]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[youtube] Fix error reporting of "Incomplete data"
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
6e634cbe 1import base64
d92f5d5a 2import calendar
109dd3b2 3import copy
fe93e2c4 4import datetime
a5c56234 5import hashlib
0ca96d48 6import itertools
c5e8d7af 7import json
720c3099 8import math
c4417ddb 9import os.path
d77ab8e2 10import random
c5e8d7af 11import re
46383212 12import sys
f8271158 13import threading
8a784c74 14import time
e0df6211 15import traceback
14f25df2 16import urllib.error
ac668111 17import urllib.parse
c5e8d7af 18
b05654f0 19from .common import InfoExtractor, SearchInfoExtractor
14f25df2 20from ..compat import functools
545cc85d 21from ..jsinterp import JSInterpreter
4bb4a188 22from ..utils import (
f8271158 23 NO_DEFAULT,
24 ExtractorError,
693f0600 25 UserNotLive,
720c3099 26 bug_reports_message,
82d02080 27 classproperty,
c5e8d7af 28 clean_html,
d92f5d5a 29 datetime_from_str,
11f9be09 30 dict_get,
2d30521a 31 float_or_none,
11f9be09 32 format_field,
ff91cf74 33 get_first,
dd27fd17 34 int_or_none,
641ad5d8 35 is_html,
34921b43 36 join_nonempty,
48416bc4 37 js_to_json,
94278f72 38 mimetype2ext,
9c0d7f49 39 network_exceptions,
11f9be09 40 orderedSet,
6310acf5 41 parse_codecs,
49bd8c66 42 parse_count,
7c80519c 43 parse_duration,
7ea65411 44 parse_iso8601,
4dfbf869 45 parse_qs,
dca3ff4a 46 qualities,
3995d37d 47 remove_start,
cf7e015f 48 smuggle_url,
dbdaaa23 49 str_or_none,
c93d53f5 50 str_to_int,
f3aa3c3f 51 strftime_or_none,
7c365c21 52 traverse_obj,
556dbe7f 53 try_get,
c5e8d7af
PH
54 unescapeHTML,
55 unified_strdate,
f0d785d3 56 unified_timestamp,
cf7e015f 57 unsmuggle_url,
8bdd16b4 58 update_url_query,
21c340b8 59 url_or_none,
fe93e2c4 60 urljoin,
7c365c21 61 variadic,
c5e8d7af
PH
62)
63
962ffcf8 64# any clients starting with _ cannot be explicitly requested by the user
000c15a4 65INNERTUBE_CLIENTS = {
66 'web': {
67 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
68 'INNERTUBE_CONTEXT': {
69 'client': {
70 'clientName': 'WEB',
a0c830f4 71 'clientVersion': '2.20220801.00.00',
000c15a4 72 }
73 },
74 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
75 },
76 'web_embedded': {
77 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
78 'INNERTUBE_CONTEXT': {
79 'client': {
80 'clientName': 'WEB_EMBEDDED_PLAYER',
a0c830f4 81 'clientVersion': '1.20220731.00.00',
000c15a4 82 },
83 },
84 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
85 },
86 'web_music': {
87 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
88 'INNERTUBE_HOST': 'music.youtube.com',
89 'INNERTUBE_CONTEXT': {
90 'client': {
91 'clientName': 'WEB_REMIX',
a0c830f4 92 'clientVersion': '1.20220727.01.00',
000c15a4 93 }
94 },
95 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
96 },
e7e94f2a 97 'web_creator': {
18c7683d 98 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
99 'INNERTUBE_CONTEXT': {
100 'client': {
101 'clientName': 'WEB_CREATOR',
a0c830f4 102 'clientVersion': '1.20220726.00.00',
e7e94f2a
D
103 }
104 },
105 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
106 },
000c15a4 107 'android': {
18c7683d 108 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 109 'INNERTUBE_CONTEXT': {
110 'client': {
111 'clientName': 'ANDROID',
c7dcf0b3 112 'clientVersion': '17.29.34',
113 'androidSdkVersion': 30
000c15a4 114 }
115 },
116 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 117 'REQUIRE_JS_PLAYER': False
000c15a4 118 },
119 'android_embedded': {
18c7683d 120 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 121 'INNERTUBE_CONTEXT': {
122 'client': {
123 'clientName': 'ANDROID_EMBEDDED_PLAYER',
c7dcf0b3 124 'clientVersion': '17.29.34',
125 'androidSdkVersion': 30
000c15a4 126 },
127 },
b6de707d 128 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
129 'REQUIRE_JS_PLAYER': False
000c15a4 130 },
131 'android_music': {
18c7683d 132 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 133 'INNERTUBE_CONTEXT': {
134 'client': {
135 'clientName': 'ANDROID_MUSIC',
a0c830f4 136 'clientVersion': '5.16.51',
c7dcf0b3 137 'androidSdkVersion': 30
000c15a4 138 }
139 },
140 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 141 'REQUIRE_JS_PLAYER': False
000c15a4 142 },
e7e94f2a 143 'android_creator': {
18c7683d 144 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
145 'INNERTUBE_CONTEXT': {
146 'client': {
147 'clientName': 'ANDROID_CREATOR',
a0c830f4 148 'clientVersion': '22.28.100',
c7dcf0b3 149 'androidSdkVersion': 30
e7e94f2a
D
150 },
151 },
b6de707d 152 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
153 'REQUIRE_JS_PLAYER': False
e7e94f2a 154 },
18c7683d 155 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
156 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 157 'ios': {
18c7683d 158 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 159 'INNERTUBE_CONTEXT': {
160 'client': {
161 'clientName': 'IOS',
a0c830f4 162 'clientVersion': '17.30.1',
18c7683d 163 'deviceModel': 'iPhone14,3',
000c15a4 164 }
165 },
b6de707d 166 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
167 'REQUIRE_JS_PLAYER': False
000c15a4 168 },
169 'ios_embedded': {
000c15a4 170 'INNERTUBE_CONTEXT': {
171 'client': {
172 'clientName': 'IOS_MESSAGES_EXTENSION',
a0c830f4 173 'clientVersion': '17.30.1',
18c7683d 174 'deviceModel': 'iPhone14,3',
000c15a4 175 },
176 },
b6de707d 177 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
178 'REQUIRE_JS_PLAYER': False
000c15a4 179 },
180 'ios_music': {
18c7683d 181 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 182 'INNERTUBE_CONTEXT': {
183 'client': {
184 'clientName': 'IOS_MUSIC',
a0c830f4 185 'clientVersion': '5.18',
000c15a4 186 },
187 },
b6de707d 188 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
189 'REQUIRE_JS_PLAYER': False
000c15a4 190 },
e7e94f2a
D
191 'ios_creator': {
192 'INNERTUBE_CONTEXT': {
193 'client': {
194 'clientName': 'IOS_CREATOR',
a0c830f4 195 'clientVersion': '22.29.101',
e7e94f2a
D
196 },
197 },
b6de707d 198 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
199 'REQUIRE_JS_PLAYER': False
e7e94f2a 200 },
3619f78d 201 # mweb has 'ultralow' formats
202 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 203 'mweb': {
18c7683d 204 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 205 'INNERTUBE_CONTEXT': {
206 'client': {
207 'clientName': 'MWEB',
a0c830f4 208 'clientVersion': '2.20220801.00.00',
000c15a4 209 }
210 },
211 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
212 },
213 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
214 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
215 'tv_embedded': {
216 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
217 'INNERTUBE_CONTEXT': {
218 'client': {
219 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
220 'clientVersion': '2.0',
221 },
222 },
223 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
224 },
000c15a4 225}
226
227
e7870111
D
228def _split_innertube_client(client_name):
229 variant, *base = client_name.rsplit('.', 1)
230 if base:
231 return variant, base[0], variant
232 base, *variant = client_name.split('_', 1)
233 return client_name, base, variant[0] if variant else None
234
235
000c15a4 236def build_innertube_clients():
2e4cacd0 237 THIRD_PARTY = {
e7870111 238 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 239 }
e7870111 240 BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb')
2e4cacd0 241 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 242
243 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 244 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 245 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 246 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 247 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 248
e7870111 249 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 250 ytcfg['priority'] = 10 * priority(base_client)
251
e48b3875 252 if not variant:
e7870111
D
253 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
254 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
255 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
256 embedscreen['priority'] -= 3
257 elif variant == 'embedded':
e48b3875 258 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 259 ytcfg['priority'] -= 2
e48b3875 260 else:
000c15a4 261 ytcfg['priority'] -= 3
262
263
264build_innertube_clients()
265
266
de7f3446 267class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 268 """Provide base functions for Youtube extractors"""
e00eb564 269
3462ffa8 270 _RESERVED_NAMES = (
3cd786db 271 r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
182bda88 272 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
3619f78d 273 r'browse|oembed|get_video_info|iframe_api|s/player|'
cd7c66cf 274 r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
3462ffa8 275
3619f78d 276 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
277
52efa4b3 278 # _NETRC_MACHINE = 'youtube'
3619f78d 279
b2e8bc1b
JMF
280 # If True it will raise an error if no login info is provided
281 _LOGIN_REQUIRED = False
282
d9190e44
RH
283 _INVIDIOUS_SITES = (
284 # invidious-redirect websites
285 r'(?:www\.)?redirect\.invidious\.io',
286 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 287 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
288 r'(?:www\.)?invidious\.pussthecat\.org',
289 r'(?:www\.)?invidious\.zee\.li',
290 r'(?:www\.)?invidious\.ethibox\.fr',
291 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
292 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
293 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
294 # youtube-dl invidious instances list
295 r'(?:(?:www|no)\.)?invidiou\.sh',
296 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
297 r'(?:www\.)?invidious\.kabi\.tk',
298 r'(?:www\.)?invidious\.mastodon\.host',
299 r'(?:www\.)?invidious\.zapashcanon\.fr',
300 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
301 r'(?:www\.)?invidious\.tinfoil-hat\.net',
302 r'(?:www\.)?invidious\.himiko\.cloud',
303 r'(?:www\.)?invidious\.reallyancient\.tech',
304 r'(?:www\.)?invidious\.tube',
305 r'(?:www\.)?invidiou\.site',
306 r'(?:www\.)?invidious\.site',
307 r'(?:www\.)?invidious\.xyz',
308 r'(?:www\.)?invidious\.nixnet\.xyz',
309 r'(?:www\.)?invidious\.048596\.xyz',
310 r'(?:www\.)?invidious\.drycat\.fr',
311 r'(?:www\.)?inv\.skyn3t\.in',
312 r'(?:www\.)?tube\.poal\.co',
313 r'(?:www\.)?tube\.connect\.cafe',
314 r'(?:www\.)?vid\.wxzm\.sx',
315 r'(?:www\.)?vid\.mint\.lgbt',
316 r'(?:www\.)?vid\.puffyan\.us',
317 r'(?:www\.)?yewtu\.be',
318 r'(?:www\.)?yt\.elukerio\.org',
319 r'(?:www\.)?yt\.lelux\.fi',
320 r'(?:www\.)?invidious\.ggc-project\.de',
321 r'(?:www\.)?yt\.maisputain\.ovh',
322 r'(?:www\.)?ytprivate\.com',
323 r'(?:www\.)?invidious\.13ad\.de',
324 r'(?:www\.)?invidious\.toot\.koeln',
325 r'(?:www\.)?invidious\.fdn\.fr',
326 r'(?:www\.)?watch\.nettohikari\.com',
327 r'(?:www\.)?invidious\.namazso\.eu',
328 r'(?:www\.)?invidious\.silkky\.cloud',
329 r'(?:www\.)?invidious\.exonip\.de',
330 r'(?:www\.)?invidious\.riverside\.rocks',
331 r'(?:www\.)?invidious\.blamefran\.net',
332 r'(?:www\.)?invidious\.moomoo\.de',
333 r'(?:www\.)?ytb\.trom\.tf',
334 r'(?:www\.)?yt\.cyberhost\.uk',
335 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
336 r'(?:www\.)?qklhadlycap4cnod\.onion',
337 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
338 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
339 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
340 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
341 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
342 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
343 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
344 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
345 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
346 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
347 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
348 r'(?:www\.)?piped\.kavin\.rocks',
349 r'(?:www\.)?piped\.silkky\.cloud',
350 r'(?:www\.)?piped\.tokhmi\.xyz',
351 r'(?:www\.)?piped\.moomoo\.me',
352 r'(?:www\.)?il\.ax',
353 r'(?:www\.)?piped\.syncpundit\.com',
354 r'(?:www\.)?piped\.mha\.fi',
355 r'(?:www\.)?piped\.mint\.lgbt',
356 r'(?:www\.)?piped\.privacy\.com\.de',
d9190e44
RH
357 )
358
cce889b9 359 def _initialize_consent(self):
360 cookies = self._get_cookies('https://www.youtube.com/')
361 if cookies.get('__Secure-3PSID'):
362 return
363 consent_id = None
364 consent = cookies.get('CONSENT')
365 if consent:
366 if 'YES' in consent.value:
367 return
368 consent_id = self._search_regex(
369 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
370 if not consent_id:
371 consent_id = random.randint(100, 999)
372 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 373
f3aa3c3f 374 def _initialize_pref(self):
375 cookies = self._get_cookies('https://www.youtube.com/')
376 pref_cookie = cookies.get('PREF')
377 pref = {}
378 if pref_cookie:
379 try:
14f25df2 380 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 381 except ValueError:
382 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
396a76f7 383 pref.update({'hl': 'en', 'tz': 'UTC'})
14f25df2 384 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 385
b2e8bc1b 386 def _real_initialize(self):
f3aa3c3f 387 self._initialize_pref()
cce889b9 388 self._initialize_consent()
a25bca9f 389 self._check_login_required()
390
391 def _check_login_required(self):
24146491 392 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 393 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 394
b7c47b74 395 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
396 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 397
000c15a4 398 def _get_default_ytcfg(self, client='web'):
399 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 400
000c15a4 401 def _get_innertube_host(self, client='web'):
402 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 403
000c15a4 404 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 405 # try_get but with fallback to default ytcfg client values when present
406 _func = lambda y: try_get(y, getter, expected_type)
407 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
408
000c15a4 409 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 410 return self._ytcfg_get_safe(
411 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 412 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 413
000c15a4 414 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 415 return self._ytcfg_get_safe(
416 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 417 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 418
2ae778b8 419 def _select_api_hostname(self, req_api_hostname, default_client=None):
420 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
421 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
422
000c15a4 423 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 424 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 425
000c15a4 426 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 427 context = get_first(
428 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 429 # Enforce language and tz for extraction
430 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
431 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 432 return context
433
cf87314d 434 _SAPISID = None
435
109dd3b2 436 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 437 time_now = round(time.time())
cf87314d 438 if self._SAPISID is None:
439 yt_cookies = self._get_cookies('https://www.youtube.com')
440 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
441 # See: https://github.com/yt-dlp/yt-dlp/issues/393
442 sapisid_cookie = dict_get(
443 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
444 if sapisid_cookie and sapisid_cookie.value:
445 self._SAPISID = sapisid_cookie.value
446 self.write_debug('Extracted SAPISID cookie')
447 # SAPISID cookie is required if not already present
448 if not yt_cookies.get('SAPISID'):
449 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
450 self._set_cookie(
451 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
452 else:
453 self._SAPISID = False
454 if not self._SAPISID:
455 return None
1974e99f 456 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
457 sapisidhash = hashlib.sha1(
86e5f3ed 458 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 459 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
460
461 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 462 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 463 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 464
109dd3b2 465 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 466 data.update(query)
11f9be09 467 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 468 real_headers.update({'content-type': 'application/json'})
469 if headers:
470 real_headers.update(headers)
2ae778b8 471 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
472 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 473 return self._download_json(
2ae778b8 474 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 475 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 476 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 477 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 478
65141660 479 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
480 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 481
99e9e001 482 @staticmethod
483 def _extract_session_index(*data):
484 """
485 Index of current account in account list.
486 See: https://github.com/yt-dlp/yt-dlp/pull/519
487 """
488 for ytcfg in data:
489 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
490 if session_index is not None:
491 return session_index
492
493 # Deprecated?
494 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 495 if ytcfg:
14f25df2 496 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
497 if token:
498 return token
99e9e001 499 if webpage:
500 return self._search_regex(
501 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
502 'identity token', default=None, fatal=False)
a1c5d2ca
M
503
504 @staticmethod
fe93e2c4 505 def _extract_account_syncid(*args):
8ea3f7b9 506 """
507 Extract syncId required to download private playlists of secondary channels
fe93e2c4 508 @params response and/or ytcfg
8ea3f7b9 509 """
fe93e2c4 510 for data in args:
511 # ytcfg includes channel_syncid if on secondary channel
14f25df2 512 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 513 if delegated_sid:
514 return delegated_sid
515 sync_ids = (try_get(
516 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 517 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 518 if len(sync_ids) >= 2 and sync_ids[1]:
519 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
520 # and just "user_syncid||" for primary channel. We only want the channel_syncid
521 return sync_ids[0]
a1c5d2ca 522
ac56cf38 523 @staticmethod
524 def _extract_visitor_data(*args):
525 """
526 Extracts visitorData from an API response or ytcfg
527 Appears to be used to track session state
528 """
9222c381 529 return get_first(
6c73052c 530 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 531 expected_type=str)
ac56cf38 532
2762dbb1 533 @functools.cached_property
99e9e001 534 def is_authenticated(self):
535 return bool(self._generate_sapisidhash_header())
536
11f9be09 537 def extract_ytcfg(self, video_id, webpage):
8c54a305 538 if not webpage:
539 return {}
29f7c58a 540 return self._parse_json(
541 self._search_regex(
542 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 543 default='{}'), video_id, fatal=False) or {}
544
11f9be09 545 def generate_api_headers(
99e9e001 546 self, *, ytcfg=None, account_syncid=None, session_index=None,
547 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
548
2ae778b8 549 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 550 headers = {
14f25df2 551 'X-YouTube-Client-Name': str(
11f9be09 552 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
553 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 554 'Origin': origin,
555 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
556 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
ac56cf38 557 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg)
99e9e001 558 }
559 if session_index is None:
314ee305 560 session_index = self._extract_session_index(ytcfg)
561 if account_syncid or session_index is not None:
562 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 563
109dd3b2 564 auth = self._generate_sapisidhash_header(origin)
f4f751af 565 if auth is not None:
566 headers['Authorization'] = auth
109dd3b2 567 headers['X-Origin'] = origin
99e9e001 568 return {h: v for h, v in headers.items() if v is not None}
29f7c58a 569
a25bca9f 570 def _download_ytcfg(self, client, video_id):
571 url = {
572 'web': 'https://www.youtube.com',
573 'web_music': 'https://music.youtube.com',
574 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
575 }.get(client)
576 if not url:
577 return {}
578 webpage = self._download_webpage(
579 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
580 return self.extract_ytcfg(video_id, webpage) or {}
581
2d6659b9 582 @staticmethod
583 def _build_api_continuation_query(continuation, ctp=None):
584 query = {
585 'continuation': continuation
586 }
587 # TODO: Inconsistency with clickTrackingParams.
588 # Currently we have a fixed ctp contained within context (from ytcfg)
589 # and a ctp in root query for continuation.
