]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[build] Exclude devscripts from installs
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
6e634cbe 1import base64
d92f5d5a 2import calendar
109dd3b2 3import copy
fe93e2c4 4import datetime
a5c56234 5import hashlib
0ca96d48 6import itertools
c5e8d7af 7import json
720c3099 8import math
c4417ddb 9import os.path
d77ab8e2 10import random
c5e8d7af 11import re
46383212 12import sys
f8271158 13import threading
8a784c74 14import time
e0df6211 15import traceback
14f25df2 16import urllib.error
ac668111 17import urllib.parse
c5e8d7af 18
b05654f0 19from .common import InfoExtractor, SearchInfoExtractor
14f25df2 20from ..compat import functools
545cc85d 21from ..jsinterp import JSInterpreter
4bb4a188 22from ..utils import (
f8271158 23 NO_DEFAULT,
24 ExtractorError,
693f0600 25 UserNotLive,
720c3099 26 bug_reports_message,
82d02080 27 classproperty,
c5e8d7af 28 clean_html,
d92f5d5a 29 datetime_from_str,
11f9be09 30 dict_get,
2d30521a 31 float_or_none,
11f9be09 32 format_field,
ff91cf74 33 get_first,
dd27fd17 34 int_or_none,
641ad5d8 35 is_html,
34921b43 36 join_nonempty,
48416bc4 37 js_to_json,
94278f72 38 mimetype2ext,
9c0d7f49 39 network_exceptions,
11f9be09 40 orderedSet,
6310acf5 41 parse_codecs,
49bd8c66 42 parse_count,
7c80519c 43 parse_duration,
7ea65411 44 parse_iso8601,
4dfbf869 45 parse_qs,
dca3ff4a 46 qualities,
3995d37d 47 remove_start,
cf7e015f 48 smuggle_url,
dbdaaa23 49 str_or_none,
c93d53f5 50 str_to_int,
f3aa3c3f 51 strftime_or_none,
7c365c21 52 traverse_obj,
556dbe7f 53 try_get,
c5e8d7af
PH
54 unescapeHTML,
55 unified_strdate,
f0d785d3 56 unified_timestamp,
cf7e015f 57 unsmuggle_url,
8bdd16b4 58 update_url_query,
21c340b8 59 url_or_none,
fe93e2c4 60 urljoin,
7c365c21 61 variadic,
c5e8d7af
PH
62)
63
962ffcf8 64# any clients starting with _ cannot be explicitly requested by the user
000c15a4 65INNERTUBE_CLIENTS = {
66 'web': {
67 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
68 'INNERTUBE_CONTEXT': {
69 'client': {
70 'clientName': 'WEB',
a0c830f4 71 'clientVersion': '2.20220801.00.00',
000c15a4 72 }
73 },
74 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
75 },
76 'web_embedded': {
77 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
78 'INNERTUBE_CONTEXT': {
79 'client': {
80 'clientName': 'WEB_EMBEDDED_PLAYER',
a0c830f4 81 'clientVersion': '1.20220731.00.00',
000c15a4 82 },
83 },
84 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
85 },
86 'web_music': {
87 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
88 'INNERTUBE_HOST': 'music.youtube.com',
89 'INNERTUBE_CONTEXT': {
90 'client': {
91 'clientName': 'WEB_REMIX',
a0c830f4 92 'clientVersion': '1.20220727.01.00',
000c15a4 93 }
94 },
95 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
96 },
e7e94f2a 97 'web_creator': {
18c7683d 98 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
99 'INNERTUBE_CONTEXT': {
100 'client': {
101 'clientName': 'WEB_CREATOR',
a0c830f4 102 'clientVersion': '1.20220726.00.00',
e7e94f2a
D
103 }
104 },
105 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
106 },
000c15a4 107 'android': {
18c7683d 108 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 109 'INNERTUBE_CONTEXT': {
110 'client': {
111 'clientName': 'ANDROID',
c7dcf0b3 112 'clientVersion': '17.29.34',
113 'androidSdkVersion': 30
000c15a4 114 }
115 },
116 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 117 'REQUIRE_JS_PLAYER': False
000c15a4 118 },
119 'android_embedded': {
18c7683d 120 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 121 'INNERTUBE_CONTEXT': {
122 'client': {
123 'clientName': 'ANDROID_EMBEDDED_PLAYER',
c7dcf0b3 124 'clientVersion': '17.29.34',
125 'androidSdkVersion': 30
000c15a4 126 },
127 },
b6de707d 128 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
129 'REQUIRE_JS_PLAYER': False
000c15a4 130 },
131 'android_music': {
18c7683d 132 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 133 'INNERTUBE_CONTEXT': {
134 'client': {
135 'clientName': 'ANDROID_MUSIC',
a0c830f4 136 'clientVersion': '5.16.51',
c7dcf0b3 137 'androidSdkVersion': 30
000c15a4 138 }
139 },
140 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 141 'REQUIRE_JS_PLAYER': False
000c15a4 142 },
e7e94f2a 143 'android_creator': {
18c7683d 144 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
145 'INNERTUBE_CONTEXT': {
146 'client': {
147 'clientName': 'ANDROID_CREATOR',
a0c830f4 148 'clientVersion': '22.28.100',
c7dcf0b3 149 'androidSdkVersion': 30
e7e94f2a
D
150 },
151 },
b6de707d 152 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
153 'REQUIRE_JS_PLAYER': False
e7e94f2a 154 },
18c7683d 155 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
156 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 157 'ios': {
18c7683d 158 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 159 'INNERTUBE_CONTEXT': {
160 'client': {
161 'clientName': 'IOS',
a0c830f4 162 'clientVersion': '17.30.1',
18c7683d 163 'deviceModel': 'iPhone14,3',
000c15a4 164 }
165 },
b6de707d 166 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
167 'REQUIRE_JS_PLAYER': False
000c15a4 168 },
169 'ios_embedded': {
000c15a4 170 'INNERTUBE_CONTEXT': {
171 'client': {
172 'clientName': 'IOS_MESSAGES_EXTENSION',
a0c830f4 173 'clientVersion': '17.30.1',
18c7683d 174 'deviceModel': 'iPhone14,3',
000c15a4 175 },
176 },
b6de707d 177 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
178 'REQUIRE_JS_PLAYER': False
000c15a4 179 },
180 'ios_music': {
18c7683d 181 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 182 'INNERTUBE_CONTEXT': {
183 'client': {
184 'clientName': 'IOS_MUSIC',
a0c830f4 185 'clientVersion': '5.18',
000c15a4 186 },
187 },
b6de707d 188 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
189 'REQUIRE_JS_PLAYER': False
000c15a4 190 },
e7e94f2a
D
191 'ios_creator': {
192 'INNERTUBE_CONTEXT': {
193 'client': {
194 'clientName': 'IOS_CREATOR',
a0c830f4 195 'clientVersion': '22.29.101',
e7e94f2a
D
196 },
197 },
b6de707d 198 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
199 'REQUIRE_JS_PLAYER': False
e7e94f2a 200 },
3619f78d 201 # mweb has 'ultralow' formats
202 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 203 'mweb': {
18c7683d 204 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 205 'INNERTUBE_CONTEXT': {
206 'client': {
207 'clientName': 'MWEB',
a0c830f4 208 'clientVersion': '2.20220801.00.00',
000c15a4 209 }
210 },
211 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
212 },
213 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
214 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
215 'tv_embedded': {
216 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
217 'INNERTUBE_CONTEXT': {
218 'client': {
219 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
220 'clientVersion': '2.0',
221 },
222 },
223 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
224 },
000c15a4 225}
226
227
e7870111
D
228def _split_innertube_client(client_name):
229 variant, *base = client_name.rsplit('.', 1)
230 if base:
231 return variant, base[0], variant
232 base, *variant = client_name.split('_', 1)
233 return client_name, base, variant[0] if variant else None
234
235
000c15a4 236def build_innertube_clients():
2e4cacd0 237 THIRD_PARTY = {
e7870111 238 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 239 }
e7870111 240 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 241 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 242
243 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 244 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 245 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 246 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 247 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 248
e7870111 249 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 250 ytcfg['priority'] = 10 * priority(base_client)
251
e48b3875 252 if not variant:
e7870111
D
253 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
254 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
255 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
256 embedscreen['priority'] -= 3
257 elif variant == 'embedded':
e48b3875 258 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 259 ytcfg['priority'] -= 2
e48b3875 260 else:
000c15a4 261 ytcfg['priority'] -= 3
262
263
264build_innertube_clients()
265
266
de7f3446 267class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 268 """Provide base functions for Youtube extractors"""
e00eb564 269
3462ffa8 270 _RESERVED_NAMES = (
3cd786db 271 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 272 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 273 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 274 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 275
3619f78d 276 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
277
52efa4b3 278 # _NETRC_MACHINE = 'youtube'
3619f78d 279
b2e8bc1b
JMF
280 # If True it will raise an error if no login info is provided
281 _LOGIN_REQUIRED = False
282
d9190e44
RH
283 _INVIDIOUS_SITES = (
284 # invidious-redirect websites
285 r'(?:www\.)?redirect\.invidious\.io',
286 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 287 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
288 r'(?:www\.)?invidious\.pussthecat\.org',
289 r'(?:www\.)?invidious\.zee\.li',
290 r'(?:www\.)?invidious\.ethibox\.fr',
291 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
292 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
293 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
294 # youtube-dl invidious instances list
295 r'(?:(?:www|no)\.)?invidiou\.sh',
296 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
297 r'(?:www\.)?invidious\.kabi\.tk',
298 r'(?:www\.)?invidious\.mastodon\.host',
299 r'(?:www\.)?invidious\.zapashcanon\.fr',
300 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
301 r'(?:www\.)?invidious\.tinfoil-hat\.net',
302 r'(?:www\.)?invidious\.himiko\.cloud',
303 r'(?:www\.)?invidious\.reallyancient\.tech',
304 r'(?:www\.)?invidious\.tube',
305 r'(?:www\.)?invidiou\.site',
306 r'(?:www\.)?invidious\.site',
307 r'(?:www\.)?invidious\.xyz',
308 r'(?:www\.)?invidious\.nixnet\.xyz',
309 r'(?:www\.)?invidious\.048596\.xyz',
310 r'(?:www\.)?invidious\.drycat\.fr',
311 r'(?:www\.)?inv\.skyn3t\.in',
312 r'(?:www\.)?tube\.poal\.co',
313 r'(?:www\.)?tube\.connect\.cafe',
314 r'(?:www\.)?vid\.wxzm\.sx',
315 r'(?:www\.)?vid\.mint\.lgbt',
316 r'(?:www\.)?vid\.puffyan\.us',
317 r'(?:www\.)?yewtu\.be',
318 r'(?:www\.)?yt\.elukerio\.org',
319 r'(?:www\.)?yt\.lelux\.fi',
320 r'(?:www\.)?invidious\.ggc-project\.de',
321 r'(?:www\.)?yt\.maisputain\.ovh',
322 r'(?:www\.)?ytprivate\.com',
323 r'(?:www\.)?invidious\.13ad\.de',
324 r'(?:www\.)?invidious\.toot\.koeln',
325 r'(?:www\.)?invidious\.fdn\.fr',
326 r'(?:www\.)?watch\.nettohikari\.com',
327 r'(?:www\.)?invidious\.namazso\.eu',
328 r'(?:www\.)?invidious\.silkky\.cloud',
329 r'(?:www\.)?invidious\.exonip\.de',
330 r'(?:www\.)?invidious\.riverside\.rocks',
331 r'(?:www\.)?invidious\.blamefran\.net',
332 r'(?:www\.)?invidious\.moomoo\.de',
333 r'(?:www\.)?ytb\.trom\.tf',
334 r'(?:www\.)?yt\.cyberhost\.uk',
335 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
336 r'(?:www\.)?qklhadlycap4cnod\.onion',
337 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
338 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
339 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
340 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
341 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
342 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
343 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
344 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
345 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
346 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
347 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
348 r'(?:www\.)?piped\.kavin\.rocks',
349 r'(?:www\.)?piped\.silkky\.cloud',
350 r'(?:www\.)?piped\.tokhmi\.xyz',
351 r'(?:www\.)?piped\.moomoo\.me',
352 r'(?:www\.)?il\.ax',
353 r'(?:www\.)?piped\.syncpundit\.com',
354 r'(?:www\.)?piped\.mha\.fi',
355 r'(?:www\.)?piped\.mint\.lgbt',
356 r'(?:www\.)?piped\.privacy\.com\.de',
d9190e44
RH
357 )
358
cce889b9 359 def _initialize_consent(self):
360 cookies = self._get_cookies('https://www.youtube.com/')
361 if cookies.get('__Secure-3PSID'):
362 return
363 consent_id = None
364 consent = cookies.get('CONSENT')
365 if consent:
366 if 'YES' in consent.value:
367 return
368 consent_id = self._search_regex(
369 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
370 if not consent_id:
371 consent_id = random.randint(100, 999)
372 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 373
f3aa3c3f 374 def _initialize_pref(self):
375 cookies = self._get_cookies('https://www.youtube.com/')
376 pref_cookie = cookies.get('PREF')
377 pref = {}
378 if pref_cookie:
379 try:
14f25df2 380 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 381 except ValueError:
382 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 383 pref.update({'hl': 'en', 'tz': 'UTC'})
14f25df2 384 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 385
b2e8bc1b 386 def _real_initialize(self):
f3aa3c3f 387 self._initialize_pref()
cce889b9 388 self._initialize_consent()
a25bca9f 389 self._check_login_required()
390
391 def _check_login_required(self):
24146491 392 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 393 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 394
b7c47b74 395 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
396 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 397
000c15a4 398 def _get_default_ytcfg(self, client='web'):
399 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 400
000c15a4 401 def _get_innertube_host(self, client='web'):
402 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 403
000c15a4 404 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 405 # try_get but with fallback to default ytcfg client values when present
406 _func = lambda y: try_get(y, getter, expected_type)
407 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
408
000c15a4 409 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 410 return self._ytcfg_get_safe(
411 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 412 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 413
000c15a4 414 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 415 return self._ytcfg_get_safe(
416 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 417 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 418
2ae778b8 419 def _select_api_hostname(self, req_api_hostname, default_client=None):
420 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
421 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
422
000c15a4 423 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 424 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 425
000c15a4 426 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 427 context = get_first(
428 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 429 # Enforce language and tz for extraction
430 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
431 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 432 return context
433
cf87314d 434 _SAPISID = None
435
109dd3b2 436 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 437 time_now = round(time.time())
cf87314d 438 if self._SAPISID is None:
439 yt_cookies = self._get_cookies('https://www.youtube.com')
440 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
441 # See: https://github.com/yt-dlp/yt-dlp/issues/393
442 sapisid_cookie = dict_get(
443 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
444 if sapisid_cookie and sapisid_cookie.value:
445 self._SAPISID = sapisid_cookie.value
446 self.write_debug('Extracted SAPISID cookie')
447 # SAPISID cookie is required if not already present
448 if not yt_cookies.get('SAPISID'):
449 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
450 self._set_cookie(
451 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
452 else:
453 self._SAPISID = False
454 if not self._SAPISID:
455 return None
1974e99f 456 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
457 sapisidhash = hashlib.sha1(
86e5f3ed 458 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 459 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
460
461 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 462 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 463 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 464
109dd3b2 465 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 466 data.update(query)
11f9be09 467 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 468 real_headers.update({'content-type': 'application/json'})
469 if headers:
470 real_headers.update(headers)
2ae778b8 471 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
472 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 473 return self._download_json(
2ae778b8 474 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 475 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 476 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 477 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 478
65141660 479 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
480 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 481
99e9e001 482 @staticmethod
483 def _extract_session_index(*data):
484 """
485 Index of current account in account list.
486 See: https://github.com/yt-dlp/yt-dlp/pull/519
487 """
488 for ytcfg in data:
489 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
490 if session_index is not None:
491 return session_index
492
493 # Deprecated?
494 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 495 if ytcfg:
14f25df2 496 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
497 if token:
498 return token
99e9e001 499 if webpage:
500 return self._search_regex(
501 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
502 'identity token', default=None, fatal=False)
a1c5d2ca
M
503
504 @staticmethod
fe93e2c4 505 def _extract_account_syncid(*args):
8ea3f7b9 506 """
507 Extract syncId required to download private playlists of secondary channels
fe93e2c4 508 @params response and/or ytcfg
8ea3f7b9 509 """
fe93e2c4 510 for data in args:
511 # ytcfg includes channel_syncid if on secondary channel
14f25df2 512 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 513 if delegated_sid:
514 return delegated_sid
515 sync_ids = (try_get(
516 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 517 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 518 if len(sync_ids) >= 2 and sync_ids[1]:
519 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
520 # and just "user_syncid||" for primary channel. We only want the channel_syncid
521 return sync_ids[0]
a1c5d2ca 522
ac56cf38 523 @staticmethod
524 def _extract_visitor_data(*args):
525 """
526 Extracts visitorData from an API response or ytcfg
527 Appears to be used to track session state
528 """
9222c381 529 return get_first(
6c73052c 530 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 531 expected_type=str)
ac56cf38 532
2762dbb1 533 @functools.cached_property
99e9e001 534 def is_authenticated(self):
535 return bool(self._generate_sapisidhash_header())
536
11f9be09 537 def extract_ytcfg(self, video_id, webpage):
8c54a305 538 if not webpage:
539 return {}
29f7c58a 540 return self._parse_json(
541 self._search_regex(
542 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 543 default='{}'), video_id, fatal=False) or {}
544
11f9be09 545 def generate_api_headers(
99e9e001 546 self, *, ytcfg=None, account_syncid=None, session_index=None,
547 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
548
2ae778b8 549 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 550 headers = {
14f25df2 551 'X-YouTube-Client-Name': str(
11f9be09 552 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
553 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 554 'Origin': origin,
555 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
556 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 557 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 558 }
559 if session_index is None:
314ee305 560 session_index = self._extract_session_index(ytcfg)
561 if account_syncid or session_index is not None:
562 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 563
109dd3b2 564 auth = self._generate_sapisidhash_header(origin)
f4f751af 565 if auth is not None:
566 headers['Authorization'] = auth
109dd3b2 567 headers['X-Origin'] = origin
99e9e001 568 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 569
a25bca9f 570 def _download_ytcfg(self, client, video_id):
571 url = {
572 'web': 'https://www.youtube.com',
573 'web_music': 'https://music.youtube.com',
574 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
575 }.get(client)
576 if not url:
577 return {}
578 webpage = self._download_webpage(
579 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
580 return self.extract_ytcfg(video_id, webpage) or {}
581
2d6659b9 582 @staticmethod
583 def _build_api_continuation_query(continuation, ctp=None):
584 query = {
585 'continuation': continuation
586 }
587 # TODO: Inconsistency with clickTrackingParams.
588 # Currently we have a fixed ctp contained within context (from ytcfg)
589 # and a ctp in root query for continuation.
