]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[web.archive:youtube] Make CDX API requests non-fatal
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
c5e8d7af 1# coding: utf-8
c5e8d7af 2
78caa52a
PH
3from __future__ import unicode_literals
4
d92f5d5a 5import calendar
109dd3b2 6import copy
fe93e2c4 7import datetime
adbc4ec4 8import functools
a5c56234 9import hashlib
0ca96d48 10import itertools
c5e8d7af 11import json
720c3099 12import math
c4417ddb 13import os.path
d77ab8e2 14import random
c5e8d7af 15import re
46383212 16import sys
8a784c74 17import time
e0df6211 18import traceback
adbc4ec4 19import threading
c5e8d7af 20
b05654f0 21from .common import InfoExtractor, SearchInfoExtractor
4bb4a188 22from ..compat import (
edf3e38e 23 compat_chr,
29f7c58a 24 compat_HTTPError,
c5e8d7af 25 compat_parse_qs,
545cc85d 26 compat_str,
7fd002c0 27 compat_urllib_parse_unquote_plus,
15707c7e 28 compat_urllib_parse_urlencode,
7c80519c 29 compat_urllib_parse_urlparse,
7c61bd36 30 compat_urlparse,
4bb4a188 31)
545cc85d 32from ..jsinterp import JSInterpreter
4bb4a188 33from ..utils import (
720c3099 34 bug_reports_message,
c5e8d7af 35 clean_html,
d92f5d5a 36 datetime_from_str,
11f9be09 37 dict_get,
358de58c 38 error_to_compat_str,
c5e8d7af 39 ExtractorError,
2d30521a 40 float_or_none,
11f9be09 41 format_field,
ff91cf74 42 get_first,
dd27fd17 43 int_or_none,
641ad5d8 44 is_html,
34921b43 45 join_nonempty,
48416bc4 46 js_to_json,
94278f72 47 mimetype2ext,
9c0d7f49 48 network_exceptions,
a6213a49 49 NO_DEFAULT,
11f9be09 50 orderedSet,
6310acf5 51 parse_codecs,
49bd8c66 52 parse_count,
7c80519c 53 parse_duration,
7ea65411 54 parse_iso8601,
4dfbf869 55 parse_qs,
dca3ff4a 56 qualities,
c0ac49bc 57 remove_end,
3995d37d 58 remove_start,
cf7e015f 59 smuggle_url,
dbdaaa23 60 str_or_none,
c93d53f5 61 str_to_int,
f3aa3c3f 62 strftime_or_none,
7c365c21 63 traverse_obj,
556dbe7f 64 try_get,
c5e8d7af
PH
65 unescapeHTML,
66 unified_strdate,
f0d785d3 67 unified_timestamp,
cf7e015f 68 unsmuggle_url,
8bdd16b4 69 update_url_query,
21c340b8 70 url_or_none,
fe93e2c4 71 urljoin,
7c365c21 72 variadic,
c5e8d7af
PH
73)
74
5f6a1245 75
000c15a4 76# any clients starting with _ cannot be explicity requested by the user
77INNERTUBE_CLIENTS = {
78 'web': {
79 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
80 'INNERTUBE_CONTEXT': {
81 'client': {
82 'clientName': 'WEB',
18c7683d 83 'clientVersion': '2.20211221.00.00',
000c15a4 84 }
85 },
86 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
87 },
88 'web_embedded': {
89 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
90 'INNERTUBE_CONTEXT': {
91 'client': {
92 'clientName': 'WEB_EMBEDDED_PLAYER',
18c7683d 93 'clientVersion': '1.20211215.00.01',
000c15a4 94 },
95 },
96 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
97 },
98 'web_music': {
99 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
100 'INNERTUBE_HOST': 'music.youtube.com',
101 'INNERTUBE_CONTEXT': {
102 'client': {
103 'clientName': 'WEB_REMIX',
18c7683d 104 'clientVersion': '1.20211213.00.00',
000c15a4 105 }
106 },
107 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
108 },
e7e94f2a 109 'web_creator': {
18c7683d 110 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
111 'INNERTUBE_CONTEXT': {
112 'client': {
113 'clientName': 'WEB_CREATOR',
18c7683d 114 'clientVersion': '1.20211220.02.00',
e7e94f2a
D
115 }
116 },
117 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
118 },
000c15a4 119 'android': {
18c7683d 120 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 121 'INNERTUBE_CONTEXT': {
122 'client': {
123 'clientName': 'ANDROID',
18c7683d 124 'clientVersion': '16.49',
000c15a4 125 }
126 },
127 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 128 'REQUIRE_JS_PLAYER': False
000c15a4 129 },
130 'android_embedded': {
18c7683d 131 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 132 'INNERTUBE_CONTEXT': {
133 'client': {
134 'clientName': 'ANDROID_EMBEDDED_PLAYER',
18c7683d 135 'clientVersion': '16.49',
000c15a4 136 },
137 },
b6de707d 138 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
139 'REQUIRE_JS_PLAYER': False
000c15a4 140 },
141 'android_music': {
18c7683d 142 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 143 'INNERTUBE_CONTEXT': {
144 'client': {
145 'clientName': 'ANDROID_MUSIC',
18c7683d 146 'clientVersion': '4.57',
000c15a4 147 }
148 },
149 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 150 'REQUIRE_JS_PLAYER': False
000c15a4 151 },
e7e94f2a 152 'android_creator': {
18c7683d 153 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
154 'INNERTUBE_CONTEXT': {
155 'client': {
156 'clientName': 'ANDROID_CREATOR',
18c7683d 157 'clientVersion': '21.47',
e7e94f2a
D
158 },
159 },
b6de707d 160 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
161 'REQUIRE_JS_PLAYER': False
e7e94f2a 162 },
18c7683d 163 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
164 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 165 'ios': {
18c7683d 166 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 167 'INNERTUBE_CONTEXT': {
168 'client': {
169 'clientName': 'IOS',
18c7683d 170 'clientVersion': '16.46',
171 'deviceModel': 'iPhone14,3',
000c15a4 172 }
173 },
b6de707d 174 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
175 'REQUIRE_JS_PLAYER': False
000c15a4 176 },
177 'ios_embedded': {
000c15a4 178 'INNERTUBE_CONTEXT': {
179 'client': {
180 'clientName': 'IOS_MESSAGES_EXTENSION',
18c7683d 181 'clientVersion': '16.46',
182 'deviceModel': 'iPhone14,3',
000c15a4 183 },
184 },
b6de707d 185 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
186 'REQUIRE_JS_PLAYER': False
000c15a4 187 },
188 'ios_music': {
18c7683d 189 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 190 'INNERTUBE_CONTEXT': {
191 'client': {
192 'clientName': 'IOS_MUSIC',
18c7683d 193 'clientVersion': '4.57',
000c15a4 194 },
195 },
b6de707d 196 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
197 'REQUIRE_JS_PLAYER': False
000c15a4 198 },
e7e94f2a
D
199 'ios_creator': {
200 'INNERTUBE_CONTEXT': {
201 'client': {
202 'clientName': 'IOS_CREATOR',
18c7683d 203 'clientVersion': '21.47',
e7e94f2a
D
204 },
205 },
b6de707d 206 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
207 'REQUIRE_JS_PLAYER': False
e7e94f2a 208 },
3619f78d 209 # mweb has 'ultralow' formats
210 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 211 'mweb': {
18c7683d 212 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 213 'INNERTUBE_CONTEXT': {
214 'client': {
215 'clientName': 'MWEB',
18c7683d 216 'clientVersion': '2.20211221.01.00',
000c15a4 217 }
218 },
219 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
220 },
221 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
222 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
223 'tv_embedded': {
224 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
225 'INNERTUBE_CONTEXT': {
226 'client': {
227 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
228 'clientVersion': '2.0',
229 },
230 },
231 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
232 },
000c15a4 233}
234
235
e7870111
D
236def _split_innertube_client(client_name):
237 variant, *base = client_name.rsplit('.', 1)
238 if base:
239 return variant, base[0], variant
240 base, *variant = client_name.split('_', 1)
241 return client_name, base, variant[0] if variant else None
242
243
000c15a4 244def build_innertube_clients():
2e4cacd0 245 THIRD_PARTY = {
e7870111 246 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 247 }
e7870111 248 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 249 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 250
251 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 252 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 253 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 254 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 255 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 256
e7870111 257 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 258 ytcfg['priority'] = 10 * priority(base_client)
259
e48b3875 260 if not variant:
e7870111
D
261 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
262 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
263 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
264 embedscreen['priority'] -= 3
265 elif variant == 'embedded':
e48b3875 266 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 267 ytcfg['priority'] -= 2
e48b3875 268 else:
000c15a4 269 ytcfg['priority'] -= 3
270
271
272build_innertube_clients()
273
274
de7f3446 275class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 276 """Provide base functions for Youtube extractors"""
e00eb564 277
3462ffa8 278 _RESERVED_NAMES = (
3cd786db 279 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 280 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 281 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 282 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 283
3619f78d 284 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
285
52efa4b3 286 # _NETRC_MACHINE = 'youtube'
3619f78d 287
b2e8bc1b
JMF
288 # If True it will raise an error if no login info is provided
289 _LOGIN_REQUIRED = False
290
d9190e44
RH
291 _INVIDIOUS_SITES = (
292 # invidious-redirect websites
293 r'(?:www\.)?redirect\.invidious\.io',
294 r'(?:(?:www|dev)\.)?invidio\.us',
295 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
296 r'(?:www\.)?invidious\.pussthecat\.org',
297 r'(?:www\.)?invidious\.zee\.li',
298 r'(?:www\.)?invidious\.ethibox\.fr',
299 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
300 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
301 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
302 # youtube-dl invidious instances list
303 r'(?:(?:www|no)\.)?invidiou\.sh',
304 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
305 r'(?:www\.)?invidious\.kabi\.tk',
306 r'(?:www\.)?invidious\.mastodon\.host',
307 r'(?:www\.)?invidious\.zapashcanon\.fr',
308 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
309 r'(?:www\.)?invidious\.tinfoil-hat\.net',
310 r'(?:www\.)?invidious\.himiko\.cloud',
311 r'(?:www\.)?invidious\.reallyancient\.tech',
312 r'(?:www\.)?invidious\.tube',
313 r'(?:www\.)?invidiou\.site',
314 r'(?:www\.)?invidious\.site',
315 r'(?:www\.)?invidious\.xyz',
316 r'(?:www\.)?invidious\.nixnet\.xyz',
317 r'(?:www\.)?invidious\.048596\.xyz',
318 r'(?:www\.)?invidious\.drycat\.fr',
319 r'(?:www\.)?inv\.skyn3t\.in',
320 r'(?:www\.)?tube\.poal\.co',
321 r'(?:www\.)?tube\.connect\.cafe',
322 r'(?:www\.)?vid\.wxzm\.sx',
323 r'(?:www\.)?vid\.mint\.lgbt',
324 r'(?:www\.)?vid\.puffyan\.us',
325 r'(?:www\.)?yewtu\.be',
326 r'(?:www\.)?yt\.elukerio\.org',
327 r'(?:www\.)?yt\.lelux\.fi',
328 r'(?:www\.)?invidious\.ggc-project\.de',
329 r'(?:www\.)?yt\.maisputain\.ovh',
330 r'(?:www\.)?ytprivate\.com',
331 r'(?:www\.)?invidious\.13ad\.de',
332 r'(?:www\.)?invidious\.toot\.koeln',
333 r'(?:www\.)?invidious\.fdn\.fr',
334 r'(?:www\.)?watch\.nettohikari\.com',
335 r'(?:www\.)?invidious\.namazso\.eu',
336 r'(?:www\.)?invidious\.silkky\.cloud',
337 r'(?:www\.)?invidious\.exonip\.de',
338 r'(?:www\.)?invidious\.riverside\.rocks',
339 r'(?:www\.)?invidious\.blamefran\.net',
340 r'(?:www\.)?invidious\.moomoo\.de',
341 r'(?:www\.)?ytb\.trom\.tf',
342 r'(?:www\.)?yt\.cyberhost\.uk',
343 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
344 r'(?:www\.)?qklhadlycap4cnod\.onion',
345 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
346 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
347 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
348 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
349 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
350 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
351 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
352 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
353 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
354 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
355 )
356
cce889b9 357 def _initialize_consent(self):
358 cookies = self._get_cookies('https://www.youtube.com/')
359 if cookies.get('__Secure-3PSID'):
360 return
361 consent_id = None
362 consent = cookies.get('CONSENT')
363 if consent:
364 if 'YES' in consent.value:
365 return
366 consent_id = self._search_regex(
367 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
368 if not consent_id:
369 consent_id = random.randint(100, 999)
370 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 371
f3aa3c3f 372 def _initialize_pref(self):
373 cookies = self._get_cookies('https://www.youtube.com/')
374 pref_cookie = cookies.get('PREF')
375 pref = {}
376 if pref_cookie:
377 try:
378 pref = dict(compat_urlparse.parse_qsl(pref_cookie.value))
379 except ValueError:
380 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 381 pref.update({'hl': 'en', 'tz': 'UTC'})
f3aa3c3f 382 self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref))
383
b2e8bc1b 384 def _real_initialize(self):
f3aa3c3f 385 self._initialize_pref()
cce889b9 386 self._initialize_consent()
52efa4b3 387 if (self._LOGIN_REQUIRED
388 and self.get_param('cookiefile') is None
389 and self.get_param('cookiesfrombrowser') is None):
390 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 391
a0566bbf 392 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
29f7c58a 393 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
394 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
a0566bbf 395
000c15a4 396 def _get_default_ytcfg(self, client='web'):
397 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 398
000c15a4 399 def _get_innertube_host(self, client='web'):
400 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 401
000c15a4 402 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 403 # try_get but with fallback to default ytcfg client values when present
404 _func = lambda y: try_get(y, getter, expected_type)
405 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
406
000c15a4 407 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 408 return self._ytcfg_get_safe(
409 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
410 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
109dd3b2 411
000c15a4 412 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 413 return self._ytcfg_get_safe(
414 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
415 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
109dd3b2 416
000c15a4 417 def _extract_api_key(self, ytcfg=None, default_client='web'):
109dd3b2 418 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
419
000c15a4 420 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 421 context = get_first(
422 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 423 # Enforce language and tz for extraction
424 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
425 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 426 return context
427
cf87314d 428 _SAPISID = None
429
109dd3b2 430 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 431 time_now = round(time.time())
cf87314d 432 if self._SAPISID is None:
433 yt_cookies = self._get_cookies('https://www.youtube.com')
434 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
435 # See: https://github.com/yt-dlp/yt-dlp/issues/393
436 sapisid_cookie = dict_get(
437 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
438 if sapisid_cookie and sapisid_cookie.value:
439 self._SAPISID = sapisid_cookie.value
440 self.write_debug('Extracted SAPISID cookie')
441 # SAPISID cookie is required if not already present
442 if not yt_cookies.get('SAPISID'):
443 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
444 self._set_cookie(
445 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
446 else:
447 self._SAPISID = False
448 if not self._SAPISID:
449 return None
1974e99f 450 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
451 sapisidhash = hashlib.sha1(
cf87314d 452 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
1974e99f 453 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
454
455 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 456 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 457 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 458
109dd3b2 459 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 460 data.update(query)
11f9be09 461 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 462 real_headers.update({'content-type': 'application/json'})
463 if headers:
464 real_headers.update(headers)
545cc85d 465 return self._download_json(
109dd3b2 466 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
a5c56234 467 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 468 data=json.dumps(data).encode('utf8'), headers=real_headers,
5dbc77df 469 query={'key': api_key or self._extract_api_key(), 'prettyPrint': 'false'})
f4f751af 470
ac56cf38 471 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
472 data = self._search_regex(
473 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
474 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
475 if data:
476 return self._parse_json(data, item_id, fatal=fatal)
0c148415 477
99e9e001 478 @staticmethod
479 def _extract_session_index(*data):
480 """
481 Index of current account in account list.
482 See: https://github.com/yt-dlp/yt-dlp/pull/519
483 """
484 for ytcfg in data:
485 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
486 if session_index is not None:
487 return session_index
488
489 # Deprecated?
490 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca
M
491 if ytcfg:
492 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
493 if token:
494 return token
99e9e001 495 if webpage:
496 return self._search_regex(
497 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
498 'identity token', default=None, fatal=False)
a1c5d2ca
M
499
500 @staticmethod
fe93e2c4 501 def _extract_account_syncid(*args):
8ea3f7b9 502 """
503 Extract syncId required to download private playlists of secondary channels
fe93e2c4 504 @params response and/or ytcfg
8ea3f7b9 505 """
fe93e2c4 506 for data in args:
507 # ytcfg includes channel_syncid if on secondary channel
508 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str)
509 if delegated_sid:
510 return delegated_sid
511 sync_ids = (try_get(
512 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
e6f21b3d 513 lambda x: x['DATASYNC_ID']), compat_str) or '').split('||')
fe93e2c4 514 if len(sync_ids) >= 2 and sync_ids[1]:
515 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
516 # and just "user_syncid||" for primary channel. We only want the channel_syncid
517 return sync_ids[0]
a1c5d2ca 518
ac56cf38 519 @staticmethod
520 def _extract_visitor_data(*args):
521 """
522 Extracts visitorData from an API response or ytcfg
523 Appears to be used to track session state
524 """
9222c381 525 return get_first(
6c73052c 526 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 527 expected_type=str)
ac56cf38 528
99e9e001 529 @property
530 def is_authenticated(self):
531 return bool(self._generate_sapisidhash_header())
532
11f9be09 533 def extract_ytcfg(self, video_id, webpage):
8c54a305 534 if not webpage:
535 return {}
29f7c58a 536 return self._parse_json(
537 self._search_regex(
538 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 539 default='{}'), video_id, fatal=False) or {}
540
11f9be09 541 def generate_api_headers(
99e9e001 542 self, *, ytcfg=None, account_syncid=None, session_index=None,
543 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
544
11f9be09 545 origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client))
f4f751af 546 headers = {
109dd3b2 547 'X-YouTube-Client-Name': compat_str(
11f9be09 548 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
549 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 550 'Origin': origin,
551 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
552 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 553 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 554 }
555 if session_index is None:
314ee305 556 session_index = self._extract_session_index(ytcfg)
557 if account_syncid or session_index is not None:
558 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 559
109dd3b2 560 auth = self._generate_sapisidhash_header(origin)
f4f751af 561 if auth is not None:
562 headers['Authorization'] = auth
109dd3b2 563 headers['X-Origin'] = origin
99e9e001 564 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 565
2d6659b9 566 @staticmethod
567 def _build_api_continuation_query(continuation, ctp=None):
568 query = {
569 'continuation': continuation
570 }
571 # TODO: Inconsistency with clickTrackingParams.
572 # Currently we have a fixed ctp contained within context (from ytcfg)
573 # and a ctp in root query for continuation.
574 if ctp:
575 query['clickTracking'] = {'clickTrackingParams': ctp}
576 return query
577
2d6659b9 578 @classmethod
579 def _extract_next_continuation_data(cls, renderer):
580 next_continuation = try_get(
581 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
582 lambda x: x['continuation']['reloadContinuationData']), dict)
583 if not next_continuation:
584 return
585 continuation = next_continuation.get('continuation')
586 if not continuation:
587 return
588 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 589 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 590
591 @classmethod
592 def _extract_continuation_ep_data(cls, continuation_ep: dict):
593 if isinstance(continuation_ep, dict):
594 continuation = try_get(
595 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
596 if not continuation:
597 return
598 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 599 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 600
601 @classmethod
602 def _extract_continuation(cls, renderer):
603 next_continuation = cls._extract_next_continuation_data(renderer)
604 if next_continuation:
605 return next_continuation
fe93e2c4 606
2d6659b9 607 contents = []
608 for key in ('contents', 'items'):
609 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 610
2d6659b9 611 for content in contents:
612 if not isinstance(content, dict):
613 continue
614 continuation_ep = try_get(
615 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
616 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
617 dict)
618 continuation = cls._extract_continuation_ep_data(continuation_ep)
619 if continuation:
620 return continuation
621
fe93e2c4 622 @classmethod
623 def _extract_alerts(cls, data):
109dd3b2 624 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
625 if not isinstance(alert_dict, dict):
626 continue
627 for alert in alert_dict.values():
628 alert_type = alert.get('type')
629 if not alert_type:
630 continue
052e1350 631 message = cls._get_text(alert, 'text')
109dd3b2 632 if message:
633 yield alert_type, message
634
c0ac49bc 635 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 636 errors = []
637 warnings = []
638 for alert_type, alert_message in alerts:
641ad5d8 639 if alert_type.lower() == 'error' and fatal:
109dd3b2 640 errors.append([alert_type, alert_message])
641 else:
642 warnings.append([alert_type, alert_message])
643
644 for alert_type, alert_message in (warnings + errors[:-1]):
c0ac49bc 645 self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message), only_once=only_once)
109dd3b2 646 if errors:
647 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
648
649 def _extract_and_report_alerts(self, data, *args, **kwargs):
650 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
651
47193e02 652 def _extract_badges(self, renderer: dict):
653 badges = set()
654 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
655 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str)
656 if label:
657 badges.add(label.lower())
658 return badges
659
660 @staticmethod
052e1350 661 def _get_text(data, *path_list, max_runs=None):
662 for path in path_list or [None]:
663 if path is None:
664 obj = [data]
665 else:
666 obj = traverse_obj(data, path, default=[])
667 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
668 obj = [obj]
669 for item in obj:
670 text = try_get(item, lambda x: x['simpleText'], compat_str)
671 if text:
672 return text
673 runs = try_get(item, lambda x: x['runs'], list) or []
674 if not runs and isinstance(item, list):
675 runs = item
676
677 runs = runs[:min(len(runs), max_runs or len(runs))]
678 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
679 if text:
680 return text
47193e02 681
f0d785d3 682 def _get_count(self, data, *path_list):
683 count_text = self._get_text(data, *path_list) or ''
684 count = parse_count(count_text)
685 if count is None:
686 count = str_to_int(
687 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
688 return count
689
a709d873 690 @staticmethod
691 def _extract_thumbnails(data, *path_list):
692 """
693 Extract thumbnails from thumbnails dict
694 @param path_list: path list to level that contains 'thumbnails' key
695 """
696 thumbnails = []
697 for path in path_list or [()]:
698 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
699 thumbnail_url = url_or_none(thumbnail.get('url'))
700 if not thumbnail_url:
701 continue
702 # Sometimes youtube gives a wrong thumbnail URL. See:
703 # https://github.com/yt-dlp/yt-dlp/issues/233
704 # https://github.com/ytdl-org/youtube-dl/issues/28023
705 if 'maxresdefault' in thumbnail_url:
706 thumbnail_url = thumbnail_url.split('?')[0]
707 thumbnails.append({
708 'url': thumbnail_url,
709 'height': int_or_none(thumbnail.get('height')),
710 'width': int_or_none(thumbnail.get('width')),
711 })
712 return thumbnails
713
f3aa3c3f 714 @staticmethod
715 def extract_relative_time(relative_time_text):
716 """
717 Extracts a relative time from string and converts to dt object
f0d785d3 718 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 719 """
f0d785d3 720 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 721 if mobj:
f0d785d3 722 start = mobj.group('start')
723 if start:
724 return datetime_from_str(start)
f3aa3c3f 725 try:
f0d785d3 726 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 727 except ValueError:
728 return None
729
730 def _extract_time_text(self, renderer, *path_list):
731 text = self._get_text(renderer, *path_list) or ''
732 dt = self.extract_relative_time(text)
733 timestamp = None
734 if isinstance(dt, datetime.datetime):
735 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 736
737 if timestamp is None:
738 timestamp = (
739 unified_timestamp(text) or unified_timestamp(
740 self._search_regex(
17322130 741 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 742 text.lower(), 'time text', default=None)))
f0d785d3 743
f3aa3c3f 744 if text and timestamp is None:
17322130 745 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
f3aa3c3f 746 return timestamp, text
747
109dd3b2 748 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
749 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 750 default_client='web'):
109dd3b2 751 response = None
752 last_error = None
753 count = -1
754 retries = self.get_param('extractor_retries', 3)
755 if check_get_keys is None:
756 check_get_keys = []
757 while count < retries:
758 count += 1
759 if last_error:
c0ac49bc 760 self.report_warning('%s. Retrying ...' % remove_end(last_error, '.'))
