]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[ie/googledrive] Fix formats extraction (#9908)
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
6e634cbe 1import base64
d92f5d5a 2import calendar
a4894d3e 3import collections
109dd3b2 4import copy
c305a25c 5import datetime as dt
c26f9b99 6import enum
a5c56234 7import hashlib
0ca96d48 8import itertools
c5e8d7af 9import json
720c3099 10import math
c4417ddb 11import os.path
d77ab8e2 12import random
c5e8d7af 13import re
8828f457 14import shlex
46383212 15import sys
f8271158 16import threading
8a784c74 17import time
e0df6211 18import traceback
ac668111 19import urllib.parse
c5e8d7af 20
b05654f0 21from .common import InfoExtractor, SearchInfoExtractor
25836db6 22from .openload import PhantomJSwrapper
14f25df2 23from ..compat import functools
545cc85d 24from ..jsinterp import JSInterpreter
3d2623a8 25from ..networking.exceptions import HTTPError, network_exceptions
4bb4a188 26from ..utils import (
f8271158 27 NO_DEFAULT,
28 ExtractorError,
4d37720a 29 LazyList,
693f0600 30 UserNotLive,
720c3099 31 bug_reports_message,
82d02080 32 classproperty,
c5e8d7af 33 clean_html,
d92f5d5a 34 datetime_from_str,
11f9be09 35 dict_get,
a25a4243 36 filesize_from_tbr,
7a32c70d 37 filter_dict,
2d30521a 38 float_or_none,
11f9be09 39 format_field,
ff91cf74 40 get_first,
dd27fd17 41 int_or_none,
641ad5d8 42 is_html,
34921b43 43 join_nonempty,
48416bc4 44 js_to_json,
94278f72 45 mimetype2ext,
11f9be09 46 orderedSet,
6310acf5 47 parse_codecs,
49bd8c66 48 parse_count,
7c80519c 49 parse_duration,
7ea65411 50 parse_iso8601,
4dfbf869 51 parse_qs,
dca3ff4a 52 qualities,
3995d37d 53 remove_start,
cf7e015f 54 smuggle_url,
dbdaaa23 55 str_or_none,
c93d53f5 56 str_to_int,
f3aa3c3f 57 strftime_or_none,
7c365c21 58 traverse_obj,
a25a4243 59 try_call,
556dbe7f 60 try_get,
c5e8d7af
PH
61 unescapeHTML,
62 unified_strdate,
f0d785d3 63 unified_timestamp,
cf7e015f 64 unsmuggle_url,
8bdd16b4 65 update_url_query,
21c340b8 66 url_or_none,
fe93e2c4 67 urljoin,
7c365c21 68 variadic,
c5e8d7af
PH
69)
70
c795c39f 71STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client'
962ffcf8 72# any clients starting with _ cannot be explicitly requested by the user
000c15a4 73INNERTUBE_CLIENTS = {
74 'web': {
75 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
76 'INNERTUBE_CONTEXT': {
77 'client': {
78 'clientName': 'WEB',
a0c830f4 79 'clientVersion': '2.20220801.00.00',
000c15a4 80 }
81 },
82 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
83 },
84 'web_embedded': {
85 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
86 'INNERTUBE_CONTEXT': {
87 'client': {
88 'clientName': 'WEB_EMBEDDED_PLAYER',
a0c830f4 89 'clientVersion': '1.20220731.00.00',
000c15a4 90 },
91 },
92 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
93 },
94 'web_music': {
95 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
96 'INNERTUBE_HOST': 'music.youtube.com',
97 'INNERTUBE_CONTEXT': {
98 'client': {
99 'clientName': 'WEB_REMIX',
a0c830f4 100 'clientVersion': '1.20220727.01.00',
000c15a4 101 }
102 },
103 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
104 },
e7e94f2a 105 'web_creator': {
18c7683d 106 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
107 'INNERTUBE_CONTEXT': {
108 'client': {
109 'clientName': 'WEB_CREATOR',
a0c830f4 110 'clientVersion': '1.20220726.00.00',
e7e94f2a
D
111 }
112 },
113 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
114 },
000c15a4 115 'android': {
18c7683d 116 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 117 'INNERTUBE_CONTEXT': {
118 'client': {
119 'clientName': 'ANDROID',
7aad0654 120 'clientVersion': '19.09.37',
50ac0e54 121 'androidSdkVersion': 30,
7aad0654 122 'userAgent': 'com.google.android.youtube/19.09.37 (Linux; U; Android 11) gzip'
000c15a4 123 }
124 },
125 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 126 'REQUIRE_JS_PLAYER': False
000c15a4 127 },
128 'android_embedded': {
18c7683d 129 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 130 'INNERTUBE_CONTEXT': {
131 'client': {
132 'clientName': 'ANDROID_EMBEDDED_PLAYER',
7aad0654 133 'clientVersion': '19.09.37',
50ac0e54 134 'androidSdkVersion': 30,
7aad0654 135 'userAgent': 'com.google.android.youtube/19.09.37 (Linux; U; Android 11) gzip'
000c15a4 136 },
137 },
b6de707d 138 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
139 'REQUIRE_JS_PLAYER': False
000c15a4 140 },
141 'android_music': {
18c7683d 142 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 143 'INNERTUBE_CONTEXT': {
144 'client': {
145 'clientName': 'ANDROID_MUSIC',
7aad0654 146 'clientVersion': '6.42.52',
50ac0e54 147 'androidSdkVersion': 30,
7aad0654 148 'userAgent': 'com.google.android.apps.youtube.music/6.42.52 (Linux; U; Android 11) gzip'
000c15a4 149 }
150 },
151 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 152 'REQUIRE_JS_PLAYER': False
000c15a4 153 },
e7e94f2a 154 'android_creator': {
18c7683d 155 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
156 'INNERTUBE_CONTEXT': {
157 'client': {
158 'clientName': 'ANDROID_CREATOR',
50ac0e54 159 'clientVersion': '22.30.100',
160 'androidSdkVersion': 30,
161 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
e7e94f2a
D
162 },
163 },
b6de707d 164 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
165 'REQUIRE_JS_PLAYER': False
e7e94f2a 166 },
18c7683d 167 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
168 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 169 'ios': {
18c7683d 170 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 171 'INNERTUBE_CONTEXT': {
172 'client': {
173 'clientName': 'IOS',
7aad0654 174 'clientVersion': '19.09.3',
18c7683d 175 'deviceModel': 'iPhone14,3',
7aad0654 176 'userAgent': 'com.google.ios.youtube/19.09.3 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 177 }
178 },
b6de707d 179 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
180 'REQUIRE_JS_PLAYER': False
000c15a4 181 },
182 'ios_embedded': {
000c15a4 183 'INNERTUBE_CONTEXT': {
184 'client': {
185 'clientName': 'IOS_MESSAGES_EXTENSION',
7aad0654 186 'clientVersion': '19.09.3',
18c7683d 187 'deviceModel': 'iPhone14,3',
7aad0654 188 'userAgent': 'com.google.ios.youtube/19.09.3 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 189 },
190 },
b6de707d 191 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
192 'REQUIRE_JS_PLAYER': False
000c15a4 193 },
194 'ios_music': {
18c7683d 195 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 196 'INNERTUBE_CONTEXT': {
197 'client': {
198 'clientName': 'IOS_MUSIC',
7aad0654 199 'clientVersion': '6.33.3',
224b5a35 200 'deviceModel': 'iPhone14,3',
7aad0654 201 'userAgent': 'com.google.ios.youtubemusic/6.33.3 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 202 },
203 },
b6de707d 204 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
205 'REQUIRE_JS_PLAYER': False
000c15a4 206 },
e7e94f2a
D
207 'ios_creator': {
208 'INNERTUBE_CONTEXT': {
209 'client': {
210 'clientName': 'IOS_CREATOR',
224b5a35
SF
211 'clientVersion': '22.33.101',
212 'deviceModel': 'iPhone14,3',
213 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
e7e94f2a
D
214 },
215 },
b6de707d 216 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
217 'REQUIRE_JS_PLAYER': False
e7e94f2a 218 },
3619f78d 219 # mweb has 'ultralow' formats
220 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 221 'mweb': {
18c7683d 222 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 223 'INNERTUBE_CONTEXT': {
224 'client': {
225 'clientName': 'MWEB',
a0c830f4 226 'clientVersion': '2.20220801.00.00',
000c15a4 227 }
228 },
229 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
230 },
231 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
232 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
233 'tv_embedded': {
234 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
235 'INNERTUBE_CONTEXT': {
236 'client': {
237 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
238 'clientVersion': '2.0',
239 },
240 },
241 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
242 },
cf212d0a
H
243 # This client has pre-merged video+audio 720p/1080p streams
244 'mediaconnect': {
245 'INNERTUBE_CONTEXT': {
246 'client': {
247 'clientName': 'MEDIA_CONNECT_FRONTEND',
248 'clientVersion': '0.1',
249 },
250 },
251 'INNERTUBE_CONTEXT_CLIENT_NAME': 95
252 },
000c15a4 253}
254
255
e7870111
D
256def _split_innertube_client(client_name):
257 variant, *base = client_name.rsplit('.', 1)
258 if base:
259 return variant, base[0], variant
260 base, *variant = client_name.split('_', 1)
261 return client_name, base, variant[0] if variant else None
262
263
c795c39f
L
264def short_client_name(client_name):
265 main, *parts = _split_innertube_client(client_name)[0].replace('embedscreen', 'e_s').split('_')
266 return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper()
267
268
000c15a4 269def build_innertube_clients():
2e4cacd0 270 THIRD_PARTY = {
e7870111 271 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 272 }
1e75d97d 273 BASE_CLIENTS = ('ios', 'android', 'web', 'tv', 'mweb')
2e4cacd0 274 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 275
276 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 277 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 278 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 279 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 280 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 281
e7870111 282 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 283 ytcfg['priority'] = 10 * priority(base_client)
284
e48b3875 285 if not variant:
e7870111
D
286 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
287 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
288 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
289 embedscreen['priority'] -= 3
290 elif variant == 'embedded':
e48b3875 291 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 292 ytcfg['priority'] -= 2
e48b3875 293 else:
000c15a4 294 ytcfg['priority'] -= 3
295
296
297build_innertube_clients()
298
299
c26f9b99 300class BadgeType(enum.Enum):
301 AVAILABILITY_UNLISTED = enum.auto()
302 AVAILABILITY_PRIVATE = enum.auto()
303 AVAILABILITY_PUBLIC = enum.auto()
304 AVAILABILITY_PREMIUM = enum.auto()
305 AVAILABILITY_SUBSCRIPTION = enum.auto()
306 LIVE_NOW = enum.auto()
14a14335 307 VERIFIED = enum.auto()
c26f9b99 308
309
de7f3446 310class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 311 """Provide base functions for Youtube extractors"""
e00eb564 312
3462ffa8 313 _RESERVED_NAMES = (
08e29b9f 314 r'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|'
182bda88 315 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
1dd18a88 316 r'browse|oembed|get_video_info|iframe_api|s/player|source|'
0a5095fe 317 r'storefront|oops|index|account|t/terms|about|upload|signin|logout')
3462ffa8 318
3619f78d 319 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
320
52efa4b3 321 # _NETRC_MACHINE = 'youtube'
3619f78d 322
b2e8bc1b
JMF
323 # If True it will raise an error if no login info is provided
324 _LOGIN_REQUIRED = False
325
d9190e44
RH
326 _INVIDIOUS_SITES = (
327 # invidious-redirect websites
328 r'(?:www\.)?redirect\.invidious\.io',
329 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 330 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
331 r'(?:www\.)?invidious\.pussthecat\.org',
332 r'(?:www\.)?invidious\.zee\.li',
333 r'(?:www\.)?invidious\.ethibox\.fr',
05799a48
RH
334 r'(?:www\.)?iv\.ggtyler\.dev',
335 r'(?:www\.)?inv\.vern\.i2p',
336 r'(?:www\.)?am74vkcrjp2d5v36lcdqgsj2m6x36tbrkhsruoegwfcizzabnfgf5zyd\.onion',
337 r'(?:www\.)?inv\.riverside\.rocks',
338 r'(?:www\.)?invidious\.silur\.me',
339 r'(?:www\.)?inv\.bp\.projectsegfau\.lt',
340 r'(?:www\.)?invidious\.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid\.onion',
341 r'(?:www\.)?invidious\.slipfox\.xyz',
342 r'(?:www\.)?invidious\.esmail5pdn24shtvieloeedh7ehz3nrwcdivnfhfcedl7gf4kwddhkqd\.onion',
343 r'(?:www\.)?inv\.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad\.onion',
344 r'(?:www\.)?invidious\.tiekoetter\.com',
345 r'(?:www\.)?iv\.odysfvr23q5wgt7i456o5t3trw2cw5dgn56vbjfbq2m7xsc5vqbqpcyd\.onion',
346 r'(?:www\.)?invidious\.nerdvpn\.de',
347 r'(?:www\.)?invidious\.weblibre\.org',
348 r'(?:www\.)?inv\.odyssey346\.dev',
349 r'(?:www\.)?invidious\.dhusch\.de',
350 r'(?:www\.)?iv\.melmac\.space',
351 r'(?:www\.)?watch\.thekitty\.zone',
352 r'(?:www\.)?invidious\.privacydev\.net',
353 r'(?:www\.)?ng27owmagn5amdm7l5s3rsqxwscl5ynppnis5dqcasogkyxcfqn7psid\.onion',
354 r'(?:www\.)?invidious\.drivet\.xyz',
355 r'(?:www\.)?vid\.priv\.au',
356 r'(?:www\.)?euxxcnhsynwmfidvhjf6uzptsmh4dipkmgdmcmxxuo7tunp3ad2jrwyd\.onion',
357 r'(?:www\.)?inv\.vern\.cc',
358 r'(?:www\.)?invidious\.esmailelbob\.xyz',
359 r'(?:www\.)?invidious\.sethforprivacy\.com',
360 r'(?:www\.)?yt\.oelrichsgarcia\.de',
361 r'(?:www\.)?yt\.artemislena\.eu',
362 r'(?:www\.)?invidious\.flokinet\.to',
363 r'(?:www\.)?invidious\.baczek\.me',
364 r'(?:www\.)?y\.com\.sb',
365 r'(?:www\.)?invidious\.epicsite\.xyz',
366 r'(?:www\.)?invidious\.lidarshield\.cloud',
367 r'(?:www\.)?yt\.funami\.tech',
d9190e44 368 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
369 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
370 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
371 # youtube-dl invidious instances list
372 r'(?:(?:www|no)\.)?invidiou\.sh',
373 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
374 r'(?:www\.)?invidious\.kabi\.tk',
375 r'(?:www\.)?invidious\.mastodon\.host',
376 r'(?:www\.)?invidious\.zapashcanon\.fr',
377 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
378 r'(?:www\.)?invidious\.tinfoil-hat\.net',
379 r'(?:www\.)?invidious\.himiko\.cloud',
380 r'(?:www\.)?invidious\.reallyancient\.tech',
381 r'(?:www\.)?invidious\.tube',
382 r'(?:www\.)?invidiou\.site',
383 r'(?:www\.)?invidious\.site',
384 r'(?:www\.)?invidious\.xyz',
385 r'(?:www\.)?invidious\.nixnet\.xyz',
386 r'(?:www\.)?invidious\.048596\.xyz',
387 r'(?:www\.)?invidious\.drycat\.fr',
388 r'(?:www\.)?inv\.skyn3t\.in',
389 r'(?:www\.)?tube\.poal\.co',
390 r'(?:www\.)?tube\.connect\.cafe',
391 r'(?:www\.)?vid\.wxzm\.sx',
392 r'(?:www\.)?vid\.mint\.lgbt',
393 r'(?:www\.)?vid\.puffyan\.us',
394 r'(?:www\.)?yewtu\.be',
395 r'(?:www\.)?yt\.elukerio\.org',
396 r'(?:www\.)?yt\.lelux\.fi',
397 r'(?:www\.)?invidious\.ggc-project\.de',
398 r'(?:www\.)?yt\.maisputain\.ovh',
399 r'(?:www\.)?ytprivate\.com',
400 r'(?:www\.)?invidious\.13ad\.de',
401 r'(?:www\.)?invidious\.toot\.koeln',
402 r'(?:www\.)?invidious\.fdn\.fr',
403 r'(?:www\.)?watch\.nettohikari\.com',
404 r'(?:www\.)?invidious\.namazso\.eu',
405 r'(?:www\.)?invidious\.silkky\.cloud',
406 r'(?:www\.)?invidious\.exonip\.de',
407 r'(?:www\.)?invidious\.riverside\.rocks',
408 r'(?:www\.)?invidious\.blamefran\.net',
409 r'(?:www\.)?invidious\.moomoo\.de',
410 r'(?:www\.)?ytb\.trom\.tf',
411 r'(?:www\.)?yt\.cyberhost\.uk',
412 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
413 r'(?:www\.)?qklhadlycap4cnod\.onion',
414 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
415 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
416 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
417 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
418 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
419 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
420 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
421 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
422 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
423 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
424 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
425 r'(?:www\.)?piped\.kavin\.rocks',
d1c4f6d4 426 r'(?:www\.)?piped\.tokhmi\.xyz',
e14ea7fb 427 r'(?:www\.)?piped\.syncpundit\.io',
d1c4f6d4 428 r'(?:www\.)?piped\.mha\.fi',
e14ea7fb
BG
429 r'(?:www\.)?watch\.whatever\.social',
430 r'(?:www\.)?piped\.garudalinux\.org',
431 r'(?:www\.)?piped\.rivo\.lol',
432 r'(?:www\.)?piped-libre\.kavin\.rocks',
433 r'(?:www\.)?yt\.jae\.fi',
d1c4f6d4 434 r'(?:www\.)?piped\.mint\.lgbt',
e14ea7fb
BG
435 r'(?:www\.)?il\.ax',
436 r'(?:www\.)?piped\.esmailelbob\.xyz',
437 r'(?:www\.)?piped\.projectsegfau\.lt',
438 r'(?:www\.)?piped\.privacydev\.net',
439 r'(?:www\.)?piped\.palveluntarjoaja\.eu',
440 r'(?:www\.)?piped\.smnz\.de',
441 r'(?:www\.)?piped\.adminforge\.de',
442 r'(?:www\.)?watch\.whatevertinfoil\.de',
443 r'(?:www\.)?piped\.qdi\.fi',
6a9c7a2b 444 r'(?:(?:www|cf)\.)?piped\.video',
bc87dac7 445 r'(?:www\.)?piped\.aeong\.one',
05799a48
RH
446 r'(?:www\.)?piped\.moomoo\.me',
447 r'(?:www\.)?piped\.chauvet\.pro',
448 r'(?:www\.)?watch\.leptons\.xyz',
449 r'(?:www\.)?pd\.vern\.cc',
450 r'(?:www\.)?piped\.hostux\.net',
451 r'(?:www\.)?piped\.lunar\.icu',
78a78fa7
BG
452 # Hyperpipe instances from https://hyperpipe.codeberg.page/
453 r'(?:www\.)?hyperpipe\.surge\.sh',
454 r'(?:www\.)?hyperpipe\.esmailelbob\.xyz',
455 r'(?:www\.)?listen\.whatever\.social',
456 r'(?:www\.)?music\.adminforge\.de',
d9190e44
RH
457 )
458
c26f9b99 459 # extracted from account/account_menu ep
460 # XXX: These are the supported YouTube UI and API languages,
461 # which is slightly different from languages supported for translation in YouTube studio
462 _SUPPORTED_LANG_CODES = [
463 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es',
464 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv',
465 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi',
466 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw',
467 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml',
468 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko'
469 ]
470
a057779d 471 _IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
472
7666b936 473 _YT_HANDLE_RE = r'@[\w.-]{3,30}' # https://support.google.com/youtube/answer/11585688?hl=en
474 _YT_CHANNEL_UCID_RE = r'UC[\w-]{22}'
475
476 def ucid_or_none(self, ucid):
477 return self._search_regex(rf'^({self._YT_CHANNEL_UCID_RE})$', ucid, 'UC-id', default=None)
478
479 def handle_or_none(self, handle):
480 return self._search_regex(rf'^({self._YT_HANDLE_RE})$', handle, '@-handle', default=None)
481
482 def handle_from_url(self, url):
483 return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_HANDLE_RE})',
484 url, 'channel handle', default=None)
485
486 def ucid_from_url(self, url):
487 return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_CHANNEL_UCID_RE})',
488 url, 'channel id', default=None)
489
c26f9b99 490 @functools.cached_property
491 def _preferred_lang(self):
492 """
493 Returns a language code supported by YouTube for the user preferred language.
494 Returns None if no preferred language set.
495 """
496 preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0]
497 if not preferred_lang:
498 return
499 if preferred_lang not in self._SUPPORTED_LANG_CODES:
500 raise ExtractorError(
501 f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.',
502 expected=True)
503 elif preferred_lang != 'en':
504 self.report_warning(
505 f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.')