590 if ctp:
591 query['clickTracking'] = {'clickTrackingParams': ctp}
592 return query
593
2d6659b9 594 @classmethod
595 def _extract_next_continuation_data(cls, renderer):
596 next_continuation = try_get(
597 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
598 lambda x: x['continuation']['reloadContinuationData']), dict)
599 if not next_continuation:
600 return
601 continuation = next_continuation.get('continuation')
602 if not continuation:
603 return
604 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 605 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 606
607 @classmethod
608 def _extract_continuation_ep_data(cls, continuation_ep: dict):
609 if isinstance(continuation_ep, dict):
610 continuation = try_get(
14f25df2 611 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 612 if not continuation:
613 return
614 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 615 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 616
617 @classmethod
618 def _extract_continuation(cls, renderer):
619 next_continuation = cls._extract_next_continuation_data(renderer)
620 if next_continuation:
621 return next_continuation
fe93e2c4 622
2d6659b9 623 contents = []
624 for key in ('contents', 'items'):
625 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 626
2d6659b9 627 for content in contents:
628 if not isinstance(content, dict):
629 continue
630 continuation_ep = try_get(
631 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
632 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
633 dict)
634 continuation = cls._extract_continuation_ep_data(continuation_ep)
635 if continuation:
636 return continuation
637
fe93e2c4 638 @classmethod
639 def _extract_alerts(cls, data):
109dd3b2 640 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
641 if not isinstance(alert_dict, dict):
642 continue
643 for alert in alert_dict.values():
644 alert_type = alert.get('type')
645 if not alert_type:
646 continue
052e1350 647 message = cls._get_text(alert, 'text')
109dd3b2 648 if message:
649 yield alert_type, message
650
c0ac49bc 651 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 652 errors = []
653 warnings = []
654 for alert_type, alert_message in alerts:
641ad5d8 655 if alert_type.lower() == 'error' and fatal:
109dd3b2 656 errors.append([alert_type, alert_message])
657 else:
658 warnings.append([alert_type, alert_message])
659
660 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 661 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 662 if errors:
663 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
664
665 def _extract_and_report_alerts(self, data, *args, **kwargs):
666 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
667
47193e02 668 def _extract_badges(self, renderer: dict):
669 badges = set()
670 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
14f25df2 671 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], str)
47193e02 672 if label:
673 badges.add(label.lower())
674 return badges
675
676 @staticmethod
052e1350 677 def _get_text(data, *path_list, max_runs=None):
678 for path in path_list or [None]:
679 if path is None:
680 obj = [data]
681 else:
682 obj = traverse_obj(data, path, default=[])
683 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
684 obj = [obj]
685 for item in obj:
14f25df2 686 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 687 if text:
688 return text
689 runs = try_get(item, lambda x: x['runs'], list) or []
690 if not runs and isinstance(item, list):
691 runs = item
692
693 runs = runs[:min(len(runs), max_runs or len(runs))]
694 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
695 if text:
696 return text
47193e02 697
f0d785d3 698 def _get_count(self, data, *path_list):
699 count_text = self._get_text(data, *path_list) or ''
700 count = parse_count(count_text)
701 if count is None:
702 count = str_to_int(
703 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
704 return count
705
a709d873 706 @staticmethod
707 def _extract_thumbnails(data, *path_list):
708 """
709 Extract thumbnails from thumbnails dict
710 @param path_list: path list to level that contains 'thumbnails' key
711 """
712 thumbnails = []
713 for path in path_list or [()]:
714 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
715 thumbnail_url = url_or_none(thumbnail.get('url'))
716 if not thumbnail_url:
717 continue
718 # Sometimes youtube gives a wrong thumbnail URL. See:
719 # https://github.com/yt-dlp/yt-dlp/issues/233
720 # https://github.com/ytdl-org/youtube-dl/issues/28023
721 if 'maxresdefault' in thumbnail_url:
722 thumbnail_url = thumbnail_url.split('?')[0]
723 thumbnails.append({
724 'url': thumbnail_url,
725 'height': int_or_none(thumbnail.get('height')),
726 'width': int_or_none(thumbnail.get('width')),
727 })
728 return thumbnails
729
f3aa3c3f 730 @staticmethod
731 def extract_relative_time(relative_time_text):
732 """
733 Extracts a relative time from string and converts to dt object
f0d785d3 734 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 735 """
f0d785d3 736 mobj = re.search(r'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>microsecond|second|minute|hour|day|week|month|year)s?\s*ago', relative_time_text)
f3aa3c3f 737 if mobj:
f0d785d3 738 start = mobj.group('start')
739 if start:
740 return datetime_from_str(start)
f3aa3c3f 741 try:
f0d785d3 742 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 743 except ValueError:
744 return None
745
746 def _extract_time_text(self, renderer, *path_list):
a25bca9f 747 """@returns (timestamp, time_text)"""
f3aa3c3f 748 text = self._get_text(renderer, *path_list) or ''
749 dt = self.extract_relative_time(text)
750 timestamp = None
751 if isinstance(dt, datetime.datetime):
752 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 753
754 if timestamp is None:
755 timestamp = (
756 unified_timestamp(text) or unified_timestamp(
757 self._search_regex(
17322130 758 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 759 text.lower(), 'time text', default=None)))
f0d785d3 760
f3aa3c3f 761 if text and timestamp is None:
17322130 762 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
f3aa3c3f 763 return timestamp, text
764
109dd3b2 765 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
766 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 767 default_client='web'):
be5c1ae8 768 for retry in self.RetryManager():
109dd3b2 769 try:
770 response = self._call_api(
771 ep=ep, fatal=True, headers=headers,
be5c1ae8 772 video_id=item_id, query=query, note=note,
109dd3b2 773 context=self._extract_context(ytcfg, default_client),
774 api_key=self._extract_api_key(ytcfg, default_client),
be5c1ae8 775 api_hostname=api_hostname, default_client=default_client)
109dd3b2 776 except ExtractorError as e:
be5c1ae8 777 if not isinstance(e.cause, network_exceptions):
778 return self._error_or_warning(e, fatal=fatal)
779 elif not isinstance(e.cause, urllib.error.HTTPError):
780 retry.error = e
781 continue
109dd3b2 782
be5c1ae8 783 first_bytes = e.cause.read(512)
784 if not is_html(first_bytes):
785 yt_error = try_get(
786 self._parse_json(
787 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
788 lambda x: x['error']['message'], str)
789 if yt_error:
790 self._report_alerts([('ERROR', yt_error)], fatal=False)
791 # Downloading page may result in intermittent 5xx HTTP error
792 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
793 # We also want to catch all other network exceptions since errors in later pages can be troublesome
794 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
795 if e.cause.code not in (403, 429):
796 retry.error = e
797 continue
798 return self._error_or_warning(e, fatal=fatal)
799
800 try:
801 self._extract_and_report_alerts(response, only_once=True)
802 except ExtractorError as e:
803 # YouTube servers may return errors we want to retry on in a 200 OK response
804 # See: https://github.com/yt-dlp/yt-dlp/issues/839
805 if 'unknown error' in e.msg.lower():
806 retry.error = e
807 continue
808 return self._error_or_warning(e, fatal=fatal)
809 # Youtube sometimes sends incomplete data
810 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
811 if not traverse_obj(response, *variadic(check_get_keys)):
812 retry.error = ExtractorError('Incomplete data received')
813 continue
814
815 return response
109dd3b2 816
9297939e 817 @staticmethod
818 def is_music_url(url):
819 return re.match(r'https?://music\.youtube\.com/', url) is not None
820
30a074c2 821 def _extract_video(self, renderer):
822 video_id = renderer.get('videoId')
052e1350 823 title = self._get_text(renderer, 'title')
824 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 825 duration = parse_duration(self._get_text(
826 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 827 if duration is None:
828 duration = parse_duration(self._search_regex(
829 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
830 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
831 video_id, default=None, group='duration'))
832
f0d785d3 833 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 834
052e1350 835 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 836 channel_id = traverse_obj(
a44ca5a4 837 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
838 expected_type=str, get_all=False)
f3aa3c3f 839 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
840 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
841 overlay_style = traverse_obj(
a44ca5a4 842 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
843 get_all=False, expected_type=str)
f3aa3c3f 844 badges = self._extract_badges(renderer)
a709d873 845 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
fd2ad7cb 846 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 847 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
848 expected_type=str)) or ''
fd2ad7cb 849 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 850 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 851 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 852
30a074c2 853 return {
39ed931e 854 '_type': 'url',
30a074c2 855 'ie_key': YoutubeIE.ie_key(),
856 'id': video_id,
fd2ad7cb 857 'url': url,
30a074c2 858 'title': title,
859 'description': description,
860 'duration': duration,
861 'view_count': view_count,
862 'uploader': uploader,
f3aa3c3f 863 'channel_id': channel_id,
a709d873 864 'thumbnails': thumbnails,
a44ca5a4 865 'upload_date': (strftime_or_none(timestamp, '%Y%m%d')
866 if self._configuration_arg('approximate_date', ie_key='youtubetab')
867 else None),
f3aa3c3f 868 'live_status': ('is_upcoming' if scheduled_timestamp is not None
869 else 'was_live' if 'streamed' in time_text.lower()
870 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
871 else None),
872 'release_timestamp': scheduled_timestamp,
873 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 874 }
875
0c148415 876
360e1ca5 877class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 878 IE_DESC = 'YouTube'
cb7dfeea 879 _VALID_URL = r"""(?x)^
c5e8d7af 880 (
edb53e2d 881 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 882 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
883 (?:www\.)?deturl\.com/www\.youtube\.com|
884 (?:www\.)?pwnyoutube\.com|
885 (?:www\.)?hooktube\.com|
886 (?:www\.)?yourepeat\.com|
887 tube\.majestyc\.net|
888 %(invidious)s|
889 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
890 (?:.*?\#/)? # handle anchor (#/) redirect urls
891 (?: # the various things that can precede the ID:
b6ce9bb0 892 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 893 |(?: # or the v= param in all its forms
f7000f3a 894 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 895 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 896 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
897 v=
898 )
f4b05232 899 ))
cbaed4bb
S
900 |(?:
901 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
902 vid\.plus| # or vid.plus/xxxx
903 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 904 %(invidious)s
cbaed4bb 905 )/
edb53e2d 906 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 907 )
c5e8d7af 908 )? # all until now is optional -> you can pass the naked ID
201c1459 909 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 910 (?(1).+)? # if we found the ID, everything can follow
9297939e 911 (?:\#|$)""" % {
d9190e44 912 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 913 }
bfd973ec 914 _EMBED_REGEX = [r'''(?x)
915 (?:
916 <iframe[^>]+?src=|
917 data-video-url=|
918 <embed[^>]+?src=|
919 embedSWF\(?:\s*|
920 <object[^>]+data=|
921 new\s+SWFObject\(
922 )
923 (["\'])
924 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
925 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
926 \1''']
e40c758c 927 _PLAYER_INFO_RE = (
cc2db878 928 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
929 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
545cc85d 930 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 931 )
2c62dc26 932 _formats = {
c2d3cb4c 933 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
934 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
935 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
936 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
937 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
938 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
939 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
940 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 941 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 942 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
943 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
944 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
945 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
946 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
947 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 948 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 949 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
950 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 951
952
953 # 3D videos
c2d3cb4c 954 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
955 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
956 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
957 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 958 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
959 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
960 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 961
96fb5605 962 # Apple HTTP Live Streaming
11f12195 963 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 964 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
965 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
966 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
967 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
968 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 969 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
970 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
971
972 # DASH mp4 video
d23028a8
S
973 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
974 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
975 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
976 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
977 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 978 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
979 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
980 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
981 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
982 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
983 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
984 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 985
f6f1fc92 986 # Dash mp4 audio
d23028a8
S
987 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
988 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
989 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
990 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
991 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
992 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
993 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
994
995 # Dash webm
d23028a8
S
996 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
997 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
998 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
999 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1000 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1001 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1002 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1003 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1004 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1005 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1006 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1007 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1008 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1009 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1010 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1011 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1012 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1013 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1014 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1015 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1016 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1017 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1018
1019 # Dash webm audio
d23028a8
S
1020 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1021 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1022
0857baad 1023 # Dash webm audio with opus inside
d23028a8
S
1024 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1025 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1026 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1027
ce6b9a2d
PH
1028 # RTMP (unnamed)
1029 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1030
1031 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1032 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1033 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1034 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1035 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1036 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1037 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1038 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1039 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1040 }
29f7c58a 1041 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1042
fd5c4aab
S
1043 _GEO_BYPASS = False
1044
78caa52a 1045 IE_NAME = 'youtube'
2eb88d95
PH
1046 _TESTS = [
1047 {
2d3d2997 1048 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1049 'info_dict': {
1050 'id': 'BaW_jenozKc',
1051 'ext': 'mp4',
3867038a 1052 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1053 'uploader': 'Philipp Hagemeister',
1054 'uploader_id': 'phihag',
ec85ded8 1055 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1056 'channel': 'Philipp Hagemeister',
dd4c4492
S
1057 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1058 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1059 'upload_date': '20121002',
ff9f925b 1060 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1061 'categories': ['Science & Technology'],
3867038a 1062 'tags': ['youtube-dl'],
556dbe7f 1063 'duration': 10,
dbdaaa23 1064 'view_count': int,
3e7c1224 1065 'like_count': int,
ff9f925b 1066 'availability': 'public',
1067 'playable_in_embed': True,
1068 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1069 'live_status': 'not_live',
1070 'age_limit': 0,
7c80519c 1071 'start_time': 1,
297a564b 1072 'end_time': 9,
12a1b225 1073 'comment_count': int,
6c73052c 1074 'channel_follower_count': int
2eb88d95 1075 }
0e853ca4 1076 },
fccd3771 1077 {
4bc3a23e
PH
1078 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1079 'note': 'Embed-only video (#1746)',
1080 'info_dict': {
1081 'id': 'yZIXLfi8CZQ',
1082 'ext': 'mp4',
1083 'upload_date': '20120608',
1084 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1085 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1086 'uploader': 'SET India',
94bfcd23 1087 'uploader_id': 'setindia',
ec85ded8 1088 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1089 'age_limit': 18,
545cc85d 1090 },
1091 'skip': 'Private video',
fccd3771 1092 },
11b56058 1093 {
8bdd16b4 1094 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1095 'note': 'Use the first video ID in the URL',
1096 'info_dict': {
1097 'id': 'BaW_jenozKc',
1098 'ext': 'mp4',
3867038a 1099 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1100 'uploader': 'Philipp Hagemeister',
1101 'uploader_id': 'phihag',
ec85ded8 1102 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1103 'channel': 'Philipp Hagemeister',
1104 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1105 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1106 'upload_date': '20121002',
976ae3ea 1107 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1108 'categories': ['Science & Technology'],
3867038a 1109 'tags': ['youtube-dl'],
556dbe7f 1110 'duration': 10,
dbdaaa23 1111 'view_count': int,
11b56058 1112 'like_count': int,
976ae3ea 1113 'availability': 'public',
1114 'playable_in_embed': True,
1115 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1116 'live_status': 'not_live',
1117 'age_limit': 0,
12a1b225 1118 'comment_count': int,
6c73052c 1119 'channel_follower_count': int
34a7de29
S
1120 },
1121 'params': {
1122 'skip_download': True,
1123 },
11b56058 1124 },
dd27fd17 1125 {
2d3d2997 1126 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1127 'note': '256k DASH audio (format 141) via DASH manifest',
1128 'info_dict': {
1129 'id': 'a9LDPn-MO4I',
1130 'ext': 'm4a',
1131 'upload_date': '20121002',
1132 'uploader_id': '8KVIDEO',
ec85ded8 1133 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1134 'description': '',
1135 'uploader': '8KVIDEO',
1136 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1137 },
4bc3a23e
PH
1138 'params': {
1139 'youtube_include_dash_manifest': True,
1140 'format': '141',
4919603f 1141 },
de3c7fe0 1142 'skip': 'format 141 not served anymore',
dd27fd17 1143 },
8bdd16b4 1144 # DASH manifest with encrypted signature
1145 {
1146 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1147 'info_dict': {
1148 'id': 'IB3lcPjvWLA',
1149 'ext': 'm4a',
1150 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1151 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1152 'duration': 244,
1153 'uploader': 'AfrojackVEVO',
1154 'uploader_id': 'AfrojackVEVO',
1155 'upload_date': '20131011',
cc2db878 1156 'abr': 129.495,
976ae3ea 1157 'like_count': int,
1158 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1159 'playable_in_embed': True,
1160 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1161 'view_count': int,
1162 'track': 'The Spark',
1163 'live_status': 'not_live',
1164 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1165 'channel': 'Afrojack',
1166 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1167 'tags': 'count:19',
1168 'availability': 'public',
1169 'categories': ['Music'],
1170 'age_limit': 0,
1171 'alt_title': 'The Spark',
6c73052c 1172 'channel_follower_count': int
8bdd16b4 1173 },
1174 'params': {
1175 'youtube_include_dash_manifest': True,
1176 'format': '141/bestaudio[ext=m4a]',
1177 },
1178 },
65c2fde2 1179 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1180 {
65c2fde2 1181 'note': 'Embed allowed age-gate video',
2d3d2997 1182 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1183 'info_dict': {
1184 'id': 'HtVdAasjOgU',
1185 'ext': 'mp4',
1186 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1187 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1188 'duration': 142,
c522adb1
JMF
1189 'uploader': 'The Witcher',
1190 'uploader_id': 'WitcherGame',
ec85ded8 1191 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1192 'upload_date': '20140605',
34952f09 1193 'age_limit': 18,
976ae3ea 1194 'categories': ['Gaming'],
1195 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1196 'availability': 'needs_auth',
1197 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1198 'like_count': int,
1199 'channel': 'The Witcher',
1200 'live_status': 'not_live',
1201 'tags': 'count:17',
1202 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1203 'playable_in_embed': True,
1204 'view_count': int,
6c73052c 1205 'channel_follower_count': int
c522adb1
JMF
1206 },
1207 },
65c2fde2 1208 {
1209 'note': 'Age-gate video with embed allowed in public site',
1210 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1211 'info_dict': {
1212 'id': 'HsUATh_Nc2U',
1213 'ext': 'mp4',
1214 'title': 'Godzilla 2 (Official Video)',
1215 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1216 'upload_date': '20200408',
1217 'uploader_id': 'FlyingKitty900',
1218 'uploader': 'FlyingKitty',
1219 'age_limit': 18,
976ae3ea 1220 'availability': 'needs_auth',
1221 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1222 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1223 'channel': 'FlyingKitty',
1224 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1225 'view_count': int,
1226 'categories': ['Entertainment'],
1227 'live_status': 'not_live',
1228 'tags': ['Flyingkitty', 'godzilla 2'],
1229 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1230 'like_count': int,
1231 'duration': 177,
1232 'playable_in_embed': True,
6c73052c 1233 'channel_follower_count': int
65c2fde2 1234 },
1235 },
1236 {
1237 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1238 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1239 'info_dict': {
1240 'id': 'Tq92D6wQ1mg',
1241 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1242 'ext': 'mp4',
17322130 1243 'upload_date': '20191228',
65c2fde2 1244 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1245 'uploader': 'Projekt Melody',
1246 'description': 'md5:17eccca93a786d51bc67646756894066',
1247 'age_limit': 18,
976ae3ea 1248 'like_count': int,
1249 'availability': 'needs_auth',
1250 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1251 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1252 'view_count': int,
1253 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1254 'channel': 'Projekt Melody',
1255 'live_status': 'not_live',
1256 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1257 'playable_in_embed': True,
1258 'categories': ['Entertainment'],
1259 'duration': 106,
1260 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1261 'comment_count': int,
6c73052c 1262 'channel_follower_count': int
65c2fde2 1263 },
1264 },
1265 {
1266 'note': 'Non-Agegated non-embeddable video',
1267 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1268 'info_dict': {
1269 'id': 'MeJVWBSsPAY',
1270 'ext': 'mp4',
1271 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1272 'uploader': 'Herr Lurik',
1273 'uploader_id': 'st3in234',
1274 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1275 'upload_date': '20130730',
976ae3ea 1276 'track': 'Such mich find mich',
1277 'age_limit': 0,
1278 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1279 'like_count': int,
1280 'playable_in_embed': False,
1281 'creator': 'OOMPH!',
1282 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1283 'view_count': int,
1284 'alt_title': 'Such mich find mich',
1285 'duration': 210,
1286 'channel': 'Herr Lurik',
1287 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1288 'categories': ['Music'],
1289 'availability': 'public',
1290 'uploader_url': 'http://www.youtube.com/user/st3in234',
1291 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1292 'live_status': 'not_live',
1293 'artist': 'OOMPH!',
6c73052c 1294 'channel_follower_count': int
65c2fde2 1295 },
1296 },
1297 {
1298 'note': 'Non-bypassable age-gated video',
1299 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1300 'only_matching': True,
1301 },
8bdd16b4 1302 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1303 # YouTube Red ad is not captured for creator
1304 {
1305 'url': '__2ABJjxzNo',
1306 'info_dict': {
1307 'id': '__2ABJjxzNo',
1308 'ext': 'mp4',
1309 'duration': 266,
1310 'upload_date': '20100430',
1311 'uploader_id': 'deadmau5',
1312 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1313 'creator': 'deadmau5',
1314 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1315 'uploader': 'deadmau5',
1316 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1317 'alt_title': 'Some Chords',
976ae3ea 1318 'availability': 'public',
1319 'tags': 'count:14',
1320 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1321 'view_count': int,
1322 'live_status': 'not_live',
1323 'channel': 'deadmau5',
1324 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1325 'like_count': int,
1326 'track': 'Some Chords',
1327 'artist': 'deadmau5',
1328 'playable_in_embed': True,
1329 'age_limit': 0,
1330 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1331 'categories': ['Music'],
1332 'album': 'Some Chords',
6c73052c 1333 'channel_follower_count': int
8bdd16b4 1334 },
1335 'expected_warnings': [
1336 'DASH manifest missing',
1337 ]
1338 },
067aa17e 1339 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1340 {
1341 'url': 'lqQg6PlCWgI',
1342 'info_dict': {
1343 'id': 'lqQg6PlCWgI',
1344 'ext': 'mp4',
556dbe7f 1345 'duration': 6085,
90227264 1346 'upload_date': '20150827',
cbe2bd91 1347 'uploader_id': 'olympic',
ec85ded8 1348 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
12a1b225 1349 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
11f9be09 1350 'uploader': 'Olympics',
cbe2bd91 1351 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1352 'like_count': int,
1353 'release_timestamp': 1343767800,
1354 'playable_in_embed': True,
1355 'categories': ['Sports'],
1356 'release_date': '20120731',
1357 'channel': 'Olympics',
1358 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1359 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1360 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1361 'age_limit': 0,
1362 'availability': 'public',
1363 'live_status': 'was_live',
1364 'view_count': int,
1365 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1366 'channel_follower_count': int
cbe2bd91
PH
1367 },
1368 'params': {
1369 'skip_download': 'requires avconv',
e52a40ab 1370 }
cbe2bd91 1371 },
6271f1ca
PH
1372 # Non-square pixels
1373 {
1374 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1375 'info_dict': {
1376 'id': '_b-2C3KPAM0',
1377 'ext': 'mp4',
1378 'stretched_ratio': 16 / 9.,
556dbe7f 1379 'duration': 85,
6271f1ca
PH
1380 'upload_date': '20110310',
1381 'uploader_id': 'AllenMeow',
ec85ded8 1382 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1383 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
eb6793ba 1384 'uploader': '孫ᄋᄅ',
6271f1ca 1385 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1386 'playable_in_embed': True,
1387 'channel': '孫ᄋᄅ',
1388 'age_limit': 0,
1389 'tags': 'count:11',
1390 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1391 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1392 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1393 'view_count': int,
1394 'categories': ['People & Blogs'],
1395 'like_count': int,
1396 'live_status': 'not_live',
1397 'availability': 'unlisted',
12a1b225 1398 'comment_count': int,
6c73052c 1399 'channel_follower_count': int
6271f1ca 1400 },
06b491eb
S
1401 },
1402 # url_encoded_fmt_stream_map is empty string
1403 {
1404 'url': 'qEJwOuvDf7I',
1405 'info_dict': {
1406 'id': 'qEJwOuvDf7I',
f57b7835 1407 'ext': 'webm',
06b491eb
S
1408 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1409 'description': '',
1410 'upload_date': '20150404',
1411 'uploader_id': 'spbelect',
1412 'uploader': 'Наблюдатели Петербурга',
1413 },
1414 'params': {
1415 'skip_download': 'requires avconv',
e323cf3f
S
1416 },
1417 'skip': 'This live event has ended.',
06b491eb 1418 },
067aa17e 1419 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1420 {
1421 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1422 'info_dict': {
1423 'id': 'FIl7x6_3R5Y',
eb6793ba 1424 'ext': 'webm',
da77d856
S
1425 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1426 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1427 'duration': 220,
da77d856
S
1428 'upload_date': '20150625',
1429 'uploader_id': 'dorappi2000',
ec85ded8 1430 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1431 'uploader': 'dorappi2000',
eb6793ba 1432 'formats': 'mincount:31',
da77d856 1433 },
eb6793ba 1434 'skip': 'not actual anymore',
2ee8f5d8 1435 },
8a1a26ce
YCH
1436 # DASH manifest with segment_list
1437 {
1438 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1439 'md5': '8ce563a1d667b599d21064e982ab9e31',
1440 'info_dict': {
1441 'id': 'CsmdDsKjzN8',
1442 'ext': 'mp4',
17ee98e1 1443 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1444 'uploader': 'Airtek',
1445 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1446 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1447 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1448 },
1449 'params': {
1450 'youtube_include_dash_manifest': True,
1451 'format': '135', # bestvideo
be49068d
S
1452 },
1453 'skip': 'This live event has ended.',
2ee8f5d8 1454 },
cf7e015f
S
1455 {
1456 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1457 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1458 'info_dict': {
545cc85d 1459 'id': 'jvGDaLqkpTg',
1460 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1461 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1462 },
1463 'playlist': [{
1464 'info_dict': {
545cc85d 1465 'id': 'jvGDaLqkpTg',
cf7e015f 1466 'ext': 'mp4',
545cc85d 1467 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1468 'description': 'md5:e03b909557865076822aa169218d6a5d',
1469 'duration': 10643,
1470 'upload_date': '20161111',
1471 'uploader': 'Team PGP',
1472 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1473 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1474 },
1475 }, {
1476 'info_dict': {
545cc85d 1477 'id': '3AKt1R1aDnw',
cf7e015f 1478 'ext': 'mp4',
545cc85d 1479 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1480 'description': 'md5:e03b909557865076822aa169218d6a5d',
1481 'duration': 10991,
1482 'upload_date': '20161111',
1483 'uploader': 'Team PGP',
1484 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1485 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1486 },
1487 }, {
1488 'info_dict': {
545cc85d 1489 'id': 'RtAMM00gpVc',
cf7e015f 1490 'ext': 'mp4',
545cc85d 1491 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1492 'description': 'md5:e03b909557865076822aa169218d6a5d',
1493 'duration': 10995,
1494 'upload_date': '20161111',
1495 'uploader': 'Team PGP',
1496 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1497 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1498 },
1499 }, {
1500 'info_dict': {
545cc85d 1501 'id': '6N2fdlP3C5U',
cf7e015f 1502 'ext': 'mp4',
545cc85d 1503 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1504 'description': 'md5:e03b909557865076822aa169218d6a5d',
1505 'duration': 10990,
1506 'upload_date': '20161111',
1507 'uploader': 'Team PGP',
1508 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1509 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1510 },
1511 }],
1512 'params': {
1513 'skip_download': True,
1514 },
65c2fde2 1515 'skip': 'Not multifeed anymore',
cbaed4bb 1516 },
f9f49d87 1517 {
067aa17e 1518 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1519 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1520 'info_dict': {
1521 'id': 'gVfLd0zydlo',
1522 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1523 },
1524 'playlist_count': 2,
be49068d 1525 'skip': 'Not multifeed anymore',
f9f49d87 1526 },
cbaed4bb 1527 {
2d3d2997 1528 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1529 'only_matching': True,
0e49d9a6 1530 },
6d4fc66b 1531 {
2d3d2997 1532 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1533 'only_matching': True,
1534 },
0e49d9a6 1535 {
067aa17e 1536 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1537 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1538 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1539 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1540 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1541 'info_dict': {
1542 'id': 'lsguqyKfVQg',
1543 'ext': 'mp4',
1544 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1545 'alt_title': 'Dark Walk',
0e49d9a6 1546 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1547 'duration': 133,
0e49d9a6
LL
1548 'upload_date': '20151119',
1549 'uploader_id': 'IronSoulElf',
ec85ded8 1550 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1551 'uploader': 'IronSoulElf',
11f9be09 1552 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1553 'track': 'Dark Walk',
1554 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1555 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1556 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1557 'categories': ['Film & Animation'],
1558 'view_count': int,
1559 'live_status': 'not_live',
1560 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1561 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1562 'tags': 'count:13',
1563 'availability': 'public',
1564 'channel': 'IronSoulElf',
1565 'playable_in_embed': True,
1566 'like_count': int,
1567 'age_limit': 0,
6c73052c 1568 'channel_follower_count': int
0e49d9a6
LL
1569 },
1570 'params': {
1571 'skip_download': True,
1572 },
1573 },
61f92af1 1574 {
067aa17e 1575 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1576 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1577 'only_matching': True,
1578 },
313dfc45
LL
1579 {
1580 # Video with yt:stretch=17:0
1581 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1582 'info_dict': {
1583 'id': 'Q39EVAstoRM',
1584 'ext': 'mp4',
1585 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1586 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1587 'upload_date': '20151107',
1588 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1589 'uploader': 'CH GAMER DROID',
1590 },
1591 'params': {
1592 'skip_download': True,
1593 },
be49068d 1594 'skip': 'This video does not exist.',
313dfc45 1595 },
201c1459 1596 {
1597 # Video with incomplete 'yt:stretch=16:'
1598 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1599 'only_matching': True,
1600 },
7caf9830
S
1601 {
1602 # Video licensed under Creative Commons
1603 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1604 'info_dict': {
1605 'id': 'M4gD1WSo5mA',
1606 'ext': 'mp4',
1607 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1608 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1609 'duration': 721,
17322130 1610 'upload_date': '20150128',
7caf9830 1611 'uploader_id': 'BerkmanCenter',
ec85ded8 1612 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1613 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1614 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1615 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1616 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1617 'like_count': int,
1618 'age_limit': 0,
1619 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1620 'channel': 'The Berkman Klein Center for Internet & Society',
1621 'availability': 'public',
1622 'view_count': int,
1623 'categories': ['Education'],
1624 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1625 'live_status': 'not_live',
1626 'playable_in_embed': True,
12a1b225 1627 'comment_count': int,
6c73052c 1628 'channel_follower_count': int
7caf9830
S
1629 },
1630 'params': {
1631 'skip_download': True,
1632 },
1633 },
fd050249
S
1634 {
1635 # Channel-like uploader_url
1636 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1637 'info_dict': {
1638 'id': 'eQcmzGIKrzg',
1639 'ext': 'mp4',
1640 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1641 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1642 'duration': 4060,
17322130 1643 'upload_date': '20151120',
eb6793ba 1644 'uploader': 'Bernie Sanders',
fd050249 1645 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1646 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1647 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1648 'playable_in_embed': True,
1649 'tags': 'count:12',
1650 'like_count': int,
1651 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1652 'age_limit': 0,
1653 'availability': 'public',
1654 'categories': ['News & Politics'],
1655 'channel': 'Bernie Sanders',
1656 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1657 'view_count': int,
1658 'live_status': 'not_live',
1659 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1660 'comment_count': int,
6c73052c 1661 'channel_follower_count': int
fd050249
S
1662 },
1663 'params': {
1664 'skip_download': True,
1665 },
1666 },
040ac686
S
1667 {
1668 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1669 'only_matching': True,
7f29cf54
S
1670 },
1671 {
067aa17e 1672 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1673 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1674 'only_matching': True,
6496ccb4
S
1675 },
1676 {
1677 # Rental video preview
1678 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1679 'info_dict': {
1680 'id': 'uGpuVWrhIzE',
1681 'ext': 'mp4',
1682 'title': 'Piku - Trailer',
1683 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1684 'upload_date': '20150811',
1685 'uploader': 'FlixMatrix',
1686 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1687 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1688 'license': 'Standard YouTube License',
1689 },
1690 'params': {
1691 'skip_download': True,
1692 },
eb6793ba 1693 'skip': 'This video is not available.',
022a5d66 1694 },
12afdc2a
S
1695 {
1696 # YouTube Red video with episode data
1697 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1698 'info_dict': {
1699 'id': 'iqKdEhx-dD4',
1700 'ext': 'mp4',
1701 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1702 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1703 'duration': 2085,
12afdc2a
S
1704 'upload_date': '20170118',
1705 'uploader': 'Vsauce',
1706 'uploader_id': 'Vsauce',
1707 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1708 'series': 'Mind Field',
1709 'season_number': 1,
1710 'episode_number': 1,
976ae3ea 1711 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1712 'tags': 'count:12',
1713 'view_count': int,
1714 'availability': 'public',
1715 'age_limit': 0,
1716 'channel': 'Vsauce',
1717 'episode': 'Episode 1',
1718 'categories': ['Entertainment'],
1719 'season': 'Season 1',
1720 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1721 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1722 'like_count': int,
1723 'playable_in_embed': True,
1724 'live_status': 'not_live',
6c73052c 1725 'channel_follower_count': int
12afdc2a
S
1726 },
1727 'params': {
1728 'skip_download': True,
1729 },
1730 'expected_warnings': [
1731 'Skipping DASH manifest',
1732 ],
1733 },
c7121fa7
S
1734 {
1735 # The following content has been identified by the YouTube community
1736 # as inappropriate or offensive to some audiences.