109dd3b2 761 try:
762 response = self._call_api(
763 ep=ep, fatal=True, headers=headers,
764 video_id=item_id, query=query,
765 context=self._extract_context(ytcfg, default_client),
766 api_key=self._extract_api_key(ytcfg, default_client),
767 api_hostname=api_hostname, default_client=default_client,
768 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
769 except ExtractorError as e:
9c0d7f49 770 if isinstance(e.cause, network_exceptions):
87e8e8a7 771 if isinstance(e.cause, compat_HTTPError):
772 first_bytes = e.cause.read(512)
773 if not is_html(first_bytes):
774 yt_error = try_get(
775 self._parse_json(
776 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
777 lambda x: x['error']['message'], compat_str)
778 if yt_error:
779 self._report_alerts([('ERROR', yt_error)], fatal=False)
109dd3b2 780 # Downloading page may result in intermittent 5xx HTTP error
781 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
9c0d7f49 782 # We also want to catch all other network exceptions since errors in later pages can be troublesome
783 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
784 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
526d74ec 785 last_error = error_to_compat_str(e.cause or e.msg)
9c0d7f49 786 if count < retries:
787 continue
109dd3b2 788 if fatal:
789 raise
790 else:
791 self.report_warning(error_to_compat_str(e))
792 return
793
794 else:
109dd3b2 795 try:
ac56cf38 796 self._extract_and_report_alerts(response, only_once=True)
109dd3b2 797 except ExtractorError as e:
c0ac49bc 798 # YouTube servers may return errors we want to retry on in a 200 OK response
799 # See: https://github.com/yt-dlp/yt-dlp/issues/839
800 if 'unknown error' in e.msg.lower():
801 last_error = e.msg
802 continue
109dd3b2 803 if fatal:
804 raise
805 self.report_warning(error_to_compat_str(e))
806 return
807 if not check_get_keys or dict_get(response, check_get_keys):
808 break
809 # Youtube sometimes sends incomplete data
810 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
811 last_error = 'Incomplete data received'
812 if count >= retries:
813 if fatal:
814 raise ExtractorError(last_error)
815 else:
816 self.report_warning(last_error)
817 return
818 return response
819
9297939e 820 @staticmethod
821 def is_music_url(url):
822 return re.match(r'https?://music\.youtube\.com/', url) is not None
823
30a074c2 824 def _extract_video(self, renderer):
825 video_id = renderer.get('videoId')
052e1350 826 title = self._get_text(renderer, 'title')
827 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 828 duration = parse_duration(self._get_text(
829 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 830 if duration is None:
831 duration = parse_duration(self._search_regex(
832 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
833 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
834 video_id, default=None, group='duration'))
835
f0d785d3 836 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 837
052e1350 838 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 839 channel_id = traverse_obj(
840 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), expected_type=str, get_all=False)
841 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
842 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
843 overlay_style = traverse_obj(
844 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all=False, expected_type=str)
845 badges = self._extract_badges(renderer)
a709d873 846 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
fd2ad7cb 847 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
848 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'), expected_type=str))
849 url = f'https://www.youtube.com/watch?v={video_id}'
850 if overlay_style == 'SHORTS' or (navigation_url and '/shorts/' in navigation_url):
851 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 852
30a074c2 853 return {
39ed931e 854 '_type': 'url',
30a074c2 855 'ie_key': YoutubeIE.ie_key(),
856 'id': video_id,
fd2ad7cb 857 'url': url,
30a074c2 858 'title': title,
859 'description': description,
860 'duration': duration,
861 'view_count': view_count,
862 'uploader': uploader,
f3aa3c3f 863 'channel_id': channel_id,
a709d873 864 'thumbnails': thumbnails,
a30a6ed3 865 'upload_date': strftime_or_none(timestamp, '%Y%m%d') if self._configuration_arg('approximate_date', ie_key='youtubetab') else None,
f3aa3c3f 866 'live_status': ('is_upcoming' if scheduled_timestamp is not None
867 else 'was_live' if 'streamed' in time_text.lower()
868 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
869 else None),
870 'release_timestamp': scheduled_timestamp,
871 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 872 }
873
0c148415 874
360e1ca5 875class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 876 IE_DESC = 'YouTube'
cb7dfeea 877 _VALID_URL = r"""(?x)^
c5e8d7af 878 (
edb53e2d 879 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 880 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
881 (?:www\.)?deturl\.com/www\.youtube\.com|
882 (?:www\.)?pwnyoutube\.com|
883 (?:www\.)?hooktube\.com|
884 (?:www\.)?yourepeat\.com|
885 tube\.majestyc\.net|
886 %(invidious)s|
887 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
888 (?:.*?\#/)? # handle anchor (#/) redirect urls
889 (?: # the various things that can precede the ID:
b6ce9bb0 890 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 891 |(?: # or the v= param in all its forms
f7000f3a 892 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 893 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 894 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
895 v=
896 )
f4b05232 897 ))
cbaed4bb
S
898 |(?:
899 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
900 vid\.plus| # or vid.plus/xxxx
901 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 902 %(invidious)s
cbaed4bb 903 )/
edb53e2d 904 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 905 )
c5e8d7af 906 )? # all until now is optional -> you can pass the naked ID
201c1459 907 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 908 (?(1).+)? # if we found the ID, everything can follow
9297939e 909 (?:\#|$)""" % {
d9190e44 910 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 911 }
e40c758c 912 _PLAYER_INFO_RE = (
cc2db878 913 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
914 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$',
545cc85d 915 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 916 )
2c62dc26 917 _formats = {
c2d3cb4c 918 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
919 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
920 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
921 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
922 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
923 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
924 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
925 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 926 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 927 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
928 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
929 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
930 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
931 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
932 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 933 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 934 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
935 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 936
937
938 # 3D videos
c2d3cb4c 939 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
940 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
941 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
942 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 943 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
944 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
945 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 946
96fb5605 947 # Apple HTTP Live Streaming
11f12195 948 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 949 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
950 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
951 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
952 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
953 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 954 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
955 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
956
957 # DASH mp4 video
d23028a8
S
958 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
959 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
960 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
961 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
962 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 963 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
964 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
965 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
966 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
967 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
968 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
969 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 970
f6f1fc92 971 # Dash mp4 audio
d23028a8
S
972 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
973 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
974 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
975 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
976 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
977 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
978 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
979
980 # Dash webm
d23028a8
S
981 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
982 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
983 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
984 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
985 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
986 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
987 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
988 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
989 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
990 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
991 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
992 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
993 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
994 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
995 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 996 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
997 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
998 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
999 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1000 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1001 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1002 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1003
1004 # Dash webm audio
d23028a8
S
1005 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1006 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1007
0857baad 1008 # Dash webm audio with opus inside
d23028a8
S
1009 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1010 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1011 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1012
ce6b9a2d
PH
1013 # RTMP (unnamed)
1014 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1015
1016 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1017 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1018 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1019 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1020 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1021 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1022 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1023 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1024 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1025 }
29f7c58a 1026 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1027
fd5c4aab
S
1028 _GEO_BYPASS = False
1029
78caa52a 1030 IE_NAME = 'youtube'
2eb88d95
PH
1031 _TESTS = [
1032 {
2d3d2997 1033 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1034 'info_dict': {
1035 'id': 'BaW_jenozKc',
1036 'ext': 'mp4',
3867038a 1037 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1038 'uploader': 'Philipp Hagemeister',
1039 'uploader_id': 'phihag',
ec85ded8 1040 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1041 'channel': 'Philipp Hagemeister',
dd4c4492
S
1042 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1043 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1044 'upload_date': '20121002',
ff9f925b 1045 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1046 'categories': ['Science & Technology'],
3867038a 1047 'tags': ['youtube-dl'],
556dbe7f 1048 'duration': 10,
dbdaaa23 1049 'view_count': int,
3e7c1224 1050 'like_count': int,
ff9f925b 1051 'availability': 'public',
1052 'playable_in_embed': True,
1053 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1054 'live_status': 'not_live',
1055 'age_limit': 0,
7c80519c 1056 'start_time': 1,
297a564b 1057 'end_time': 9,
6c73052c 1058 'channel_follower_count': int
2eb88d95 1059 }
0e853ca4 1060 },
fccd3771 1061 {
4bc3a23e
PH
1062 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1063 'note': 'Embed-only video (#1746)',
1064 'info_dict': {
1065 'id': 'yZIXLfi8CZQ',
1066 'ext': 'mp4',
1067 'upload_date': '20120608',
1068 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1069 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1070 'uploader': 'SET India',
94bfcd23 1071 'uploader_id': 'setindia',
ec85ded8 1072 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1073 'age_limit': 18,
545cc85d 1074 },
1075 'skip': 'Private video',
fccd3771 1076 },
11b56058 1077 {
8bdd16b4 1078 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1079 'note': 'Use the first video ID in the URL',
1080 'info_dict': {
1081 'id': 'BaW_jenozKc',
1082 'ext': 'mp4',
3867038a 1083 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1084 'uploader': 'Philipp Hagemeister',
1085 'uploader_id': 'phihag',
ec85ded8 1086 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1087 'channel': 'Philipp Hagemeister',
1088 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1089 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1090 'upload_date': '20121002',
976ae3ea 1091 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1092 'categories': ['Science & Technology'],
3867038a 1093 'tags': ['youtube-dl'],
556dbe7f 1094 'duration': 10,
dbdaaa23 1095 'view_count': int,
11b56058 1096 'like_count': int,
976ae3ea 1097 'availability': 'public',
1098 'playable_in_embed': True,
1099 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1100 'live_status': 'not_live',
1101 'age_limit': 0,
6c73052c 1102 'channel_follower_count': int
34a7de29
S
1103 },
1104 'params': {
1105 'skip_download': True,
1106 },
11b56058 1107 },
dd27fd17 1108 {
2d3d2997 1109 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1110 'note': '256k DASH audio (format 141) via DASH manifest',
1111 'info_dict': {
1112 'id': 'a9LDPn-MO4I',
1113 'ext': 'm4a',
1114 'upload_date': '20121002',
1115 'uploader_id': '8KVIDEO',
ec85ded8 1116 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1117 'description': '',
1118 'uploader': '8KVIDEO',
1119 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1120 },
4bc3a23e
PH
1121 'params': {
1122 'youtube_include_dash_manifest': True,
1123 'format': '141',
4919603f 1124 },
de3c7fe0 1125 'skip': 'format 141 not served anymore',
dd27fd17 1126 },
8bdd16b4 1127 # DASH manifest with encrypted signature
1128 {
1129 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1130 'info_dict': {
1131 'id': 'IB3lcPjvWLA',
1132 'ext': 'm4a',
1133 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1134 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1135 'duration': 244,
1136 'uploader': 'AfrojackVEVO',
1137 'uploader_id': 'AfrojackVEVO',
1138 'upload_date': '20131011',
cc2db878 1139 'abr': 129.495,
976ae3ea 1140 'like_count': int,
1141 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1142 'playable_in_embed': True,
1143 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1144 'view_count': int,
1145 'track': 'The Spark',
1146 'live_status': 'not_live',
1147 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1148 'channel': 'Afrojack',
1149 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1150 'tags': 'count:19',
1151 'availability': 'public',
1152 'categories': ['Music'],
1153 'age_limit': 0,
1154 'alt_title': 'The Spark',
6c73052c 1155 'channel_follower_count': int
8bdd16b4 1156 },
1157 'params': {
1158 'youtube_include_dash_manifest': True,
1159 'format': '141/bestaudio[ext=m4a]',
1160 },
1161 },
65c2fde2 1162 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1163 {
65c2fde2 1164 'note': 'Embed allowed age-gate video',
2d3d2997 1165 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1166 'info_dict': {
1167 'id': 'HtVdAasjOgU',
1168 'ext': 'mp4',
1169 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1170 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1171 'duration': 142,
c522adb1
JMF
1172 'uploader': 'The Witcher',
1173 'uploader_id': 'WitcherGame',
ec85ded8 1174 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1175 'upload_date': '20140605',
34952f09 1176 'age_limit': 18,
976ae3ea 1177 'categories': ['Gaming'],
1178 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1179 'availability': 'needs_auth',
1180 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1181 'like_count': int,
1182 'channel': 'The Witcher',
1183 'live_status': 'not_live',
1184 'tags': 'count:17',
1185 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1186 'playable_in_embed': True,
1187 'view_count': int,
6c73052c 1188 'channel_follower_count': int
c522adb1
JMF
1189 },
1190 },
65c2fde2 1191 {
1192 'note': 'Age-gate video with embed allowed in public site',
1193 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1194 'info_dict': {
1195 'id': 'HsUATh_Nc2U',
1196 'ext': 'mp4',
1197 'title': 'Godzilla 2 (Official Video)',
1198 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1199 'upload_date': '20200408',
1200 'uploader_id': 'FlyingKitty900',
1201 'uploader': 'FlyingKitty',
1202 'age_limit': 18,
976ae3ea 1203 'availability': 'needs_auth',
1204 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1205 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1206 'channel': 'FlyingKitty',
1207 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1208 'view_count': int,
1209 'categories': ['Entertainment'],
1210 'live_status': 'not_live',
1211 'tags': ['Flyingkitty', 'godzilla 2'],
1212 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1213 'like_count': int,
1214 'duration': 177,
1215 'playable_in_embed': True,
6c73052c 1216 'channel_follower_count': int
65c2fde2 1217 },
1218 },
1219 {
1220 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1221 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1222 'info_dict': {
1223 'id': 'Tq92D6wQ1mg',
1224 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1225 'ext': 'mp4',
17322130 1226 'upload_date': '20191228',
65c2fde2 1227 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1228 'uploader': 'Projekt Melody',
1229 'description': 'md5:17eccca93a786d51bc67646756894066',
1230 'age_limit': 18,
976ae3ea 1231 'like_count': int,
1232 'availability': 'needs_auth',
1233 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1234 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1235 'view_count': int,
1236 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1237 'channel': 'Projekt Melody',
1238 'live_status': 'not_live',
1239 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1240 'playable_in_embed': True,
1241 'categories': ['Entertainment'],
1242 'duration': 106,
1243 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
6c73052c 1244 'channel_follower_count': int
65c2fde2 1245 },
1246 },
1247 {
1248 'note': 'Non-Agegated non-embeddable video',
1249 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1250 'info_dict': {
1251 'id': 'MeJVWBSsPAY',
1252 'ext': 'mp4',
1253 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1254 'uploader': 'Herr Lurik',
1255 'uploader_id': 'st3in234',
1256 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1257 'upload_date': '20130730',
976ae3ea 1258 'track': 'Such mich find mich',
1259 'age_limit': 0,
1260 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1261 'like_count': int,
1262 'playable_in_embed': False,
1263 'creator': 'OOMPH!',
1264 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1265 'view_count': int,
1266 'alt_title': 'Such mich find mich',
1267 'duration': 210,
1268 'channel': 'Herr Lurik',
1269 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1270 'categories': ['Music'],
1271 'availability': 'public',
1272 'uploader_url': 'http://www.youtube.com/user/st3in234',
1273 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1274 'live_status': 'not_live',
1275 'artist': 'OOMPH!',
6c73052c 1276 'channel_follower_count': int
65c2fde2 1277 },
1278 },
1279 {
1280 'note': 'Non-bypassable age-gated video',
1281 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1282 'only_matching': True,
1283 },
8bdd16b4 1284 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1285 # YouTube Red ad is not captured for creator
1286 {
1287 'url': '__2ABJjxzNo',
1288 'info_dict': {
1289 'id': '__2ABJjxzNo',
1290 'ext': 'mp4',
1291 'duration': 266,
1292 'upload_date': '20100430',
1293 'uploader_id': 'deadmau5',
1294 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1295 'creator': 'deadmau5',
1296 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1297 'uploader': 'deadmau5',
1298 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1299 'alt_title': 'Some Chords',
976ae3ea 1300 'availability': 'public',
1301 'tags': 'count:14',
1302 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1303 'view_count': int,
1304 'live_status': 'not_live',
1305 'channel': 'deadmau5',
1306 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1307 'like_count': int,
1308 'track': 'Some Chords',
1309 'artist': 'deadmau5',
1310 'playable_in_embed': True,
1311 'age_limit': 0,
1312 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1313 'categories': ['Music'],
1314 'album': 'Some Chords',
6c73052c 1315 'channel_follower_count': int
8bdd16b4 1316 },
1317 'expected_warnings': [
1318 'DASH manifest missing',
1319 ]
1320 },
067aa17e 1321 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1322 {
1323 'url': 'lqQg6PlCWgI',
1324 'info_dict': {
1325 'id': 'lqQg6PlCWgI',
1326 'ext': 'mp4',
556dbe7f 1327 'duration': 6085,
90227264 1328 'upload_date': '20150827',
cbe2bd91 1329 'uploader_id': 'olympic',
ec85ded8 1330 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
cbe2bd91 1331 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
11f9be09 1332 'uploader': 'Olympics',
cbe2bd91 1333 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1334 'like_count': int,
1335 'release_timestamp': 1343767800,
1336 'playable_in_embed': True,
1337 'categories': ['Sports'],
1338 'release_date': '20120731',
1339 'channel': 'Olympics',
1340 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1341 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1342 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1343 'age_limit': 0,
1344 'availability': 'public',
1345 'live_status': 'was_live',
1346 'view_count': int,
1347 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1348 'channel_follower_count': int
cbe2bd91
PH
1349 },
1350 'params': {
1351 'skip_download': 'requires avconv',
e52a40ab 1352 }
cbe2bd91 1353 },
6271f1ca
PH
1354 # Non-square pixels
1355 {
1356 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1357 'info_dict': {
1358 'id': '_b-2C3KPAM0',
1359 'ext': 'mp4',
1360 'stretched_ratio': 16 / 9.,
556dbe7f 1361 'duration': 85,
6271f1ca
PH
1362 'upload_date': '20110310',
1363 'uploader_id': 'AllenMeow',
ec85ded8 1364 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1365 '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 1366 'uploader': '孫ᄋᄅ',
6271f1ca 1367 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1368 'playable_in_embed': True,
1369 'channel': '孫ᄋᄅ',
1370 'age_limit': 0,
1371 'tags': 'count:11',
1372 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1373 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1374 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1375 'view_count': int,
1376 'categories': ['People & Blogs'],
1377 'like_count': int,
1378 'live_status': 'not_live',
1379 'availability': 'unlisted',
6c73052c 1380 'channel_follower_count': int
6271f1ca 1381 },
06b491eb
S
1382 },
1383 # url_encoded_fmt_stream_map is empty string
1384 {
1385 'url': 'qEJwOuvDf7I',
1386 'info_dict': {
1387 'id': 'qEJwOuvDf7I',
f57b7835 1388 'ext': 'webm',
06b491eb
S
1389 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1390 'description': '',
1391 'upload_date': '20150404',
1392 'uploader_id': 'spbelect',
1393 'uploader': 'Наблюдатели Петербурга',
1394 },
1395 'params': {
1396 'skip_download': 'requires avconv',
e323cf3f
S
1397 },
1398 'skip': 'This live event has ended.',
06b491eb 1399 },
067aa17e 1400 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1401 {
1402 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1403 'info_dict': {
1404 'id': 'FIl7x6_3R5Y',
eb6793ba 1405 'ext': 'webm',
da77d856
S
1406 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1407 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1408 'duration': 220,
da77d856
S
1409 'upload_date': '20150625',
1410 'uploader_id': 'dorappi2000',
ec85ded8 1411 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1412 'uploader': 'dorappi2000',
eb6793ba 1413 'formats': 'mincount:31',