506 return preferred_lang
507
cce889b9 508 def _initialize_consent(self):
509 cookies = self._get_cookies('https://www.youtube.com/')
510 if cookies.get('__Secure-3PSID'):
511 return
378ae9f9 512 socs = cookies.get('SOCS')
513 if socs and not socs.value.startswith('CAA'): # not consented
514 return
515 self._set_cookie('.youtube.com', 'SOCS', 'CAI', secure=True) # accept all (required for mixes)
8d81f3e3 516
f3aa3c3f 517 def _initialize_pref(self):
518 cookies = self._get_cookies('https://www.youtube.com/')
519 pref_cookie = cookies.get('PREF')
520 pref = {}
521 if pref_cookie:
522 try:
14f25df2 523 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 524 except ValueError:
525 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
c26f9b99 526 pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'})
14f25df2 527 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 528
b2e8bc1b 529 def _real_initialize(self):
f3aa3c3f 530 self._initialize_pref()
cce889b9 531 self._initialize_consent()
a25bca9f 532 self._check_login_required()
533
534 def _check_login_required(self):
24146491 535 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 536 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 537
b7c47b74 538 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
539 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 540
000c15a4 541 def _get_default_ytcfg(self, client='web'):
542 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 543
000c15a4 544 def _get_innertube_host(self, client='web'):
545 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 546
000c15a4 547 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 548 # try_get but with fallback to default ytcfg client values when present
549 _func = lambda y: try_get(y, getter, expected_type)
550 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
551
000c15a4 552 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 553 return self._ytcfg_get_safe(
554 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 555 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 556
000c15a4 557 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 558 return self._ytcfg_get_safe(
559 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 560 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 561
2ae778b8 562 def _select_api_hostname(self, req_api_hostname, default_client=None):
563 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
564 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
565
000c15a4 566 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 567 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 568
000c15a4 569 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 570 context = get_first(
571 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 572 # Enforce language and tz for extraction
573 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
c26f9b99 574 client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 575 return context
576
cf87314d 577 _SAPISID = None
578
109dd3b2 579 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 580 time_now = round(time.time())
cf87314d 581 if self._SAPISID is None:
582 yt_cookies = self._get_cookies('https://www.youtube.com')
583 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
584 # See: https://github.com/yt-dlp/yt-dlp/issues/393
585 sapisid_cookie = dict_get(
586 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
587 if sapisid_cookie and sapisid_cookie.value:
588 self._SAPISID = sapisid_cookie.value
589 self.write_debug('Extracted SAPISID cookie')
590 # SAPISID cookie is required if not already present
591 if not yt_cookies.get('SAPISID'):
592 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
593 self._set_cookie(
594 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
595 else:
596 self._SAPISID = False
597 if not self._SAPISID:
598 return None
1974e99f 599 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
600 sapisidhash = hashlib.sha1(
86e5f3ed 601 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 602 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
603
604 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 605 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 606 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 607
109dd3b2 608 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 609 data.update(query)
11f9be09 610 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 611 real_headers.update({'content-type': 'application/json'})
612 if headers:
613 real_headers.update(headers)
2ae778b8 614 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
615 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 616 return self._download_json(
2ae778b8 617 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 618 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 619 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 620 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 621
65141660 622 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
623 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 624
99e9e001 625 @staticmethod
626 def _extract_session_index(*data):
627 """
628 Index of current account in account list.
629 See: https://github.com/yt-dlp/yt-dlp/pull/519
630 """
631 for ytcfg in data:
632 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
633 if session_index is not None:
634 return session_index
635
636 # Deprecated?
637 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 638 if ytcfg:
14f25df2 639 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
640 if token:
641 return token
99e9e001 642 if webpage:
643 return self._search_regex(
644 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
645 'identity token', default=None, fatal=False)
a1c5d2ca
M
646
647 @staticmethod
fe93e2c4 648 def _extract_account_syncid(*args):
8ea3f7b9 649 """
650 Extract syncId required to download private playlists of secondary channels
fe93e2c4 651 @params response and/or ytcfg
8ea3f7b9 652 """
fe93e2c4 653 for data in args:
654 # ytcfg includes channel_syncid if on secondary channel
14f25df2 655 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 656 if delegated_sid:
657 return delegated_sid
658 sync_ids = (try_get(
659 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 660 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 661 if len(sync_ids) >= 2 and sync_ids[1]:
662 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
663 # and just "user_syncid||" for primary channel. We only want the channel_syncid
664 return sync_ids[0]
a1c5d2ca 665
ac56cf38 666 @staticmethod
667 def _extract_visitor_data(*args):
668 """
669 Extracts visitorData from an API response or ytcfg
670 Appears to be used to track session state
671 """
9222c381 672 return get_first(
6c73052c 673 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 674 expected_type=str)
ac56cf38 675
2762dbb1 676 @functools.cached_property
99e9e001 677 def is_authenticated(self):
678 return bool(self._generate_sapisidhash_header())
679
11f9be09 680 def extract_ytcfg(self, video_id, webpage):
8c54a305 681 if not webpage:
682 return {}
29f7c58a 683 return self._parse_json(
684 self._search_regex(
685 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 686 default='{}'), video_id, fatal=False) or {}
687
11f9be09 688 def generate_api_headers(
99e9e001 689 self, *, ytcfg=None, account_syncid=None, session_index=None,
690 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
691
2ae778b8 692 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 693 headers = {
14f25df2 694 'X-YouTube-Client-Name': str(
11f9be09 695 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
696 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 697 'Origin': origin,
698 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
699 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
50ac0e54 700 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
701 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
99e9e001 702 }
703 if session_index is None:
314ee305 704 session_index = self._extract_session_index(ytcfg)
705 if account_syncid or session_index is not None:
706 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 707
109dd3b2 708 auth = self._generate_sapisidhash_header(origin)
f4f751af 709 if auth is not None:
710 headers['Authorization'] = auth
109dd3b2 711 headers['X-Origin'] = origin
7a32c70d 712 return filter_dict(headers)
29f7c58a 713
a25bca9f 714 def _download_ytcfg(self, client, video_id):
715 url = {
716 'web': 'https://www.youtube.com',
717 'web_music': 'https://music.youtube.com',
718 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
719 }.get(client)
720 if not url:
721 return {}
722 webpage = self._download_webpage(
723 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
724 return self.extract_ytcfg(video_id, webpage) or {}
725
2d6659b9 726 @staticmethod
727 def _build_api_continuation_query(continuation, ctp=None):
728 query = {
729 'continuation': continuation
730 }
731 # TODO: Inconsistency with clickTrackingParams.
732 # Currently we have a fixed ctp contained within context (from ytcfg)
733 # and a ctp in root query for continuation.
734 if ctp:
735 query['clickTracking'] = {'clickTrackingParams': ctp}
736 return query
737
2d6659b9 738 @classmethod
739 def _extract_next_continuation_data(cls, renderer):
740 next_continuation = try_get(
741 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
742 lambda x: x['continuation']['reloadContinuationData']), dict)
743 if not next_continuation:
744 return
745 continuation = next_continuation.get('continuation')
746 if not continuation:
747 return
748 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 749 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 750
751 @classmethod
752 def _extract_continuation_ep_data(cls, continuation_ep: dict):
753 if isinstance(continuation_ep, dict):
754 continuation = try_get(
14f25df2 755 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 756 if not continuation:
757 return
758 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 759 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 760
761 @classmethod
762 def _extract_continuation(cls, renderer):
763 next_continuation = cls._extract_next_continuation_data(renderer)
764 if next_continuation:
765 return next_continuation
fe93e2c4 766
7a32c70d 767 return traverse_obj(renderer, (
768 ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
769 ('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
770 ), get_all=False, expected_type=cls._extract_continuation_ep_data)
2d6659b9 771
fe93e2c4 772 @classmethod
773 def _extract_alerts(cls, data):
109dd3b2 774 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
775 if not isinstance(alert_dict, dict):
776 continue
777 for alert in alert_dict.values():
778 alert_type = alert.get('type')
779 if not alert_type:
780 continue
052e1350 781 message = cls._get_text(alert, 'text')
109dd3b2 782 if message:
783 yield alert_type, message
784
c0ac49bc 785 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
a057779d 786 errors, warnings = [], []
109dd3b2 787 for alert_type, alert_message in alerts:
641ad5d8 788 if alert_type.lower() == 'error' and fatal:
109dd3b2 789 errors.append([alert_type, alert_message])
a057779d 790 elif alert_message not in self._IGNORED_WARNINGS:
109dd3b2 791 warnings.append([alert_type, alert_message])
792
793 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 794 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 795 if errors:
796 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
797
798 def _extract_and_report_alerts(self, data, *args, **kwargs):
799 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
800
14a14335 801 def _extract_badges(self, badge_list: list):
802 """
803 Extract known BadgeType's from a list of badge renderers.
804 @returns [{'type': BadgeType}]
805 """
806 icon_type_map = {
c26f9b99 807 'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED,
808 'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE,
14a14335 809 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC,
810 'CHECK_CIRCLE_THICK': BadgeType.VERIFIED,
811 'OFFICIAL_ARTIST_BADGE': BadgeType.VERIFIED,
8213ce28 812 'CHECK': BadgeType.VERIFIED,
c26f9b99 813 }
814
815 badge_style_map = {
816 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION,
817 'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM,
14a14335 818 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW,
8213ce28 819 'BADGE_STYLE_TYPE_VERIFIED': BadgeType.VERIFIED,
ad54c913 820 'BADGE_STYLE_TYPE_VERIFIED_ARTIST': BadgeType.VERIFIED,
c26f9b99 821 }
822
823 label_map = {
824 'unlisted': BadgeType.AVAILABILITY_UNLISTED,
825 'private': BadgeType.AVAILABILITY_PRIVATE,
826 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION,
827 'live': BadgeType.LIVE_NOW,
14a14335 828 'premium': BadgeType.AVAILABILITY_PREMIUM,
8213ce28 829 'verified': BadgeType.VERIFIED,
ad54c913 830 'official artist channel': BadgeType.VERIFIED,
c26f9b99 831 }
832
833 badges = []
14a14335 834 for badge in traverse_obj(badge_list, (..., lambda key, _: re.search(r'[bB]adgeRenderer$', key))):
c26f9b99 835 badge_type = (
14a14335 836 icon_type_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
c26f9b99 837 or badge_style_map.get(traverse_obj(badge, 'style'))
838 )
839 if badge_type:
840 badges.append({'type': badge_type})
841 continue
842
843 # fallback, won't work in some languages
14a14335 844 label = traverse_obj(
845 badge, 'label', ('accessibilityData', 'label'), 'tooltip', 'iconTooltip', get_all=False, expected_type=str, default='')
c26f9b99 846 for match, label_badge_type in label_map.items():
847 if match in label.lower():
14a14335 848 badges.append({'type': label_badge_type})
849 break
c26f9b99 850
47193e02 851 return badges
852
c26f9b99 853 @staticmethod
854 def _has_badge(badges, badge_type):
855 return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type))
856
47193e02 857 @staticmethod
052e1350 858 def _get_text(data, *path_list, max_runs=None):
859 for path in path_list or [None]:
860 if path is None:
861 obj = [data]
862 else:
863 obj = traverse_obj(data, path, default=[])
864 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
865 obj = [obj]
866 for item in obj:
14f25df2 867 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 868 if text:
869 return text
870 runs = try_get(item, lambda x: x['runs'], list) or []
871 if not runs and isinstance(item, list):
872 runs = item
873
874 runs = runs[:min(len(runs), max_runs or len(runs))]
6839ae1f 875 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str))
052e1350 876 if text:
877 return text
47193e02 878
f0d785d3 879 def _get_count(self, data, *path_list):
880 count_text = self._get_text(data, *path_list) or ''
881 count = parse_count(count_text)
882 if count is None:
883 count = str_to_int(
884 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
885 return count
886
a709d873 887 @staticmethod
888 def _extract_thumbnails(data, *path_list):
889 """
890 Extract thumbnails from thumbnails dict
891 @param path_list: path list to level that contains 'thumbnails' key
892 """
893 thumbnails = []
894 for path in path_list or [()]:
6839ae1f 895 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...)):
a709d873 896 thumbnail_url = url_or_none(thumbnail.get('url'))
897 if not thumbnail_url:
898 continue
899 # Sometimes youtube gives a wrong thumbnail URL. See:
900 # https://github.com/yt-dlp/yt-dlp/issues/233
901 # https://github.com/ytdl-org/youtube-dl/issues/28023
902 if 'maxresdefault' in thumbnail_url:
903 thumbnail_url = thumbnail_url.split('?')[0]
904 thumbnails.append({
905 'url': thumbnail_url,
906 'height': int_or_none(thumbnail.get('height')),
907 'width': int_or_none(thumbnail.get('width')),
908 })
909 return thumbnails
910
f3aa3c3f 911 @staticmethod
912 def extract_relative_time(relative_time_text):
913 """
914 Extracts a relative time from string and converts to dt object
2fb35f60 915 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today', '8 yr ago'
f3aa3c3f 916 """
2fb35f60 917
5ca095cb 918 # XXX: this could be moved to a general function in utils/_utils.py
2fb35f60 919 # The relative time text strings are roughly the same as what
920 # Javascript's Intl.RelativeTimeFormat function generates.
921 # See: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Intl/RelativeTimeFormat
922 mobj = re.search(
923 r'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>sec(?:ond)?|s|min(?:ute)?|h(?:our|r)?|d(?:ay)?|w(?:eek|k)?|mo(?:nth)?|y(?:ear|r)?)s?\s*ago',
924 relative_time_text)
f3aa3c3f 925 if mobj:
f0d785d3 926 start = mobj.group('start')
927 if start:
928 return datetime_from_str(start)
f3aa3c3f 929 try:
f0d785d3 930 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 931 except ValueError:
932 return None
933
c26f9b99 934 def _parse_time_text(self, text):
935 if not text:
936 return
c305a25c 937 dt_ = self.extract_relative_time(text)
f3aa3c3f 938 timestamp = None
c305a25c 939 if isinstance(dt_, dt.datetime):
940 timestamp = calendar.timegm(dt_.timetuple())
f0d785d3 941
942 if timestamp is None:
943 timestamp = (
944 unified_timestamp(text) or unified_timestamp(
945 self._search_regex(
17322130 946 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 947 text.lower(), 'time text', default=None)))
f0d785d3 948
c26f9b99 949 if text and timestamp is None and self._preferred_lang in (None, 'en'):
950 self.report_warning(
951 f'Cannot parse localized time text "{text}"', only_once=True)
952 return timestamp
f3aa3c3f 953
109dd3b2 954 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
955 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 956 default_client='web'):
eb5bdbfa 957 raise_for_incomplete = bool(self._configuration_arg('raise_incomplete_data', ie_key=YoutubeIE))
958 # Incomplete Data should be a warning by default when retries are exhausted, while other errors should be fatal.
959 icd_retries = iter(self.RetryManager(fatal=raise_for_incomplete))
960 icd_rm = next(icd_retries)
961 main_retries = iter(self.RetryManager())
962 main_rm = next(main_retries)
feebf6d0
SS
963 # Manual retry loop for multiple RetryManagers
964 # The proper RetryManager MUST be advanced after an error
b634ba74 965 # and its result MUST be checked if the manager is non fatal
feebf6d0 966 while True:
109dd3b2 967 try:
968 response = self._call_api(
969 ep=ep, fatal=True, headers=headers,
be5c1ae8 970 video_id=item_id, query=query, note=note,
109dd3b2 971 context=self._extract_context(ytcfg, default_client),
972 api_key=self._extract_api_key(ytcfg, default_client),
be5c1ae8 973 api_hostname=api_hostname, default_client=default_client)
109dd3b2 974 except ExtractorError as e:
be5c1ae8 975 if not isinstance(e.cause, network_exceptions):
976 return self._error_or_warning(e, fatal=fatal)
3d2623a8 977 elif not isinstance(e.cause, HTTPError):
eb5bdbfa 978 main_rm.error = e
979 next(main_retries)
be5c1ae8 980 continue
109dd3b2 981
3d2623a8 982 first_bytes = e.cause.response.read(512)
be5c1ae8 983 if not is_html(first_bytes):
984 yt_error = try_get(
985 self._parse_json(
3d2623a8 986 self._webpage_read_content(e.cause.response, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
be5c1ae8 987 lambda x: x['error']['message'], str)
988 if yt_error:
989 self._report_alerts([('ERROR', yt_error)], fatal=False)
990 # Downloading page may result in intermittent 5xx HTTP error
eb5bdbfa 991 # Sometimes a 404 is also received. See: https://github.com/ytdl-org/youtube-dl/issues/28289
be5c1ae8 992 # We also want to catch all other network exceptions since errors in later pages can be troublesome
993 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
3d2623a8 994 if e.cause.status not in (403, 429):
eb5bdbfa 995 main_rm.error = e
996 next(main_retries)
be5c1ae8 997 continue
998 return self._error_or_warning(e, fatal=fatal)
999
1000 try:
1001 self._extract_and_report_alerts(response, only_once=True)
1002 except ExtractorError as e:
eb5bdbfa 1003 # YouTube's servers may return errors we want to retry on in a 200 OK response
be5c1ae8 1004 # See: https://github.com/yt-dlp/yt-dlp/issues/839
1005 if 'unknown error' in e.msg.lower():
eb5bdbfa 1006 main_rm.error = e
1007 next(main_retries)
be5c1ae8 1008 continue
1009 return self._error_or_warning(e, fatal=fatal)
1010 # Youtube sometimes sends incomplete data
1011 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
1012 if not traverse_obj(response, *variadic(check_get_keys)):
eb5bdbfa 1013 icd_rm.error = ExtractorError('Incomplete data received', expected=True)
1014 should_retry = next(icd_retries, None)
1015 if not should_retry:
1016 return None
be5c1ae8 1017 continue
1018
1019 return response
109dd3b2 1020
9297939e 1021 @staticmethod
1022 def is_music_url(url):
5b28cef7 1023 return re.match(r'(https?://)?music\.youtube\.com/', url) is not None
9297939e 1024
30a074c2 1025 def _extract_video(self, renderer):
1026 video_id = renderer.get('videoId')
4dc23a80
M
1027
1028 reel_header_renderer = traverse_obj(renderer, (
1029 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer',
1030 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer'))
1031
1032 title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText')
052e1350 1033 description = self._get_text(renderer, 'descriptionSnippet')
6141346d
M
1034
1035 duration = int_or_none(renderer.get('lengthSeconds'))
1036 if duration is None:
1037 duration = parse_duration(self._get_text(
1038 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 1039 if duration is None:
4dc23a80 1040 # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab)
1c1b2f96 1041 duration = parse_duration(self._search_regex(
1042 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
1043 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
1044 video_id, default=None, group='duration'))
1045
f3aa3c3f 1046 channel_id = traverse_obj(
a44ca5a4 1047 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
1048 expected_type=str, get_all=False)
4dc23a80
M
1049 if not channel_id:
1050 channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId'))
1051
7666b936 1052 channel_id = self.ucid_or_none(channel_id)
1053
f3aa3c3f 1054 overlay_style = traverse_obj(
a44ca5a4 1055 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
1056 get_all=False, expected_type=str)
14a14335 1057 badges = self._extract_badges(traverse_obj(renderer, 'badges'))
8213ce28 1058 owner_badges = self._extract_badges(traverse_obj(renderer, 'ownerBadges'))
fd2ad7cb 1059 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 1060 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
1061 expected_type=str)) or ''
fd2ad7cb 1062 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 1063 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 1064 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 1065
4dc23a80
M
1066 time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo')
1067 or self._get_text(reel_header_renderer, 'timestampText') or '')
1068 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
1069
867c66ff
M
1070 live_status = (
1071 'is_upcoming' if scheduled_timestamp is not None
1072 else 'was_live' if 'streamed' in time_text.lower()
1073 else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW)
1074 else None)
1075
4dc23a80
M
1076 # videoInfo is a string like '50K views • 10 years ago'.
1077 view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or ''
1078 view_count = (0 if 'no views' in view_count_text.lower()
1079 else self._get_count({'simpleText': view_count_text}))
1080 view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count'
1081
93e12ed7 1082 channel = (self._get_text(renderer, 'ownerText', 'shortBylineText')
1083 or self._get_text(reel_header_renderer, 'channelTitleText'))
1084
1085 channel_handle = traverse_obj(renderer, (
1086 'shortBylineText', 'runs', ..., 'navigationEndpoint',
1087 (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl'))),
1088 expected_type=self.handle_from_url, get_all=False)
30a074c2 1089 return {
39ed931e 1090 '_type': 'url',
30a074c2 1091 'ie_key': YoutubeIE.ie_key(),
1092 'id': video_id,
fd2ad7cb 1093 'url': url,
30a074c2 1094 'title': title,
1095 'description': description,
1096 'duration': duration,
f3aa3c3f 1097 'channel_id': channel_id,
93e12ed7 1098 'channel': channel,
4dc23a80 1099 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
93e12ed7 1100 'uploader': channel,
1101 'uploader_id': channel_handle,
1102 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
4dc23a80 1103 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
5225df50 1104 'timestamp': (self._parse_time_text(time_text)
1105 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
1106 else None),
f3aa3c3f 1107 'release_timestamp': scheduled_timestamp,
c26f9b99 1108 'availability':
1109 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
1110 else self._availability(
1111 is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None,
1112 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
1113 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
867c66ff 1114 is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
4dc23a80 1115 view_count_field: view_count,
14a14335 1116 'live_status': live_status,
8213ce28 1117 'channel_is_verified': True if self._has_badge(owner_badges, BadgeType.VERIFIED) else None
30a074c2 1118 }
1119
0c148415 1120
360e1ca5 1121class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 1122 IE_DESC = 'YouTube'
cb7dfeea 1123 _VALID_URL = r"""(?x)^
c5e8d7af 1124 (
edb53e2d 1125 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 1126 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
1127 (?:www\.)?deturl\.com/www\.youtube\.com|
1128 (?:www\.)?pwnyoutube\.com|
1129 (?:www\.)?hooktube\.com|
1130 (?:www\.)?yourepeat\.com|
1131 tube\.majestyc\.net|
1132 %(invidious)s|
1133 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
1134 (?:.*?\#/)? # handle anchor (#/) redirect urls
1135 (?: # the various things that can precede the ID:
dad2210c 1136 (?:(?:v|embed|e|shorts|live)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 1137 |(?: # or the v= param in all its forms
f7000f3a 1138 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 1139 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 1140 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
1141 v=
1142 )
f4b05232 1143 ))
cbaed4bb
S
1144 |(?:
1145 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
1146 vid\.plus| # or vid.plus/xxxx
1147 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 1148 %(invidious)s
cbaed4bb 1149 )/
edb53e2d 1150 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 1151 )
c5e8d7af 1152 )? # all until now is optional -> you can pass the naked ID
201c1459 1153 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 1154 (?(1).+)? # if we found the ID, everything can follow
9297939e 1155 (?:\#|$)""" % {
d9190e44 1156 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 1157 }
7c6eb424 1158 _EMBED_REGEX = [
1159 r'''(?x)
1160 (?:
0ca0f881 1161 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
7c6eb424 1162 data-video-url=|
1163 <embed[^>]+?src=|
1164 embedSWF\(?:\s*|
1165 <object[^>]+data=|
1166 new\s+SWFObject\(
1167 )
1168 (["\'])
1169 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1170 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1171 \1''',
1172 # https://wordpress.org/plugins/lazy-load-for-videos/
1173 r'''(?xs)
1174 <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1175 \s[^>]*\bclass="[^"]*\blazy-load-youtube''',
1176 ]
6368e2e6 1177 _RETURN_TYPE = 'video' # XXX: How to handle multifeed?