1737 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1738 'info_dict': {
1739 'id': '6SJNVb0GnPI',
1740 'ext': 'mp4',
1741 'title': 'Race Differences in Intelligence',
1742 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1743 'duration': 965,
1744 'upload_date': '20140124',
1745 'uploader': 'New Century Foundation',
1746 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1747 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1748 },
1749 'params': {
1750 'skip_download': True,
1751 },
545cc85d 1752 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1753 },
022a5d66
S
1754 {
1755 # itag 212
1756 'url': '1t24XAntNCY',
1757 'only_matching': True,
fd5c4aab
S
1758 },
1759 {
1760 # geo restricted to JP
1761 'url': 'sJL6WA-aGkQ',
1762 'only_matching': True,
1763 },
cd5a74a2
S
1764 {
1765 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1766 'only_matching': True,
1767 },
bc2ca1bb 1768 {
1769 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1770 'only_matching': True,
1771 },
1772 {
1773 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1774 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1775 'only_matching': True,
1776 },
825cd268
RA
1777 {
1778 # DRM protected
1779 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1780 'only_matching': True,
4fe54c12
S
1781 },
1782 {
1783 # Video with unsupported adaptive stream type formats
1784 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1785 'info_dict': {
1786 'id': 'Z4Vy8R84T1U',
1787 'ext': 'mp4',
1788 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1789 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1790 'duration': 433,
1791 'upload_date': '20130923',
1792 'uploader': 'Amelia Putri Harwita',
1793 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1794 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1795 'formats': 'maxcount:10',
1796 },
1797 'params': {
1798 'skip_download': True,
1799 'youtube_include_dash_manifest': False,
1800 },
5429d6a9 1801 'skip': 'not actual anymore',
5caabd3c 1802 },
1803 {
822b9d9c 1804 # Youtube Music Auto-generated description
5caabd3c 1805 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1806 'info_dict': {
1807 'id': 'MgNrAu2pzNs',
1808 'ext': 'mp4',
1809 'title': 'Voyeur Girl',
1810 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1811 'upload_date': '20190312',
5429d6a9
S
1812 'uploader': 'Stephen - Topic',
1813 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1814 'artist': 'Stephen',
1815 'track': 'Voyeur Girl',
1816 'album': 'it\'s too much love to know my dear',
1817 'release_date': '20190313',
1818 'release_year': 2019,
976ae3ea 1819 'alt_title': 'Voyeur Girl',
1820 'view_count': int,
1821 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1822 'playable_in_embed': True,
1823 'like_count': int,
1824 'categories': ['Music'],
1825 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1826 'channel': 'Stephen',
1827 'availability': 'public',
1828 'creator': 'Stephen',
1829 'duration': 169,
1830 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1831 'age_limit': 0,
1832 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1833 'tags': 'count:11',
1834 'live_status': 'not_live',
6c73052c 1835 'channel_follower_count': int
5caabd3c 1836 },
1837 'params': {
1838 'skip_download': True,
1839 },
1840 },
66b48727
RA
1841 {
1842 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1843 'only_matching': True,
1844 },
011e75e6
S
1845 {
1846 # invalid -> valid video id redirection
1847 'url': 'DJztXj2GPfl',
1848 'info_dict': {
1849 'id': 'DJztXj2GPfk',
1850 'ext': 'mp4',
1851 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1852 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1853 'upload_date': '20090125',
1854 'uploader': 'Prochorowka',
1855 'uploader_id': 'Prochorowka',
1856 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1857 'artist': 'Panjabi MC',
1858 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1859 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1860 },
1861 'params': {
1862 'skip_download': True,
1863 },
545cc85d 1864 'skip': 'Video unavailable',
ea74e00b
DP
1865 },
1866 {
1867 # empty description results in an empty string
1868 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1869 'info_dict': {
1870 'id': 'x41yOUIvK2k',
1871 'ext': 'mp4',
1872 'title': 'IMG 3456',
1873 'description': '',
1874 'upload_date': '20170613',
1875 'uploader_id': 'ElevageOrVert',
1876 'uploader': 'ElevageOrVert',
976ae3ea 1877 'view_count': int,
1878 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1879 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1880 'like_count': int,
1881 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1882 'tags': [],
1883 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1884 'availability': 'public',
1885 'age_limit': 0,
1886 'categories': ['Pets & Animals'],
1887 'duration': 7,
1888 'playable_in_embed': True,
1889 'live_status': 'not_live',
1890 'channel': 'ElevageOrVert',
6c73052c 1891 'channel_follower_count': int
ea74e00b
DP
1892 },
1893 'params': {
1894 'skip_download': True,
1895 },
1896 },
a0566bbf 1897 {
29f7c58a 1898 # with '};' inside yt initial data (see [1])
1899 # see [2] for an example with '};' inside ytInitialPlayerResponse
1900 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1901 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1902 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1903 'info_dict': {
1904 'id': 'CHqg6qOn4no',
1905 'ext': 'mp4',
1906 'title': 'Part 77 Sort a list of simple types in c#',
1907 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1908 'upload_date': '20130831',
1909 'uploader_id': 'kudvenkat',
1910 'uploader': 'kudvenkat',
976ae3ea 1911 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1912 'like_count': int,
1913 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1914 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1915 'live_status': 'not_live',
1916 'categories': ['Education'],
1917 'availability': 'public',
1918 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1919 'tags': 'count:12',
1920 'playable_in_embed': True,
1921 'age_limit': 0,
1922 'view_count': int,
1923 'duration': 522,
1924 'channel': 'kudvenkat',
12a1b225 1925 'comment_count': int,
6c73052c 1926 'channel_follower_count': int
a0566bbf 1927 },
1928 'params': {
1929 'skip_download': True,
1930 },
1931 },
29f7c58a 1932 {
1933 # another example of '};' in ytInitialData
1934 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1935 'only_matching': True,
1936 },
1937 {
1938 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1939 'only_matching': True,
1940 },
545cc85d 1941 {
cc2db878 1942 # https://github.com/ytdl-org/youtube-dl/pull/28094
1943 'url': 'OtqTfy26tG0',
1944 'info_dict': {
1945 'id': 'OtqTfy26tG0',
1946 'ext': 'mp4',
1947 'title': 'Burn Out',
1948 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1949 'upload_date': '20141120',
1950 'uploader': 'The Cinematic Orchestra - Topic',
1951 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1952 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1953 'artist': 'The Cinematic Orchestra',
1954 'track': 'Burn Out',
1955 'album': 'Every Day',
976ae3ea 1956 'like_count': int,
1957 'live_status': 'not_live',
1958 'alt_title': 'Burn Out',
1959 'duration': 614,
1960 'age_limit': 0,
1961 'view_count': int,
1962 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1963 'creator': 'The Cinematic Orchestra',
1964 'channel': 'The Cinematic Orchestra',
1965 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1966 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1967 'availability': 'public',
1968 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1969 'categories': ['Music'],
1970 'playable_in_embed': True,
6c73052c 1971 'channel_follower_count': int
cc2db878 1972 },
1973 'params': {
1974 'skip_download': True,
1975 },
545cc85d 1976 },
bc2ca1bb 1977 {
1978 # controversial video, only works with bpctr when authenticated with cookies
1979 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1980 'only_matching': True,
1981 },
a1a7907b 1982 {
1983 # controversial video, requires bpctr/contentCheckOk
1984 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1985 'info_dict': {
1986 'id': 'SZJvDhaSDnc',
1987 'ext': 'mp4',
1988 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1989 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1990 'uploader': 'CBS Mornings',
11f9be09 1991 'uploader_id': 'CBSThisMorning',
a1a7907b 1992 'upload_date': '20140716',
976ae3ea 1993 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1994 'duration': 170,
1995 'categories': ['News & Politics'],
1996 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1997 'view_count': int,
1998 'channel': 'CBS Mornings',
1999 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2000 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2001 'age_limit': 18,
2002 'availability': 'needs_auth',
2003 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2004 'like_count': int,
2005 'live_status': 'not_live',
2006 'playable_in_embed': True,
6c73052c 2007 'channel_follower_count': int
a1a7907b 2008 }
2009 },
f7ad7160 2010 {
2011 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2012 'url': 'cBvYw8_A0vQ',
2013 'info_dict': {
2014 'id': 'cBvYw8_A0vQ',
2015 'ext': 'mp4',
2016 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2017 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2018 'upload_date': '20201120',
2019 'uploader': 'Walk around Japan',
2020 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2021 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2022 'duration': 1456,
2023 'categories': ['Travel & Events'],
2024 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2025 'view_count': int,
2026 'channel': 'Walk around Japan',
2027 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2028 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2029 'age_limit': 0,
2030 'availability': 'public',
2031 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2032 'live_status': 'not_live',
2033 'playable_in_embed': True,
6c73052c 2034 'channel_follower_count': int
f7ad7160 2035 },
2036 'params': {
2037 'skip_download': True,
2038 },
0fb983f6 2039 }, {
2040 # Has multiple audio streams
2041 'url': 'WaOKSUlf4TM',
2042 'only_matching': True
9297939e 2043 }, {
2044 # Requires Premium: has format 141 when requested using YTM url
2045 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2046 'only_matching': True
2047 }, {
120916da 2048 # multiple subtitles with same lang_code
2049 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2050 'only_matching': True,
109dd3b2 2051 }, {
2052 # Force use android client fallback
2053 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2054 'info_dict': {
2055 'id': 'YOelRv7fMxY',
11f9be09 2056 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2057 'ext': '3gp',
2058 'upload_date': '20210624',
2059 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2060 'uploader': 'colinfurze',
11f9be09 2061 'uploader_id': 'colinfurze',
109dd3b2 2062 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2063 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2064 'duration': 596,
2065 'categories': ['Entertainment'],
2066 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2067 'view_count': int,
2068 'channel': 'colinfurze',
2069 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2070 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2071 'age_limit': 0,
2072 'availability': 'public',
2073 'like_count': int,
2074 'live_status': 'not_live',
2075 'playable_in_embed': True,
6c73052c 2076 'channel_follower_count': int
109dd3b2 2077 },
2078 'params': {
2079 'format': '17', # 3gp format available on android
2080 'extractor_args': {'youtube': {'player_client': ['android']}},
2081 },
120916da 2082 },
109dd3b2 2083 {
2084 # Skip download of additional client configs (remix client config in this case)
2085 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2086 'only_matching': True,
2087 'params': {
2088 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2089 },
8fc54b12 2090 }, {
2091 # shorts
2092 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2093 'only_matching': True,
9222c381 2094 }, {
2095 'note': 'Storyboards',
2096 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2097 'info_dict': {
2098 'id': '5KLPxDtMqe8',
2099 'ext': 'mhtml',
2100 'format_id': 'sb0',
2101 'title': 'Your Brain is Plastic',
2102 'uploader_id': 'scishow',
2103 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2104 'upload_date': '20140324',
2105 'uploader': 'SciShow',
976ae3ea 2106 'like_count': int,
2107 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2108 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2109 'view_count': int,
2110 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2111 'playable_in_embed': True,
2112 'tags': 'count:12',
2113 'uploader_url': 'http://www.youtube.com/user/scishow',
2114 'availability': 'public',
2115 'channel': 'SciShow',
2116 'live_status': 'not_live',
2117 'duration': 248,
2118 'categories': ['Education'],
2119 'age_limit': 0,
6c73052c 2120 'channel_follower_count': int
9222c381 2121 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2122 }, {
2123 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2124 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2125 'info_dict': {
2126 'id': '2NUZ8W2llS4',
2127 'ext': 'mp4',
2128 'title': 'The NP that test your phone performance 🙂',
2129 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2130 'uploader': 'Leon Nguyen',
2131 'uploader_id': 'VNSXIII',
2132 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2133 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2134 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2135 'duration': 21,
2136 'view_count': int,
2137 'age_limit': 0,
2138 'categories': ['Gaming'],
2139 'tags': 'count:23',
2140 'playable_in_embed': True,
2141 'live_status': 'not_live',
2142 'upload_date': '20220103',
2143 'like_count': int,
2144 'availability': 'public',
2145 'channel': 'Leon Nguyen',
2146 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2147 'comment_count': int,
992f9a73 2148 'channel_follower_count': int
2149 }
2150 }, {
2151 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2152 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2153 'info_dict': {
2154 'id': 'mzZzzBU6lrM',
2155 'ext': 'mp4',
2156 'title': 'I Met GeorgeNotFound In Real Life...',
2157 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2158 'uploader': 'Quackity',
2159 'uploader_id': 'QuackityHQ',
2160 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2161 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2162 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2163 'duration': 955,
2164 'view_count': int,
2165 'age_limit': 0,
2166 'categories': ['Entertainment'],
2167 'tags': 'count:26',
2168 'playable_in_embed': True,
2169 'live_status': 'not_live',
2170 'release_timestamp': 1641172509,
2171 'release_date': '20220103',
2172 'upload_date': '20220103',
2173 'like_count': int,
2174 'availability': 'public',
2175 'channel': 'Quackity',
2176 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2177 'channel_follower_count': int
2178 }
2179 },
2180 { # continuous livestream. Microformat upload date should be preferred.
2181 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2182 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2183 'info_dict': {
2184 'id': 'kgx4WGK0oNU',
2185 'title': r're:jazz\/lofi hip hop radio🌱chill beats to relax\/study to \[LIVE 24\/7\] \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
2186 'ext': 'mp4',
2187 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2188 'availability': 'public',
2189 'age_limit': 0,
2190 'release_timestamp': 1637975704,
2191 'upload_date': '20210619',
2192 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2193 'live_status': 'is_live',
2194 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2195 'uploader': '阿鲍Abao',
2196 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2197 'channel': 'Abao in Tokyo',
2198 'channel_follower_count': int,
2199 'release_date': '20211127',
2200 'tags': 'count:39',
2201 'categories': ['People & Blogs'],
2202 'like_count': int,
2203 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2204 'view_count': int,
2205 'playable_in_embed': True,
2206 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2207 },
2208 'params': {'skip_download': True}
6e634cbe 2209 }, {
2210 # Story. Requires specific player params to work.