590 if ctp:
591 query['clickTracking'] = {'clickTrackingParams': ctp}
592 return query
593
2d6659b9 594 @classmethod
595 def _extract_next_continuation_data(cls, renderer):
596 next_continuation = try_get(
597 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
598 lambda x: x['continuation']['reloadContinuationData']), dict)
599 if not next_continuation:
600 return
601 continuation = next_continuation.get('continuation')
602 if not continuation:
603 return
604 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 605 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 606
607 @classmethod
608 def _extract_continuation_ep_data(cls, continuation_ep: dict):
609 if isinstance(continuation_ep, dict):
610 continuation = try_get(
14f25df2 611 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 612 if not continuation:
613 return
614 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 615 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 616
617 @classmethod
618 def _extract_continuation(cls, renderer):
619 next_continuation = cls._extract_next_continuation_data(renderer)
620 if next_continuation:
621 return next_continuation
fe93e2c4 622
2d6659b9 623 contents = []
624 for key in ('contents', 'items'):
625 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
fe93e2c4 626
2d6659b9 627 for content in contents:
628 if not isinstance(content, dict):
629 continue
630 continuation_ep = try_get(
631 content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'],
632 lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']),
633 dict)
634 continuation = cls._extract_continuation_ep_data(continuation_ep)
635 if continuation:
636 return continuation
637
fe93e2c4 638 @classmethod
639 def _extract_alerts(cls, data):
109dd3b2 640 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
641 if not isinstance(alert_dict, dict):
642 continue
643 for alert in alert_dict.values():
644 alert_type = alert.get('type')
645 if not alert_type:
646 continue
052e1350 647 message = cls._get_text(alert, 'text')
109dd3b2 648 if message:
649 yield alert_type, message
650
c0ac49bc 651 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
109dd3b2 652 errors = []
653 warnings = []
654 for alert_type, alert_message in alerts:
641ad5d8 655 if alert_type.lower() == 'error' and fatal:
109dd3b2 656 errors.append([alert_type, alert_message])
657 else:
658 warnings.append([alert_type, alert_message])
659
660 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 661 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 662 if errors:
663 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
664
665 def _extract_and_report_alerts(self, data, *args, **kwargs):
666 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
667
47193e02 668 def _extract_badges(self, renderer: dict):
669 badges = set()
670 for badge in try_get(renderer, lambda x: x['badges'], list) or []:
14f25df2 671 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], str)
47193e02 672 if label:
673 badges.add(label.lower())
674 return badges
675
676 @staticmethod
052e1350 677 def _get_text(data, *path_list, max_runs=None):
678 for path in path_list or [None]:
679 if path is None:
680 obj = [data]
681 else:
682 obj = traverse_obj(data, path, default=[])
683 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
684 obj = [obj]
685 for item in obj:
14f25df2 686 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 687 if text:
688 return text
689 runs = try_get(item, lambda x: x['runs'], list) or []
690 if not runs and isinstance(item, list):
691 runs = item
692
693 runs = runs[:min(len(runs), max_runs or len(runs))]
694 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[]))
695 if text:
696 return text
47193e02 697
f0d785d3 698 def _get_count(self, data, *path_list):
699 count_text = self._get_text(data, *path_list) or ''
700 count = parse_count(count_text)
701 if count is None:
702 count = str_to_int(
703 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
704 return count
705
a709d873 706 @staticmethod
707 def _extract_thumbnails(data, *path_list):
708 """
709 Extract thumbnails from thumbnails dict
710 @param path_list: path list to level that contains 'thumbnails' key
711 """
712 thumbnails = []
713 for path in path_list or [()]:
714 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]):
715 thumbnail_url = url_or_none(thumbnail.get('url'))
716 if not thumbnail_url:
717 continue
718 # Sometimes youtube gives a wrong thumbnail URL. See:
719 # https://github.com/yt-dlp/yt-dlp/issues/233
720 # https://github.com/ytdl-org/youtube-dl/issues/28023
721 if 'maxresdefault' in thumbnail_url:
722 thumbnail_url = thumbnail_url.split('?')[0]
723 thumbnails.append({
724 'url': thumbnail_url,
725 'height': int_or_none(thumbnail.get('height')),
726 'width': int_or_none(thumbnail.get('width')),
727 })
728 return thumbnails
729
f3aa3c3f 730 @staticmethod
731 def extract_relative_time(relative_time_text):
732 """
733 Extracts a relative time from string and converts to dt object
f0d785d3 734 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
f3aa3c3f 735 """
f0d785d3 736 mobj = re.search(r'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>microsecond|second|minute|hour|day|week|month|year)s?\s*ago', relative_time_text)
f3aa3c3f 737 if mobj:
f0d785d3 738 start = mobj.group('start')
739 if start:
740 return datetime_from_str(start)
f3aa3c3f 741 try:
f0d785d3 742 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 743 except ValueError:
744 return None
745
746 def _extract_time_text(self, renderer, *path_list):
a25bca9f 747 """@returns (timestamp, time_text)"""
f3aa3c3f 748 text = self._get_text(renderer, *path_list) or ''
749 dt = self.extract_relative_time(text)
750 timestamp = None
751 if isinstance(dt, datetime.datetime):
752 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 753
754 if timestamp is None:
755 timestamp = (
756 unified_timestamp(text) or unified_timestamp(
757 self._search_regex(
17322130 758 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 759 text.lower(), 'time text', default=None)))
f0d785d3 760
f3aa3c3f 761 if text and timestamp is None:
17322130 762 self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True)
f3aa3c3f 763 return timestamp, text
764
109dd3b2 765 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
766 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 767 default_client='web'):
be5c1ae8 768 for retry in self.RetryManager():
109dd3b2 769 try:
770 response = self._call_api(
771 ep=ep, fatal=True, headers=headers,
be5c1ae8 772 video_id=item_id, query=query, note=note,
109dd3b2 773 context=self._extract_context(ytcfg, default_client),
774 api_key=self._extract_api_key(ytcfg, default_client),
be5c1ae8 775 api_hostname=api_hostname, default_client=default_client)
109dd3b2 776 except ExtractorError as e:
be5c1ae8 777 if not isinstance(e.cause, network_exceptions):
778 return self._error_or_warning(e, fatal=fatal)
779 elif not isinstance(e.cause, urllib.error.HTTPError):
780 retry.error = e
781 continue
109dd3b2 782
be5c1ae8 783 first_bytes = e.cause.read(512)
784 if not is_html(first_bytes):
785 yt_error = try_get(
786 self._parse_json(
787 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
788 lambda x: x['error']['message'], str)
789 if yt_error:
790 self._report_alerts([('ERROR', yt_error)], fatal=False)
791 # Downloading page may result in intermittent 5xx HTTP error
792 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
793 # We also want to catch all other network exceptions since errors in later pages can be troublesome
794 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
795 if e.cause.code not in (403, 429):
796 retry.error = e
797 continue
798 return self._error_or_warning(e, fatal=fatal)
799
800 try:
801 self._extract_and_report_alerts(response, only_once=True)
802 except ExtractorError as e:
803 # YouTube servers may return errors we want to retry on in a 200 OK response
804 # See: https://github.com/yt-dlp/yt-dlp/issues/839
805 if 'unknown error' in e.msg.lower():
806 retry.error = e
807 continue
808 return self._error_or_warning(e, fatal=fatal)
809 # Youtube sometimes sends incomplete data
810 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
811 if not traverse_obj(response, *variadic(check_get_keys)):
3ce29336 812 retry.error = ExtractorError('Incomplete data received', expected=True)
be5c1ae8 813 continue
814
815 return response
109dd3b2 816
9297939e 817 @staticmethod
818 def is_music_url(url):
819 return re.match(r'https?://music\.youtube\.com/', url) is not None
820
30a074c2 821 def _extract_video(self, renderer):
822 video_id = renderer.get('videoId')
052e1350 823 title = self._get_text(renderer, 'title')
824 description = self._get_text(renderer, 'descriptionSnippet')
a353beba 825 duration = parse_duration(self._get_text(
826 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 827 if duration is None:
828 duration = parse_duration(self._search_regex(
829 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
830 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
831 video_id, default=None, group='duration'))
832
f0d785d3 833 view_count = self._get_count(renderer, 'viewCountText')
fe93e2c4 834
052e1350 835 uploader = self._get_text(renderer, 'ownerText', 'shortBylineText')
f3aa3c3f 836 channel_id = traverse_obj(
a44ca5a4 837 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
838 expected_type=str, get_all=False)
f3aa3c3f 839 timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText')
840 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
841 overlay_style = traverse_obj(
a44ca5a4 842 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
843 get_all=False, expected_type=str)
f3aa3c3f 844 badges = self._extract_badges(renderer)
a709d873 845 thumbnails = self._extract_thumbnails(renderer, 'thumbnail')
fd2ad7cb 846 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 847 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
848 expected_type=str)) or ''
fd2ad7cb 849 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 850 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 851 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 852
30a074c2 853 return {
39ed931e 854 '_type': 'url',
30a074c2 855 'ie_key': YoutubeIE.ie_key(),
856 'id': video_id,
fd2ad7cb 857 'url': url,
30a074c2 858 'title': title,
859 'description': description,
860 'duration': duration,
861 'view_count': view_count,
862 'uploader': uploader,
f3aa3c3f 863 'channel_id': channel_id,
a709d873 864 'thumbnails': thumbnails,
a44ca5a4 865 'upload_date': (strftime_or_none(timestamp, '%Y%m%d')
866 if self._configuration_arg('approximate_date', ie_key='youtubetab')
867 else None),
f3aa3c3f 868 'live_status': ('is_upcoming' if scheduled_timestamp is not None
869 else 'was_live' if 'streamed' in time_text.lower()
870 else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges
871 else None),
872 'release_timestamp': scheduled_timestamp,
873 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges)
30a074c2 874 }
875
0c148415 876
360e1ca5 877class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 878 IE_DESC = 'YouTube'
cb7dfeea 879 _VALID_URL = r"""(?x)^
c5e8d7af 880 (
edb53e2d 881 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 882 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
883 (?:www\.)?deturl\.com/www\.youtube\.com|
884 (?:www\.)?pwnyoutube\.com|
885 (?:www\.)?hooktube\.com|
886 (?:www\.)?yourepeat\.com|
887 tube\.majestyc\.net|
888 %(invidious)s|
889 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
890 (?:.*?\#/)? # handle anchor (#/) redirect urls
891 (?: # the various things that can precede the ID:
b6ce9bb0 892 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 893 |(?: # or the v= param in all its forms
f7000f3a 894 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 895 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 896 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
897 v=
898 )
f4b05232 899 ))
cbaed4bb
S
900 |(?:
901 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
902 vid\.plus| # or vid.plus/xxxx
903 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 904 %(invidious)s
cbaed4bb 905 )/
edb53e2d 906 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 907 )
c5e8d7af 908 )? # all until now is optional -> you can pass the naked ID
201c1459 909 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 910 (?(1).+)? # if we found the ID, everything can follow
9297939e 911 (?:\#|$)""" % {
d9190e44 912 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 913 }
bfd973ec 914 _EMBED_REGEX = [r'''(?x)
915 (?:
916 <iframe[^>]+?src=|
917 data-video-url=|
918 <embed[^>]+?src=|
919 embedSWF\(?:\s*|
920 <object[^>]+data=|
921 new\s+SWFObject\(
922 )
923 (["\'])
924 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
925 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
926 \1''']
e40c758c 927 _PLAYER_INFO_RE = (
cc2db878 928 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
929 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
545cc85d 930 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 931 )
2c62dc26 932 _formats = {
c2d3cb4c 933 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
934 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
935 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
936 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
937 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
938 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
939 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
940 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 941 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 942 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
943 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
944 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
945 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
946 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
947 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 948 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 949 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
950 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 951
952
953 # 3D videos
c2d3cb4c 954 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
955 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
956 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
957 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 958 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
959 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
960 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 961
96fb5605 962 # Apple HTTP Live Streaming
11f12195 963 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 964 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
965 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
966 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
967 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
968 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 969 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
970 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
971
972 # DASH mp4 video
d23028a8
S
973 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
974 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
975 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
976 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
977 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 978 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
979 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
980 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
981 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
982 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
983 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
984 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 985
f6f1fc92 986 # Dash mp4 audio
d23028a8
S
987 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
988 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
989 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
990 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
991 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
992 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
993 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
994
995 # Dash webm
d23028a8
S
996 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
997 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
998 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
999 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1000 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1001 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1002 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1003 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1004 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1005 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1006 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1007 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1008 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1009 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1010 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1011 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1012 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1013 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1014 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1015 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1016 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1017 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1018
1019 # Dash webm audio
d23028a8
S
1020 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1021 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1022
0857baad 1023 # Dash webm audio with opus inside
d23028a8
S
1024 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1025 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1026 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1027
ce6b9a2d
PH
1028 # RTMP (unnamed)
1029 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1030
1031 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1032 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1033 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1034 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1035 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1036 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1037 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1038 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1039 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1040 }
29f7c58a 1041 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1042
fd5c4aab
S
1043 _GEO_BYPASS = False
1044
78caa52a 1045 IE_NAME = 'youtube'
2eb88d95
PH
1046 _TESTS = [
1047 {
2d3d2997 1048 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1049 'info_dict': {
1050 'id': 'BaW_jenozKc',
1051 'ext': 'mp4',
3867038a 1052 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
4bc3a23e
PH
1053 'uploader': 'Philipp Hagemeister',
1054 'uploader_id': 'phihag',
ec85ded8 1055 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
ff9f925b 1056 'channel': 'Philipp Hagemeister',
dd4c4492
S
1057 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1058 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1059 'upload_date': '20121002',
ff9f925b 1060 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1061 'categories': ['Science & Technology'],
3867038a 1062 'tags': ['youtube-dl'],
556dbe7f 1063 'duration': 10,
dbdaaa23 1064 'view_count': int,
3e7c1224 1065 'like_count': int,
ff9f925b 1066 'availability': 'public',
1067 'playable_in_embed': True,
1068 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1069 'live_status': 'not_live',
1070 'age_limit': 0,
7c80519c 1071 'start_time': 1,
297a564b 1072 'end_time': 9,
12a1b225 1073 'comment_count': int,
6c73052c 1074 'channel_follower_count': int
2eb88d95 1075 }
0e853ca4 1076 },
fccd3771 1077 {
4bc3a23e
PH
1078 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1079 'note': 'Embed-only video (#1746)',
1080 'info_dict': {
1081 'id': 'yZIXLfi8CZQ',
1082 'ext': 'mp4',
1083 'upload_date': '20120608',
1084 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1085 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1086 'uploader': 'SET India',
94bfcd23 1087 'uploader_id': 'setindia',
ec85ded8 1088 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
94bfcd23 1089 'age_limit': 18,
545cc85d 1090 },
1091 'skip': 'Private video',
fccd3771 1092 },
11b56058 1093 {
8bdd16b4 1094 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1095 'note': 'Use the first video ID in the URL',
1096 'info_dict': {
1097 'id': 'BaW_jenozKc',
1098 'ext': 'mp4',
3867038a 1099 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
11b56058
PM
1100 'uploader': 'Philipp Hagemeister',
1101 'uploader_id': 'phihag',
ec85ded8 1102 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
976ae3ea 1103 'channel': 'Philipp Hagemeister',
1104 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1105 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1106 'upload_date': '20121002',
976ae3ea 1107 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1108 'categories': ['Science & Technology'],
3867038a 1109 'tags': ['youtube-dl'],
556dbe7f 1110 'duration': 10,
dbdaaa23 1111 'view_count': int,
11b56058 1112 'like_count': int,
976ae3ea 1113 'availability': 'public',
1114 'playable_in_embed': True,
1115 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1116 'live_status': 'not_live',
1117 'age_limit': 0,
12a1b225 1118 'comment_count': int,
6c73052c 1119 'channel_follower_count': int
34a7de29
S
1120 },
1121 'params': {
1122 'skip_download': True,
1123 },
11b56058 1124 },
dd27fd17 1125 {
2d3d2997 1126 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1127 'note': '256k DASH audio (format 141) via DASH manifest',
1128 'info_dict': {
1129 'id': 'a9LDPn-MO4I',
1130 'ext': 'm4a',
1131 'upload_date': '20121002',
1132 'uploader_id': '8KVIDEO',
ec85ded8 1133 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
1134 'description': '',
1135 'uploader': '8KVIDEO',
1136 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1137 },
4bc3a23e
PH
1138 'params': {
1139 'youtube_include_dash_manifest': True,
1140 'format': '141',
4919603f 1141 },
de3c7fe0 1142 'skip': 'format 141 not served anymore',
dd27fd17 1143 },
8bdd16b4 1144 # DASH manifest with encrypted signature
1145 {
1146 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1147 'info_dict': {
1148 'id': 'IB3lcPjvWLA',
1149 'ext': 'm4a',
1150 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1151 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1152 'duration': 244,
1153 'uploader': 'AfrojackVEVO',
1154 'uploader_id': 'AfrojackVEVO',
1155 'upload_date': '20131011',
cc2db878 1156 'abr': 129.495,
976ae3ea 1157 'like_count': int,
1158 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1159 'playable_in_embed': True,
1160 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1161 'view_count': int,
1162 'track': 'The Spark',
1163 'live_status': 'not_live',
1164 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1165 'channel': 'Afrojack',
1166 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1167 'tags': 'count:19',
1168 'availability': 'public',
1169 'categories': ['Music'],
1170 'age_limit': 0,
1171 'alt_title': 'The Spark',
6c73052c 1172 'channel_follower_count': int
8bdd16b4 1173 },
1174 'params': {
1175 'youtube_include_dash_manifest': True,
1176 'format': '141/bestaudio[ext=m4a]',
1177 },
1178 },
65c2fde2 1179 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1180 {
65c2fde2 1181 'note': 'Embed allowed age-gate video',
2d3d2997 1182 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1183 'info_dict': {
1184 'id': 'HtVdAasjOgU',
1185 'ext': 'mp4',
1186 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1187 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1188 'duration': 142,
c522adb1
JMF
1189 'uploader': 'The Witcher',
1190 'uploader_id': 'WitcherGame',
ec85ded8 1191 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 1192 'upload_date': '20140605',
34952f09 1193 'age_limit': 18,
976ae3ea 1194 'categories': ['Gaming'],
1195 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1196 'availability': 'needs_auth',
1197 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1198 'like_count': int,
1199 'channel': 'The Witcher',
1200 'live_status': 'not_live',
1201 'tags': 'count:17',
1202 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1203 'playable_in_embed': True,
1204 'view_count': int,
6c73052c 1205 'channel_follower_count': int
c522adb1
JMF
1206 },
1207 },
65c2fde2 1208 {
1209 'note': 'Age-gate video with embed allowed in public site',
1210 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1211 'info_dict': {
1212 'id': 'HsUATh_Nc2U',
1213 'ext': 'mp4',
1214 'title': 'Godzilla 2 (Official Video)',
1215 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1216 'upload_date': '20200408',
1217 'uploader_id': 'FlyingKitty900',
1218 'uploader': 'FlyingKitty',
1219 'age_limit': 18,
976ae3ea 1220 'availability': 'needs_auth',
1221 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1222 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1223 'channel': 'FlyingKitty',
1224 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1225 'view_count': int,
1226 'categories': ['Entertainment'],
1227 'live_status': 'not_live',
1228 'tags': ['Flyingkitty', 'godzilla 2'],
1229 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1230 'like_count': int,
1231 'duration': 177,
1232 'playable_in_embed': True,
6c73052c 1233 'channel_follower_count': int
65c2fde2 1234 },
1235 },
1236 {
1237 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1238 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1239 'info_dict': {
1240 'id': 'Tq92D6wQ1mg',
1241 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1242 'ext': 'mp4',
17322130 1243 'upload_date': '20191228',
65c2fde2 1244 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1245 'uploader': 'Projekt Melody',
1246 'description': 'md5:17eccca93a786d51bc67646756894066',
1247 'age_limit': 18,
976ae3ea 1248 'like_count': int,
1249 'availability': 'needs_auth',
1250 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1251 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1252 'view_count': int,
1253 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1254 'channel': 'Projekt Melody',
1255 'live_status': 'not_live',
1256 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1257 'playable_in_embed': True,
1258 'categories': ['Entertainment'],
1259 'duration': 106,
1260 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1261 'comment_count': int,
6c73052c 1262 'channel_follower_count': int
65c2fde2 1263 },
1264 },
1265 {
1266 'note': 'Non-Agegated non-embeddable video',
1267 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1268 'info_dict': {
1269 'id': 'MeJVWBSsPAY',
1270 'ext': 'mp4',
1271 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1272 'uploader': 'Herr Lurik',
1273 'uploader_id': 'st3in234',
1274 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1275 'upload_date': '20130730',
976ae3ea 1276 'track': 'Such mich find mich',
1277 'age_limit': 0,
1278 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1279 'like_count': int,
1280 'playable_in_embed': False,
1281 'creator': 'OOMPH!',
1282 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1283 'view_count': int,
1284 'alt_title': 'Such mich find mich',
1285 'duration': 210,
1286 'channel': 'Herr Lurik',
1287 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1288 'categories': ['Music'],
1289 'availability': 'public',
1290 'uploader_url': 'http://www.youtube.com/user/st3in234',
1291 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1292 'live_status': 'not_live',
1293 'artist': 'OOMPH!',
6c73052c 1294 'channel_follower_count': int
65c2fde2 1295 },
1296 },
1297 {
1298 'note': 'Non-bypassable age-gated video',
1299 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1300 'only_matching': True,
1301 },
8bdd16b4 1302 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1303 # YouTube Red ad is not captured for creator
1304 {
1305 'url': '__2ABJjxzNo',
1306 'info_dict': {
1307 'id': '__2ABJjxzNo',
1308 'ext': 'mp4',
1309 'duration': 266,
1310 'upload_date': '20100430',
1311 'uploader_id': 'deadmau5',
1312 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
545cc85d 1313 'creator': 'deadmau5',
1314 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1315 'uploader': 'deadmau5',
1316 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1317 'alt_title': 'Some Chords',
976ae3ea 1318 'availability': 'public',
1319 'tags': 'count:14',
1320 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1321 'view_count': int,
1322 'live_status': 'not_live',
1323 'channel': 'deadmau5',
1324 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1325 'like_count': int,
1326 'track': 'Some Chords',
1327 'artist': 'deadmau5',
1328 'playable_in_embed': True,
1329 'age_limit': 0,
1330 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1331 'categories': ['Music'],
1332 'album': 'Some Chords',
6c73052c 1333 'channel_follower_count': int
8bdd16b4 1334 },
1335 'expected_warnings': [
1336 'DASH manifest missing',
1337 ]
1338 },
067aa17e 1339 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1340 {