da77d856 1414 },
eb6793ba 1415 'skip': 'not actual anymore',
2ee8f5d8 1416 },
8a1a26ce
YCH
1417 # DASH manifest with segment_list
1418 {
1419 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1420 'md5': '8ce563a1d667b599d21064e982ab9e31',
1421 'info_dict': {
1422 'id': 'CsmdDsKjzN8',
1423 'ext': 'mp4',
17ee98e1 1424 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1425 'uploader': 'Airtek',
1426 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1427 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1428 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1429 },
1430 'params': {
1431 'youtube_include_dash_manifest': True,
1432 'format': '135', # bestvideo
be49068d
S
1433 },
1434 'skip': 'This live event has ended.',
2ee8f5d8 1435 },
cf7e015f
S
1436 {
1437 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1438 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1439 'info_dict': {
545cc85d 1440 'id': 'jvGDaLqkpTg',
1441 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1442 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1443 },
1444 'playlist': [{
1445 'info_dict': {
545cc85d 1446 'id': 'jvGDaLqkpTg',
cf7e015f 1447 'ext': 'mp4',
545cc85d 1448 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1449 'description': 'md5:e03b909557865076822aa169218d6a5d',
1450 'duration': 10643,
1451 'upload_date': '20161111',
1452 'uploader': 'Team PGP',
1453 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1454 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1455 },
1456 }, {
1457 'info_dict': {
545cc85d 1458 'id': '3AKt1R1aDnw',
cf7e015f 1459 'ext': 'mp4',
545cc85d 1460 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1461 'description': 'md5:e03b909557865076822aa169218d6a5d',
1462 'duration': 10991,
1463 'upload_date': '20161111',
1464 'uploader': 'Team PGP',
1465 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1466 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1467 },
1468 }, {
1469 'info_dict': {
545cc85d 1470 'id': 'RtAMM00gpVc',
cf7e015f 1471 'ext': 'mp4',
545cc85d 1472 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1473 'description': 'md5:e03b909557865076822aa169218d6a5d',
1474 'duration': 10995,
1475 'upload_date': '20161111',
1476 'uploader': 'Team PGP',
1477 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1478 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1479 },
1480 }, {
1481 'info_dict': {
545cc85d 1482 'id': '6N2fdlP3C5U',
cf7e015f 1483 'ext': 'mp4',
545cc85d 1484 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1485 'description': 'md5:e03b909557865076822aa169218d6a5d',
1486 'duration': 10990,
1487 'upload_date': '20161111',
1488 'uploader': 'Team PGP',
1489 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1490 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1491 },
1492 }],
1493 'params': {
1494 'skip_download': True,
1495 },
65c2fde2 1496 'skip': 'Not multifeed anymore',
cbaed4bb 1497 },
f9f49d87 1498 {
067aa17e 1499 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1500 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1501 'info_dict': {
1502 'id': 'gVfLd0zydlo',
1503 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1504 },
1505 'playlist_count': 2,
be49068d 1506 'skip': 'Not multifeed anymore',
f9f49d87 1507 },
cbaed4bb 1508 {
2d3d2997 1509 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1510 'only_matching': True,
0e49d9a6 1511 },
6d4fc66b 1512 {
2d3d2997 1513 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1514 'only_matching': True,
1515 },
0e49d9a6 1516 {
067aa17e 1517 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1518 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1519 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1520 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1521 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1522 'info_dict': {
1523 'id': 'lsguqyKfVQg',
1524 'ext': 'mp4',
1525 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1526 'alt_title': 'Dark Walk',
0e49d9a6 1527 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1528 'duration': 133,
0e49d9a6
LL
1529 'upload_date': '20151119',
1530 'uploader_id': 'IronSoulElf',
ec85ded8 1531 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1532 'uploader': 'IronSoulElf',
11f9be09 1533 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1534 'track': 'Dark Walk',
1535 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1536 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1537 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1538 'categories': ['Film & Animation'],
1539 'view_count': int,
1540 'live_status': 'not_live',
1541 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1542 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1543 'tags': 'count:13',
1544 'availability': 'public',
1545 'channel': 'IronSoulElf',
1546 'playable_in_embed': True,
1547 'like_count': int,
1548 'age_limit': 0,
6c73052c 1549 'channel_follower_count': int
0e49d9a6
LL
1550 },
1551 'params': {
1552 'skip_download': True,
1553 },
1554 },
61f92af1 1555 {
067aa17e 1556 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1557 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1558 'only_matching': True,
1559 },
313dfc45
LL
1560 {
1561 # Video with yt:stretch=17:0
1562 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1563 'info_dict': {
1564 'id': 'Q39EVAstoRM',
1565 'ext': 'mp4',
1566 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1567 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1568 'upload_date': '20151107',
1569 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1570 'uploader': 'CH GAMER DROID',
1571 },
1572 'params': {
1573 'skip_download': True,
1574 },
be49068d 1575 'skip': 'This video does not exist.',
313dfc45 1576 },
201c1459 1577 {
1578 # Video with incomplete 'yt:stretch=16:'
1579 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1580 'only_matching': True,
1581 },
7caf9830
S
1582 {
1583 # Video licensed under Creative Commons
1584 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1585 'info_dict': {
1586 'id': 'M4gD1WSo5mA',
1587 'ext': 'mp4',
1588 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1589 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1590 'duration': 721,
17322130 1591 'upload_date': '20150128',
7caf9830 1592 'uploader_id': 'BerkmanCenter',
ec85ded8 1593 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1594 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1595 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1596 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1597 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1598 'like_count': int,
1599 'age_limit': 0,
1600 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1601 'channel': 'The Berkman Klein Center for Internet & Society',
1602 'availability': 'public',
1603 'view_count': int,
1604 'categories': ['Education'],
1605 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1606 'live_status': 'not_live',
1607 'playable_in_embed': True,
6c73052c 1608 'channel_follower_count': int
7caf9830
S
1609 },
1610 'params': {
1611 'skip_download': True,
1612 },
1613 },
fd050249
S
1614 {
1615 # Channel-like uploader_url
1616 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1617 'info_dict': {
1618 'id': 'eQcmzGIKrzg',
1619 'ext': 'mp4',
1620 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1621 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1622 'duration': 4060,
17322130 1623 'upload_date': '20151120',
eb6793ba 1624 'uploader': 'Bernie Sanders',
fd050249 1625 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1626 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1627 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1628 'playable_in_embed': True,
1629 'tags': 'count:12',
1630 'like_count': int,
1631 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1632 'age_limit': 0,
1633 'availability': 'public',
1634 'categories': ['News & Politics'],
1635 'channel': 'Bernie Sanders',
1636 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1637 'view_count': int,
1638 'live_status': 'not_live',
1639 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
6c73052c 1640 'channel_follower_count': int
fd050249
S
1641 },
1642 'params': {
1643 'skip_download': True,
1644 },
1645 },
040ac686
S
1646 {
1647 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1648 'only_matching': True,
7f29cf54
S
1649 },
1650 {
067aa17e 1651 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1652 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1653 'only_matching': True,
6496ccb4
S
1654 },
1655 {
1656 # Rental video preview
1657 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1658 'info_dict': {
1659 'id': 'uGpuVWrhIzE',
1660 'ext': 'mp4',
1661 'title': 'Piku - Trailer',
1662 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1663 'upload_date': '20150811',
1664 'uploader': 'FlixMatrix',
1665 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1666 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1667 'license': 'Standard YouTube License',
1668 },
1669 'params': {
1670 'skip_download': True,
1671 },
eb6793ba 1672 'skip': 'This video is not available.',
022a5d66 1673 },
12afdc2a
S
1674 {
1675 # YouTube Red video with episode data
1676 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1677 'info_dict': {
1678 'id': 'iqKdEhx-dD4',
1679 'ext': 'mp4',
1680 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1681 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1682 'duration': 2085,
12afdc2a
S
1683 'upload_date': '20170118',
1684 'uploader': 'Vsauce',
1685 'uploader_id': 'Vsauce',
1686 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1687 'series': 'Mind Field',
1688 'season_number': 1,
1689 'episode_number': 1,
976ae3ea 1690 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1691 'tags': 'count:12',
1692 'view_count': int,
1693 'availability': 'public',
1694 'age_limit': 0,
1695 'channel': 'Vsauce',
1696 'episode': 'Episode 1',
1697 'categories': ['Entertainment'],
1698 'season': 'Season 1',
1699 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1700 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1701 'like_count': int,
1702 'playable_in_embed': True,
1703 'live_status': 'not_live',
6c73052c 1704 'channel_follower_count': int
12afdc2a
S
1705 },
1706 'params': {
1707 'skip_download': True,
1708 },
1709 'expected_warnings': [
1710 'Skipping DASH manifest',
1711 ],
1712 },
c7121fa7
S
1713 {
1714 # The following content has been identified by the YouTube community
1715 # as inappropriate or offensive to some audiences.
1716 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1717 'info_dict': {
1718 'id': '6SJNVb0GnPI',
1719 'ext': 'mp4',
1720 'title': 'Race Differences in Intelligence',
1721 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1722 'duration': 965,
1723 'upload_date': '20140124',
1724 'uploader': 'New Century Foundation',
1725 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1726 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1727 },
1728 'params': {
1729 'skip_download': True,
1730 },
545cc85d 1731 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1732 },
022a5d66
S
1733 {
1734 # itag 212
1735 'url': '1t24XAntNCY',
1736 'only_matching': True,
fd5c4aab
S
1737 },
1738 {
1739 # geo restricted to JP
1740 'url': 'sJL6WA-aGkQ',
1741 'only_matching': True,
1742 },
cd5a74a2
S
1743 {
1744 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1745 'only_matching': True,
1746 },
bc2ca1bb 1747 {
1748 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1749 'only_matching': True,
1750 },
1751 {
1752 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1753 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1754 'only_matching': True,
1755 },
825cd268
RA
1756 {
1757 # DRM protected
1758 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1759 'only_matching': True,
4fe54c12
S
1760 },
1761 {
1762 # Video with unsupported adaptive stream type formats
1763 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1764 'info_dict': {
1765 'id': 'Z4Vy8R84T1U',
1766 'ext': 'mp4',
1767 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1768 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1769 'duration': 433,
1770 'upload_date': '20130923',
1771 'uploader': 'Amelia Putri Harwita',
1772 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1773 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1774 'formats': 'maxcount:10',
1775 },
1776 'params': {
1777 'skip_download': True,
1778 'youtube_include_dash_manifest': False,
1779 },
5429d6a9 1780 'skip': 'not actual anymore',
5caabd3c 1781 },
1782 {
822b9d9c 1783 # Youtube Music Auto-generated description
5caabd3c 1784 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1785 'info_dict': {
1786 'id': 'MgNrAu2pzNs',
1787 'ext': 'mp4',
1788 'title': 'Voyeur Girl',
1789 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1790 'upload_date': '20190312',
5429d6a9
S
1791 'uploader': 'Stephen - Topic',
1792 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1793 'artist': 'Stephen',
1794 'track': 'Voyeur Girl',
1795 'album': 'it\'s too much love to know my dear',
1796 'release_date': '20190313',
1797 'release_year': 2019,
976ae3ea 1798 'alt_title': 'Voyeur Girl',
1799 'view_count': int,
1800 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1801 'playable_in_embed': True,
1802 'like_count': int,
1803 'categories': ['Music'],
1804 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1805 'channel': 'Stephen',
1806 'availability': 'public',
1807 'creator': 'Stephen',
1808 'duration': 169,
1809 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1810 'age_limit': 0,
1811 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1812 'tags': 'count:11',
1813 'live_status': 'not_live',
6c73052c 1814 'channel_follower_count': int
5caabd3c 1815 },
1816 'params': {
1817 'skip_download': True,
1818 },
1819 },
66b48727
RA
1820 {
1821 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1822 'only_matching': True,
1823 },
011e75e6
S
1824 {
1825 # invalid -> valid video id redirection
1826 'url': 'DJztXj2GPfl',
1827 'info_dict': {
1828 'id': 'DJztXj2GPfk',
1829 'ext': 'mp4',
1830 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1831 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1832 'upload_date': '20090125',
1833 'uploader': 'Prochorowka',
1834 'uploader_id': 'Prochorowka',
1835 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1836 'artist': 'Panjabi MC',
1837 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1838 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1839 },
1840 'params': {
1841 'skip_download': True,
1842 },
545cc85d 1843 'skip': 'Video unavailable',
ea74e00b
DP
1844 },
1845 {
1846 # empty description results in an empty string
1847 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1848 'info_dict': {
1849 'id': 'x41yOUIvK2k',
1850 'ext': 'mp4',
1851 'title': 'IMG 3456',
1852 'description': '',
1853 'upload_date': '20170613',
1854 'uploader_id': 'ElevageOrVert',
1855 'uploader': 'ElevageOrVert',
976ae3ea 1856 'view_count': int,
1857 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1858 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1859 'like_count': int,
1860 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1861 'tags': [],
1862 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1863 'availability': 'public',
1864 'age_limit': 0,
1865 'categories': ['Pets & Animals'],
1866 'duration': 7,
1867 'playable_in_embed': True,
1868 'live_status': 'not_live',
1869 'channel': 'ElevageOrVert',
6c73052c 1870 'channel_follower_count': int
ea74e00b
DP
1871 },
1872 'params': {
1873 'skip_download': True,
1874 },
1875 },
a0566bbf 1876 {
29f7c58a 1877 # with '};' inside yt initial data (see [1])
1878 # see [2] for an example with '};' inside ytInitialPlayerResponse
1879 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1880 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1881 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1882 'info_dict': {
1883 'id': 'CHqg6qOn4no',
1884 'ext': 'mp4',
1885 'title': 'Part 77 Sort a list of simple types in c#',
1886 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1887 'upload_date': '20130831',
1888 'uploader_id': 'kudvenkat',
1889 'uploader': 'kudvenkat',
976ae3ea 1890 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1891 'like_count': int,
1892 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1893 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1894 'live_status': 'not_live',
1895 'categories': ['Education'],
1896 'availability': 'public',
1897 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1898 'tags': 'count:12',
1899 'playable_in_embed': True,
1900 'age_limit': 0,
1901 'view_count': int,
1902 'duration': 522,
1903 'channel': 'kudvenkat',
6c73052c 1904 'channel_follower_count': int
a0566bbf 1905 },
1906 'params': {
1907 'skip_download': True,
1908 },
1909 },
29f7c58a 1910 {
1911 # another example of '};' in ytInitialData
1912 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1913 'only_matching': True,
1914 },
1915 {
1916 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1917 'only_matching': True,
1918 },
545cc85d 1919 {
cc2db878 1920 # https://github.com/ytdl-org/youtube-dl/pull/28094
1921 'url': 'OtqTfy26tG0',
1922 'info_dict': {
1923 'id': 'OtqTfy26tG0',
1924 'ext': 'mp4',
1925 'title': 'Burn Out',
1926 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1927 'upload_date': '20141120',
1928 'uploader': 'The Cinematic Orchestra - Topic',
1929 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1930 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1931 'artist': 'The Cinematic Orchestra',
1932 'track': 'Burn Out',
1933 'album': 'Every Day',
976ae3ea 1934 'like_count': int,
1935 'live_status': 'not_live',
1936 'alt_title': 'Burn Out',
1937 'duration': 614,
1938 'age_limit': 0,
1939 'view_count': int,
1940 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1941 'creator': 'The Cinematic Orchestra',
1942 'channel': 'The Cinematic Orchestra',
1943 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1944 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1945 'availability': 'public',
1946 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1947 'categories': ['Music'],
1948 'playable_in_embed': True,
6c73052c 1949 'channel_follower_count': int
cc2db878 1950 },
1951 'params': {
1952 'skip_download': True,
1953 },
545cc85d 1954 },
bc2ca1bb 1955 {
1956 # controversial video, only works with bpctr when authenticated with cookies
1957 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1958 'only_matching': True,
1959 },
a1a7907b 1960 {
1961 # controversial video, requires bpctr/contentCheckOk
1962 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1963 'info_dict': {
1964 'id': 'SZJvDhaSDnc',
1965 'ext': 'mp4',
1966 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1967 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1968 'uploader': 'CBS Mornings',
11f9be09 1969 'uploader_id': 'CBSThisMorning',
a1a7907b 1970 'upload_date': '20140716',
976ae3ea 1971 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1972 'duration': 170,
1973 'categories': ['News & Politics'],
1974 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1975 'view_count': int,
1976 'channel': 'CBS Mornings',
1977 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1978 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1979 'age_limit': 18,
1980 'availability': 'needs_auth',
1981 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1982 'like_count': int,
1983 'live_status': 'not_live',
1984 'playable_in_embed': True,
6c73052c 1985 'channel_follower_count': int
a1a7907b 1986 }
1987 },
f7ad7160 1988 {
1989 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1990 'url': 'cBvYw8_A0vQ',
1991 'info_dict': {
1992 'id': 'cBvYw8_A0vQ',
1993 'ext': 'mp4',
1994 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1995 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1996 'upload_date': '20201120',
1997 'uploader': 'Walk around Japan',
1998 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1999 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2000 'duration': 1456,
2001 'categories': ['Travel & Events'],
2002 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2003 'view_count': int,
2004 'channel': 'Walk around Japan',
2005 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2006 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2007 'age_limit': 0,
2008 'availability': 'public',
2009 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2010 'live_status': 'not_live',
2011 'playable_in_embed': True,
6c73052c 2012 'channel_follower_count': int
f7ad7160 2013 },
2014 'params': {
2015 'skip_download': True,
2016 },
0fb983f6 2017 }, {
2018 # Has multiple audio streams
2019 'url': 'WaOKSUlf4TM',
2020 'only_matching': True
9297939e 2021 }, {
2022 # Requires Premium: has format 141 when requested using YTM url
2023 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2024 'only_matching': True
2025 }, {
120916da 2026 # multiple subtitles with same lang_code
2027 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2028 'only_matching': True,
109dd3b2 2029 }, {
2030 # Force use android client fallback
2031 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2032 'info_dict': {
2033 'id': 'YOelRv7fMxY',
11f9be09 2034 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2035 'ext': '3gp',
2036 'upload_date': '20210624',
2037 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2038 'uploader': 'colinfurze',
11f9be09 2039 'uploader_id': 'colinfurze',
109dd3b2 2040 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2041 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2042 'duration': 596,
2043 'categories': ['Entertainment'],
2044 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2045 'view_count': int,
2046 'channel': 'colinfurze',
2047 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2048 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2049 'age_limit': 0,
2050 'availability': 'public',
2051 'like_count': int,
2052 'live_status': 'not_live',
2053 'playable_in_embed': True,
6c73052c 2054 'channel_follower_count': int
109dd3b2 2055 },
2056 'params': {
2057 'format': '17', # 3gp format available on android
2058 'extractor_args': {'youtube': {'player_client': ['android']}},
2059 },
120916da 2060 },
109dd3b2 2061 {
2062 # Skip download of additional client configs (remix client config in this case)
2063 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2064 'only_matching': True,
2065 'params': {
2066 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2067 },
8fc54b12 2068 }, {
2069 # shorts
2070 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2071 'only_matching': True,
9222c381 2072 }, {
2073 'note': 'Storyboards',
2074 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2075 'info_dict': {
2076 'id': '5KLPxDtMqe8',
2077 'ext': 'mhtml',
2078 'format_id': 'sb0',
2079 'title': 'Your Brain is Plastic',
2080 'uploader_id': 'scishow',
2081 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2082 'upload_date': '20140324',
2083 'uploader': 'SciShow',
976ae3ea 2084 'like_count': int,
2085 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2086 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2087 'view_count': int,
2088 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2089 'playable_in_embed': True,
2090 'tags': 'count:12',
2091 'uploader_url': 'http://www.youtube.com/user/scishow',
2092 'availability': 'public',
2093 'channel': 'SciShow',
2094 'live_status': 'not_live',
2095 'duration': 248,
2096 'categories': ['Education'],
2097 'age_limit': 0,
6c73052c 2098 'channel_follower_count': int
9222c381 2099 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2100 }, {
2101 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2102 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2103 'info_dict': {
2104 'id': '2NUZ8W2llS4',
2105 'ext': 'mp4',
2106 'title': 'The NP that test your phone performance 🙂',
2107 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2108 'uploader': 'Leon Nguyen',
2109 'uploader_id': 'VNSXIII',
2110 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2111 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2112 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2113 'duration': 21,
2114 'view_count': int,
2115 'age_limit': 0,
2116 'categories': ['Gaming'],
2117 'tags': 'count:23',
2118 'playable_in_embed': True,
2119 'live_status': 'not_live',
2120 'upload_date': '20220103',
2121 'like_count': int,
2122 'availability': 'public',
2123 'channel': 'Leon Nguyen',
2124 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2125 'channel_follower_count': int
2126 }
2127 }, {
2128 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2129 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2130 'info_dict': {
2131 'id': 'mzZzzBU6lrM',
2132 'ext': 'mp4',
2133 'title': 'I Met GeorgeNotFound In Real Life...',
2134 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2135 'uploader': 'Quackity',
2136 'uploader_id': 'QuackityHQ',
2137 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2138 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2139 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2140 'duration': 955,
2141 'view_count': int,
2142 'age_limit': 0,
2143 'categories': ['Entertainment'],
2144 'tags': 'count:26',
2145 'playable_in_embed': True,
2146 'live_status': 'not_live',
2147 'release_timestamp': 1641172509,
2148 'release_date': '20220103',
2149 'upload_date': '20220103',
2150 'like_count': int,
2151 'availability': 'public',
2152 'channel': 'Quackity',
2153 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2154 'channel_follower_count': int
2155 }
2156 },
2157 { # continuous livestream. Microformat upload date should be preferred.