ee27297f 2211 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2212 'info_dict': {
ee27297f 2213 'id': 'vv8qTUWmulI',
6e634cbe 2214 'ext': 'mp4',
ee27297f 2215 'availability': 'unlisted',
2216 'view_count': int,
2217 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2218 'upload_date': '20220526',
2219 'categories': ['Education'],
2220 'title': 'Story',
2221 'channel': 'IT\'S HISTORY',
2222 'description': '',
2223 'uploader_id': 'BlastfromthePast',
2224 'duration': 12,
2225 'uploader': 'IT\'S HISTORY',
6e634cbe 2226 'playable_in_embed': True,
6e634cbe 2227 'age_limit': 0,
6e634cbe 2228 'live_status': 'not_live',
ee27297f 2229 'tags': [],
2230 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2231 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2232 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
12a1b225
A
2233 },
2234 'skip': 'stories get removed after some period of time',
ee27297f 2235 }, {
2236 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2237 'info_dict': {
2238 'id': 'tjjjtzRLHvA',
2239 'ext': 'mp4',
2240 'title': 'ハッシュタグ無し };if window.ytcsi',
2241 'upload_date': '20220323',
2242 'like_count': int,
2243 'availability': 'unlisted',
2244 'channel': 'nao20010128nao',
2245 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2246 'age_limit': 0,
2247 'uploader': 'nao20010128nao',
2248 'uploader_id': 'nao20010128nao',
2249 'categories': ['Music'],
6e634cbe 2250 'view_count': int,
2251 'description': '',
ee27297f 2252 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2253 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2254 'live_status': 'not_live',
2255 'playable_in_embed': True,
2256 'channel_follower_count': int,
2257 'duration': 6,
2258 'tags': [],
2259 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2260 }
a4166234 2261 }, {
2262 'note': '6 channel audio',
2263 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2264 'only_matching': True,
6e634cbe 2265 }
2eb88d95
PH
2266 ]
2267
f2e8dbcc 2268 _WEBPAGE_TESTS = [
2269 # YouTube <object> embed
2270 {
2271 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2272 'md5': '873c81d308b979f0e23ee7e620b312a3',
2273 'info_dict': {
2274 'id': 'msN87y-iEx0',
2275 'ext': 'mp4',
2276 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2277 'upload_date': '20080526',
2278 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2279 'uploader': 'Christopher Sykes',
2280 'uploader_id': 'ChristopherJSykes',
2281 'age_limit': 0,
2282 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2283 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2284 'playable_in_embed': True,
2285 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2286 'like_count': int,
2287 'comment_count': int,
2288 'channel': 'Christopher Sykes',
2289 'live_status': 'not_live',
2290 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2291 'availability': 'public',
2292 'duration': 195,
2293 'view_count': int,
2294 'categories': ['Science & Technology'],
2295 'channel_follower_count': int,
2296 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2297 },
2298 'params': {
2299 'skip_download': True,
2300 }
2301 },
2302 ]
2303
201c1459 2304 @classmethod
2305 def suitable(cls, url):
4dfbf869 2306 from ..utils import parse_qs
2307
201c1459 2308 qs = parse_qs(url)
2309 if qs.get('list', [None])[0]:
2310 return False
86e5f3ed 2311 return super().suitable(url)
201c1459 2312
e0df6211 2313 def __init__(self, *args, **kwargs):
86e5f3ed 2314 super().__init__(*args, **kwargs)
545cc85d 2315 self._code_cache = {}
83799698 2316 self._player_cache = {}
e0df6211 2317
adbc4ec4 2318 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2319 lock = threading.Lock()
2320
2321 is_live = True
185bf310 2322 start_time = time.time()
adbc4ec4
THD
2323 formats = [f for f in formats if f.get('is_from_start')]
2324
185bf310 2325 def refetch_manifest(format_id, delay):
2326 nonlocal formats, start_time, is_live
2327 if time.time() <= start_time + delay:
adbc4ec4
THD
2328 return
2329
2330 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2331 video_details = traverse_obj(
2332 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2333 microformats = traverse_obj(
2334 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2335 expected_type=dict, default=[])
c646d76f 2336 _, is_live, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2337 start_time = time.time()
adbc4ec4 2338
185bf310 2339 def mpd_feed(format_id, delay):
adbc4ec4
THD
2340 """
2341 @returns (manifest_url, manifest_stream_number, is_live) or None
2342 """
2343 with lock:
185bf310 2344 refetch_manifest(format_id, delay)
adbc4ec4
THD
2345
2346 f = next((f for f in formats if f['format_id'] == format_id), None)
2347 if not f:
185bf310 2348 if not is_live:
2349 self.to_screen(f'{video_id}: Video is no longer live')
2350 else:
2351 self.report_warning(
2352 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2353 return None
2354 return f['manifest_url'], f['manifest_stream_number'], is_live
2355
2356 for f in formats:
a539f065 2357 f['is_live'] = True
adbc4ec4
THD
2358 f['protocol'] = 'http_dash_segments_generator'
2359 f['fragments'] = functools.partial(
2360 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2361
2362 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2363 FETCH_SPAN, MAX_DURATION = 5, 432000
2364
2365 mpd_url, stream_number, is_live = None, None, True
2366
2367 begin_index = 0
2368 download_start_time = ctx.get('start') or time.time()
2369
2370 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2371 if lack_early_segments:
2372 self.report_warning(bug_reports_message(
2373 'Starting download from the last 120 hours of the live stream since '
2374 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2375 lack_early_segments = True
2376
2377 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2378 fragments, fragment_base_url = None, None
2379
a539f065 2380 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2381 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2382 # Obtain from MPD's maximum seq value
2383 old_mpd_url = mpd_url
185bf310 2384 last_error = ctx.pop('last_error', None)
14f25df2 2385 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2386 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2387 or (mpd_url, stream_number, False))
2388 if not refresh_sequence:
2389 if expire_fast and not is_live:
2390 return False, last_seq
2391 elif old_mpd_url == mpd_url:
2392 return True, last_seq
adbc4ec4
THD
2393 try:
2394 fmts, _ = self._extract_mpd_formats_and_subtitles(
2395 mpd_url, None, note=False, errnote=False, fatal=False)
2396 except ExtractorError:
2397 fmts = None
2398 if not fmts:
a539f065 2399 no_fragment_score += 2
adbc4ec4
THD
2400 return False, last_seq
2401 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2402 fragments = fmt_info['fragments']
2403 fragment_base_url = fmt_info['fragment_base_url']
2404 assert fragment_base_url
2405
2406 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2407 return True, _last_seq
2408
2409 while is_live:
2410 fetch_time = time.time()
2411 if no_fragment_score > 30:
2412 return
2413 if last_segment_url:
2414 # Obtain from "X-Head-Seqnum" header value from each segment
2415 try:
2416 urlh = self._request_webpage(
2417 last_segment_url, None, note=False, errnote=False, fatal=False)
2418 except ExtractorError:
2419 urlh = None
2420 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2421 if last_seq is None:
a539f065 2422 no_fragment_score += 2
adbc4ec4
THD
2423 last_segment_url = None
2424 continue
2425 else:
a539f065
LNO
2426 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2427 no_fragment_score += 2
185bf310 2428 if not should_continue:
adbc4ec4
THD
2429 continue
2430
2431 if known_idx > last_seq:
2432 last_segment_url = None
2433 continue
2434
2435 last_seq += 1
2436
2437 if begin_index < 0 and known_idx < 0:
2438 # skip from the start when it's negative value
2439 known_idx = last_seq + begin_index
2440 if lack_early_segments:
2441 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2442 try:
2443 for idx in range(known_idx, last_seq):
2444 # do not update sequence here or you'll get skipped some part of it
a539f065 2445 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2446 if not should_continue:
adbc4ec4
THD
2447 known_idx = idx - 1
2448 raise ExtractorError('breaking out of outer loop')
2449 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2450 yield {
2451 'url': last_segment_url,
36195c44 2452 'fragment_count': last_seq,
adbc4ec4
THD
2453 }
2454 if known_idx == last_seq:
2455 no_fragment_score += 5
2456 else:
2457 no_fragment_score = 0
2458 known_idx = last_seq
2459 except ExtractorError:
2460 continue
2461
2462 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2463
b6de707d 2464 def _extract_player_url(self, *ytcfgs, webpage=None):
2465 player_url = traverse_obj(
2466 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2467 get_all=False, expected_type=str)
11f9be09 2468 if not player_url:
b6de707d 2469 return
60f393e4 2470 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2471
b6de707d 2472 def _download_player_url(self, video_id, fatal=False):
2473 res = self._download_webpage(
2474 'https://www.youtube.com/iframe_api',
2475 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2476 if res:
2477 player_version = self._search_regex(
2478 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2479 if player_version:
2480 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2481
60064c53
PH
2482 def _signature_cache_id(self, example_sig):
2483 """ Return a string representation of a signature """
14f25df2 2484 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2485
e40c758c
S
2486 @classmethod
2487 def _extract_player_info(cls, player_url):
2488 for player_re in cls._PLAYER_INFO_RE:
2489 id_m = re.search(player_re, player_url)
2490 if id_m:
2491 break
2492 else:
c081b35c 2493 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2494 return id_m.group('id')
e40c758c 2495
404f611f 2496 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2497 player_id = self._extract_player_info(player_url)
2498 if player_id not in self._code_cache:
1276a43a 2499 code = self._download_webpage(
109dd3b2 2500 player_url, video_id, fatal=fatal,
2501 note='Downloading player ' + player_id,
2502 errnote='Download of %s failed' % player_url)
1276a43a 2503 if code:
2504 self._code_cache[player_id] = code
404f611f 2505 return self._code_cache.get(player_id)
109dd3b2 2506
e40c758c 2507 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2508 player_id = self._extract_player_info(player_url)
e0df6211 2509
c4417ddb 2510 # Read from filesystem cache
86e5f3ed 2511 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2512 assert os.path.basename(func_id) == func_id
a0e07d31 2513
ae61d108 2514 self.write_debug(f'Extracting signature function {func_id}')
9809740b 2515 cache_spec = self.cache.load('youtube-sigfuncs', func_id)
a0e07d31 2516 if cache_spec is not None:
78caa52a 2517 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2518
404f611f 2519 code = self._load_player(video_id, player_url)
2520 if code:
109dd3b2 2521 res = self._parse_sig_js(code)
e0df6211 2522
ac668111 2523 test_string = ''.join(map(chr, range(len(example_sig))))
109dd3b2 2524 cache_res = res(test_string)
2525 cache_spec = [ord(c) for c in cache_res]
83799698 2526
9809740b 2527 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
109dd3b2 2528 return res
83799698 2529
60064c53 2530 def _print_sig_code(self, func, example_sig):
404f611f 2531 if not self.get_param('youtube_print_sig_code'):
2532 return
2533
edf3e38e
PH
2534 def gen_sig_code(idxs):
2535 def _genslice(start, end, step):
78caa52a 2536 starts = '' if start == 0 else str(start)
8bcc8756 2537 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 2538 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 2539 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
2540
2541 step = None
7af808a5
PH
2542 # Quelch pyflakes warnings - start will be set when step is set
2543 start = '(Never used)'
edf3e38e
PH
2544 for i, prev in zip(idxs[1:], idxs[:-1]):
2545 if step is not None:
2546 if i - prev == step:
2547 continue
2548 yield _genslice(start, prev, step)
2549 step = None
2550 continue
2551 if i - prev in [-1, 1]:
2552 step = i - prev
2553 start = prev
2554 continue
2555 else:
78caa52a 2556 yield 's[%d]' % prev
edf3e38e 2557 if step is None:
78caa52a 2558 yield 's[%d]' % i
edf3e38e
PH
2559 else:
2560 yield _genslice(start, i, step)
2561
ac668111 2562 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 2563 cache_res = func(test_string)
edf3e38e 2564 cache_spec = [ord(c) for c in cache_res]
78caa52a 2565 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 2566 signature_id_tuple = '(%s)' % (
14f25df2 2567 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 2568 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 2569 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 2570 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 2571
e0df6211
PH
2572 def _parse_sig_js(self, jscode):
2573 funcname = self._search_regex(
abefc03f
S
2574 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2575 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
858a65ec
P
2576 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2577 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2578 r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\);[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\)',
2579 r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
31ce6e99 2580 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f
S
2581 # Obsolete patterns
2582 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 2583 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
2584 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2585 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2586 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2587 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2588 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2589 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 2590 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
2591
2592 jsi = JSInterpreter(jscode)
2593 initial_function = jsi.extract_function(funcname)
e0df6211
PH
2594 return lambda s: initial_function([s])
2595
545cc85d 2596 def _decrypt_signature(self, s, video_id, player_url):
257a2501 2597 """Turn the encrypted s field into a working signature"""
c8bf86d5 2598 try:
62af3a0e 2599 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5 2600 if player_id not in self._player_cache:
52023f12 2601 func = self._extract_signature_function(video_id, player_url, s)
c8bf86d5
PH
2602 self._player_cache[player_id] = func
2603 func = self._player_cache[player_id]
404f611f 2604 self._print_sig_code(func, s)
c8bf86d5
PH
2605 return func(s)
2606 except Exception as e:
52023f12 2607 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2608
2609 def _decrypt_nsig(self, s, video_id, player_url):
2610 """Turn the encrypted n field into a working signature"""
2611 if player_url is None:
2612 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 2613 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 2614
2615 sig_id = ('nsig_value', s)
2616 if sig_id in self._player_cache:
2617 return self._player_cache[sig_id]
2618
2619 try:
2620 player_id = ('nsig', player_url)
2621 if player_id not in self._player_cache:
2622 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2623 func = self._player_cache[player_id]
2624 self._player_cache[sig_id] = func(s)
2625 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2626 return self._player_cache[sig_id]
2627 except Exception as e:
aa9369a2 2628 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
404f611f 2629
2630 def _extract_n_function_name(self, jscode):
48416bc4 2631 nfunc, idx = self._search_regex(
c571b3a6 2632 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
48416bc4 2633 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2634 if not idx:
2635 return nfunc
2636 return json.loads(js_to_json(self._search_regex(
a7d4acc0 2637 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
48416bc4 2638 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
404f611f 2639
2640 def _extract_n_function(self, video_id, player_url):
2641 player_id = self._extract_player_info(player_url)
9809740b 2642 func_code = self.cache.load('youtube-nsig', player_id)
404f611f 2643
2644 if func_code:
2645 jsi = JSInterpreter(func_code)
2646 else:
2647 jscode = self._load_player(video_id, player_url)
2648 funcname = self._extract_n_function_name(jscode)
2649 jsi = JSInterpreter(jscode)
2650 func_code = jsi.extract_function_code(funcname)
9809740b 2651 self.cache.store('youtube-nsig', player_id, func_code)
404f611f 2652
2653 if self.get_param('youtube_print_sig_code'):
2654 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2655
8f53dc44 2656 func = jsi.extract_function_from_code(*func_code)
2657 return lambda s: func([s])
e0df6211 2658
109dd3b2 2659 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2660 """
2661 Extract signatureTimestamp (sts)
2662 Required to tell API what sig/player version is in use.
2663 """
2664 sts = None
2665 if isinstance(ytcfg, dict):
2666 sts = int_or_none(ytcfg.get('STS'))
2667
2668 if not sts:
2669 # Attempt to extract from player
2670 if player_url is None:
2671 error_msg = 'Cannot extract signature timestamp without player_url.'
2672 if fatal:
2673 raise ExtractorError(error_msg)
2674 self.report_warning(error_msg)
2675 return
404f611f 2676 code = self._load_player(video_id, player_url, fatal=fatal)
2677 if code:
109dd3b2 2678 sts = int_or_none(self._search_regex(
2679 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2680 'JS player signature timestamp', group='sts', fatal=fatal))
2681 return sts
2682
11f9be09 2683 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
2684 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2685 label = 'fully ' if is_full else ''
2686 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2687 expected_type=url_or_none)
2688 if not url:
2689 self.report_warning(f'Unable to mark {label}watched')
2690 return
14f25df2 2691 parsed_url = urllib.parse.urlparse(url)
2692 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
2693
2694 # cpn generation algorithm is reverse engineered from base.js.
2695 # In fact it works even with dummy cpn.
2696 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2697 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2698
2699 # # more consistent results setting it to right before the end
2700 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2701
2702 qs.update({
2703 'ver': ['2'],
2704 'cpn': [cpn],
2705 'cmt': video_length,
2706 'el': 'detailpage', # otherwise defaults to "shorts"
2707 })
2708
2709 if is_full:
2710 # these seem to mark watchtime "history" in the real world
2711 # they're required, so send in a single value
2712 qs.update({
2713 'st': video_length,
2714 'et': video_length,
2715 })
2716
14f25df2 2717 url = urllib.parse.urlunparse(
2718 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
2719
2720 self._download_webpage(
2721 url, video_id, f'Marking {label}watched',
2722 'Unable to mark watched', fatal=False)
d77ab8e2 2723
bfd973ec 2724 @classmethod
2725 def _extract_from_webpage(cls, url, webpage):
2726 # Invidious Instances
2727 # https://github.com/yt-dlp/yt-dlp/issues/195
2728 # https://github.com/iv-org/invidious/pull/1730
2729 mobj = re.search(
2730 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2731 webpage)
2732 if mobj:
2733 yield cls.url_result(mobj.group('url'), cls)
2734 raise cls.StopExtraction()
2735
2736 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
2737
2738 # lazyYT YouTube embed
bfd973ec 2739 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
2740 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
2741
2742 # Wordpress "YouTube Video Importer" plugin
bfd973ec 2743 for m in re.findall(r'''(?x)<div[^>]+
2744 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
2745 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
2746 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 2747
97665381
PH
2748 @classmethod
2749 def extract_id(cls, url):
ae61d108 2750 video_id = cls.get_temp_id(url)
2751 if not video_id:
2752 raise ExtractorError(f'Invalid URL: {url}')
2753 return video_id
c5e8d7af 2754
7c365c21 2755 def _extract_chapters_from_json(self, data, duration):
2756 chapter_list = traverse_obj(
2757 data, (
2758 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2759 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2760 ), expected_type=list)
2761
2762 return self._extract_chapters(
2763 chapter_list,
2764 chapter_time=lambda chapter: float_or_none(
2765 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2766 chapter_title=lambda chapter: traverse_obj(
2767 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2768 duration=duration)
2769
2770 def _extract_chapters_from_engagement_panel(self, data, duration):
2771 content_list = traverse_obj(
8bdd16b4 2772 data,
7c365c21 2773 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
da503b7a 2774 expected_type=list, default=[])
052e1350 2775 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2776 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 2777
1890fc63 2778 return next(filter(None, (
2779 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2780 chapter_time, chapter_title, duration)
2781 for contents in content_list)), [])
7c365c21 2782
1890fc63 2783 def _extract_chapters_from_description(self, description, duration):
2784 return self._extract_chapters(
2785 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2786 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2787 duration=duration, strict=False)
84213ea8 2788
1890fc63 2789 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2790 if not duration:
2791 return
2792 chapter_list = [{
2793 'start_time': chapter_time(chapter),
2794 'title': chapter_title(chapter),
2795 } for chapter in chapter_list or []]
2796 if not strict:
2797 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2798
a3976e07 2799 chapters = [{'start_time': 0}]
1890fc63 2800 for idx, chapter in enumerate(chapter_list):
a3976e07 2801 if chapter['start_time'] is None:
1890fc63 2802 self.report_warning(f'Incomplete chapter {idx}')
2803 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
1890fc63 2804 chapters.append(chapter)
2805 else:
2806 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}"')
a3976e07 2807 return chapters[1:]
84213ea8 2808
a1c5d2ca
M
2809 def _extract_comment(self, comment_renderer, parent=None):
2810 comment_id = comment_renderer.get('commentId')
2811 if not comment_id:
2812 return
fe93e2c4 2813
052e1350 2814 text = self._get_text(comment_renderer, 'contentText')
fe93e2c4 2815
49bd8c66 2816 # note: timestamp is an estimate calculated from the current time and time_text
f3aa3c3f 2817 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
052e1350 2818 author = self._get_text(comment_renderer, 'authorText')
a1c5d2ca 2819 author_id = try_get(comment_renderer,
14f25df2 2820 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
fe93e2c4 2821
49bd8c66 2822 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
14f25df2 2823 lambda x: x['likeCount']), str)) or 0
a1c5d2ca 2824 author_thumbnail = try_get(comment_renderer,
14f25df2 2825 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
a1c5d2ca
M
2826
2827 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
97524332 2828 is_favorited = 'creatorHeart' in (try_get(
2829 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
a1c5d2ca
M
2830 return {
2831 'id': comment_id,
2832 'text': text,
d92f5d5a 2833 'timestamp': timestamp,
a1c5d2ca
M
2834 'time_text': time_text,
2835 'like_count': votes,
97524332 2836 'is_favorited': is_favorited,
a1c5d2ca
M
2837 'author': author,
2838 'author_id': author_id,
2839 'author_thumbnail': author_thumbnail,
2840 'author_is_uploader': author_is_uploader,
2841 'parent': parent or 'root'
2842 }
2843
46383212 2844 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2845
2846 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 2847
2848 def extract_header(contents):
2d6659b9 2849 _continuation = None
2850 for content in contents:
46383212 2851 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 2852 expected_comment_count = self._get_count(
2853 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 2854
2d6659b9 2855 if expected_comment_count:
46383212 2856 tracker['est_total'] = expected_comment_count
2857 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2858 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 2859
2860 sort_menu_item = try_get(
2861 comments_header_renderer,
2862 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2863 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2864
2865 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2866 if not _continuation:
2867 continue
2868
46383212 2869 sort_text = str_or_none(sort_menu_item.get('title'))
2870 if not sort_text:
2d6659b9 2871 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 2872 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 2873 break
a2160aa4 2874 return _continuation
a1c5d2ca 2875
2d6659b9 2876 def extract_thread(contents):
a1c5d2ca 2877 if not parent:
46383212 2878 tracker['current_page_thread'] = 0
a1c5d2ca 2879 for content in contents:
46383212 2880 if not parent and tracker['total_parent_comments'] >= max_parents:
2881 yield
a1c5d2ca 2882 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 2883 comment_renderer = get_first(
2884 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2885 expected_type=dict, default={})
a1c5d2ca 2886
a1c5d2ca
M
2887 comment = self._extract_comment(comment_renderer, parent)
2888 if not comment:
2889 continue
46383212 2890
2891 tracker['running_total'] += 1
2892 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 2893 yield comment
46383212 2894
a1c5d2ca
M
2895 # Attempt to get the replies
2896 comment_replies_renderer = try_get(
2897 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2898
2899 if comment_replies_renderer:
46383212 2900 tracker['current_page_thread'] += 1
a1c5d2ca 2901 comment_entries_iter = self._comment_entries(
99e9e001 2902 comment_replies_renderer, ytcfg, video_id,
46383212 2903 parent=comment.get('id'), tracker=tracker)
86e5f3ed 2904 yield from itertools.islice(comment_entries_iter, min(
2905 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 2906
46383212 2907 # Keeps track of counts across recursive calls
2908 if not tracker:
2909 tracker = dict(
2910 running_total=0,
2911 est_total=0,
2912 current_page_thread=0,
2913 total_parent_comments=0,
2914 total_reply_comments=0)
2915
2916 # TODO: Deprecated
2d6659b9 2917 # YouTube comments have a max depth of 2
46383212 2918 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2919 if max_depth:
2920 self._downloader.deprecation_warning(
2921 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2d6659b9 2922 if max_depth == 1 and parent:
2923 return
a1c5d2ca 2924
46383212 2925 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2926 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 2927
46383212 2928 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 2929
46383212 2930 response = None
6e634cbe 2931 is_forced_continuation = False
2d6659b9 2932 is_first_continuation = parent is None
6e634cbe 2933 if is_first_continuation and not continuation:
2934 # Sometimes you can get comments by generating the continuation yourself,
2935 # even if YouTube initially reports them being disabled - e.g. stories comments.
2936 # Note: if the comment section is actually disabled, YouTube may return a response with
2937 # required check_get_keys missing. So we will disable that check initially in this case.