7c6eb424 1178
e40c758c 1179 _PLAYER_INFO_RE = (
cc2db878 1180 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1181 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$',
545cc85d 1182 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 1183 )
85ec2a33 1184 _formats = { # NB: Used in YoutubeWebArchiveIE and GoogleDriveIE
c2d3cb4c 1185 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1186 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1187 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1188 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1189 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1190 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1191 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1192 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 1193 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 1194 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1195 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1196 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1197 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1198 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1199 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 1200 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 1201 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1202 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 1203
1204
1205 # 3D videos
c2d3cb4c 1206 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1207 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1208 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1209 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 1210 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1211 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1212 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 1213
96fb5605 1214 # Apple HTTP Live Streaming
11f12195 1215 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 1216 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1217 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1218 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1219 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1220 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 1221 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1222 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
1223
1224 # DASH mp4 video
d23028a8
S
1225 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1226 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1227 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1228 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1229 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 1230 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
1231 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1232 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1233 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1234 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1235 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1236 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 1237
f6f1fc92 1238 # Dash mp4 audio
d23028a8
S
1239 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1240 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1241 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1242 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1243 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1244 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1245 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1246
1247 # Dash webm
d23028a8
S
1248 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1249 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1250 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1251 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1252 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1253 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1254 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1255 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1256 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1257 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1258 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1259 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1260 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1261 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1262 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1263 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1264 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1265 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1266 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1267 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1268 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1269 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1270
1271 # Dash webm audio
d23028a8
S
1272 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1273 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1274
0857baad 1275 # Dash webm audio with opus inside
d23028a8
S
1276 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1277 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1278 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1279
ce6b9a2d
PH
1280 # RTMP (unnamed)
1281 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1282
1283 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1284 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1285 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1286 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1287 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1288 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1289 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1290 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1291 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1292 }
29f7c58a 1293 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1294
fd5c4aab
S
1295 _GEO_BYPASS = False
1296
78caa52a 1297 IE_NAME = 'youtube'
2eb88d95
PH
1298 _TESTS = [
1299 {
2d3d2997 1300 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1301 'info_dict': {
1302 'id': 'BaW_jenozKc',
1303 'ext': 'mp4',
3867038a 1304 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
ff9f925b 1305 'channel': 'Philipp Hagemeister',
dd4c4492
S
1306 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1307 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1308 'upload_date': '20121002',
ff9f925b 1309 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1310 'categories': ['Science & Technology'],
3867038a 1311 'tags': ['youtube-dl'],
556dbe7f 1312 'duration': 10,
dbdaaa23 1313 'view_count': int,
3e7c1224 1314 'like_count': int,
ff9f925b 1315 'availability': 'public',
1316 'playable_in_embed': True,
1317 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1318 'live_status': 'not_live',
1319 'age_limit': 0,
7c80519c 1320 'start_time': 1,
297a564b 1321 'end_time': 9,
12a1b225 1322 'comment_count': int,
7666b936 1323 'channel_follower_count': int,
1324 'uploader': 'Philipp Hagemeister',
1325 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
1326 'uploader_id': '@PhilippHagemeister',
5caf30db 1327 'heatmap': 'count:100',
2eb88d95 1328 }
0e853ca4 1329 },
fccd3771 1330 {
4bc3a23e
PH
1331 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1332 'note': 'Embed-only video (#1746)',
1333 'info_dict': {
1334 'id': 'yZIXLfi8CZQ',
1335 'ext': 'mp4',
1336 'upload_date': '20120608',
1337 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1338 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
94bfcd23 1339 'age_limit': 18,
545cc85d 1340 },
1341 'skip': 'Private video',
fccd3771 1342 },
11b56058 1343 {
8bdd16b4 1344 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1345 'note': 'Use the first video ID in the URL',
1346 'info_dict': {
1347 'id': 'BaW_jenozKc',
1348 'ext': 'mp4',
3867038a 1349 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
976ae3ea 1350 'channel': 'Philipp Hagemeister',
1351 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1352 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1353 'upload_date': '20121002',
976ae3ea 1354 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1355 'categories': ['Science & Technology'],
3867038a 1356 'tags': ['youtube-dl'],
556dbe7f 1357 'duration': 10,
dbdaaa23 1358 'view_count': int,
11b56058 1359 'like_count': int,
976ae3ea 1360 'availability': 'public',
1361 'playable_in_embed': True,
1362 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1363 'live_status': 'not_live',
1364 'age_limit': 0,
12a1b225 1365 'comment_count': int,
7666b936 1366 'channel_follower_count': int,
1367 'uploader': 'Philipp Hagemeister',
1368 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
1369 'uploader_id': '@PhilippHagemeister',
14a14335 1370 'heatmap': 'count:100',
34a7de29
S
1371 },
1372 'params': {
1373 'skip_download': True,
1374 },
11b56058 1375 },
dd27fd17 1376 {
2d3d2997 1377 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1378 'note': '256k DASH audio (format 141) via DASH manifest',
1379 'info_dict': {
1380 'id': 'a9LDPn-MO4I',
1381 'ext': 'm4a',
1382 'upload_date': '20121002',
4bc3a23e 1383 'description': '',
4bc3a23e 1384 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1385 },
4bc3a23e
PH
1386 'params': {
1387 'youtube_include_dash_manifest': True,
1388 'format': '141',
4919603f 1389 },
de3c7fe0 1390 'skip': 'format 141 not served anymore',
dd27fd17 1391 },
8bdd16b4 1392 # DASH manifest with encrypted signature
1393 {
1394 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1395 'info_dict': {
1396 'id': 'IB3lcPjvWLA',
1397 'ext': 'm4a',
1398 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1399 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1400 'duration': 244,
8bdd16b4 1401 'upload_date': '20131011',
cc2db878 1402 'abr': 129.495,
976ae3ea 1403 'like_count': int,
1404 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1405 'playable_in_embed': True,
1406 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1407 'view_count': int,
1408 'track': 'The Spark',
1409 'live_status': 'not_live',
1410 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1411 'channel': 'Afrojack',
976ae3ea 1412 'tags': 'count:19',
1413 'availability': 'public',
1414 'categories': ['Music'],
1415 'age_limit': 0,
1416 'alt_title': 'The Spark',
7666b936 1417 'channel_follower_count': int,
1418 'uploader': 'Afrojack',
1419 'uploader_url': 'https://www.youtube.com/@Afrojack',
1420 'uploader_id': '@Afrojack',
8bdd16b4 1421 },
1422 'params': {
1423 'youtube_include_dash_manifest': True,
1424 'format': '141/bestaudio[ext=m4a]',
1425 },
1426 },
65c2fde2 1427 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1428 {
65c2fde2 1429 'note': 'Embed allowed age-gate video',
2d3d2997 1430 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1431 'info_dict': {
1432 'id': 'HtVdAasjOgU',
1433 'ext': 'mp4',
1434 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1435 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1436 'duration': 142,
c522adb1 1437 'upload_date': '20140605',
34952f09 1438 'age_limit': 18,
976ae3ea 1439 'categories': ['Gaming'],
1440 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1441 'availability': 'needs_auth',
1442 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1443 'like_count': int,
1444 'channel': 'The Witcher',
1445 'live_status': 'not_live',
1446 'tags': 'count:17',
1447 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1448 'playable_in_embed': True,
1449 'view_count': int,
7666b936 1450 'channel_follower_count': int,
1451 'uploader': 'The Witcher',
1452 'uploader_url': 'https://www.youtube.com/@thewitcher',
1453 'uploader_id': '@thewitcher',
14a14335 1454 'comment_count': int,
8213ce28 1455 'channel_is_verified': True,
14a14335 1456 'heatmap': 'count:100',
c522adb1
JMF
1457 },
1458 },
65c2fde2 1459 {
1460 'note': 'Age-gate video with embed allowed in public site',
1461 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1462 'info_dict': {
1463 'id': 'HsUATh_Nc2U',
1464 'ext': 'mp4',
1465 'title': 'Godzilla 2 (Official Video)',
1466 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1467 'upload_date': '20200408',
65c2fde2 1468 'age_limit': 18,
976ae3ea 1469 'availability': 'needs_auth',
1470 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
976ae3ea 1471 'channel': 'FlyingKitty',
1472 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1473 'view_count': int,
1474 'categories': ['Entertainment'],
1475 'live_status': 'not_live',
1476 'tags': ['Flyingkitty', 'godzilla 2'],
1477 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1478 'like_count': int,
1479 'duration': 177,
1480 'playable_in_embed': True,
7666b936 1481 'channel_follower_count': int,
1482 'uploader': 'FlyingKitty',
1483 'uploader_url': 'https://www.youtube.com/@FlyingKitty900',
1484 'uploader_id': '@FlyingKitty900',
5caf30db 1485 'comment_count': int,
8213ce28 1486 'channel_is_verified': True,
65c2fde2 1487 },
1488 },
1489 {
1490 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1491 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1492 'info_dict': {
1493 'id': 'Tq92D6wQ1mg',
1494 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1495 'ext': 'mp4',
17322130 1496 'upload_date': '20191228',
65c2fde2 1497 'description': 'md5:17eccca93a786d51bc67646756894066',
1498 'age_limit': 18,
976ae3ea 1499 'like_count': int,
1500 'availability': 'needs_auth',
976ae3ea 1501 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1502 'view_count': int,
1503 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1504 'channel': 'Projekt Melody',
1505 'live_status': 'not_live',
1506 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1507 'playable_in_embed': True,
1508 'categories': ['Entertainment'],
1509 'duration': 106,
1510 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1511 'comment_count': int,
7666b936 1512 'channel_follower_count': int,
1513 'uploader': 'Projekt Melody',
1514 'uploader_url': 'https://www.youtube.com/@ProjektMelody',
1515 'uploader_id': '@ProjektMelody',
65c2fde2 1516 },
1517 },
1518 {
1519 'note': 'Non-Agegated non-embeddable video',
1520 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1521 'info_dict': {
1522 'id': 'MeJVWBSsPAY',
1523 'ext': 'mp4',
1524 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
65c2fde2 1525 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1526 'upload_date': '20130730',
976ae3ea 1527 'track': 'Such mich find mich',
1528 'age_limit': 0,
1529 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1530 'like_count': int,
1531 'playable_in_embed': False,
1532 'creator': 'OOMPH!',
1533 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1534 'view_count': int,
1535 'alt_title': 'Such mich find mich',
1536 'duration': 210,
1537 'channel': 'Herr Lurik',
1538 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1539 'categories': ['Music'],
1540 'availability': 'public',
976ae3ea 1541 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1542 'live_status': 'not_live',
1543 'artist': 'OOMPH!',
7666b936 1544 'channel_follower_count': int,
1545 'uploader': 'Herr Lurik',
1546 'uploader_url': 'https://www.youtube.com/@HerrLurik',
1547 'uploader_id': '@HerrLurik',
65c2fde2 1548 },
1549 },
1550 {
1551 'note': 'Non-bypassable age-gated video',
1552 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1553 'only_matching': True,
1554 },
8bdd16b4 1555 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1556 # YouTube Red ad is not captured for creator
1557 {
1558 'url': '__2ABJjxzNo',
1559 'info_dict': {
1560 'id': '__2ABJjxzNo',
1561 'ext': 'mp4',
1562 'duration': 266,
1563 'upload_date': '20100430',
545cc85d 1564 'creator': 'deadmau5',
1565 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1566 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1567 'alt_title': 'Some Chords',
976ae3ea 1568 'availability': 'public',
1569 'tags': 'count:14',
1570 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1571 'view_count': int,
1572 'live_status': 'not_live',
1573 'channel': 'deadmau5',
1574 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1575 'like_count': int,
1576 'track': 'Some Chords',
1577 'artist': 'deadmau5',
1578 'playable_in_embed': True,
1579 'age_limit': 0,
1580 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1581 'categories': ['Music'],
1582 'album': 'Some Chords',
7666b936 1583 'channel_follower_count': int,
1584 'uploader': 'deadmau5',
1585 'uploader_url': 'https://www.youtube.com/@deadmau5',
1586 'uploader_id': '@deadmau5',
8bdd16b4 1587 },
1588 'expected_warnings': [
1589 'DASH manifest missing',
1590 ]
1591 },
067aa17e 1592 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1593 {
1594 'url': 'lqQg6PlCWgI',
1595 'info_dict': {
1596 'id': 'lqQg6PlCWgI',
1597 'ext': 'mp4',
556dbe7f 1598 'duration': 6085,
90227264 1599 'upload_date': '20150827',
12a1b225 1600 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
cbe2bd91 1601 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1602 'like_count': int,
1603 'release_timestamp': 1343767800,
1604 'playable_in_embed': True,
1605 'categories': ['Sports'],
1606 'release_date': '20120731',
1607 'channel': 'Olympics',
1608 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1609 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1610 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1611 'age_limit': 0,
1612 'availability': 'public',
1613 'live_status': 'was_live',
1614 'view_count': int,
1615 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
7666b936 1616 'channel_follower_count': int,
1617 'uploader': 'Olympics',
1618 'uploader_url': 'https://www.youtube.com/@Olympics',
1619 'uploader_id': '@Olympics',
8213ce28 1620 'channel_is_verified': True,
cbe2bd91
PH
1621 },
1622 'params': {
1623 'skip_download': 'requires avconv',
e52a40ab 1624 }
cbe2bd91 1625 },
6271f1ca
PH
1626 # Non-square pixels
1627 {
1628 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1629 'info_dict': {
1630 'id': '_b-2C3KPAM0',
1631 'ext': 'mp4',
1632 'stretched_ratio': 16 / 9.,
556dbe7f 1633 'duration': 85,
6271f1ca 1634 'upload_date': '20110310',
6271f1ca 1635 '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',
6271f1ca 1636 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1637 'playable_in_embed': True,
1638 'channel': '孫ᄋᄅ',
1639 'age_limit': 0,
1640 'tags': 'count:11',
1641 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1642 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1643 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1644 'view_count': int,
1645 'categories': ['People & Blogs'],
1646 'like_count': int,
1647 'live_status': 'not_live',
1648 'availability': 'unlisted',
12a1b225 1649 'comment_count': int,
7666b936 1650 'channel_follower_count': int,
1651 'uploader': '孫ᄋᄅ',
1652 'uploader_url': 'https://www.youtube.com/@AllenMeow',
1653 'uploader_id': '@AllenMeow',
6271f1ca 1654 },
06b491eb
S
1655 },
1656 # url_encoded_fmt_stream_map is empty string
1657 {
1658 'url': 'qEJwOuvDf7I',
1659 'info_dict': {
1660 'id': 'qEJwOuvDf7I',
f57b7835 1661 'ext': 'webm',
06b491eb
S
1662 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1663 'description': '',
1664 'upload_date': '20150404',
06b491eb
S
1665 },
1666 'params': {
1667 'skip_download': 'requires avconv',
e323cf3f
S
1668 },
1669 'skip': 'This live event has ended.',
06b491eb 1670 },
067aa17e 1671 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1672 {
1673 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1674 'info_dict': {
1675 'id': 'FIl7x6_3R5Y',
eb6793ba 1676 'ext': 'webm',
da77d856
S
1677 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1678 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1679 'duration': 220,
da77d856 1680 'upload_date': '20150625',
eb6793ba 1681 'formats': 'mincount:31',
da77d856 1682 },
eb6793ba 1683 'skip': 'not actual anymore',
2ee8f5d8 1684 },
8a1a26ce
YCH
1685 # DASH manifest with segment_list
1686 {
1687 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1688 'md5': '8ce563a1d667b599d21064e982ab9e31',
1689 'info_dict': {
1690 'id': 'CsmdDsKjzN8',
1691 'ext': 'mp4',
17ee98e1 1692 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce 1693 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
8a1a26ce
YCH
1694 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1695 },
1696 'params': {
1697 'youtube_include_dash_manifest': True,
1698 'format': '135', # bestvideo
be49068d
S
1699 },
1700 'skip': 'This live event has ended.',
2ee8f5d8 1701 },
cf7e015f 1702 {
6368e2e6 1703 # Multifeed videos (multiple cameras), URL can be of any Camera
7666b936 1704 # TODO: fix multifeed titles
6368e2e6 1705 'url': 'https://www.youtube.com/watch?v=zaPI8MvL8pg',
cf7e015f 1706 'info_dict': {
6368e2e6 1707 'id': 'zaPI8MvL8pg',
1708 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04',
1709 'description': 'md5:563ccbc698b39298481ca3c571169519',
cf7e015f
S
1710 },
1711 'playlist': [{
1712 'info_dict': {
6368e2e6 1713 'id': 'j5yGuxZ8lLU',
cf7e015f 1714 'ext': 'mp4',
6368e2e6 1715 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Chris)',
6368e2e6 1716 'description': 'md5:563ccbc698b39298481ca3c571169519',
6368e2e6 1717 'duration': 10120,
1718 'channel_follower_count': int,
1719 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1720 'availability': 'public',
1721 'playable_in_embed': True,
1722 'upload_date': '20131105',
6368e2e6 1723 'categories': ['Gaming'],
1724 'live_status': 'was_live',
1725 'tags': 'count:24',
1726 'release_timestamp': 1383701910,
1727 'thumbnail': 'https://i.ytimg.com/vi/j5yGuxZ8lLU/maxresdefault.jpg',
1728 'comment_count': int,
1729 'age_limit': 0,
1730 'like_count': int,
1731 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1732 'channel': 'WiiLikeToPlay',
1733 'view_count': int,
1734 'release_date': '20131106',
7666b936 1735 'uploader': 'WiiLikeToPlay',
1736 'uploader_id': '@WLTP',
1737 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1738 },
1739 }, {
1740 'info_dict': {
6368e2e6 1741 'id': 'zaPI8MvL8pg',
cf7e015f 1742 'ext': 'mp4',
6368e2e6 1743 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Tyson)',
6368e2e6 1744 'availability': 'public',
1745 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1746 'channel': 'WiiLikeToPlay',
6368e2e6 1747 'channel_follower_count': int,
1748 'description': 'md5:563ccbc698b39298481ca3c571169519',
1749 'duration': 10108,
1750 'age_limit': 0,
1751 'like_count': int,
1752 'tags': 'count:24',
1753 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
6368e2e6 1754 'release_timestamp': 1383701915,
1755 'comment_count': int,
1756 'upload_date': '20131105',
1757 'thumbnail': 'https://i.ytimg.com/vi/zaPI8MvL8pg/maxresdefault.jpg',
1758 'release_date': '20131106',
1759 'playable_in_embed': True,
1760 'live_status': 'was_live',
1761 'categories': ['Gaming'],
1762 'view_count': int,
7666b936 1763 'uploader': 'WiiLikeToPlay',
1764 'uploader_id': '@WLTP',
1765 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1766 },
1767 }, {
1768 'info_dict': {
6368e2e6 1769 'id': 'R7r3vfO7Hao',
cf7e015f 1770 'ext': 'mp4',
6368e2e6 1771 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Spencer)',
1772 'thumbnail': 'https://i.ytimg.com/vi/R7r3vfO7Hao/maxresdefault.jpg',
1773 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1774 'like_count': int,
1775 'availability': 'public',
1776 'playable_in_embed': True,
1777 'upload_date': '20131105',
1778 'description': 'md5:563ccbc698b39298481ca3c571169519',
6368e2e6 1779 'channel_follower_count': int,
1780 'tags': 'count:24',
1781 'release_date': '20131106',
6368e2e6 1782 'comment_count': int,
1783 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1784 'channel': 'WiiLikeToPlay',
1785 'categories': ['Gaming'],
1786 'release_timestamp': 1383701914,
1787 'live_status': 'was_live',
1788 'age_limit': 0,
1789 'duration': 10128,
1790 'view_count': int,
7666b936 1791 'uploader': 'WiiLikeToPlay',
1792 'uploader_id': '@WLTP',
1793 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1794 },
1795 }],
6368e2e6 1796 'params': {'skip_download': True},
cbaed4bb 1797 },
f9f49d87 1798 {
067aa17e 1799 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1800 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1801 'info_dict': {
1802 'id': 'gVfLd0zydlo',
1803 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1804 },
1805 'playlist_count': 2,
be49068d 1806 'skip': 'Not multifeed anymore',
f9f49d87 1807 },
cbaed4bb 1808 {
2d3d2997 1809 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1810 'only_matching': True,
0e49d9a6 1811 },
6d4fc66b 1812 {
2d3d2997 1813 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1814 'only_matching': True,
1815 },
0e49d9a6 1816 {
067aa17e 1817 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1818 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1819 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1820 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1821 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1822 'info_dict': {
1823 'id': 'lsguqyKfVQg',
1824 'ext': 'mp4',
1825 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1826 'alt_title': 'Dark Walk',
0e49d9a6 1827 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1828 'duration': 133,
0e49d9a6 1829 'upload_date': '20151119',
11f9be09 1830 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1831 'track': 'Dark Walk',
1832 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1833 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1834 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1835 'categories': ['Film & Animation'],
1836 'view_count': int,
1837 'live_status': 'not_live',
1838 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1839 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1840 'tags': 'count:13',
1841 'availability': 'public',
1842 'channel': 'IronSoulElf',
1843 'playable_in_embed': True,
1844 'like_count': int,
1845 'age_limit': 0,
6c73052c 1846 'channel_follower_count': int
0e49d9a6
LL
1847 },
1848 'params': {
1849 'skip_download': True,
1850 },
1851 },
61f92af1 1852 {
067aa17e 1853 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1854 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1855 'only_matching': True,
1856 },
313dfc45
LL
1857 {
1858 # Video with yt:stretch=17:0
1859 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1860 'info_dict': {
1861 'id': 'Q39EVAstoRM',
1862 'ext': 'mp4',
1863 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1864 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1865 'upload_date': '20151107',
313dfc45
LL
1866 },
1867 'params': {
1868 'skip_download': True,
1869 },
be49068d 1870 'skip': 'This video does not exist.',
313dfc45 1871 },
201c1459 1872 {
1873 # Video with incomplete 'yt:stretch=16:'
1874 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1875 'only_matching': True,
1876 },
7caf9830
S
1877 {
1878 # Video licensed under Creative Commons
1879 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1880 'info_dict': {
1881 'id': 'M4gD1WSo5mA',
1882 'ext': 'mp4',
1883 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1884 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1885 'duration': 721,
17322130 1886 'upload_date': '20150128',
7caf9830 1887 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1888 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1889 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1890 'like_count': int,
1891 'age_limit': 0,
1892 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1893 'channel': 'The Berkman Klein Center for Internet & Society',
1894 'availability': 'public',
1895 'view_count': int,
1896 'categories': ['Education'],
1897 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1898 'live_status': 'not_live',
1899 'playable_in_embed': True,
d5d1df8a 1900 'channel_follower_count': int,
1901 'chapters': list,
7666b936 1902 'uploader': 'The Berkman Klein Center for Internet & Society',
1903 'uploader_id': '@BKCHarvard',
1904 'uploader_url': 'https://www.youtube.com/@BKCHarvard',
7caf9830
S
1905 },
1906 'params': {
1907 'skip_download': True,
1908 },
1909 },
fd050249 1910 {
fd050249
S
1911 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1912 'info_dict': {
1913 'id': 'eQcmzGIKrzg',
1914 'ext': 'mp4',
1915 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1916 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1917 'duration': 4060,
17322130 1918 'upload_date': '20151120',
fd050249 1919 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1920 'playable_in_embed': True,
1921 'tags': 'count:12',
1922 'like_count': int,
1923 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1924 'age_limit': 0,
1925 'availability': 'public',
1926 'categories': ['News & Politics'],
1927 'channel': 'Bernie Sanders',
1928 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1929 'view_count': int,
1930 'live_status': 'not_live',
1931 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1932 'comment_count': int,
d5d1df8a 1933 'channel_follower_count': int,
1934 'chapters': list,
7666b936 1935 'uploader': 'Bernie Sanders',
1936 'uploader_url': 'https://www.youtube.com/@BernieSanders',
1937 'uploader_id': '@BernieSanders',
8213ce28 1938 'channel_is_verified': True,
14a14335 1939 'heatmap': 'count:100',
fd050249
S
1940 },
1941 'params': {
1942 'skip_download': True,
1943 },
1944 },
040ac686
S
1945 {
1946 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1947 'only_matching': True,
7f29cf54
S
1948 },
1949 {
067aa17e 1950 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1951 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1952 'only_matching': True,
6496ccb4
S
1953 },
1954 {
1955 # Rental video preview
1956 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1957 'info_dict': {
1958 'id': 'uGpuVWrhIzE',
1959 'ext': 'mp4',
1960 'title': 'Piku - Trailer',
1961 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1962 'upload_date': '20150811',
6496ccb4
S
1963 'license': 'Standard YouTube License',
1964 },
1965 'params': {
1966 'skip_download': True,
1967 },
eb6793ba 1968 'skip': 'This video is not available.',
022a5d66 1969 },
12afdc2a
S
1970 {
1971 # YouTube Red video with episode data
1972 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1973 'info_dict': {
1974 'id': 'iqKdEhx-dD4',
1975 'ext': 'mp4',
1976 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1977 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1978 'duration': 2085,
12afdc2a 1979 'upload_date': '20170118',
12afdc2a
S
1980 'series': 'Mind Field',
1981 'season_number': 1,
1982 'episode_number': 1,
976ae3ea 1983 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1984 'tags': 'count:12',
1985 'view_count': int,
1986 'availability': 'public',
1987 'age_limit': 0,
1988 'channel': 'Vsauce',
1989 'episode': 'Episode 1',
1990 'categories': ['Entertainment'],
1991 'season': 'Season 1',
1992 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1993 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1994 'like_count': int,
1995 'playable_in_embed': True,
1996 'live_status': 'not_live',
7666b936 1997 'channel_follower_count': int,
1998 'uploader': 'Vsauce',
1999 'uploader_url': 'https://www.youtube.com/@Vsauce',
2000 'uploader_id': '@Vsauce',
14a14335 2001 'comment_count': int,
8213ce28 2002 'channel_is_verified': True,
12afdc2a
S
2003 },
2004 'params': {
2005 'skip_download': True,
2006 },
2007 'expected_warnings': [
2008 'Skipping DASH manifest',
2009 ],
2010 },
c7121fa7
S
2011 {
2012 # The following content has been identified by the YouTube community
2013 # as inappropriate or offensive to some audiences.