2158 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2159 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2160 'info_dict': {
2161 'id': 'kgx4WGK0oNU',
2162 '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}',
2163 'ext': 'mp4',
2164 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2165 'availability': 'public',
2166 'age_limit': 0,
2167 'release_timestamp': 1637975704,
2168 'upload_date': '20210619',
2169 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2170 'live_status': 'is_live',
2171 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2172 'uploader': '阿鲍Abao',
2173 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2174 'channel': 'Abao in Tokyo',
2175 'channel_follower_count': int,
2176 'release_date': '20211127',
2177 'tags': 'count:39',
2178 'categories': ['People & Blogs'],
2179 'like_count': int,
2180 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2181 'view_count': int,
2182 'playable_in_embed': True,
2183 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2184 },
2185 'params': {'skip_download': True}
2186 },
2eb88d95
PH
2187 ]
2188
201c1459 2189 @classmethod
2190 def suitable(cls, url):
4dfbf869 2191 from ..utils import parse_qs
2192
201c1459 2193 qs = parse_qs(url)
2194 if qs.get('list', [None])[0]:
2195 return False
2196 return super(YoutubeIE, cls).suitable(url)
2197
e0df6211
PH
2198 def __init__(self, *args, **kwargs):
2199 super(YoutubeIE, self).__init__(*args, **kwargs)
545cc85d 2200 self._code_cache = {}
83799698 2201 self._player_cache = {}
e0df6211 2202
adbc4ec4 2203 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2204 lock = threading.Lock()
2205
2206 is_live = True
185bf310 2207 start_time = time.time()
adbc4ec4
THD
2208 formats = [f for f in formats if f.get('is_from_start')]
2209
185bf310 2210 def refetch_manifest(format_id, delay):
2211 nonlocal formats, start_time, is_live
2212 if time.time() <= start_time + delay:
adbc4ec4
THD
2213 return
2214
2215 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2216 video_details = traverse_obj(
2217 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2218 microformats = traverse_obj(
2219 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2220 expected_type=dict, default=[])
2221 _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2222 start_time = time.time()
adbc4ec4 2223
185bf310 2224 def mpd_feed(format_id, delay):
adbc4ec4
THD
2225 """
2226 @returns (manifest_url, manifest_stream_number, is_live) or None
2227 """
2228 with lock:
185bf310 2229 refetch_manifest(format_id, delay)
adbc4ec4
THD
2230
2231 f = next((f for f in formats if f['format_id'] == format_id), None)
2232 if not f:
185bf310 2233 if not is_live:
2234 self.to_screen(f'{video_id}: Video is no longer live')
2235 else:
2236 self.report_warning(
2237 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2238 return None
2239 return f['manifest_url'], f['manifest_stream_number'], is_live
2240
2241 for f in formats:
a539f065 2242 f['is_live'] = True
adbc4ec4
THD
2243 f['protocol'] = 'http_dash_segments_generator'
2244 f['fragments'] = functools.partial(
2245 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2246
2247 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2248 FETCH_SPAN, MAX_DURATION = 5, 432000
2249
2250 mpd_url, stream_number, is_live = None, None, True
2251
2252 begin_index = 0
2253 download_start_time = ctx.get('start') or time.time()
2254
2255 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2256 if lack_early_segments:
2257 self.report_warning(bug_reports_message(
2258 'Starting download from the last 120 hours of the live stream since '
2259 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2260 lack_early_segments = True
2261
2262 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2263 fragments, fragment_base_url = None, None
2264
a539f065 2265 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2266 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2267 # Obtain from MPD's maximum seq value
2268 old_mpd_url = mpd_url
185bf310 2269 last_error = ctx.pop('last_error', None)
a539f065 2270 expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403
185bf310 2271 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2272 or (mpd_url, stream_number, False))
2273 if not refresh_sequence:
2274 if expire_fast and not is_live:
2275 return False, last_seq
2276 elif old_mpd_url == mpd_url:
2277 return True, last_seq
adbc4ec4
THD
2278 try:
2279 fmts, _ = self._extract_mpd_formats_and_subtitles(
2280 mpd_url, None, note=False, errnote=False, fatal=False)
2281 except ExtractorError:
2282 fmts = None
2283 if not fmts:
a539f065 2284 no_fragment_score += 2
adbc4ec4
THD
2285 return False, last_seq
2286 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2287 fragments = fmt_info['fragments']
2288 fragment_base_url = fmt_info['fragment_base_url']
2289 assert fragment_base_url
2290
2291 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2292 return True, _last_seq
2293
2294 while is_live:
2295 fetch_time = time.time()
2296 if no_fragment_score > 30:
2297 return
2298 if last_segment_url:
2299 # Obtain from "X-Head-Seqnum" header value from each segment
2300 try:
2301 urlh = self._request_webpage(
2302 last_segment_url, None, note=False, errnote=False, fatal=False)
2303 except ExtractorError:
2304 urlh = None
2305 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2306 if last_seq is None:
a539f065 2307 no_fragment_score += 2
adbc4ec4
THD
2308 last_segment_url = None
2309 continue
2310 else:
a539f065
LNO
2311 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2312 no_fragment_score += 2
185bf310 2313 if not should_continue:
adbc4ec4
THD
2314 continue
2315
2316 if known_idx > last_seq:
2317 last_segment_url = None
2318 continue
2319
2320 last_seq += 1
2321
2322 if begin_index < 0 and known_idx < 0:
2323 # skip from the start when it's negative value
2324 known_idx = last_seq + begin_index
2325 if lack_early_segments:
2326 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2327 try:
2328 for idx in range(known_idx, last_seq):
2329 # do not update sequence here or you'll get skipped some part of it
a539f065 2330 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2331 if not should_continue:
adbc4ec4
THD
2332 known_idx = idx - 1
2333 raise ExtractorError('breaking out of outer loop')
2334 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2335 yield {
2336 'url': last_segment_url,
2337 }
2338 if known_idx == last_seq:
2339 no_fragment_score += 5
2340 else:
2341 no_fragment_score = 0
2342 known_idx = last_seq
2343 except ExtractorError:
2344 continue
2345
2346 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2347
b6de707d 2348 def _extract_player_url(self, *ytcfgs, webpage=None):
2349 player_url = traverse_obj(
2350 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2351 get_all=False, expected_type=compat_str)
11f9be09 2352 if not player_url:
b6de707d 2353 return
60f393e4 2354 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2355
b6de707d 2356 def _download_player_url(self, video_id, fatal=False):
2357 res = self._download_webpage(
2358 'https://www.youtube.com/iframe_api',
2359 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2360 if res:
2361 player_version = self._search_regex(
2362 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2363 if player_version:
2364 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2365
60064c53
PH
2366 def _signature_cache_id(self, example_sig):
2367 """ Return a string representation of a signature """
78caa52a 2368 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53 2369
e40c758c
S
2370 @classmethod
2371 def _extract_player_info(cls, player_url):
2372 for player_re in cls._PLAYER_INFO_RE:
2373 id_m = re.search(player_re, player_url)
2374 if id_m:
2375 break
2376 else:
c081b35c 2377 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2378 return id_m.group('id')
e40c758c 2379
404f611f 2380 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2381 player_id = self._extract_player_info(player_url)
2382 if player_id not in self._code_cache:
1276a43a 2383 code = self._download_webpage(
109dd3b2 2384 player_url, video_id, fatal=fatal,
2385 note='Downloading player ' + player_id,
2386 errnote='Download of %s failed' % player_url)
1276a43a 2387 if code:
2388 self._code_cache[player_id] = code
404f611f 2389 return self._code_cache.get(player_id)
109dd3b2 2390
e40c758c 2391 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2392 player_id = self._extract_player_info(player_url)
e0df6211 2393
c4417ddb 2394 # Read from filesystem cache
545cc85d 2395 func_id = 'js_%s_%s' % (
2396 player_id, self._signature_cache_id(example_sig))
c4417ddb 2397 assert os.path.basename(func_id) == func_id
a0e07d31 2398
69ea8ca4 2399 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2400 if cache_spec is not None:
78caa52a 2401 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2402
404f611f 2403 code = self._load_player(video_id, player_url)
2404 if code:
109dd3b2 2405 res = self._parse_sig_js(code)
e0df6211 2406
109dd3b2 2407 test_string = ''.join(map(compat_chr, range(len(example_sig))))
2408 cache_res = res(test_string)
2409 cache_spec = [ord(c) for c in cache_res]
83799698 2410
109dd3b2 2411 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
2412 return res
83799698 2413
60064c53 2414 def _print_sig_code(self, func, example_sig):
404f611f 2415 if not self.get_param('youtube_print_sig_code'):
2416 return
2417
edf3e38e
PH
2418 def gen_sig_code(idxs):
2419 def _genslice(start, end, step):
78caa52a 2420 starts = '' if start == 0 else str(start)
8bcc8756 2421 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2422 steps = '' if step == 1 else (':%d' % step)
78caa52a 2423 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
2424
2425 step = None
7af808a5
PH
2426 # Quelch pyflakes warnings - start will be set when step is set
2427 start = '(Never used)'
edf3e38e
PH
2428 for i, prev in zip(idxs[1:], idxs[:-1]):
2429 if step is not None:
2430 if i - prev == step:
2431 continue
2432 yield _genslice(start, prev, step)
2433 step = None
2434 continue
2435 if i - prev in [-1, 1]:
2436 step = i - prev
2437 start = prev
2438 continue
2439 else:
78caa52a 2440 yield 's[%d]' % prev
edf3e38e 2441 if step is None:
78caa52a 2442 yield 's[%d]' % i
edf3e38e
PH
2443 else:
2444 yield _genslice(start, i, step)
2445
78caa52a 2446 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 2447 cache_res = func(test_string)
edf3e38e 2448 cache_spec = [ord(c) for c in cache_res]
78caa52a 2449 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
2450 signature_id_tuple = '(%s)' % (
2451 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2452 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2453 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2454 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2455
e0df6211
PH
2456 def _parse_sig_js(self, jscode):
2457 funcname = self._search_regex(
abefc03f
S
2458 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2459 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
2460 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2461 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2462 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}\(a,\d+\)',
2463 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 2464 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2465 # Obsolete patterns
2466 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2467 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2468 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2469 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2470 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2471 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2472 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2473 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2474 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2475
2476 jsi = JSInterpreter(jscode)
2477 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2478 return lambda s: initial_function([s])
2479
545cc85d 2480 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2481 """Turn the encrypted s field into a working signature"""
6b37f0be 2482
c8bf86d5 2483 if player_url is None:
69ea8ca4 2484 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 2485
c8bf86d5 2486 try:
62af3a0e 2487 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
2488 if player_id not in self._player_cache:
2489 func = self._extract_signature_function(
60064c53 2490 video_id, player_url, s
c8bf86d5
PH
2491 )
2492 self._player_cache[player_id] = func
2493 func = self._player_cache[player_id]
404f611f 2494 self._print_sig_code(func, s)
c8bf86d5
PH
2495 return func(s)
2496 except Exception as e:
404f611f 2497 raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e)
2498
2499 def _decrypt_nsig(self, s, video_id, player_url):
2500 """Turn the encrypted n field into a working signature"""
2501 if player_url is None:
2502 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2503 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2504
2505 sig_id = ('nsig_value', s)
2506 if sig_id in self._player_cache:
2507 return self._player_cache[sig_id]
2508
2509 try:
2510 player_id = ('nsig', player_url)
2511 if player_id not in self._player_cache:
2512 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2513 func = self._player_cache[player_id]
2514 self._player_cache[sig_id] = func(s)
2515 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2516 return self._player_cache[sig_id]
2517 except Exception as e:
aa9369a2 2518 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2519
2520 def _extract_n_function_name(self, jscode):
48416bc4 2521 nfunc, idx = self._search_regex(
c571b3a6 2522 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2523 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2524 if not idx:
2525 return nfunc
2526 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2527 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2528 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2529
2530 def _extract_n_function(self, video_id, player_url):
2531 player_id = self._extract_player_info(player_url)
2532 func_code = self._downloader.cache.load('youtube-nsig', player_id)
2533
2534 if func_code:
2535 jsi = JSInterpreter(func_code)
2536 else:
2537 jscode = self._load_player(video_id, player_url)
2538 funcname = self._extract_n_function_name(jscode)
2539 jsi = JSInterpreter(jscode)
2540 func_code = jsi.extract_function_code(funcname)
2541 self._downloader.cache.store('youtube-nsig', player_id, func_code)
2542
2543 if self.get_param('youtube_print_sig_code'):
2544 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2545
2546 return lambda s: jsi.extract_function_from_code(*func_code)([s])
e0df6211 2547
109dd3b2 2548 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2549 """
2550 Extract signatureTimestamp (sts)
2551 Required to tell API what sig/player version is in use.
2552 """
2553 sts = None
2554 if isinstance(ytcfg, dict):
2555 sts = int_or_none(ytcfg.get('STS'))
2556
2557 if not sts:
2558 # Attempt to extract from player
2559 if player_url is None:
2560 error_msg = 'Cannot extract signature timestamp without player_url.'
2561 if fatal:
2562 raise ExtractorError(error_msg)
2563 self.report_warning(error_msg)
2564 return
404f611f 2565 code = self._load_player(video_id, player_url, fatal=fatal)
2566 if code:
109dd3b2 2567 sts = int_or_none(self._search_regex(
2568 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2569 'JS player signature timestamp', group='sts', fatal=fatal))
2570 return sts
2571
11f9be09 2572 def _mark_watched(self, video_id, player_responses):
9222c381 2573 playback_url = get_first(
2574 player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'),
2575 expected_type=url_or_none)
d77ab8e2 2576 if not playback_url:
352d63fd 2577 self.report_warning('Unable to mark watched')
d77ab8e2
S
2578 return
2579 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2580 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2581
2582 # cpn generation algorithm is reverse engineered from base.js.
2583 # In fact it works even with dummy cpn.
2584 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2585 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2586
2587 qs.update({
2588 'ver': ['2'],
2589 'cpn': [cpn],
2590 })
2591 playback_url = compat_urlparse.urlunparse(
15707c7e 2592 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
2593
2594 self._download_webpage(
2595 playback_url, video_id, 'Marking watched',
2596 'Unable to mark watched', fatal=False)
2597
66c9fa36
S
2598 @staticmethod
2599 def _extract_urls(webpage):
2600 # Embedded YouTube player
2601 entries = [
2602 unescapeHTML(mobj.group('url'))
2603 for mobj in re.finditer(r'''(?x)
2604 (?:
2605 <iframe[^>]+?src=|
2606 data-video-url=|
2607 <embed[^>]+?src=|
2608 embedSWF\(?:\s*|
2609 <object[^>]+data=|
2610 new\s+SWFObject\(
2611 )
2612 (["\'])
2613 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
f2332f18 2614 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
66c9fa36
S
2615 \1''', webpage)]
2616
2617 # lazyYT YouTube embed
2618 entries.extend(list(map(
2619 unescapeHTML,
2620 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2621
2622 # Wordpress "YouTube Video Importer" plugin
2623 matches = re.findall(r'''(?x)<div[^>]+
2624 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2625 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
2626 entries.extend(m[-1] for m in matches)
2627
2628 return entries
2629
2630 @staticmethod
2631 def _extract_url(webpage):
2632 urls = YoutubeIE._extract_urls(webpage)
2633 return urls[0] if urls else None
2634
97665381
PH
2635 @classmethod
2636 def extract_id(cls, url):
2637 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 2638 if mobj is None:
69ea8ca4 2639 raise ExtractorError('Invalid URL: %s' % url)
5ad28e7f 2640 return mobj.group('id')
c5e8d7af 2641
7c365c21 2642 def _extract_chapters_from_json(self, data, duration):
2643 chapter_list = traverse_obj(
2644 data, (
2645 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2646 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2647 ), expected_type=list)
2648
2649 return self._extract_chapters(
2650 chapter_list,
2651 chapter_time=lambda chapter: float_or_none(
2652 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2653 chapter_title=lambda chapter: traverse_obj(
2654 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2655 duration=duration)
2656
2657 def _extract_chapters_from_engagement_panel(self, data, duration):
2658 content_list = traverse_obj(
8bdd16b4 2659 data,
7c365c21 2660 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2661 expected_type=list, default=[])
052e1350 2662 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2663 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2664
2665 return next((
2666 filter(None, (
2667 self._extract_chapters(
2668 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2669 chapter_time, chapter_title, duration)
2670 for contents in content_list
2671 ))), [])
2672
2673 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
84213ea8 2674 chapters = []
7c365c21 2675 last_chapter = {'start_time': 0}
2676 for idx, chapter in enumerate(chapter_list or []):
2677 title = chapter_title(chapter)
84213ea8
S
2678 start_time = chapter_time(chapter)
2679 if start_time is None:
2680 continue
7c365c21 2681 last_chapter['end_time'] = start_time
2682 if start_time < last_chapter['start_time']:
2683 if idx == 1:
2684 chapters.pop()
2685 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2686 else:
2687 self.report_warning(f'Invalid start time for chapter "{title}"')
2688 continue
2689 last_chapter = {'start_time': start_time, 'title': title}
2690 chapters.append(last_chapter)
2691 last_chapter['end_time'] = duration
84213ea8
S
2692 return chapters
2693
545cc85d 2694 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2695 return self._parse_json(self._search_regex(
2696 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2697 regex), webpage, name, default='{}'), video_id, fatal=False)
84213ea8 2698
a1c5d2ca
M
2699 def _extract_comment(self, comment_renderer, parent=None):
2700 comment_id = comment_renderer.get('commentId')
2701 if not comment_id:
2702 return
fe93e2c4 2703
052e1350 2704 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2705
49bd8c66 2706 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2707 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2708 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca
M
2709 author_id = try_get(comment_renderer,
2710 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
fe93e2c4 2711
49bd8c66 2712 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2713 lambda x: x['likeCount']), compat_str)) or 0
a1c5d2ca
M
2714 author_thumbnail = try_get(comment_renderer,
2715 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2716
2717 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2718 is_favorited = 'creatorHeart' in (try_get(
2719 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2720 return {
2721 'id': comment_id,
2722 'text': text,
d92f5d5a 2723 'timestamp': timestamp,
a1c5d2ca
M
2724 'time_text': time_text,
2725 'like_count': votes,
97524332 2726 'is_favorited': is_favorited,
a1c5d2ca
M
2727 'author': author,
2728 'author_id': author_id,
2729 'author_thumbnail': author_thumbnail,
2730 'author_is_uploader': author_is_uploader,
2731 'parent': parent or 'root'
2732 }
2733
46383212 2734 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2735
2736 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2737
2738 def extract_header(contents):
2d6659b9 2739 _continuation = None
2740 for content in contents:
46383212 2741 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2742 expected_comment_count = self._get_count(
2743 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2744
2d6659b9 2745 if expected_comment_count:
46383212 2746 tracker['est_total'] = expected_comment_count
2747 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2748 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2749
2750 sort_menu_item = try_get(
2751 comments_header_renderer,
2752 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2753 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2754
2755 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2756 if not _continuation:
2757 continue
2758
46383212 2759 sort_text = str_or_none(sort_menu_item.get('title'))
2760 if not sort_text:
2d6659b9 2761 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2762 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2763 break
a2160aa4 2764 return _continuation
a1c5d2ca 2765
2d6659b9 2766 def extract_thread(contents):
a1c5d2ca 2767 if not parent:
46383212 2768 tracker['current_page_thread'] = 0
a1c5d2ca 2769 for content in contents:
46383212 2770 if not parent and tracker['total_parent_comments'] >= max_parents:
2771 yield
a1c5d2ca 2772 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2773 comment_renderer = get_first(
2774 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2775 expected_type=dict, default={})
a1c5d2ca 2776
a1c5d2ca
M
2777 comment = self._extract_comment(comment_renderer, parent)
2778 if not comment:
2779 continue
46383212 2780
2781 tracker['running_total'] += 1
2782 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2783 yield comment
46383212 2784
a1c5d2ca
M
2785 # Attempt to get the replies
2786 comment_replies_renderer = try_get(
2787 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2788
2789 if comment_replies_renderer:
46383212 2790 tracker['current_page_thread'] += 1
a1c5d2ca 2791 comment_entries_iter = self._comment_entries(
99e9e001 2792 comment_replies_renderer, ytcfg, video_id,
46383212 2793 parent=comment.get('id'), tracker=tracker)
2794 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
a1c5d2ca
M
2795 yield reply_comment
2796
46383212 2797 # Keeps track of counts across recursive calls
2798 if not tracker:
2799 tracker = dict(
2800 running_total=0,
2801 est_total=0,
2802 current_page_thread=0,
2803 total_parent_comments=0,
2804 total_reply_comments=0)
2805
2806 # TODO: Deprecated
2d6659b9 2807 # YouTube comments have a max depth of 2
46383212 2808 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2809 if max_depth:
2810 self._downloader.deprecation_warning(
2811 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2812 if max_depth == 1 and parent:
2813 return
a1c5d2ca 2814
46383212 2815 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2816 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2817
46383212 2818 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2819 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2820 if message and not parent:
2821 self.report_warning(message, video_id=video_id)
2822
46383212 2823 response = None
2d6659b9 2824 is_first_continuation = parent is None
a1c5d2ca
M
2825
2826 for page_num in itertools.count(0):
2827 if not continuation:
2828 break
46383212 2829 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2830 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2831 if page_num == 0:
2832 if is_first_continuation:
2833 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2834 else:
2d6659b9 2835 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2836 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2837 else:
2838 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2839 ' ' if parent else '', ' replies' if parent else '',
2840 page_num, comment_prog_str)
2841
2842 response = self._extract_response(
fe93e2c4 2843 item_id=None, query=continuation,
2d6659b9 2844 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
46383212 2845 check_get_keys='onResponseReceivedEndpoints')
a1c5d2ca 2846
46383212 2847 continuation_contents = traverse_obj(
2848 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2849
2d6659b9 2850 continuation = None
46383212 2851 for continuation_section in continuation_contents:
2852 continuation_items = traverse_obj(
2853 continuation_section,
2854 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2855 get_all=False, expected_type=list) or []
2856 if is_first_continuation:
2857 continuation = extract_header(continuation_items)
2858 is_first_continuation = False
2d6659b9 2859 if continuation:
a1c5d2ca 2860 break
46383212 2861 continue
a1c5d2ca 2862
46383212 2863 for entry in extract_thread(continuation_items):
2864 if not entry:
2865 return
2866 yield entry