2938 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2939 is_forced_continuation = True
a1c5d2ca
M
2940
2941 for page_num in itertools.count(0):
2942 if not continuation:
2943 break
46383212 2944 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2945 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2d6659b9 2946 if page_num == 0:
2947 if is_first_continuation:
2948 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 2949 else:
2d6659b9 2950 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 2951 tracker['current_page_thread'], comment_prog_str)
2d6659b9 2952 else:
2953 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2954 ' ' if parent else '', ' replies' if parent else '',
2955 page_num, comment_prog_str)
2956
2957 response = self._extract_response(
fe93e2c4 2958 item_id=None, query=continuation,
2d6659b9 2959 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
6e634cbe 2960 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2961 is_forced_continuation = False
46383212 2962 continuation_contents = traverse_obj(
2963 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
a1c5d2ca 2964
2d6659b9 2965 continuation = None
46383212 2966 for continuation_section in continuation_contents:
2967 continuation_items = traverse_obj(
2968 continuation_section,
2969 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2970 get_all=False, expected_type=list) or []
2971 if is_first_continuation:
2972 continuation = extract_header(continuation_items)
2973 is_first_continuation = False
2d6659b9 2974 if continuation:
a1c5d2ca 2975 break
46383212 2976 continue
a1c5d2ca 2977
46383212 2978 for entry in extract_thread(continuation_items):
2979 if not entry:
2980 return
2981 yield entry
2982 continuation = self._extract_continuation({'contents': continuation_items})
2983 if continuation:
2d6659b9 2984 break
a1c5d2ca 2985
6e634cbe 2986 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2987 if message and not parent and tracker['running_total'] == 0:
2988 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
2989
2990 @staticmethod
2991 def _generate_comment_continuation(video_id):
2992 """
2993 Generates initial comment section continuation token from given video id
2994 """
2995 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
2996 return base64.b64encode(token.encode()).decode()
2997
a2160aa4 2998 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 2999 """Entry for comment extraction"""
2d6659b9 3000 def _real_comment_extract(contents):
aae16f6e 3001 renderer = next((
3002 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3003 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3004 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3005
a2160aa4 3006 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3007 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3008
109dd3b2 3009 @staticmethod
99e9e001 3010 def _get_checkok_params():
3011 return {'contentCheckOk': True, 'racyCheckOk': True}
3012
3013 @classmethod
3014 def _generate_player_context(cls, sts=None):
109dd3b2 3015 context = {
3016 'html5Preference': 'HTML5_PREF_WANTS',
3017 }
3018 if sts is not None:
3019 context['signatureTimestamp'] = sts
3020 return {
3021 'playbackContext': {
3022 'contentPlaybackContext': context
a1a7907b 3023 },
99e9e001 3024 **cls._get_checkok_params()
109dd3b2 3025 }
3026
e7e94f2a
D
3027 @staticmethod
3028 def _is_agegated(player_response):
3029 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3030 return True
e7e94f2a
D
3031
3032 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3033 AGE_GATE_REASONS = (
3034 'confirm your age', 'age-restricted', 'inappropriate', # reason
3035 'age_verification_required', 'age_check_required', # status
3036 )
3037 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3038
3039 @staticmethod
3040 def _is_unplayable(player_response):
3041 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3042
99e9e001 3043 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
109dd3b2 3044
11f9be09 3045 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3046 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3047 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3048 headers = self.generate_api_headers(
99e9e001 3049 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3050
6e634cbe 3051 yt_query = {
3052 'videoId': video_id,
3053 'params': '8AEB' # enable stories
3054 }
11f9be09 3055 yt_query.update(self._generate_player_context(sts))
3056 return self._extract_response(
3057 item_id=video_id, ep='player', query=yt_query,
379e44ed 3058 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3059 default_client=client,
11f9be09 3060 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3061 ) or None
3062
11f9be09 3063 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3064 requested_clients = []
d0d012d4 3065 default = ['android', 'web']
000c15a4 3066 allowed_clients = sorted(
86e5f3ed 3067 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3068 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3069 for client in self._configuration_arg('player_client'):
3070 if client in allowed_clients:
3071 requested_clients.append(client)
d0d012d4 3072 elif client == 'default':
3073 requested_clients.extend(default)
b4c055ba 3074 elif client == 'all':
3075 requested_clients.extend(allowed_clients)
3076 else:
3077 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3078 if not requested_clients:
d0d012d4 3079 requested_clients = default
cf7e015f 3080
11f9be09 3081 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3082 requested_clients.extend(
e7e94f2a 3083 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3084
11f9be09 3085 return orderedSet(requested_clients)
cf7e015f 3086
99e9e001 3087 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
11f9be09 3088 initial_pr = None
3089 if webpage:
b7c47b74 3090 initial_pr = self._search_json(
3091 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3092
ae729626 3093 all_clients = set(clients)
c0bc527b 3094 clients = clients[::-1]
b6de707d 3095 prs = []
e7e94f2a 3096
ae729626 3097 def append_client(*client_names):
e7870111 3098 """ Append the first client name that exists but not already used """
ae729626 3099 for client_name in client_names:
e7870111
D
3100 actual_client = _split_innertube_client(client_name)[0]
3101 if actual_client in INNERTUBE_CLIENTS:
3102 if actual_client not in all_clients:
ae729626 3103 clients.append(client_name)
e7870111
D
3104 all_clients.add(actual_client)
3105 return
e7e94f2a 3106
379e44ed 3107 # Android player_response does not have microFormats which are needed for
3108 # extraction of some data. So we return the initial_pr with formats
3109 # stripped out even if not requested by the user
3110 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3111 if initial_pr:
3112 pr = dict(initial_pr)
3113 pr['streamingData'] = None
b6de707d 3114 prs.append(pr)
379e44ed 3115
3116 last_error = None
b6de707d 3117 tried_iframe_fallback = False
3118 player_url = None
c0bc527b 3119 while clients:
e7870111 3120 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3121 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3122 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3123 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3124
b6de707d 3125 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3126 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3127 if 'js' in self._configuration_arg('player_skip'):
3128 require_js_player = False
3129 player_url = None
3130
3131 if not player_url and not tried_iframe_fallback and require_js_player:
3132 player_url = self._download_player_url(video_id)
3133 tried_iframe_fallback = True
3134
379e44ed 3135 try:
3136 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
99e9e001 3137 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
379e44ed 3138 except ExtractorError as e:
3139 if last_error:
3140 self.report_warning(last_error)
3141 last_error = e
3142 continue
3143
11f9be09 3144 if pr:
a3e96421 3145 # YouTube may return a different video player response than expected.
3146 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3147 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3148 if pr_video_id and pr_video_id != video_id:
3149 self.report_warning(
c7dcf0b3 3150 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3151 else:
3152 prs.append(pr)
c0bc527b 3153
e7e94f2a 3154 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3155 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3156 append_client(f'{base_client}_creator')
e7e94f2a 3157 elif self._is_agegated(pr):
e7870111
D
3158 if variant == 'tv_embedded':
3159 append_client(f'{base_client}_embedded')
3160 elif not variant:
3161 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3162
379e44ed 3163 if last_error:
b6de707d 3164 if not len(prs):
379e44ed 3165 raise last_error
3166 self.report_warning(last_error)
b6de707d 3167 return prs, player_url
11f9be09 3168
c646d76f 3169 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, is_live, duration):
a0bb6ce5 3170 itags, stream_ids = {}, []
2a9c6dcd 3171 itag_qualities, res_qualities = {}, {}
d3fc8074 3172 q = qualities([
2a9c6dcd 3173 # Normally tiny is the smallest video-only formats. But
3174 # audio-only formats with unknown quality may get tagged as tiny
3175 'tiny',
3176 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3177 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3178 ])
11f9be09 3179 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
9297939e 3180
545cc85d 3181 for fmt in streaming_formats:
727029c5 3182 if fmt.get('targetDurationSec'):
545cc85d 3183 continue
321bf820 3184
cc2db878 3185 itag = str_or_none(fmt.get('itag'))
9297939e 3186 audio_track = fmt.get('audioTrack') or {}
3187 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3188 if stream_id in stream_ids:
3189 continue
3190
cc2db878 3191 quality = fmt.get('quality')
2a9c6dcd 3192 height = int_or_none(fmt.get('height'))
d3fc8074 3193 if quality == 'tiny' or not quality:
3194 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3195 # The 3gp format (17) in android client has a quality of "small",
3196 # but is actually worse than other formats
3197 if itag == '17':
3198 quality = 'tiny'
3199 if quality:
3200 if itag:
3201 itag_qualities[itag] = quality
3202 if height:
3203 res_qualities[height] = quality
cc2db878 3204 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3205 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3206 # number of fragment that would subsequently requested with (`&sq=N`)
3207 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3208 continue
3209
545cc85d 3210 fmt_url = fmt.get('url')
3211 if not fmt_url:
14f25df2 3212 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3213 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3214 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3215 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3216 continue
52023f12 3217 try:
3218 fmt_url += '&%s=%s' % (
3219 traverse_obj(sc, ('sp', -1)) or 'signature',
3220 self._decrypt_signature(encrypted_sig, video_id, player_url)
3221 )
3222 except ExtractorError as e:
3223 self.report_warning('Signature extraction failed: Some formats may be missing', only_once=True)
3224 self.write_debug(e, only_once=True)
201e9eaa 3225 continue
545cc85d 3226
404f611f 3227 query = parse_qs(fmt_url)
3228 throttled = False
b2916526 3229 if query.get('n'):
404f611f 3230 try:
3231 fmt_url = update_url_query(fmt_url, {
3232 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3233 except ExtractorError as e:
aa9369a2 3234 self.report_warning(
1d485a1a 3235 'nsig extraction failed: You may experience throttling for some formats\n'
52023f12 3236 f'n = {query["n"][0]} ; player = {player_url}', only_once=True)
3237 self.write_debug(e, only_once=True)
404f611f 3238 throttled = True
3239
545cc85d 3240 if itag:
a0bb6ce5 3241 itags[itag] = 'https'
9297939e 3242 stream_ids.append(stream_id)
3243
0ad92dfb 3244 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3245 language_preference = (
3246 10 if audio_track.get('audioIsDefault') and 10
3247 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3248 else -1)
0ad92dfb 3249 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3250 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3251 # Make sure to avoid false positives with small duration differences.
62b58c09 3252 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3253 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3254 if is_damaged:
0f06bcd7 3255 self.report_warning(
3256 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
545cc85d 3257 dct = {
3258 'asr': int_or_none(fmt.get('audioSampleRate')),
3259 'filesize': int_or_none(fmt.get('contentLength')),
3260 'format_id': itag,
34921b43 3261 'format_note': join_nonempty(
26e8e044 3262 '%s%s' % (audio_track.get('displayName') or '',
ab6df717 3263 ' (default)' if language_preference > 0 else ''),
404f611f 3264 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
a4166234 3265 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3266 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
0ad92dfb 3267 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
91e5e839 3268 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3269 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
a4211baf 3270 'fps': int_or_none(fmt.get('fps')) or None,
a4166234 3271 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3272 'height': height,
dca3ff4a 3273 'quality': q(quality),
727029c5 3274 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3275 'tbr': tbr,
545cc85d 3276 'url': fmt_url,
2a9c6dcd 3277 'width': int_or_none(fmt.get('width')),
ab6df717 3278 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3279 'desc' if language_preference < -1 else ''),
3280 'language_preference': language_preference,
a405b38f 3281 # Strictly de-prioritize damaged and 3gp formats
3282 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3283 }
60bdb7bd 3284 mime_mobj = re.match(
3285 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3286 if mime_mobj:
3287 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3288 dct.update(parse_codecs(mime_mobj.group(2)))
cc2db878 3289 no_audio = dct.get('acodec') == 'none'
3290 no_video = dct.get('vcodec') == 'none'
3291 if no_audio:
3292 dct['vbr'] = tbr
3293 if no_video:
3294 dct['abr'] = tbr
3295 if no_audio or no_video:
545cc85d 3296 dct['downloader_options'] = {
3297 # Youtube throttles chunks >~10M
3298 'http_chunk_size': 10485760,
bf1317d2 3299 }
7c60c33e 3300 if dct.get('ext'):
3301 dct['container'] = dct['ext'] + '_dash'
11f9be09 3302 yield dct
545cc85d 3303
adbc4ec4 3304 live_from_start = is_live and self.get_param('live_from_start')
4bb6b02f 3305 skip_manifests = self._configuration_arg('skip')
adbc4ec4
THD
3306 if not self.get_param('youtube_include_hls_manifest', True):
3307 skip_manifests.append('hls')
0f06bcd7 3308 if not self.get_param('youtube_include_dash_manifest', True):
3309 skip_manifests.append('dash')
adbc4ec4
THD
3310 get_dash = 'dash' not in skip_manifests and (
3311 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3312 get_hls = not live_from_start and 'hls' not in skip_manifests
5d3a0e79 3313
a0bb6ce5 3314 def process_manifest_format(f, proto, itag):
3315 if itag in itags:
3316 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3317 return False
3318 itag = f'{itag}-{proto}'
3319 if itag:
3320 f['format_id'] = itag
3321 itags[itag] = proto
3322
3323 f['quality'] = next((
3324 q(qdict[val])
e339d25a 3325 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
a0bb6ce5 3326 if val in qdict), -1)
3327 return True
2a9c6dcd 3328
c646d76f 3329 subtitles = {}
11f9be09 3330 for sd in streaming_data:
5d3a0e79 3331 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3332 if hls_manifest_url:
c646d76f 3333 fmts, subs = self._extract_m3u8_formats_and_subtitles(hls_manifest_url, video_id, 'mp4', fatal=False, live=is_live)
3334 subtitles = self._merge_subtitles(subs, subtitles)
3335 for f in fmts:
a0bb6ce5 3336 if process_manifest_format(f, 'hls', self._search_regex(
3337 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3338 yield f
545cc85d 3339
5d3a0e79 3340 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3341 if dash_manifest_url:
c646d76f 3342 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3343 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3344 for f in formats:
a0bb6ce5 3345 if process_manifest_format(f, 'dash', f['format_id']):
3346 f['filesize'] = int_or_none(self._search_regex(
3347 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3348 if live_from_start:
3349 f['is_from_start'] = True
3350
a0bb6ce5 3351 yield f
c646d76f 3352 yield subtitles
11f9be09 3353
720c3099 3354 def _extract_storyboard(self, player_responses, duration):
3355 spec = get_first(
3356 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3357 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3358 if not base_url:
720c3099 3359 return
720c3099 3360 L = len(spec) - 1
3361 for i, args in enumerate(spec):
3362 args = args.split('#')
3363 counts = list(map(int_or_none, args[:5]))
3364 if len(args) != 8 or not all(counts):
3365 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3366 continue
3367 width, height, frame_count, cols, rows = counts
3368 N, sigh = args[6:]
3369
3370 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3371 fragment_count = frame_count / (cols * rows)
3372 fragment_duration = duration / fragment_count
3373 yield {
3374 'format_id': f'sb{i}',
3375 'format_note': 'storyboard',
3376 'ext': 'mhtml',
3377 'protocol': 'mhtml',
3378 'acodec': 'none',
3379 'vcodec': 'none',
3380 'url': url,
3381 'width': width,
3382 'height': height,
45e8a04e 3383 'fps': frame_count / duration,
3384 'rows': rows,
3385 'columns': cols,
720c3099 3386 'fragments': [{
b3edc806 3387 'url': url.replace('$M', str(j)),
720c3099 3388 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3389 } for j in range(math.ceil(fragment_count))],
3390 }
3391
adbc4ec4 3392 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3393 webpage = None
3394 if 'webpage' not in self._configuration_arg('player_skip'):
3395 webpage = self._download_webpage(
6e634cbe 3396 webpage_url + '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id, fatal=False)
11f9be09 3397
3398 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3399
b6de707d 3400 player_responses, player_url = self._extract_player_responses(
11f9be09 3401 self._get_requested_clients(url, smuggled_data),
99e9e001 3402 video_id, webpage, master_ytcfg)
11f9be09 3403
adbc4ec4
THD
3404 return webpage, master_ytcfg, player_responses, player_url
3405
a1b2d843 3406 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3407 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3408 is_live = get_first(video_details, 'isLive')
3409 if is_live is None:
3410 is_live = get_first(live_broadcast_details, 'isLiveNow')
3411
3412 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
c646d76f 3413 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, is_live, duration)
adbc4ec4 3414
c646d76f 3415 return live_broadcast_details, is_live, streaming_data, formats, subtitles
adbc4ec4
THD
3416
3417 def _real_extract(self, url):
3418 url, smuggled_data = unsmuggle_url(url, {})
3419 video_id = self._match_id(url)
3420
3421 base_url = self.http_scheme() + '//www.youtube.com/'
3422 webpage_url = base_url + 'watch?v=' + video_id
3423
3424 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3425
11f9be09 3426 playability_statuses = traverse_obj(
3427 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3428
3429 trailer_video_id = get_first(
3430 playability_statuses,
3431 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3432 expected_type=str)
3433 if trailer_video_id:
3434 return self.url_result(
3435 trailer_video_id, self.ie_key(), trailer_video_id)
3436
3437 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3438 if webpage else (lambda x: None))
3439
3440 video_details = traverse_obj(
3441 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3442 microformats = traverse_obj(
3443 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3444 expected_type=dict, default=[])
3445 video_title = (
3446 get_first(video_details, 'title')
3447 or self._get_text(microformats, (..., 'title'))
3448 or search_meta(['og:title', 'twitter:title', 'title']))
3449 video_description = get_first(video_details, 'shortDescription')
3450
d89257f3 3451 multifeed_metadata_list = get_first(
3452 player_responses,
3453 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3454 expected_type=str)
3455 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3456 if self.get_param('noplaylist'):
11f9be09 3457 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3458 else:
3459 entries = []
3460 feed_ids = []
3461 for feed in multifeed_metadata_list.split(','):
3462 # Unquote should take place before split on comma (,) since textual
3463 # fields may contain comma as well (see
3464 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3465 feed_data = urllib.parse.parse_qs(
ac668111 3466 urllib.parse.unquote_plus(feed))
d89257f3 3467
3468 def feed_entry(name):
3469 return try_get(
14f25df2 3470 feed_data, lambda x: x[name][0], str)
d89257f3 3471
3472 feed_id = feed_entry('id')
3473 if not feed_id:
3474 continue
3475 feed_title = feed_entry('title')
3476 title = video_title
3477 if feed_title:
3478 title += ' (%s)' % feed_title
3479 entries.append({
3480 '_type': 'url_transparent',
3481 'ie_key': 'Youtube',
3482 'url': smuggle_url(
3483 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3484 {'force_singlefeed': True}),
3485 'title': title,
3486 })
3487 feed_ids.append(feed_id)
3488 self.to_screen(
3489 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3490 % (', '.join(feed_ids), video_id))
3491 return self.playlist_result(
3492 entries, video_id, video_title, video_description)
11f9be09 3493
a1b2d843 3494 duration = int_or_none(
3495 get_first(video_details, 'lengthSeconds')
3496 or get_first(microformats, 'lengthSeconds')
3497 or parse_duration(search_meta('duration'))) or None
3498
c646d76f 3499 live_broadcast_details, is_live, streaming_data, formats, automatic_captions = \
3500 self._list_formats(video_id, microformats, video_details, player_responses, player_url)
bf1317d2 3501
545cc85d 3502 if not formats:
11f9be09 3503 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3504 self.report_drm(video_id)
11f9be09 3505 pemr = get_first(
3506 playability_statuses,
3507 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3508 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3509 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3510 if subreason:
545cc85d 3511 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3512 countries = get_first(microformats, 'availableCountries')
545cc85d 3513 if not countries:
3514 regions_allowed = search_meta('regionsAllowed')
3515 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3516 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3517 reason += f'. {subreason}'
545cc85d 3518 if reason:
b7da73eb 3519 self.raise_no_formats(reason, expected=True)
bf1317d2 3520
11f9be09 3521 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3522 if not keywords and webpage:
3523 keywords = [
3524 unescapeHTML(m.group('content'))
3525 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3526 for keyword in keywords:
3527 if keyword.startswith('yt:stretch='):
201c1459 3528 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3529 if mobj:
3530 # NB: float is intentional for forcing float division
3531 w, h = (float(v) for v in mobj.groups())
3532 if w > 0 and h > 0:
3533 ratio = w / h
3534 for f in formats:
3535 if f.get('vcodec') != 'none':
3536 f['stretched_ratio'] = ratio
3537 break
a709d873 3538 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3539 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3540 if thumbnail_url:
3541 thumbnails.append({
3542 'url': thumbnail_url,
ff2751ac 3543 })
fccf5021 3544 original_thumbnails = thumbnails.copy()
3545
0ba692ac 3546 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3547 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3548 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3549 thumbnail_names = [
962ffcf8 3550 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 3551 # in resolution, these are not the custom thumbnail. So de-prioritize them
3552 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3553 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3554 ]
cca80fe6 3555 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3556 thumbnails.extend({
3557 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3558 video_id=video_id, name=name, ext=ext,
3559 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3560 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3561 for thumb in thumbnails:
cca80fe6 3562 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3563 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3564 self._remove_duplicate_formats(thumbnails)
fccf5021 3565 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3566
7ea65411 3567 category = get_first(microformats, 'category') or search_meta('genre')
3568 channel_id = str_or_none(
3569 get_first(video_details, 'channelId')
3570 or get_first(microformats, 'externalChannelId')
3571 or search_meta('channelId'))
7ea65411 3572 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3573
3574 live_content = get_first(video_details, 'isLiveContent')
3575 is_upcoming = get_first(video_details, 'isUpcoming')
3576 if is_live is None:
3577 if is_upcoming or live_content is False:
3578 is_live = False
3579 if is_upcoming is None and (live_content or is_live):
3580 is_upcoming = False
adbc4ec4
THD
3581 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3582 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3583 if not duration and live_end_time and live_start_time:
3584 duration = live_end_time - live_start_time
3585
3586 if is_live and self.get_param('live_from_start'):
3587 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3588
720c3099 3589 formats.extend(self._extract_storyboard(player_responses, duration))
3590
31b532a1 3591 # source_preference is lower for throttled/potentially damaged formats
7e798d72 3592 self._sort_formats(formats, (
3593 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'))
720c3099 3594
545cc85d 3595 info = {
3596 'id': video_id,
39ca3b5c 3597 'title': video_title,
545cc85d 3598 'formats': formats,
3599 'thumbnails': thumbnails,
fccf5021 3600 # The best thumbnail that we are sure exists. Prevents unnecessary
3601 # URL checking if user don't care about getting the best possible thumbnail
3602 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3603 'description': video_description,
11f9be09 3604 'uploader': get_first(video_details, 'author'),
545cc85d 3605 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3606 'uploader_url': owner_profile_url,
3607 'channel_id': channel_id,
a70635b8 3608 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3609 'duration': duration,
3610 'view_count': int_or_none(
11f9be09 3611 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3612 or search_meta('interactionCount')),
11f9be09 3613 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3614 'age_limit': 18 if (
11f9be09 3615 get_first(microformats, 'isFamilySafe') is False
545cc85d 3616 or search_meta('isFamilyFriendly') == 'false'
3617 or search_meta('og:restrictions:age') == '18+') else 0,
3618 'webpage_url': webpage_url,
3619 'categories': [category] if category else None,
3620 'tags': keywords,
11f9be09 3621 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3622 'is_live': is_live,
3623 'was_live': (False if is_live or is_upcoming or live_content is False
3624 else None if is_live is None or is_upcoming is None
3625 else live_content),
3626 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3627 'release_timestamp': live_start_time,
545cc85d 3628 }
b477fc13 3629
e325a21a 3630 if get_first(video_details, 'isPostLiveDvr'):
3631 self.write_debug('Video is in Post-Live Manifestless mode')
3632 info['live_status'] = 'post_live'
3633 if (duration or 0) > 4 * 3600:
3634 self.report_warning(
3635 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3636 'This is a known issue and patches are welcome')
3637
c646d76f 3638 subtitles = {}
3944e7af 3639 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3640 if pctr:
ecdc9049 3641 def get_lang_code(track):
3642 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3643 or track.get('languageCode'))
3644
3645 # Converted into dicts to remove duplicates
3646 captions = {
3647 get_lang_code(sub): sub
3648 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3649 translation_languages = {
3650 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3651 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3652
774d79cc 3653 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3654 lang_subs = container.setdefault(lang_code, [])
545cc85d 3655 for fmt in self._SUBTITLE_FORMATS:
3656 query.update({
3657 'fmt': fmt,
3658 })
3659 lang_subs.append({
3660 'ext': fmt,
60f393e4 3661 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3662 'name': sub_name,
545cc85d 3663 })
7e72694b 3664
07b47084 3665 # NB: Constructing the full subtitle dictionary is slow
3666 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
3667 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 3668 for lang_code, caption_track in captions.items():
3669 base_url = caption_track.get('baseUrl')
1235d333 3670 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3671 if not base_url:
3672 continue
ecdc9049 3673 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3674 if caption_track.get('kind') != 'asr':
545cc85d 3675 if not lang_code:
3676 continue
3677 process_language(
ecdc9049 3678 subtitles, base_url, lang_code, lang_name, {})
3679 if not caption_track.get('isTranslatable'):
3680 continue
3944e7af 3681 for trans_code, trans_name in translation_languages.items():
3682 if not trans_code:
545cc85d 3683 continue
1235d333 3684 orig_trans_code = trans_code
ecdc9049 3685 if caption_track.get('kind') != 'asr':
07b47084 3686 if not get_translated_subs:
18e49408 3687 continue
ecdc9049 3688 trans_code += f'-{lang_code}'
a70635b8 3689 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 3690 # Add an "-orig" label to the original language so that it can be distinguished.
