072 'url': 'https://www.youtube.com/feed/trending',
5073 'only_matching': True,
5074 }, {
5075 'url': 'https://www.youtube.com/feed/library',
5076 'only_matching': True,
5077 }, {
5078 'url': 'https://www.youtube.com/feed/history',
5079 'only_matching': True,
5080 }, {
5081 'url': 'https://www.youtube.com/feed/subscriptions',
5082 'only_matching': True,
5083 }, {
5084 'url': 'https://www.youtube.com/feed/watch_later',
5085 'only_matching': True,
5086 }, {
5087 'note': 'Recommended - redirects to home page.',
5088 'url': 'https://www.youtube.com/feed/recommended',
5089 'only_matching': True,
5090 }, {
5091 'note': 'inline playlist with not always working continuations',
5092 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5093 'only_matching': True,
5094 }, {
5095 'url': 'https://www.youtube.com/course',
5096 'only_matching': True,
5097 }, {
5098 'url': 'https://www.youtube.com/zsecurity',
5099 'only_matching': True,
5100 }, {
5101 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5102 'only_matching': True,
5103 }, {
5104 'url': 'https://www.youtube.com/TheYoungTurks/live',
5105 'only_matching': True,
5106 }, {
5107 'url': 'https://www.youtube.com/hashtag/cctv9',
5108 'info_dict': {
5109 'id': 'cctv9',
5110 'title': '#cctv9',
976ae3ea 5111 'tags': [],
a6213a49 5112 },
5113 'playlist_mincount': 350,
5114 }, {
5115 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5116 'only_matching': True,
5117 }, {
5118 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5119 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5120 'only_matching': True
5121 }, {
5122 'note': '/browse/ should redirect to /channel/',
5123 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5124 'only_matching': True
5125 }, {
5126 'note': 'VLPL, should redirect to playlist?list=PL...',
5127 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5128 'info_dict': {
5129 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5130 'uploader': 'NoCopyrightSounds',
5131 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5132 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5133 'title': 'NCS Releases',
976ae3ea 5134 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5135 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5136 'modified_date': r're:\d{8}',
5137 'view_count': int,
5138 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5139 'tags': [],
5140 'channel': 'NoCopyrightSounds',
a6213a49 5141 },
5142 'playlist_mincount': 166,
976ae3ea 5143 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5144 }, {
5145 'note': 'Topic, should redirect to playlist?list=UU...',
5146 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5147 'info_dict': {
5148 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5149 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5150 'title': 'Uploads from Royalty Free Music - Topic',
5151 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5152 'tags': [],
5153 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5154 'channel': 'Royalty Free Music - Topic',
5155 'view_count': int,
5156 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5157 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5158 'modified_date': r're:\d{8}',
5159 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5160 'description': '',
a6213a49 5161 },
5162 'expected_warnings': [
a6213a49 5163 'The URL does not have a videos tab',
976ae3ea 5164 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5165 ],
5166 'playlist_mincount': 101,
5167 }, {
5168 'note': 'Topic without a UU playlist',
5169 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5170 'info_dict': {
5171 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5172 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5173 'tags': [],
a6213a49 5174 },
5175 'expected_warnings': [
976ae3ea 5176 'the playlist redirect gave error',
a6213a49 5177 ],
5178 'playlist_mincount': 9,
5179 }, {
5180 'note': 'Youtube music Album',
5181 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5182 'info_dict': {
5183 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5184 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5185 'tags': [],
5186 'view_count': int,
5187 'description': '',
5188 'availability': 'unlisted',
5189 'modified_date': r're:\d{8}',
a6213a49 5190 },
5191 'playlist_count': 50,
5192 }, {
5193 'note': 'unlisted single video playlist',
5194 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5195 'info_dict': {
5196 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5197 'uploader': 'colethedj',
5198 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5199 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5200 'availability': 'unlisted',
5201 'tags': [],
5202 'modified_date': '20211208',
5203 'channel': 'colethedj',
5204 'view_count': int,
5205 'description': '',
5206 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5207 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5208 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5209 },
5210 'playlist_count': 1,
5211 }, {
5212 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5213 'url': 'https://www.youtube.com/feed/recommended',
5214 'info_dict': {
5215 'id': 'recommended',
5216 'title': 'recommended',
6c73052c 5217 'tags': [],
a6213a49 5218 },
5219 'playlist_mincount': 50,
5220 'params': {
5221 'skip_download': True,
5222 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5223 },