2867 continuation = self._extract_continuation({'contents': continuation_items})
2868 if continuation:
2d6659b9 2869 break
a1c5d2ca 2870
a2160aa4 2871 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2872 """Entry for comment extraction"""
2d6659b9 2873 def _real_comment_extract(contents):
aae16f6e 2874 renderer = next((
2875 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2876 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2877 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 2878
a2160aa4 2879 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 2880 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 2881
109dd3b2 2882 @staticmethod
99e9e001 2883 def _get_checkok_params():
2884 return {'contentCheckOk': True, 'racyCheckOk': True}
2885
2886 @classmethod
2887 def _generate_player_context(cls, sts=None):
109dd3b2 2888 context = {
2889 'html5Preference': 'HTML5_PREF_WANTS',
2890 }
2891 if sts is not None:
2892 context['signatureTimestamp'] = sts
2893 return {
2894 'playbackContext': {
2895 'contentPlaybackContext': context
a1a7907b 2896 },
99e9e001 2897 **cls._get_checkok_params()
109dd3b2 2898 }
2899
e7e94f2a
D
2900 @staticmethod
2901 def _is_agegated(player_response):
2902 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 2903 return True
e7e94f2a
D
2904
2905 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2906 AGE_GATE_REASONS = (
2907 'confirm your age', 'age-restricted', 'inappropriate', # reason
2908 'age_verification_required', 'age_check_required', # status
2909 )
2910 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2911
2912 @staticmethod
2913 def _is_unplayable(player_response):
2914 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 2915
99e9e001 2916 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 2917
11f9be09 2918 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2919 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 2920 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 2921 headers = self.generate_api_headers(
99e9e001 2922 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 2923
11f9be09 2924 yt_query = {'videoId': video_id}
2925 yt_query.update(self._generate_player_context(sts))
2926 return self._extract_response(
2927 item_id=video_id, ep='player', query=yt_query,
379e44ed 2928 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 2929 default_client=client,
11f9be09 2930 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2931 ) or None
2932
11f9be09 2933 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 2934 requested_clients = []
d0d012d4 2935 default = ['android', 'web']
000c15a4 2936 allowed_clients = sorted(
2937 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2938 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 2939 for client in self._configuration_arg('player_client'):
2940 if client in allowed_clients:
2941 requested_clients.append(client)
d0d012d4 2942 elif client == 'default':
2943 requested_clients.extend(default)
b4c055ba 2944 elif client == 'all':
2945 requested_clients.extend(allowed_clients)
2946 else:
2947 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 2948 if not requested_clients:
d0d012d4 2949 requested_clients = default
cf7e015f 2950
11f9be09 2951 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2952 requested_clients.extend(
e7e94f2a 2953 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 2954
11f9be09 2955 return orderedSet(requested_clients)
cf7e015f 2956
c0bc527b
M
2957 def _extract_player_ytcfg(self, client, video_id):
2958 url = {
2959 'web_music': 'https://music.youtube.com',
2960 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2961 }.get(client)
2962 if not url:
2963 return {}
18c7683d 2964 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
c0bc527b
M
2965 return self.extract_ytcfg(video_id, webpage) or {}
2966
99e9e001 2967 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 2968 initial_pr = None
2969 if webpage:
2970 initial_pr = self._extract_yt_initial_variable(
2971 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2972 video_id, 'initial player response')
6b09401b 2973
ae729626 2974 all_clients = set(clients)
c0bc527b 2975 clients = clients[::-1]
b6de707d 2976 prs = []
e7e94f2a 2977
ae729626 2978 def append_client(*client_names):
e7870111 2979 """ Append the first client name that exists but not already used """
ae729626 2980 for client_name in client_names:
e7870111
D
2981 actual_client = _split_innertube_client(client_name)[0]
2982 if actual_client in INNERTUBE_CLIENTS:
2983 if actual_client not in all_clients:
ae729626 2984 clients.append(client_name)
e7870111
D
2985 all_clients.add(actual_client)
2986 return
e7e94f2a 2987
379e44ed 2988 # Android player_response does not have microFormats which are needed for
2989 # extraction of some data. So we return the initial_pr with formats
2990 # stripped out even if not requested by the user
2991 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 2992 if initial_pr:
2993 pr = dict(initial_pr)
2994 pr['streamingData'] = None
b6de707d 2995 prs.append(pr)
379e44ed 2996
2997 last_error = None
b6de707d 2998 tried_iframe_fallback = False
2999 player_url = None
c0bc527b 3000 while clients:
e7870111 3001 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3002 player_ytcfg = master_ytcfg if client == 'web' else {}
c0bc527b
M
3003 if 'configs' not in self._configuration_arg('player_skip'):
3004 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3005
b6de707d 3006 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3007 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3008 if 'js' in self._configuration_arg('player_skip'):
3009 require_js_player = False
3010 player_url = None
3011
3012 if not player_url and not tried_iframe_fallback and require_js_player:
3013 player_url = self._download_player_url(video_id)
3014 tried_iframe_fallback = True
3015
379e44ed 3016 try:
3017 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 3018 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 3019 except ExtractorError as e:
3020 if last_error:
3021 self.report_warning(last_error)
3022 last_error = e
3023 continue
3024
11f9be09 3025 if pr:
b6de707d 3026 prs.append(pr)
c0bc527b 3027
e7e94f2a 3028 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3029 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3030 append_client(f'{base_client}_creator')
e7e94f2a 3031 elif self._is_agegated(pr):
e7870111
D
3032 if variant == 'tv_embedded':
3033 append_client(f'{base_client}_embedded')
3034 elif not variant:
3035 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3036
379e44ed 3037 if last_error:
b6de707d 3038 if not len(prs):
379e44ed 3039 raise last_error
3040 self.report_warning(last_error)
b6de707d 3041 return prs, player_url
11f9be09 3042
a1b2d843 3043 def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3044 itags, stream_ids = {}, []
2a9c6dcd 3045 itag_qualities, res_qualities = {}, {}
d3fc8074 3046 q = qualities([
2a9c6dcd 3047 # Normally tiny is the smallest video-only formats. But
3048 # audio-only formats with unknown quality may get tagged as tiny
3049 'tiny',
3050 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3051 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3052 ])
11f9be09 3053 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3054
545cc85d 3055 for fmt in streaming_formats:
727029c5 3056 if fmt.get('targetDurationSec'):
545cc85d 3057 continue
321bf820 3058
cc2db878 3059 itag = str_or_none(fmt.get('itag'))
9297939e 3060 audio_track = fmt.get('audioTrack') or {}
3061 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3062 if stream_id in stream_ids:
3063 continue
3064
cc2db878 3065 quality = fmt.get('quality')
2a9c6dcd 3066 height = int_or_none(fmt.get('height'))
d3fc8074 3067 if quality == 'tiny' or not quality:
3068 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3069 # The 3gp format (17) in android client has a quality of "small",
3070 # but is actually worse than other formats
3071 if itag == '17':
3072 quality = 'tiny'
3073 if quality:
3074 if itag:
3075 itag_qualities[itag] = quality
3076 if height:
3077 res_qualities[height] = quality
cc2db878 3078 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3079 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3080 # number of fragment that would subsequently requested with (`&sq=N`)
3081 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3082 continue
3083
545cc85d 3084 fmt_url = fmt.get('url')
3085 if not fmt_url:
3086 sc = compat_parse_qs(fmt.get('signatureCipher'))
3087 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3088 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3089 if not (sc and fmt_url and encrypted_sig):
3090 continue
545cc85d 3091 if not player_url:
201e9eaa 3092 continue
545cc85d 3093 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
3094 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
3095 fmt_url += '&' + sp + '=' + signature
3096
404f611f 3097 query = parse_qs(fmt_url)
3098 throttled = False
b2916526 3099 if query.get('n'):
404f611f 3100 try:
3101 fmt_url = update_url_query(fmt_url, {
3102 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3103 except ExtractorError as e:
aa9369a2 3104 self.report_warning(
3105 f'nsig extraction failed: You may experience throttling for some formats\n'
3106 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
404f611f 3107 throttled = True
3108
545cc85d 3109 if itag:
a0bb6ce5 3110 itags[itag] = 'https'
9297939e 3111 stream_ids.append(stream_id)
3112
0ad92dfb 3113 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3114 language_preference = (
3115 10 if audio_track.get('audioIsDefault') and 10
3116 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3117 else -1)
0ad92dfb 3118 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3119 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3120 # Make sure to avoid false positives with small duration differences.
3121 # Eg: __2ABJjxzNo, ySuUZEjARPY
3122 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3123 if is_damaged:
3124 self.report_warning(f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3125 dct = {
3126 'asr': int_or_none(fmt.get('audioSampleRate')),
3127 'filesize': int_or_none(fmt.get('contentLength')),
3128 'format_id': itag,
34921b43 3129 'format_note': join_nonempty(
26e8e044 3130 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3131 ' (default)' if language_preference > 0 else ''),
404f611f 3132 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
0ad92dfb 3133 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
c18d4482 3134 'source_preference': -10 if throttled else -1,
a4211baf 3135 'fps': int_or_none(fmt.get('fps')) or None,
2a9c6dcd 3136 'height': height,
dca3ff4a 3137 'quality': q(quality),
727029c5 3138 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3139 'tbr': tbr,
545cc85d 3140 'url': fmt_url,
2a9c6dcd 3141 'width': int_or_none(fmt.get('width')),
ab6df717 3142 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3143 'desc' if language_preference < -1 else ''),
3144 'language_preference': language_preference,
a405b38f 3145 # Strictly de-prioritize damaged and 3gp formats
3146 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3147 }
60bdb7bd 3148 mime_mobj = re.match(
3149 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3150 if mime_mobj:
3151 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3152 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3153 no_audio = dct.get('acodec') == 'none'
3154 no_video = dct.get('vcodec') == 'none'
3155 if no_audio:
3156 dct['vbr'] = tbr
3157 if no_video:
3158 dct['abr'] = tbr
3159 if no_audio or no_video:
545cc85d 3160 dct['downloader_options'] = {
3161 # Youtube throttles chunks >~10M
3162 'http_chunk_size': 10485760,
bf1317d2 3163 }
7c60c33e 3164 if dct.get('ext'):
3165 dct['container'] = dct['ext'] + '_dash'
11f9be09 3166 yield dct
545cc85d 3167
adbc4ec4 3168 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3169 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3170 if not self.get_param('youtube_include_hls_manifest', True):
3171 skip_manifests.append('hls')
3172 get_dash = 'dash' not in skip_manifests and (
3173 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3174 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3175
a0bb6ce5 3176 def process_manifest_format(f, proto, itag):
3177 if itag in itags:
3178 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3179 return False
3180 itag = f'{itag}-{proto}'
3181 if itag:
3182 f['format_id'] = itag
3183 itags[itag] = proto
3184
3185 f['quality'] = next((
3186 q(qdict[val])
e339d25a 3187 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3188 if val in qdict), -1)
3189 return True
2a9c6dcd 3190
11f9be09 3191 for sd in streaming_data:
5d3a0e79 3192 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3193 if hls_manifest_url:
2a9c6dcd 3194 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
a0bb6ce5 3195 if process_manifest_format(f, 'hls', self._search_regex(
3196 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3197 yield f
545cc85d 3198
5d3a0e79 3199 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3200 if dash_manifest_url:
2a9c6dcd 3201 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
a0bb6ce5 3202 if process_manifest_format(f, 'dash', f['format_id']):
3203 f['filesize'] = int_or_none(self._search_regex(
3204 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3205 if live_from_start:
3206 f['is_from_start'] = True
3207
a0bb6ce5 3208 yield f
11f9be09 3209
720c3099 3210 def _extract_storyboard(self, player_responses, duration):
3211 spec = get_first(
3212 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3213 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3214 if not base_url:
720c3099 3215 return
720c3099 3216 L = len(spec) - 1
3217 for i, args in enumerate(spec):
3218 args = args.split('#')
3219 counts = list(map(int_or_none, args[:5]))
3220 if len(args) != 8 or not all(counts):
3221 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3222 continue
3223 width, height, frame_count, cols, rows = counts
3224 N, sigh = args[6:]
3225
3226 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3227 fragment_count = frame_count / (cols * rows)
3228 fragment_duration = duration / fragment_count
3229 yield {
3230 'format_id': f'sb{i}',
3231 'format_note': 'storyboard',
3232 'ext': 'mhtml',
3233 'protocol': 'mhtml',
3234 'acodec': 'none',
3235 'vcodec': 'none',
3236 'url': url,
3237 'width': width,
3238 'height': height,
3239 'fragments': [{
b3edc806 3240 'url': url.replace('$M', str(j)),
720c3099 3241 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3242 } for j in range(math.ceil(fragment_count))],
3243 }
3244
adbc4ec4 3245 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3246 webpage = None
3247 if 'webpage' not in self._configuration_arg('player_skip'):
3248 webpage = self._download_webpage(
3249 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
11f9be09 3250
3251 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3252
b6de707d 3253 player_responses, player_url = self._extract_player_responses(
11f9be09 3254 self._get_requested_clients(url, smuggled_data),
99e9e001 3255 video_id, webpage, master_ytcfg)
11f9be09 3256
adbc4ec4
THD
3257 return webpage, master_ytcfg, player_responses, player_url
3258
a1b2d843 3259 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3260 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3261 is_live = get_first(video_details, 'isLive')
3262 if is_live is None:
3263 is_live = get_first(live_broadcast_details, 'isLiveNow')
3264
3265 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
a1b2d843 3266 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration))
adbc4ec4
THD
3267
3268 return live_broadcast_details, is_live, streaming_data, formats
3269
3270 def _real_extract(self, url):
3271 url, smuggled_data = unsmuggle_url(url, {})
3272 video_id = self._match_id(url)
3273
3274 base_url = self.http_scheme() + '//www.youtube.com/'
3275 webpage_url = base_url + 'watch?v=' + video_id
3276
3277 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3278
11f9be09 3279 playability_statuses = traverse_obj(
3280 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3281
3282 trailer_video_id = get_first(
3283 playability_statuses,
3284 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3285 expected_type=str)
3286 if trailer_video_id:
3287 return self.url_result(
3288 trailer_video_id, self.ie_key(), trailer_video_id)
3289
3290 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3291 if webpage else (lambda x: None))
3292
3293 video_details = traverse_obj(
3294 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3295 microformats = traverse_obj(
3296 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3297 expected_type=dict, default=[])
3298 video_title = (
3299 get_first(video_details, 'title')
3300 or self._get_text(microformats, (..., 'title'))
3301 or search_meta(['og:title', 'twitter:title', 'title']))
3302 video_description = get_first(video_details, 'shortDescription')
3303
d89257f3 3304 multifeed_metadata_list = get_first(
3305 player_responses,
3306 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3307 expected_type=str)
3308 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3309 if self.get_param('noplaylist'):
11f9be09 3310 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3311 else:
3312 entries = []
3313 feed_ids = []
3314 for feed in multifeed_metadata_list.split(','):
3315 # Unquote should take place before split on comma (,) since textual
3316 # fields may contain comma as well (see
3317 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3318 feed_data = compat_parse_qs(
3319 compat_urllib_parse_unquote_plus(feed))
3320
3321 def feed_entry(name):
3322 return try_get(
3323 feed_data, lambda x: x[name][0], compat_str)
3324
3325 feed_id = feed_entry('id')
3326 if not feed_id:
3327 continue
3328 feed_title = feed_entry('title')
3329 title = video_title
3330 if feed_title:
3331 title += ' (%s)' % feed_title
3332 entries.append({
3333 '_type': 'url_transparent',
3334 'ie_key': 'Youtube',
3335 'url': smuggle_url(
3336 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3337 {'force_singlefeed': True}),
3338 'title': title,
3339 })
3340 feed_ids.append(feed_id)
3341 self.to_screen(
3342 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3343 % (', '.join(feed_ids), video_id))
3344 return self.playlist_result(
3345 entries, video_id, video_title, video_description)
11f9be09 3346
a1b2d843 3347 duration = int_or_none(
3348 get_first(video_details, 'lengthSeconds')
3349 or get_first(microformats, 'lengthSeconds')
3350 or parse_duration(search_meta('duration'))) or None
3351
3352 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(
3353 video_id, microformats, video_details, player_responses, player_url, duration)
bf1317d2 3354
545cc85d 3355 if not formats:
11f9be09 3356 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3357 self.report_drm(video_id)
11f9be09 3358 pemr = get_first(
3359 playability_statuses,
3360 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3361 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3362 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3363 if subreason:
545cc85d 3364 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3365 countries = get_first(microformats, 'availableCountries')
545cc85d 3366 if not countries:
3367 regions_allowed = search_meta('regionsAllowed')
3368 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3369 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3370 reason += f'. {subreason}'
545cc85d 3371 if reason:
b7da73eb 3372 self.raise_no_formats(reason, expected=True)
bf1317d2 3373
11f9be09 3374 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3375 if not keywords and webpage:
3376 keywords = [
3377 unescapeHTML(m.group('content'))
3378 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3379 for keyword in keywords:
3380 if keyword.startswith('yt:stretch='):
201c1459 3381 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3382 if mobj:
3383 # NB: float is intentional for forcing float division
3384 w, h = (float(v) for v in mobj.groups())
3385 if w > 0 and h > 0:
3386 ratio = w / h
3387 for f in formats:
3388 if f.get('vcodec') != 'none':
3389 f['stretched_ratio'] = ratio
3390 break
a709d873 3391 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3392 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3393 if thumbnail_url:
3394 thumbnails.append({
3395 'url': thumbnail_url,
ff2751ac 3396 })
fccf5021 3397 original_thumbnails = thumbnails.copy()
3398
0ba692ac 3399 # The best resolution thumbnails sometimes does not appear in the webpage
3400 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3401 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3402 thumbnail_names = [
3403 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
cca80fe6 3404 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3405 'mqdefault', 'mq1', 'mq2', 'mq3',
3406 'default', '1', '2', '3'
3407 ]
cca80fe6 3408 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3409 thumbnails.extend({
3410 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3411 video_id=video_id, name=name, ext=ext,
3412 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3413 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3414 for thumb in thumbnails:
cca80fe6 3415 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3416 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3417 self._remove_duplicate_formats(thumbnails)
fccf5021 3418 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3419
7ea65411 3420 category = get_first(microformats, 'category') or search_meta('genre')
3421 channel_id = str_or_none(
3422 get_first(video_details, 'channelId')
3423 or get_first(microformats, 'externalChannelId')
3424 or search_meta('channelId'))
7ea65411 3425 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3426
3427 live_content = get_first(video_details, 'isLiveContent')
3428 is_upcoming = get_first(video_details, 'isUpcoming')
3429 if is_live is None:
3430 if is_upcoming or live_content is False:
3431 is_live = False
3432 if is_upcoming is None and (live_content or is_live):
3433 is_upcoming = False
adbc4ec4
THD
3434 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3435 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3436 if not duration and live_end_time and live_start_time:
3437 duration = live_end_time - live_start_time
3438
3439 if is_live and self.get_param('live_from_start'):
3440 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3441
720c3099 3442 formats.extend(self._extract_storyboard(player_responses, duration))
3443
3444 # Source is given priority since formats that throttle are given lower source_preference
3445 # When throttling issue is fully fixed, remove this
3446 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3447
545cc85d 3448 info = {
3449 'id': video_id,
39ca3b5c 3450 'title': video_title,
545cc85d 3451 'formats': formats,
3452 'thumbnails': thumbnails,
fccf5021 3453 # The best thumbnail that we are sure exists. Prevents unnecessary
3454 # URL checking if user don't care about getting the best possible thumbnail
3455 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3456 'description': video_description,
11f9be09 3457 'uploader': get_first(video_details, 'author'),
545cc85d 3458 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3459 'uploader_url': owner_profile_url,
3460 'channel_id': channel_id,
e0ddbd02 3461 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
545cc85d 3462 'duration': duration,
3463 'view_count': int_or_none(
11f9be09 3464 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3465 or search_meta('interactionCount')),
11f9be09 3466 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3467 'age_limit': 18 if (
11f9be09 3468 get_first(microformats, 'isFamilySafe') is False
545cc85d 3469 or search_meta('isFamilyFriendly') == 'false'
3470 or search_meta('og:restrictions:age') == '18+') else 0,
3471 'webpage_url': webpage_url,
3472 'categories': [category] if category else None,
3473 'tags': keywords,
11f9be09 3474 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3475 'is_live': is_live,
3476 'was_live': (False if is_live or is_upcoming or live_content is False
3477 else None if is_live is None or is_upcoming is None
3478 else live_content),
3479 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3480 'release_timestamp': live_start_time,
545cc85d 3481 }
b477fc13 3482
3944e7af 3483 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3484 if pctr:
ecdc9049 3485 def get_lang_code(track):
3486 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3487 or track.get('languageCode'))
3488
3489 # Converted into dicts to remove duplicates
3490 captions = {
3491 get_lang_code(sub): sub
3492 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3493 translation_languages = {
3494 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3495 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3496
774d79cc 3497 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3498 lang_subs = container.setdefault(lang_code, [])
545cc85d 3499 for fmt in self._SUBTITLE_FORMATS:
3500 query.update({
3501 'fmt': fmt,
3502 })
3503 lang_subs.append({
3504 'ext': fmt,
60f393e4 3505 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3506 'name': sub_name,
545cc85d 3507 })
7e72694b 3508
ecdc9049 3509 subtitles, automatic_captions = {}, {}
3510 for lang_code, caption_track in captions.items():
3511 base_url = caption_track.get('baseUrl')
1235d333 3512 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3513 if not base_url:
3514 continue
ecdc9049 3515 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3516 if caption_track.get('kind') != 'asr':
545cc85d 3517 if not lang_code:
3518 continue
3519 process_language(
ecdc9049 3520 subtitles, base_url, lang_code, lang_name, {})
3521 if not caption_track.get('isTranslatable'):
3522 continue
3944e7af 3523 for trans_code, trans_name in translation_languages.items():
3524 if not trans_code:
545cc85d 3525 continue
1235d333 3526 orig_trans_code = trans_code
ecdc9049 3527 if caption_track.get('kind') != 'asr':
18e49408 3528 if 'translated_subs' in self._configuration_arg('skip'):
3529 continue
ecdc9049 3530 trans_code += f'-{lang_code}'
3531 trans_name += format_field(lang_name, template=' from %s')
d49669ac 3532 # Add an "-orig" label to the original language so that it can be distinguished.