2014 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
2015 'info_dict': {
2016 'id': '6SJNVb0GnPI',
2017 'ext': 'mp4',
2018 'title': 'Race Differences in Intelligence',
2019 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
2020 'duration': 965,
2021 'upload_date': '20140124',
c7121fa7
S
2022 },
2023 'params': {
2024 'skip_download': True,
2025 },
545cc85d 2026 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 2027 },
022a5d66
S
2028 {
2029 # itag 212
2030 'url': '1t24XAntNCY',
2031 'only_matching': True,
fd5c4aab
S
2032 },
2033 {
2034 # geo restricted to JP
2035 'url': 'sJL6WA-aGkQ',
2036 'only_matching': True,
2037 },
cd5a74a2
S
2038 {
2039 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
2040 'only_matching': True,
2041 },
bc2ca1bb 2042 {
2043 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
2044 'only_matching': True,
2045 },
2046 {
2047 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
2048 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
2049 'only_matching': True,
2050 },
825cd268
RA
2051 {
2052 # DRM protected
2053 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
2054 'only_matching': True,
4fe54c12
S
2055 },
2056 {
2057 # Video with unsupported adaptive stream type formats
2058 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
2059 'info_dict': {
2060 'id': 'Z4Vy8R84T1U',
2061 'ext': 'mp4',
2062 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
2063 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2064 'duration': 433,
2065 'upload_date': '20130923',
4fe54c12
S
2066 'formats': 'maxcount:10',
2067 },
2068 'params': {
2069 'skip_download': True,
2070 'youtube_include_dash_manifest': False,
2071 },
5429d6a9 2072 'skip': 'not actual anymore',
5caabd3c 2073 },
2074 {
822b9d9c 2075 # Youtube Music Auto-generated description
7666b936 2076 # TODO: fix metadata extraction
5caabd3c 2077 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2078 'info_dict': {
2079 'id': 'MgNrAu2pzNs',
2080 'ext': 'mp4',
2081 'title': 'Voyeur Girl',
2082 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
2083 'upload_date': '20190312',
104a7b5a
L
2084 'artists': ['Stephen'],
2085 'creators': ['Stephen'],
5caabd3c 2086 'track': 'Voyeur Girl',
2087 'album': 'it\'s too much love to know my dear',
2088 'release_date': '20190313',
976ae3ea 2089 'alt_title': 'Voyeur Girl',
2090 'view_count': int,
976ae3ea 2091 'playable_in_embed': True,
2092 'like_count': int,
2093 'categories': ['Music'],
2094 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
7666b936 2095 'channel': 'Stephen', # TODO: should be "Stephen - Topic"
2096 'uploader': 'Stephen',
976ae3ea 2097 'availability': 'public',
976ae3ea 2098 'duration': 169,
2099 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
2100 'age_limit': 0,
2101 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2102 'tags': 'count:11',
2103 'live_status': 'not_live',
6c73052c 2104 'channel_follower_count': int
5caabd3c 2105 },
2106 'params': {
2107 'skip_download': True,
2108 },
2109 },
66b48727
RA
2110 {
2111 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
2112 'only_matching': True,
2113 },
011e75e6
S
2114 {
2115 # invalid -> valid video id redirection
2116 'url': 'DJztXj2GPfl',
2117 'info_dict': {
2118 'id': 'DJztXj2GPfk',
2119 'ext': 'mp4',
2120 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
2121 'description': 'md5:bf577a41da97918e94fa9798d9228825',
2122 'upload_date': '20090125',
011e75e6
S
2123 'artist': 'Panjabi MC',
2124 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
2125 'album': 'Beware of the Boys (Mundian To Bach Ke)',
2126 },
2127 'params': {
2128 'skip_download': True,
2129 },
545cc85d 2130 'skip': 'Video unavailable',
ea74e00b
DP
2131 },
2132 {
2133 # empty description results in an empty string
2134 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
2135 'info_dict': {
2136 'id': 'x41yOUIvK2k',
2137 'ext': 'mp4',
2138 'title': 'IMG 3456',
2139 'description': '',
2140 'upload_date': '20170613',
976ae3ea 2141 'view_count': int,
2142 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
976ae3ea 2143 'like_count': int,
2144 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
2145 'tags': [],
2146 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
2147 'availability': 'public',
2148 'age_limit': 0,
2149 'categories': ['Pets & Animals'],
2150 'duration': 7,
2151 'playable_in_embed': True,
2152 'live_status': 'not_live',
7666b936 2153 'channel': 'l\'Or Vert asbl',
2154 'channel_follower_count': int,
2155 'uploader': 'l\'Or Vert asbl',
2156 'uploader_url': 'https://www.youtube.com/@ElevageOrVert',
2157 'uploader_id': '@ElevageOrVert',
ea74e00b
DP
2158 },
2159 'params': {
2160 'skip_download': True,
2161 },
2162 },
a0566bbf 2163 {
29f7c58a 2164 # with '};' inside yt initial data (see [1])
2165 # see [2] for an example with '};' inside ytInitialPlayerResponse
2166 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2167 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 2168 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2169 'info_dict': {
2170 'id': 'CHqg6qOn4no',
2171 'ext': 'mp4',
2172 'title': 'Part 77 Sort a list of simple types in c#',
2173 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2174 'upload_date': '20130831',
976ae3ea 2175 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2176 'like_count': int,
976ae3ea 2177 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2178 'live_status': 'not_live',
2179 'categories': ['Education'],
2180 'availability': 'public',
2181 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2182 'tags': 'count:12',
2183 'playable_in_embed': True,
2184 'age_limit': 0,
2185 'view_count': int,
2186 'duration': 522,
2187 'channel': 'kudvenkat',
12a1b225 2188 'comment_count': int,
d5d1df8a 2189 'channel_follower_count': int,
2190 'chapters': list,
7666b936 2191 'uploader': 'kudvenkat',
2192 'uploader_url': 'https://www.youtube.com/@Csharp-video-tutorialsBlogspot',
2193 'uploader_id': '@Csharp-video-tutorialsBlogspot',
8213ce28 2194 'channel_is_verified': True,
14a14335 2195 'heatmap': 'count:100',
a0566bbf 2196 },
2197 'params': {
2198 'skip_download': True,
2199 },
2200 },
29f7c58a 2201 {
2202 # another example of '};' in ytInitialData
2203 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2204 'only_matching': True,
2205 },
2206 {
2207 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2208 'only_matching': True,
2209 },
545cc85d 2210 {
cc2db878 2211 # https://github.com/ytdl-org/youtube-dl/pull/28094
2212 'url': 'OtqTfy26tG0',
2213 'info_dict': {
2214 'id': 'OtqTfy26tG0',
2215 'ext': 'mp4',
2216 'title': 'Burn Out',
2217 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2218 'upload_date': '20141120',
cc2db878 2219 'artist': 'The Cinematic Orchestra',
2220 'track': 'Burn Out',
2221 'album': 'Every Day',
976ae3ea 2222 'like_count': int,
2223 'live_status': 'not_live',
2224 'alt_title': 'Burn Out',
2225 'duration': 614,
2226 'age_limit': 0,
2227 'view_count': int,
2228 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2229 'creator': 'The Cinematic Orchestra',
2230 'channel': 'The Cinematic Orchestra',
2231 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2232 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2233 'availability': 'public',
2234 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2235 'categories': ['Music'],
2236 'playable_in_embed': True,
7666b936 2237 'channel_follower_count': int,
2238 'uploader': 'The Cinematic Orchestra',
2239 'comment_count': int,
cc2db878 2240 },
2241 'params': {
2242 'skip_download': True,
2243 },
545cc85d 2244 },
bc2ca1bb 2245 {
2246 # controversial video, only works with bpctr when authenticated with cookies
2247 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2248 'only_matching': True,
2249 },
a1a7907b 2250 {
2251 # controversial video, requires bpctr/contentCheckOk
2252 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2253 'info_dict': {
2254 'id': 'SZJvDhaSDnc',
2255 'ext': 'mp4',
2256 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2257 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
a1a7907b 2258 'upload_date': '20140716',
976ae3ea 2259 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2260 'duration': 170,
2261 'categories': ['News & Politics'],
976ae3ea 2262 'view_count': int,
2263 'channel': 'CBS Mornings',
2264 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2265 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2266 'age_limit': 18,
2267 'availability': 'needs_auth',
2268 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2269 'like_count': int,
2270 'live_status': 'not_live',
2271 'playable_in_embed': True,
7666b936 2272 'channel_follower_count': int,
2273 'uploader': 'CBS Mornings',
2274 'uploader_url': 'https://www.youtube.com/@CBSMornings',
2275 'uploader_id': '@CBSMornings',
14a14335 2276 'comment_count': int,
8213ce28 2277 'channel_is_verified': True,
a1a7907b 2278 }
2279 },
f7ad7160 2280 {
2281 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2282 'url': 'cBvYw8_A0vQ',
2283 'info_dict': {
2284 'id': 'cBvYw8_A0vQ',
2285 'ext': 'mp4',
2286 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2287 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2288 'upload_date': '20201120',
976ae3ea 2289 'duration': 1456,
2290 'categories': ['Travel & Events'],
2291 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2292 'view_count': int,
2293 'channel': 'Walk around Japan',
2294 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2295 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2296 'age_limit': 0,
2297 'availability': 'public',
2298 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2299 'live_status': 'not_live',
2300 'playable_in_embed': True,
7666b936 2301 'channel_follower_count': int,
2302 'uploader': 'Walk around Japan',
2303 'uploader_url': 'https://www.youtube.com/@walkaroundjapan7124',
2304 'uploader_id': '@walkaroundjapan7124',
f7ad7160 2305 },
2306 'params': {
2307 'skip_download': True,
2308 },
0fb983f6 2309 }, {
2310 # Has multiple audio streams
2311 'url': 'WaOKSUlf4TM',
2312 'only_matching': True
9297939e 2313 }, {
2314 # Requires Premium: has format 141 when requested using YTM url
2315 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2316 'only_matching': True
2317 }, {
120916da 2318 # multiple subtitles with same lang_code
2319 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2320 'only_matching': True,
109dd3b2 2321 }, {
2322 # Force use android client fallback
2323 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2324 'info_dict': {
2325 'id': 'YOelRv7fMxY',
11f9be09 2326 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2327 'ext': '3gp',
2328 'upload_date': '20210624',
2329 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
109dd3b2 2330 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2331 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2332 'duration': 596,
2333 'categories': ['Entertainment'],
976ae3ea 2334 'view_count': int,
2335 'channel': 'colinfurze',
2336 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2337 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2338 'age_limit': 0,
2339 'availability': 'public',
2340 'like_count': int,
2341 'live_status': 'not_live',
2342 'playable_in_embed': True,
d5d1df8a 2343 'channel_follower_count': int,
2344 'chapters': list,
7666b936 2345 'uploader': 'colinfurze',
2346 'uploader_url': 'https://www.youtube.com/@colinfurze',
2347 'uploader_id': '@colinfurze',
14a14335 2348 'comment_count': int,
8213ce28 2349 'channel_is_verified': True,
14a14335 2350 'heatmap': 'count:100',
109dd3b2 2351 },
2352 'params': {
2353 'format': '17', # 3gp format available on android
2354 'extractor_args': {'youtube': {'player_client': ['android']}},
2355 },
120916da 2356 },
109dd3b2 2357 {
2358 # Skip download of additional client configs (remix client config in this case)
2359 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2360 'only_matching': True,
2361 'params': {
2362 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2363 },
8fc54b12 2364 }, {
2365 # shorts
2366 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2367 'only_matching': True,
9222c381 2368 }, {
2369 'note': 'Storyboards',
2370 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2371 'info_dict': {
2372 'id': '5KLPxDtMqe8',
2373 'ext': 'mhtml',
2374 'format_id': 'sb0',
2375 'title': 'Your Brain is Plastic',
9222c381 2376 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2377 'upload_date': '20140324',
976ae3ea 2378 'like_count': int,
2379 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2380 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2381 'view_count': int,
2382 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2383 'playable_in_embed': True,
2384 'tags': 'count:12',
976ae3ea 2385 'availability': 'public',
2386 'channel': 'SciShow',
2387 'live_status': 'not_live',
2388 'duration': 248,
2389 'categories': ['Education'],
2390 'age_limit': 0,
d5d1df8a 2391 'channel_follower_count': int,
2392 'chapters': list,
7666b936 2393 'uploader': 'SciShow',
2394 'uploader_url': 'https://www.youtube.com/@SciShow',
2395 'uploader_id': '@SciShow',
14a14335 2396 'comment_count': int,
8213ce28 2397 'channel_is_verified': True,
14a14335 2398 'heatmap': 'count:100',
9222c381 2399 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2400 }, {
2401 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2402 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2403 'info_dict': {
2404 'id': '2NUZ8W2llS4',
2405 'ext': 'mp4',
2406 'title': 'The NP that test your phone performance 🙂',
2407 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
992f9a73 2408 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2409 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2410 'duration': 21,
2411 'view_count': int,
2412 'age_limit': 0,
2413 'categories': ['Gaming'],
2414 'tags': 'count:23',
2415 'playable_in_embed': True,
2416 'live_status': 'not_live',
2417 'upload_date': '20220103',
2418 'like_count': int,
2419 'availability': 'public',
2420 'channel': 'Leon Nguyen',
2421 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2422 'comment_count': int,
7666b936 2423 'channel_follower_count': int,
2424 'uploader': 'Leon Nguyen',
2425 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
2426 'uploader_id': '@LeonNguyen',
14a14335 2427 'heatmap': 'count:100',
992f9a73 2428 }
1ff88b7a 2429 }, {
2430 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2431 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2432 'info_dict': {
2433 'id': '2NUZ8W2llS4',
2434 'ext': 'mp4',
2435 'title': 'The NP that test your phone performance 🙂',
2436 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
1ff88b7a 2437 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2438 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2439 'duration': 21,
2440 'view_count': int,
2441 'age_limit': 0,
2442 'categories': ['Gaming'],
2443 'tags': 'count:23',
2444 'playable_in_embed': True,
2445 'live_status': 'not_live',
2446 'upload_date': '20220102',
2447 'like_count': int,
2448 'availability': 'public',
2449 'channel': 'Leon Nguyen',
2450 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2451 'comment_count': int,
7666b936 2452 'channel_follower_count': int,
2453 'uploader': 'Leon Nguyen',
2454 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
2455 'uploader_id': '@LeonNguyen',
14a14335 2456 'heatmap': 'count:100',
1ff88b7a 2457 },
2458 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
992f9a73 2459 }, {
2460 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2461 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2462 'info_dict': {
2463 'id': 'mzZzzBU6lrM',
2464 'ext': 'mp4',
2465 'title': 'I Met GeorgeNotFound In Real Life...',
7666b936 2466 'description': 'md5:978296ec9783a031738b684d4ebf302d',
992f9a73 2467 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2468 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2469 'duration': 955,
2470 'view_count': int,
2471 'age_limit': 0,
2472 'categories': ['Entertainment'],
2473 'tags': 'count:26',
2474 'playable_in_embed': True,
2475 'live_status': 'not_live',
2476 'release_timestamp': 1641172509,
2477 'release_date': '20220103',
2478 'upload_date': '20220103',
2479 'like_count': int,
2480 'availability': 'public',
2481 'channel': 'Quackity',
2482 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
7666b936 2483 'channel_follower_count': int,
2484 'uploader': 'Quackity',
2485 'uploader_id': '@Quackity',
2486 'uploader_url': 'https://www.youtube.com/@Quackity',
14a14335 2487 'comment_count': int,
8213ce28 2488 'channel_is_verified': True,
14a14335 2489 'heatmap': 'count:100',
992f9a73 2490 }
2491 },
2492 { # continuous livestream. Microformat upload date should be preferred.