5224 }, {
5225 'note': 'API Fallback: /videos tab, sorted by oldest first',
5226 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5227 'info_dict': {
5228 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5229 'title': 'Cody\'sLab - Videos',
5230 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5231 'uploader': 'Cody\'sLab',
5232 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5233 'channel': 'Cody\'sLab',
5234 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5235 'tags': [],
5236 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5237 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5238 'channel_follower_count': int
a6213a49 5239 },
5240 'playlist_mincount': 650,
5241 'params': {
5242 'skip_download': True,
5243 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5244 },
5245 }, {
5246 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5247 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5248 'info_dict': {
5249 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5250 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5251 'title': 'Uploads from Royalty Free Music - Topic',
5252 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5253 'modified_date': r're:\d{8}',
5254 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5255 'description': '',
5256 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5257 'tags': [],
5258 'channel': 'Royalty Free Music - Topic',
5259 'view_count': int,
5260 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5261 },
5262 'expected_warnings': [
976ae3ea 5263 'does not have a videos tab',
5264 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5265 ],
5266 'playlist_mincount': 101,
5267 'params': {
5268 'skip_download': True,
5269 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5270 },
7c219ea6 5271 }, {
5272 'note': 'non-standard redirect to regional channel',
5273 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5274 'only_matching': True
61d3665d 5275 }, {
5276 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5277 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5278 'info_dict': {
5279 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5280 'modified_date': '20220407',
5281 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5282 'tags': [],
5283 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5284 'uploader': 'pukkandan',
5285 'availability': 'unlisted',
5286 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5287 'channel': 'pukkandan',
5288 'description': 'Test for collaborative playlist',
5289 'title': 'yt-dlp test - collaborative playlist',
5290 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5291 },
5292 'playlist_mincount': 2
a6213a49 5293 }]
5294
5295 @classmethod
5296 def suitable(cls, url):
86e5f3ed 5297 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5298
64f36541 5299 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5300
182bda88 5301 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5302 def _real_extract(self, url, smuggled_data):
cd7c66cf 5303 item_id = self._match_id(url)
5304 url = compat_urlparse.urlunparse(
5305 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5306 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5307
fe03a6cd 5308 def get_mobj(url):
37e57a9f 5309 mobj = self._URL_RE.match(url).groupdict()
07cce701 5310 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5311 return mobj
5312
37e57a9f 5313 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5314 # Youtube returns incomplete data if tabname is not lower case
5315 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5316 if is_channel:
5317 if smuggled_data.get('is_music_url'):
37e57a9f 5318 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5319 item_id = item_id[2:]
37e57a9f 5320 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5321 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5322 mdata = self._extract_tab_endpoint(
37e57a9f 5323 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5324 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5325 get_all=False, expected_type=compat_str)
ac56cf38 5326 if not murl:
37e57a9f 5327 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5328 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5329 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5330 pre = f'https://www.youtube.com/channel/{item_id}'
5331
64f36541 5332 original_tab_name = tab
fe03a6cd 5333 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5334 # Home URLs should redirect to /videos/
37e57a9f 5335 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5336 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5337 tab = '/videos'
5338
5339 url = ''.join((pre, tab, post))
5340 mobj = get_mobj(url)
cd7c66cf 5341
5342 # Handle both video/playlist URLs
201c1459 5343 qs = parse_qs(url)
86e5f3ed 5344 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5345
fe03a6cd 5346 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5347 if not playlist_id:
fe03a6cd 5348 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5349 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5350 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5351 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5352 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5353 mobj = get_mobj(url)
cd7c66cf 5354
5355 if video_id and playlist_id:
a06916d9 5356 if self.get_param('noplaylist'):