3533 # The subs are returned without "-orig" as well for compatibility
1235d333 3534 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3535 process_language(
d49669ac 3536 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3537 # Setting tlang=lang returns damaged subtitles.
d49669ac 3538 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3539 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
ecdc9049 3540 info['automatic_captions'] = automatic_captions
3541 info['subtitles'] = subtitles
7e72694b 3542
545cc85d 3543 parsed_url = compat_urllib_parse_urlparse(url)
3544 for component in [parsed_url.fragment, parsed_url.query]:
3545 query = compat_parse_qs(component)
3546 for k, v in query.items():
3547 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3548 d_k += '_time'
3549 if d_k not in info and k in s_ks:
3550 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3551
3552 # Youtube Music Auto-generated description
822b9d9c 3553 if video_description:
38d70284 3554 mobj = re.search(r'(?s)(?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?.+\nAuto-generated by YouTube\.\s*$', video_description)
822b9d9c 3555 if mobj:
822b9d9c
RA
3556 release_year = mobj.group('release_year')
3557 release_date = mobj.group('release_date')
3558 if release_date:
3559 release_date = release_date.replace('-', '')
3560 if not release_year:
545cc85d 3561 release_year = release_date[:4]
3562 info.update({
3563 'album': mobj.group('album'.strip()),
3564 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3565 'track': mobj.group('track').strip(),
3566 'release_date': release_date,
cc2db878 3567 'release_year': int_or_none(release_year),
545cc85d 3568 })
7e72694b 3569
545cc85d 3570 initial_data = None
3571 if webpage:
3572 initial_data = self._extract_yt_initial_variable(
3573 webpage, self._YT_INITIAL_DATA_RE, video_id,
3574 'yt initial data')
3575 if not initial_data:
99e9e001 3576 query = {'videoId': video_id}
3577 query.update(self._get_checkok_params())
109dd3b2 3578 initial_data = self._extract_response(
3579 item_id=video_id, ep='next', fatal=False,
99e9e001 3580 ytcfg=master_ytcfg, query=query,
3581 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3582 note='Downloading initial data API JSON')
545cc85d 3583
c60ee3a2 3584 try:
3585 # This will error if there is no livechat
3586 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
ecdc9049 3587 info.setdefault('subtitles', {})['live_chat'] = [{
c60ee3a2 3588 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3589 'video_id': video_id,
3590 'ext': 'json',
f6745c49 3591 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3592 }]
3593 except (KeyError, IndexError, TypeError):
3594 pass
545cc85d 3595
3596 if initial_data:
7c365c21 3597 info['chapters'] = (
3598 self._extract_chapters_from_json(initial_data, duration)
3599 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3600 or None)
545cc85d 3601
17322130 3602 contents = traverse_obj(
3603 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3604 expected_type=list, default=[])
3605
3606 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3607 if vpir:
3608 stl = vpir.get('superTitleLink')
3609 if stl:
3610 stl = self._get_text(stl)
3611 if try_get(
3612 vpir,
3613 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3614 info['location'] = stl
3615 else:
3616 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3617 if mobj:
545cc85d 3618 info.update({
17322130 3619 'series': mobj.group(1),
3620 'season_number': int(mobj.group(2)),
3621 'episode_number': int(mobj.group(3)),
545cc85d 3622 })
17322130 3623 for tlb in (try_get(
3624 vpir,
3625 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3626 list) or []):
3627 tbr = tlb.get('toggleButtonRenderer') or {}
3628 for getter, regex in [(
3629 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3630 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3631 lambda x: x['accessibility'],
3632 lambda x: x['accessibilityData']['accessibilityData'],
3633 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3634 label = (try_get(tbr, getter, dict) or {}).get('label')
3635 if label:
3636 mobj = re.match(regex, label)
3637 if mobj:
3638 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3639 break
17322130 3640 sbr_tooltip = try_get(
3641 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3642 if sbr_tooltip:
3643 like_count, dislike_count = sbr_tooltip.split(' / ')
3644 info.update({
3645 'like_count': str_to_int(like_count),
3646 'dislike_count': str_to_int(dislike_count),
3647 })
3648 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3649 if vsir:
3650 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3651 info.update({
3652 'channel': self._get_text(vor, 'title'),
3653 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3654
3655 rows = try_get(
3656 vsir,
3657 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3658 list) or []
3659 multiple_songs = False
3660 for row in rows:
3661 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3662 multiple_songs = True
3663 break
3664 for row in rows:
3665 mrr = row.get('metadataRowRenderer') or {}
3666 mrr_title = mrr.get('title')
3667 if not mrr_title:
3668 continue
3669 mrr_title = self._get_text(mrr, 'title')
3670 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3671 if mrr_title == 'License':
3672 info['license'] = mrr_contents_text
3673 elif not multiple_songs:
3674 if mrr_title == 'Album':
3675 info['album'] = mrr_contents_text
3676 elif mrr_title == 'Artist':
3677 info['artist'] = mrr_contents_text
3678 elif mrr_title == 'Song':
3679 info['track'] = mrr_contents_text
545cc85d 3680
3681 fallbacks = {
3682 'channel': 'uploader',
3683 'channel_id': 'uploader_id',
3684 'channel_url': 'uploader_url',
3685 }
992f9a73 3686
17322130 3687 # The upload date for scheduled, live and past live streams / premieres in microformats
3688 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3689 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3690 upload_date = (
3691 unified_strdate(get_first(microformats, 'uploadDate'))
3692 or unified_strdate(search_meta('uploadDate')))
3693 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
3694 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d')
3695 info['upload_date'] = upload_date
992f9a73 3696
545cc85d 3697 for to, frm in fallbacks.items():
3698 if not info.get(to):
3699 info[to] = info.get(frm)
3700
3701 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3702 v = info.get(s_k)
3703 if v:
3704 info[d_k] = v
b84071c0 3705
11f9be09 3706 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3707 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3708 is_membersonly = None
b28f8d24 3709 is_premium = None
c224251a
M
3710 if initial_data and is_private is not None:
3711 is_membersonly = False
b28f8d24 3712 is_premium = False
47193e02 3713 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3714 badge_labels = set()
3715 for content in contents:
3716 if not isinstance(content, dict):
3717 continue
3718 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3719 for badge_label in badge_labels:
3720 if badge_label.lower() == 'members only':
3721 is_membersonly = True
3722 elif badge_label.lower() == 'premium':
3723 is_premium = True
3724 elif badge_label.lower() == 'unlisted':
3725 is_unlisted = True
c224251a 3726
c224251a
M
3727 info['availability'] = self._availability(
3728 is_private=is_private,
b28f8d24 3729 needs_premium=is_premium,
c224251a
M
3730 needs_subscription=is_membersonly,
3731 needs_auth=info['age_limit'] >= 18,
3732 is_unlisted=None if is_private is None else is_unlisted)
3733
a2160aa4 3734 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3735
11f9be09 3736 self.mark_watched(video_id, player_responses)
d77ab8e2 3737
545cc85d 3738 return info
c5e8d7af 3739
a61fd4cf 3740
a6213a49 3741class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3742
182bda88 3743 @staticmethod
3744 def passthrough_smuggled_data(func):
3745 def _smuggle(entries, smuggled_data):
3746 for entry in entries:
3747 # TODO: Convert URL to music.youtube instead.
3748 # Do we need to passthrough any other smuggled_data?
3749 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3750 yield entry
3751
3752 @functools.wraps(func)
3753 def wrapper(self, url):
3754 url, smuggled_data = unsmuggle_url(url, {})
3755 if self.is_music_url(url):
3756 smuggled_data['is_music_url'] = True
3757 info_dict = func(self, url, smuggled_data)
3758 if smuggled_data and info_dict.get('entries'):
3759 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3760 return info_dict
3761 return wrapper
3762
a6213a49 3763 def _extract_channel_id(self, webpage):
3764 channel_id = self._html_search_meta(
3765 'channelId', webpage, 'channel id', default=None)
3766 if channel_id:
3767 return channel_id
3768 channel_url = self._html_search_meta(
3769 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3770 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3771 'twitter:app:url:googleplay'), webpage, 'channel url')
3772 return self._search_regex(
3773 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3774 channel_url, 'channel id')
15f6397c 3775
8bdd16b4 3776 @staticmethod
cd7c66cf 3777 def _extract_basic_item_renderer(item):
3778 # Modified from _extract_grid_item_renderer
201c1459 3779 known_basic_renderers = (
3780 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
cd7c66cf 3781 )
3782 for key, renderer in item.items():
201c1459 3783 if not isinstance(renderer, dict):
cd7c66cf 3784 continue
201c1459 3785 elif key in known_basic_renderers:
3786 return renderer
3787 elif key.startswith('grid') and key.endswith('Renderer'):
3788 return renderer
8bdd16b4 3789
8bdd16b4 3790 def _grid_entries(self, grid_renderer):
3791 for item in grid_renderer['items']:
3792 if not isinstance(item, dict):
39b62db1 3793 continue
cd7c66cf 3794 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3795 if not isinstance(renderer, dict):
3796 continue
052e1350 3797 title = self._get_text(renderer, 'title')
fe93e2c4 3798
8bdd16b4 3799 # playlist
3800 playlist_id = renderer.get('playlistId')
3801 if playlist_id:
3802 yield self.url_result(
3803 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3804 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3805 video_title=title)
201c1459 3806 continue
8bdd16b4 3807 # video
3808 video_id = renderer.get('videoId')
3809 if video_id:
3810 yield self._extract_video(renderer)
201c1459 3811 continue
8bdd16b4 3812 # channel
3813 channel_id = renderer.get('channelId')
3814 if channel_id:
8bdd16b4 3815 yield self.url_result(
3816 'https://www.youtube.com/channel/%s' % channel_id,
3817 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3818 continue
3819 # generic endpoint URL support
3820 ep_url = urljoin('https://www.youtube.com/', try_get(
3821 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3822 compat_str))
3823 if ep_url:
3824 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3825 if ie.suitable(ep_url):
3826 yield self.url_result(
3827 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3828 break
8bdd16b4 3829
16aa9ea4 3830 def _music_reponsive_list_entry(self, renderer):
3831 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3832 if video_id:
3833 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3834 ie=YoutubeIE.ie_key(), video_id=video_id)
3835 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3836 if playlist_id:
3837 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3838 if video_id:
3839 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3840 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3841 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3842 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3843 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3844 if browse_id:
3845 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3846 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3847
3d3dddc9 3848 def _shelf_entries_from_content(self, shelf_renderer):
3849 content = shelf_renderer.get('content')
3850 if not isinstance(content, dict):
8bdd16b4 3851 return
cd7c66cf 3852 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 3853 if renderer:
3854 # TODO: add support for nested playlists so each shelf is processed
3855 # as separate playlist
3856 # TODO: this includes only first N items
3857 for entry in self._grid_entries(renderer):
3858 yield entry
3859 renderer = content.get('horizontalListRenderer')
3860 if renderer:
3861 # TODO
3862 pass
8bdd16b4 3863
29f7c58a 3864 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 3865 ep = try_get(
3866 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3867 compat_str)
3868 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 3869 if shelf_url:
29f7c58a 3870 # Skipping links to another channels, note that checking for
3871 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3872 # will not work
3873 if skip_channels and '/channels?' in shelf_url:
3874 return
052e1350 3875 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 3876 yield self.url_result(shelf_url, video_title=title)
3877 # Shelf may not contain shelf URL, fallback to extraction from content
3878 for entry in self._shelf_entries_from_content(shelf_renderer):
3879 yield entry
c5e8d7af 3880
8bdd16b4 3881 def _playlist_entries(self, video_list_renderer):
3882 for content in video_list_renderer['contents']:
3883 if not isinstance(content, dict):
3884 continue
3885 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3886 if not isinstance(renderer, dict):
3887 continue
3888 video_id = renderer.get('videoId')
3889 if not video_id:
3890 continue
3891 yield self._extract_video(renderer)
07aeced6 3892
3462ffa8 3893 def _rich_entries(self, rich_grid_renderer):
3894 renderer = try_get(
70d5c17b 3895 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 3896 video_id = renderer.get('videoId')
3897 if not video_id:
3898 return
3899 yield self._extract_video(renderer)
3900
8bdd16b4 3901 def _video_entry(self, video_renderer):
3902 video_id = video_renderer.get('videoId')
3903 if video_id:
3904 return self._extract_video(video_renderer)
dacb3a86 3905
8bdd16b4 3906 def _post_thread_entries(self, post_thread_renderer):
3907 post_renderer = try_get(
3908 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3909 if not post_renderer:
3910 return
3911 # video attachment
3912 video_renderer = try_get(
895b0931 3913 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3914 video_id = video_renderer.get('videoId')
3915 if video_id:
3916 entry = self._extract_video(video_renderer)
8bdd16b4 3917 if entry:
3918 yield entry
895b0931 3919 # playlist attachment
3920 playlist_id = try_get(
3921 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3922 if playlist_id:
3923 yield self.url_result(
e28f1c0a 3924 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3925 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 3926 # inline video links
3927 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3928 for run in runs:
3929 if not isinstance(run, dict):
3930 continue
3931 ep_url = try_get(
3932 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3933 if not ep_url:
3934 continue
3935 if not YoutubeIE.suitable(ep_url):
3936 continue
3937 ep_video_id = YoutubeIE._match_id(ep_url)
3938 if video_id == ep_video_id:
3939 continue
895b0931 3940 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 3941
8bdd16b4 3942 def _post_thread_continuation_entries(self, post_thread_continuation):
3943 contents = post_thread_continuation.get('contents')
3944 if not isinstance(contents, list):
3945 return
3946 for content in contents:
3947 renderer = content.get('backstagePostThreadRenderer')
3948 if not isinstance(renderer, dict):
3949 continue
3950 for entry in self._post_thread_entries(renderer):
3951 yield entry
07aeced6 3952
39ed931e 3953 r''' # unused
3954 def _rich_grid_entries(self, contents):
3955 for content in contents:
3956 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
3957 if video_renderer:
3958 entry = self._video_entry(video_renderer)
3959 if entry:
3960 yield entry
3961 '''
52efa4b3 3962
a6213a49 3963 def _extract_entries(self, parent_renderer, continuation_list):
3964 # continuation_list is modified in-place with continuation_list = [continuation_token]
3965 continuation_list[:] = [None]
3966 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3967 for content in contents:
3968 if not isinstance(content, dict):
3969 continue
16aa9ea4 3970 is_renderer = traverse_obj(
3971 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
3972 expected_type=dict)
a6213a49 3973 if not is_renderer:
3974 renderer = content.get('richItemRenderer')
3975 if renderer:
3976 for entry in self._rich_entries(renderer):
3977 yield entry
3978 continuation_list[0] = self._extract_continuation(parent_renderer)
3979 continue
3980 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3981 for isr_content in isr_contents:
3982 if not isinstance(isr_content, dict):
8bdd16b4 3983 continue
69184e41 3984
a6213a49 3985 known_renderers = {
3986 'playlistVideoListRenderer': self._playlist_entries,
3987 'gridRenderer': self._grid_entries,
3988 'shelfRenderer': lambda x: self._shelf_entries(x),
16aa9ea4 3989 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 3990 'backstagePostThreadRenderer': self._post_thread_entries,
3991 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 3992 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
3993 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
a6213a49 3994 }
3995 for key, renderer in isr_content.items():
3996 if key not in known_renderers:
3997 continue
3998 for entry in known_renderers[key](renderer):
3999 if entry:
4000 yield entry
4001 continuation_list[0] = self._extract_continuation(renderer)
4002 break
70d5c17b 4003
4004 if not continuation_list[0]:
a6213a49 4005 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4006
a6213a49 4007 if not continuation_list[0]:
4008 continuation_list[0] = self._extract_continuation(parent_renderer)
4009
4010 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4011 continuation_list = [None]
4012 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4013 tab_content = try_get(tab, lambda x: x['content'], dict)
4014 if not tab_content:
4015 return
3462ffa8 4016 parent_renderer = (
29f7c58a 4017 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4018 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
70d5c17b 4019 for entry in extract_entries(parent_renderer):
4020 yield entry
3462ffa8 4021 continuation = continuation_list[0]
d069eca7 4022
8bdd16b4 4023 for page_num in itertools.count(1):
4024 if not continuation:
4025 break
99e9e001 4026 headers = self.generate_api_headers(
4027 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4028 response = self._extract_response(
4029 item_id='%s page %s' % (item_id, page_num),
fe93e2c4 4030 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4031 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4032
4033 if not response:
8bdd16b4 4034 break
ac56cf38 4035 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4036 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4037 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4038
69184e41 4039 known_continuation_renderers = {
4040 'playlistVideoListContinuation': self._playlist_entries,
4041 'gridContinuation': self._grid_entries,
4042 'itemSectionContinuation': self._post_thread_continuation_entries,
4043 'sectionListContinuation': extract_entries, # for feeds
4044 }
8bdd16b4 4045 continuation_contents = try_get(
69184e41 4046 response, lambda x: x['continuationContents'], dict) or {}
4047 continuation_renderer = None
4048 for key, value in continuation_contents.items():
4049 if key not in known_continuation_renderers:
3462ffa8 4050 continue
69184e41 4051 continuation_renderer = value
4052 continuation_list = [None]
4053 for entry in known_continuation_renderers[key](continuation_renderer):
4054 yield entry
4055 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4056 break
4057 if continuation_renderer:
4058 continue
c5e8d7af 4059
a1b535bd 4060 known_renderers = {
e4b98809 4061 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4062 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4063 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4064 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4065 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4066 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4067 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4068 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4069 }
cce889b9 4070 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4071 continuation_items = try_get(
cce889b9 4072 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4073 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4074 video_items_renderer = None
4075 for key, value in continuation_item.items():
4076 if key not in known_renderers:
8bdd16b4 4077 continue
a1b535bd 4078 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4079 continuation_list = [None]
a1b535bd 4080 for entry in known_renderers[key][0](video_items_renderer):
4081 yield entry
9ba5705a 4082 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4083 break
4084 if video_items_renderer:
4085 continue
8bdd16b4 4086 break
9558dcec 4087
8bdd16b4 4088 @staticmethod
7c219ea6 4089 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4090 for tab in tabs:
cd684175 4091 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4092 if renderer.get('selected') is True:
4093 return renderer
2b3c2546 4094 else:
7c219ea6 4095 if fatal:
4096 raise ExtractorError('Unable to find selected tab')
b82f815f 4097
47193e02 4098 @classmethod
4099 def _extract_uploader(cls, data):
8bdd16b4 4100 uploader = {}
47193e02 4101 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
4102 owner = try_get(
4103 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4104 if owner:
4105 uploader['uploader'] = owner.get('text')
4106 uploader['uploader_id'] = try_get(
4107 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
4108 uploader['uploader_url'] = urljoin(
4109 'https://www.youtube.com/',
4110 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
9c3fe2ef 4111 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4112
ac56cf38 4113 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4114 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4115 tags = []
b60419c5 4116
8bdd16b4 4117 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4118 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4119 renderer = try_get(
4120 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4121 if renderer:
b60419c5 4122 channel_name = renderer.get('title')
4123 channel_url = renderer.get('channelUrl')
4124 channel_id = renderer.get('externalId')
39ed931e 4125 else:
64c0d954 4126 renderer = try_get(
4127 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4128
8bdd16b4 4129 if renderer:
4130 title = renderer.get('title')
ecc97af3 4131 description = renderer.get('description', '')
b60419c5 4132 playlist_id = channel_id
4133 tags = renderer.get('keywords', '').split()
b60419c5 4134
301d07fc 4135 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4136 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4137 def _get_uncropped(url):
4138 return url_or_none((url or '').split('=')[0] + '=s0')
4139
4140 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4141 if avatar_thumbnails:
4142 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4143 if uncropped_avatar:
4144 avatar_thumbnails.append({
4145 'url': uncropped_avatar,
4146 'id': 'avatar_uncropped',
4147 'preference': 1
4148 })
4149
4150 channel_banners = self._extract_thumbnails(
4151 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4152 for banner in channel_banners:
4153 banner['preference'] = -10
4154
4155 if channel_banners:
4156 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4157 if uncropped_banner:
4158 channel_banners.append({
4159 'url': uncropped_banner,
4160 'id': 'banner_uncropped',
4161 'preference': -5
4162 })
4163
4164 primary_thumbnails = self._extract_thumbnails(
4165 primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
a709d873 4166
3462ffa8 4167 if playlist_id is None:
70d5c17b 4168 playlist_id = item_id
f0d785d3 4169
4170 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4171 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4172 if title is None:
f0d785d3 4173 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4174 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4175 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4176
b60419c5 4177 metadata = {
4178 'playlist_id': playlist_id,
4179 'playlist_title': title,
4180 'playlist_description': description,
4181 'uploader': channel_name,
4182 'uploader_id': channel_id,
4183 'uploader_url': channel_url,
301d07fc 4184 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4185 'tags': tags,
f0d785d3 4186 'view_count': self._get_count(playlist_stats, 1),
4187 'availability': self._extract_availability(data),
4188 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4189 'playlist_count': self._get_count(playlist_stats, 0),
4190 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4191 }
4192 if not channel_id:
4193 metadata.update(self._extract_uploader(data))
4194 metadata.update({
4195 'channel': metadata['uploader'],
4196 'channel_id': metadata['uploader_id'],
4197 'channel_url': metadata['uploader_url']})
4198 return self.playlist_result(
d069eca7 4199 self._entries(
ac56cf38 4200 selected_tab, playlist_id, ytcfg,
4201 self._extract_account_syncid(ytcfg, data),
4202 self._extract_visitor_data(data, ytcfg)),
b60419c5 4203 **metadata)
73c4ac2c 4204
ac56cf38 4205 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4206 first_id = last_id = response = None
2be71994 4207 for page_num in itertools.count(1):
cd7c66cf 4208 videos = list(self._playlist_entries(playlist))
4209 if not videos:
4210 return
2be71994 4211 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4212 if start >= len(videos):
4213 return
4214 for video in videos[start:]:
4215 if video['id'] == first_id:
4216 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4217 return
4218 yield video
4219 first_id = first_id or videos[0]['id']
4220 last_id = videos[-1]['id']
79360d99 4221 watch_endpoint = try_get(
4222 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4223 headers = self.generate_api_headers(
4224 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4225 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4226 query = {
4227 'playlistId': playlist_id,
4228 'videoId': watch_endpoint.get('videoId') or last_id,
4229 'index': watch_endpoint.get('index') or len(videos),
4230 'params': watch_endpoint.get('params') or 'OAE%3D'
4231 }
4232 response = self._extract_response(
4233 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4234 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4235 check_get_keys='contents'
4236 )
cd7c66cf 4237 playlist = try_get(
79360d99 4238 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4239
ac56cf38 4240 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4241 title = playlist.get('title') or try_get(
4242 data, lambda x: x['titleText']['simpleText'], compat_str)
4243 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4244
4245 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4246 playlist_url = urljoin(url, try_get(
4247 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4248 compat_str))
4249 if playlist_url and playlist_url != url:
4250 return self.url_result(
4251 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4252 video_title=title)
cd7c66cf 4253
8bdd16b4 4254 return self.playlist_result(
ac56cf38 4255 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4256 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4257
47193e02 4258 def _extract_availability(self, data):
4259 """