3691 # The subs are returned without "-orig" as well for compatibility
1235d333 3692 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3693 process_language(
d49669ac 3694 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3695 # Setting tlang=lang returns damaged subtitles.
d49669ac 3696 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3697 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 3698
3699 info['automatic_captions'] = automatic_captions
3700 info['subtitles'] = subtitles
7e72694b 3701
14f25df2 3702 parsed_url = urllib.parse.urlparse(url)
545cc85d 3703 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 3704 query = urllib.parse.parse_qs(component)
545cc85d 3705 for k, v in query.items():
3706 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3707 d_k += '_time'
3708 if d_k not in info and k in s_ks:
3709 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3710
3711 # Youtube Music Auto-generated description
822b9d9c 3712 if video_description:
1890fc63 3713 mobj = re.search(
3714 r'''(?xs)
3715 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3716 (?P<album>[^\n]+)
3717 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3718 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3719 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3720 .+\nAuto-generated\ by\ YouTube\.\s*$
3721 ''', video_description)
822b9d9c 3722 if mobj:
822b9d9c
RA
3723 release_year = mobj.group('release_year')
3724 release_date = mobj.group('release_date')
3725 if release_date:
3726 release_date = release_date.replace('-', '')
3727 if not release_year:
545cc85d 3728 release_year = release_date[:4]
3729 info.update({
3730 'album': mobj.group('album'.strip()),
3731 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3732 'track': mobj.group('track').strip(),
3733 'release_date': release_date,
cc2db878 3734 'release_year': int_or_none(release_year),
545cc85d 3735 })
7e72694b 3736
545cc85d 3737 initial_data = None
3738 if webpage:
56ba69e4 3739 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 3740 if not initial_data:
99e9e001 3741 query = {'videoId': video_id}
3742 query.update(self._get_checkok_params())
109dd3b2 3743 initial_data = self._extract_response(
3744 item_id=video_id, ep='next', fatal=False,
99e9e001 3745 ytcfg=master_ytcfg, query=query,
3746 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3747 note='Downloading initial data API JSON')
545cc85d 3748
0df111a3 3749 info['comment_count'] = traverse_obj(initial_data, (
3750 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3751 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3752 ), (
3753 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3754 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3755 ), expected_type=int_or_none, get_all=False)
3756
19a03940 3757 try: # This will error if there is no livechat
c60ee3a2 3758 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 3759 except (KeyError, IndexError, TypeError):
3760 pass
3761 else:
ecdc9049 3762 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 3763 # url is needed to set cookies
3764 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 3765 'video_id': video_id,
3766 'ext': 'json',
f6745c49 3767 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3768 }]
545cc85d 3769
3770 if initial_data:
7c365c21 3771 info['chapters'] = (
3772 self._extract_chapters_from_json(initial_data, duration)
3773 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 3774 or self._extract_chapters_from_description(video_description, duration)
7c365c21 3775 or None)
545cc85d 3776
17322130 3777 contents = traverse_obj(
3778 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3779 expected_type=list, default=[])
3780
3781 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3782 if vpir:
3783 stl = vpir.get('superTitleLink')
3784 if stl:
3785 stl = self._get_text(stl)
3786 if try_get(
3787 vpir,
3788 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3789 info['location'] = stl
3790 else:
affc4fef 3791 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 3792 if mobj:
545cc85d 3793 info.update({
17322130 3794 'series': mobj.group(1),
3795 'season_number': int(mobj.group(2)),
3796 'episode_number': int(mobj.group(3)),
545cc85d 3797 })
17322130 3798 for tlb in (try_get(
3799 vpir,
3800 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3801 list) or []):
3802 tbr = tlb.get('toggleButtonRenderer') or {}
3803 for getter, regex in [(
3804 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3805 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3806 lambda x: x['accessibility'],
3807 lambda x: x['accessibilityData']['accessibilityData'],
3808 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3809 label = (try_get(tbr, getter, dict) or {}).get('label')
3810 if label:
3811 mobj = re.match(regex, label)
3812 if mobj:
3813 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3814 break
17322130 3815 sbr_tooltip = try_get(
3816 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3817 if sbr_tooltip:
3818 like_count, dislike_count = sbr_tooltip.split(' / ')
3819 info.update({
3820 'like_count': str_to_int(like_count),
3821 'dislike_count': str_to_int(dislike_count),
3822 })
3823 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3824 if vsir:
3825 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3826 info.update({
3827 'channel': self._get_text(vor, 'title'),
3828 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3829
3830 rows = try_get(
3831 vsir,
3832 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3833 list) or []
3834 multiple_songs = False
3835 for row in rows:
3836 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3837 multiple_songs = True
3838 break
3839 for row in rows:
3840 mrr = row.get('metadataRowRenderer') or {}
3841 mrr_title = mrr.get('title')
3842 if not mrr_title:
3843 continue
3844 mrr_title = self._get_text(mrr, 'title')
3845 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3846 if mrr_title == 'License':
3847 info['license'] = mrr_contents_text
3848 elif not multiple_songs:
3849 if mrr_title == 'Album':
3850 info['album'] = mrr_contents_text
3851 elif mrr_title == 'Artist':
3852 info['artist'] = mrr_contents_text
3853 elif mrr_title == 'Song':
3854 info['track'] = mrr_contents_text
545cc85d 3855
3856 fallbacks = {
3857 'channel': 'uploader',
3858 'channel_id': 'uploader_id',
3859 'channel_url': 'uploader_url',
3860 }
992f9a73 3861
17322130 3862 # The upload date for scheduled, live and past live streams / premieres in microformats
3863 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3864 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3865 upload_date = (
3866 unified_strdate(get_first(microformats, 'uploadDate'))
3867 or unified_strdate(search_meta('uploadDate')))
3868 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
6e634cbe 3869 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date
17322130 3870 info['upload_date'] = upload_date
992f9a73 3871
545cc85d 3872 for to, frm in fallbacks.items():
3873 if not info.get(to):
3874 info[to] = info.get(frm)
3875
3876 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3877 v = info.get(s_k)
3878 if v:
3879 info[d_k] = v
b84071c0 3880
11f9be09 3881 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3882 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3883 is_membersonly = None
b28f8d24 3884 is_premium = None
c224251a
M
3885 if initial_data and is_private is not None:
3886 is_membersonly = False
b28f8d24 3887 is_premium = False
47193e02 3888 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3889 badge_labels = set()
3890 for content in contents:
3891 if not isinstance(content, dict):
3892 continue
3893 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3894 for badge_label in badge_labels:
3895 if badge_label.lower() == 'members only':
3896 is_membersonly = True
3897 elif badge_label.lower() == 'premium':
3898 is_premium = True
3899 elif badge_label.lower() == 'unlisted':
3900 is_unlisted = True
c224251a 3901
c224251a
M
3902 info['availability'] = self._availability(
3903 is_private=is_private,
b28f8d24 3904 needs_premium=is_premium,
c224251a
M
3905 needs_subscription=is_membersonly,
3906 needs_auth=info['age_limit'] >= 18,
3907 is_unlisted=None if is_private is None else is_unlisted)
3908
a2160aa4 3909 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3910
11f9be09 3911 self.mark_watched(video_id, player_responses)
d77ab8e2 3912
545cc85d 3913 return info
c5e8d7af 3914
a61fd4cf 3915
a6213a49 3916class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3917
182bda88 3918 @staticmethod
3919 def passthrough_smuggled_data(func):
3920 def _smuggle(entries, smuggled_data):
3921 for entry in entries:
3922 # TODO: Convert URL to music.youtube instead.
3923 # Do we need to passthrough any other smuggled_data?
3924 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3925 yield entry
3926
3927 @functools.wraps(func)
3928 def wrapper(self, url):
3929 url, smuggled_data = unsmuggle_url(url, {})
3930 if self.is_music_url(url):
3931 smuggled_data['is_music_url'] = True
3932 info_dict = func(self, url, smuggled_data)
3933 if smuggled_data and info_dict.get('entries'):
3934 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3935 return info_dict
3936 return wrapper
3937
a6213a49 3938 def _extract_channel_id(self, webpage):
3939 channel_id = self._html_search_meta(
3940 'channelId', webpage, 'channel id', default=None)
3941 if channel_id:
3942 return channel_id
3943 channel_url = self._html_search_meta(
3944 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3945 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3946 'twitter:app:url:googleplay'), webpage, 'channel url')
3947 return self._search_regex(
3948 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3949 channel_url, 'channel id')
15f6397c 3950
8bdd16b4 3951 @staticmethod
cd7c66cf 3952 def _extract_basic_item_renderer(item):
3953 # Modified from _extract_grid_item_renderer
201c1459 3954 known_basic_renderers = (
a17526e4 3955 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 3956 )
3957 for key, renderer in item.items():
201c1459 3958 if not isinstance(renderer, dict):
cd7c66cf 3959 continue
201c1459 3960 elif key in known_basic_renderers:
3961 return renderer
3962 elif key.startswith('grid') and key.endswith('Renderer'):
3963 return renderer
8bdd16b4 3964
8bdd16b4 3965 def _grid_entries(self, grid_renderer):
3966 for item in grid_renderer['items']:
3967 if not isinstance(item, dict):
39b62db1 3968 continue
cd7c66cf 3969 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3970 if not isinstance(renderer, dict):
3971 continue
052e1350 3972 title = self._get_text(renderer, 'title')
fe93e2c4 3973
8bdd16b4 3974 # playlist
3975 playlist_id = renderer.get('playlistId')
3976 if playlist_id:
3977 yield self.url_result(
3978 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3979 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3980 video_title=title)
201c1459 3981 continue
8bdd16b4 3982 # video
3983 video_id = renderer.get('videoId')
3984 if video_id:
3985 yield self._extract_video(renderer)
201c1459 3986 continue
8bdd16b4 3987 # channel
3988 channel_id = renderer.get('channelId')
3989 if channel_id:
8bdd16b4 3990 yield self.url_result(
3991 'https://www.youtube.com/channel/%s' % channel_id,
3992 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3993 continue
3994 # generic endpoint URL support
3995 ep_url = urljoin('https://www.youtube.com/', try_get(
3996 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 3997 str))
201c1459 3998 if ep_url:
3999 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4000 if ie.suitable(ep_url):
4001 yield self.url_result(
4002 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4003 break
8bdd16b4 4004
16aa9ea4 4005 def _music_reponsive_list_entry(self, renderer):
4006 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4007 if video_id:
4008 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4009 ie=YoutubeIE.ie_key(), video_id=video_id)
4010 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4011 if playlist_id:
4012 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4013 if video_id:
4014 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4015 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4016 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4017 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4018 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4019 if browse_id:
4020 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4021 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4022
3d3dddc9 4023 def _shelf_entries_from_content(self, shelf_renderer):
4024 content = shelf_renderer.get('content')
4025 if not isinstance(content, dict):
8bdd16b4 4026 return
cd7c66cf 4027 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4028 if renderer:
4029 # TODO: add support for nested playlists so each shelf is processed
4030 # as separate playlist
4031 # TODO: this includes only first N items
86e5f3ed 4032 yield from self._grid_entries(renderer)
3d3dddc9 4033 renderer = content.get('horizontalListRenderer')
4034 if renderer:
4035 # TODO
4036 pass
8bdd16b4 4037
29f7c58a 4038 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4039 ep = try_get(
4040 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4041 str)
8bdd16b4 4042 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4043 if shelf_url:
29f7c58a 4044 # Skipping links to another channels, note that checking for
4045 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4046 # will not work
4047 if skip_channels and '/channels?' in shelf_url:
4048 return
052e1350 4049 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4050 yield self.url_result(shelf_url, video_title=title)
4051 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4052 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4053
8bdd16b4 4054 def _playlist_entries(self, video_list_renderer):
4055 for content in video_list_renderer['contents']:
4056 if not isinstance(content, dict):
4057 continue
4058 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4059 if not isinstance(renderer, dict):
4060 continue
4061 video_id = renderer.get('videoId')
4062 if not video_id:
4063 continue
4064 yield self._extract_video(renderer)
07aeced6 4065
3462ffa8 4066 def _rich_entries(self, rich_grid_renderer):
4067 renderer = try_get(
70d5c17b 4068 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 4069 video_id = renderer.get('videoId')
4070 if not video_id:
4071 return
4072 yield self._extract_video(renderer)
4073
8bdd16b4 4074 def _video_entry(self, video_renderer):
4075 video_id = video_renderer.get('videoId')
4076 if video_id:
4077 return self._extract_video(video_renderer)
dacb3a86 4078
ad210f4f 4079 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4080 url = urljoin('https://youtube.com', traverse_obj(
4081 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4082 if url:
4083 return self.url_result(
4084 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4085
8bdd16b4 4086 def _post_thread_entries(self, post_thread_renderer):
4087 post_renderer = try_get(
4088 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4089 if not post_renderer:
4090 return
4091 # video attachment
4092 video_renderer = try_get(
895b0931 4093 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4094 video_id = video_renderer.get('videoId')
4095 if video_id:
4096 entry = self._extract_video(video_renderer)
8bdd16b4 4097 if entry:
4098 yield entry
895b0931 4099 # playlist attachment
4100 playlist_id = try_get(
14f25df2 4101 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4102 if playlist_id:
4103 yield self.url_result(
e28f1c0a 4104 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4105 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4106 # inline video links
4107 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4108 for run in runs:
4109 if not isinstance(run, dict):
4110 continue
4111 ep_url = try_get(
14f25df2 4112 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4113 if not ep_url:
4114 continue
4115 if not YoutubeIE.suitable(ep_url):
4116 continue
4117 ep_video_id = YoutubeIE._match_id(ep_url)
4118 if video_id == ep_video_id:
4119 continue
895b0931 4120 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4121
8bdd16b4 4122 def _post_thread_continuation_entries(self, post_thread_continuation):
4123 contents = post_thread_continuation.get('contents')
4124 if not isinstance(contents, list):
4125 return
4126 for content in contents:
4127 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4128 if isinstance(renderer, dict):
4129 yield from self._post_thread_entries(renderer)
8bdd16b4 4130 continue
6b0b0a28 4131 renderer = content.get('videoRenderer')
4132 if isinstance(renderer, dict):
4133 yield self._video_entry(renderer)
07aeced6 4134
39ed931e 4135 r''' # unused
4136 def _rich_grid_entries(self, contents):
4137 for content in contents:
4138 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4139 if video_renderer:
4140 entry = self._video_entry(video_renderer)
4141 if entry:
4142 yield entry
4143 '''
52efa4b3 4144
a6213a49 4145 def _extract_entries(self, parent_renderer, continuation_list):
4146 # continuation_list is modified in-place with continuation_list = [continuation_token]
4147 continuation_list[:] = [None]
4148 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4149 for content in contents:
4150 if not isinstance(content, dict):
4151 continue
16aa9ea4 4152 is_renderer = traverse_obj(
4153 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4154 expected_type=dict)
a6213a49 4155 if not is_renderer:
4156 renderer = content.get('richItemRenderer')
4157 if renderer:
4158 for entry in self._rich_entries(renderer):
4159 yield entry
4160 continuation_list[0] = self._extract_continuation(parent_renderer)
4161 continue
4162 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4163 for isr_content in isr_contents:
4164 if not isinstance(isr_content, dict):
8bdd16b4 4165 continue
69184e41 4166
a6213a49 4167 known_renderers = {
4168 'playlistVideoListRenderer': self._playlist_entries,
4169 'gridRenderer': self._grid_entries,
a17526e4 4170 'reelShelfRenderer': self._grid_entries,
4171 'shelfRenderer': self._shelf_entries,
16aa9ea4 4172 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4173 'backstagePostThreadRenderer': self._post_thread_entries,
4174 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4175 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4176 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4177 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4178 }
4179 for key, renderer in isr_content.items():
4180 if key not in known_renderers:
4181 continue
4182 for entry in known_renderers[key](renderer):
4183 if entry:
4184 yield entry
4185 continuation_list[0] = self._extract_continuation(renderer)
4186 break
70d5c17b 4187
4188 if not continuation_list[0]:
a6213a49 4189 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4190
a6213a49 4191 if not continuation_list[0]:
4192 continuation_list[0] = self._extract_continuation(parent_renderer)
4193
4194 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4195 continuation_list = [None]
4196 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4197 tab_content = try_get(tab, lambda x: x['content'], dict)
4198 if not tab_content:
4199 return
3462ffa8 4200 parent_renderer = (
29f7c58a 4201 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4202 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4203 yield from extract_entries(parent_renderer)
3462ffa8 4204 continuation = continuation_list[0]
d069eca7 4205
8bdd16b4 4206 for page_num in itertools.count(1):
4207 if not continuation:
4208 break
99e9e001 4209 headers = self.generate_api_headers(
4210 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4211 response = self._extract_response(
86e5f3ed 4212 item_id=f'{item_id} page {page_num}',
fe93e2c4 4213 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4214 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4215
4216 if not response:
8bdd16b4 4217 break
ac56cf38 4218 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4219 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4220 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4221
69184e41 4222 known_continuation_renderers = {
4223 'playlistVideoListContinuation': self._playlist_entries,
4224 'gridContinuation': self._grid_entries,
4225 'itemSectionContinuation': self._post_thread_continuation_entries,
4226 'sectionListContinuation': extract_entries, # for feeds
4227 }
8bdd16b4 4228 continuation_contents = try_get(
69184e41 4229 response, lambda x: x['continuationContents'], dict) or {}
4230 continuation_renderer = None
4231 for key, value in continuation_contents.items():
4232 if key not in known_continuation_renderers:
3462ffa8 4233 continue
69184e41 4234 continuation_renderer = value
4235 continuation_list = [None]
86e5f3ed 4236 yield from known_continuation_renderers[key](continuation_renderer)
69184e41 4237 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4238 break
4239 if continuation_renderer:
4240 continue
c5e8d7af 4241
a1b535bd 4242 known_renderers = {
e4b98809 4243 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4244 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4245 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4246 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4247 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4248 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4249 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4250 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4251 }
cce889b9 4252 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4253 continuation_items = try_get(
cce889b9 4254 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4255 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4256 video_items_renderer = None
4257 for key, value in continuation_item.items():
4258 if key not in known_renderers:
8bdd16b4 4259 continue
a1b535bd 4260 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4261 continuation_list = [None]
86e5f3ed 4262 yield from known_renderers[key][0](video_items_renderer)
9ba5705a 4263 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4264 break
4265 if video_items_renderer:
4266 continue
8bdd16b4 4267 break
9558dcec 4268
8bdd16b4 4269 @staticmethod
7c219ea6 4270 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4271 for tab in tabs:
cd684175 4272 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4273 if renderer.get('selected') is True:
4274 return renderer
2b3c2546 4275 else:
7c219ea6 4276 if fatal:
4277 raise ExtractorError('Unable to find selected tab')
b82f815f 4278
61d3665d 4279 def _extract_uploader(self, data):
8bdd16b4 4280 uploader = {}
61d3665d 4281 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
47193e02 4282 owner = try_get(
4283 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4284 if owner:
61d3665d 4285 owner_text = owner.get('text')
4286 uploader['uploader'] = self._search_regex(
4287 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
47193e02 4288 uploader['uploader_id'] = try_get(
14f25df2 4289 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], str)
47193e02 4290 uploader['uploader_url'] = urljoin(
4291 'https://www.youtube.com/',
14f25df2 4292 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
9c3fe2ef 4293 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4294
ac56cf38 4295 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4296 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4297 tags = []
b60419c5 4298
8bdd16b4 4299 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4300 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4301 renderer = try_get(
4302 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4303 if renderer:
b60419c5 4304 channel_name = renderer.get('title')
4305 channel_url = renderer.get('channelUrl')
4306 channel_id = renderer.get('externalId')
39ed931e 4307 else:
64c0d954 4308 renderer = try_get(
4309 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4310
8bdd16b4 4311 if renderer:
4312 title = renderer.get('title')
ecc97af3 4313 description = renderer.get('description', '')
b60419c5 4314 playlist_id = channel_id
4315 tags = renderer.get('keywords', '').split()
b60419c5 4316
301d07fc 4317 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4318 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4319 def _get_uncropped(url):
4320 return url_or_none((url or '').split('=')[0] + '=s0')
4321
4322 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4323 if avatar_thumbnails:
4324 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4325 if uncropped_avatar:
4326 avatar_thumbnails.append({
4327 'url': uncropped_avatar,
4328 'id': 'avatar_uncropped',
4329 'preference': 1
4330 })
4331
4332 channel_banners = self._extract_thumbnails(
4333 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4334 for banner in channel_banners:
4335 banner['preference'] = -10
4336
4337 if channel_banners:
4338 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4339 if uncropped_banner:
4340 channel_banners.append({
4341 'url': uncropped_banner,
4342 'id': 'banner_uncropped',
4343 'preference': -5
4344 })
4345
4346 primary_thumbnails = self._extract_thumbnails(
a17526e4 4347 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4348
3462ffa8 4349 if playlist_id is None:
70d5c17b 4350 playlist_id = item_id
f0d785d3 4351
4352 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4353 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4354 if title is None:
f0d785d3 4355 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4356 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4357 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4358
b60419c5 4359 metadata = {
4360 'playlist_id': playlist_id,
4361 'playlist_title': title,
4362 'playlist_description': description,
4363 'uploader': channel_name,
4364 'uploader_id': channel_id,
4365 'uploader_url': channel_url,
301d07fc 4366 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4367 'tags': tags,
f0d785d3 4368 'view_count': self._get_count(playlist_stats, 1),
4369 'availability': self._extract_availability(data),
4370 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4371 'playlist_count': self._get_count(playlist_stats, 0),
4372 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4373 }
4374 if not channel_id:
4375 metadata.update(self._extract_uploader(data))
4376 metadata.update({
4377 'channel': metadata['uploader'],
4378 'channel_id': metadata['uploader_id'],
4379 'channel_url': metadata['uploader_url']})
4380 return self.playlist_result(
d069eca7 4381 self._entries(
ac56cf38 4382 selected_tab, playlist_id, ytcfg,
4383 self._extract_account_syncid(ytcfg, data),
4384 self._extract_visitor_data(data, ytcfg)),
b60419c5 4385 **metadata)
73c4ac2c 4386
6e634cbe 4387 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4388 first_id = last_id = response = None
2be71994 4389 for page_num in itertools.count(1):
cd7c66cf 4390 videos = list(self._playlist_entries(playlist))
4391 if not videos:
4392 return
2be71994 4393 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4394 if start >= len(videos):
4395 return
24146491 4396 yield from videos[start:]
2be71994 4397 first_id = first_id or videos[0]['id']
4398 last_id = videos[-1]['id']
79360d99 4399 watch_endpoint = try_get(
4400 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4401 headers = self.generate_api_headers(
4402 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4403 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4404 query = {
4405 'playlistId': playlist_id,
4406 'videoId': watch_endpoint.get('videoId') or last_id,
4407 'index': watch_endpoint.get('index') or len(videos),
4408 'params': watch_endpoint.get('params') or 'OAE%3D'
4409 }
4410 response = self._extract_response(
4411 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4412 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4413 check_get_keys='contents'
4414 )
cd7c66cf 4415 playlist = try_get(
79360d99 4416 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4417
ac56cf38 4418 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4419 title = playlist.get('title') or try_get(
14f25df2 4420 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4421 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4422
4423 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4424 playlist_url = urljoin(url, try_get(
4425 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4426 str))
6e634cbe 4427
4428 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4429 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4430 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4431
4432 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4433 return self.url_result(
4434 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4435 video_title=title)
cd7c66cf 4436
8bdd16b4 4437 return self.playlist_result(
6e634cbe 4438 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4439 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4440
47193e02 4441 def _extract_availability(self, data):
4442 """