1341 'url': 'lqQg6PlCWgI',
1342 'info_dict': {
1343 'id': 'lqQg6PlCWgI',
1344 'ext': 'mp4',
556dbe7f 1345 'duration': 6085,
90227264 1346 'upload_date': '20150827',
cbe2bd91 1347 'uploader_id': 'olympic',
ec85ded8 1348 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
12a1b225 1349 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
11f9be09 1350 'uploader': 'Olympics',
cbe2bd91 1351 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1352 'like_count': int,
1353 'release_timestamp': 1343767800,
1354 'playable_in_embed': True,
1355 'categories': ['Sports'],
1356 'release_date': '20120731',
1357 'channel': 'Olympics',
1358 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1359 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1360 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1361 'age_limit': 0,
1362 'availability': 'public',
1363 'live_status': 'was_live',
1364 'view_count': int,
1365 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
6c73052c 1366 'channel_follower_count': int
cbe2bd91
PH
1367 },
1368 'params': {
1369 'skip_download': 'requires avconv',
e52a40ab 1370 }
cbe2bd91 1371 },
6271f1ca
PH
1372 # Non-square pixels
1373 {
1374 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1375 'info_dict': {
1376 'id': '_b-2C3KPAM0',
1377 'ext': 'mp4',
1378 'stretched_ratio': 16 / 9.,
556dbe7f 1379 'duration': 85,
6271f1ca
PH
1380 'upload_date': '20110310',
1381 'uploader_id': 'AllenMeow',
ec85ded8 1382 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca 1383 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
eb6793ba 1384 'uploader': '孫ᄋᄅ',
6271f1ca 1385 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1386 'playable_in_embed': True,
1387 'channel': '孫ᄋᄅ',
1388 'age_limit': 0,
1389 'tags': 'count:11',
1390 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1391 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1392 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1393 'view_count': int,
1394 'categories': ['People & Blogs'],
1395 'like_count': int,
1396 'live_status': 'not_live',
1397 'availability': 'unlisted',
12a1b225 1398 'comment_count': int,
6c73052c 1399 'channel_follower_count': int
6271f1ca 1400 },
06b491eb
S
1401 },
1402 # url_encoded_fmt_stream_map is empty string
1403 {
1404 'url': 'qEJwOuvDf7I',
1405 'info_dict': {
1406 'id': 'qEJwOuvDf7I',
f57b7835 1407 'ext': 'webm',
06b491eb
S
1408 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1409 'description': '',
1410 'upload_date': '20150404',
1411 'uploader_id': 'spbelect',
1412 'uploader': 'Наблюдатели Петербурга',
1413 },
1414 'params': {
1415 'skip_download': 'requires avconv',
e323cf3f
S
1416 },
1417 'skip': 'This live event has ended.',
06b491eb 1418 },
067aa17e 1419 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1420 {
1421 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1422 'info_dict': {
1423 'id': 'FIl7x6_3R5Y',
eb6793ba 1424 'ext': 'webm',
da77d856
S
1425 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1426 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1427 'duration': 220,
da77d856
S
1428 'upload_date': '20150625',
1429 'uploader_id': 'dorappi2000',
ec85ded8 1430 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 1431 'uploader': 'dorappi2000',
eb6793ba 1432 'formats': 'mincount:31',
da77d856 1433 },
eb6793ba 1434 'skip': 'not actual anymore',
2ee8f5d8 1435 },
8a1a26ce
YCH
1436 # DASH manifest with segment_list
1437 {
1438 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1439 'md5': '8ce563a1d667b599d21064e982ab9e31',
1440 'info_dict': {
1441 'id': 'CsmdDsKjzN8',
1442 'ext': 'mp4',
17ee98e1 1443 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
1444 'uploader': 'Airtek',
1445 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1446 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1447 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1448 },
1449 'params': {
1450 'youtube_include_dash_manifest': True,
1451 'format': '135', # bestvideo
be49068d
S
1452 },
1453 'skip': 'This live event has ended.',
2ee8f5d8 1454 },
cf7e015f
S
1455 {
1456 # Multifeed videos (multiple cameras), URL is for Main Camera
545cc85d 1457 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
cf7e015f 1458 'info_dict': {
545cc85d 1459 'id': 'jvGDaLqkpTg',
1460 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1461 'description': 'md5:e03b909557865076822aa169218d6a5d',
cf7e015f
S
1462 },
1463 'playlist': [{
1464 'info_dict': {
545cc85d 1465 'id': 'jvGDaLqkpTg',
cf7e015f 1466 'ext': 'mp4',
545cc85d 1467 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1468 'description': 'md5:e03b909557865076822aa169218d6a5d',
1469 'duration': 10643,
1470 'upload_date': '20161111',
1471 'uploader': 'Team PGP',
1472 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1473 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1474 },
1475 }, {
1476 'info_dict': {
545cc85d 1477 'id': '3AKt1R1aDnw',
cf7e015f 1478 'ext': 'mp4',
545cc85d 1479 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1480 'description': 'md5:e03b909557865076822aa169218d6a5d',
1481 'duration': 10991,
1482 'upload_date': '20161111',
1483 'uploader': 'Team PGP',
1484 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1485 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1486 },
1487 }, {
1488 'info_dict': {
545cc85d 1489 'id': 'RtAMM00gpVc',
cf7e015f 1490 'ext': 'mp4',
545cc85d 1491 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1492 'description': 'md5:e03b909557865076822aa169218d6a5d',
1493 'duration': 10995,
1494 'upload_date': '20161111',
1495 'uploader': 'Team PGP',
1496 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1497 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1498 },
1499 }, {
1500 'info_dict': {
545cc85d 1501 'id': '6N2fdlP3C5U',
cf7e015f 1502 'ext': 'mp4',
545cc85d 1503 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1504 'description': 'md5:e03b909557865076822aa169218d6a5d',
1505 'duration': 10990,
1506 'upload_date': '20161111',
1507 'uploader': 'Team PGP',
1508 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1509 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
cf7e015f
S
1510 },
1511 }],
1512 'params': {
1513 'skip_download': True,
1514 },
65c2fde2 1515 'skip': 'Not multifeed anymore',
cbaed4bb 1516 },
f9f49d87 1517 {
067aa17e 1518 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1519 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1520 'info_dict': {
1521 'id': 'gVfLd0zydlo',
1522 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1523 },
1524 'playlist_count': 2,
be49068d 1525 'skip': 'Not multifeed anymore',
f9f49d87 1526 },
cbaed4bb 1527 {
2d3d2997 1528 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1529 'only_matching': True,
0e49d9a6 1530 },
6d4fc66b 1531 {
2d3d2997 1532 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1533 'only_matching': True,
1534 },
0e49d9a6 1535 {
067aa17e 1536 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1537 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1538 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1539 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1540 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1541 'info_dict': {
1542 'id': 'lsguqyKfVQg',
1543 'ext': 'mp4',
1544 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1545 'alt_title': 'Dark Walk',
0e49d9a6 1546 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1547 'duration': 133,
0e49d9a6
LL
1548 'upload_date': '20151119',
1549 'uploader_id': 'IronSoulElf',
ec85ded8 1550 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 1551 'uploader': 'IronSoulElf',
11f9be09 1552 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1553 'track': 'Dark Walk',
1554 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1555 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1556 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1557 'categories': ['Film & Animation'],
1558 'view_count': int,
1559 'live_status': 'not_live',
1560 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1561 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1562 'tags': 'count:13',
1563 'availability': 'public',
1564 'channel': 'IronSoulElf',
1565 'playable_in_embed': True,
1566 'like_count': int,
1567 'age_limit': 0,
6c73052c 1568 'channel_follower_count': int
0e49d9a6
LL
1569 },
1570 'params': {
1571 'skip_download': True,
1572 },
1573 },
61f92af1 1574 {
067aa17e 1575 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1576 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1577 'only_matching': True,
1578 },
313dfc45
LL
1579 {
1580 # Video with yt:stretch=17:0
1581 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1582 'info_dict': {
1583 'id': 'Q39EVAstoRM',
1584 'ext': 'mp4',
1585 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1586 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1587 'upload_date': '20151107',
1588 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1589 'uploader': 'CH GAMER DROID',
1590 },
1591 'params': {
1592 'skip_download': True,
1593 },
be49068d 1594 'skip': 'This video does not exist.',
313dfc45 1595 },
201c1459 1596 {
1597 # Video with incomplete 'yt:stretch=16:'
1598 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1599 'only_matching': True,
1600 },
7caf9830
S
1601 {
1602 # Video licensed under Creative Commons
1603 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1604 'info_dict': {
1605 'id': 'M4gD1WSo5mA',
1606 'ext': 'mp4',
1607 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1608 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1609 'duration': 721,
17322130 1610 'upload_date': '20150128',
7caf9830 1611 'uploader_id': 'BerkmanCenter',
ec85ded8 1612 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
556dbe7f 1613 'uploader': 'The Berkman Klein Center for Internet & Society',
7caf9830 1614 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1615 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1616 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1617 'like_count': int,
1618 'age_limit': 0,
1619 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1620 'channel': 'The Berkman Klein Center for Internet & Society',
1621 'availability': 'public',
1622 'view_count': int,
1623 'categories': ['Education'],
1624 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1625 'live_status': 'not_live',
1626 'playable_in_embed': True,
12a1b225 1627 'comment_count': int,
6c73052c 1628 'channel_follower_count': int
7caf9830
S
1629 },
1630 'params': {
1631 'skip_download': True,
1632 },
1633 },
fd050249
S
1634 {
1635 # Channel-like uploader_url
1636 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1637 'info_dict': {
1638 'id': 'eQcmzGIKrzg',
1639 'ext': 'mp4',
1640 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1641 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1642 'duration': 4060,
17322130 1643 'upload_date': '20151120',
eb6793ba 1644 'uploader': 'Bernie Sanders',
fd050249 1645 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
ec85ded8 1646 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
fd050249 1647 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1648 'playable_in_embed': True,
1649 'tags': 'count:12',
1650 'like_count': int,
1651 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1652 'age_limit': 0,
1653 'availability': 'public',
1654 'categories': ['News & Politics'],
1655 'channel': 'Bernie Sanders',
1656 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1657 'view_count': int,
1658 'live_status': 'not_live',
1659 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1660 'comment_count': int,
6c73052c 1661 'channel_follower_count': int
fd050249
S
1662 },
1663 'params': {
1664 'skip_download': True,
1665 },
1666 },
040ac686
S
1667 {
1668 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1669 'only_matching': True,
7f29cf54
S
1670 },
1671 {
067aa17e 1672 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1673 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1674 'only_matching': True,
6496ccb4
S
1675 },
1676 {
1677 # Rental video preview
1678 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1679 'info_dict': {
1680 'id': 'uGpuVWrhIzE',
1681 'ext': 'mp4',
1682 'title': 'Piku - Trailer',
1683 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1684 'upload_date': '20150811',
1685 'uploader': 'FlixMatrix',
1686 'uploader_id': 'FlixMatrixKaravan',
ec85ded8 1687 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
6496ccb4
S
1688 'license': 'Standard YouTube License',
1689 },
1690 'params': {
1691 'skip_download': True,
1692 },
eb6793ba 1693 'skip': 'This video is not available.',
022a5d66 1694 },
12afdc2a
S
1695 {
1696 # YouTube Red video with episode data
1697 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1698 'info_dict': {
1699 'id': 'iqKdEhx-dD4',
1700 'ext': 'mp4',
1701 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1702 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1703 'duration': 2085,
12afdc2a
S
1704 'upload_date': '20170118',
1705 'uploader': 'Vsauce',
1706 'uploader_id': 'Vsauce',
1707 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
12afdc2a
S
1708 'series': 'Mind Field',
1709 'season_number': 1,
1710 'episode_number': 1,
976ae3ea 1711 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1712 'tags': 'count:12',
1713 'view_count': int,
1714 'availability': 'public',
1715 'age_limit': 0,
1716 'channel': 'Vsauce',
1717 'episode': 'Episode 1',
1718 'categories': ['Entertainment'],
1719 'season': 'Season 1',
1720 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1721 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1722 'like_count': int,
1723 'playable_in_embed': True,
1724 'live_status': 'not_live',
6c73052c 1725 'channel_follower_count': int
12afdc2a
S
1726 },
1727 'params': {
1728 'skip_download': True,
1729 },
1730 'expected_warnings': [
1731 'Skipping DASH manifest',
1732 ],
1733 },
c7121fa7
S
1734 {
1735 # The following content has been identified by the YouTube community
1736 # as inappropriate or offensive to some audiences.
1737 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1738 'info_dict': {
1739 'id': '6SJNVb0GnPI',
1740 'ext': 'mp4',
1741 'title': 'Race Differences in Intelligence',
1742 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1743 'duration': 965,
1744 'upload_date': '20140124',
1745 'uploader': 'New Century Foundation',
1746 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1747 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
c7121fa7
S
1748 },
1749 'params': {
1750 'skip_download': True,
1751 },
545cc85d 1752 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 1753 },
022a5d66
S
1754 {
1755 # itag 212
1756 'url': '1t24XAntNCY',
1757 'only_matching': True,
fd5c4aab
S
1758 },
1759 {
1760 # geo restricted to JP
1761 'url': 'sJL6WA-aGkQ',
1762 'only_matching': True,
1763 },
cd5a74a2
S
1764 {
1765 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1766 'only_matching': True,
1767 },
bc2ca1bb 1768 {
1769 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1770 'only_matching': True,
1771 },
1772 {
1773 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1774 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1775 'only_matching': True,
1776 },
825cd268
RA
1777 {
1778 # DRM protected
1779 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1780 'only_matching': True,
4fe54c12
S
1781 },
1782 {
1783 # Video with unsupported adaptive stream type formats
1784 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1785 'info_dict': {
1786 'id': 'Z4Vy8R84T1U',
1787 'ext': 'mp4',
1788 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1789 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1790 'duration': 433,
1791 'upload_date': '20130923',
1792 'uploader': 'Amelia Putri Harwita',
1793 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1794 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1795 'formats': 'maxcount:10',
1796 },
1797 'params': {
1798 'skip_download': True,
1799 'youtube_include_dash_manifest': False,
1800 },
5429d6a9 1801 'skip': 'not actual anymore',
5caabd3c 1802 },
1803 {
822b9d9c 1804 # Youtube Music Auto-generated description
5caabd3c 1805 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1806 'info_dict': {
1807 'id': 'MgNrAu2pzNs',
1808 'ext': 'mp4',
1809 'title': 'Voyeur Girl',
1810 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1811 'upload_date': '20190312',
5429d6a9
S
1812 'uploader': 'Stephen - Topic',
1813 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
5caabd3c 1814 'artist': 'Stephen',
1815 'track': 'Voyeur Girl',
1816 'album': 'it\'s too much love to know my dear',
1817 'release_date': '20190313',
1818 'release_year': 2019,
976ae3ea 1819 'alt_title': 'Voyeur Girl',
1820 'view_count': int,
1821 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1822 'playable_in_embed': True,
1823 'like_count': int,
1824 'categories': ['Music'],
1825 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1826 'channel': 'Stephen',
1827 'availability': 'public',
1828 'creator': 'Stephen',
1829 'duration': 169,
1830 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1831 'age_limit': 0,
1832 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1833 'tags': 'count:11',
1834 'live_status': 'not_live',
6c73052c 1835 'channel_follower_count': int
5caabd3c 1836 },
1837 'params': {
1838 'skip_download': True,
1839 },
1840 },
66b48727
RA
1841 {
1842 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1843 'only_matching': True,
1844 },
011e75e6
S
1845 {
1846 # invalid -> valid video id redirection
1847 'url': 'DJztXj2GPfl',
1848 'info_dict': {
1849 'id': 'DJztXj2GPfk',
1850 'ext': 'mp4',
1851 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1852 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1853 'upload_date': '20090125',
1854 'uploader': 'Prochorowka',
1855 'uploader_id': 'Prochorowka',
1856 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1857 'artist': 'Panjabi MC',
1858 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1859 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1860 },
1861 'params': {
1862 'skip_download': True,
1863 },
545cc85d 1864 'skip': 'Video unavailable',
ea74e00b
DP
1865 },
1866 {
1867 # empty description results in an empty string
1868 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1869 'info_dict': {
1870 'id': 'x41yOUIvK2k',
1871 'ext': 'mp4',
1872 'title': 'IMG 3456',
1873 'description': '',
1874 'upload_date': '20170613',
1875 'uploader_id': 'ElevageOrVert',
1876 'uploader': 'ElevageOrVert',
976ae3ea 1877 'view_count': int,
1878 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1879 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1880 'like_count': int,
1881 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1882 'tags': [],
1883 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1884 'availability': 'public',
1885 'age_limit': 0,
1886 'categories': ['Pets & Animals'],
1887 'duration': 7,
1888 'playable_in_embed': True,
1889 'live_status': 'not_live',
1890 'channel': 'ElevageOrVert',
6c73052c 1891 'channel_follower_count': int
ea74e00b
DP
1892 },
1893 'params': {
1894 'skip_download': True,
1895 },
1896 },
a0566bbf 1897 {
29f7c58a 1898 # with '};' inside yt initial data (see [1])
1899 # see [2] for an example with '};' inside ytInitialPlayerResponse
1900 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1901 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 1902 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1903 'info_dict': {
1904 'id': 'CHqg6qOn4no',
1905 'ext': 'mp4',
1906 'title': 'Part 77 Sort a list of simple types in c#',
1907 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1908 'upload_date': '20130831',
1909 'uploader_id': 'kudvenkat',
1910 'uploader': 'kudvenkat',
976ae3ea 1911 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1912 'like_count': int,
1913 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1914 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1915 'live_status': 'not_live',
1916 'categories': ['Education'],
1917 'availability': 'public',
1918 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1919 'tags': 'count:12',
1920 'playable_in_embed': True,
1921 'age_limit': 0,
1922 'view_count': int,
1923 'duration': 522,
1924 'channel': 'kudvenkat',
12a1b225 1925 'comment_count': int,
6c73052c 1926 'channel_follower_count': int
a0566bbf 1927 },
1928 'params': {
1929 'skip_download': True,
1930 },
1931 },
29f7c58a 1932 {
1933 # another example of '};' in ytInitialData
1934 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1935 'only_matching': True,
1936 },
1937 {
1938 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1939 'only_matching': True,
1940 },
545cc85d 1941 {
cc2db878 1942 # https://github.com/ytdl-org/youtube-dl/pull/28094
1943 'url': 'OtqTfy26tG0',
1944 'info_dict': {
1945 'id': 'OtqTfy26tG0',
1946 'ext': 'mp4',
1947 'title': 'Burn Out',
1948 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1949 'upload_date': '20141120',
1950 'uploader': 'The Cinematic Orchestra - Topic',
1951 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1952 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1953 'artist': 'The Cinematic Orchestra',
1954 'track': 'Burn Out',
1955 'album': 'Every Day',
976ae3ea 1956 'like_count': int,
1957 'live_status': 'not_live',
1958 'alt_title': 'Burn Out',
1959 'duration': 614,
1960 'age_limit': 0,
1961 'view_count': int,
1962 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1963 'creator': 'The Cinematic Orchestra',
1964 'channel': 'The Cinematic Orchestra',
1965 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1966 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1967 'availability': 'public',
1968 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1969 'categories': ['Music'],
1970 'playable_in_embed': True,
6c73052c 1971 'channel_follower_count': int
cc2db878 1972 },
1973 'params': {
1974 'skip_download': True,
1975 },
545cc85d 1976 },
bc2ca1bb 1977 {
1978 # controversial video, only works with bpctr when authenticated with cookies
1979 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1980 'only_matching': True,
1981 },
a1a7907b 1982 {
1983 # controversial video, requires bpctr/contentCheckOk
1984 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1985 'info_dict': {
1986 'id': 'SZJvDhaSDnc',
1987 'ext': 'mp4',
1988 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1989 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
976ae3ea 1990 'uploader': 'CBS Mornings',
11f9be09 1991 'uploader_id': 'CBSThisMorning',
a1a7907b 1992 'upload_date': '20140716',
976ae3ea 1993 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1994 'duration': 170,
1995 'categories': ['News & Politics'],
1996 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1997 'view_count': int,
1998 'channel': 'CBS Mornings',
1999 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2000 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2001 'age_limit': 18,
2002 'availability': 'needs_auth',
2003 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2004 'like_count': int,
2005 'live_status': 'not_live',
2006 'playable_in_embed': True,
6c73052c 2007 'channel_follower_count': int
a1a7907b 2008 }
2009 },
f7ad7160 2010 {
2011 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2012 'url': 'cBvYw8_A0vQ',
2013 'info_dict': {
2014 'id': 'cBvYw8_A0vQ',
2015 'ext': 'mp4',
2016 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2017 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2018 'upload_date': '20201120',
2019 'uploader': 'Walk around Japan',
2020 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2021 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
976ae3ea 2022 'duration': 1456,
2023 'categories': ['Travel & Events'],
2024 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2025 'view_count': int,
2026 'channel': 'Walk around Japan',
2027 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2028 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2029 'age_limit': 0,
2030 'availability': 'public',
2031 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2032 'live_status': 'not_live',
2033 'playable_in_embed': True,
6c73052c 2034 'channel_follower_count': int
f7ad7160 2035 },
2036 'params': {
2037 'skip_download': True,
2038 },
0fb983f6 2039 }, {
2040 # Has multiple audio streams
2041 'url': 'WaOKSUlf4TM',
2042 'only_matching': True
9297939e 2043 }, {
2044 # Requires Premium: has format 141 when requested using YTM url
2045 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2046 'only_matching': True
2047 }, {
120916da 2048 # multiple subtitles with same lang_code
2049 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2050 'only_matching': True,
109dd3b2 2051 }, {
2052 # Force use android client fallback
2053 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2054 'info_dict': {
2055 'id': 'YOelRv7fMxY',
11f9be09 2056 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2057 'ext': '3gp',
2058 'upload_date': '20210624',
2059 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2060 'uploader': 'colinfurze',
11f9be09 2061 'uploader_id': 'colinfurze',
109dd3b2 2062 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2063 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2064 'duration': 596,
2065 'categories': ['Entertainment'],
2066 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2067 'view_count': int,
2068 'channel': 'colinfurze',
2069 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2070 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2071 'age_limit': 0,
2072 'availability': 'public',
2073 'like_count': int,
2074 'live_status': 'not_live',
2075 'playable_in_embed': True,
6c73052c 2076 'channel_follower_count': int
109dd3b2 2077 },
2078 'params': {
2079 'format': '17', # 3gp format available on android
2080 'extractor_args': {'youtube': {'player_client': ['android']}},
2081 },
120916da 2082 },
109dd3b2 2083 {
2084 # Skip download of additional client configs (remix client config in this case)
2085 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2086 'only_matching': True,
2087 'params': {
2088 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2089 },
8fc54b12 2090 }, {
2091 # shorts
2092 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2093 'only_matching': True,
9222c381 2094 }, {
2095 'note': 'Storyboards',
2096 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2097 'info_dict': {
2098 'id': '5KLPxDtMqe8',
2099 'ext': 'mhtml',
2100 'format_id': 'sb0',
2101 'title': 'Your Brain is Plastic',
2102 'uploader_id': 'scishow',
2103 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2104 'upload_date': '20140324',
2105 'uploader': 'SciShow',
976ae3ea 2106 'like_count': int,
2107 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2108 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2109 'view_count': int,
2110 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2111 'playable_in_embed': True,
2112 'tags': 'count:12',
2113 'uploader_url': 'http://www.youtube.com/user/scishow',
2114 'availability': 'public',
2115 'channel': 'SciShow',
2116 'live_status': 'not_live',
2117 'duration': 248,
2118 'categories': ['Education'],
2119 'age_limit': 0,
6c73052c 2120 'channel_follower_count': int
9222c381 2121 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2122 }, {
2123 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2124 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2125 'info_dict': {
2126 'id': '2NUZ8W2llS4',
2127 'ext': 'mp4',
2128 'title': 'The NP that test your phone performance 🙂',
2129 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2130 'uploader': 'Leon Nguyen',
2131 'uploader_id': 'VNSXIII',
2132 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2133 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2134 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2135 'duration': 21,
2136 'view_count': int,
2137 'age_limit': 0,
2138 'categories': ['Gaming'],
2139 'tags': 'count:23',
2140 'playable_in_embed': True,
2141 'live_status': 'not_live',
2142 'upload_date': '20220103',
2143 'like_count': int,
2144 'availability': 'public',
2145 'channel': 'Leon Nguyen',
2146 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2147 'comment_count': int,
992f9a73 2148 'channel_follower_count': int
2149 }
2150 }, {
2151 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2152 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2153 'info_dict': {
2154 'id': 'mzZzzBU6lrM',
2155 'ext': 'mp4',
2156 'title': 'I Met GeorgeNotFound In Real Life...',
2157 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2158 'uploader': 'Quackity',
2159 'uploader_id': 'QuackityHQ',
2160 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2161 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2162 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2163 'duration': 955,
2164 'view_count': int,
2165 'age_limit': 0,
2166 'categories': ['Entertainment'],
2167 'tags': 'count:26',
2168 'playable_in_embed': True,
2169 'live_status': 'not_live',
2170 'release_timestamp': 1641172509,
2171 'release_date': '20220103',
2172 'upload_date': '20220103',
2173 'like_count': int,
2174 'availability': 'public',
2175 'channel': 'Quackity',
2176 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2177 'channel_follower_count': int
2178 }
2179 },
2180 { # continuous livestream. Microformat upload date should be preferred.