2493 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2494 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2495 'info_dict': {
2496 'id': 'kgx4WGK0oNU',
2497 '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}',
2498 'ext': 'mp4',
2499 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2500 'availability': 'public',
2501 'age_limit': 0,
2502 'release_timestamp': 1637975704,
2503 'upload_date': '20210619',
2504 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2505 'live_status': 'is_live',
2506 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
992f9a73 2507 'channel': 'Abao in Tokyo',
2508 'channel_follower_count': int,
2509 'release_date': '20211127',
2510 'tags': 'count:39',
2511 'categories': ['People & Blogs'],
2512 'like_count': int,
992f9a73 2513 'view_count': int,
2514 'playable_in_embed': True,
2515 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
867c66ff 2516 'concurrent_view_count': int,
7666b936 2517 'uploader': 'Abao in Tokyo',
2518 'uploader_url': 'https://www.youtube.com/@abaointokyo',
2519 'uploader_id': '@abaointokyo',
992f9a73 2520 },
2521 'params': {'skip_download': True}
ee27297f 2522 }, {
2523 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2524 'info_dict': {
2525 'id': 'tjjjtzRLHvA',
2526 'ext': 'mp4',
2527 'title': 'ハッシュタグ無し };if window.ytcsi',
2528 'upload_date': '20220323',
2529 'like_count': int,
2530 'availability': 'unlisted',
7666b936 2531 'channel': 'Lesmiscore',
2532 'thumbnail': r're:^https?://.*\.jpg',
ee27297f 2533 'age_limit': 0,
ee27297f 2534 'categories': ['Music'],
6e634cbe 2535 'view_count': int,
2536 'description': '',
ee27297f 2537 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2538 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2539 'live_status': 'not_live',
2540 'playable_in_embed': True,
2541 'channel_follower_count': int,
2542 'duration': 6,
2543 'tags': [],
7666b936 2544 'uploader_id': '@lesmiscore',
2545 'uploader': 'Lesmiscore',
2546 'uploader_url': 'https://www.youtube.com/@lesmiscore',
6e634cbe 2547 }
c26f9b99 2548 }, {
2549 # Prefer primary title+description language metadata by default
2550 # Do not prefer translated description if primary is empty
2551 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2552 'info_dict': {
2553 'id': 'el3E4MbxRqQ',
2554 'ext': 'mp4',
2555 'title': 'dlp test video 2 - primary sv no desc',
2556 'description': '',
2557 'channel': 'cole-dlp-test-acc',
2558 'tags': [],
2559 'view_count': int,
2560 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2561 'like_count': int,
2562 'playable_in_embed': True,
2563 'availability': 'unlisted',
7666b936 2564 'thumbnail': r're:^https?://.*\.jpg',
c26f9b99 2565 'age_limit': 0,
2566 'duration': 5,
c26f9b99 2567 'live_status': 'not_live',
2568 'upload_date': '20220908',
2569 'categories': ['People & Blogs'],
c26f9b99 2570 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
7666b936 2571 'uploader_url': 'https://www.youtube.com/@coletdjnz',
2572 'uploader_id': '@coletdjnz',
2573 'uploader': 'cole-dlp-test-acc',
c26f9b99 2574 },
2575 'params': {'skip_download': True}
2576 }, {
2577 # Extractor argument: prefer translated title+description
2578 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2579 'info_dict': {
2580 'id': 'gHKT4uU8Zng',
2581 'ext': 'mp4',
2582 'channel': 'cole-dlp-test-acc',
2583 'tags': [],
2584 'duration': 5,
2585 'live_status': 'not_live',
2586 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2587 'upload_date': '20220728',
c26f9b99 2588 'view_count': int,
2589 'categories': ['People & Blogs'],
7666b936 2590 'thumbnail': r're:^https?://.*\.jpg',
c26f9b99 2591 'title': 'dlp test video title translated (fr)',
2592 'availability': 'public',
c26f9b99 2593 'age_limit': 0,
2594 'description': 'dlp test video description translated (fr)',
2595 'playable_in_embed': True,
2596 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
7666b936 2597 'uploader_url': 'https://www.youtube.com/@coletdjnz',
2598 'uploader_id': '@coletdjnz',
2599 'uploader': 'cole-dlp-test-acc',
c26f9b99 2600 },
2601 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2602 'expected_warnings': [r'Preferring "fr" translated fields'],
a4166234 2603 }, {
2604 'note': '6 channel audio',
2605 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2606 'only_matching': True,
a4894d3e 2607 }, {
2608 'note': 'Multiple HLS formats with same itag',
2609 'url': 'https://www.youtube.com/watch?v=kX3nB4PpJko',
2610 'info_dict': {
2611 'id': 'kX3nB4PpJko',
2612 'ext': 'mp4',
2613 'categories': ['Entertainment'],
2614 'description': 'md5:e8031ff6e426cdb6a77670c9b81f6fa6',
a4894d3e 2615 'live_status': 'not_live',
2616 'duration': 937,
2617 'channel_follower_count': int,
2618 'thumbnail': 'https://i.ytimg.com/vi_webp/kX3nB4PpJko/maxresdefault.webp',
2619 'title': 'Last To Take Hand Off Jet, Keeps It!',
2620 'channel': 'MrBeast',
2621 'playable_in_embed': True,
2622 'view_count': int,
2623 'upload_date': '20221112',
a4894d3e 2624 'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA',
2625 'age_limit': 0,
2626 'availability': 'public',
2627 'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA',
2628 'like_count': int,
2629 'tags': [],
7666b936 2630 'uploader': 'MrBeast',
2631 'uploader_url': 'https://www.youtube.com/@MrBeast',
2632 'uploader_id': '@MrBeast',
14a14335 2633 'comment_count': int,
8213ce28 2634 'channel_is_verified': True,
14a14335 2635 'heatmap': 'count:100',
a4894d3e 2636 },
2637 'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
9bb85699 2638 }, {
2639 'note': 'Audio formats with Dynamic Range Compression',
2640 'url': 'https://www.youtube.com/watch?v=Tq92D6wQ1mg',
2641 'info_dict': {
2642 'id': 'Tq92D6wQ1mg',
7666b936 2643 'ext': 'webm',
9bb85699 2644 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
2645 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2646 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2647 'channel_follower_count': int,
2648 'description': 'md5:17eccca93a786d51bc67646756894066',
2649 'upload_date': '20191228',
9bb85699 2650 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
2651 'playable_in_embed': True,
2652 'like_count': int,
2653 'categories': ['Entertainment'],
2654 'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
2655 'age_limit': 18,
2656 'channel': 'Projekt Melody',
9bb85699 2657 'view_count': int,
2658 'availability': 'needs_auth',
2659 'comment_count': int,
2660 'live_status': 'not_live',
9bb85699 2661 'duration': 106,
7666b936 2662 'uploader': 'Projekt Melody',
2663 'uploader_id': '@ProjektMelody',
2664 'uploader_url': 'https://www.youtube.com/@ProjektMelody',
9bb85699 2665 },
2666 'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
dad2210c 2667 },
2668 {
2669 'url': 'https://www.youtube.com/live/qVv6vCqciTM',
2670 'info_dict': {
2671 'id': 'qVv6vCqciTM',
2672 'ext': 'mp4',
2673 'age_limit': 0,
dad2210c 2674 'comment_count': int,
2675 'chapters': 'count:13',
2676 'upload_date': '20221223',
2677 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
2678 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
dad2210c 2679 'like_count': int,
2680 'release_date': '20221223',
2681 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
2682 'title': '【 #インターネット女クリスマス 】3Dで歌ってはしゃぐインターネットの女たち【月ノ美兎/名取さな】',
2683 'view_count': int,
2684 'playable_in_embed': True,
2685 'duration': 4438,
2686 'availability': 'public',
2687 'channel_follower_count': int,
2688 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2689 'categories': ['Entertainment'],
2690 'live_status': 'was_live',
2691 'release_timestamp': 1671793345,
2692 'channel': 'さなちゃんねる',
2693 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
2694 'uploader': 'さなちゃんねる',
7666b936 2695 'uploader_url': 'https://www.youtube.com/@sana_natori',
2696 'uploader_id': '@sana_natori',
8213ce28 2697 'channel_is_verified': True,
14a14335 2698 'heatmap': 'count:100',
7666b936 2699 },
2700 },
2701 {
2702 # Fallbacks when webpage and web client is unavailable
2703 'url': 'https://www.youtube.com/watch?v=wSSmNUl9Snw',
2704 'info_dict': {
2705 'id': 'wSSmNUl9Snw',
2706 'ext': 'mp4',
2707 # 'categories': ['Science & Technology'],
2708 'view_count': int,
2709 'chapters': 'count:2',
2710 'channel': 'Scott Manley',
2711 'like_count': int,
2712 'age_limit': 0,
2713 # 'availability': 'public',
2714 'channel_follower_count': int,
2715 'live_status': 'not_live',
2716 'upload_date': '20170831',
2717 'duration': 682,
2718 'tags': 'count:8',
2719 'uploader_url': 'https://www.youtube.com/@scottmanley',
2720 'description': 'md5:f4bed7b200404b72a394c2f97b782c02',
2721 'uploader': 'Scott Manley',
2722 'uploader_id': '@scottmanley',
2723 'title': 'The Computer Hack That Saved Apollo 14',
2724 'channel_id': 'UCxzC4EngIsMrPmbm6Nxvb-A',
2725 'thumbnail': r're:^https?://.*\.webp',
2726 'channel_url': 'https://www.youtube.com/channel/UCxzC4EngIsMrPmbm6Nxvb-A',
2727 'playable_in_embed': True,
14a14335 2728 'comment_count': int,
8213ce28 2729 'channel_is_verified': True,
14a14335 2730 'heatmap': 'count:100',
7666b936 2731 },
2732 'params': {
2733 'extractor_args': {'youtube': {'player_client': ['android'], 'player_skip': ['webpage']}},
dad2210c 2734 },
2735 },
2eb88d95
PH
2736 ]
2737
f2e8dbcc 2738 _WEBPAGE_TESTS = [
2739 # YouTube <object> embed
2740 {
2741 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2742 'md5': '873c81d308b979f0e23ee7e620b312a3',
2743 'info_dict': {
2744 'id': 'msN87y-iEx0',
2745 'ext': 'mp4',
2746 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2747 'upload_date': '20080526',
2748 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
f2e8dbcc 2749 'age_limit': 0,
2750 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2751 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2752 'playable_in_embed': True,
2753 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2754 'like_count': int,
2755 'comment_count': int,
2756 'channel': 'Christopher Sykes',
2757 'live_status': 'not_live',
2758 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2759 'availability': 'public',
2760 'duration': 195,
2761 'view_count': int,
2762 'categories': ['Science & Technology'],
2763 'channel_follower_count': int,
7666b936 2764 'uploader': 'Christopher Sykes',
2765 'uploader_url': 'https://www.youtube.com/@ChristopherSykesDocumentaries',
2766 'uploader_id': '@ChristopherSykesDocumentaries',
14a14335 2767 'heatmap': 'count:100',
f2e8dbcc 2768 },
2769 'params': {
2770 'skip_download': True,
2771 }
2772 },
2773 ]
2774
201c1459 2775 @classmethod
2776 def suitable(cls, url):
4dfbf869 2777 from ..utils import parse_qs
2778
201c1459 2779 qs = parse_qs(url)
2780 if qs.get('list', [None])[0]:
2781 return False
86e5f3ed 2782 return super().suitable(url)
201c1459 2783
e0df6211 2784 def __init__(self, *args, **kwargs):
86e5f3ed 2785 super().__init__(*args, **kwargs)
545cc85d 2786 self._code_cache = {}
83799698 2787 self._player_cache = {}
e0df6211 2788
4d37720a 2789 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
adbc4ec4 2790 lock = threading.Lock()
185bf310 2791 start_time = time.time()
adbc4ec4
THD
2792 formats = [f for f in formats if f.get('is_from_start')]
2793
185bf310 2794 def refetch_manifest(format_id, delay):
2795 nonlocal formats, start_time, is_live
2796 if time.time() <= start_time + delay:
adbc4ec4
THD
2797 return
2798
2799 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
6839ae1f 2800 video_details = traverse_obj(prs, (..., 'videoDetails'), expected_type=dict)
adbc4ec4
THD
2801 microformats = traverse_obj(
2802 prs, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 2803 expected_type=dict)
4d37720a
L
2804 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2805 is_live = live_status == 'is_live'
185bf310 2806 start_time = time.time()
adbc4ec4 2807
185bf310 2808 def mpd_feed(format_id, delay):
adbc4ec4
THD
2809 """
2810 @returns (manifest_url, manifest_stream_number, is_live) or None
2811 """
253ac4ba 2812 for retry in self.RetryManager(fatal=False):
2813 with lock:
2814 refetch_manifest(format_id, delay)
2815
2816 f = next((f for f in formats if f['format_id'] == format_id), None)
2817 if not f:
2818 if not is_live:
2819 retry.error = f'{video_id}: Video is no longer live'
2820 else:
2821 retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
2822 continue
2823 return f['manifest_url'], f['manifest_stream_number'], is_live
2824 return None
adbc4ec4
THD
2825
2826 for f in formats:
4d37720a
L
2827 f['is_live'] = is_live
2828 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2829 live_start_time, mpd_feed, not is_live and f.copy())
2830 if is_live:
2831 f['fragments'] = gen
2832 f['protocol'] = 'http_dash_segments_generator'
2833 else:
2834 f['fragments'] = LazyList(gen({}))
2835 del f['is_from_start']
adbc4ec4 2836
4d37720a 2837 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
adbc4ec4
THD
2838 FETCH_SPAN, MAX_DURATION = 5, 432000
2839
2840 mpd_url, stream_number, is_live = None, None, True
2841
2842 begin_index = 0
2843 download_start_time = ctx.get('start') or time.time()
2844
2845 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2846 if lack_early_segments:
2847 self.report_warning(bug_reports_message(
2848 'Starting download from the last 120 hours of the live stream since '
2849 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2850 lack_early_segments = True
2851
2852 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2853 fragments, fragment_base_url = None, None
2854
a539f065 2855 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2856 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2857 # Obtain from MPD's maximum seq value
2858 old_mpd_url = mpd_url
185bf310 2859 last_error = ctx.pop('last_error', None)
3d2623a8 2860 expire_fast = immediate or last_error and isinstance(last_error, HTTPError) and last_error.status == 403
185bf310 2861 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2862 or (mpd_url, stream_number, False))
2863 if not refresh_sequence:
2864 if expire_fast and not is_live:
2865 return False, last_seq
2866 elif old_mpd_url == mpd_url:
2867 return True, last_seq
4d37720a
L
2868 if manifestless_orig_fmt:
2869 fmt_info = manifestless_orig_fmt
2870 else:
2871 try:
2872 fmts, _ = self._extract_mpd_formats_and_subtitles(
2873 mpd_url, None, note=False, errnote=False, fatal=False)
2874 except ExtractorError:
2875 fmts = None
2876 if not fmts:
2877 no_fragment_score += 2
2878 return False, last_seq
2879 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
adbc4ec4
THD
2880 fragments = fmt_info['fragments']
2881 fragment_base_url = fmt_info['fragment_base_url']
2882 assert fragment_base_url
2883
2884 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2885 return True, _last_seq
2886
4d37720a 2887 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
adbc4ec4
THD
2888 while is_live:
2889 fetch_time = time.time()
2890 if no_fragment_score > 30:
2891 return
2892 if last_segment_url:
2893 # Obtain from "X-Head-Seqnum" header value from each segment
2894 try:
2895 urlh = self._request_webpage(
2896 last_segment_url, None, note=False, errnote=False, fatal=False)
2897 except ExtractorError:
2898 urlh = None
2899 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2900 if last_seq is None:
a539f065 2901 no_fragment_score += 2
adbc4ec4
THD
2902 last_segment_url = None
2903 continue
2904 else:
a539f065
LNO
2905 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2906 no_fragment_score += 2
185bf310 2907 if not should_continue:
adbc4ec4
THD
2908 continue
2909
2910 if known_idx > last_seq:
2911 last_segment_url = None
2912 continue
2913
2914 last_seq += 1
2915
2916 if begin_index < 0 and known_idx < 0:
2917 # skip from the start when it's negative value
2918 known_idx = last_seq + begin_index
2919 if lack_early_segments:
2920 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2921 try:
2922 for idx in range(known_idx, last_seq):
2923 # do not update sequence here or you'll get skipped some part of it
a539f065 2924 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2925 if not should_continue:
adbc4ec4
THD
2926 known_idx = idx - 1
2927 raise ExtractorError('breaking out of outer loop')
2928 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2929 yield {
2930 'url': last_segment_url,
36195c44 2931 'fragment_count': last_seq,
adbc4ec4
THD
2932 }
2933 if known_idx == last_seq:
2934 no_fragment_score += 5
2935 else:
2936 no_fragment_score = 0
2937 known_idx = last_seq
2938 except ExtractorError:
2939 continue
2940
4d37720a
L
2941 if manifestless_orig_fmt:
2942 # Stop at the first iteration if running for post-live manifestless;
2943 # fragment count no longer increase since it starts
2944 break
2945
adbc4ec4
THD
2946 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2947
b6de707d 2948 def _extract_player_url(self, *ytcfgs, webpage=None):
2949 player_url = traverse_obj(
2950 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2951 get_all=False, expected_type=str)
11f9be09 2952 if not player_url:
b6de707d 2953 return
60f393e4 2954 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2955
b6de707d 2956 def _download_player_url(self, video_id, fatal=False):
2957 res = self._download_webpage(
2958 'https://www.youtube.com/iframe_api',
2959 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2960 if res:
2961 player_version = self._search_regex(
2962 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2963 if player_version:
2964 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2965
60064c53
PH
2966 def _signature_cache_id(self, example_sig):
2967 """ Return a string representation of a signature """
14f25df2 2968 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2969
e40c758c
S
2970 @classmethod
2971 def _extract_player_info(cls, player_url):
2972 for player_re in cls._PLAYER_INFO_RE:
2973 id_m = re.search(player_re, player_url)
2974 if id_m:
2975 break
2976 else:
c081b35c 2977 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2978 return id_m.group('id')
e40c758c 2979
404f611f 2980 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2981 player_id = self._extract_player_info(player_url)
2982 if player_id not in self._code_cache:
1276a43a 2983 code = self._download_webpage(
109dd3b2 2984 player_url, video_id, fatal=fatal,
2985 note='Downloading player ' + player_id,
2986 errnote='Download of %s failed' % player_url)
1276a43a 2987 if code:
2988 self._code_cache[player_id] = code
404f611f 2989 return self._code_cache.get(player_id)
109dd3b2 2990
e40c758c 2991 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2992 player_id = self._extract_player_info(player_url)
e0df6211 2993
c4417ddb 2994 # Read from filesystem cache
86e5f3ed 2995 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2996 assert os.path.basename(func_id) == func_id
a0e07d31 2997
ae61d108 2998 self.write_debug(f'Extracting signature function {func_id}')
580ce007 2999 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 3000
580ce007 3001 if not cache_spec:
3002 code = self._load_player(video_id, player_url)
404f611f 3003 if code:
109dd3b2 3004 res = self._parse_sig_js(code)
ac668111 3005 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 3006 cache_spec = [ord(c) for c in res(test_string)]
9809740b 3007 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 3008
3009 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 3010
60064c53 3011 def _print_sig_code(self, func, example_sig):
404f611f 3012 if not self.get_param('youtube_print_sig_code'):
3013 return
3014
edf3e38e
PH
3015 def gen_sig_code(idxs):
3016 def _genslice(start, end, step):
78caa52a 3017 starts = '' if start == 0 else str(start)
8bcc8756 3018 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 3019 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 3020 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
3021
3022 step = None
7af808a5
PH
3023 # Quelch pyflakes warnings - start will be set when step is set
3024 start = '(Never used)'
edf3e38e
PH
3025 for i, prev in zip(idxs[1:], idxs[:-1]):
3026 if step is not None:
3027 if i - prev == step:
3028 continue
3029 yield _genslice(start, prev, step)
3030 step = None
3031 continue
3032 if i - prev in [-1, 1]:
3033 step = i - prev
3034 start = prev
3035 continue
3036 else:
78caa52a 3037 yield 's[%d]' % prev
edf3e38e 3038 if step is None:
78caa52a 3039 yield 's[%d]' % i
edf3e38e
PH
3040 else:
3041 yield _genslice(start, i, step)
3042
ac668111 3043 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 3044 cache_res = func(test_string)
edf3e38e 3045 cache_spec = [ord(c) for c in cache_res]
78caa52a 3046 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 3047 signature_id_tuple = '(%s)' % (
14f25df2 3048 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 3049 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 3050 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 3051 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 3052
e0df6211
PH
3053 def _parse_sig_js(self, jscode):
3054 funcname = self._search_regex(
abefc03f
S
3055 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3056 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
3057 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
3058 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
4823ec9f 3059 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}\(a,\d+\))?',
31ce6e99 3060 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f 3061 # Obsolete patterns
4823ec9f 3062 r'("|\')signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 3063 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
3064 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3065 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3066 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f 3067 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 3068 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
3069
3070 jsi = JSInterpreter(jscode)
3071 initial_function = jsi.extract_function(funcname)
e0df6211
PH
3072 return lambda s: initial_function([s])
3073
580ce007 3074 def _cached(self, func, *cache_id):
3075 def inner(*args, **kwargs):
3076 if cache_id not in self._player_cache:
3077 try:
3078 self._player_cache[cache_id] = func(*args, **kwargs)
3079 except ExtractorError as e:
3080 self._player_cache[cache_id] = e
3081 except Exception as e:
3082 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
3083
3084 ret = self._player_cache[cache_id]
3085 if isinstance(ret, Exception):
3086 raise ret
3087 return ret
3088 return inner
3089
545cc85d 3090 def _decrypt_signature(self, s, video_id, player_url):
257a2501 3091 """Turn the encrypted s field into a working signature"""
580ce007 3092 extract_sig = self._cached(
3093 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
3094 func = extract_sig(video_id, player_url, s)
3095 self._print_sig_code(func, s)
3096 return func(s)
404f611f 3097
3098 def _decrypt_nsig(self, s, video_id, player_url):
3099 """Turn the encrypted n field into a working signature"""
3100 if player_url is None:
3101 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 3102 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 3103
b505e851 3104 try:
3105 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
3106 except ExtractorError as e:
3107 raise ExtractorError('Unable to extract nsig function code', cause=e)
580ce007 3108 if self.get_param('youtube_print_sig_code'):
3109 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 3110
25836db6 3111 try:
3112 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
3113 ret = extract_nsig(jsi, func_code)(s)
3114 except JSInterpreter.Exception as e:
3115 try:
992dc6b4 3116 jsi = PhantomJSwrapper(self, timeout=5000)
25836db6 3117 except ExtractorError:
3118 raise e
3119 self.report_warning(
3120 f'Native nsig extraction failed: Trying with PhantomJS\n'
3121 f' n = {s} ; player = {player_url}', video_id)
0468a3b3 3122 self.write_debug(e, only_once=True)
25836db6 3123
3124 args, func_body = func_code
3125 ret = jsi.execute(
3126 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
3127 video_id=video_id, note='Executing signature code').strip()
580ce007 3128
3129 self.write_debug(f'Decrypted nsig {s} => {ret}')
3130 return ret
3131
90a1df30 3132 def _extract_n_function_name(self, jscode):
3133 funcname, idx = self._search_regex(
3134 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
3135 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
3136 if not idx:
3137 return funcname
3138
3139 return json.loads(js_to_json(self._search_regex(
337734d4 3140 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])\s*[,;]', jscode,
90a1df30 3141 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
3142
580ce007 3143 def _extract_n_function_code(self, video_id, player_url):
404f611f 3144 player_id = self._extract_player_info(player_url)
05deb747 3145 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
580ce007 3146 jscode = func_code or self._load_player(video_id, player_url)
3147 jsi = JSInterpreter(jscode)
404f611f 3148
3149 if func_code:
580ce007 3150 return jsi, player_id, func_code
404f611f 3151
b505e851 3152 func_name = self._extract_n_function_name(jscode)
3153
3154 # For redundancy
3155 func_code = self._search_regex(
3156 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
3157 # NB: The end of the regex is intentionally kept strict
3158 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
3159 jscode, 'nsig function', group=('var', 'code'), default=None)
3160 if func_code:
3161 func_code = ([func_code[0]], func_code[1])
3162 else:
3163 self.write_debug('Extracting nsig function with jsinterp')
3164 func_code = jsi.extract_function_code(func_name)
3165
580ce007 3166 self.cache.store('youtube-nsig', player_id, func_code)
3167 return jsi, player_id, func_code
3168
3169 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 3170 func = jsi.extract_function_from_code(*func_code)
f6ca640b 3171
580ce007 3172 def extract_nsig(s):
25836db6 3173 try:
3174 ret = func([s])
3175 except JSInterpreter.Exception:
3176 raise
3177 except Exception as e:
3178 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
3179
f6ca640b 3180 if ret.startswith('enhanced_except_'):
25836db6 3181 raise JSInterpreter.Exception('Signature function returned an exception')
f6ca640b 3182 return ret
580ce007 3183
3184 return extract_nsig
e0df6211 3185
109dd3b2 3186 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
3187 """