4443 Gets the availability of a given playlist/tab.
4444 Note: Unless YouTube tells us explicitly, we do not assume it is public
4445 @param data: response
4446 """
4447 is_private = is_unlisted = None
4448 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4449 badge_labels = self._extract_badges(renderer)
4450
4451 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4452 privacy_dropdown_entries = try_get(
4453 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4454 for renderer_dict in privacy_dropdown_entries:
4455 is_selected = try_get(
4456 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4457 if not is_selected:
4458 continue
052e1350 4459 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4460 if label:
4461 badge_labels.add(label.lower())
4462 break
4463
4464 for badge_label in badge_labels:
4465 if badge_label == 'unlisted':
4466 is_unlisted = True
4467 elif badge_label == 'private':
4468 is_private = True
4469 elif badge_label == 'public':
4470 is_unlisted = is_private = False
4471 return self._availability(is_private, False, False, False, is_unlisted)
4472
4473 @staticmethod
4474 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4475 sidebar_renderer = try_get(
4476 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4477 for item in sidebar_renderer:
4478 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4479 if renderer:
4480 return renderer
4481
ac56cf38 4482 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4483 """
4484 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4485 """
5d342002 4486 browse_id = params = None
47193e02 4487 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4488 if not renderer:
4489 return
4490 menu_renderer = try_get(
4491 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4492 for menu_item in menu_renderer:
4493 if not isinstance(menu_item, dict):
358de58c 4494 continue
47193e02 4495 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4496 text = try_get(
14f25df2 4497 nav_item_renderer, lambda x: x['text']['simpleText'], str)
47193e02 4498 if not text or text.lower() != 'show unavailable videos':
4499 continue
4500 browse_endpoint = try_get(
4501 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4502 browse_id = browse_endpoint.get('browseId')
4503 params = browse_endpoint.get('params')
4504 break
5d342002 4505
11f9be09 4506 headers = self.generate_api_headers(
99e9e001 4507 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4508 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4509 query = {
4510 'params': params or 'wgYCCAA=',
4511 'browseId': browse_id or 'VL%s' % item_id
4512 }
4513 return self._extract_response(
4514 item_id=item_id, headers=headers, query=query,
fe93e2c4 4515 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4516 note='Downloading API JSON with unavailable videos')
358de58c 4517
2762dbb1 4518 @functools.cached_property
a25bca9f 4519 def skip_webpage(self):
4520 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4521
ac56cf38 4522 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 4523 webpage, data = None, None
4524 for retry in self.RetryManager(fatal=fatal):
ac56cf38 4525 try:
be5c1ae8 4526 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 4527 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4528 except ExtractorError as e:
4529 if isinstance(e.cause, network_exceptions):
14f25df2 4530 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 4531 retry.error = e
4532 continue
4533 self._error_or_warning(e, fatal=fatal)
14fdfea9 4534 break
ac56cf38 4535
be5c1ae8 4536 try:
4537 self._extract_and_report_alerts(data)
4538 except ExtractorError as e:
4539 self._error_or_warning(e, fatal=fatal)
4540 break
ac56cf38 4541
be5c1ae8 4542 # Sometimes youtube returns a webpage with incomplete ytInitialData
4543 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4544 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4545 retry.error = ExtractorError('Incomplete yt initial data received')
4546 continue
ac56cf38 4547
cd7c66cf 4548 return webpage, data
4549
a25bca9f 4550 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4551 """Use if failed to extract ytcfg (and data) from initial webpage"""
4552 if not ytcfg and self.is_authenticated:
4553 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4554 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4555 raise ExtractorError(
4556 f'{msg}. If you are not downloading private content, or '
4557 'your cookies are only for the first account and channel,'
4558 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4559 expected=True)
4560 self.report_warning(msg, only_once=True)
4561
ac56cf38 4562 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4563 data = None
a25bca9f 4564 if not self.skip_webpage:
ac56cf38 4565 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4566 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4567 # Reject webpage data if redirected to home page without explicitly requesting
4568 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4569 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4570 if (url != 'https://www.youtube.com/feed/recommended'
4571 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4572 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4573 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4574 if fatal:
4575 raise ExtractorError(msg, expected=True)
4576 self.report_warning(msg, only_once=True)
ac56cf38 4577 if not data:
a25bca9f 4578 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4579 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4580 return data, ytcfg
4581
4582 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4583 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4584 resolve_response = self._extract_response(
4585 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4586 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4587 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4588 for ep_key, ep in endpoints.items():
4589 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4590 if params:
4591 return self._extract_response(
4592 item_id=item_id, query=params, ep=ep, headers=headers,
4593 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4594 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4595 err_note = 'Failed to resolve url (does the playlist exist?)'
4596 if fatal:
4597 raise ExtractorError(err_note, expected=True)
4598 self.report_warning(err_note, item_id)
4599
a6213a49 4600 _SEARCH_PARAMS = None
4601
af5c1c55 4602 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4603 data = {'query': query}
4604 if params is NO_DEFAULT:
4605 params = self._SEARCH_PARAMS
4606 if params:
4607 data['params'] = params
16aa9ea4 4608
4609 content_keys = (
4610 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4611 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4612 # ytmusic search
4613 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4614 ('continuationContents', ),
4615 )
a25bca9f 4616 display_id = f'query "{query}"'
86e5f3ed 4617 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4618 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4619 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4620
a61fd4cf 4621 continuation_list = [None]
a25bca9f 4622 search = None
a6213a49 4623 for page_num in itertools.count(1):
a61fd4cf 4624 data.update(continuation_list[0] or {})
a25bca9f 4625 headers = self.generate_api_headers(
4626 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4627 search = self._extract_response(
a25bca9f 4628 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4629 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4630 slr_contents = traverse_obj(search, *content_keys)
4631 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4632 if not continuation_list[0]:
a6213a49 4633 break
4634
4635
4636class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4637 IE_DESC = 'YouTube Tabs'
4638 _VALID_URL = r'''(?x:
4639 https?://
4640 (?:\w+\.)?
4641 (?:
4642 youtube(?:kids)?\.com|
4643 %(invidious)s
4644 )/
4645 (?:
4646 (?P<channel_type>channel|c|user|browse)/|
4647 (?P<not_channel>
4648 feed/|hashtag/|
4649 (?:playlist|watch)\?.*?\blist=
4650 )|
4651 (?!(?:%(reserved_names)s)\b) # Direct URLs
4652 )
4653 (?P<id>[^/?\#&]+)
4654 )''' % {
4655 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4656 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4657 }
4658 IE_NAME = 'youtube:tab'
4659
4660 _TESTS = [{
4661 'note': 'playlists, multipage',
4662 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4663 'playlist_mincount': 94,
4664 'info_dict': {
4665 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4666 'title': 'Igor Kleiner - Playlists',
a6213a49 4667 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4668 'uploader': 'Igor Kleiner',
a6213a49 4669 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4670 'channel': 'Igor Kleiner',
4671 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4672 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4673 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4674 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4675 'channel_follower_count': int
a6213a49 4676 },
4677 }, {
4678 'note': 'playlists, multipage, different order',
4679 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4680 'playlist_mincount': 94,
4681 'info_dict': {
4682 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4683 'title': 'Igor Kleiner - Playlists',
a6213a49 4684 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4685 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4686 'uploader': 'Igor Kleiner',
4687 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4688 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4689 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4690 'channel': 'Igor Kleiner',
4691 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4692 'channel_follower_count': int
a6213a49 4693 },
4694 }, {
4695 'note': 'playlists, series',
4696 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4697 'playlist_mincount': 5,
4698 'info_dict': {
4699 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4700 'title': '3Blue1Brown - Playlists',
4701 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4702 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4703 'uploader': '3Blue1Brown',
976ae3ea 4704 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4705 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4706 'channel': '3Blue1Brown',
4707 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4708 'tags': ['Mathematics'],
6c73052c 4709 'channel_follower_count': int
a6213a49 4710 },
4711 }, {
4712 'note': 'playlists, singlepage',
4713 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4714 'playlist_mincount': 4,
4715 'info_dict': {
4716 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4717 'title': 'ThirstForScience - Playlists',
4718 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4719 'uploader': 'ThirstForScience',
4720 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4721 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4722 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4723 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4724 'tags': 'count:13',
4725 'channel': 'ThirstForScience',
6c73052c 4726 'channel_follower_count': int
a6213a49 4727 }
4728 }, {
4729 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4730 'only_matching': True,
4731 }, {
4732 'note': 'basic, single video playlist',
4733 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4734 'info_dict': {
4735 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4736 'uploader': 'Sergey M.',
4737 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4738 'title': 'youtube-dl public playlist',
976ae3ea 4739 'description': '',
4740 'tags': [],
4741 'view_count': int,
4742 'modified_date': '20201130',
4743 'channel': 'Sergey M.',
4744 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4745 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4746 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4747 },
4748 'playlist_count': 1,
4749 }, {
4750 'note': 'empty playlist',
4751 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4752 'info_dict': {
4753 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4754 'uploader': 'Sergey M.',
4755 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4756 'title': 'youtube-dl empty playlist',
976ae3ea 4757 'tags': [],
4758 'channel': 'Sergey M.',
4759 'description': '',
4760 'modified_date': '20160902',
4761 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4762 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4763 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4764 },
4765 'playlist_count': 0,
4766 }, {
4767 'note': 'Home tab',
4768 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4769 'info_dict': {
4770 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4771 'title': 'lex will - Home',
4772 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4773 'uploader': 'lex will',
4774 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4775 'channel': 'lex will',
4776 'tags': ['bible', 'history', 'prophesy'],
4777 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4778 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4779 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4780 'channel_follower_count': int
a6213a49 4781 },
4782 'playlist_mincount': 2,
4783 }, {
4784 'note': 'Videos tab',
4785 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4786 'info_dict': {
4787 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4788 'title': 'lex will - Videos',
4789 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4790 'uploader': 'lex will',
4791 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4792 'tags': ['bible', 'history', 'prophesy'],
4793 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4794 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4795 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4796 'channel': 'lex will',
6c73052c 4797 'channel_follower_count': int
a6213a49 4798 },
4799 'playlist_mincount': 975,
4800 }, {
4801 'note': 'Videos tab, sorted by popular',
4802 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4803 'info_dict': {
4804 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4805 'title': 'lex will - Videos',
4806 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4807 'uploader': 'lex will',
4808 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4809 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4810 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4811 'channel': 'lex will',
4812 'tags': ['bible', 'history', 'prophesy'],
4813 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4814 'channel_follower_count': int
a6213a49 4815 },
4816 'playlist_mincount': 199,
4817 }, {
4818 'note': 'Playlists tab',
4819 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4820 'info_dict': {
4821 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4822 'title': 'lex will - Playlists',
4823 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4824 'uploader': 'lex will',
4825 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4826 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4827 'channel': 'lex will',
4828 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4829 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4830 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4831 'channel_follower_count': int
a6213a49 4832 },
4833 'playlist_mincount': 17,
4834 }, {
4835 'note': 'Community tab',
4836 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4837 'info_dict': {
4838 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4839 'title': 'lex will - Community',
4840 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4841 'uploader': 'lex will',
4842 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4843 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4844 'channel': 'lex will',
4845 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4846 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4847 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4848 'channel_follower_count': int
a6213a49 4849 },
4850 'playlist_mincount': 18,
4851 }, {
4852 'note': 'Channels tab',
4853 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4854 'info_dict': {
4855 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4856 'title': 'lex will - Channels',
4857 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4858 'uploader': 'lex will',
4859 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4860 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4861 'channel': 'lex will',
4862 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4863 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4864 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4865 'channel_follower_count': int
a6213a49 4866 },
4867 'playlist_mincount': 12,
4868 }, {
4869 'note': 'Search tab',
4870 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4871 'playlist_mincount': 40,
4872 'info_dict': {
4873 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4874 'title': '3Blue1Brown - Search - linear algebra',
4875 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4876 'uploader': '3Blue1Brown',
4877 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4878 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4879 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4880 'tags': ['Mathematics'],
4881 'channel': '3Blue1Brown',
4882 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4883 'channel_follower_count': int
a6213a49 4884 },
4885 }, {
4886 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4887 'only_matching': True,
4888 }, {
4889 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4890 'only_matching': True,
4891 }, {
4892 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4893 'only_matching': True,
4894 }, {
4895 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4896 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4897 'info_dict': {
4898 'title': '29C3: Not my department',
4899 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4900 'uploader': 'Christiaan008',
4901 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4902 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4903 'tags': [],
4904 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4905 'view_count': int,
4906 'modified_date': '20150605',
4907 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4908 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4909 'channel': 'Christiaan008',
a6213a49 4910 },
4911 'playlist_count': 96,
4912 }, {
4913 'note': 'Large playlist',
4914 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4915 'info_dict': {
4916 'title': 'Uploads from Cauchemar',
4917 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4918 'uploader': 'Cauchemar',
4919 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4920 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4921 'tags': [],
4922 'modified_date': r're:\d{8}',
4923 'channel': 'Cauchemar',
4924 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4925 'view_count': int,
4926 'description': '',
4927 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4928 },
4929 'playlist_mincount': 1123,
976ae3ea 4930 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4931 }, {
4932 'note': 'even larger playlist, 8832 videos',
4933 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4934 'only_matching': True,
4935 }, {
4936 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4937 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4938 'info_dict': {
4939 'title': 'Uploads from Interstellar Movie',
4940 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4941 'uploader': 'Interstellar Movie',
4942 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4943 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4944 'tags': [],
4945 'view_count': int,
4946 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4947 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4948 'channel': 'Interstellar Movie',
4949 'description': '',
4950 'modified_date': r're:\d{8}',
a6213a49 4951 },
4952 'playlist_mincount': 21,
4953 }, {
4954 'note': 'Playlist with "show unavailable videos" button',
4955 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4956 'info_dict': {
4957 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4958 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4959 'uploader': 'Phim Siêu Nhân Nhật Bản',
4960 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4961 'view_count': int,
4962 'channel': 'Phim Siêu Nhân Nhật Bản',
4963 'tags': [],
4964 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4965 'description': '',
4966 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4967 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4968 'modified_date': r're:\d{8}',
a6213a49 4969 },
4970 'playlist_mincount': 200,
976ae3ea 4971 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4972 }, {
4973 'note': 'Playlist with unavailable videos in page 7',
4974 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4975 'info_dict': {
4976 'title': 'Uploads from BlankTV',
4977 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4978 'uploader': 'BlankTV',
4979 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4980 'channel': 'BlankTV',
4981 'channel_url': 'https://www.youtube.com/c/blanktv',
4982 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4983 'view_count': int,
4984 'tags': [],
4985 'uploader_url': 'https://www.youtube.com/c/blanktv',
4986 'modified_date': r're:\d{8}',
4987 'description': '',
a6213a49 4988 },
4989 'playlist_mincount': 1000,
976ae3ea 4990 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4991 }, {
4992 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4993 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4994 'info_dict': {
4995 'title': 'Data Analysis with Dr Mike Pound',
4996 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4997 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4998 'uploader': 'Computerphile',
4999 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5000 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5001 'tags': [],
5002 'view_count': int,
5003 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5004 'channel_url': 'https://www.youtube.com/user/Computerphile',
5005 'channel': 'Computerphile',
a6213a49 5006 },
5007 'playlist_mincount': 11,
5008 }, {
5009 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5010 'only_matching': True,
5011 }, {
5012 'note': 'Playlist URL that does not actually serve a playlist',
5013 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5014 'info_dict': {
5015 'id': 'FqZTN594JQw',
5016 'ext': 'webm',
5017 'title': "Smiley's People 01 detective, Adventure Series, Action",
5018 'uploader': 'STREEM',
5019 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5020 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5021 'upload_date': '20150526',
5022 'license': 'Standard YouTube License',
5023 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5024 'categories': ['People & Blogs'],
5025 'tags': list,
5026 'view_count': int,
5027 'like_count': int,
a6213a49 5028 },
5029 'params': {
5030 'skip_download': True,
5031 },
5032 'skip': 'This video is not available.',
5033 'add_ie': [YoutubeIE.ie_key()],
5034 }, {
5035 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5036 'only_matching': True,
5037 }, {
5038 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5039 'only_matching': True,
5040 }, {
5041 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5042 'info_dict': {
12a1b225 5043 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5044 'ext': 'mp4',
976ae3ea 5045 'title': str,
a6213a49 5046 'uploader': 'Sky News',
5047 'uploader_id': 'skynews',
5048 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5049 'upload_date': r're:\d{8}',
976ae3ea 5050 'description': str,
a6213a49 5051 'categories': ['News & Politics'],
5052 'tags': list,
5053 'like_count': int,
6c73052c 5054 'release_timestamp': 1642502819,
976ae3ea 5055 'channel': 'Sky News',
5056 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5057 'age_limit': 0,
5058 'view_count': int,
6c73052c 5059 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 5060 'playable_in_embed': True,
6c73052c 5061 'release_date': '20220118',
976ae3ea 5062 'availability': 'public',
5063 'live_status': 'is_live',
5064 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 5065 'channel_follower_count': int
a6213a49 5066 },
5067 'params': {
5068 'skip_download': True,
5069 },
976ae3ea 5070 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5071 }, {
5072 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5073 'info_dict': {
5074 'id': 'a48o2S1cPoo',
5075 'ext': 'mp4',
5076 'title': 'The Young Turks - Live Main Show',
5077 'uploader': 'The Young Turks',
5078 'uploader_id': 'TheYoungTurks',
5079 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5080 'upload_date': '20150715',
5081 'license': 'Standard YouTube License',
5082 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5083 'categories': ['News & Politics'],
5084 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5085 'like_count': int,
a6213a49 5086 },
5087 'params': {
5088 'skip_download': True,
5089 },
5090 'only_matching': True,
5091 }, {
5092 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5093 'only_matching': True,
5094 }, {
5095 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5096 'only_matching': True,
5097 }, {
5098 'note': 'A channel that is not live. Should raise error',
5099 'url': 'https://www.youtube.com/user/numberphile/live',
5100 'only_matching': True,
5101 }, {
5102 'url': 'https://www.youtube.com/feed/trending',
5103 'only_matching': True,
5104 }, {
5105 'url': 'https://www.youtube.com/feed/library',
5106 'only_matching': True,
5107 }, {
5108 'url': 'https://www.youtube.com/feed/history',
5109 'only_matching': True,
5110 }, {
5111 'url': 'https://www.youtube.com/feed/subscriptions',
5112 'only_matching': True,
5113 }, {
5114 'url': 'https://www.youtube.com/feed/watch_later',
5115 'only_matching': True,
5116 }, {
5117 'note': 'Recommended - redirects to home page.',
5118 'url': 'https://www.youtube.com/feed/recommended',
5119 'only_matching': True,
5120 }, {
5121 'note': 'inline playlist with not always working continuations',
5122 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5123 'only_matching': True,
5124 }, {
5125 'url': 'https://www.youtube.com/course',
5126 'only_matching': True,
5127 }, {
5128 'url': 'https://www.youtube.com/zsecurity',
5129 'only_matching': True,
5130 }, {
5131 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5132 'only_matching': True,
5133 }, {
5134 'url': 'https://www.youtube.com/TheYoungTurks/live',
5135 'only_matching': True,
5136 }, {
5137 'url': 'https://www.youtube.com/hashtag/cctv9',
5138 'info_dict': {
5139 'id': 'cctv9',
5140 'title': '#cctv9',
976ae3ea 5141 'tags': [],
a6213a49 5142 },
5143 'playlist_mincount': 350,
5144 }, {
5145 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5146 'only_matching': True,
5147 }, {
5148 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5149 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5150 'only_matching': True
5151 }, {
5152 'note': '/browse/ should redirect to /channel/',
5153 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5154 'only_matching': True
5155 }, {
5156 'note': 'VLPL, should redirect to playlist?list=PL...',
5157 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5158 'info_dict': {
5159 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5160 'uploader': 'NoCopyrightSounds',
5161 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5162 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5163 'title': 'NCS : All Releases 💿',
976ae3ea 5164 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5165 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5166 'modified_date': r're:\d{8}',
5167 'view_count': int,
5168 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5169 'tags': [],
5170 'channel': 'NoCopyrightSounds',
a6213a49 5171 },
5172 'playlist_mincount': 166,
976ae3ea 5173 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5174 }, {
5175 'note': 'Topic, should redirect to playlist?list=UU...',
5176 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5177 'info_dict': {
5178 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5179 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5180 'title': 'Uploads from Royalty Free Music - Topic',
5181 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5182 'tags': [],
5183 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5184 'channel': 'Royalty Free Music - Topic',
5185 'view_count': int,
5186 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5187 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5188 'modified_date': r're:\d{8}',
5189 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5190 'description': '',
a6213a49 5191 },
5192 'expected_warnings': [
a6213a49 5193 'The URL does not have a videos tab',
976ae3ea 5194 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5195 ],
5196 'playlist_mincount': 101,
5197 }, {
5198 'note': 'Topic without a UU playlist',
5199 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5200 'info_dict': {
5201 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5202 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5203 'tags': [],
a6213a49 5204 },
5205 'expected_warnings': [
976ae3ea 5206 'the playlist redirect gave error',
a6213a49 5207 ],
5208 'playlist_mincount': 9,
5209 }, {
5210 'note': 'Youtube music Album',
5211 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5212 'info_dict': {
5213 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5214 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5215 'tags': [],
5216 'view_count': int,
5217 'description': '',
5218 'availability': 'unlisted',
5219 'modified_date': r're:\d{8}',
a6213a49 5220 },
5221 'playlist_count': 50,
5222 }, {
5223 'note': 'unlisted single video playlist',
5224 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5225 'info_dict': {
5226 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5227 'uploader': 'colethedj',
5228 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5229 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5230 'availability': 'unlisted',
5231 'tags': [],
12a1b225 5232 'modified_date': '20220418',
976ae3ea 5233 'channel': 'colethedj',
5234 'view_count': int,
5235 'description': '',
5236 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5237 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5238 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5239 },
5240 'playlist_count': 1,
5241 }, {
5242 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5243 'url': 'https://www.youtube.com/feed/recommended',
5244 'info_dict': {
5245 'id': 'recommended',
5246 'title': 'recommended',
6c73052c 5247 'tags': [],
a6213a49 5248 },
5249 'playlist_mincount': 50,
5250 'params': {
5251 'skip_download': True,
5252 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5253 },
5254 }, {
5255 'note': 'API Fallback: /videos tab, sorted by oldest first',
5256 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5257 'info_dict': {
5258 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5259 'title': 'Cody\'sLab - Videos',
5260 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5261 'uploader': 'Cody\'sLab',
5262 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5263 'channel': 'Cody\'sLab',
5264 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5265 'tags': [],
5266 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5267 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5268 'channel_follower_count': int
a6213a49 5269 },
5270 'playlist_mincount': 650,
5271 'params': {
5272 'skip_download': True,
5273 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5274 },
5275 }, {
5276 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5277 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5278 'info_dict': {
5279 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5280 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5281 'title': 'Uploads from Royalty Free Music - Topic',
5282 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5283 'modified_date': r're:\d{8}',
5284 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5285 'description': '',
5286 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5287 'tags': [],
5288 'channel': 'Royalty Free Music - Topic',
5289 'view_count': int,
5290 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5291 },
5292 'expected_warnings': [
976ae3ea 5293 'does not have a videos tab',
5294 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5295 ],
5296 'playlist_mincount': 101,
5297 'params': {
5298 'skip_download': True,
5299 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5300 },
7c219ea6 5301 }, {
5302 'note': 'non-standard redirect to regional channel',
5303 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5304 'only_matching': True
61d3665d 5305 }, {
5306 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5307 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5308 'info_dict': {
5309 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5310 'modified_date': '20220407',
5311 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5312 'tags': [],
5313 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5314 'uploader': 'pukkandan',
5315 'availability': 'unlisted',
5316 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5317 'channel': 'pukkandan',
5318 'description': 'Test for collaborative playlist',
5319 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5320 'view_count': int,
61d3665d 5321 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5322 },
5323 'playlist_mincount': 2
a6213a49 5324 }]
5325
5326 @classmethod
5327 def suitable(cls, url):
86e5f3ed 5328 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5329
64f36541 5330 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5331
182bda88 5332 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5333 def _real_extract(self, url, smuggled_data):
cd7c66cf 5334 item_id = self._match_id(url)
14f25df2 5335 url = urllib.parse.urlunparse(
5336 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5337 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5338
fe03a6cd 5339 def get_mobj(url):
37e57a9f 5340 mobj = self._URL_RE.match(url).groupdict()
07cce701 5341 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5342 return mobj
5343
37e57a9f 5344 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5345 # Youtube returns incomplete data if tabname is not lower case
5346 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5347 if is_channel:
5348 if smuggled_data.get('is_music_url'):
37e57a9f 5349 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5350 item_id = item_id[2:]
37e57a9f 5351 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5352 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5353 mdata = self._extract_tab_endpoint(
37e57a9f 5354 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5355 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
14f25df2 5356 get_all=False, expected_type=str)
ac56cf38 5357 if not murl:
37e57a9f 5358 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5359 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5360 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5361 pre = f'https://www.youtube.com/channel/{item_id}'
5362
64f36541 5363 original_tab_name = tab
fe03a6cd 5364 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5365 # Home URLs should redirect to /videos/
37e57a9f 5366 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5367 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5368 tab = '/videos'
5369
5370 url = ''.join((pre, tab, post))
5371 mobj = get_mobj(url)
cd7c66cf 5372
5373 # Handle both video/playlist URLs
201c1459 5374 qs = parse_qs(url)
86e5f3ed 5375 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5376
fe03a6cd 5377 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5378 if not playlist_id:
fe03a6cd 5379 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5380 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5381 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5382 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5383 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5384 mobj = get_mobj(url)
cd7c66cf 5385
5386 if video_id and playlist_id:
a06916d9 5387 if self.get_param('noplaylist'):
37e57a9f 5388 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5389 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5390 ie=YoutubeIE.ie_key(), video_id=video_id)
5391 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5392
ac56cf38 5393 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5394
7c219ea6 5395 # YouTube may provide a non-standard redirect to the regional channel
5396 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5397 redirect_url = traverse_obj(
5398 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5399 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5400 redirect_url = ''.join((
5401 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5402 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5403 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5404
37e57a9f 5405 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5406 if tabs:
5407 selected_tab = self._extract_selected_tab(tabs)
64f36541 5408 selected_tab_name = selected_tab.get('title', '').lower()
5409 if selected_tab_name == 'home':
5410 selected_tab_name = 'featured'
5411 requested_tab_name = mobj['tab'][1:]
09f1580e 5412 if 'no-youtube-channel-redirect' not in compat_opts:
693f0600 5413 if requested_tab_name == 'live': # Live tab should have redirected to the video
5414 raise UserNotLive(video_id=mobj['id'])
64f36541 5415 if requested_tab_name not in ('', selected_tab_name):
5416 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5417 if not original_tab_name:
5418 if item_id[:2] == 'UC':
5419 # Topic channels don't have /videos. Use the equivalent playlist instead
5420 pl_id = f'UU{item_id[2:]}'
5421 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5422 try:
5423 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5424 except ExtractorError:
5425 redirect_warning += ' and the playlist redirect gave error'
5426 else:
5427 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5428 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5429 if selected_tab_name and selected_tab_name != requested_tab_name:
5430 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5431 else:
5432 raise ExtractorError(redirect_warning, expected=True)
18db7548 5433
37e57a9f 5434 if redirect_warning:
64f36541 5435 self.to_screen(redirect_warning)
37e57a9f 5436 self.write_debug(f'Final URL: {url}')
18db7548 5437
358de58c 5438 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5439 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5440 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5441 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5442 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5443 if tabs:
ac56cf38 5444 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5445
37e57a9f 5446 playlist = traverse_obj(
5447 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5448 if playlist:
ac56cf38 5449 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5450
37e57a9f 5451 video_id = traverse_obj(
5452 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5453 if video_id:
09f1580e 5454 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5455 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5456 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5457 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5458
8bdd16b4 5459 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5460
c5e8d7af 5461
8bdd16b4 5462class YoutubePlaylistIE(InfoExtractor):
96565c7e 5463 IE_DESC = 'YouTube playlists'
8bdd16b4 5464 _VALID_URL = r'''(?x)(?:
5465 (?:https?://)?