2181 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2182 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2183 'info_dict': {
2184 'id': 'kgx4WGK0oNU',
2185 'title': r're:jazz\/lofi hip hop radio🌱chill beats to relax\/study to \[LIVE 24\/7\] \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
2186 'ext': 'mp4',
2187 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2188 'availability': 'public',
2189 'age_limit': 0,
2190 'release_timestamp': 1637975704,
2191 'upload_date': '20210619',
2192 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2193 'live_status': 'is_live',
2194 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2195 'uploader': '阿鲍Abao',
2196 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2197 'channel': 'Abao in Tokyo',
2198 'channel_follower_count': int,
2199 'release_date': '20211127',
2200 'tags': 'count:39',
2201 'categories': ['People & Blogs'],
2202 'like_count': int,
2203 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2204 'view_count': int,
2205 'playable_in_embed': True,
2206 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2207 },
2208 'params': {'skip_download': True}
6e634cbe 2209 }, {
2210 # Story. Requires specific player params to work.
ee27297f 2211 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2212 'info_dict': {
ee27297f 2213 'id': 'vv8qTUWmulI',
6e634cbe 2214 'ext': 'mp4',
ee27297f 2215 'availability': 'unlisted',
2216 'view_count': int,
2217 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2218 'upload_date': '20220526',
2219 'categories': ['Education'],
2220 'title': 'Story',
2221 'channel': 'IT\'S HISTORY',
2222 'description': '',
2223 'uploader_id': 'BlastfromthePast',
2224 'duration': 12,
2225 'uploader': 'IT\'S HISTORY',
6e634cbe 2226 'playable_in_embed': True,
6e634cbe 2227 'age_limit': 0,
6e634cbe 2228 'live_status': 'not_live',
ee27297f 2229 'tags': [],
2230 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2231 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2232 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
12a1b225
A
2233 },
2234 'skip': 'stories get removed after some period of time',
ee27297f 2235 }, {
2236 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2237 'info_dict': {
2238 'id': 'tjjjtzRLHvA',
2239 'ext': 'mp4',
2240 'title': 'ハッシュタグ無し };if window.ytcsi',
2241 'upload_date': '20220323',
2242 'like_count': int,
2243 'availability': 'unlisted',
2244 'channel': 'nao20010128nao',
2245 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2246 'age_limit': 0,
2247 'uploader': 'nao20010128nao',
2248 'uploader_id': 'nao20010128nao',
2249 'categories': ['Music'],
6e634cbe 2250 'view_count': int,
2251 'description': '',
ee27297f 2252 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2253 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2254 'live_status': 'not_live',
2255 'playable_in_embed': True,
2256 'channel_follower_count': int,
2257 'duration': 6,
2258 'tags': [],
2259 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
6e634cbe 2260 }
a4166234 2261 }, {
2262 'note': '6 channel audio',
2263 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2264 'only_matching': True,
6e634cbe 2265 }
2eb88d95
PH
2266 ]
2267
f2e8dbcc 2268 _WEBPAGE_TESTS = [
2269 # YouTube <object> embed
2270 {
2271 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2272 'md5': '873c81d308b979f0e23ee7e620b312a3',
2273 'info_dict': {
2274 'id': 'msN87y-iEx0',
2275 'ext': 'mp4',
2276 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2277 'upload_date': '20080526',
2278 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2279 'uploader': 'Christopher Sykes',
2280 'uploader_id': 'ChristopherJSykes',
2281 'age_limit': 0,
2282 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2283 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2284 'playable_in_embed': True,
2285 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2286 'like_count': int,
2287 'comment_count': int,
2288 'channel': 'Christopher Sykes',
2289 'live_status': 'not_live',
2290 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2291 'availability': 'public',
2292 'duration': 195,
2293 'view_count': int,
2294 'categories': ['Science & Technology'],
2295 'channel_follower_count': int,
2296 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2297 },
2298 'params': {
2299 'skip_download': True,
2300 }
2301 },
2302 ]
2303
201c1459 2304 @classmethod
2305 def suitable(cls, url):
4dfbf869 2306 from ..utils import parse_qs
2307
201c1459 2308 qs = parse_qs(url)
2309 if qs.get('list', [None])[0]:
2310 return False
86e5f3ed 2311 return super().suitable(url)
201c1459 2312
e0df6211 2313 def __init__(self, *args, **kwargs):
86e5f3ed 2314 super().__init__(*args, **kwargs)
545cc85d 2315 self._code_cache = {}
83799698 2316 self._player_cache = {}
e0df6211 2317
adbc4ec4 2318 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
adbc4ec4
THD
2319 lock = threading.Lock()
2320
2321 is_live = True
185bf310 2322 start_time = time.time()
adbc4ec4
THD
2323 formats = [f for f in formats if f.get('is_from_start')]
2324
185bf310 2325 def refetch_manifest(format_id, delay):
2326 nonlocal formats, start_time, is_live
2327 if time.time() <= start_time + delay:
adbc4ec4
THD
2328 return
2329
2330 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2331 video_details = traverse_obj(
2332 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2333 microformats = traverse_obj(
2334 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2335 expected_type=dict, default=[])
c646d76f 2336 _, is_live, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
185bf310 2337 start_time = time.time()
adbc4ec4 2338
185bf310 2339 def mpd_feed(format_id, delay):
adbc4ec4
THD
2340 """
2341 @returns (manifest_url, manifest_stream_number, is_live) or None
2342 """
2343 with lock:
185bf310 2344 refetch_manifest(format_id, delay)
adbc4ec4
THD
2345
2346 f = next((f for f in formats if f['format_id'] == format_id), None)
2347 if not f:
185bf310 2348 if not is_live:
2349 self.to_screen(f'{video_id}: Video is no longer live')
2350 else:
2351 self.report_warning(
2352 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
adbc4ec4
THD
2353 return None
2354 return f['manifest_url'], f['manifest_stream_number'], is_live
2355
2356 for f in formats:
a539f065 2357 f['is_live'] = True
adbc4ec4
THD
2358 f['protocol'] = 'http_dash_segments_generator'
2359 f['fragments'] = functools.partial(
2360 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2361
2362 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2363 FETCH_SPAN, MAX_DURATION = 5, 432000
2364
2365 mpd_url, stream_number, is_live = None, None, True
2366
2367 begin_index = 0
2368 download_start_time = ctx.get('start') or time.time()
2369
2370 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2371 if lack_early_segments:
2372 self.report_warning(bug_reports_message(
2373 'Starting download from the last 120 hours of the live stream since '
2374 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2375 lack_early_segments = True
2376
2377 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2378 fragments, fragment_base_url = None, None
2379
a539f065 2380 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2381 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2382 # Obtain from MPD's maximum seq value
2383 old_mpd_url = mpd_url
185bf310 2384 last_error = ctx.pop('last_error', None)
14f25df2 2385 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2386 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2387 or (mpd_url, stream_number, False))
2388 if not refresh_sequence:
2389 if expire_fast and not is_live:
2390 return False, last_seq
2391 elif old_mpd_url == mpd_url:
2392 return True, last_seq
adbc4ec4
THD
2393 try:
2394 fmts, _ = self._extract_mpd_formats_and_subtitles(
2395 mpd_url, None, note=False, errnote=False, fatal=False)
2396 except ExtractorError:
2397 fmts = None
2398 if not fmts:
a539f065 2399 no_fragment_score += 2
adbc4ec4
THD
2400 return False, last_seq
2401 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2402 fragments = fmt_info['fragments']
2403 fragment_base_url = fmt_info['fragment_base_url']
2404 assert fragment_base_url
2405
2406 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2407 return True, _last_seq
2408
2409 while is_live:
2410 fetch_time = time.time()
2411 if no_fragment_score > 30:
2412 return
2413 if last_segment_url:
2414 # Obtain from "X-Head-Seqnum" header value from each segment
2415 try:
2416 urlh = self._request_webpage(
2417 last_segment_url, None, note=False, errnote=False, fatal=False)
2418 except ExtractorError:
2419 urlh = None
2420 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2421 if last_seq is None:
a539f065 2422 no_fragment_score += 2
adbc4ec4
THD
2423 last_segment_url = None
2424 continue
2425 else:
a539f065
LNO
2426 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2427 no_fragment_score += 2
185bf310 2428 if not should_continue:
adbc4ec4
THD
2429 continue
2430
2431 if known_idx > last_seq:
2432 last_segment_url = None
2433 continue
2434
2435 last_seq += 1
2436
2437 if begin_index < 0 and known_idx < 0:
2438 # skip from the start when it's negative value
2439 known_idx = last_seq + begin_index
2440 if lack_early_segments:
2441 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2442 try:
2443 for idx in range(known_idx, last_seq):
2444 # do not update sequence here or you'll get skipped some part of it
a539f065 2445 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2446 if not should_continue:
adbc4ec4
THD
2447 known_idx = idx - 1
2448 raise ExtractorError('breaking out of outer loop')
2449 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2450 yield {
2451 'url': last_segment_url,
36195c44 2452 'fragment_count': last_seq,
adbc4ec4
THD
2453 }
2454 if known_idx == last_seq:
2455 no_fragment_score += 5
2456 else:
2457 no_fragment_score = 0
2458 known_idx = last_seq
2459 except ExtractorError:
2460 continue
2461
2462 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2463
b6de707d 2464 def _extract_player_url(self, *ytcfgs, webpage=None):
2465 player_url = traverse_obj(
2466 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2467 get_all=False, expected_type=str)
11f9be09 2468 if not player_url:
b6de707d 2469 return
60f393e4 2470 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2471
b6de707d 2472 def _download_player_url(self, video_id, fatal=False):
2473 res = self._download_webpage(
2474 'https://www.youtube.com/iframe_api',
2475 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2476 if res:
2477 player_version = self._search_regex(
2478 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2479 if player_version:
2480 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2481
60064c53
PH
2482 def _signature_cache_id(self, example_sig):
2483 """ Return a string representation of a signature """
14f25df2 2484 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2485
e40c758c
S
2486 @classmethod
2487 def _extract_player_info(cls, player_url):
2488 for player_re in cls._PLAYER_INFO_RE:
2489 id_m = re.search(player_re, player_url)
2490 if id_m:
2491 break
2492 else:
c081b35c 2493 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2494 return id_m.group('id')
e40c758c 2495
404f611f 2496 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2497 player_id = self._extract_player_info(player_url)
2498 if player_id not in self._code_cache:
1276a43a 2499 code = self._download_webpage(
109dd3b2 2500 player_url, video_id, fatal=fatal,
2501 note='Downloading player ' + player_id,
2502 errnote='Download of %s failed' % player_url)
1276a43a 2503 if code:
2504 self._code_cache[player_id] = code
404f611f 2505 return self._code_cache.get(player_id)
109dd3b2 2506
e40c758c 2507 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2508 player_id = self._extract_player_info(player_url)
e0df6211 2509
c4417ddb 2510 # Read from filesystem cache
86e5f3ed 2511 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2512 assert os.path.basename(func_id) == func_id
a0e07d31 2513
ae61d108 2514 self.write_debug(f'Extracting signature function {func_id}')
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 = {}, []
5c6d2ef9 3171 itag_qualities, res_qualities = {}, {0: -1}
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
5c6d2ef9 3323 f['quality'] = itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1)
3324 if f['quality'] == -1 and f.get('height'):
3325 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
a0bb6ce5 3326 return True
2a9c6dcd 3327
c646d76f 3328 subtitles = {}
11f9be09 3329 for sd in streaming_data:
5d3a0e79 3330 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
9297939e 3331 if hls_manifest_url:
c646d76f 3332 fmts, subs = self._extract_m3u8_formats_and_subtitles(hls_manifest_url, video_id, 'mp4', fatal=False, live=is_live)
3333 subtitles = self._merge_subtitles(subs, subtitles)
3334 for f in fmts:
a0bb6ce5 3335 if process_manifest_format(f, 'hls', self._search_regex(
3336 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3337 yield f
545cc85d 3338
5d3a0e79 3339 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3340 if dash_manifest_url:
c646d76f 3341 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3342 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3343 for f in formats:
a0bb6ce5 3344 if process_manifest_format(f, 'dash', f['format_id']):
3345 f['filesize'] = int_or_none(self._search_regex(
3346 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
adbc4ec4
THD
3347 if live_from_start:
3348 f['is_from_start'] = True
3349
a0bb6ce5 3350 yield f
c646d76f 3351 yield subtitles
11f9be09 3352
720c3099 3353 def _extract_storyboard(self, player_responses, duration):
3354 spec = get_first(
3355 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3356 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3357 if not base_url:
720c3099 3358 return
720c3099 3359 L = len(spec) - 1
3360 for i, args in enumerate(spec):
3361 args = args.split('#')
3362 counts = list(map(int_or_none, args[:5]))
3363 if len(args) != 8 or not all(counts):
3364 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3365 continue
3366 width, height, frame_count, cols, rows = counts
3367 N, sigh = args[6:]
3368
3369 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3370 fragment_count = frame_count / (cols * rows)
3371 fragment_duration = duration / fragment_count
3372 yield {
3373 'format_id': f'sb{i}',
3374 'format_note': 'storyboard',
3375 'ext': 'mhtml',
3376 'protocol': 'mhtml',
3377 'acodec': 'none',
3378 'vcodec': 'none',
3379 'url': url,
3380 'width': width,
3381 'height': height,
45e8a04e 3382 'fps': frame_count / duration,
3383 'rows': rows,
3384 'columns': cols,
720c3099 3385 'fragments': [{
b3edc806 3386 'url': url.replace('$M', str(j)),
720c3099 3387 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3388 } for j in range(math.ceil(fragment_count))],
3389 }
3390
adbc4ec4 3391 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 3392 webpage = None
3393 if 'webpage' not in self._configuration_arg('player_skip'):
3394 webpage = self._download_webpage(
6e634cbe 3395 webpage_url + '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id, fatal=False)
11f9be09 3396
3397 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 3398
b6de707d 3399 player_responses, player_url = self._extract_player_responses(
11f9be09 3400 self._get_requested_clients(url, smuggled_data),
99e9e001 3401 video_id, webpage, master_ytcfg)
11f9be09 3402
adbc4ec4
THD
3403 return webpage, master_ytcfg, player_responses, player_url
3404
a1b2d843 3405 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
3406 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3407 is_live = get_first(video_details, 'isLive')
3408 if is_live is None:
3409 is_live = get_first(live_broadcast_details, 'isLiveNow')
3410
3411 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
c646d76f 3412 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, is_live, duration)
adbc4ec4 3413
c646d76f 3414 return live_broadcast_details, is_live, streaming_data, formats, subtitles
adbc4ec4
THD
3415
3416 def _real_extract(self, url):
3417 url, smuggled_data = unsmuggle_url(url, {})
3418 video_id = self._match_id(url)
3419
3420 base_url = self.http_scheme() + '//www.youtube.com/'
3421 webpage_url = base_url + 'watch?v=' + video_id
3422
3423 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3424
11f9be09 3425 playability_statuses = traverse_obj(
3426 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3427
3428 trailer_video_id = get_first(
3429 playability_statuses,
3430 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3431 expected_type=str)
3432 if trailer_video_id:
3433 return self.url_result(
3434 trailer_video_id, self.ie_key(), trailer_video_id)
3435
3436 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3437 if webpage else (lambda x: None))
3438
3439 video_details = traverse_obj(
3440 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3441 microformats = traverse_obj(
3442 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3443 expected_type=dict, default=[])
3444 video_title = (
3445 get_first(video_details, 'title')
3446 or self._get_text(microformats, (..., 'title'))
3447 or search_meta(['og:title', 'twitter:title', 'title']))
3448 video_description = get_first(video_details, 'shortDescription')
3449
d89257f3 3450 multifeed_metadata_list = get_first(
3451 player_responses,
3452 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3453 expected_type=str)
3454 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3455 if self.get_param('noplaylist'):
11f9be09 3456 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 3457 else:
3458 entries = []
3459 feed_ids = []
3460 for feed in multifeed_metadata_list.split(','):
3461 # Unquote should take place before split on comma (,) since textual
3462 # fields may contain comma as well (see
3463 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 3464 feed_data = urllib.parse.parse_qs(
ac668111 3465 urllib.parse.unquote_plus(feed))
d89257f3 3466
3467 def feed_entry(name):
3468 return try_get(
14f25df2 3469 feed_data, lambda x: x[name][0], str)
d89257f3 3470