3188 Extract signatureTimestamp (sts)
3189 Required to tell API what sig/player version is in use.
3190 """
3191 sts = None
3192 if isinstance(ytcfg, dict):
3193 sts = int_or_none(ytcfg.get('STS'))
3194
3195 if not sts:
3196 # Attempt to extract from player
3197 if player_url is None:
3198 error_msg = 'Cannot extract signature timestamp without player_url.'
3199 if fatal:
3200 raise ExtractorError(error_msg)
3201 self.report_warning(error_msg)
3202 return
404f611f 3203 code = self._load_player(video_id, player_url, fatal=fatal)
3204 if code:
109dd3b2 3205 sts = int_or_none(self._search_regex(
3206 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
3207 'JS player signature timestamp', group='sts', fatal=fatal))
3208 return sts
3209
11f9be09 3210 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
3211 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
3212 label = 'fully ' if is_full else ''
3213 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
3214 expected_type=url_or_none)
3215 if not url:
3216 self.report_warning(f'Unable to mark {label}watched')
3217 return
14f25df2 3218 parsed_url = urllib.parse.urlparse(url)
3219 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
3220
3221 # cpn generation algorithm is reverse engineered from base.js.
3222 # In fact it works even with dummy cpn.
3223 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
3224 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
3225
3226 # # more consistent results setting it to right before the end
3227 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
3228
3229 qs.update({
3230 'ver': ['2'],
3231 'cpn': [cpn],
3232 'cmt': video_length,
3233 'el': 'detailpage', # otherwise defaults to "shorts"
3234 })
3235
3236 if is_full:
3237 # these seem to mark watchtime "history" in the real world
3238 # they're required, so send in a single value
3239 qs.update({
5318156f 3240 'st': 0,
06cc8f10
B
3241 'et': video_length,
3242 })
3243
14f25df2 3244 url = urllib.parse.urlunparse(
3245 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
3246
3247 self._download_webpage(
3248 url, video_id, f'Marking {label}watched',
3249 'Unable to mark watched', fatal=False)
d77ab8e2 3250
bfd973ec 3251 @classmethod
3252 def _extract_from_webpage(cls, url, webpage):
3253 # Invidious Instances
3254 # https://github.com/yt-dlp/yt-dlp/issues/195
3255 # https://github.com/iv-org/invidious/pull/1730
3256 mobj = re.search(
3257 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
3258 webpage)
3259 if mobj:
3260 yield cls.url_result(mobj.group('url'), cls)
3261 raise cls.StopExtraction()
3262
3263 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
3264
3265 # lazyYT YouTube embed
bfd973ec 3266 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3267 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
3268
3269 # Wordpress "YouTube Video Importer" plugin
bfd973ec 3270 for m in re.findall(r'''(?x)<div[^>]+
3271 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
3272 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
3273 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 3274
97665381
PH
3275 @classmethod
3276 def extract_id(cls, url):
ae61d108 3277 video_id = cls.get_temp_id(url)
3278 if not video_id:
3279 raise ExtractorError(f'Invalid URL: {url}')
3280 return video_id
c5e8d7af 3281
7c365c21 3282 def _extract_chapters_from_json(self, data, duration):
3283 chapter_list = traverse_obj(
3284 data, (
3285 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3286 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3287 ), expected_type=list)
3288
22ccd542 3289 return self._extract_chapters_helper(
7c365c21 3290 chapter_list,
22ccd542 3291 start_function=lambda chapter: float_or_none(
7c365c21 3292 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
22ccd542 3293 title_function=lambda chapter: traverse_obj(
7c365c21 3294 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3295 duration=duration)
3296
3297 def _extract_chapters_from_engagement_panel(self, data, duration):
3298 content_list = traverse_obj(
8bdd16b4 3299 data,
7c365c21 3300 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
6839ae1f 3301 expected_type=list)
052e1350 3302 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3303 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 3304
1890fc63 3305 return next(filter(None, (
22ccd542 3306 self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3307 chapter_time, chapter_title, duration)
1890fc63 3308 for contents in content_list)), [])
7c365c21 3309
03e85ea9 3310 def _extract_heatmap(self, data):
3311 return traverse_obj(data, (
3312 'frameworkUpdates', 'entityBatchUpdate', 'mutations',
3313 lambda _, v: v['payload']['macroMarkersListEntity']['markersList']['markerType'] == 'MARKER_TYPE_HEATMAP',
3314 'payload', 'macroMarkersListEntity', 'markersList', 'markers', ..., {
3315 'start_time': ('startMillis', {functools.partial(float_or_none, scale=1000)}),
3316 'end_time': {lambda x: (int(x['startMillis']) + int(x['durationMillis'])) / 1000},
3317 'value': ('intensityScoreNormalized', {float_or_none}),
3318 })) or None
5caf30db 3319
a1c5d2ca
M
3320 def _extract_comment(self, comment_renderer, parent=None):
3321 comment_id = comment_renderer.get('commentId')
3322 if not comment_id:
3323 return
fe93e2c4 3324
c35448b7 3325 info = {
3326 'id': comment_id,
3327 'text': self._get_text(comment_renderer, 'contentText'),
3328 'like_count': self._get_count(comment_renderer, 'voteCount'),
3329 'author_id': traverse_obj(comment_renderer, ('authorEndpoint', 'browseEndpoint', 'browseId', {self.ucid_or_none})),
3330 'author': self._get_text(comment_renderer, 'authorText'),
3331 'author_thumbnail': traverse_obj(comment_renderer, ('authorThumbnail', 'thumbnails', -1, 'url', {url_or_none})),
3332 'parent': parent or 'root',
3333 }
fe93e2c4 3334
c26f9b99 3335 # Timestamp is an estimate calculated from the current time and time_text
3336 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3337 timestamp = self._parse_time_text(time_text)
3338
c35448b7 3339 info.update({
3340 # FIXME: non-standard, but we need a way of showing that it is an estimate.
3341 '_time_text': time_text,
3342 'timestamp': timestamp,
3343 })
fe93e2c4 3344
c35448b7 3345 info['author_url'] = urljoin(
3346 'https://www.youtube.com', traverse_obj(comment_renderer, ('authorEndpoint', (
3347 ('browseEndpoint', 'canonicalBaseUrl'), ('commandMetadata', 'webCommandMetadata', 'url'))),
3348 expected_type=str, get_all=False))
a1c5d2ca 3349
c35448b7 3350 author_is_uploader = traverse_obj(comment_renderer, 'authorIsChannelOwner')
3351 if author_is_uploader is not None:
3352 info['author_is_uploader'] = author_is_uploader
3353
3354 comment_abr = traverse_obj(
89bed013 3355 comment_renderer, ('actionButtons', 'commentActionButtonsRenderer'), expected_type=dict)
c35448b7 3356 if comment_abr is not None:
3357 info['is_favorited'] = 'creatorHeart' in comment_abr
3358
14a14335 3359 badges = self._extract_badges([traverse_obj(comment_renderer, 'authorCommentBadge')])
3360 if self._has_badge(badges, BadgeType.VERIFIED):
3361 info['author_is_verified'] = True
c35448b7 3362
3363 is_pinned = traverse_obj(comment_renderer, 'pinnedCommentBadge')
3364 if is_pinned:
3365 info['is_pinned'] = True
3366
3367 return info
a1c5d2ca 3368
46383212 3369 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3370
3371 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 3372
3373 def extract_header(contents):
2d6659b9 3374 _continuation = None
3375 for content in contents:
46383212 3376 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 3377 expected_comment_count = self._get_count(
3378 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 3379
18f8fba7 3380 if expected_comment_count is not None:
46383212 3381 tracker['est_total'] = expected_comment_count
3382 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3383 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 3384
3385 sort_menu_item = try_get(
3386 comments_header_renderer,
3387 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3388 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3389
3390 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3391 if not _continuation:
3392 continue
3393
46383212 3394 sort_text = str_or_none(sort_menu_item.get('title'))
3395 if not sort_text:
2d6659b9 3396 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 3397 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 3398 break
a2160aa4 3399 return _continuation
a1c5d2ca 3400
2d6659b9 3401 def extract_thread(contents):
a1c5d2ca 3402 if not parent:
46383212 3403 tracker['current_page_thread'] = 0
a1c5d2ca 3404 for content in contents:
46383212 3405 if not parent and tracker['total_parent_comments'] >= max_parents:
3406 yield
a1c5d2ca 3407 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 3408 comment_renderer = get_first(
3409 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3410 expected_type=dict, default={})
a1c5d2ca 3411
a1c5d2ca
M
3412 comment = self._extract_comment(comment_renderer, parent)
3413 if not comment:
3414 continue
141a8dff 3415 comment_id = comment['id']
c35448b7 3416 if comment.get('is_pinned'):
141a8dff 3417 tracker['pinned_comment_ids'].add(comment_id)
7f51861b 3418 # Sometimes YouTube may break and give us infinite looping comments.
3419 # See: https://github.com/yt-dlp/yt-dlp/issues/6290
141a8dff 3420 if comment_id in tracker['seen_comment_ids']:
c35448b7 3421 if comment_id in tracker['pinned_comment_ids'] and not comment.get('is_pinned'):
141a8dff 3422 # Pinned comments may appear a second time in newest first sort
3423 # See: https://github.com/yt-dlp/yt-dlp/issues/6712
3424 continue
4dc4d847 3425 self.report_warning(
3426 'Detected YouTube comments looping. Stopping comment extraction '
3427 f'{"for this thread" if parent else ""} as we probably cannot get any more.')
7f51861b 3428 yield
3429 else:
3430 tracker['seen_comment_ids'].add(comment['id'])
46383212 3431
3432 tracker['running_total'] += 1
3433 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 3434 yield comment
46383212 3435
a1c5d2ca
M
3436 # Attempt to get the replies
3437 comment_replies_renderer = try_get(
3438 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3439
3440 if comment_replies_renderer:
46383212 3441 tracker['current_page_thread'] += 1
a1c5d2ca 3442 comment_entries_iter = self._comment_entries(
99e9e001 3443 comment_replies_renderer, ytcfg, video_id,
46383212 3444 parent=comment.get('id'), tracker=tracker)
86e5f3ed 3445 yield from itertools.islice(comment_entries_iter, min(
3446 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 3447
46383212 3448 # Keeps track of counts across recursive calls
3449 if not tracker:
3450 tracker = dict(
3451 running_total=0,
18f8fba7 3452 est_total=None,
46383212 3453 current_page_thread=0,
3454 total_parent_comments=0,
7f51861b 3455 total_reply_comments=0,
141a8dff 3456 seen_comment_ids=set(),
3457 pinned_comment_ids=set()
3458 )
46383212 3459
3460 # TODO: Deprecated
2d6659b9 3461 # YouTube comments have a max depth of 2
46383212 3462 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3463 if max_depth:
da4db748 3464 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3465 'Set max replies in the max-comments extractor argument instead')
2d6659b9 3466 if max_depth == 1 and parent:
3467 return
a1c5d2ca 3468
46383212 3469 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3470 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 3471
46383212 3472 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 3473
46383212 3474 response = None
6e634cbe 3475 is_forced_continuation = False
2d6659b9 3476 is_first_continuation = parent is None
6e634cbe 3477 if is_first_continuation and not continuation:
3478 # Sometimes you can get comments by generating the continuation yourself,
3479 # even if YouTube initially reports them being disabled - e.g. stories comments.
3480 # Note: if the comment section is actually disabled, YouTube may return a response with
3481 # required check_get_keys missing. So we will disable that check initially in this case.
3482 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3483 is_forced_continuation = True
a1c5d2ca 3484
18f8fba7 3485 continuation_items_path = (
3486 'onResponseReceivedEndpoints', ..., ('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems')
a1c5d2ca
M
3487 for page_num in itertools.count(0):
3488 if not continuation:
3489 break
46383212 3490 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
18f8fba7 3491 comment_prog_str = f"({tracker['running_total']}/~{tracker['est_total']})"
2d6659b9 3492 if page_num == 0:
3493 if is_first_continuation:
3494 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 3495 else:
2d6659b9 3496 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 3497 tracker['current_page_thread'], comment_prog_str)
2d6659b9 3498 else:
3499 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3500 ' ' if parent else '', ' replies' if parent else '',
3501 page_num, comment_prog_str)
18f8fba7 3502
3503 # Do a deep check for incomplete data as sometimes YouTube may return no comments for a continuation
3504 # Ignore check if YouTube says the comment count is 0.
3505 check_get_keys = None
3506 if not is_forced_continuation and not (tracker['est_total'] == 0 and tracker['running_total'] == 0):
3507 check_get_keys = [[*continuation_items_path, ..., (
3508 'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentRenderer'))]]
e72e48c5
M
3509 try:
3510 response = self._extract_response(
3511 item_id=None, query=continuation,
3512 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
18f8fba7 3513 check_get_keys=check_get_keys)
e72e48c5
M
3514 except ExtractorError as e:
3515 # Ignore incomplete data error for replies if retries didn't work.
3516 # This is to allow any other parent comments and comment threads to be downloaded.
3517 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
4dc4d847 3518 if 'incomplete data' in str(e).lower() and parent:
3519 if self.get_param('ignoreerrors') in (True, 'only_download'):
3520 self.report_warning(
3521 'Received incomplete data for a comment reply thread and retrying did not help. '
3522 'Ignoring to let other comments be downloaded. Pass --no-ignore-errors to not ignore.')
3523 return
3524 else:
3525 raise ExtractorError(
3526 'Incomplete data received for comment reply thread. '
3527 'Pass --ignore-errors to ignore and allow rest of comments to download.',
3528 expected=True)
3529 raise
6e634cbe 3530 is_forced_continuation = False
2d6659b9 3531 continuation = None
18f8fba7 3532 for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]):
46383212 3533 if is_first_continuation:
3534 continuation = extract_header(continuation_items)
3535 is_first_continuation = False
2d6659b9 3536 if continuation:
a1c5d2ca 3537 break
46383212 3538 continue
a1c5d2ca 3539
46383212 3540 for entry in extract_thread(continuation_items):
3541 if not entry:
3542 return
3543 yield entry
3544 continuation = self._extract_continuation({'contents': continuation_items})
3545 if continuation:
2d6659b9 3546 break
a1c5d2ca 3547
6e634cbe 3548 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3549 if message and not parent and tracker['running_total'] == 0:
3550 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
0cf643b2 3551 raise self.CommentsDisabled
6e634cbe 3552
3553 @staticmethod
3554 def _generate_comment_continuation(video_id):
3555 """
3556 Generates initial comment section continuation token from given video id
3557 """
3558 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3559 return base64.b64encode(token.encode()).decode()
3560
a2160aa4 3561 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3562 """Entry for comment extraction"""
2d6659b9 3563 def _real_comment_extract(contents):
aae16f6e 3564 renderer = next((
3565 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3566 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3567 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3568
a2160aa4 3569 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3570 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3571
109dd3b2 3572 @staticmethod
99e9e001 3573 def _get_checkok_params():
3574 return {'contentCheckOk': True, 'racyCheckOk': True}
3575
3576 @classmethod
3577 def _generate_player_context(cls, sts=None):
109dd3b2 3578 context = {
3579 'html5Preference': 'HTML5_PREF_WANTS',
3580 }
3581 if sts is not None:
3582 context['signatureTimestamp'] = sts
3583 return {
3584 'playbackContext': {
3585 'contentPlaybackContext': context
a1a7907b 3586 },
99e9e001 3587 **cls._get_checkok_params()
109dd3b2 3588 }
3589
e7e94f2a
D
3590 @staticmethod
3591 def _is_agegated(player_response):
3592 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3593 return True
e7e94f2a 3594
6839ae1f 3595 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')))
e7e94f2a
D
3596 AGE_GATE_REASONS = (
3597 'confirm your age', 'age-restricted', 'inappropriate', # reason
3598 'age_verification_required', 'age_check_required', # status
3599 )
3600 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3601
3602 @staticmethod
3603 def _is_unplayable(player_response):
3604 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3605
50ac0e54 3606 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3607
11f9be09 3608 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3609 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3610 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3611 headers = self.generate_api_headers(
99e9e001 3612 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3613
6e634cbe 3614 yt_query = {
3615 'videoId': video_id,
6e634cbe 3616 }
e7b17fce 3617 if _split_innertube_client(client)[0] in ('android', 'android_embedscreen'):
3618 yt_query['params'] = 'CgIIAQ=='
ba06d77a 3619
546b2c28 3620 pp_arg = self._configuration_arg('player_params', [None], casesense=True)[0]
ba06d77a 3621 if pp_arg:
3622 yt_query['params'] = pp_arg
50ac0e54 3623
11f9be09 3624 yt_query.update(self._generate_player_context(sts))
3625 return self._extract_response(
3626 item_id=video_id, ep='player', query=yt_query,
379e44ed 3627 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3628 default_client=client,
11f9be09 3629 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3630 ) or None
3631
11f9be09 3632 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3633 requested_clients = []
fd8fcf8f 3634 default = ['ios', 'android', 'web']
000c15a4 3635 allowed_clients = sorted(
86e5f3ed 3636 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3637 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3638 for client in self._configuration_arg('player_client'):
3639 if client in allowed_clients:
3640 requested_clients.append(client)
d0d012d4 3641 elif client == 'default':
3642 requested_clients.extend(default)
b4c055ba 3643 elif client == 'all':
3644 requested_clients.extend(allowed_clients)
3645 else:
3646 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3647 if not requested_clients:
d0d012d4 3648 requested_clients = default
cf7e015f 3649
11f9be09 3650 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3651 requested_clients.extend(
e7e94f2a 3652 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3653
11f9be09 3654 return orderedSet(requested_clients)
cf7e015f 3655
5eedc208
SS
3656 def _invalid_player_response(self, pr, video_id):
3657 # YouTube may return a different video player response than expected.