37e57a9f 5357 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5358 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5359 ie=YoutubeIE.ie_key(), video_id=video_id)
5360 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5361
ac56cf38 5362 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5363
7c219ea6 5364 # YouTube may provide a non-standard redirect to the regional channel
5365 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5366 redirect_url = traverse_obj(
5367 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5368 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5369 redirect_url = ''.join((
5370 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5371 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5372 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5373
37e57a9f 5374 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5375 if tabs:
5376 selected_tab = self._extract_selected_tab(tabs)
64f36541 5377 selected_tab_name = selected_tab.get('title', '').lower()
5378 if selected_tab_name == 'home':
5379 selected_tab_name = 'featured'
5380 requested_tab_name = mobj['tab'][1:]
09f1580e 5381 if 'no-youtube-channel-redirect' not in compat_opts:
64f36541 5382 if requested_tab_name == 'live':
09f1580e 5383 # Live tab should have redirected to the video
5384 raise ExtractorError('The channel is not currently live', expected=True)
64f36541 5385 if requested_tab_name not in ('', selected_tab_name):
5386 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5387 if not original_tab_name:
5388 if item_id[:2] == 'UC':
5389 # Topic channels don't have /videos. Use the equivalent playlist instead
5390 pl_id = f'UU{item_id[2:]}'
5391 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5392 try:
5393 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5394 except ExtractorError:
5395 redirect_warning += ' and the playlist redirect gave error'
5396 else:
5397 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5398 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5399 if selected_tab_name and selected_tab_name != requested_tab_name:
5400 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5401 else:
5402 raise ExtractorError(redirect_warning, expected=True)
18db7548 5403
37e57a9f 5404 if redirect_warning:
64f36541 5405 self.to_screen(redirect_warning)
37e57a9f 5406 self.write_debug(f'Final URL: {url}')
18db7548 5407
358de58c 5408 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5409 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5410 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5411 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5412 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5413 if tabs:
ac56cf38 5414 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5415
37e57a9f 5416 playlist = traverse_obj(
5417 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5418 if playlist:
ac56cf38 5419 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5420
37e57a9f 5421 video_id = traverse_obj(
5422 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5423 if video_id:
09f1580e 5424 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5425 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5426 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5427 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5428
8bdd16b4 5429 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5430
c5e8d7af 5431
8bdd16b4 5432class YoutubePlaylistIE(InfoExtractor):
96565c7e 5433 IE_DESC = 'YouTube playlists'
8bdd16b4 5434 _VALID_URL = r'''(?x)(?:
5435 (?:https?://)?
5436 (?:\w+\.)?
5437 (?:
5438 (?:
5439 youtube(?:kids)?\.com|
d9190e44 5440 %(invidious)s
8bdd16b4 5441 )
5442 /.*?\?.*?\blist=
5443 )?
5444 (?P<id>%(playlist_id)s)
d9190e44
RH
5445 )''' % {
5446 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5447 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5448 }
8bdd16b4 5449 IE_NAME = 'youtube:playlist'
cdc628a4 5450 _TESTS = [{
8bdd16b4 5451 'note': 'issue #673',
5452 'url': 'PLBB231211A4F62143',
cdc628a4 5453 'info_dict': {
8bdd16b4 5454 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5455 'id': 'PLBB231211A4F62143',
976ae3ea 5456 'uploader': 'Wickman',
8bdd16b4 5457 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5458 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5459 'view_count': int,
5460 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5461 'modified_date': r're:\d{8}',
5462 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5463 'channel': 'Wickman',
5464 'tags': [],
5465 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5466 },
5467 'playlist_mincount': 29,
5468 }, {
5469 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5470 'info_dict': {
5471 'title': 'YDL_safe_search',
5472 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5473 },
5474 'playlist_count': 2,
5475 'skip': 'This playlist is private',
9558dcec 5476 }, {
8bdd16b4 5477 'note': 'embedded',
5478 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5479 'playlist_count': 4,
9558dcec 5480 'info_dict': {
8bdd16b4 5481 'title': 'JODA15',
5482 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5483 'uploader': 'milan',
5484 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5485 'description': '',
5486 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5487 'tags': [],
5488 'modified_date': '20140919',
5489 'view_count': int,