4260 Gets the availability of a given playlist/tab.
4261 Note: Unless YouTube tells us explicitly, we do not assume it is public
4262 @param data: response
4263 """
4264 is_private = is_unlisted = None
4265 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4266 badge_labels = self._extract_badges(renderer)
4267
4268 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4269 privacy_dropdown_entries = try_get(
4270 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4271 for renderer_dict in privacy_dropdown_entries:
4272 is_selected = try_get(
4273 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4274 if not is_selected:
4275 continue
052e1350 4276 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4277 if label:
4278 badge_labels.add(label.lower())
4279 break
4280
4281 for badge_label in badge_labels:
4282 if badge_label == 'unlisted':
4283 is_unlisted = True
4284 elif badge_label == 'private':
4285 is_private = True
4286 elif badge_label == 'public':
4287 is_unlisted = is_private = False
4288 return self._availability(is_private, False, False, False, is_unlisted)
4289
4290 @staticmethod
4291 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4292 sidebar_renderer = try_get(
4293 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4294 for item in sidebar_renderer:
4295 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4296 if renderer:
4297 return renderer
4298
ac56cf38 4299 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4300 """
4301 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4302 """
5d342002 4303 browse_id = params = None
47193e02 4304 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4305 if not renderer:
4306 return
4307 menu_renderer = try_get(
4308 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4309 for menu_item in menu_renderer:
4310 if not isinstance(menu_item, dict):
358de58c 4311 continue
47193e02 4312 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4313 text = try_get(
4314 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4315 if not text or text.lower() != 'show unavailable videos':
4316 continue
4317 browse_endpoint = try_get(
4318 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4319 browse_id = browse_endpoint.get('browseId')
4320 params = browse_endpoint.get('params')
4321 break
5d342002 4322
11f9be09 4323 headers = self.generate_api_headers(
99e9e001 4324 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4325 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4326 query = {
4327 'params': params or 'wgYCCAA=',
4328 'browseId': browse_id or 'VL%s' % item_id
4329 }
4330 return self._extract_response(
4331 item_id=item_id, headers=headers, query=query,
fe93e2c4 4332 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4333 note='Downloading API JSON with unavailable videos')
358de58c 4334
ac56cf38 4335 def _extract_webpage(self, url, item_id, fatal=True):
a06916d9 4336 retries = self.get_param('extractor_retries', 3)
62bff2c1 4337 count = -1
ac56cf38 4338 webpage = data = last_error = None
14fdfea9 4339 while count < retries:
62bff2c1 4340 count += 1
14fdfea9 4341 # Sometimes youtube returns a webpage with incomplete ytInitialData
62bff2c1 4342 # See: https://github.com/yt-dlp/yt-dlp/issues/116
ac56cf38 4343 if last_error:
c705177d 4344 self.report_warning('%s. Retrying ...' % last_error)
ac56cf38 4345 try:
4346 webpage = self._download_webpage(
4347 url, item_id,
4348 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4349 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4350 except ExtractorError as e:
4351 if isinstance(e.cause, network_exceptions):
4352 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4353 last_error = error_to_compat_str(e.cause or e.msg)
4354 if count < retries:
4355 continue
4356 if fatal:
4357 raise
4358 self.report_warning(error_to_compat_str(e))
14fdfea9 4359 break
ac56cf38 4360 else:
4361 try:
4362 self._extract_and_report_alerts(data)
4363 except ExtractorError as e:
4364 if fatal:
4365 raise
4366 self.report_warning(error_to_compat_str(e))
4367 break
4368
7c219ea6 4369 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
ac56cf38 4370 break
4371
4372 last_error = 'Incomplete yt initial data received'
4373 if count >= retries:
4374 if fatal:
4375 raise ExtractorError(last_error)
4376 self.report_warning(last_error)
4377 break
4378
cd7c66cf 4379 return webpage, data
4380
ac56cf38 4381 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4382 data = None
4383 if 'webpage' not in self._configuration_arg('skip'):
4384 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4385 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4386 # Reject webpage data if redirected to home page without explicitly requesting
4387 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4388 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4389 if (url != 'https://www.youtube.com/feed/recommended'
4390 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4391 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4392 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4393 if fatal:
4394 raise ExtractorError(msg, expected=True)
4395 self.report_warning(msg, only_once=True)
ac56cf38 4396 if not data:
4397 if not ytcfg and self.is_authenticated:
4398 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4399 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4400 raise ExtractorError(
4401 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4402 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4403 expected=True)
4404 self.report_warning(msg, only_once=True)
4405 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4406 return data, ytcfg
4407
4408 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4409 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4410 resolve_response = self._extract_response(
4411 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4412 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4413 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4414 for ep_key, ep in endpoints.items():
4415 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4416 if params:
4417 return self._extract_response(
4418 item_id=item_id, query=params, ep=ep, headers=headers,
4419 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4420 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4421 err_note = 'Failed to resolve url (does the playlist exist?)'
4422 if fatal:
4423 raise ExtractorError(err_note, expected=True)
4424 self.report_warning(err_note, item_id)
4425
a6213a49 4426 _SEARCH_PARAMS = None
4427
af5c1c55 4428 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4429 data = {'query': query}
4430 if params is NO_DEFAULT:
4431 params = self._SEARCH_PARAMS
4432 if params:
4433 data['params'] = params
16aa9ea4 4434
4435 content_keys = (
4436 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4437 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4438 # ytmusic search
4439 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4440 ('continuationContents', ),
4441 )
4442 check_get_keys = tuple(set(keys[0] for keys in content_keys))
4443
a61fd4cf 4444 continuation_list = [None]
a6213a49 4445 for page_num in itertools.count(1):
a61fd4cf 4446 data.update(continuation_list[0] or {})
a6213a49 4447 search = self._extract_response(
4448 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
af5c1c55 4449 default_client=default_client, check_get_keys=check_get_keys)
16aa9ea4 4450 slr_contents = traverse_obj(search, *content_keys)
4451 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4452 if not continuation_list[0]:
a6213a49 4453 break
4454
4455
4456class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4457 IE_DESC = 'YouTube Tabs'
4458 _VALID_URL = r'''(?x:
4459 https?://
4460 (?:\w+\.)?
4461 (?:
4462 youtube(?:kids)?\.com|
4463 %(invidious)s
4464 )/
4465 (?:
4466 (?P<channel_type>channel|c|user|browse)/|
4467 (?P<not_channel>
4468 feed/|hashtag/|
4469 (?:playlist|watch)\?.*?\blist=
4470 )|
4471 (?!(?:%(reserved_names)s)\b) # Direct URLs
4472 )
4473 (?P<id>[^/?\#&]+)
4474 )''' % {
4475 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4476 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4477 }
4478 IE_NAME = 'youtube:tab'
4479
4480 _TESTS = [{
4481 'note': 'playlists, multipage',
4482 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4483 'playlist_mincount': 94,
4484 'info_dict': {
4485 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4486 'title': 'Igor Kleiner - Playlists',
a6213a49 4487 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4488 'uploader': 'Igor Kleiner',
a6213a49 4489 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4490 'channel': 'Igor Kleiner',
4491 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4492 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4493 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4494 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4495 'channel_follower_count': int
a6213a49 4496 },
4497 }, {
4498 'note': 'playlists, multipage, different order',
4499 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4500 'playlist_mincount': 94,
4501 'info_dict': {
4502 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4503 'title': 'Igor Kleiner - Playlists',
a6213a49 4504 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4505 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4506 'uploader': 'Igor Kleiner',
4507 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4508 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4509 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4510 'channel': 'Igor Kleiner',
4511 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4512 'channel_follower_count': int
a6213a49 4513 },
4514 }, {
4515 'note': 'playlists, series',
4516 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4517 'playlist_mincount': 5,
4518 'info_dict': {
4519 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4520 'title': '3Blue1Brown - Playlists',
4521 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4522 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4523 'uploader': '3Blue1Brown',
976ae3ea 4524 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4525 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4526 'channel': '3Blue1Brown',
4527 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4528 'tags': ['Mathematics'],
6c73052c 4529 'channel_follower_count': int
a6213a49 4530 },
4531 }, {
4532 'note': 'playlists, singlepage',
4533 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4534 'playlist_mincount': 4,
4535 'info_dict': {
4536 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4537 'title': 'ThirstForScience - Playlists',
4538 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4539 'uploader': 'ThirstForScience',
4540 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4541 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4542 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4543 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4544 'tags': 'count:13',
4545 'channel': 'ThirstForScience',
6c73052c 4546 'channel_follower_count': int
a6213a49 4547 }
4548 }, {
4549 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4550 'only_matching': True,
4551 }, {
4552 'note': 'basic, single video playlist',
4553 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4554 'info_dict': {
4555 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4556 'uploader': 'Sergey M.',
4557 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4558 'title': 'youtube-dl public playlist',
976ae3ea 4559 'description': '',
4560 'tags': [],
4561 'view_count': int,
4562 'modified_date': '20201130',
4563 'channel': 'Sergey M.',
4564 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4565 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4566 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4567 },
4568 'playlist_count': 1,
4569 }, {
4570 'note': 'empty playlist',
4571 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4572 'info_dict': {
4573 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4574 'uploader': 'Sergey M.',
4575 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4576 'title': 'youtube-dl empty playlist',
976ae3ea 4577 'tags': [],
4578 'channel': 'Sergey M.',
4579 'description': '',
4580 'modified_date': '20160902',
4581 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4582 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4583 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4584 },
4585 'playlist_count': 0,
4586 }, {
4587 'note': 'Home tab',
4588 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4589 'info_dict': {
4590 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4591 'title': 'lex will - Home',
4592 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4593 'uploader': 'lex will',
4594 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4595 'channel': 'lex will',
4596 'tags': ['bible', 'history', 'prophesy'],
4597 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4598 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4599 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4600 'channel_follower_count': int
a6213a49 4601 },
4602 'playlist_mincount': 2,
4603 }, {
4604 'note': 'Videos tab',
4605 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4606 'info_dict': {
4607 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4608 'title': 'lex will - Videos',
4609 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4610 'uploader': 'lex will',
4611 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4612 'tags': ['bible', 'history', 'prophesy'],
4613 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4614 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4615 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4616 'channel': 'lex will',
6c73052c 4617 'channel_follower_count': int
a6213a49 4618 },
4619 'playlist_mincount': 975,
4620 }, {
4621 'note': 'Videos tab, sorted by popular',
4622 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4623 'info_dict': {
4624 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4625 'title': 'lex will - Videos',
4626 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4627 'uploader': 'lex will',
4628 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4629 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4630 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4631 'channel': 'lex will',
4632 'tags': ['bible', 'history', 'prophesy'],
4633 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4634 'channel_follower_count': int
a6213a49 4635 },
4636 'playlist_mincount': 199,
4637 }, {
4638 'note': 'Playlists tab',
4639 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4640 'info_dict': {
4641 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4642 'title': 'lex will - Playlists',
4643 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4644 'uploader': 'lex will',
4645 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4646 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4647 'channel': 'lex will',
4648 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4649 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4650 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4651 'channel_follower_count': int
a6213a49 4652 },
4653 'playlist_mincount': 17,
4654 }, {
4655 'note': 'Community tab',
4656 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4657 'info_dict': {
4658 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4659 'title': 'lex will - Community',
4660 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4661 'uploader': 'lex will',
4662 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4663 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4664 'channel': 'lex will',
4665 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4666 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4667 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4668 'channel_follower_count': int
a6213a49 4669 },
4670 'playlist_mincount': 18,
4671 }, {
4672 'note': 'Channels tab',
4673 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4674 'info_dict': {
4675 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4676 'title': 'lex will - Channels',
4677 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4678 'uploader': 'lex will',
4679 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4680 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4681 'channel': 'lex will',
4682 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4683 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4684 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4685 'channel_follower_count': int
a6213a49 4686 },
4687 'playlist_mincount': 12,
4688 }, {
4689 'note': 'Search tab',
4690 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4691 'playlist_mincount': 40,
4692 'info_dict': {
4693 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4694 'title': '3Blue1Brown - Search - linear algebra',
4695 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4696 'uploader': '3Blue1Brown',
4697 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4698 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4699 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4700 'tags': ['Mathematics'],
4701 'channel': '3Blue1Brown',
4702 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4703 'channel_follower_count': int
a6213a49 4704 },
4705 }, {
4706 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4707 'only_matching': True,
4708 }, {
4709 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4710 'only_matching': True,
4711 }, {
4712 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4713 'only_matching': True,
4714 }, {
4715 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4716 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4717 'info_dict': {
4718 'title': '29C3: Not my department',
4719 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4720 'uploader': 'Christiaan008',
4721 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4722 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4723 'tags': [],
4724 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4725 'view_count': int,
4726 'modified_date': '20150605',
4727 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4728 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4729 'channel': 'Christiaan008',
a6213a49 4730 },
4731 'playlist_count': 96,
4732 }, {
4733 'note': 'Large playlist',
4734 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4735 'info_dict': {
4736 'title': 'Uploads from Cauchemar',
4737 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4738 'uploader': 'Cauchemar',
4739 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4740 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4741 'tags': [],
4742 'modified_date': r're:\d{8}',
4743 'channel': 'Cauchemar',
4744 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4745 'view_count': int,
4746 'description': '',
4747 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4748 },
4749 'playlist_mincount': 1123,
976ae3ea 4750 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4751 }, {
4752 'note': 'even larger playlist, 8832 videos',
4753 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4754 'only_matching': True,
4755 }, {
4756 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4757 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4758 'info_dict': {
4759 'title': 'Uploads from Interstellar Movie',
4760 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4761 'uploader': 'Interstellar Movie',
4762 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4763 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4764 'tags': [],
4765 'view_count': int,
4766 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4767 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4768 'channel': 'Interstellar Movie',
4769 'description': '',
4770 'modified_date': r're:\d{8}',
a6213a49 4771 },
4772 'playlist_mincount': 21,
4773 }, {
4774 'note': 'Playlist with "show unavailable videos" button',
4775 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4776 'info_dict': {
4777 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4778 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4779 'uploader': 'Phim Siêu Nhân Nhật Bản',
4780 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4781 'view_count': int,
4782 'channel': 'Phim Siêu Nhân Nhật Bản',
4783 'tags': [],
4784 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4785 'description': '',
4786 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4787 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4788 'modified_date': r're:\d{8}',
a6213a49 4789 },
4790 'playlist_mincount': 200,
976ae3ea 4791 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4792 }, {
4793 'note': 'Playlist with unavailable videos in page 7',
4794 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4795 'info_dict': {
4796 'title': 'Uploads from BlankTV',
4797 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4798 'uploader': 'BlankTV',
4799 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4800 'channel': 'BlankTV',
4801 'channel_url': 'https://www.youtube.com/c/blanktv',
4802 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4803 'view_count': int,
4804 'tags': [],
4805 'uploader_url': 'https://www.youtube.com/c/blanktv',
4806 'modified_date': r're:\d{8}',
4807 'description': '',
a6213a49 4808 },
4809 'playlist_mincount': 1000,
976ae3ea 4810 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4811 }, {
4812 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4813 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4814 'info_dict': {
4815 'title': 'Data Analysis with Dr Mike Pound',
4816 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4817 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4818 'uploader': 'Computerphile',
4819 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4820 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4821 'tags': [],
4822 'view_count': int,
4823 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4824 'channel_url': 'https://www.youtube.com/user/Computerphile',
4825 'channel': 'Computerphile',
a6213a49 4826 },
4827 'playlist_mincount': 11,
4828 }, {
4829 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4830 'only_matching': True,
4831 }, {
4832 'note': 'Playlist URL that does not actually serve a playlist',
4833 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4834 'info_dict': {
4835 'id': 'FqZTN594JQw',
4836 'ext': 'webm',
4837 'title': "Smiley's People 01 detective, Adventure Series, Action",
4838 'uploader': 'STREEM',
4839 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4840 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4841 'upload_date': '20150526',
4842 'license': 'Standard YouTube License',
4843 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4844 'categories': ['People & Blogs'],
4845 'tags': list,
4846 'view_count': int,
4847 'like_count': int,
a6213a49 4848 },
4849 'params': {
4850 'skip_download': True,
4851 },
4852 'skip': 'This video is not available.',
4853 'add_ie': [YoutubeIE.ie_key()],
4854 }, {
4855 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4856 'only_matching': True,
4857 }, {
4858 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4859 'only_matching': True,
4860 }, {
4861 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4862 'info_dict': {
6c73052c 4863 'id': 'GgL890LIznQ', # This will keep changing
a6213a49 4864 'ext': 'mp4',
976ae3ea 4865 'title': str,
a6213a49 4866 'uploader': 'Sky News',
4867 'uploader_id': 'skynews',
4868 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4869 'upload_date': r're:\d{8}',
976ae3ea 4870 'description': str,
a6213a49 4871 'categories': ['News & Politics'],
4872 'tags': list,
4873 'like_count': int,
6c73052c 4874 'release_timestamp': 1642502819,
976ae3ea 4875 'channel': 'Sky News',
4876 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4877 'age_limit': 0,
4878 'view_count': int,
6c73052c 4879 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 4880 'playable_in_embed': True,
6c73052c 4881 'release_date': '20220118',
976ae3ea 4882 'availability': 'public',
4883 'live_status': 'is_live',
4884 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 4885 'channel_follower_count': int
a6213a49 4886 },
4887 'params': {
4888 'skip_download': True,
4889 },
976ae3ea 4890 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 4891 }, {
4892 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4893 'info_dict': {
4894 'id': 'a48o2S1cPoo',
4895 'ext': 'mp4',
4896 'title': 'The Young Turks - Live Main Show',
4897 'uploader': 'The Young Turks',
4898 'uploader_id': 'TheYoungTurks',
4899 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4900 'upload_date': '20150715',
4901 'license': 'Standard YouTube License',
4902 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4903 'categories': ['News & Politics'],
4904 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4905 'like_count': int,
a6213a49 4906 },
4907 'params': {
4908 'skip_download': True,
4909 },
4910 'only_matching': True,
4911 }, {
4912 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4913 'only_matching': True,
4914 }, {
4915 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4916 'only_matching': True,
4917 }, {
4918 'note': 'A channel that is not live. Should raise error',
4919 'url': 'https://www.youtube.com/user/numberphile/live',
4920 'only_matching': True,
4921 }, {
4922 'url': 'https://www.youtube.com/feed/trending',
4923 'only_matching': True,
4924 }, {
4925 'url': 'https://www.youtube.com/feed/library',
4926 'only_matching': True,
4927 }, {
4928 'url': 'https://www.youtube.com/feed/history',
4929 'only_matching': True,
4930 }, {
4931 'url': 'https://www.youtube.com/feed/subscriptions',
4932 'only_matching': True,
4933 }, {
4934 'url': 'https://www.youtube.com/feed/watch_later',
4935 'only_matching': True,
4936 }, {
4937 'note': 'Recommended - redirects to home page.',
4938 'url': 'https://www.youtube.com/feed/recommended',
4939 'only_matching': True,
4940 }, {
4941 'note': 'inline playlist with not always working continuations',
4942 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4943 'only_matching': True,
4944 }, {
4945 'url': 'https://www.youtube.com/course',
4946 'only_matching': True,
4947 }, {
4948 'url': 'https://www.youtube.com/zsecurity',
4949 'only_matching': True,
4950 }, {
4951 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4952 'only_matching': True,
4953 }, {
4954 'url': 'https://www.youtube.com/TheYoungTurks/live',
4955 'only_matching': True,
4956 }, {
4957 'url': 'https://www.youtube.com/hashtag/cctv9',
4958 'info_dict': {
4959 'id': 'cctv9',
4960 'title': '#cctv9',
976ae3ea 4961 'tags': [],
a6213a49 4962 },
4963 'playlist_mincount': 350,
4964 }, {
4965 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4966 'only_matching': True,
4967 }, {
4968 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4969 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4970 'only_matching': True
4971 }, {
4972 'note': '/browse/ should redirect to /channel/',
4973 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4974 'only_matching': True
4975 }, {
4976 'note': 'VLPL, should redirect to playlist?list=PL...',
4977 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4978 'info_dict': {
4979 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4980 'uploader': 'NoCopyrightSounds',