5466 (?:\w+\.)?
5467 (?:
5468 (?:
5469 youtube(?:kids)?\.com|
d9190e44 5470 %(invidious)s
8bdd16b4 5471 )
5472 /.*?\?.*?\blist=
5473 )?
5474 (?P<id>%(playlist_id)s)
d9190e44
RH
5475 )''' % {
5476 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5477 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5478 }
8bdd16b4 5479 IE_NAME = 'youtube:playlist'
cdc628a4 5480 _TESTS = [{
8bdd16b4 5481 'note': 'issue #673',
5482 'url': 'PLBB231211A4F62143',
cdc628a4 5483 'info_dict': {
8bdd16b4 5484 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5485 'id': 'PLBB231211A4F62143',
976ae3ea 5486 'uploader': 'Wickman',
8bdd16b4 5487 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5488 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5489 'view_count': int,
5490 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5491 'modified_date': r're:\d{8}',
5492 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5493 'channel': 'Wickman',
5494 'tags': [],
5495 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5496 },
5497 'playlist_mincount': 29,
5498 }, {
5499 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5500 'info_dict': {
5501 'title': 'YDL_safe_search',
5502 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5503 },
5504 'playlist_count': 2,
5505 'skip': 'This playlist is private',
9558dcec 5506 }, {
8bdd16b4 5507 'note': 'embedded',
5508 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5509 'playlist_count': 4,
9558dcec 5510 'info_dict': {
8bdd16b4 5511 'title': 'JODA15',
5512 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5513 'uploader': 'milan',
5514 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5515 'description': '',
5516 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5517 'tags': [],
5518 'modified_date': '20140919',
5519 'view_count': int,
5520 'channel': 'milan',
5521 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5522 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5523 },
5524 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5525 }, {
8bdd16b4 5526 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 5527 'playlist_mincount': 455,
8bdd16b4 5528 'info_dict': {
5529 'title': '2018 Chinese New Singles (11/6 updated)',
5530 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5531 'uploader': 'LBK',
5532 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5533 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5534 'channel': 'LBK',
5535 'view_count': int,
5536 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5537 'tags': [],
5538 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5539 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5540 'modified_date': r're:\d{8}',
5541 },
5542 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5543 }, {
29f7c58a 5544 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5545 'only_matching': True,
5546 }, {
5547 # music album playlist
5548 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5549 'only_matching': True,
5550 }]
5551
5552 @classmethod
5553 def suitable(cls, url):
201c1459 5554 if YoutubeTabIE.suitable(url):
5555 return False
49a57e70 5556 from ..utils import parse_qs
201c1459 5557 qs = parse_qs(url)
5558 if qs.get('v', [None])[0]:
5559 return False
86e5f3ed 5560 return super().suitable(url)
29f7c58a 5561
5562 def _real_extract(self, url):
5563 playlist_id = self._match_id(url)
46953e7e 5564 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5565 url = update_url_query(
5566 'https://www.youtube.com/playlist',
5567 parse_qs(url) or {'list': playlist_id})
5568 if is_music_url:
5569 url = smuggle_url(url, {'is_music_url': True})
5570 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5571
5572
5573class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5574 IE_DESC = 'youtu.be'
29f7c58a 5575 _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}
5576 _TESTS = [{
8bdd16b4 5577 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5578 'info_dict': {
5579 'id': 'yeWKywCrFtk',
5580 'ext': 'mp4',
5581 'title': 'Small Scale Baler and Braiding Rugs',
5582 'uploader': 'Backus-Page House Museum',
5583 'uploader_id': 'backuspagemuseum',
5584 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5585 'upload_date': '20161008',
5586 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5587 'categories': ['Nonprofits & Activism'],
5588 'tags': list,
5589 'like_count': int,
976ae3ea 5590 'age_limit': 0,
5591 'playable_in_embed': True,
5592 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5593 'channel': 'Backus-Page House Museum',
5594 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5595 'live_status': 'not_live',
5596 'view_count': int,
5597 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5598 'availability': 'public',
5599 'duration': 59,
12a1b225
A
5600 'comment_count': int,
5601 'channel_follower_count': int
8bdd16b4 5602 },
5603 'params': {
5604 'noplaylist': True,
5605 'skip_download': True,
5606 },
39e7107d 5607 }, {
8bdd16b4 5608 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5609 'only_matching': True,
cdc628a4
PH
5610 }]
5611
8bdd16b4 5612 def _real_extract(self, url):
5ad28e7f 5613 mobj = self._match_valid_url(url)
29f7c58a 5614 video_id = mobj.group('id')
5615 playlist_id = mobj.group('playlist_id')
8bdd16b4 5616 return self.url_result(
29f7c58a 5617 update_url_query('https://www.youtube.com/watch', {
5618 'v': video_id,
5619 'list': playlist_id,
5620 'feature': 'youtu.be',
5621 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5622
5623
b6ce9bb0 5624class YoutubeLivestreamEmbedIE(InfoExtractor):
5625 IE_DESC = 'YouTube livestream embeds'
5626 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5627 _TESTS = [{
5628 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5629 'only_matching': True,
5630 }]
5631
5632 def _real_extract(self, url):
5633 channel_id = self._match_id(url)
5634 return self.url_result(
5635 f'https://www.youtube.com/channel/{channel_id}/live',
5636 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5637
5638
8bdd16b4 5639class YoutubeYtUserIE(InfoExtractor):
96565c7e 5640 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5641 IE_NAME = 'youtube:user'
8bdd16b4 5642 _VALID_URL = r'ytuser:(?P<id>.+)'
5643 _TESTS = [{
5644 'url': 'ytuser:phihag',
5645 'only_matching': True,
5646 }]
5647
5648 def _real_extract(self, url):
5649 user_id = self._match_id(url)
5650 return self.url_result(
c586f9e8 5651 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5652 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5653
b05654f0 5654
3d3dddc9 5655class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5656 IE_NAME = 'youtube:favorites'
96565c7e 5657 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5658 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5659 _LOGIN_REQUIRED = True
5660 _TESTS = [{
5661 'url': ':ytfav',
5662 'only_matching': True,
5663 }, {
5664 'url': ':ytfavorites',
5665 'only_matching': True,
5666 }]
5667
5668 def _real_extract(self, url):
5669 return self.url_result(
5670 'https://www.youtube.com/playlist?list=LL',
5671 ie=YoutubeTabIE.ie_key())
5672
5673
ca5300c7 5674class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
5675 IE_NAME = 'youtube:notif'
5676 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5677 _VALID_URL = r':ytnotif(?:ication)?s?'
5678 _LOGIN_REQUIRED = True
5679 _TESTS = [{
5680 'url': ':ytnotif',
5681 'only_matching': True,
5682 }, {
5683 'url': ':ytnotifications',
5684 'only_matching': True,
5685 }]
5686
5687 def _extract_notification_menu(self, response, continuation_list):
5688 notification_list = traverse_obj(
5689 response,
5690 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5691 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5692 expected_type=list) or []
5693 continuation_list[0] = None
5694 for item in notification_list:
5695 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
5696 if entry:
5697 yield entry
5698 continuation = item.get('continuationItemRenderer')
5699 if continuation:
5700 continuation_list[0] = continuation
5701
5702 def _extract_notification_renderer(self, notification):
5703 video_id = traverse_obj(
5704 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
5705 url = f'https://www.youtube.com/watch?v={video_id}'
5706 channel_id = None
5707 if not video_id:
5708 browse_ep = traverse_obj(
5709 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
5710 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
5711 post_id = self._search_regex(
5712 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
5713 'post id', default=None)
5714 if not channel_id or not post_id:
5715 return
5716 # The direct /post url redirects to this in the browser
5717 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5718
5719 channel = traverse_obj(
5720 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5721 expected_type=str)
c7a7baaa 5722 notification_title = self._get_text(notification, 'shortMessage')
5723 if notification_title:
5724 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
5725 # TODO: handle recommended videos
ca5300c7 5726 title = self._search_regex(
c7a7baaa 5727 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 5728 'video title', default=None)
ca5300c7 5729 upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d')
5730 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
5731 else None)
5732 return {
5733 '_type': 'url',
5734 'url': url,
5735 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
5736 'video_id': video_id,
5737 'title': title,
5738 'channel_id': channel_id,
5739 'channel': channel,
5740 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5741 'upload_date': upload_date,
5742 }
5743
5744 def _notification_menu_entries(self, ytcfg):
5745 continuation_list = [None]
5746 response = None
5747 for page in itertools.count(1):
5748 ctoken = traverse_obj(
5749 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
5750 response = self._extract_response(
5751 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
5752 ep='notification/get_notification_menu', check_get_keys='actions',
5753 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
5754 yield from self._extract_notification_menu(response, continuation_list)
5755 if not continuation_list[0]:
5756 break
5757
5758 def _real_extract(self, url):
5759 display_id = 'notifications'
5760 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
5761 self._report_playlist_authcheck(ytcfg)
5762 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
5763
5764
a6213a49 5765class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5766 IE_DESC = 'YouTube search'
78caa52a 5767 IE_NAME = 'youtube:search'
b05654f0 5768 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5769 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5770 _TESTS = [{
5771 'url': 'ytsearch5:youtube-dl test video',
5772 'playlist_count': 5,
5773 'info_dict': {
5774 'id': 'youtube-dl test video',
5775 'title': 'youtube-dl test video',
5776 }
5777 }]
b05654f0 5778
a61fd4cf 5779
5f7cb91a 5780class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5781 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5782 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5783 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5784 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5785 _TESTS = [{
5786 'url': 'ytsearchdate5:youtube-dl test video',
5787 'playlist_count': 5,
5788 'info_dict': {
5789 'id': 'youtube-dl test video',
5790 'title': 'youtube-dl test video',
5791 }
5792 }]
75dff0ee 5793
c9ae7b95 5794
a6213a49 5795class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5796 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5797 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5798 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5799 _TESTS = [{
5800 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5801 'playlist_mincount': 5,
5802 'info_dict': {
11f9be09 5803 'id': 'youtube-dl test video',
3462ffa8 5804 'title': 'youtube-dl test video',
5805 }
a61fd4cf 5806 }, {
5807 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5808 'playlist_mincount': 5,
5809 'info_dict': {
5810 'id': 'python',
5811 'title': 'python',
5812 }
ad210f4f 5813 }, {
5814 'url': 'https://www.youtube.com/results?search_query=%23cats',
5815 'playlist_mincount': 1,
5816 'info_dict': {
5817 'id': '#cats',
5818 'title': '#cats',
12a1b225
A
5819 # The test suite does not have support for nested playlists
5820 # 'entries': [{
5821 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5822 # 'title': '#cats',
5823 # }],
ad210f4f 5824 },
3462ffa8 5825 }, {
5826 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5827 'only_matching': True,
5828 }]
5829
5830 def _real_extract(self, url):
4dfbf869 5831 qs = parse_qs(url)
386e1dd9 5832 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5833 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5834
5835
16aa9ea4 5836class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 5837 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 5838 IE_NAME = 'youtube:music:search_url'
5839 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5840 _TESTS = [{
5841 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5842 'playlist_count': 16,
5843 'info_dict': {
5844 'id': 'royalty free music',
5845 'title': 'royalty free music',
5846 }
5847 }, {
5848 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5849 'playlist_mincount': 30,
5850 'info_dict': {
5851 'id': 'royalty free music - songs',
5852 'title': 'royalty free music - songs',
5853 },
5854 'params': {'extract_flat': 'in_playlist'}
5855 }, {
5856 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5857 'playlist_mincount': 30,
5858 'info_dict': {
5859 'id': 'royalty free music - community playlists',
5860 'title': 'royalty free music - community playlists',
5861 },
5862 'params': {'extract_flat': 'in_playlist'}
5863 }]
5864
5865 _SECTIONS = {
5866 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5867 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5868 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5869 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5870 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5871 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5872 }
5873
5874 def _real_extract(self, url):
5875 qs = parse_qs(url)
5876 query = (qs.get('search_query') or qs.get('q'))[0]
5877 params = qs.get('sp', (None,))[0]
5878 if params:
5879 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5880 else:
ac668111 5881 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 5882 params = self._SECTIONS.get(section)
5883 if not params:
5884 section = None
5885 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5886 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5887
5888
182bda88 5889class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5890 """
25f14e9f 5891 Base class for feed extractors
82d02080 5892 Subclasses must re-define the _FEED_NAME property.
d7ae0639 5893 """
b2e8bc1b 5894 _LOGIN_REQUIRED = True
82d02080 5895 _FEED_NAME = 'feeds'
a25bca9f 5896
5897 def _real_initialize(self):
5898 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 5899
82d02080 5900 @classproperty
d7ae0639 5901 def IE_NAME(self):
82d02080 5902 return f'youtube:{self._FEED_NAME}'
04cc9617 5903
3853309f 5904 def _real_extract(self, url):
3d3dddc9 5905 return self.url_result(
182bda88 5906 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5907
5908
ef2f3c7f 5909class YoutubeWatchLaterIE(InfoExtractor):
5910 IE_NAME = 'youtube:watchlater'
96565c7e 5911 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5912 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5913 _TESTS = [{
8bdd16b4 5914 'url': ':ytwatchlater',
bc7a9cd8
S
5915 'only_matching': True,
5916 }]
25f14e9f
S
5917
5918 def _real_extract(self, url):
ef2f3c7f 5919 return self.url_result(
5920 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5921
5922
25f14e9f 5923class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5924 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5925 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5926 _FEED_NAME = 'recommended'
45db527f 5927 _LOGIN_REQUIRED = False
3d3dddc9 5928 _TESTS = [{
5929 'url': ':ytrec',
5930 'only_matching': True,
5931 }, {
5932 'url': ':ytrecommended',
5933 'only_matching': True,
5934 }, {
5935 'url': 'https://youtube.com',
5936 'only_matching': True,
5937 }]
1ed5b5c9 5938
1ed5b5c9 5939
25f14e9f 5940class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5941 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5942 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5943 _FEED_NAME = 'subscriptions'
3d3dddc9 5944 _TESTS = [{
5945 'url': ':ytsubs',
5946 'only_matching': True,
5947 }, {
5948 'url': ':ytsubscriptions',
5949 'only_matching': True,
5950 }]
1ed5b5c9 5951
1ed5b5c9 5952
25f14e9f 5953class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5954 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5955 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5956 _FEED_NAME = 'history'
3d3dddc9 5957 _TESTS = [{
5958 'url': ':ythistory',
5959 'only_matching': True,
5960 }]
1ed5b5c9
JMF
5961
5962
6e634cbe 5963class YoutubeStoriesIE(InfoExtractor):
5964 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
5965 IE_NAME = 'youtube:stories'
5966 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
5967 _TESTS = [{
5968 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
5969 'only_matching': True,
5970 }]
5971
5972 def _real_extract(self, url):
5973 playlist_id = f'RLTD{self._match_id(url)}'
5974 return self.url_result(
5975 f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
5976 ie=YoutubeTabIE, video_id=playlist_id)
5977
5978
15870e90
PH
5979class YoutubeTruncatedURLIE(InfoExtractor):
5980 IE_NAME = 'youtube:truncated_url'
5981 IE_DESC = False # Do not list
975d35db 5982 _VALID_URL = r'''(?x)
b95aab84
PH
5983 (?:https?://)?
5984 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5985 (?:watch\?(?:
c4808c60 5986 feature=[a-z_]+|
b95aab84
PH
5987 annotation_id=annotation_[^&]+|
5988 x-yt-cl=[0-9]+|
c1708b89 5989 hl=[^&]*|
287be8c6 5990 t=[0-9]+
b95aab84
PH
5991 )?
5992 |
5993 attribution_link\?a=[^&]+
5994 )
5995 $
975d35db 5996 '''
15870e90 5997
c4808c60 5998 _TESTS = [{
2d3d2997 5999 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 6000 'only_matching': True,
dc2fc736 6001 }, {
2d3d2997 6002 'url': 'https://www.youtube.com/watch?',
dc2fc736 6003 'only_matching': True,
b95aab84
PH
6004 }, {
6005 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6006 'only_matching': True,
6007 }, {
6008 'url': 'https://www.youtube.com/watch?feature=foo',
6009 'only_matching': True,
c1708b89
PH
6010 }, {
6011 'url': 'https://www.youtube.com/watch?hl=en-GB',
6012 'only_matching': True,
287be8c6
PH
6013 }, {
6014 'url': 'https://www.youtube.com/watch?t=2372',
6015 'only_matching': True,
c4808c60
PH
6016 }]
6017
15870e90
PH
6018 def _real_extract(self, url):
6019 raise ExtractorError(
78caa52a
PH
6020 'Did you forget to quote the URL? Remember that & is a meta '
6021 'character in most shells, so you want to put the URL in quotes, '
3867038a 6022 'like youtube-dl '
2d3d2997 6023 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 6024 ' or simply youtube-dl BaW_jenozKc .',
15870e90 6025 expected=True)
772fd5cc
PH
6026
6027
471d0367 6028class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6029 IE_NAME = 'youtube:clip'
471d0367 6030 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6031 _TESTS = [{
6032 # FIXME: Other metadata should be extracted from the clip, not from the base video
6033 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6034 'info_dict': {
6035 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6036 'ext': 'mp4',
6037 'section_start': 29.0,
6038 'section_end': 39.7,
6039 'duration': 10.7,
12a1b225
A
6040 'age_limit': 0,
6041 'availability': 'public',
6042 'categories': ['Gaming'],
6043 'channel': 'Scott The Woz',
6044 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6045 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6046 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6047 'like_count': int,
6048 'playable_in_embed': True,
6049 'tags': 'count:17',
6050 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6051 'title': 'Mobile Games on Console - Scott The Woz',
6052 'upload_date': '20210920',
6053 'uploader': 'Scott The Woz',
6054 'uploader_id': 'scottthewoz',
6055 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6056 'view_count': int,
6057 'live_status': 'not_live',
6058 'channel_follower_count': int
471d0367 6059 }
6060 }]
3cd786db 6061
6062 def _real_extract(self, url):
471d0367 6063 clip_id = self._match_id(url)
6064 _, data = self._extract_webpage(url, clip_id)
6065
6066 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6067 if not video_id:
6068 raise ExtractorError('Unable to find video ID')
6069
6070 clip_data = traverse_obj(data, (
6071 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6072 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6073 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6074 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6075
6076 return {
6077 '_type': 'url_transparent',
6078 'url': f'https://www.youtube.com/watch?v={video_id}',
6079 'ie_key': YoutubeIE.ie_key(),
6080 'id': clip_id,
6081 'section_start': int(clip_data['startTimeMs']) / 1000,
6082 'section_end': int(clip_data['endTimeMs']) / 1000,
6083 }
3cd786db 6084
6085
772fd5cc
PH
6086class YoutubeTruncatedIDIE(InfoExtractor):
6087 IE_NAME = 'youtube:truncated_id'
6088 IE_DESC = False # Do not list
b95aab84 6089 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6090
6091 _TESTS = [{
6092 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6093 'only_matching': True,
6094 }]
6095
6096 def _real_extract(self, url):
6097 video_id = self._match_id(url)
6098 raise ExtractorError(
86e5f3ed 6099 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6100 expected=True)