5490 'channel': 'milan',
5491 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5492 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5493 },
5494 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5495 }, {
8bdd16b4 5496 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 5497 'playlist_mincount': 654,
8bdd16b4 5498 'info_dict': {
5499 'title': '2018 Chinese New Singles (11/6 updated)',
5500 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5501 'uploader': 'LBK',
5502 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5503 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5504 'channel': 'LBK',
5505 'view_count': int,
5506 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5507 'tags': [],
5508 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5509 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5510 'modified_date': r're:\d{8}',
5511 },
5512 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5513 }, {
29f7c58a 5514 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5515 'only_matching': True,
5516 }, {
5517 # music album playlist
5518 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5519 'only_matching': True,
5520 }]
5521
5522 @classmethod
5523 def suitable(cls, url):
201c1459 5524 if YoutubeTabIE.suitable(url):
5525 return False
49a57e70 5526 from ..utils import parse_qs
201c1459 5527 qs = parse_qs(url)
5528 if qs.get('v', [None])[0]:
5529 return False
86e5f3ed 5530 return super().suitable(url)
29f7c58a 5531
5532 def _real_extract(self, url):
5533 playlist_id = self._match_id(url)
46953e7e 5534 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5535 url = update_url_query(
5536 'https://www.youtube.com/playlist',
5537 parse_qs(url) or {'list': playlist_id})
5538 if is_music_url:
5539 url = smuggle_url(url, {'is_music_url': True})
5540 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5541
5542
5543class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5544 IE_DESC = 'youtu.be'
29f7c58a 5545 _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}
5546 _TESTS = [{
8bdd16b4 5547 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5548 'info_dict': {
5549 'id': 'yeWKywCrFtk',
5550 'ext': 'mp4',
5551 'title': 'Small Scale Baler and Braiding Rugs',
5552 'uploader': 'Backus-Page House Museum',
5553 'uploader_id': 'backuspagemuseum',
5554 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5555 'upload_date': '20161008',
5556 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5557 'categories': ['Nonprofits & Activism'],
5558 'tags': list,
5559 'like_count': int,
976ae3ea 5560 'age_limit': 0,
5561 'playable_in_embed': True,
5562 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5563 'channel': 'Backus-Page House Museum',
5564 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5565 'live_status': 'not_live',
5566 'view_count': int,
5567 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5568 'availability': 'public',
5569 'duration': 59,
8bdd16b4 5570 },
5571 'params': {
5572 'noplaylist': True,
5573 'skip_download': True,
5574 },
39e7107d 5575 }, {
8bdd16b4 5576 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5577 'only_matching': True,
cdc628a4
PH
5578 }]
5579
8bdd16b4 5580 def _real_extract(self, url):
5ad28e7f 5581 mobj = self._match_valid_url(url)
29f7c58a 5582 video_id = mobj.group('id')
5583 playlist_id = mobj.group('playlist_id')
8bdd16b4 5584 return self.url_result(
29f7c58a 5585 update_url_query('https://www.youtube.com/watch', {
5586 'v': video_id,
5587 'list': playlist_id,
5588 'feature': 'youtu.be',
5589 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5590
5591
b6ce9bb0 5592class YoutubeLivestreamEmbedIE(InfoExtractor):
5593 IE_DESC = 'YouTube livestream embeds'
5594 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5595 _TESTS = [{
5596 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5597 'only_matching': True,
5598 }]
5599
5600 def _real_extract(self, url):
5601 channel_id = self._match_id(url)
5602 return self.url_result(
5603 f'https://www.youtube.com/channel/{channel_id}/live',
5604 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5605
5606
8bdd16b4 5607class YoutubeYtUserIE(InfoExtractor):
96565c7e 5608 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5609 IE_NAME = 'youtube:user'
8bdd16b4 5610 _VALID_URL = r'ytuser:(?P<id>.+)'
5611 _TESTS = [{
5612 'url': 'ytuser:phihag',
5613 'only_matching': True,
5614 }]
5615
5616 def _real_extract(self, url):
5617 user_id = self._match_id(url)
5618 return self.url_result(
c586f9e8 5619 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5620 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5621
b05654f0 5622
3d3dddc9 5623class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5624 IE_NAME = 'youtube:favorites'
96565c7e 5625 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5626 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5627 _LOGIN_REQUIRED = True
5628 _TESTS = [{
5629 'url': ':ytfav',
5630 'only_matching': True,
5631 }, {
5632 'url': ':ytfavorites',
5633 'only_matching': True,
5634 }]
5635
5636 def _real_extract(self, url):
5637 return self.url_result(
5638 'https://www.youtube.com/playlist?list=LL',
5639 ie=YoutubeTabIE.ie_key())
5640
5641
ca5300c7 5642class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
5643 IE_NAME = 'youtube:notif'
5644 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5645 _VALID_URL = r':ytnotif(?:ication)?s?'