3471 feed_id = feed_entry('id')
3472 if not feed_id:
3473 continue
3474 feed_title = feed_entry('title')
3475 title = video_title
3476 if feed_title:
3477 title += ' (%s)' % feed_title
3478 entries.append({
3479 '_type': 'url_transparent',
3480 'ie_key': 'Youtube',
3481 'url': smuggle_url(
3482 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3483 {'force_singlefeed': True}),
3484 'title': title,
3485 })
3486 feed_ids.append(feed_id)
3487 self.to_screen(
3488 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3489 % (', '.join(feed_ids), video_id))
3490 return self.playlist_result(
3491 entries, video_id, video_title, video_description)
11f9be09 3492
a1b2d843 3493 duration = int_or_none(
3494 get_first(video_details, 'lengthSeconds')
3495 or get_first(microformats, 'lengthSeconds')
3496 or parse_duration(search_meta('duration'))) or None
3497
c646d76f 3498 live_broadcast_details, is_live, streaming_data, formats, automatic_captions = \
3499 self._list_formats(video_id, microformats, video_details, player_responses, player_url)
bf1317d2 3500
545cc85d 3501 if not formats:
11f9be09 3502 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 3503 self.report_drm(video_id)
11f9be09 3504 pemr = get_first(
3505 playability_statuses,
3506 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3507 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3508 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 3509 if subreason:
545cc85d 3510 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 3511 countries = get_first(microformats, 'availableCountries')
545cc85d 3512 if not countries:
3513 regions_allowed = search_meta('regionsAllowed')
3514 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 3515 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 3516 reason += f'. {subreason}'
545cc85d 3517 if reason:
b7da73eb 3518 self.raise_no_formats(reason, expected=True)
bf1317d2 3519
11f9be09 3520 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 3521 if not keywords and webpage:
3522 keywords = [
3523 unescapeHTML(m.group('content'))
3524 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3525 for keyword in keywords:
3526 if keyword.startswith('yt:stretch='):
201c1459 3527 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3528 if mobj:
3529 # NB: float is intentional for forcing float division
3530 w, h = (float(v) for v in mobj.groups())
3531 if w > 0 and h > 0:
3532 ratio = w / h
3533 for f in formats:
3534 if f.get('vcodec') != 'none':
3535 f['stretched_ratio'] = ratio
3536 break
a709d873 3537 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 3538 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3539 if thumbnail_url:
3540 thumbnails.append({
3541 'url': thumbnail_url,
ff2751ac 3542 })
fccf5021 3543 original_thumbnails = thumbnails.copy()
3544
0ba692ac 3545 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 3546 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 3547 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 3548 thumbnail_names = [
962ffcf8 3549 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 3550 # in resolution, these are not the custom thumbnail. So de-prioritize them
3551 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3552 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 3553 ]
cca80fe6 3554 n_thumbnail_names = len(thumbnail_names)
0ba692ac 3555 thumbnails.extend({
3556 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3557 video_id=video_id, name=name, ext=ext,
3558 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
cca80fe6 3559 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 3560 for thumb in thumbnails:
cca80fe6 3561 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 3562 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 3563 self._remove_duplicate_formats(thumbnails)
fccf5021 3564 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 3565
7ea65411 3566 category = get_first(microformats, 'category') or search_meta('genre')
3567 channel_id = str_or_none(
3568 get_first(video_details, 'channelId')
3569 or get_first(microformats, 'externalChannelId')
3570 or search_meta('channelId'))
7ea65411 3571 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3572
3573 live_content = get_first(video_details, 'isLiveContent')
3574 is_upcoming = get_first(video_details, 'isUpcoming')
3575 if is_live is None:
3576 if is_upcoming or live_content is False:
3577 is_live = False
3578 if is_upcoming is None and (live_content or is_live):
3579 is_upcoming = False
adbc4ec4
THD
3580 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3581 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3582 if not duration and live_end_time and live_start_time:
3583 duration = live_end_time - live_start_time
3584
3585 if is_live and self.get_param('live_from_start'):
3586 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
7ea65411 3587
720c3099 3588 formats.extend(self._extract_storyboard(player_responses, duration))
3589
31b532a1 3590 # source_preference is lower for throttled/potentially damaged formats
7e798d72 3591 self._sort_formats(formats, (
3592 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'))
720c3099 3593
545cc85d 3594 info = {
3595 'id': video_id,
39ca3b5c 3596 'title': video_title,
545cc85d 3597 'formats': formats,
3598 'thumbnails': thumbnails,
fccf5021 3599 # The best thumbnail that we are sure exists. Prevents unnecessary
3600 # URL checking if user don't care about getting the best possible thumbnail
3601 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 3602 'description': video_description,
11f9be09 3603 'uploader': get_first(video_details, 'author'),
545cc85d 3604 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3605 'uploader_url': owner_profile_url,
3606 'channel_id': channel_id,
a70635b8 3607 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'),
545cc85d 3608 'duration': duration,
3609 'view_count': int_or_none(
11f9be09 3610 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 3611 or search_meta('interactionCount')),
11f9be09 3612 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 3613 'age_limit': 18 if (
11f9be09 3614 get_first(microformats, 'isFamilySafe') is False
545cc85d 3615 or search_meta('isFamilyFriendly') == 'false'
3616 or search_meta('og:restrictions:age') == '18+') else 0,
3617 'webpage_url': webpage_url,
3618 'categories': [category] if category else None,
3619 'tags': keywords,
11f9be09 3620 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
7ea65411 3621 'is_live': is_live,
3622 'was_live': (False if is_live or is_upcoming or live_content is False
3623 else None if is_live is None or is_upcoming is None
3624 else live_content),
3625 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
adbc4ec4 3626 'release_timestamp': live_start_time,
545cc85d 3627 }
b477fc13 3628
e325a21a 3629 if get_first(video_details, 'isPostLiveDvr'):
3630 self.write_debug('Video is in Post-Live Manifestless mode')
3631 info['live_status'] = 'post_live'
3632 if (duration or 0) > 4 * 3600:
3633 self.report_warning(
3634 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3635 'This is a known issue and patches are welcome')
3636
c646d76f 3637 subtitles = {}
3944e7af 3638 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 3639 if pctr:
ecdc9049 3640 def get_lang_code(track):
3641 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3642 or track.get('languageCode'))
3643
3644 # Converted into dicts to remove duplicates
3645 captions = {
3646 get_lang_code(sub): sub
3647 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3648 translation_languages = {
3649 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3650 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3651
774d79cc 3652 def process_language(container, base_url, lang_code, sub_name, query):
120916da 3653 lang_subs = container.setdefault(lang_code, [])
545cc85d 3654 for fmt in self._SUBTITLE_FORMATS:
3655 query.update({
3656 'fmt': fmt,
3657 })
3658 lang_subs.append({
3659 'ext': fmt,
60f393e4 3660 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 3661 'name': sub_name,
545cc85d 3662 })
7e72694b 3663
07b47084 3664 # NB: Constructing the full subtitle dictionary is slow
3665 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
3666 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 3667 for lang_code, caption_track in captions.items():
3668 base_url = caption_track.get('baseUrl')
1235d333 3669 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 3670 if not base_url:
3671 continue
ecdc9049 3672 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 3673 if caption_track.get('kind') != 'asr':
545cc85d 3674 if not lang_code:
3675 continue
3676 process_language(
ecdc9049 3677 subtitles, base_url, lang_code, lang_name, {})
3678 if not caption_track.get('isTranslatable'):
3679 continue
3944e7af 3680 for trans_code, trans_name in translation_languages.items():
3681 if not trans_code:
545cc85d 3682 continue
1235d333 3683 orig_trans_code = trans_code
ecdc9049 3684 if caption_track.get('kind') != 'asr':
07b47084 3685 if not get_translated_subs:
18e49408 3686 continue
ecdc9049 3687 trans_code += f'-{lang_code}'
a70635b8 3688 trans_name += format_field(lang_name, None, ' from %s')
d49669ac 3689 # Add an "-orig" label to the original language so that it can be distinguished.
3690 # The subs are returned without "-orig" as well for compatibility
1235d333 3691 if lang_code == f'a-{orig_trans_code}':
0c8d9e5f 3692 process_language(
d49669ac 3693 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3694 # Setting tlang=lang returns damaged subtitles.
d49669ac 3695 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 3696 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 3697
3698 info['automatic_captions'] = automatic_captions
3699 info['subtitles'] = subtitles
7e72694b 3700
14f25df2 3701 parsed_url = urllib.parse.urlparse(url)
545cc85d 3702 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 3703 query = urllib.parse.parse_qs(component)
545cc85d 3704 for k, v in query.items():
3705 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3706 d_k += '_time'
3707 if d_k not in info and k in s_ks:
3708 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
3709
3710 # Youtube Music Auto-generated description
822b9d9c 3711 if video_description:
1890fc63 3712 mobj = re.search(
3713 r'''(?xs)
3714 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3715 (?P<album>[^\n]+)
3716 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3717 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3718 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3719 .+\nAuto-generated\ by\ YouTube\.\s*$
3720 ''', video_description)
822b9d9c 3721 if mobj:
822b9d9c
RA
3722 release_year = mobj.group('release_year')
3723 release_date = mobj.group('release_date')
3724 if release_date:
3725 release_date = release_date.replace('-', '')
3726 if not release_year:
545cc85d 3727 release_year = release_date[:4]
3728 info.update({
3729 'album': mobj.group('album'.strip()),
3730 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3731 'track': mobj.group('track').strip(),
3732 'release_date': release_date,
cc2db878 3733 'release_year': int_or_none(release_year),
545cc85d 3734 })
7e72694b 3735
545cc85d 3736 initial_data = None
3737 if webpage:
56ba69e4 3738 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
545cc85d 3739 if not initial_data:
99e9e001 3740 query = {'videoId': video_id}
3741 query.update(self._get_checkok_params())
109dd3b2 3742 initial_data = self._extract_response(
3743 item_id=video_id, ep='next', fatal=False,
99e9e001 3744 ytcfg=master_ytcfg, query=query,
3745 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 3746 note='Downloading initial data API JSON')
545cc85d 3747
0df111a3 3748 info['comment_count'] = traverse_obj(initial_data, (
3749 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3750 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3751 ), (
3752 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3753 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3754 ), expected_type=int_or_none, get_all=False)
3755
19a03940 3756 try: # This will error if there is no livechat
c60ee3a2 3757 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 3758 except (KeyError, IndexError, TypeError):
3759 pass
3760 else:
ecdc9049 3761 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 3762 # url is needed to set cookies
3763 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 3764 'video_id': video_id,
3765 'ext': 'json',
f6745c49 3766 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
c60ee3a2 3767 }]
545cc85d 3768
3769 if initial_data:
7c365c21 3770 info['chapters'] = (
3771 self._extract_chapters_from_json(initial_data, duration)
3772 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 3773 or self._extract_chapters_from_description(video_description, duration)
7c365c21 3774 or None)
545cc85d 3775
17322130 3776 contents = traverse_obj(
3777 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3778 expected_type=list, default=[])
3779
3780 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3781 if vpir:
3782 stl = vpir.get('superTitleLink')
3783 if stl:
3784 stl = self._get_text(stl)
3785 if try_get(
3786 vpir,
3787 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3788 info['location'] = stl
3789 else:
affc4fef 3790 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 3791 if mobj:
545cc85d 3792 info.update({
17322130 3793 'series': mobj.group(1),
3794 'season_number': int(mobj.group(2)),
3795 'episode_number': int(mobj.group(3)),
545cc85d 3796 })
17322130 3797 for tlb in (try_get(
3798 vpir,
3799 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3800 list) or []):
3801 tbr = tlb.get('toggleButtonRenderer') or {}
3802 for getter, regex in [(
3803 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3804 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3805 lambda x: x['accessibility'],
3806 lambda x: x['accessibilityData']['accessibilityData'],
3807 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3808 label = (try_get(tbr, getter, dict) or {}).get('label')
3809 if label:
3810 mobj = re.match(regex, label)
3811 if mobj:
3812 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
545cc85d 3813 break
17322130 3814 sbr_tooltip = try_get(
3815 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3816 if sbr_tooltip:
3817 like_count, dislike_count = sbr_tooltip.split(' / ')
3818 info.update({
3819 'like_count': str_to_int(like_count),
3820 'dislike_count': str_to_int(dislike_count),
3821 })
3822 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3823 if vsir:
3824 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3825 info.update({
3826 'channel': self._get_text(vor, 'title'),
3827 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3828
3829 rows = try_get(
3830 vsir,
3831 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3832 list) or []
3833 multiple_songs = False
3834 for row in rows:
3835 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3836 multiple_songs = True
3837 break
3838 for row in rows:
3839 mrr = row.get('metadataRowRenderer') or {}
3840 mrr_title = mrr.get('title')
3841 if not mrr_title:
3842 continue
3843 mrr_title = self._get_text(mrr, 'title')
3844 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3845 if mrr_title == 'License':
3846 info['license'] = mrr_contents_text
3847 elif not multiple_songs:
3848 if mrr_title == 'Album':
3849 info['album'] = mrr_contents_text
3850 elif mrr_title == 'Artist':
3851 info['artist'] = mrr_contents_text
3852 elif mrr_title == 'Song':
3853 info['track'] = mrr_contents_text
545cc85d 3854
3855 fallbacks = {
3856 'channel': 'uploader',
3857 'channel_id': 'uploader_id',
3858 'channel_url': 'uploader_url',
3859 }
992f9a73 3860
17322130 3861 # The upload date for scheduled, live and past live streams / premieres in microformats
3862 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 3863 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 3864 upload_date = (
3865 unified_strdate(get_first(microformats, 'uploadDate'))
3866 or unified_strdate(search_meta('uploadDate')))
3867 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
6e634cbe 3868 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date
17322130 3869 info['upload_date'] = upload_date
992f9a73 3870
545cc85d 3871 for to, frm in fallbacks.items():
3872 if not info.get(to):
3873 info[to] = info.get(frm)
3874
3875 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3876 v = info.get(s_k)
3877 if v:
3878 info[d_k] = v
b84071c0 3879
11f9be09 3880 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3881 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
c224251a 3882 is_membersonly = None
b28f8d24 3883 is_premium = None
c224251a
M
3884 if initial_data and is_private is not None:
3885 is_membersonly = False
b28f8d24 3886 is_premium = False
47193e02 3887 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3888 badge_labels = set()
3889 for content in contents:
3890 if not isinstance(content, dict):
3891 continue
3892 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3893 for badge_label in badge_labels:
3894 if badge_label.lower() == 'members only':
3895 is_membersonly = True
3896 elif badge_label.lower() == 'premium':
3897 is_premium = True
3898 elif badge_label.lower() == 'unlisted':
3899 is_unlisted = True
c224251a 3900
c224251a
M
3901 info['availability'] = self._availability(
3902 is_private=is_private,
b28f8d24 3903 needs_premium=is_premium,
c224251a
M
3904 needs_subscription=is_membersonly,
3905 needs_auth=info['age_limit'] >= 18,
3906 is_unlisted=None if is_private is None else is_unlisted)
3907
a2160aa4 3908 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 3909
11f9be09 3910 self.mark_watched(video_id, player_responses)
d77ab8e2 3911
545cc85d 3912 return info
c5e8d7af 3913
a61fd4cf 3914
a6213a49 3915class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
5f6a1245 3916
182bda88 3917 @staticmethod
3918 def passthrough_smuggled_data(func):
3919 def _smuggle(entries, smuggled_data):
3920 for entry in entries:
3921 # TODO: Convert URL to music.youtube instead.
3922 # Do we need to passthrough any other smuggled_data?