3658 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3659 if (pr_id := traverse_obj(pr, ('videoDetails', 'videoId'))) != video_id:
3660 return pr_id
3661
50ac0e54 3662 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3663 initial_pr = None
3664 if webpage:
b7c47b74 3665 initial_pr = self._search_json(
3666 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3667
5eedc208
SS
3668 prs = []
3669 if initial_pr and not self._invalid_player_response(initial_pr, video_id):
3670 # Android player_response does not have microFormats which are needed for
3671 # extraction of some data. So we return the initial_pr with formats
3672 # stripped out even if not requested by the user
3673 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3674 prs.append({**initial_pr, 'streamingData': None})
3675
ae729626 3676 all_clients = set(clients)
c0bc527b 3677 clients = clients[::-1]
e7e94f2a 3678
ae729626 3679 def append_client(*client_names):
e7870111 3680 """ Append the first client name that exists but not already used """
ae729626 3681 for client_name in client_names:
e7870111
D
3682 actual_client = _split_innertube_client(client_name)[0]
3683 if actual_client in INNERTUBE_CLIENTS:
3684 if actual_client not in all_clients:
ae729626 3685 clients.append(client_name)
e7870111
D
3686 all_clients.add(actual_client)
3687 return
e7e94f2a 3688
b6de707d 3689 tried_iframe_fallback = False
3690 player_url = None
5eedc208 3691 skipped_clients = {}
c0bc527b 3692 while clients:
e7870111 3693 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3694 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3695 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3696 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3697
b6de707d 3698 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3699 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3700 if 'js' in self._configuration_arg('player_skip'):
3701 require_js_player = False
3702 player_url = None
3703
3704 if not player_url and not tried_iframe_fallback and require_js_player:
3705 player_url = self._download_player_url(video_id)
3706 tried_iframe_fallback = True
3707
379e44ed 3708 try:
3709 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3710 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3711 except ExtractorError as e:
5eedc208 3712 self.report_warning(e)
379e44ed 3713 continue
3714
5eedc208
SS
3715 if pr_id := self._invalid_player_response(pr, video_id):
3716 skipped_clients[client] = pr_id
3717 elif pr:
3718 # Save client name for introspection later
3719 name = short_client_name(client)
3720 sd = traverse_obj(pr, ('streamingData', {dict})) or {}
3721 sd[STREAMING_DATA_CLIENT_NAME] = name
3722 for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})):
3723 f[STREAMING_DATA_CLIENT_NAME] = name
3724 prs.append(pr)
c0bc527b 3725
e7e94f2a 3726 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3727 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3728 append_client(f'{base_client}_creator')
e7e94f2a 3729 elif self._is_agegated(pr):
e7870111
D
3730 if variant == 'tv_embedded':
3731 append_client(f'{base_client}_embedded')
3732 elif not variant:
3733 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3734
5eedc208
SS
3735 if skipped_clients:
3736 self.report_warning(
3737 f'Skipping player responses from {"/".join(skipped_clients)} clients '
3738 f'(got player responses for video "{"/".join(set(skipped_clients.values()))}" instead of "{video_id}")')
3739 if not prs:
3740 raise ExtractorError(
3741 'All player responses are invalid. Your IP is likely being blocked by Youtube', expected=True)
3742 elif not prs:
3743 raise ExtractorError('Failed to extract any player response')
b6de707d 3744 return prs, player_url
11f9be09 3745
4d37720a
L
3746 def _needs_live_processing(self, live_status, duration):
3747 if (live_status == 'is_live' and self.get_param('live_from_start')
d949c10c 3748 or live_status == 'post_live' and (duration or 0) > 2 * 3600):
4d37720a
L
3749 return live_status
3750
3751 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
e389d172 3752 CHUNK_SIZE = 10 << 20
a4894d3e 3753 itags, stream_ids = collections.defaultdict(set), []
b25cac65 3754 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3755 q = qualities([
2a9c6dcd 3756 # Normally tiny is the smallest video-only formats. But
3757 # audio-only formats with unknown quality may get tagged as tiny
3758 'tiny',
3759 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3760 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3761 ])
6839ae1f 3762 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
58786a10 3763 format_types = self._configuration_arg('formats')
3764 all_formats = 'duplicate' in format_types
3765 if self._configuration_arg('include_duplicate_formats'):
3766 all_formats = True
3767 self._downloader.deprecated_feature('[youtube] include_duplicate_formats extractor argument is deprecated. '
3768 'Use formats=duplicate extractor argument instead')
9297939e 3769
e389d172 3770 def build_fragments(f):
3771 return LazyList({
3772 'url': update_url_query(f['url'], {
3773 'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, f["filesize"])}'
3774 })
3775 } for range_start in range(0, f['filesize'], CHUNK_SIZE))
3776
545cc85d 3777 for fmt in streaming_formats:
727029c5 3778 if fmt.get('targetDurationSec'):
545cc85d 3779 continue
321bf820 3780
cc2db878 3781 itag = str_or_none(fmt.get('itag'))
9297939e 3782 audio_track = fmt.get('audioTrack') or {}
9bb85699 3783 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
86cb9221 3784 if not all_formats:
3785 if stream_id in stream_ids:
3786 continue
9297939e 3787
cc2db878 3788 quality = fmt.get('quality')
2a9c6dcd 3789 height = int_or_none(fmt.get('height'))
d3fc8074 3790 if quality == 'tiny' or not quality:
3791 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3792 # The 3gp format (17) in android client has a quality of "small",
3793 # but is actually worse than other formats
3794 if itag == '17':
3795 quality = 'tiny'
3796 if quality:
3797 if itag:
3798 itag_qualities[itag] = quality
3799 if height:
3800 res_qualities[height] = quality
cc2db878 3801 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3802 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3803 # number of fragment that would subsequently requested with (`&sq=N`)
3804 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3805 continue
3806
545cc85d 3807 fmt_url = fmt.get('url')
3808 if not fmt_url:
14f25df2 3809 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3810 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3811 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3812 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3813 continue
52023f12 3814 try:
3815 fmt_url += '&%s=%s' % (
3816 traverse_obj(sc, ('sp', -1)) or 'signature',
3817 self._decrypt_signature(encrypted_sig, video_id, player_url)
3818 )
3819 except ExtractorError as e:
580ce007 3820 self.report_warning('Signature extraction failed: Some formats may be missing',
3821 video_id=video_id, only_once=True)
52023f12 3822 self.write_debug(e, only_once=True)
201e9eaa 3823 continue
545cc85d 3824
404f611f 3825 query = parse_qs(fmt_url)
3826 throttled = False
b2916526 3827 if query.get('n'):
404f611f 3828 try:
580ce007 3829 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3830 fmt_url = update_url_query(fmt_url, {
580ce007 3831 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3832 })
404f611f 3833 except ExtractorError as e:
25836db6 3834 phantomjs_hint = ''
3835 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3836 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3837 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
17ffed18 3838 if player_url:
3839 self.report_warning(
3840 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3841 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3842 self.write_debug(e, only_once=True)
3843 else:
3844 self.report_warning(
3845 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3846 video_id=video_id, only_once=True)
404f611f 3847 throttled = True
3848
86e3b822 3849 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3850 language_preference = (
3851 10 if audio_track.get('audioIsDefault') and 10
3852 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3853 else -1)
a25a4243 3854 format_duration = traverse_obj(fmt, ('approxDurationMs', {lambda x: float_or_none(x, 1000)}))
0ad92dfb 3855 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3856 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3857 # Make sure to avoid false positives with small duration differences.
62b58c09 3858 # E.g. __2ABJjxzNo, ySuUZEjARPY
a25a4243 3859 is_damaged = try_call(lambda: format_duration < duration // 2)
08d30158 3860 if is_damaged:
0f06bcd7 3861 self.report_warning(
3862 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
c795c39f
L
3863
3864 client_name = fmt.get(STREAMING_DATA_CLIENT_NAME)
51a07b0d 3865 name = fmt.get('qualityLabel') or quality.replace('audio_quality_', '') or ''
97afb093 3866 fps = int_or_none(fmt.get('fps')) or 0
545cc85d 3867 dct = {
3868 'asr': int_or_none(fmt.get('audioSampleRate')),
3869 'filesize': int_or_none(fmt.get('contentLength')),
9bb85699 3870 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
34921b43 3871 'format_note': join_nonempty(
392389b7 3872 join_nonempty(audio_track.get('displayName'),
3873 language_preference > 0 and ' (default)', delim=''),
51a07b0d 3874 name, fmt.get('isDrc') and 'DRC',
a4166234 3875 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3876 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
c795c39f 3877 throttled and 'THROTTLED', is_damaged and 'DAMAGED',
86cb9221 3878 (self.get_param('verbose') or all_formats) and client_name,
c795c39f 3879 delim=', '),
91e5e839 3880 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
51a07b0d 3881 'source_preference': ((-10 if throttled else -5 if itag == '22' else -1)
3882 + (100 if 'Premium' in name else 0)),
97afb093 3883 'fps': fps if fps > 1 else None, # For some formats, fps is wrongly returned as 1
a4166234 3884 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3885 'height': height,
9bb85699 3886 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
727029c5 3887 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3888 'tbr': tbr,
a25a4243 3889 'filesize_approx': filesize_from_tbr(tbr, format_duration),
545cc85d 3890 'url': fmt_url,
2a9c6dcd 3891 'width': int_or_none(fmt.get('width')),
ab6df717 3892 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
08e29b9f 3893 'desc' if language_preference < -1 else '') or None,
ab6df717 3894 'language_preference': language_preference,
a405b38f 3895 # Strictly de-prioritize damaged and 3gp formats
3896 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3897 }
60bdb7bd 3898 mime_mobj = re.match(
3899 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3900 if mime_mobj:
3901 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3902 dct.update(parse_codecs(mime_mobj.group(2)))
86cb9221 3903 if itag:
3904 itags[itag].add(('https', dct.get('language')))
3905 stream_ids.append(stream_id)
c9abebb8 3906 single_stream = 'none' in (dct.get('acodec'), dct.get('vcodec'))
3907 if single_stream and dct.get('ext'):
3908 dct['container'] = dct['ext'] + '_dash'
86cb9221 3909
58786a10 3910 if (all_formats or 'dashy' in format_types) and dct['filesize']:
86cb9221 3911 yield {
3912 **dct,
3913 'format_id': f'{dct["format_id"]}-dashy' if all_formats else dct['format_id'],
5038f6d7 3914 'protocol': 'http_dash_segments',
e389d172 3915 'fragments': build_fragments(dct),
86cb9221 3916 }
58786a10 3917 if all_formats or 'dashy' not in format_types:
3918 dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE}
3919 yield dct
545cc85d 3920
4d37720a 3921 needs_live_processing = self._needs_live_processing(live_status, duration)
58786a10 3922 skip_bad_formats = 'incomplete' not in format_types
3923 if self._configuration_arg('include_incomplete_formats'):
3924 skip_bad_formats = False
3925 self._downloader.deprecated_feature('[youtube] include_incomplete_formats extractor argument is deprecated. '
3926 'Use formats=incomplete extractor argument instead')
4d37720a
L
3927
3928 skip_manifests = set(self._configuration_arg('skip'))
3929 if (not self.get_param('youtube_include_hls_manifest', True)
3930 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3931 or needs_live_processing and skip_bad_formats):
3932 skip_manifests.add('hls')
3933
0f06bcd7 3934 if not self.get_param('youtube_include_dash_manifest', True):
4d37720a
L
3935 skip_manifests.add('dash')
3936 if self._configuration_arg('include_live_dash'):
3937 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
58786a10 3938 'Use formats=incomplete extractor argument instead')
4d37720a
L
3939 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3940 skip_manifests.add('dash')
5d3a0e79 3941
c795c39f 3942 def process_manifest_format(f, proto, client_name, itag):
a4894d3e 3943 key = (proto, f.get('language'))
86cb9221 3944 if not all_formats and key in itags[itag]:
a4894d3e 3945 return False
3946 itags[itag].add(key)
3947
86cb9221 3948 if itag and all_formats:
3949 f['format_id'] = f'{itag}-{proto}'
3950 elif any(p != proto for p, _ in itags[itag]):
a4894d3e 3951 f['format_id'] = f'{itag}-{proto}'
3952 elif itag:
a0bb6ce5 3953 f['format_id'] = itag
a0bb6ce5 3954
94ed638a 3955 if f.get('source_preference') is None:
3956 f['source_preference'] = -1
3957
1e75d97d 3958 if itag in ('616', '235'):
3959 f['format_note'] = join_nonempty(f.get('format_note'), 'Premium', delim=' ')
94ed638a 3960 f['source_preference'] += 100
1e75d97d 3961
b25cac65 3962 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3963 if f['quality'] == -1 and f.get('height'):
3964 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
ad54c913 3965 if self.get_param('verbose') or all_formats:
c795c39f 3966 f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ')
97afb093 3967 if f.get('fps') and f['fps'] <= 1:
3968 del f['fps']
94ed638a 3969
3970 if proto == 'hls' and f.get('has_drm'):
3971 f['has_drm'] = 'maybe'
3972 f['source_preference'] -= 5
a0bb6ce5 3973 return True
2a9c6dcd 3974
c646d76f 3975 subtitles = {}
11f9be09 3976 for sd in streaming_data:
c795c39f
L
3977 client_name = sd.get(STREAMING_DATA_CLIENT_NAME)
3978
4d37720a 3979 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
9297939e 3980 if hls_manifest_url:
4d37720a
L
3981 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3982 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
c646d76f 3983 subtitles = self._merge_subtitles(subs, subtitles)
3984 for f in fmts:
c795c39f 3985 if process_manifest_format(f, 'hls', client_name, self._search_regex(
a0bb6ce5 3986 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3987 yield f
545cc85d 3988
4d37720a 3989 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
5d3a0e79 3990 if dash_manifest_url:
c646d76f 3991 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3992 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3993 for f in formats:
c795c39f 3994 if process_manifest_format(f, 'dash', client_name, f['format_id']):
a0bb6ce5 3995 f['filesize'] = int_or_none(self._search_regex(
3996 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
4d37720a 3997 if needs_live_processing:
adbc4ec4
THD
3998 f['is_from_start'] = True
3999
a0bb6ce5 4000 yield f
c646d76f 4001 yield subtitles
11f9be09 4002
720c3099 4003 def _extract_storyboard(self, player_responses, duration):
4004 spec = get_first(
4005 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 4006 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
4007 if not base_url:
720c3099 4008 return
720c3099 4009 L = len(spec) - 1
4010 for i, args in enumerate(spec):
4011 args = args.split('#')
4012 counts = list(map(int_or_none, args[:5]))
4013 if len(args) != 8 or not all(counts):
4014 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
4015 continue
4016 width, height, frame_count, cols, rows = counts
4017 N, sigh = args[6:]
4018
4019 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
4020 fragment_count = frame_count / (cols * rows)
4021 fragment_duration = duration / fragment_count
4022 yield {
4023 'format_id': f'sb{i}',
4024 'format_note': 'storyboard',
4025 'ext': 'mhtml',
4026 'protocol': 'mhtml',
4027 'acodec': 'none',
4028 'vcodec': 'none',
4029 'url': url,
4030 'width': width,
4031 'height': height,
45e8a04e 4032 'fps': frame_count / duration,
4033 'rows': rows,
4034 'columns': cols,
720c3099 4035 'fragments': [{
b3edc806 4036 'url': url.replace('$M', str(j)),
720c3099 4037 'duration': min(fragment_duration, duration - (j * fragment_duration)),
4038 } for j in range(math.ceil(fragment_count))],
4039 }
4040
adbc4ec4 4041 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 4042 webpage = None
4043 if 'webpage' not in self._configuration_arg('player_skip'):
50ac0e54 4044 query = {'bpctr': '9999999999', 'has_verified': '1'}
546b2c28 4045 pp = self._configuration_arg('player_params', [None], casesense=True)[0]
ba06d77a 4046 if pp:
4047 query['pp'] = pp
b6de707d 4048 webpage = self._download_webpage(
50ac0e54 4049 webpage_url, video_id, fatal=False, query=query)
11f9be09 4050
4051 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 4052
b6de707d 4053 player_responses, player_url = self._extract_player_responses(
11f9be09 4054 self._get_requested_clients(url, smuggled_data),
50ac0e54 4055 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 4056
adbc4ec4
THD
4057 return webpage, master_ytcfg, player_responses, player_url
4058
a1b2d843 4059 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
4060 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
4061 is_live = get_first(video_details, 'isLive')
4062 if is_live is None:
4063 is_live = get_first(live_broadcast_details, 'isLiveNow')
4d37720a
L
4064 live_content = get_first(video_details, 'isLiveContent')
4065 is_upcoming = get_first(video_details, 'isUpcoming')
4d37720a
L
4066 post_live = get_first(video_details, 'isPostLiveDvr')
4067 live_status = ('post_live' if post_live
4068 else 'is_live' if is_live
4069 else 'is_upcoming' if is_upcoming
6678a4f0 4070 else 'was_live' if live_content
4071 else 'not_live' if False in (is_live, live_content)
4072 else None)
6839ae1f 4073 streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
4d37720a 4074 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
94ed638a 4075 if all(f.get('has_drm') for f in formats):
4076 # If there are no formats that definitely don't have DRM, all have DRM
4077 for f in formats:
4078 f['has_drm'] = True
adbc4ec4 4079
4d37720a 4080 return live_broadcast_details, live_status, streaming_data, formats, subtitles
adbc4ec4
THD
4081
4082 def _real_extract(self, url):
4083 url, smuggled_data = unsmuggle_url(url, {})
4084 video_id = self._match_id(url)
4085
4086 base_url = self.http_scheme() + '//www.youtube.com/'
4087 webpage_url = base_url + 'watch?v=' + video_id
4088
4089 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
4090
11f9be09 4091 playability_statuses = traverse_obj(
6839ae1f 4092 player_responses, (..., 'playabilityStatus'), expected_type=dict)
11f9be09 4093
4094 trailer_video_id = get_first(
4095 playability_statuses,
4096 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
4097 expected_type=str)
4098 if trailer_video_id:
4099 return self.url_result(
4100 trailer_video_id, self.ie_key(), trailer_video_id)
4101
4102 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
4103 if webpage else (lambda x: None))
4104
6839ae1f 4105 video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict)
11f9be09 4106 microformats = traverse_obj(
4107 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 4108 expected_type=dict)
c26f9b99 4109
4110 translated_title = self._get_text(microformats, (..., 'title'))
4111 video_title = (self._preferred_lang and translated_title
4112 or get_first(video_details, 'title') # primary
4113 or translated_title
4114 or search_meta(['og:title', 'twitter:title', 'title']))
4115 translated_description = self._get_text(microformats, (..., 'description'))
4116 original_description = get_first(video_details, 'shortDescription')
4117 video_description = (
4118 self._preferred_lang and translated_description
4119 # If original description is blank, it will be an empty string.
4120 # Do not prefer translated description in this case.