5646 _LOGIN_REQUIRED = True
5647 _TESTS = [{
5648 'url': ':ytnotif',
5649 'only_matching': True,
5650 }, {
5651 'url': ':ytnotifications',
5652 'only_matching': True,
5653 }]
5654
5655 def _extract_notification_menu(self, response, continuation_list):
5656 notification_list = traverse_obj(
5657 response,
5658 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5659 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5660 expected_type=list) or []
5661 continuation_list[0] = None
5662 for item in notification_list:
5663 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
5664 if entry:
5665 yield entry
5666 continuation = item.get('continuationItemRenderer')
5667 if continuation:
5668 continuation_list[0] = continuation
5669
5670 def _extract_notification_renderer(self, notification):
5671 video_id = traverse_obj(
5672 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
5673 url = f'https://www.youtube.com/watch?v={video_id}'
5674 channel_id = None
5675 if not video_id:
5676 browse_ep = traverse_obj(
5677 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
5678 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
5679 post_id = self._search_regex(
5680 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
5681 'post id', default=None)
5682 if not channel_id or not post_id:
5683 return
5684 # The direct /post url redirects to this in the browser
5685 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5686
5687 channel = traverse_obj(
5688 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5689 expected_type=str)
c7a7baaa 5690 notification_title = self._get_text(notification, 'shortMessage')
5691 if notification_title:
5692 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
5693 # TODO: handle recommended videos
ca5300c7 5694 title = self._search_regex(
c7a7baaa 5695 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 5696 'video title', default=None)
ca5300c7 5697 upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d')
5698 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
5699 else None)
5700 return {
5701 '_type': 'url',
5702 'url': url,
5703 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
5704 'video_id': video_id,
5705 'title': title,
5706 'channel_id': channel_id,
5707 'channel': channel,
5708 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5709 'upload_date': upload_date,
5710 }
5711
5712 def _notification_menu_entries(self, ytcfg):
5713 continuation_list = [None]
5714 response = None
5715 for page in itertools.count(1):
5716 ctoken = traverse_obj(
5717 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
5718 response = self._extract_response(
5719 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
5720 ep='notification/get_notification_menu', check_get_keys='actions',
5721 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
5722 yield from self._extract_notification_menu(response, continuation_list)
5723 if not continuation_list[0]:
5724 break
5725
5726 def _real_extract(self, url):
5727 display_id = 'notifications'
5728 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
5729 self._report_playlist_authcheck(ytcfg)
5730 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
5731
5732
a6213a49 5733class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5734 IE_DESC = 'YouTube search'
78caa52a 5735 IE_NAME = 'youtube:search'
b05654f0 5736 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5737 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5738 _TESTS = [{
5739 'url': 'ytsearch5:youtube-dl test video',
5740 'playlist_count': 5,
5741 'info_dict': {
5742 'id': 'youtube-dl test video',
5743 'title': 'youtube-dl test video',
5744 }
5745 }]
b05654f0 5746
a61fd4cf 5747
5f7cb91a 5748class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5749 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5750 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5751 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5752 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5753 _TESTS = [{
5754 'url': 'ytsearchdate5:youtube-dl test video',
5755 'playlist_count': 5,
5756 'info_dict': {
5757 'id': 'youtube-dl test video',
5758 'title': 'youtube-dl test video',
5759 }
5760 }]
75dff0ee 5761
c9ae7b95 5762
a6213a49 5763class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5764 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5765 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5766 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5767 _TESTS = [{
5768 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5769 'playlist_mincount': 5,
5770 'info_dict': {
11f9be09 5771 'id': 'youtube-dl test video',
3462ffa8 5772 'title': 'youtube-dl test video',
5773 }
a61fd4cf 5774 }, {
5775 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5776 'playlist_mincount': 5,
5777 'info_dict': {
5778 'id': 'python',
5779 'title': 'python',
5780 }
ad210f4f 5781 }, {
5782 'url': 'https://www.youtube.com/results?search_query=%23cats',
5783 'playlist_mincount': 1,
5784 'info_dict': {
5785 'id': '#cats',
5786 'title': '#cats',
5787 'entries': [{
5788 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5789 'title': '#cats',
5790 }],
5791 },
3462ffa8 5792 }, {
5793 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5794 'only_matching': True,