3923 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3924 yield entry
3925
3926 @functools.wraps(func)
3927 def wrapper(self, url):
3928 url, smuggled_data = unsmuggle_url(url, {})
3929 if self.is_music_url(url):
3930 smuggled_data['is_music_url'] = True
3931 info_dict = func(self, url, smuggled_data)
3932 if smuggled_data and info_dict.get('entries'):
3933 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3934 return info_dict
3935 return wrapper
3936
a6213a49 3937 def _extract_channel_id(self, webpage):
3938 channel_id = self._html_search_meta(
3939 'channelId', webpage, 'channel id', default=None)
3940 if channel_id:
3941 return channel_id
3942 channel_url = self._html_search_meta(
3943 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3944 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3945 'twitter:app:url:googleplay'), webpage, 'channel url')
3946 return self._search_regex(
3947 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3948 channel_url, 'channel id')
15f6397c 3949
8bdd16b4 3950 @staticmethod
cd7c66cf 3951 def _extract_basic_item_renderer(item):
3952 # Modified from _extract_grid_item_renderer
201c1459 3953 known_basic_renderers = (
a17526e4 3954 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 3955 )
3956 for key, renderer in item.items():
201c1459 3957 if not isinstance(renderer, dict):
cd7c66cf 3958 continue
201c1459 3959 elif key in known_basic_renderers:
3960 return renderer
3961 elif key.startswith('grid') and key.endswith('Renderer'):
3962 return renderer
8bdd16b4 3963
8bdd16b4 3964 def _grid_entries(self, grid_renderer):
3965 for item in grid_renderer['items']:
3966 if not isinstance(item, dict):
39b62db1 3967 continue
cd7c66cf 3968 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 3969 if not isinstance(renderer, dict):
3970 continue
052e1350 3971 title = self._get_text(renderer, 'title')
fe93e2c4 3972
8bdd16b4 3973 # playlist
3974 playlist_id = renderer.get('playlistId')
3975 if playlist_id:
3976 yield self.url_result(
3977 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3978 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3979 video_title=title)
201c1459 3980 continue
8bdd16b4 3981 # video
3982 video_id = renderer.get('videoId')
3983 if video_id:
3984 yield self._extract_video(renderer)
201c1459 3985 continue
8bdd16b4 3986 # channel
3987 channel_id = renderer.get('channelId')
3988 if channel_id:
8bdd16b4 3989 yield self.url_result(
3990 'https://www.youtube.com/channel/%s' % channel_id,
3991 ie=YoutubeTabIE.ie_key(), video_title=title)
201c1459 3992 continue
3993 # generic endpoint URL support
3994 ep_url = urljoin('https://www.youtube.com/', try_get(
3995 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 3996 str))
201c1459 3997 if ep_url:
3998 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3999 if ie.suitable(ep_url):
4000 yield self.url_result(
4001 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4002 break
8bdd16b4 4003
16aa9ea4 4004 def _music_reponsive_list_entry(self, renderer):
4005 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4006 if video_id:
4007 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
4008 ie=YoutubeIE.ie_key(), video_id=video_id)
4009 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4010 if playlist_id:
4011 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4012 if video_id:
4013 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4014 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4015 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4016 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4017 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4018 if browse_id:
4019 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4020 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4021
3d3dddc9 4022 def _shelf_entries_from_content(self, shelf_renderer):
4023 content = shelf_renderer.get('content')
4024 if not isinstance(content, dict):
8bdd16b4 4025 return
cd7c66cf 4026 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4027 if renderer:
4028 # TODO: add support for nested playlists so each shelf is processed
4029 # as separate playlist
4030 # TODO: this includes only first N items
86e5f3ed 4031 yield from self._grid_entries(renderer)
3d3dddc9 4032 renderer = content.get('horizontalListRenderer')
4033 if renderer:
4034 # TODO
4035 pass
8bdd16b4 4036
29f7c58a 4037 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4038 ep = try_get(
4039 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4040 str)
8bdd16b4 4041 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4042 if shelf_url:
29f7c58a 4043 # Skipping links to another channels, note that checking for
4044 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4045 # will not work
4046 if skip_channels and '/channels?' in shelf_url:
4047 return
052e1350 4048 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4049 yield self.url_result(shelf_url, video_title=title)
4050 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4051 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4052
8bdd16b4 4053 def _playlist_entries(self, video_list_renderer):
4054 for content in video_list_renderer['contents']:
4055 if not isinstance(content, dict):
4056 continue
4057 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4058 if not isinstance(renderer, dict):
4059 continue
4060 video_id = renderer.get('videoId')
4061 if not video_id:
4062 continue
4063 yield self._extract_video(renderer)
07aeced6 4064
3462ffa8 4065 def _rich_entries(self, rich_grid_renderer):
4066 renderer = try_get(
70d5c17b 4067 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3462ffa8 4068 video_id = renderer.get('videoId')
4069 if not video_id:
4070 return
4071 yield self._extract_video(renderer)
4072
8bdd16b4 4073 def _video_entry(self, video_renderer):
4074 video_id = video_renderer.get('videoId')
4075 if video_id:
4076 return self._extract_video(video_renderer)
dacb3a86 4077
ad210f4f 4078 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4079 url = urljoin('https://youtube.com', traverse_obj(
4080 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4081 if url:
4082 return self.url_result(
4083 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4084
8bdd16b4 4085 def _post_thread_entries(self, post_thread_renderer):
4086 post_renderer = try_get(
4087 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4088 if not post_renderer:
4089 return
4090 # video attachment
4091 video_renderer = try_get(
895b0931 4092 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4093 video_id = video_renderer.get('videoId')
4094 if video_id:
4095 entry = self._extract_video(video_renderer)
8bdd16b4 4096 if entry:
4097 yield entry
895b0931 4098 # playlist attachment
4099 playlist_id = try_get(
14f25df2 4100 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4101 if playlist_id:
4102 yield self.url_result(
e28f1c0a 4103 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4104 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4105 # inline video links
4106 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4107 for run in runs:
4108 if not isinstance(run, dict):
4109 continue
4110 ep_url = try_get(
14f25df2 4111 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4112 if not ep_url:
4113 continue
4114 if not YoutubeIE.suitable(ep_url):
4115 continue
4116 ep_video_id = YoutubeIE._match_id(ep_url)
4117 if video_id == ep_video_id:
4118 continue
895b0931 4119 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4120
8bdd16b4 4121 def _post_thread_continuation_entries(self, post_thread_continuation):
4122 contents = post_thread_continuation.get('contents')
4123 if not isinstance(contents, list):
4124 return
4125 for content in contents:
4126 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4127 if isinstance(renderer, dict):
4128 yield from self._post_thread_entries(renderer)
8bdd16b4 4129 continue
6b0b0a28 4130 renderer = content.get('videoRenderer')
4131 if isinstance(renderer, dict):
4132 yield self._video_entry(renderer)
07aeced6 4133
39ed931e 4134 r''' # unused
4135 def _rich_grid_entries(self, contents):
4136 for content in contents:
4137 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4138 if video_renderer:
4139 entry = self._video_entry(video_renderer)
4140 if entry:
4141 yield entry
4142 '''
52efa4b3 4143
a6213a49 4144 def _extract_entries(self, parent_renderer, continuation_list):
4145 # continuation_list is modified in-place with continuation_list = [continuation_token]
4146 continuation_list[:] = [None]
4147 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4148 for content in contents:
4149 if not isinstance(content, dict):
4150 continue
16aa9ea4 4151 is_renderer = traverse_obj(
4152 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4153 expected_type=dict)
a6213a49 4154 if not is_renderer:
4155 renderer = content.get('richItemRenderer')
4156 if renderer:
4157 for entry in self._rich_entries(renderer):
4158 yield entry
4159 continuation_list[0] = self._extract_continuation(parent_renderer)
4160 continue
4161 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4162 for isr_content in isr_contents:
4163 if not isinstance(isr_content, dict):
8bdd16b4 4164 continue
69184e41 4165
a6213a49 4166 known_renderers = {
4167 'playlistVideoListRenderer': self._playlist_entries,
4168 'gridRenderer': self._grid_entries,
a17526e4 4169 'reelShelfRenderer': self._grid_entries,
4170 'shelfRenderer': self._shelf_entries,
16aa9ea4 4171 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4172 'backstagePostThreadRenderer': self._post_thread_entries,
4173 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4174 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4175 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
ad210f4f 4176 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
a6213a49 4177 }
4178 for key, renderer in isr_content.items():
4179 if key not in known_renderers:
4180 continue
4181 for entry in known_renderers[key](renderer):
4182 if entry:
4183 yield entry
4184 continuation_list[0] = self._extract_continuation(renderer)
4185 break
70d5c17b 4186
4187 if not continuation_list[0]:
a6213a49 4188 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4189
a6213a49 4190 if not continuation_list[0]:
4191 continuation_list[0] = self._extract_continuation(parent_renderer)
4192
4193 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4194 continuation_list = [None]
4195 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4196 tab_content = try_get(tab, lambda x: x['content'], dict)
4197 if not tab_content:
4198 return
3462ffa8 4199 parent_renderer = (
29f7c58a 4200 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4201 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4202 yield from extract_entries(parent_renderer)
3462ffa8 4203 continuation = continuation_list[0]
d069eca7 4204
8bdd16b4 4205 for page_num in itertools.count(1):
4206 if not continuation:
4207 break
99e9e001 4208 headers = self.generate_api_headers(
4209 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4210 response = self._extract_response(
86e5f3ed 4211 item_id=f'{item_id} page {page_num}',
fe93e2c4 4212 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4213 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4214
4215 if not response:
8bdd16b4 4216 break
ac56cf38 4217 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4218 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4219 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4220
69184e41 4221 known_continuation_renderers = {
4222 'playlistVideoListContinuation': self._playlist_entries,
4223 'gridContinuation': self._grid_entries,
4224 'itemSectionContinuation': self._post_thread_continuation_entries,
4225 'sectionListContinuation': extract_entries, # for feeds
4226 }
8bdd16b4 4227 continuation_contents = try_get(
69184e41 4228 response, lambda x: x['continuationContents'], dict) or {}
4229 continuation_renderer = None
4230 for key, value in continuation_contents.items():
4231 if key not in known_continuation_renderers:
3462ffa8 4232 continue
69184e41 4233 continuation_renderer = value
4234 continuation_list = [None]
86e5f3ed 4235 yield from known_continuation_renderers[key](continuation_renderer)
69184e41 4236 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4237 break
4238 if continuation_renderer:
4239 continue
c5e8d7af 4240
a1b535bd 4241 known_renderers = {
e4b98809 4242 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4243 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4244 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4245 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4246 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4247 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4248 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
26fe8ffe 4249 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
a1b535bd 4250 }
cce889b9 4251 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
8bdd16b4 4252 continuation_items = try_get(
cce889b9 4253 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
a1b535bd 4254 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4255 video_items_renderer = None
4256 for key, value in continuation_item.items():
4257 if key not in known_renderers:
8bdd16b4 4258 continue
a1b535bd 4259 video_items_renderer = {known_renderers[key][1]: continuation_items}
9ba5705a 4260 continuation_list = [None]
86e5f3ed 4261 yield from known_renderers[key][0](video_items_renderer)
9ba5705a 4262 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
a1b535bd 4263 break
4264 if video_items_renderer:
4265 continue
8bdd16b4 4266 break
9558dcec 4267
8bdd16b4 4268 @staticmethod
7c219ea6 4269 def _extract_selected_tab(tabs, fatal=True):
8bdd16b4 4270 for tab in tabs:
cd684175 4271 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4272 if renderer.get('selected') is True:
4273 return renderer
2b3c2546 4274 else:
7c219ea6 4275 if fatal:
4276 raise ExtractorError('Unable to find selected tab')
b82f815f 4277
61d3665d 4278 def _extract_uploader(self, data):
8bdd16b4 4279 uploader = {}
61d3665d 4280 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
47193e02 4281 owner = try_get(
4282 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4283 if owner:
61d3665d 4284 owner_text = owner.get('text')
4285 uploader['uploader'] = self._search_regex(
4286 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
47193e02 4287 uploader['uploader_id'] = try_get(
14f25df2 4288 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], str)
47193e02 4289 uploader['uploader_url'] = urljoin(
4290 'https://www.youtube.com/',
14f25df2 4291 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
9c3fe2ef 4292 return {k: v for k, v in uploader.items() if v is not None}
8bdd16b4 4293
ac56cf38 4294 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
b60419c5 4295 playlist_id = title = description = channel_url = channel_name = channel_id = None
ac56cf38 4296 tags = []
b60419c5 4297
8bdd16b4 4298 selected_tab = self._extract_selected_tab(tabs)
f0d785d3 4299 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
8bdd16b4 4300 renderer = try_get(
4301 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4302 if renderer:
b60419c5 4303 channel_name = renderer.get('title')
4304 channel_url = renderer.get('channelUrl')
4305 channel_id = renderer.get('externalId')
39ed931e 4306 else:
64c0d954 4307 renderer = try_get(
4308 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
39ed931e 4309
8bdd16b4 4310 if renderer:
4311 title = renderer.get('title')
ecc97af3 4312 description = renderer.get('description', '')
b60419c5 4313 playlist_id = channel_id
4314 tags = renderer.get('keywords', '').split()
b60419c5 4315
301d07fc 4316 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4317 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4318 def _get_uncropped(url):
4319 return url_or_none((url or '').split('=')[0] + '=s0')
4320
4321 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4322 if avatar_thumbnails:
4323 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4324 if uncropped_avatar:
4325 avatar_thumbnails.append({
4326 'url': uncropped_avatar,
4327 'id': 'avatar_uncropped',
4328 'preference': 1
4329 })
4330
4331 channel_banners = self._extract_thumbnails(
4332 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4333 for banner in channel_banners:
4334 banner['preference'] = -10
4335
4336 if channel_banners:
4337 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4338 if uncropped_banner:
4339 channel_banners.append({
4340 'url': uncropped_banner,
4341 'id': 'banner_uncropped',
4342 'preference': -5
4343 })
4344
4345 primary_thumbnails = self._extract_thumbnails(
a17526e4 4346 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
a709d873 4347
3462ffa8 4348 if playlist_id is None:
70d5c17b 4349 playlist_id = item_id
f0d785d3 4350
4351 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4352 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
70d5c17b 4353 if title is None:
f0d785d3 4354 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
b60419c5 4355 title += format_field(selected_tab, 'title', ' - %s')
cd684175 4356 title += format_field(selected_tab, 'expandedText', ' - %s')
f0d785d3 4357
b60419c5 4358 metadata = {
4359 'playlist_id': playlist_id,
4360 'playlist_title': title,
4361 'playlist_description': description,
4362 'uploader': channel_name,
4363 'uploader_id': channel_id,
4364 'uploader_url': channel_url,
301d07fc 4365 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
b60419c5 4366 'tags': tags,
f0d785d3 4367 'view_count': self._get_count(playlist_stats, 1),
4368 'availability': self._extract_availability(data),
4369 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
6c73052c 4370 'playlist_count': self._get_count(playlist_stats, 0),
4371 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
b60419c5 4372 }
4373 if not channel_id:
4374 metadata.update(self._extract_uploader(data))
4375 metadata.update({
4376 'channel': metadata['uploader'],
4377 'channel_id': metadata['uploader_id'],
4378 'channel_url': metadata['uploader_url']})
4379 return self.playlist_result(
d069eca7 4380 self._entries(
ac56cf38 4381 selected_tab, playlist_id, ytcfg,
4382 self._extract_account_syncid(ytcfg, data),
4383 self._extract_visitor_data(data, ytcfg)),
b60419c5 4384 **metadata)
73c4ac2c 4385
6e634cbe 4386 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 4387 first_id = last_id = response = None
2be71994 4388 for page_num in itertools.count(1):
cd7c66cf 4389 videos = list(self._playlist_entries(playlist))
4390 if not videos:
4391 return
2be71994 4392 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4393 if start >= len(videos):
4394 return
24146491 4395 yield from videos[start:]
2be71994 4396 first_id = first_id or videos[0]['id']
4397 last_id = videos[-1]['id']
79360d99 4398 watch_endpoint = try_get(
4399 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 4400 headers = self.generate_api_headers(
4401 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4402 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 4403 query = {
4404 'playlistId': playlist_id,
4405 'videoId': watch_endpoint.get('videoId') or last_id,
4406 'index': watch_endpoint.get('index') or len(videos),
4407 'params': watch_endpoint.get('params') or 'OAE%3D'
4408 }
4409 response = self._extract_response(
4410 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 4411 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 4412 check_get_keys='contents'
4413 )
cd7c66cf 4414 playlist = try_get(
79360d99 4415 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 4416
ac56cf38 4417 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 4418 title = playlist.get('title') or try_get(
14f25df2 4419 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 4420 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 4421
4422 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 4423 playlist_url = urljoin(url, try_get(
4424 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4425 str))
6e634cbe 4426
4427 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4428 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4429 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
4430
4431 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 4432 return self.url_result(
4433 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4434 video_title=title)
cd7c66cf 4435
8bdd16b4 4436 return self.playlist_result(
6e634cbe 4437 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 4438 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 4439
47193e02 4440 def _extract_availability(self, data):
4441 """
4442 Gets the availability of a given playlist/tab.
4443 Note: Unless YouTube tells us explicitly, we do not assume it is public
4444 @param data: response
4445 """
4446 is_private = is_unlisted = None
4447 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4448 badge_labels = self._extract_badges(renderer)
4449
4450 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4451 privacy_dropdown_entries = try_get(
4452 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4453 for renderer_dict in privacy_dropdown_entries:
4454 is_selected = try_get(
4455 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4456 if not is_selected:
4457 continue
052e1350 4458 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
47193e02 4459 if label:
4460 badge_labels.add(label.lower())
4461 break
4462
4463 for badge_label in badge_labels:
4464 if badge_label == 'unlisted':
4465 is_unlisted = True
4466 elif badge_label == 'private':
4467 is_private = True
4468 elif badge_label == 'public':
4469 is_unlisted = is_private = False
4470 return self._availability(is_private, False, False, False, is_unlisted)
4471
4472 @staticmethod
4473 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4474 sidebar_renderer = try_get(
4475 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4476 for item in sidebar_renderer:
4477 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4478 if renderer:
4479 return renderer
4480
ac56cf38 4481 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 4482 """
4483 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4484 """
5d342002 4485 browse_id = params = None
47193e02 4486 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4487 if not renderer:
4488 return
4489 menu_renderer = try_get(
4490 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4491 for menu_item in menu_renderer:
4492 if not isinstance(menu_item, dict):
358de58c 4493 continue
47193e02 4494 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4495 text = try_get(
14f25df2 4496 nav_item_renderer, lambda x: x['text']['simpleText'], str)
47193e02 4497 if not text or text.lower() != 'show unavailable videos':
4498 continue
4499 browse_endpoint = try_get(
4500 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4501 browse_id = browse_endpoint.get('browseId')
4502 params = browse_endpoint.get('params')
4503 break
5d342002 4504
11f9be09 4505 headers = self.generate_api_headers(
99e9e001 4506 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 4507 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 4508 query = {
4509 'params': params or 'wgYCCAA=',
4510 'browseId': browse_id or 'VL%s' % item_id
4511 }
4512 return self._extract_response(
4513 item_id=item_id, headers=headers, query=query,
fe93e2c4 4514 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
47193e02 4515 note='Downloading API JSON with unavailable videos')
358de58c 4516
2762dbb1 4517 @functools.cached_property
a25bca9f 4518 def skip_webpage(self):
4519 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4520
ac56cf38 4521 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 4522 webpage, data = None, None
4523 for retry in self.RetryManager(fatal=fatal):
ac56cf38 4524 try:
be5c1ae8 4525 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 4526 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4527 except ExtractorError as e:
4528 if isinstance(e.cause, network_exceptions):
14f25df2 4529 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 4530 retry.error = e
4531 continue
4532 self._error_or_warning(e, fatal=fatal)
14fdfea9 4533 break
ac56cf38 4534
be5c1ae8 4535 try:
4536 self._extract_and_report_alerts(data)
4537 except ExtractorError as e:
4538 self._error_or_warning(e, fatal=fatal)
4539 break
ac56cf38 4540
be5c1ae8 4541 # Sometimes youtube returns a webpage with incomplete ytInitialData
4542 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4543 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4544 retry.error = ExtractorError('Incomplete yt initial data received')
4545 continue
ac56cf38 4546
cd7c66cf 4547 return webpage, data
4548
a25bca9f 4549 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4550 """Use if failed to extract ytcfg (and data) from initial webpage"""
4551 if not ytcfg and self.is_authenticated:
4552 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4553 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4554 raise ExtractorError(
4555 f'{msg}. If you are not downloading private content, or '
4556 'your cookies are only for the first account and channel,'
4557 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4558 expected=True)
4559 self.report_warning(msg, only_once=True)
4560
ac56cf38 4561 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4562 data = None
a25bca9f 4563 if not self.skip_webpage:
ac56cf38 4564 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4565 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 4566 # Reject webpage data if redirected to home page without explicitly requesting
4567 selected_tab = self._extract_selected_tab(traverse_obj(
7c219ea6 4568 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
1108613f 4569 if (url != 'https://www.youtube.com/feed/recommended'
4570 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4571 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4572 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4573 if fatal:
4574 raise ExtractorError(msg, expected=True)
4575 self.report_warning(msg, only_once=True)
ac56cf38 4576 if not data:
a25bca9f 4577 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 4578 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4579 return data, ytcfg
4580
4581 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4582 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4583 resolve_response = self._extract_response(
4584 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4585 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4586 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4587 for ep_key, ep in endpoints.items():
4588 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4589 if params:
4590 return self._extract_response(
4591 item_id=item_id, query=params, ep=ep, headers=headers,
4592 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 4593 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 4594 err_note = 'Failed to resolve url (does the playlist exist?)'
4595 if fatal:
4596 raise ExtractorError(err_note, expected=True)
4597 self.report_warning(err_note, item_id)
4598
a6213a49 4599 _SEARCH_PARAMS = None
4600
af5c1c55 4601 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 4602 data = {'query': query}
4603 if params is NO_DEFAULT:
4604 params = self._SEARCH_PARAMS
4605 if params:
4606 data['params'] = params
16aa9ea4 4607
4608 content_keys = (
4609 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4610 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4611 # ytmusic search
4612 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4613 ('continuationContents', ),
4614 )
a25bca9f 4615 display_id = f'query "{query}"'
86e5f3ed 4616 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 4617 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4618 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 4619
a61fd4cf 4620 continuation_list = [None]
a25bca9f 4621 search = None
a6213a49 4622 for page_num in itertools.count(1):
a61fd4cf 4623 data.update(continuation_list[0] or {})
a25bca9f 4624 headers = self.generate_api_headers(
4625 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 4626 search = self._extract_response(
a25bca9f 4627 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4628 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 4629 slr_contents = traverse_obj(search, *content_keys)
4630 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 4631 if not continuation_list[0]:
a6213a49 4632 break
4633
4634
4635class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4636 IE_DESC = 'YouTube Tabs'
4637 _VALID_URL = r'''(?x:
4638 https?://
4639 (?:\w+\.)?