4981 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4982 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4983 'title': 'NCS Releases',
976ae3ea 4984 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4985 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4986 'modified_date': r're:\d{8}',
4987 'view_count': int,
4988 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4989 'tags': [],
4990 'channel': 'NoCopyrightSounds',
a6213a49 4991 },
4992 'playlist_mincount': 166,
976ae3ea 4993 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4994 }, {
4995 'note': 'Topic, should redirect to playlist?list=UU...',
4996 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4997 'info_dict': {
4998 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4999 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5000 'title': 'Uploads from Royalty Free Music - Topic',
5001 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5002 'tags': [],
5003 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5004 'channel': 'Royalty Free Music - Topic',
5005 'view_count': int,
5006 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5007 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5008 'modified_date': r're:\d{8}',
5009 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5010 'description': '',
a6213a49 5011 },
5012 'expected_warnings': [
a6213a49 5013 'The URL does not have a videos tab',
976ae3ea 5014 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5015 ],
5016 'playlist_mincount': 101,
5017 }, {
5018 'note': 'Topic without a UU playlist',
5019 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5020 'info_dict': {
5021 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5022 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5023 'tags': [],
a6213a49 5024 },
5025 'expected_warnings': [
976ae3ea 5026 'the playlist redirect gave error',
a6213a49 5027 ],
5028 'playlist_mincount': 9,
5029 }, {
5030 'note': 'Youtube music Album',
5031 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5032 'info_dict': {
5033 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5034 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5035 'tags': [],
5036 'view_count': int,
5037 'description': '',
5038 'availability': 'unlisted',
5039 'modified_date': r're:\d{8}',
a6213a49 5040 },
5041 'playlist_count': 50,
5042 }, {
5043 'note': 'unlisted single video playlist',
5044 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5045 'info_dict': {
5046 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5047 'uploader': 'colethedj',
5048 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5049 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5050 'availability': 'unlisted',
5051 'tags': [],
5052 'modified_date': '20211208',
5053 'channel': 'colethedj',
5054 'view_count': int,
5055 'description': '',
5056 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5057 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5058 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5059 },
5060 'playlist_count': 1,
5061 }, {
5062 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5063 'url': 'https://www.youtube.com/feed/recommended',
5064 'info_dict': {
5065 'id': 'recommended',
5066 'title': 'recommended',
6c73052c 5067 'tags': [],
a6213a49 5068 },
5069 'playlist_mincount': 50,
5070 'params': {
5071 'skip_download': True,
5072 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5073 },
5074 }, {
5075 'note': 'API Fallback: /videos tab, sorted by oldest first',
5076 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5077 'info_dict': {
5078 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5079 'title': 'Cody\'sLab - Videos',
5080 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5081 'uploader': 'Cody\'sLab',
5082 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5083 'channel': 'Cody\'sLab',
5084 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5085 'tags': [],
5086 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5087 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5088 'channel_follower_count': int
a6213a49 5089 },
5090 'playlist_mincount': 650,
5091 'params': {
5092 'skip_download': True,
5093 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5094 },
5095 }, {
5096 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5097 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5098 'info_dict': {
5099 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5100 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5101 'title': 'Uploads from Royalty Free Music - Topic',
5102 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5103 'modified_date': r're:\d{8}',
5104 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5105 'description': '',
5106 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5107 'tags': [],
5108 'channel': 'Royalty Free Music - Topic',
5109 'view_count': int,
5110 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5111 },
5112 'expected_warnings': [
976ae3ea 5113 'does not have a videos tab',
5114 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5115 ],
5116 'playlist_mincount': 101,
5117 'params': {
5118 'skip_download': True,
5119 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5120 },
7c219ea6 5121 }, {
5122 'note': 'non-standard redirect to regional channel',
5123 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5124 'only_matching': True
a6213a49 5125 }]
5126
5127 @classmethod
5128 def suitable(cls, url):
5129 return False if YoutubeIE.suitable(url) else super(
5130 YoutubeTabIE, cls).suitable(url)
9297939e 5131
64f36541 5132 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5133
182bda88 5134 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5135 def _real_extract(self, url, smuggled_data):
cd7c66cf 5136 item_id = self._match_id(url)
5137 url = compat_urlparse.urlunparse(
5138 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5139 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5140
fe03a6cd 5141 def get_mobj(url):
37e57a9f 5142 mobj = self._URL_RE.match(url).groupdict()
07cce701 5143 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5144 return mobj
5145
37e57a9f 5146 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5147 # Youtube returns incomplete data if tabname is not lower case
5148 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5149 if is_channel:
5150 if smuggled_data.get('is_music_url'):
37e57a9f 5151 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5152 item_id = item_id[2:]
37e57a9f 5153 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5154 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5155 mdata = self._extract_tab_endpoint(
37e57a9f 5156 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5157 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5158 get_all=False, expected_type=compat_str)
ac56cf38 5159 if not murl:
37e57a9f 5160 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5161 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5162 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5163 pre = f'https://www.youtube.com/channel/{item_id}'
5164
64f36541 5165 original_tab_name = tab
fe03a6cd 5166 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5167 # Home URLs should redirect to /videos/
37e57a9f 5168 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5169 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5170 tab = '/videos'
5171
5172 url = ''.join((pre, tab, post))
5173 mobj = get_mobj(url)
cd7c66cf 5174
5175 # Handle both video/playlist URLs
201c1459 5176 qs = parse_qs(url)
37e57a9f 5177 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
cd7c66cf 5178
fe03a6cd 5179 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5180 if not playlist_id:
fe03a6cd 5181 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5182 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5183 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5184 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5185 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5186 mobj = get_mobj(url)
cd7c66cf 5187
5188 if video_id and playlist_id:
a06916d9 5189 if self.get_param('noplaylist'):
37e57a9f 5190 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5191 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5192 ie=YoutubeIE.ie_key(), video_id=video_id)
5193 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5194
ac56cf38 5195 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5196
7c219ea6 5197 # YouTube may provide a non-standard redirect to the regional channel
5198 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5199 redirect_url = traverse_obj(
5200 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5201 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5202 redirect_url = ''.join((
5203 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5204 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5205 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5206
37e57a9f 5207 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5208 if tabs:
5209 selected_tab = self._extract_selected_tab(tabs)
64f36541 5210 selected_tab_name = selected_tab.get('title', '').lower()
5211 if selected_tab_name == 'home':
5212 selected_tab_name = 'featured'
5213 requested_tab_name = mobj['tab'][1:]
09f1580e 5214 if 'no-youtube-channel-redirect' not in compat_opts:
64f36541 5215 if requested_tab_name == 'live':
09f1580e 5216 # Live tab should have redirected to the video
5217 raise ExtractorError('The channel is not currently live', expected=True)
64f36541 5218 if requested_tab_name not in ('', selected_tab_name):
5219 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5220 if not original_tab_name:
5221 if item_id[:2] == 'UC':
5222 # Topic channels don't have /videos. Use the equivalent playlist instead
5223 pl_id = f'UU{item_id[2:]}'
5224 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5225 try:
5226 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5227 except ExtractorError:
5228 redirect_warning += ' and the playlist redirect gave error'
5229 else:
5230 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5231 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5232 if selected_tab_name and selected_tab_name != requested_tab_name:
5233 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5234 else:
5235 raise ExtractorError(redirect_warning, expected=True)
18db7548 5236
37e57a9f 5237 if redirect_warning:
64f36541 5238 self.to_screen(redirect_warning)
37e57a9f 5239 self.write_debug(f'Final URL: {url}')
18db7548 5240
358de58c 5241 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5242 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5243 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5244 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5245 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5246 if tabs:
ac56cf38 5247 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5248
37e57a9f 5249 playlist = traverse_obj(
5250 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5251 if playlist:
ac56cf38 5252 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5253
37e57a9f 5254 video_id = traverse_obj(
5255 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5256 if video_id:
09f1580e 5257 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5258 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5259 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5260 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5261
8bdd16b4 5262 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5263
c5e8d7af 5264
8bdd16b4 5265class YoutubePlaylistIE(InfoExtractor):
96565c7e 5266 IE_DESC = 'YouTube playlists'
8bdd16b4 5267 _VALID_URL = r'''(?x)(?:
5268 (?:https?://)?
5269 (?:\w+\.)?
5270 (?:
5271 (?:
5272 youtube(?:kids)?\.com|
d9190e44 5273 %(invidious)s
8bdd16b4 5274 )
5275 /.*?\?.*?\blist=
5276 )?
5277 (?P<id>%(playlist_id)s)
d9190e44
RH
5278 )''' % {
5279 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5280 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5281 }
8bdd16b4 5282 IE_NAME = 'youtube:playlist'
cdc628a4 5283 _TESTS = [{
8bdd16b4 5284 'note': 'issue #673',
5285 'url': 'PLBB231211A4F62143',
cdc628a4 5286 'info_dict': {
8bdd16b4 5287 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5288 'id': 'PLBB231211A4F62143',
976ae3ea 5289 'uploader': 'Wickman',
8bdd16b4 5290 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5291 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5292 'view_count': int,
5293 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5294 'modified_date': r're:\d{8}',
5295 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5296 'channel': 'Wickman',
5297 'tags': [],
5298 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5299 },
5300 'playlist_mincount': 29,
5301 }, {
5302 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5303 'info_dict': {
5304 'title': 'YDL_safe_search',
5305 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5306 },
5307 'playlist_count': 2,
5308 'skip': 'This playlist is private',
9558dcec 5309 }, {
8bdd16b4 5310 'note': 'embedded',
5311 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5312 'playlist_count': 4,
9558dcec 5313 'info_dict': {
8bdd16b4 5314 'title': 'JODA15',
5315 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5316 'uploader': 'milan',
5317 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5318 'description': '',
5319 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5320 'tags': [],
5321 'modified_date': '20140919',
5322 'view_count': int,
5323 'channel': 'milan',
5324 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5325 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5326 },
5327 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5328 }, {
8bdd16b4 5329 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
11f9be09 5330 'playlist_mincount': 654,
8bdd16b4 5331 'info_dict': {
5332 'title': '2018 Chinese New Singles (11/6 updated)',
5333 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5334 'uploader': 'LBK',
5335 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5336 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5337 'channel': 'LBK',
5338 'view_count': int,
5339 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5340 'tags': [],
5341 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5342 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5343 'modified_date': r're:\d{8}',
5344 },
5345 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5346 }, {
29f7c58a 5347 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5348 'only_matching': True,
5349 }, {
5350 # music album playlist
5351 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5352 'only_matching': True,
5353 }]
5354
5355 @classmethod
5356 def suitable(cls, url):
201c1459 5357 if YoutubeTabIE.suitable(url):
5358 return False
49a57e70 5359 from ..utils import parse_qs
201c1459 5360 qs = parse_qs(url)
5361 if qs.get('v', [None])[0]:
5362 return False
5363 return super(YoutubePlaylistIE, cls).suitable(url)
29f7c58a 5364
5365 def _real_extract(self, url):
5366 playlist_id = self._match_id(url)
46953e7e 5367 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5368 url = update_url_query(
5369 'https://www.youtube.com/playlist',
5370 parse_qs(url) or {'list': playlist_id})
5371 if is_music_url:
5372 url = smuggle_url(url, {'is_music_url': True})
5373 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5374
5375
5376class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5377 IE_DESC = 'youtu.be'
29f7c58a 5378 _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}
5379 _TESTS = [{
8bdd16b4 5380 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5381 'info_dict': {
5382 'id': 'yeWKywCrFtk',
5383 'ext': 'mp4',
5384 'title': 'Small Scale Baler and Braiding Rugs',
5385 'uploader': 'Backus-Page House Museum',
5386 'uploader_id': 'backuspagemuseum',
5387 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5388 'upload_date': '20161008',
5389 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5390 'categories': ['Nonprofits & Activism'],
5391 'tags': list,
5392 'like_count': int,
976ae3ea 5393 'age_limit': 0,
5394 'playable_in_embed': True,
5395 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5396 'channel': 'Backus-Page House Museum',
5397 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5398 'live_status': 'not_live',
5399 'view_count': int,
5400 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5401 'availability': 'public',
5402 'duration': 59,
8bdd16b4 5403 },
5404 'params': {
5405 'noplaylist': True,
5406 'skip_download': True,
5407 },
39e7107d 5408 }, {
8bdd16b4 5409 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5410 'only_matching': True,
cdc628a4
PH
5411 }]
5412
8bdd16b4 5413 def _real_extract(self, url):
5ad28e7f 5414 mobj = self._match_valid_url(url)
29f7c58a 5415 video_id = mobj.group('id')
5416 playlist_id = mobj.group('playlist_id')
8bdd16b4 5417 return self.url_result(
29f7c58a 5418 update_url_query('https://www.youtube.com/watch', {
5419 'v': video_id,
5420 'list': playlist_id,
5421 'feature': 'youtu.be',
5422 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5423
5424
b6ce9bb0 5425class YoutubeLivestreamEmbedIE(InfoExtractor):
5426 IE_DESC = 'YouTube livestream embeds'
5427 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5428 _TESTS = [{
5429 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5430 'only_matching': True,
5431 }]
5432
5433 def _real_extract(self, url):
5434 channel_id = self._match_id(url)
5435 return self.url_result(
5436 f'https://www.youtube.com/channel/{channel_id}/live',
5437 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5438
5439
8bdd16b4 5440class YoutubeYtUserIE(InfoExtractor):
96565c7e 5441 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5442 IE_NAME = 'youtube:user'
8bdd16b4 5443 _VALID_URL = r'ytuser:(?P<id>.+)'
5444 _TESTS = [{
5445 'url': 'ytuser:phihag',
5446 'only_matching': True,
5447 }]
5448
5449 def _real_extract(self, url):
5450 user_id = self._match_id(url)
5451 return self.url_result(
c586f9e8 5452 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5453 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5454
b05654f0 5455
3d3dddc9 5456class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5457 IE_NAME = 'youtube:favorites'
96565c7e 5458 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5459 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5460 _LOGIN_REQUIRED = True
5461 _TESTS = [{
5462 'url': ':ytfav',
5463 'only_matching': True,
5464 }, {
5465 'url': ':ytfavorites',
5466 'only_matching': True,
5467 }]
5468
5469 def _real_extract(self, url):
5470 return self.url_result(
5471 'https://www.youtube.com/playlist?list=LL',
5472 ie=YoutubeTabIE.ie_key())
5473
5474
a6213a49 5475class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5476 IE_DESC = 'YouTube search'
78caa52a 5477 IE_NAME = 'youtube:search'
b05654f0 5478 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5479 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5480 _TESTS = [{
5481 'url': 'ytsearch5:youtube-dl test video',
5482 'playlist_count': 5,
5483 'info_dict': {
5484 'id': 'youtube-dl test video',
5485 'title': 'youtube-dl test video',
5486 }
5487 }]
b05654f0 5488
a61fd4cf 5489
5f7cb91a 5490class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5491 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5492 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5493 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5494 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5495 _TESTS = [{
5496 'url': 'ytsearchdate5:youtube-dl test video',
5497 'playlist_count': 5,
5498 'info_dict': {
5499 'id': 'youtube-dl test video',
5500 'title': 'youtube-dl test video',
5501 }
5502 }]
75dff0ee 5503
c9ae7b95 5504
a6213a49 5505class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5506 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5507 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5508 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5509 _TESTS = [{
5510 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5511 'playlist_mincount': 5,
5512 'info_dict': {
11f9be09 5513 'id': 'youtube-dl test video',
3462ffa8 5514 'title': 'youtube-dl test video',
5515 }
a61fd4cf 5516 }, {
5517 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5518 'playlist_mincount': 5,
5519 'info_dict': {
5520 'id': 'python',
5521 'title': 'python',
5522 }
5523
3462ffa8 5524 }, {
5525 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5526 'only_matching': True,
5527 }]
5528
5529 def _real_extract(self, url):
4dfbf869 5530 qs = parse_qs(url)
386e1dd9 5531 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5532 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5533
5534
16aa9ea4 5535class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
455a15e2 5536 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
16aa9ea4 5537 IE_NAME = 'youtube:music:search_url'
5538 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5539 _TESTS = [{
5540 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5541 'playlist_count': 16,
5542 'info_dict': {
5543 'id': 'royalty free music',
5544 'title': 'royalty free music',
5545 }
5546 }, {
5547 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5548 'playlist_mincount': 30,
5549 'info_dict': {
5550 'id': 'royalty free music - songs',
5551 'title': 'royalty free music - songs',
5552 },
5553 'params': {'extract_flat': 'in_playlist'}
5554 }, {
5555 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5556 'playlist_mincount': 30,
5557 'info_dict': {
5558 'id': 'royalty free music - community playlists',
5559 'title': 'royalty free music - community playlists',
5560 },
5561 'params': {'extract_flat': 'in_playlist'}
5562 }]
5563
5564 _SECTIONS = {
5565 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5566 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5567 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5568 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5569 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5570 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5571 }
5572
5573 def _real_extract(self, url):
5574 qs = parse_qs(url)
5575 query = (qs.get('search_query') or qs.get('q'))[0]
5576 params = qs.get('sp', (None,))[0]
5577 if params:
5578 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5579 else:
5580 section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
5581 params = self._SECTIONS.get(section)
5582 if not params:
5583 section = None
5584 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5585 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5586
5587
182bda88 5588class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5589 """
25f14e9f 5590 Base class for feed extractors
3d3dddc9 5591 Subclasses must define the _FEED_NAME property.
d7ae0639 5592 """
b2e8bc1b 5593 _LOGIN_REQUIRED = True
ef2f3c7f 5594 _TESTS = []
d7ae0639
JMF
5595
5596 @property
5597 def IE_NAME(self):
78caa52a 5598 return 'youtube:%s' % self._FEED_NAME
04cc9617 5599
3853309f 5600 def _real_extract(self, url):
3d3dddc9 5601 return self.url_result(
182bda88 5602 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5603
5604
ef2f3c7f 5605class YoutubeWatchLaterIE(InfoExtractor):
5606 IE_NAME = 'youtube:watchlater'
96565c7e 5607 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5608 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5609 _TESTS = [{
8bdd16b4 5610 'url': ':ytwatchlater',
bc7a9cd8
S
5611 'only_matching': True,
5612 }]
25f14e9f
S
5613
5614 def _real_extract(self, url):
ef2f3c7f 5615 return self.url_result(
5616 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5617
5618
25f14e9f 5619class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5620 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5621 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5622 _FEED_NAME = 'recommended'
45db527f 5623 _LOGIN_REQUIRED = False
3d3dddc9 5624 _TESTS = [{
5625 'url': ':ytrec',
5626 'only_matching': True,
5627 }, {
5628 'url': ':ytrecommended',
5629 'only_matching': True,
5630 }, {
5631 'url': 'https://youtube.com',
5632 'only_matching': True,
5633 }]
1ed5b5c9 5634
1ed5b5c9 5635
25f14e9f 5636class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5637 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5638 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5639 _FEED_NAME = 'subscriptions'
3d3dddc9 5640 _TESTS = [{
5641 'url': ':ytsubs',
5642 'only_matching': True,
5643 }, {
5644 'url': ':ytsubscriptions',
5645 'only_matching': True,
5646 }]
1ed5b5c9 5647
1ed5b5c9 5648
25f14e9f 5649class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5650 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5651 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5652 _FEED_NAME = 'history'
3d3dddc9 5653 _TESTS = [{
5654 'url': ':ythistory',
5655 'only_matching': True,
5656 }]
1ed5b5c9
JMF
5657
5658
15870e90
PH
5659class YoutubeTruncatedURLIE(InfoExtractor):
5660 IE_NAME = 'youtube:truncated_url'
5661 IE_DESC = False # Do not list
975d35db 5662 _VALID_URL = r'''(?x)
b95aab84
PH
5663 (?:https?://)?
5664 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5665 (?:watch\?(?:
c4808c60 5666 feature=[a-z_]+|
b95aab84
PH
5667 annotation_id=annotation_[^&]+|
5668 x-yt-cl=[0-9]+|
c1708b89 5669 hl=[^&]*|
287be8c6 5670 t=[0-9]+
b95aab84
PH
5671 )?
5672 |
5673 attribution_link\?a=[^&]+
5674 )
5675 $
975d35db 5676 '''
15870e90 5677
c4808c60 5678 _TESTS = [{
2d3d2997 5679 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5680 'only_matching': True,
dc2fc736 5681 }, {
2d3d2997 5682 'url': 'https://www.youtube.com/watch?',
dc2fc736 5683 'only_matching': True,
b95aab84
PH
5684 }, {
5685 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5686 'only_matching': True,
5687 }, {
5688 'url': 'https://www.youtube.com/watch?feature=foo',
5689 'only_matching': True,
c1708b89
PH
5690 }, {
5691 'url': 'https://www.youtube.com/watch?hl=en-GB',
5692 'only_matching': True,
287be8c6
PH
5693 }, {
5694 'url': 'https://www.youtube.com/watch?t=2372',
5695 'only_matching': True,
c4808c60
PH
5696 }]
5697
15870e90
PH
5698 def _real_extract(self, url):
5699 raise ExtractorError(
78caa52a
PH
5700 'Did you forget to quote the URL? Remember that & is a meta '
5701 'character in most shells, so you want to put the URL in quotes, '
3867038a 5702 'like youtube-dl '
2d3d2997 5703 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 5704 ' or simply youtube-dl BaW_jenozKc .',
15870e90 5705 expected=True)
772fd5cc
PH
5706
5707
3cd786db 5708class YoutubeClipIE(InfoExtractor):
5709 IE_NAME = 'youtube:clip'
5710 IE_DESC = False # Do not list
5711 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5712
5713 def _real_extract(self, url):
5714 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5715 return self.url_result(url, 'Generic')
5716
5717
772fd5cc
PH
5718class YoutubeTruncatedIDIE(InfoExtractor):
5719 IE_NAME = 'youtube:truncated_id'
5720 IE_DESC = False # Do not list
b95aab84 5721 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
5722
5723 _TESTS = [{
5724 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5725 'only_matching': True,
5726 }]
5727
5728 def _real_extract(self, url):
5729 video_id = self._match_id(url)
5730 raise ExtractorError(
5731 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
5732 expected=True)