5795 }]
5796
5797 def _real_extract(self, url):
4dfbf869 5798 qs = parse_qs(url)
386e1dd9 5799 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5800 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5801
5802
16aa9ea4 5803class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
455a15e2 5804 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
16aa9ea4 5805 IE_NAME = 'youtube:music:search_url'
5806 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5807 _TESTS = [{
5808 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5809 'playlist_count': 16,
5810 'info_dict': {
5811 'id': 'royalty free music',
5812 'title': 'royalty free music',
5813 }
5814 }, {
5815 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5816 'playlist_mincount': 30,
5817 'info_dict': {
5818 'id': 'royalty free music - songs',
5819 'title': 'royalty free music - songs',
5820 },
5821 'params': {'extract_flat': 'in_playlist'}
5822 }, {
5823 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5824 'playlist_mincount': 30,
5825 'info_dict': {
5826 'id': 'royalty free music - community playlists',
5827 'title': 'royalty free music - community playlists',
5828 },
5829 'params': {'extract_flat': 'in_playlist'}
5830 }]
5831
5832 _SECTIONS = {
5833 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5834 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5835 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5836 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5837 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5838 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5839 }
5840
5841 def _real_extract(self, url):
5842 qs = parse_qs(url)
5843 query = (qs.get('search_query') or qs.get('q'))[0]
5844 params = qs.get('sp', (None,))[0]
5845 if params:
5846 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5847 else:
ac668111 5848 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 5849 params = self._SECTIONS.get(section)
5850 if not params:
5851 section = None
5852 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5853 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5854
5855
182bda88 5856class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5857 """
25f14e9f 5858 Base class for feed extractors
82d02080 5859 Subclasses must re-define the _FEED_NAME property.
d7ae0639 5860 """
b2e8bc1b 5861 _LOGIN_REQUIRED = True
82d02080 5862 _FEED_NAME = 'feeds'
a25bca9f 5863
5864 def _real_initialize(self):
5865 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 5866
82d02080 5867 @classproperty
d7ae0639 5868 def IE_NAME(self):
82d02080 5869 return f'youtube:{self._FEED_NAME}'
04cc9617 5870
3853309f 5871 def _real_extract(self, url):
3d3dddc9 5872 return self.url_result(
182bda88 5873 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5874
5875
ef2f3c7f 5876class YoutubeWatchLaterIE(InfoExtractor):
5877 IE_NAME = 'youtube:watchlater'
96565c7e 5878 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5879 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5880 _TESTS = [{
8bdd16b4 5881 'url': ':ytwatchlater',
bc7a9cd8
S
5882 'only_matching': True,
5883 }]
25f14e9f
S
5884
5885 def _real_extract(self, url):
ef2f3c7f 5886 return self.url_result(
5887 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5888
5889
25f14e9f 5890class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5891 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5892 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5893 _FEED_NAME = 'recommended'
45db527f 5894 _LOGIN_REQUIRED = False
3d3dddc9 5895 _TESTS = [{
5896 'url': ':ytrec',
5897 'only_matching': True,
5898 }, {
5899 'url': ':ytrecommended',
5900 'only_matching': True,
5901 }, {
5902 'url': 'https://youtube.com',
5903 'only_matching': True,
5904 }]
1ed5b5c9 5905
1ed5b5c9 5906
25f14e9f 5907class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5908 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5909 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5910 _FEED_NAME = 'subscriptions'
3d3dddc9 5911 _TESTS = [{
5912 'url': ':ytsubs',
5913 'only_matching': True,
5914 }, {
5915 'url': ':ytsubscriptions',
5916 'only_matching': True,
5917 }]
1ed5b5c9 5918
1ed5b5c9 5919
25f14e9f 5920class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5921 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5922 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5923 _FEED_NAME = 'history'
3d3dddc9 5924 _TESTS = [{
5925 'url': ':ythistory',
5926 'only_matching': True,
5927 }]
1ed5b5c9
JMF
5928
5929
6e634cbe 5930class YoutubeStoriesIE(InfoExtractor):
5931 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
5932 IE_NAME = 'youtube:stories'
5933 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
5934 _TESTS = [{
5935 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
5936 'only_matching': True,
5937 }]
5938
5939 def _real_extract(self, url):
5940 playlist_id = f'RLTD{self._match_id(url)}'
5941 return self.url_result(
5942 f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
5943 ie=YoutubeTabIE, video_id=playlist_id)
5944
5945
15870e90
PH
5946class YoutubeTruncatedURLIE(InfoExtractor):
5947 IE_NAME = 'youtube:truncated_url'
5948 IE_DESC = False # Do not list
975d35db 5949 _VALID_URL = r'''(?x)
b95aab84
PH
5950 (?:https?://)?