4640 (?:
4641 youtube(?:kids)?\.com|
4642 %(invidious)s
4643 )/
4644 (?:
4645 (?P<channel_type>channel|c|user|browse)/|
4646 (?P<not_channel>
4647 feed/|hashtag/|
4648 (?:playlist|watch)\?.*?\blist=
4649 )|
4650 (?!(?:%(reserved_names)s)\b) # Direct URLs
4651 )
4652 (?P<id>[^/?\#&]+)
4653 )''' % {
4654 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4655 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4656 }
4657 IE_NAME = 'youtube:tab'
4658
4659 _TESTS = [{
4660 'note': 'playlists, multipage',
4661 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4662 'playlist_mincount': 94,
4663 'info_dict': {
4664 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4665 'title': 'Igor Kleiner - Playlists',
a6213a49 4666 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 4667 'uploader': 'Igor Kleiner',
a6213a49 4668 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4669 'channel': 'Igor Kleiner',
4670 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4671 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4672 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4673 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4674 'channel_follower_count': int
a6213a49 4675 },
4676 }, {
4677 'note': 'playlists, multipage, different order',
4678 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4679 'playlist_mincount': 94,
4680 'info_dict': {
4681 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4682 'title': 'Igor Kleiner - Playlists',
a6213a49 4683 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4684 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 4685 'uploader': 'Igor Kleiner',
4686 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4687 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4688 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4689 'channel': 'Igor Kleiner',
4690 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 4691 'channel_follower_count': int
a6213a49 4692 },
4693 }, {
4694 'note': 'playlists, series',
4695 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4696 'playlist_mincount': 5,
4697 'info_dict': {
4698 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4699 'title': '3Blue1Brown - Playlists',
4700 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4701 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4702 'uploader': '3Blue1Brown',
976ae3ea 4703 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4704 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4705 'channel': '3Blue1Brown',
4706 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4707 'tags': ['Mathematics'],
6c73052c 4708 'channel_follower_count': int
a6213a49 4709 },
4710 }, {
4711 'note': 'playlists, singlepage',
4712 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4713 'playlist_mincount': 4,
4714 'info_dict': {
4715 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4716 'title': 'ThirstForScience - Playlists',
4717 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4718 'uploader': 'ThirstForScience',
4719 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 4720 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4721 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4722 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4723 'tags': 'count:13',
4724 'channel': 'ThirstForScience',
6c73052c 4725 'channel_follower_count': int
a6213a49 4726 }
4727 }, {
4728 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4729 'only_matching': True,
4730 }, {
4731 'note': 'basic, single video playlist',
4732 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4733 'info_dict': {
4734 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4735 'uploader': 'Sergey M.',
4736 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4737 'title': 'youtube-dl public playlist',
976ae3ea 4738 'description': '',
4739 'tags': [],
4740 'view_count': int,
4741 'modified_date': '20201130',
4742 'channel': 'Sergey M.',
4743 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4744 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4745 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4746 },
4747 'playlist_count': 1,
4748 }, {
4749 'note': 'empty playlist',
4750 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4751 'info_dict': {
4752 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4753 'uploader': 'Sergey M.',
4754 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4755 'title': 'youtube-dl empty playlist',
976ae3ea 4756 'tags': [],
4757 'channel': 'Sergey M.',
4758 'description': '',
4759 'modified_date': '20160902',
4760 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4761 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4762 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
a6213a49 4763 },
4764 'playlist_count': 0,
4765 }, {
4766 'note': 'Home tab',
4767 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4768 'info_dict': {
4769 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4770 'title': 'lex will - Home',
4771 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4772 'uploader': 'lex will',
4773 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4774 'channel': 'lex will',
4775 'tags': ['bible', 'history', 'prophesy'],
4776 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4777 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4778 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4779 'channel_follower_count': int
a6213a49 4780 },
4781 'playlist_mincount': 2,
4782 }, {
4783 'note': 'Videos tab',
4784 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4785 'info_dict': {
4786 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4787 'title': 'lex will - Videos',
4788 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4789 'uploader': 'lex will',
4790 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4791 'tags': ['bible', 'history', 'prophesy'],
4792 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4793 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4794 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4795 'channel': 'lex will',
6c73052c 4796 'channel_follower_count': int
a6213a49 4797 },
4798 'playlist_mincount': 975,
4799 }, {
4800 'note': 'Videos tab, sorted by popular',
4801 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4802 'info_dict': {
4803 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4804 'title': 'lex will - Videos',
4805 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4806 'uploader': 'lex will',
4807 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4808 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4809 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4810 'channel': 'lex will',
4811 'tags': ['bible', 'history', 'prophesy'],
4812 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 4813 'channel_follower_count': int
a6213a49 4814 },
4815 'playlist_mincount': 199,
4816 }, {
4817 'note': 'Playlists tab',
4818 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4819 'info_dict': {
4820 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4821 'title': 'lex will - Playlists',
4822 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4823 'uploader': 'lex will',
4824 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4825 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4826 'channel': 'lex will',
4827 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4828 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4829 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4830 'channel_follower_count': int
a6213a49 4831 },
4832 'playlist_mincount': 17,
4833 }, {
4834 'note': 'Community tab',
4835 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4836 'info_dict': {
4837 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4838 'title': 'lex will - Community',
4839 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4840 'uploader': 'lex will',
4841 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4842 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4843 'channel': 'lex will',
4844 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4845 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4846 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4847 'channel_follower_count': int
a6213a49 4848 },
4849 'playlist_mincount': 18,
4850 }, {
4851 'note': 'Channels tab',
4852 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4853 'info_dict': {
4854 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4855 'title': 'lex will - Channels',
4856 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4857 'uploader': 'lex will',
4858 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
976ae3ea 4859 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4860 'channel': 'lex will',
4861 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4862 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4863 'tags': ['bible', 'history', 'prophesy'],
6c73052c 4864 'channel_follower_count': int
a6213a49 4865 },
4866 'playlist_mincount': 12,
4867 }, {
4868 'note': 'Search tab',
4869 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4870 'playlist_mincount': 40,
4871 'info_dict': {
4872 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4873 'title': '3Blue1Brown - Search - linear algebra',
4874 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4875 'uploader': '3Blue1Brown',
4876 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 4877 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4878 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4879 'tags': ['Mathematics'],
4880 'channel': '3Blue1Brown',
4881 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6c73052c 4882 'channel_follower_count': int
a6213a49 4883 },
4884 }, {
4885 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4886 'only_matching': True,
4887 }, {
4888 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4889 'only_matching': True,
4890 }, {
4891 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4892 'only_matching': True,
4893 }, {
4894 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4895 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4896 'info_dict': {
4897 'title': '29C3: Not my department',
4898 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4899 'uploader': 'Christiaan008',
4900 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4901 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 4902 'tags': [],
4903 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4904 'view_count': int,
4905 'modified_date': '20150605',
4906 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4907 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4908 'channel': 'Christiaan008',
a6213a49 4909 },
4910 'playlist_count': 96,
4911 }, {
4912 'note': 'Large playlist',
4913 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4914 'info_dict': {
4915 'title': 'Uploads from Cauchemar',
4916 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4917 'uploader': 'Cauchemar',
4918 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 4919 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4920 'tags': [],
4921 'modified_date': r're:\d{8}',
4922 'channel': 'Cauchemar',
4923 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4924 'view_count': int,
4925 'description': '',
4926 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
a6213a49 4927 },
4928 'playlist_mincount': 1123,
976ae3ea 4929 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4930 }, {
4931 'note': 'even larger playlist, 8832 videos',
4932 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4933 'only_matching': True,
4934 }, {
4935 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4936 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4937 'info_dict': {
4938 'title': 'Uploads from Interstellar Movie',
4939 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4940 'uploader': 'Interstellar Movie',
4941 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 4942 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4943 'tags': [],
4944 'view_count': int,
4945 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4946 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4947 'channel': 'Interstellar Movie',
4948 'description': '',
4949 'modified_date': r're:\d{8}',
a6213a49 4950 },
4951 'playlist_mincount': 21,
4952 }, {
4953 'note': 'Playlist with "show unavailable videos" button',
4954 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4955 'info_dict': {
4956 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4957 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4958 'uploader': 'Phim Siêu Nhân Nhật Bản',
4959 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 4960 'view_count': int,
4961 'channel': 'Phim Siêu Nhân Nhật Bản',
4962 'tags': [],
4963 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4964 'description': '',
4965 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4966 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4967 'modified_date': r're:\d{8}',
a6213a49 4968 },
4969 'playlist_mincount': 200,
976ae3ea 4970 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4971 }, {
4972 'note': 'Playlist with unavailable videos in page 7',
4973 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4974 'info_dict': {
4975 'title': 'Uploads from BlankTV',
4976 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4977 'uploader': 'BlankTV',
4978 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 4979 'channel': 'BlankTV',
4980 'channel_url': 'https://www.youtube.com/c/blanktv',
4981 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4982 'view_count': int,
4983 'tags': [],
4984 'uploader_url': 'https://www.youtube.com/c/blanktv',
4985 'modified_date': r're:\d{8}',
4986 'description': '',
a6213a49 4987 },
4988 'playlist_mincount': 1000,
976ae3ea 4989 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 4990 }, {
4991 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4992 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4993 'info_dict': {
4994 'title': 'Data Analysis with Dr Mike Pound',
4995 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4996 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4997 'uploader': 'Computerphile',
4998 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 4999 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5000 'tags': [],
5001 'view_count': int,
5002 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5003 'channel_url': 'https://www.youtube.com/user/Computerphile',
5004 'channel': 'Computerphile',
a6213a49 5005 },
5006 'playlist_mincount': 11,
5007 }, {
5008 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5009 'only_matching': True,
5010 }, {
5011 'note': 'Playlist URL that does not actually serve a playlist',
5012 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5013 'info_dict': {
5014 'id': 'FqZTN594JQw',
5015 'ext': 'webm',
5016 'title': "Smiley's People 01 detective, Adventure Series, Action",
5017 'uploader': 'STREEM',
5018 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5019 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5020 'upload_date': '20150526',
5021 'license': 'Standard YouTube License',
5022 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5023 'categories': ['People & Blogs'],
5024 'tags': list,
5025 'view_count': int,
5026 'like_count': int,
a6213a49 5027 },
5028 'params': {
5029 'skip_download': True,
5030 },
5031 'skip': 'This video is not available.',
5032 'add_ie': [YoutubeIE.ie_key()],
5033 }, {
5034 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5035 'only_matching': True,
5036 }, {
5037 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5038 'only_matching': True,
5039 }, {
5040 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5041 'info_dict': {
12a1b225 5042 'id': 'Wq15eF5vCbI', # This will keep changing
a6213a49 5043 'ext': 'mp4',
976ae3ea 5044 'title': str,
a6213a49 5045 'uploader': 'Sky News',
5046 'uploader_id': 'skynews',
5047 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
5048 'upload_date': r're:\d{8}',
976ae3ea 5049 'description': str,
a6213a49 5050 'categories': ['News & Politics'],
5051 'tags': list,
5052 'like_count': int,
6c73052c 5053 'release_timestamp': 1642502819,
976ae3ea 5054 'channel': 'Sky News',
5055 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5056 'age_limit': 0,
5057 'view_count': int,
6c73052c 5058 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
976ae3ea 5059 'playable_in_embed': True,
6c73052c 5060 'release_date': '20220118',
976ae3ea 5061 'availability': 'public',
5062 'live_status': 'is_live',
5063 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
6c73052c 5064 'channel_follower_count': int
a6213a49 5065 },
5066 'params': {
5067 'skip_download': True,
5068 },
976ae3ea 5069 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5070 }, {
5071 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5072 'info_dict': {
5073 'id': 'a48o2S1cPoo',
5074 'ext': 'mp4',
5075 'title': 'The Young Turks - Live Main Show',
5076 'uploader': 'The Young Turks',
5077 'uploader_id': 'TheYoungTurks',
5078 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5079 'upload_date': '20150715',
5080 'license': 'Standard YouTube License',
5081 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5082 'categories': ['News & Politics'],
5083 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5084 'like_count': int,
a6213a49 5085 },
5086 'params': {
5087 'skip_download': True,
5088 },
5089 'only_matching': True,
5090 }, {
5091 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5092 'only_matching': True,
5093 }, {
5094 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5095 'only_matching': True,
5096 }, {
5097 'note': 'A channel that is not live. Should raise error',
5098 'url': 'https://www.youtube.com/user/numberphile/live',
5099 'only_matching': True,
5100 }, {
5101 'url': 'https://www.youtube.com/feed/trending',
5102 'only_matching': True,
5103 }, {
5104 'url': 'https://www.youtube.com/feed/library',
5105 'only_matching': True,
5106 }, {
5107 'url': 'https://www.youtube.com/feed/history',
5108 'only_matching': True,
5109 }, {
5110 'url': 'https://www.youtube.com/feed/subscriptions',
5111 'only_matching': True,
5112 }, {
5113 'url': 'https://www.youtube.com/feed/watch_later',
5114 'only_matching': True,
5115 }, {
5116 'note': 'Recommended - redirects to home page.',
5117 'url': 'https://www.youtube.com/feed/recommended',
5118 'only_matching': True,
5119 }, {
5120 'note': 'inline playlist with not always working continuations',
5121 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5122 'only_matching': True,
5123 }, {
5124 'url': 'https://www.youtube.com/course',
5125 'only_matching': True,
5126 }, {
5127 'url': 'https://www.youtube.com/zsecurity',
5128 'only_matching': True,
5129 }, {
5130 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5131 'only_matching': True,
5132 }, {
5133 'url': 'https://www.youtube.com/TheYoungTurks/live',
5134 'only_matching': True,
5135 }, {
5136 'url': 'https://www.youtube.com/hashtag/cctv9',
5137 'info_dict': {
5138 'id': 'cctv9',
5139 'title': '#cctv9',
976ae3ea 5140 'tags': [],
a6213a49 5141 },
5142 'playlist_mincount': 350,
5143 }, {
5144 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5145 'only_matching': True,
5146 }, {
5147 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5148 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5149 'only_matching': True
5150 }, {
5151 'note': '/browse/ should redirect to /channel/',
5152 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5153 'only_matching': True
5154 }, {
5155 'note': 'VLPL, should redirect to playlist?list=PL...',
5156 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5157 'info_dict': {
5158 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5159 'uploader': 'NoCopyrightSounds',
5160 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5161 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
12a1b225 5162 'title': 'NCS : All Releases 💿',
976ae3ea 5163 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5164 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5165 'modified_date': r're:\d{8}',
5166 'view_count': int,
5167 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5168 'tags': [],
5169 'channel': 'NoCopyrightSounds',
a6213a49 5170 },
5171 'playlist_mincount': 166,
976ae3ea 5172 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5173 }, {
5174 'note': 'Topic, should redirect to playlist?list=UU...',
5175 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5176 'info_dict': {
5177 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5178 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5179 'title': 'Uploads from Royalty Free Music - Topic',
5180 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5181 'tags': [],
5182 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5183 'channel': 'Royalty Free Music - Topic',
5184 'view_count': int,
5185 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5186 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5187 'modified_date': r're:\d{8}',
5188 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5189 'description': '',
a6213a49 5190 },
5191 'expected_warnings': [
a6213a49 5192 'The URL does not have a videos tab',
976ae3ea 5193 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5194 ],
5195 'playlist_mincount': 101,
5196 }, {
5197 'note': 'Topic without a UU playlist',
5198 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5199 'info_dict': {
5200 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5201 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5202 'tags': [],
a6213a49 5203 },
5204 'expected_warnings': [
976ae3ea 5205 'the playlist redirect gave error',
a6213a49 5206 ],
5207 'playlist_mincount': 9,
5208 }, {
5209 'note': 'Youtube music Album',
5210 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5211 'info_dict': {
5212 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5213 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5214 'tags': [],
5215 'view_count': int,
5216 'description': '',
5217 'availability': 'unlisted',
5218 'modified_date': r're:\d{8}',
a6213a49 5219 },
5220 'playlist_count': 50,
5221 }, {
5222 'note': 'unlisted single video playlist',
5223 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5224 'info_dict': {
5225 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5226 'uploader': 'colethedj',
5227 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5228 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5229 'availability': 'unlisted',
5230 'tags': [],
12a1b225 5231 'modified_date': '20220418',
976ae3ea 5232 'channel': 'colethedj',
5233 'view_count': int,
5234 'description': '',
5235 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5236 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5237 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
a6213a49 5238 },
5239 'playlist_count': 1,
5240 }, {
5241 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5242 'url': 'https://www.youtube.com/feed/recommended',
5243 'info_dict': {
5244 'id': 'recommended',
5245 'title': 'recommended',
6c73052c 5246 'tags': [],
a6213a49 5247 },
5248 'playlist_mincount': 50,
5249 'params': {
5250 'skip_download': True,
5251 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5252 },
5253 }, {
5254 'note': 'API Fallback: /videos tab, sorted by oldest first',
5255 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5256 'info_dict': {
5257 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5258 'title': 'Cody\'sLab - Videos',
5259 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5260 'uploader': 'Cody\'sLab',
5261 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
976ae3ea 5262 'channel': 'Cody\'sLab',
5263 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5264 'tags': [],
5265 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5266 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 5267 'channel_follower_count': int
a6213a49 5268 },
5269 'playlist_mincount': 650,
5270 'params': {
5271 'skip_download': True,
5272 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5273 },
5274 }, {
5275 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5276 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5277 'info_dict': {
5278 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5279 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5280 'title': 'Uploads from Royalty Free Music - Topic',
5281 'uploader': 'Royalty Free Music - Topic',
976ae3ea 5282 'modified_date': r're:\d{8}',
5283 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5284 'description': '',
5285 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5286 'tags': [],
5287 'channel': 'Royalty Free Music - Topic',
5288 'view_count': int,
5289 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5290 },
5291 'expected_warnings': [
976ae3ea 5292 'does not have a videos tab',
5293 r'[Uu]navailable videos (are|will be) hidden',
a6213a49 5294 ],
5295 'playlist_mincount': 101,
5296 'params': {
5297 'skip_download': True,
5298 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5299 },
7c219ea6 5300 }, {
5301 'note': 'non-standard redirect to regional channel',
5302 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5303 'only_matching': True
61d3665d 5304 }, {
5305 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5306 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5307 'info_dict': {
5308 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5309 'modified_date': '20220407',
5310 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5311 'tags': [],
5312 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5313 'uploader': 'pukkandan',
5314 'availability': 'unlisted',
5315 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5316 'channel': 'pukkandan',
5317 'description': 'Test for collaborative playlist',
5318 'title': 'yt-dlp test - collaborative playlist',
12a1b225 5319 'view_count': int,
61d3665d 5320 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5321 },
5322 'playlist_mincount': 2
a6213a49 5323 }]
5324
5325 @classmethod
5326 def suitable(cls, url):
86e5f3ed 5327 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 5328
64f36541 5329 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
fe03a6cd 5330
182bda88 5331 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5332 def _real_extract(self, url, smuggled_data):
cd7c66cf 5333 item_id = self._match_id(url)
14f25df2 5334 url = urllib.parse.urlunparse(
5335 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 5336 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 5337
fe03a6cd 5338 def get_mobj(url):
37e57a9f 5339 mobj = self._URL_RE.match(url).groupdict()
07cce701 5340 mobj.update((k, '') for k, v in mobj.items() if v is None)
fe03a6cd 5341 return mobj
5342
37e57a9f 5343 mobj, redirect_warning = get_mobj(url), None
fe03a6cd 5344 # Youtube returns incomplete data if tabname is not lower case
5345 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
fe03a6cd 5346 if is_channel:
5347 if smuggled_data.get('is_music_url'):
37e57a9f 5348 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
fe03a6cd 5349 item_id = item_id[2:]
37e57a9f 5350 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5351 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
ac56cf38 5352 mdata = self._extract_tab_endpoint(
37e57a9f 5353 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5354 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
14f25df2 5355 get_all=False, expected_type=str)
ac56cf38 5356 if not murl:
37e57a9f 5357 raise ExtractorError('Failed to resolve album to playlist')
ac56cf38 5358 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
37e57a9f 5359 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5360 pre = f'https://www.youtube.com/channel/{item_id}'
5361
64f36541 5362 original_tab_name = tab
fe03a6cd 5363 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5364 # Home URLs should redirect to /videos/
37e57a9f 5365 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5366 'To download only the videos in the home page, add a "/featured" to the URL')
fe03a6cd 5367 tab = '/videos'
5368
5369 url = ''.join((pre, tab, post))
5370 mobj = get_mobj(url)
cd7c66cf 5371
5372 # Handle both video/playlist URLs
201c1459 5373 qs = parse_qs(url)
86e5f3ed 5374 video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list'))
cd7c66cf 5375
fe03a6cd 5376 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 5377 if not playlist_id:
fe03a6cd 5378 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
cd7c66cf 5379 raise ExtractorError('Unable to recognize tab page')
fe03a6cd 5380 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 5381 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5382 url = f'https://www.youtube.com/playlist?list={playlist_id}'
18db7548 5383 mobj = get_mobj(url)
cd7c66cf 5384
5385 if video_id and playlist_id:
a06916d9 5386 if self.get_param('noplaylist'):
37e57a9f 5387 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5388 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5389 ie=YoutubeIE.ie_key(), video_id=video_id)
5390 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
cd7c66cf 5391
ac56cf38 5392 data, ytcfg = self._extract_data(url, item_id)
14fdfea9 5393
7c219ea6 5394 # YouTube may provide a non-standard redirect to the regional channel
5395 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5396 redirect_url = traverse_obj(
5397 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5398 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5399 redirect_url = ''.join((
5400 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5401 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5402 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5403
37e57a9f 5404 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
18db7548 5405 if tabs:
5406 selected_tab = self._extract_selected_tab(tabs)
64f36541 5407 selected_tab_name = selected_tab.get('title', '').lower()
5408 if selected_tab_name == 'home':
5409 selected_tab_name = 'featured'
5410 requested_tab_name = mobj['tab'][1:]
09f1580e 5411 if 'no-youtube-channel-redirect' not in compat_opts:
693f0600 5412 if requested_tab_name == 'live': # Live tab should have redirected to the video
5413 raise UserNotLive(video_id=mobj['id'])
64f36541 5414 if requested_tab_name not in ('', selected_tab_name):
5415 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5416 if not original_tab_name:
5417 if item_id[:2] == 'UC':
5418 # Topic channels don't have /videos. Use the equivalent playlist instead
5419 pl_id = f'UU{item_id[2:]}'
5420 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5421 try:
5422 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5423 except ExtractorError:
5424 redirect_warning += ' and the playlist redirect gave error'
5425 else:
5426 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5427 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5428 if selected_tab_name and selected_tab_name != requested_tab_name:
5429 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5430 else:
5431 raise ExtractorError(redirect_warning, expected=True)
18db7548 5432
37e57a9f 5433 if redirect_warning:
64f36541 5434 self.to_screen(redirect_warning)
37e57a9f 5435 self.write_debug(f'Final URL: {url}')
18db7548 5436
358de58c 5437 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 5438 if 'no-youtube-unavailable-videos' not in compat_opts:
ac56cf38 5439 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
c0ac49bc 5440 self._extract_and_report_alerts(data, only_once=True)
37e57a9f 5441 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
8bdd16b4 5442 if tabs:
ac56cf38 5443 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
cd7c66cf 5444
37e57a9f 5445 playlist = traverse_obj(
5446 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 5447 if playlist:
ac56cf38 5448 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 5449
37e57a9f 5450 video_id = traverse_obj(
5451 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 5452 if video_id:
09f1580e 5453 if mobj['tab'] != '/live': # live tab is expected to redirect to video
37e57a9f 5454 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5455 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5456 ie=YoutubeIE.ie_key(), video_id=video_id)
cd7c66cf 5457
8bdd16b4 5458 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 5459
c5e8d7af 5460
8bdd16b4 5461class YoutubePlaylistIE(InfoExtractor):
96565c7e 5462 IE_DESC = 'YouTube playlists'
8bdd16b4 5463 _VALID_URL = r'''(?x)(?:
5464 (?:https?://)?
5465 (?:\w+\.)?
5466 (?:
5467 (?:
5468 youtube(?:kids)?\.com|
d9190e44 5469 %(invidious)s
8bdd16b4 5470 )
5471 /.*?\?.*?\blist=
5472 )?
5473 (?P<id>%(playlist_id)s)
d9190e44
RH
5474 )''' % {
5475 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5476 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5477 }
8bdd16b4 5478 IE_NAME = 'youtube:playlist'
cdc628a4 5479 _TESTS = [{
8bdd16b4 5480 'note': 'issue #673',
5481 'url': 'PLBB231211A4F62143',
cdc628a4 5482 'info_dict': {
8bdd16b4 5483 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5484 'id': 'PLBB231211A4F62143',
976ae3ea 5485 'uploader': 'Wickman',
8bdd16b4 5486 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
11f9be09 5487 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 5488 'view_count': int,
5489 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5490 'modified_date': r're:\d{8}',
5491 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5492 'channel': 'Wickman',
5493 'tags': [],
5494 'channel_url': 'https://www.youtube.com/user/Wickydoo',
8bdd16b4 5495 },
5496 'playlist_mincount': 29,
5497 }, {
5498 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5499 'info_dict': {
5500 'title': 'YDL_safe_search',
5501 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5502 },
5503 'playlist_count': 2,
5504 'skip': 'This playlist is private',
9558dcec 5505 }, {
8bdd16b4 5506 'note': 'embedded',
5507 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5508 'playlist_count': 4,
9558dcec 5509 'info_dict': {
8bdd16b4 5510 'title': 'JODA15',
5511 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5512 'uploader': 'milan',
5513 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
976ae3ea 5514 'description': '',
5515 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5516 'tags': [],
5517 'modified_date': '20140919',
5518 'view_count': int,
5519 'channel': 'milan',
5520 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5521 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5522 },
5523 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
cdc628a4 5524 }, {
8bdd16b4 5525 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 5526 'playlist_mincount': 455,
8bdd16b4 5527 'info_dict': {
5528 'title': '2018 Chinese New Singles (11/6 updated)',
5529 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5530 'uploader': 'LBK',
5531 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
11f9be09 5532 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 5533 'channel': 'LBK',
5534 'view_count': int,
5535 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5536 'tags': [],
5537 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5538 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5539 'modified_date': r're:\d{8}',
5540 },
5541 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 5542 }, {
29f7c58a 5543 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5544 'only_matching': True,
5545 }, {
5546 # music album playlist
5547 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5548 'only_matching': True,
5549 }]
5550
5551 @classmethod
5552 def suitable(cls, url):
201c1459 5553 if YoutubeTabIE.suitable(url):
5554 return False
49a57e70 5555 from ..utils import parse_qs
201c1459 5556 qs = parse_qs(url)
5557 if qs.get('v', [None])[0]:
5558 return False
86e5f3ed 5559 return super().suitable(url)
29f7c58a 5560
5561 def _real_extract(self, url):
5562 playlist_id = self._match_id(url)
46953e7e 5563 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 5564 url = update_url_query(
5565 'https://www.youtube.com/playlist',
5566 parse_qs(url) or {'list': playlist_id})
5567 if is_music_url:
5568 url = smuggle_url(url, {'is_music_url': True})
5569 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 5570
5571
5572class YoutubeYtBeIE(InfoExtractor):
c76eb41b 5573 IE_DESC = 'youtu.be'
29f7c58a 5574 _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}
5575 _TESTS = [{
8bdd16b4 5576 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5577 'info_dict': {
5578 'id': 'yeWKywCrFtk',
5579 'ext': 'mp4',
5580 'title': 'Small Scale Baler and Braiding Rugs',
5581 'uploader': 'Backus-Page House Museum',
5582 'uploader_id': 'backuspagemuseum',
5583 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5584 'upload_date': '20161008',
5585 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5586 'categories': ['Nonprofits & Activism'],
5587 'tags': list,
5588 'like_count': int,
976ae3ea 5589 'age_limit': 0,
5590 'playable_in_embed': True,
5591 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5592 'channel': 'Backus-Page House Museum',
5593 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5594 'live_status': 'not_live',
5595 'view_count': int,
5596 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5597 'availability': 'public',
5598 'duration': 59,
12a1b225
A
5599 'comment_count': int,
5600 'channel_follower_count': int
8bdd16b4 5601 },
5602 'params': {
5603 'noplaylist': True,
5604 'skip_download': True,
5605 },
39e7107d 5606 }, {
8bdd16b4 5607 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 5608 'only_matching': True,
cdc628a4
PH
5609 }]
5610
8bdd16b4 5611 def _real_extract(self, url):
5ad28e7f 5612 mobj = self._match_valid_url(url)
29f7c58a 5613 video_id = mobj.group('id')
5614 playlist_id = mobj.group('playlist_id')
8bdd16b4 5615 return self.url_result(
29f7c58a 5616 update_url_query('https://www.youtube.com/watch', {
5617 'v': video_id,
5618 'list': playlist_id,
5619 'feature': 'youtu.be',
5620 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 5621
5622
b6ce9bb0 5623class YoutubeLivestreamEmbedIE(InfoExtractor):
5624 IE_DESC = 'YouTube livestream embeds'
5625 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5626 _TESTS = [{
5627 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5628 'only_matching': True,
5629 }]
5630
5631 def _real_extract(self, url):
5632 channel_id = self._match_id(url)
5633 return self.url_result(
5634 f'https://www.youtube.com/channel/{channel_id}/live',
5635 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5636
5637
8bdd16b4 5638class YoutubeYtUserIE(InfoExtractor):
96565c7e 5639 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 5640 IE_NAME = 'youtube:user'
8bdd16b4 5641 _VALID_URL = r'ytuser:(?P<id>.+)'
5642 _TESTS = [{
5643 'url': 'ytuser:phihag',
5644 'only_matching': True,
5645 }]
5646
5647 def _real_extract(self, url):
5648 user_id = self._match_id(url)
5649 return self.url_result(
c586f9e8 5650 'https://www.youtube.com/user/%s/videos' % user_id,
8bdd16b4 5651 ie=YoutubeTabIE.ie_key(), video_id=user_id)
9558dcec 5652
b05654f0 5653
3d3dddc9 5654class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 5655 IE_NAME = 'youtube:favorites'
96565c7e 5656 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 5657 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5658 _LOGIN_REQUIRED = True
5659 _TESTS = [{
5660 'url': ':ytfav',
5661 'only_matching': True,
5662 }, {
5663 'url': ':ytfavorites',
5664 'only_matching': True,
5665 }]
5666
5667 def _real_extract(self, url):
5668 return self.url_result(
5669 'https://www.youtube.com/playlist?list=LL',
5670 ie=YoutubeTabIE.ie_key())
5671
5672
ca5300c7 5673class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
5674 IE_NAME = 'youtube:notif'
5675 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5676 _VALID_URL = r':ytnotif(?:ication)?s?'
5677 _LOGIN_REQUIRED = True
5678 _TESTS = [{
5679 'url': ':ytnotif',
5680 'only_matching': True,
5681 }, {
5682 'url': ':ytnotifications',
5683 'only_matching': True,
5684 }]
5685
5686 def _extract_notification_menu(self, response, continuation_list):
5687 notification_list = traverse_obj(
5688 response,
5689 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5690 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5691 expected_type=list) or []
5692 continuation_list[0] = None
5693 for item in notification_list:
5694 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
5695 if entry:
5696 yield entry
5697 continuation = item.get('continuationItemRenderer')
5698 if continuation:
5699 continuation_list[0] = continuation
5700
5701 def _extract_notification_renderer(self, notification):
5702 video_id = traverse_obj(
5703 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
5704 url = f'https://www.youtube.com/watch?v={video_id}'
5705 channel_id = None
5706 if not video_id:
5707 browse_ep = traverse_obj(
5708 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
5709 channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str)
5710 post_id = self._search_regex(
5711 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
5712 'post id', default=None)
5713 if not channel_id or not post_id:
5714 return
5715 # The direct /post url redirects to this in the browser
5716 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5717
5718 channel = traverse_obj(
5719 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5720 expected_type=str)
c7a7baaa 5721 notification_title = self._get_text(notification, 'shortMessage')
5722 if notification_title:
5723 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
5724 # TODO: handle recommended videos
ca5300c7 5725 title = self._search_regex(
c7a7baaa 5726 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 5727 'video title', default=None)
ca5300c7 5728 upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d')
5729 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
5730 else None)
5731 return {
5732 '_type': 'url',
5733 'url': url,
5734 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
5735 'video_id': video_id,
5736 'title': title,
5737 'channel_id': channel_id,
5738 'channel': channel,
5739 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5740 'upload_date': upload_date,
5741 }
5742
5743 def _notification_menu_entries(self, ytcfg):
5744 continuation_list = [None]
5745 response = None
5746 for page in itertools.count(1):
5747 ctoken = traverse_obj(
5748 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
5749 response = self._extract_response(
5750 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
5751 ep='notification/get_notification_menu', check_get_keys='actions',
5752 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
5753 yield from self._extract_notification_menu(response, continuation_list)
5754 if not continuation_list[0]:
5755 break
5756
5757 def _real_extract(self, url):
5758 display_id = 'notifications'
5759 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
5760 self._report_playlist_authcheck(ytcfg)
5761 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
5762
5763
a6213a49 5764class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5765 IE_DESC = 'YouTube search'
78caa52a 5766 IE_NAME = 'youtube:search'
b05654f0 5767 _SEARCH_KEY = 'ytsearch'
a61fd4cf 5768 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 5769 _TESTS = [{
5770 'url': 'ytsearch5:youtube-dl test video',
5771 'playlist_count': 5,
5772 'info_dict': {
5773 'id': 'youtube-dl test video',
5774 'title': 'youtube-dl test video',
5775 }
5776 }]
b05654f0 5777
a61fd4cf 5778
5f7cb91a 5779class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 5780 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 5781 _SEARCH_KEY = 'ytsearchdate'
a6213a49 5782 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 5783 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 5784 _TESTS = [{
5785 'url': 'ytsearchdate5:youtube-dl test video',
5786 'playlist_count': 5,
5787 'info_dict': {
5788 'id': 'youtube-dl test video',
5789 'title': 'youtube-dl test video',
5790 }
5791 }]
75dff0ee 5792
c9ae7b95 5793
a6213a49 5794class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 5795 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 5796 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 5797 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 5798 _TESTS = [{
5799 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5800 'playlist_mincount': 5,
5801 'info_dict': {
11f9be09 5802 'id': 'youtube-dl test video',
3462ffa8 5803 'title': 'youtube-dl test video',
5804 }
a61fd4cf 5805 }, {
5806 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5807 'playlist_mincount': 5,
5808 'info_dict': {
5809 'id': 'python',
5810 'title': 'python',
5811 }
ad210f4f 5812 }, {
5813 'url': 'https://www.youtube.com/results?search_query=%23cats',
5814 'playlist_mincount': 1,
5815 'info_dict': {
5816 'id': '#cats',
5817 'title': '#cats',
12a1b225
A
5818 # The test suite does not have support for nested playlists
5819 # 'entries': [{
5820 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5821 # 'title': '#cats',
5822 # }],
ad210f4f 5823 },
3462ffa8 5824 }, {
5825 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5826 'only_matching': True,
5827 }]
5828
5829 def _real_extract(self, url):
4dfbf869 5830 qs = parse_qs(url)
386e1dd9 5831 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 5832 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 5833
5834
16aa9ea4 5835class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 5836 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 5837 IE_NAME = 'youtube:music:search_url'
5838 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5839 _TESTS = [{
5840 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5841 'playlist_count': 16,
5842 'info_dict': {
5843 'id': 'royalty free music',
5844 'title': 'royalty free music',
5845 }
5846 }, {
5847 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5848 'playlist_mincount': 30,
5849 'info_dict': {
5850 'id': 'royalty free music - songs',
5851 'title': 'royalty free music - songs',
5852 },
5853 'params': {'extract_flat': 'in_playlist'}
5854 }, {
5855 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5856 'playlist_mincount': 30,
5857 'info_dict': {
5858 'id': 'royalty free music - community playlists',
5859 'title': 'royalty free music - community playlists',
5860 },
5861 'params': {'extract_flat': 'in_playlist'}
5862 }]
5863
5864 _SECTIONS = {
5865 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5866 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5867 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5868 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5869 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5870 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5871 }
5872
5873 def _real_extract(self, url):
5874 qs = parse_qs(url)
5875 query = (qs.get('search_query') or qs.get('q'))[0]
5876 params = qs.get('sp', (None,))[0]
5877 if params:
5878 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5879 else:
ac668111 5880 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 5881 params = self._SECTIONS.get(section)
5882 if not params:
5883 section = None
5884 title = join_nonempty(query, section, delim=' - ')
af5c1c55 5885 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 5886
5887
182bda88 5888class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 5889 """
25f14e9f 5890 Base class for feed extractors
82d02080 5891 Subclasses must re-define the _FEED_NAME property.
d7ae0639 5892 """
b2e8bc1b 5893 _LOGIN_REQUIRED = True
82d02080 5894 _FEED_NAME = 'feeds'
a25bca9f 5895
5896 def _real_initialize(self):
5897 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 5898
82d02080 5899 @classproperty
d7ae0639 5900 def IE_NAME(self):
82d02080 5901 return f'youtube:{self._FEED_NAME}'
04cc9617 5902
3853309f 5903 def _real_extract(self, url):
3d3dddc9 5904 return self.url_result(
182bda88 5905 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
5906
5907
ef2f3c7f 5908class YoutubeWatchLaterIE(InfoExtractor):
5909 IE_NAME = 'youtube:watchlater'
96565c7e 5910 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 5911 _VALID_URL = r':ytwatchlater'
bc7a9cd8 5912 _TESTS = [{
8bdd16b4 5913 'url': ':ytwatchlater',
bc7a9cd8
S
5914 'only_matching': True,
5915 }]
25f14e9f
S
5916
5917 def _real_extract(self, url):
ef2f3c7f 5918 return self.url_result(
5919 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 5920
5921
25f14e9f 5922class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 5923 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 5924 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 5925 _FEED_NAME = 'recommended'
45db527f 5926 _LOGIN_REQUIRED = False
3d3dddc9 5927 _TESTS = [{
5928 'url': ':ytrec',
5929 'only_matching': True,
5930 }, {
5931 'url': ':ytrecommended',
5932 'only_matching': True,
5933 }, {
5934 'url': 'https://youtube.com',
5935 'only_matching': True,
5936 }]
1ed5b5c9 5937
1ed5b5c9 5938
25f14e9f 5939class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 5940 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 5941 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 5942 _FEED_NAME = 'subscriptions'
3d3dddc9 5943 _TESTS = [{
5944 'url': ':ytsubs',
5945 'only_matching': True,
5946 }, {
5947 'url': ':ytsubscriptions',
5948 'only_matching': True,
5949 }]
1ed5b5c9 5950
1ed5b5c9 5951
25f14e9f 5952class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 5953 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 5954 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 5955 _FEED_NAME = 'history'
3d3dddc9 5956 _TESTS = [{
5957 'url': ':ythistory',
5958 'only_matching': True,
5959 }]
1ed5b5c9
JMF
5960
5961
6e634cbe 5962class YoutubeStoriesIE(InfoExtractor):
5963 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
5964 IE_NAME = 'youtube:stories'
5965 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
5966 _TESTS = [{
5967 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
5968 'only_matching': True,
5969 }]
5970
5971 def _real_extract(self, url):
5972 playlist_id = f'RLTD{self._match_id(url)}'
5973 return self.url_result(
5974 f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
5975 ie=YoutubeTabIE, video_id=playlist_id)
5976
5977
15870e90
PH
5978class YoutubeTruncatedURLIE(InfoExtractor):
5979 IE_NAME = 'youtube:truncated_url'
5980 IE_DESC = False # Do not list
975d35db 5981 _VALID_URL = r'''(?x)
b95aab84
PH
5982 (?:https?://)?
5983 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5984 (?:watch\?(?:
c4808c60 5985 feature=[a-z_]+|
b95aab84
PH
5986 annotation_id=annotation_[^&]+|
5987 x-yt-cl=[0-9]+|
c1708b89 5988 hl=[^&]*|
287be8c6 5989 t=[0-9]+
b95aab84
PH
5990 )?
5991 |
5992 attribution_link\?a=[^&]+
5993 )
5994 $
975d35db 5995 '''
15870e90 5996
c4808c60 5997 _TESTS = [{
2d3d2997 5998 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 5999 'only_matching': True,
dc2fc736 6000 }, {
2d3d2997 6001 'url': 'https://www.youtube.com/watch?',
dc2fc736 6002 'only_matching': True,
b95aab84
PH
6003 }, {
6004 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6005 'only_matching': True,
6006 }, {
6007 'url': 'https://www.youtube.com/watch?feature=foo',
6008 'only_matching': True,
c1708b89
PH
6009 }, {
6010 'url': 'https://www.youtube.com/watch?hl=en-GB',
6011 'only_matching': True,
287be8c6
PH
6012 }, {
6013 'url': 'https://www.youtube.com/watch?t=2372',
6014 'only_matching': True,
c4808c60
PH
6015 }]
6016
15870e90
PH
6017 def _real_extract(self, url):
6018 raise ExtractorError(
78caa52a
PH
6019 'Did you forget to quote the URL? Remember that & is a meta '
6020 'character in most shells, so you want to put the URL in quotes, '
3867038a 6021 'like youtube-dl '
2d3d2997 6022 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 6023 ' or simply youtube-dl BaW_jenozKc .',
15870e90 6024 expected=True)
772fd5cc
PH
6025
6026
471d0367 6027class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 6028 IE_NAME = 'youtube:clip'
471d0367 6029 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6030 _TESTS = [{
6031 # FIXME: Other metadata should be extracted from the clip, not from the base video
6032 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6033 'info_dict': {
6034 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6035 'ext': 'mp4',
6036 'section_start': 29.0,
6037 'section_end': 39.7,
6038 'duration': 10.7,
12a1b225
A
6039 'age_limit': 0,
6040 'availability': 'public',
6041 'categories': ['Gaming'],
6042 'channel': 'Scott The Woz',
6043 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6044 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6045 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6046 'like_count': int,
6047 'playable_in_embed': True,
6048 'tags': 'count:17',
6049 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6050 'title': 'Mobile Games on Console - Scott The Woz',
6051 'upload_date': '20210920',
6052 'uploader': 'Scott The Woz',
6053 'uploader_id': 'scottthewoz',
6054 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6055 'view_count': int,
6056 'live_status': 'not_live',
6057 'channel_follower_count': int
471d0367 6058 }
6059 }]
3cd786db 6060
6061 def _real_extract(self, url):
471d0367 6062 clip_id = self._match_id(url)
6063 _, data = self._extract_webpage(url, clip_id)
6064
6065 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6066 if not video_id:
6067 raise ExtractorError('Unable to find video ID')
6068
6069 clip_data = traverse_obj(data, (
6070 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6071 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6072 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6073 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
6074
6075 return {
6076 '_type': 'url_transparent',
6077 'url': f'https://www.youtube.com/watch?v={video_id}',
6078 'ie_key': YoutubeIE.ie_key(),
6079 'id': clip_id,
6080 'section_start': int(clip_data['startTimeMs']) / 1000,
6081 'section_end': int(clip_data['endTimeMs']) / 1000,
6082 }
3cd786db 6083
6084
772fd5cc
PH
6085class YoutubeTruncatedIDIE(InfoExtractor):
6086 IE_NAME = 'youtube:truncated_id'
6087 IE_DESC = False # Do not list
b95aab84 6088 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
6089
6090 _TESTS = [{
6091 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6092 'only_matching': True,
6093 }]
6094
6095 def _real_extract(self, url):
6096 video_id = self._match_id(url)
6097 raise ExtractorError(
86e5f3ed 6098 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 6099 expected=True)