5951 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5952 (?:watch\?(?:
c4808c60 5953 feature=[a-z_]+|
b95aab84
PH
5954 annotation_id=annotation_[^&]+|
5955 x-yt-cl=[0-9]+|
c1708b89 5956 hl=[^&]*|
287be8c6 5957 t=[0-9]+
b95aab84
PH
5958 )?
5959 |
5960 attribution_link\?a=[^&]+
5961 )
5962 $
975d35db 5963 '''
15870e90 5964
c4808c60 5965 _TESTS = [{
2d3d2997 5966 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5967 'only_matching': True,
dc2fc736 5968 }, {
2d3d2997 5969 'url': 'https://www.youtube.com/watch?',
dc2fc736 5970 'only_matching': True,
b95aab84
PH
5971 }, {
5972 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5973 'only_matching': True,
5974 }, {
5975 'url': 'https://www.youtube.com/watch?feature=foo',
5976 'only_matching': True,
c1708b89
PH
5977 }, {
5978 'url': 'https://www.youtube.com/watch?hl=en-GB',
5979 'only_matching': True,
287be8c6
PH
5980 }, {
5981 'url': 'https://www.youtube.com/watch?t=2372',
5982 'only_matching': True,
c4808c60
PH
5983 }]
5984
15870e90
PH
5985 def _real_extract(self, url):
5986 raise ExtractorError(
78caa52a
PH
5987 'Did you forget to quote the URL? Remember that & is a meta '
5988 'character in most shells, so you want to put the URL in quotes, '
3867038a 5989 'like youtube-dl '
2d3d2997 5990 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 5991 ' or simply youtube-dl BaW_jenozKc .',
15870e90 5992 expected=True)
772fd5cc
PH
5993
5994
471d0367 5995class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 5996 IE_NAME = 'youtube:clip'
471d0367 5997 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
5998 _TESTS = [{
5999 # FIXME: Other metadata should be extracted from the clip, not from the base video
6000 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6001 'info_dict': {
6002 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6003 'ext': 'mp4',
6004 'section_start': 29.0,
6005 'section_end': 39.7,
6006 'duration': 10.7,
6007 }
6008 }]
3cd786db 6009
6010 def _real_extract(self, url):
471d0367 6011 clip_id = self._match_id(url)
6012 _, data = self._extract_webpage(url, clip_id)
6013
6014 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6015 if not video_id:
6016 raise ExtractorError('Unable to find video ID')
6017
6018 clip_data = traverse_obj(data, (
6019 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6020 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6021 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6022 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6023
6024 return {
6025 '_type': 'url_transparent',
6026 'url': f'https://www.youtube.com/watch?v={video_id}',
6027 'ie_key': YoutubeIE.ie_key(),
6028 'id': clip_id,
6029 'section_start': int(clip_data['startTimeMs']) / 1000,
6030 'section_end': int(clip_data['endTimeMs']) / 1000,
6031 }
3cd786db 6032
6033
772fd5cc
PH
6034class YoutubeTruncatedIDIE(InfoExtractor):
6035 IE_NAME = 'youtube:truncated_id'
6036 IE_DESC = False # Do not list
b95aab84 6037 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6038
6039 _TESTS = [{
6040 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6041 'only_matching': True,
6042 }]
6043
6044 def _real_extract(self, url):
6045 video_id = self._match_id(url)
6046 raise ExtractorError(
86e5f3ed 6047 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6048 expected=True)