4121 or original_description if original_description is not None else translated_description)
11f9be09 4122
d89257f3 4123 multifeed_metadata_list = get_first(
4124 player_responses,
4125 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
4126 expected_type=str)
4127 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
4128 if self.get_param('noplaylist'):
11f9be09 4129 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 4130 else:
4131 entries = []
4132 feed_ids = []
4133 for feed in multifeed_metadata_list.split(','):
4134 # Unquote should take place before split on comma (,) since textual
4135 # fields may contain comma as well (see
4136 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 4137 feed_data = urllib.parse.parse_qs(
ac668111 4138 urllib.parse.unquote_plus(feed))
d89257f3 4139
4140 def feed_entry(name):
4141 return try_get(
14f25df2 4142 feed_data, lambda x: x[name][0], str)
d89257f3 4143
4144 feed_id = feed_entry('id')
4145 if not feed_id:
4146 continue
4147 feed_title = feed_entry('title')
4148 title = video_title
4149 if feed_title:
4150 title += ' (%s)' % feed_title
4151 entries.append({
4152 '_type': 'url_transparent',
4153 'ie_key': 'Youtube',
4154 'url': smuggle_url(
4155 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
4156 {'force_singlefeed': True}),
4157 'title': title,
4158 })
4159 feed_ids.append(feed_id)
4160 self.to_screen(
4161 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
4162 % (', '.join(feed_ids), video_id))
4163 return self.playlist_result(
4164 entries, video_id, video_title, video_description)
11f9be09 4165
9da6612b 4166 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
4167 or int_or_none(get_first(microformats, 'lengthSeconds'))
4168 or parse_duration(search_meta('duration')) or None)
a1b2d843 4169
4d37720a
L
4170 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
4171 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
4172 if live_status == 'post_live':
4173 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
bf1317d2 4174
545cc85d 4175 if not formats:
11f9be09 4176 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 4177 self.report_drm(video_id)
11f9be09 4178 pemr = get_first(
4179 playability_statuses,
4180 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
4181 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
4182 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 4183 if subreason:
545cc85d 4184 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 4185 countries = get_first(microformats, 'availableCountries')
545cc85d 4186 if not countries:
4187 regions_allowed = search_meta('regionsAllowed')
4188 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 4189 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 4190 reason += f'. {subreason}'
545cc85d 4191 if reason:
b7da73eb 4192 self.raise_no_formats(reason, expected=True)
bf1317d2 4193
11f9be09 4194 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 4195 if not keywords and webpage:
4196 keywords = [
4197 unescapeHTML(m.group('content'))
4198 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
4199 for keyword in keywords:
4200 if keyword.startswith('yt:stretch='):
201c1459 4201 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
4202 if mobj:
4203 # NB: float is intentional for forcing float division
4204 w, h = (float(v) for v in mobj.groups())
4205 if w > 0 and h > 0:
4206 ratio = w / h
4207 for f in formats:
4208 if f.get('vcodec') != 'none':
4209 f['stretched_ratio'] = ratio
4210 break
a709d873 4211 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 4212 thumbnail_url = search_meta(['og:image', 'twitter:image'])
4213 if thumbnail_url:
4214 thumbnails.append({
4215 'url': thumbnail_url,
ff2751ac 4216 })
fccf5021 4217 original_thumbnails = thumbnails.copy()
4218
0ba692ac 4219 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 4220 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 4221 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 4222 thumbnail_names = [
962ffcf8 4223 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 4224 # in resolution, these are not the custom thumbnail. So de-prioritize them
4225 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4226 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 4227 ]
cca80fe6 4228 n_thumbnail_names = len(thumbnail_names)
0ba692ac 4229 thumbnails.extend({
4230 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4231 video_id=video_id, name=name, ext=ext,
4d37720a 4232 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
cca80fe6 4233 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 4234 for thumb in thumbnails:
cca80fe6 4235 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 4236 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 4237 self._remove_duplicate_formats(thumbnails)
fccf5021 4238 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 4239
7ea65411 4240 category = get_first(microformats, 'category') or search_meta('genre')
7666b936 4241 channel_id = self.ucid_or_none(str_or_none(
7ea65411 4242 get_first(video_details, 'channelId')
4243 or get_first(microformats, 'externalChannelId')
7666b936 4244 or search_meta('channelId')))
7ea65411 4245 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4246
adbc4ec4
THD
4247 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4248 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4249 if not duration and live_end_time and live_start_time:
4250 duration = live_end_time - live_start_time
4251
4d37720a
L
4252 needs_live_processing = self._needs_live_processing(live_status, duration)
4253
4254 def is_bad_format(fmt):
4255 if needs_live_processing and not fmt.get('is_from_start'):
4256 return True
4257 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4258 and fmt.get('protocol') == 'http_dash_segments'):
4259 return True
4260
4261 for fmt in filter(is_bad_format, formats):
4262 fmt['preference'] = (fmt.get('preference') or -1) - 10
d949c10c 4263 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 2 hours)', delim=' ')
4d37720a
L
4264
4265 if needs_live_processing:
4266 self._prepare_live_from_start_formats(
4267 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
7ea65411 4268
720c3099 4269 formats.extend(self._extract_storyboard(player_responses, duration))
4270
7666b936 4271 channel_handle = self.handle_from_url(owner_profile_url)
4272
545cc85d 4273 info = {
4274 'id': video_id,
39ca3b5c 4275 'title': video_title,
545cc85d 4276 'formats': formats,
4277 'thumbnails': thumbnails,
fccf5021 4278 # The best thumbnail that we are sure exists. Prevents unnecessary
4279 # URL checking if user don't care about getting the best possible thumbnail
4280 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 4281 'description': video_description,
545cc85d 4282 'channel_id': channel_id,
7666b936 4283 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None),
545cc85d 4284 'duration': duration,
4285 'view_count': int_or_none(
11f9be09 4286 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 4287 or search_meta('interactionCount')),
11f9be09 4288 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 4289 'age_limit': 18 if (
11f9be09 4290 get_first(microformats, 'isFamilySafe') is False
545cc85d 4291 or search_meta('isFamilyFriendly') == 'false'
4292 or search_meta('og:restrictions:age') == '18+') else 0,
4293 'webpage_url': webpage_url,
4294 'categories': [category] if category else None,
4295 'tags': keywords,
11f9be09 4296 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4d37720a 4297 'live_status': live_status,
adbc4ec4 4298 'release_timestamp': live_start_time,
9f14daf2 4299 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4300 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
545cc85d 4301 }
b477fc13 4302
c646d76f 4303 subtitles = {}
3944e7af 4304 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 4305 if pctr:
ecdc9049 4306 def get_lang_code(track):
4307 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4308 or track.get('languageCode'))
4309
4310 # Converted into dicts to remove duplicates
4311 captions = {
4312 get_lang_code(sub): sub
6839ae1f 4313 for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
ecdc9049 4314 translation_languages = {
4315 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
6839ae1f 4316 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
ecdc9049 4317
774d79cc 4318 def process_language(container, base_url, lang_code, sub_name, query):
120916da 4319 lang_subs = container.setdefault(lang_code, [])
545cc85d 4320 for fmt in self._SUBTITLE_FORMATS:
4321 query.update({
4322 'fmt': fmt,
4323 })
4324 lang_subs.append({
4325 'ext': fmt,
60f393e4 4326 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 4327 'name': sub_name,
545cc85d 4328 })
7e72694b 4329
07b47084 4330 # NB: Constructing the full subtitle dictionary is slow
4331 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4332 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 4333 for lang_code, caption_track in captions.items():
4334 base_url = caption_track.get('baseUrl')
1235d333 4335 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 4336 if not base_url:
4337 continue
ecdc9049 4338 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 4339 if caption_track.get('kind') != 'asr':
545cc85d 4340 if not lang_code:
4341 continue
4342 process_language(
ecdc9049 4343 subtitles, base_url, lang_code, lang_name, {})
4344 if not caption_track.get('isTranslatable'):
4345 continue
3944e7af 4346 for trans_code, trans_name in translation_languages.items():
4347 if not trans_code:
545cc85d 4348 continue
1235d333 4349 orig_trans_code = trans_code
71eb82d1 4350 if caption_track.get('kind') != 'asr' and trans_code != 'und':
07b47084 4351 if not get_translated_subs:
18e49408 4352 continue
ecdc9049 4353 trans_code += f'-{lang_code}'
a70635b8 4354 trans_name += format_field(lang_name, None, ' from %s')
1235d333 4355 if lang_code == f'a-{orig_trans_code}':
ff9b0e07 4356 # Set audio language based on original subtitles
4357 for f in formats:
4358 if f.get('acodec') != 'none' and not f.get('language'):
4359 f['language'] = orig_trans_code
4360 # Add an "-orig" label to the original language so that it can be distinguished.
4361 # The subs are returned without "-orig" as well for compatibility
0c8d9e5f 4362 process_language(
d49669ac 4363 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4364 # Setting tlang=lang returns damaged subtitles.
d49669ac 4365 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 4366 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 4367
4368 info['automatic_captions'] = automatic_captions
4369 info['subtitles'] = subtitles
7e72694b 4370
14f25df2 4371 parsed_url = urllib.parse.urlparse(url)
545cc85d 4372 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 4373 query = urllib.parse.parse_qs(component)
545cc85d 4374 for k, v in query.items():
4375 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4376 d_k += '_time'
4377 if d_k not in info and k in s_ks:
4378 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
4379
4380 # Youtube Music Auto-generated description
71dc18fa
BT
4381 if (video_description or '').strip().endswith('\nAuto-generated by YouTube.'):
4382 # XXX: Causes catastrophic backtracking if description has "·"
4383 # E.g. https://www.youtube.com/watch?v=DoPaAxMQoiI
4384 # Simulating atomic groups: (?P<a>[^xy]+)x => (?=(?P<a>[^xy]+))(?P=a)x
4385 # reduces it, but does not fully fix it. https://regex101.com/r/8Ssf2h/2
1890fc63 4386 mobj = re.search(
4387 r'''(?xs)
71dc18fa
BT
4388 (?=(?P<track>[^\n·]+))(?P=track)·
4389 (?=(?P<artist>[^\n]+))(?P=artist)\n+
4390 (?=(?P<album>[^\n]+))(?P=album)\n
1890fc63 4391 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4392 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
71dc18fa
BT
4393 (.+?\nArtist\s*:\s*
4394 (?=(?P<clean_artist>[^\n]+))(?P=clean_artist)\n
4395 )?.+\nAuto-generated\ by\ YouTube\.\s*$
1890fc63 4396 ''', video_description)
822b9d9c 4397 if mobj:
822b9d9c
RA
4398 release_year = mobj.group('release_year')
4399 release_date = mobj.group('release_date')
4400 if release_date:
4401 release_date = release_date.replace('-', '')
4402 if not release_year:
545cc85d 4403 release_year = release_date[:4]
4404 info.update({
4405 'album': mobj.group('album'.strip()),
104a7b5a
L
4406 'artists': ([a] if (a := mobj.group('clean_artist'))
4407 else [a.strip() for a in mobj.group('artist').split('·')]),
545cc85d 4408 'track': mobj.group('track').strip(),
4409 'release_date': release_date,
cc2db878 4410 'release_year': int_or_none(release_year),
545cc85d 4411 })
7e72694b 4412
545cc85d 4413 initial_data = None
4414 if webpage:
56ba69e4 4415 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
607510b9 4416 if not traverse_obj(initial_data, 'contents'):
4417 self.report_warning('Incomplete data received in embedded initial data; re-fetching using API.')
4418 initial_data = None
545cc85d 4419 if not initial_data:
99e9e001 4420 query = {'videoId': video_id}
4421 query.update(self._get_checkok_params())
109dd3b2 4422 initial_data = self._extract_response(
4423 item_id=video_id, ep='next', fatal=False,
607510b9 4424 ytcfg=master_ytcfg, query=query, check_get_keys='contents',
99e9e001 4425 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 4426 note='Downloading initial data API JSON')
545cc85d 4427
0df111a3 4428 info['comment_count'] = traverse_obj(initial_data, (
4429 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
071670cb 4430 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount'
0df111a3 4431 ), (
4432 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
071670cb
ND
4433 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo'
4434 ), expected_type=self._get_count, get_all=False)
0df111a3 4435
19a03940 4436 try: # This will error if there is no livechat
c60ee3a2 4437 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 4438 except (KeyError, IndexError, TypeError):
4439 pass
4440 else:
ecdc9049 4441 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 4442 # url is needed to set cookies
4443 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 4444 'video_id': video_id,
4445 'ext': 'json',
4d37720a
L
4446 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4447 else 'youtube_live_chat_replay'),
c60ee3a2 4448 }]
545cc85d 4449
4450 if initial_data:
7c365c21 4451 info['chapters'] = (
4452 self._extract_chapters_from_json(initial_data, duration)
4453 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 4454 or self._extract_chapters_from_description(video_description, duration)
7c365c21 4455 or None)
545cc85d 4456
03e85ea9 4457 info['heatmap'] = self._extract_heatmap(initial_data)
5caf30db 4458
17322130 4459 contents = traverse_obj(
4460 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4461 expected_type=list, default=[])
4462
4463 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4464 if vpir:
4465 stl = vpir.get('superTitleLink')
4466 if stl:
4467 stl = self._get_text(stl)
4468 if try_get(
4469 vpir,
4470 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4471 info['location'] = stl
4472 else:
affc4fef 4473 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 4474 if mobj:
545cc85d 4475 info.update({
17322130 4476 'series': mobj.group(1),
4477 'season_number': int(mobj.group(2)),
4478 'episode_number': int(mobj.group(3)),
545cc85d 4479 })
17322130 4480 for tlb in (try_get(
4481 vpir,
4482 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4483 list) or []):
3ffb2f5b 4484 tbrs = variadic(
4485 traverse_obj(
6839ae1f
SS
4486 tlb, ('toggleButtonRenderer', ...),
4487 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
3ffb2f5b 4488 for tbr in tbrs:
4489 for getter, regex in [(
4490 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4491 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4492 lambda x: x['accessibility'],
4493 lambda x: x['accessibilityData']['accessibilityData'],
4494 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4495 label = (try_get(tbr, getter, dict) or {}).get('label')
4496 if label:
4497 mobj = re.match(regex, label)
4498 if mobj:
4499 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4500 break
6b5d93b0
PG
4501
4502 info['like_count'] = traverse_obj(vpir, (
4503 'videoActions', 'menuRenderer', 'topLevelButtons', ...,
4504 'segmentedLikeDislikeButtonViewModel', 'likeButtonViewModel', 'likeButtonViewModel',
4505 'toggleButtonViewModel', 'toggleButtonViewModel', 'defaultButtonViewModel',
4506 'buttonViewModel', 'accessibilityText', {parse_count}), get_all=False)
4507
867c66ff
M
4508 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4509 if vcr:
4510 vc = self._get_count(vcr, 'viewCount')
4511 # Upcoming premieres with waiting count are treated as live here
4512 if vcr.get('isLive'):
4513 info['concurrent_view_count'] = vc
4514 elif info.get('view_count') is None:
4515 info['view_count'] = vc
4516
17322130 4517 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4518 if vsir:
4519 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4520 info.update({
4521 'channel': self._get_text(vor, 'title'),
4522 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4523
7666b936 4524 if not channel_handle:
4525 channel_handle = self.handle_from_url(
4526 traverse_obj(vor, (
4527 ('navigationEndpoint', ('title', 'runs', ..., 'navigationEndpoint')),
4528 (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl')),
4529 {str}), get_all=False))
4530
17322130 4531 rows = try_get(
4532 vsir,
4533 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4534 list) or []
4535 multiple_songs = False
4536 for row in rows:
4537 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4538 multiple_songs = True
4539 break
4540 for row in rows:
4541 mrr = row.get('metadataRowRenderer') or {}
4542 mrr_title = mrr.get('title')
4543 if not mrr_title:
4544 continue
4545 mrr_title = self._get_text(mrr, 'title')
4546 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4547 if mrr_title == 'License':
4548 info['license'] = mrr_contents_text
4549 elif not multiple_songs:
4550 if mrr_title == 'Album':
4551 info['album'] = mrr_contents_text
4552 elif mrr_title == 'Artist':
104a7b5a 4553 info['artists'] = [mrr_contents_text] if mrr_contents_text else None
17322130 4554 elif mrr_title == 'Song':
4555 info['track'] = mrr_contents_text
8213ce28 4556 owner_badges = self._extract_badges(traverse_obj(vsir, ('owner', 'videoOwnerRenderer', 'badges')))
4557 if self._has_badge(owner_badges, BadgeType.VERIFIED):
4558 info['channel_is_verified'] = True
545cc85d 4559
7666b936 4560 info.update({
4561 'uploader': info.get('channel'),
4562 'uploader_id': channel_handle,
4563 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
4564 })
17322130 4565 # The upload date for scheduled, live and past live streams / premieres in microformats
4566 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 4567 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 4568 upload_date = (
4569 unified_strdate(get_first(microformats, 'uploadDate'))
4570 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 4571 if not upload_date or (
4d37720a 4572 live_status in ('not_live', None)
1ff88b7a 4573 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4574 ):
c26f9b99 4575 upload_date = strftime_or_none(
ad54c913 4576 self._parse_time_text(self._get_text(vpir, 'dateText'))) or upload_date
17322130 4577 info['upload_date'] = upload_date
992f9a73 4578
ef79d20d 4579 if upload_date and live_status not in ('is_live', 'post_live', 'is_upcoming'):
4580 # Newly uploaded videos' HLS formats are potentially problematic and need to be checked
c305a25c 4581 upload_datetime = datetime_from_str(upload_date).replace(tzinfo=dt.timezone.utc)
bb5a54e6 4582 if upload_datetime >= datetime_from_str('today-2days'):
ef79d20d 4583 for fmt in info['formats']:
4584 if fmt.get('protocol') == 'm3u8_native':
4585 fmt['__needs_testing'] = True
4586
104a7b5a 4587 for s_k, d_k in [('artists', 'creators'), ('track', 'alt_title')]:
545cc85d 4588 v = info.get(s_k)
4589 if v:
4590 info[d_k] = v
b84071c0 4591
14a14335 4592 badges = self._extract_badges(traverse_obj(vpir, 'badges'))
c26f9b99 4593
4594 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4595 or get_first(video_details, 'isPrivate', expected_type=bool))
4596
4597 info['availability'] = (
4598 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4599 else self._availability(
4600 is_private=is_private,
4601 needs_premium=(
4602 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4603 or False if initial_data and is_private is not None else None),
4604 needs_subscription=(
4605 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4606 or False if initial_data and is_private is not None else None),
4607 needs_auth=info['age_limit'] >= 18,
4608 is_unlisted=None if is_private is None else (
4609 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4610 or get_first(microformats, 'isUnlisted', expected_type=bool))))
c224251a 4611
a2160aa4 4612 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 4613
11f9be09 4614 self.mark_watched(video_id, player_responses)
d77ab8e2 4615
545cc85d 4616 return info
c5e8d7af 4617
a61fd4cf 4618
a6213a49 4619class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
182bda88 4620 @staticmethod
4621 def passthrough_smuggled_data(func):
bd7e919a 4622 def _smuggle(info, smuggled_data):
4623 if info.get('_type') not in ('url', 'url_transparent'):
4624 return info
4625 if smuggled_data.get('is_music_url'):
4626 parsed_url = urllib.parse.urlparse(info['url'])
4627 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4628 smuggled_data.pop('is_music_url')
4629 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4630 if smuggled_data:
4631 info['url'] = smuggle_url(info['url'], smuggled_data)
4632 return info
182bda88 4633
4634 @functools.wraps(func)
4635 def wrapper(self, url):
4636 url, smuggled_data = unsmuggle_url(url, {})
4637 if self.is_music_url(url):
4638 smuggled_data['is_music_url'] = True
4639 info_dict = func(self, url, smuggled_data)
bd7e919a 4640 if smuggled_data:
4641 _smuggle(info_dict, smuggled_data)
4642 if info_dict.get('entries'):
a8c754cc 4643 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
182bda88 4644 return info_dict
4645 return wrapper
4646
8bdd16b4 4647 @staticmethod
cd7c66cf 4648 def _extract_basic_item_renderer(item):
4649 # Modified from _extract_grid_item_renderer
201c1459 4650 known_basic_renderers = (
a17526e4 4651 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4652 )
4653 for key, renderer in item.items():
201c1459 4654 if not isinstance(renderer, dict):
cd7c66cf 4655 continue
201c1459 4656 elif key in known_basic_renderers:
4657 return renderer
4658 elif key.startswith('grid') and key.endswith('Renderer'):
4659 return renderer
8bdd16b4 4660
c7335551 4661 def _extract_channel_renderer(self, renderer):
7666b936 4662 channel_id = self.ucid_or_none(renderer['channelId'])
c7335551 4663 title = self._get_text(renderer, 'title')
7666b936 4664 channel_url = format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None)
7666b936 4665 channel_handle = self.handle_from_url(
4666 traverse_obj(renderer, (
4667 'navigationEndpoint', (('commandMetadata', 'webCommandMetadata', 'url'),
4668 ('browseEndpoint', 'canonicalBaseUrl')),
4669 {str}), get_all=False))
14a14335 4670 if not channel_handle:
4671 # As of 2023-06-01, YouTube sets subscriberCountText to the handle in search
4672 channel_handle = self.handle_or_none(self._get_text(renderer, 'subscriberCountText'))
c7335551
M
4673 return {
4674 '_type': 'url',
4675 'url': channel_url,
4676 'id': channel_id,
4677 'ie_key': YoutubeTabIE.ie_key(),
4678 'channel': title,
7666b936 4679 'uploader': title,
c7335551
M
4680 'channel_id': channel_id,
4681 'channel_url': channel_url,
4682 'title': title,
7666b936 4683 'uploader_id': channel_handle,
4684 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
14a14335 4685 # See above. YouTube sets videoCountText to the subscriber text in search channel renderers.
4686 # However, in feed/channels this is set correctly to the subscriber count
4687 'channel_follower_count': traverse_obj(
4688 renderer, 'subscriberCountText', 'videoCountText', expected_type=self._get_count),
c7335551 4689 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
14a14335 4690 'playlist_count': (
4691 # videoCountText may be the subscriber count
4692 self._get_count(renderer, 'videoCountText')
4693 if self._get_count(renderer, 'subscriberCountText') is not None else None),
c7335551 4694 'description': self._get_text(renderer, 'descriptionSnippet'),
8213ce28 4695 'channel_is_verified': True if self._has_badge(
4696 self._extract_badges(traverse_obj(renderer, 'ownerBadges')), BadgeType.VERIFIED) else None,
c7335551
M
4697 }
4698
8bdd16b4 4699 def _grid_entries(self, grid_renderer):
4700 for item in grid_renderer['items']:
4701 if not isinstance(item, dict):
39b62db1 4702 continue
cd7c66cf 4703 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4704 if not isinstance(renderer, dict):
4705 continue
052e1350 4706 title = self._get_text(renderer, 'title')
fe93e2c4 4707
8bdd16b4 4708 # playlist
4709 playlist_id = renderer.get('playlistId')
4710 if playlist_id:
4711 yield self.url_result(
4712 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4713 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4714 video_title=title)
201c1459 4715 continue
8bdd16b4 4716 # video
4717 video_id = renderer.get('videoId')
4718 if video_id:
4719 yield self._extract_video(renderer)
201c1459 4720 continue
8bdd16b4 4721 # channel
4722 channel_id = renderer.get('channelId')
4723 if channel_id:
c7335551 4724 yield self._extract_channel_renderer(renderer)
201c1459 4725 continue
4726 # generic endpoint URL support
4727 ep_url = urljoin('https://www.youtube.com/', try_get(
4728 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4729 str))
201c1459 4730 if ep_url:
4731 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4732 if ie.suitable(ep_url):
4733 yield self.url_result(
4734 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4735 break
8bdd16b4 4736
16aa9ea4 4737 def _music_reponsive_list_entry(self, renderer):
4738 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4739 if video_id:
69a40e4a 4740 title = traverse_obj(renderer, (
4741 'flexColumns', 0, 'musicResponsiveListItemFlexColumnRenderer',
4742 'text', 'runs', 0, 'text'))
16aa9ea4 4743 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
69a40e4a 4744 ie=YoutubeIE.ie_key(), video_id=video_id, title=title)
16aa9ea4 4745 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4746 if playlist_id:
4747 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4748 if video_id:
4749 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4750 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4751 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4752 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4753 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4754 if browse_id:
4755 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4756 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4757
3d3dddc9 4758 def _shelf_entries_from_content(self, shelf_renderer):
4759 content = shelf_renderer.get('content')
4760 if not isinstance(content, dict):
8bdd16b4 4761 return
cd7c66cf 4762 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4763 if renderer:
4764 # TODO: add support for nested playlists so each shelf is processed
4765 # as separate playlist
4766 # TODO: this includes only first N items
86e5f3ed 4767 yield from self._grid_entries(renderer)
3d3dddc9 4768 renderer = content.get('horizontalListRenderer')
4769 if renderer:
4770 # TODO
4771 pass
8bdd16b4 4772
29f7c58a 4773 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4774 ep = try_get(
4775 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4776 str)
8bdd16b4 4777 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4778 if shelf_url:
29f7c58a 4779 # Skipping links to another channels, note that checking for
4780 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4781 # will not work
4782 if skip_channels and '/channels?' in shelf_url:
4783 return
052e1350 4784 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4785 yield self.url_result(shelf_url, video_title=title)
4786 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4787 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4788
8bdd16b4 4789 def _playlist_entries(self, video_list_renderer):
4790 for content in video_list_renderer['contents']:
4791 if not isinstance(content, dict):
4792 continue
4793 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4794 if not isinstance(renderer, dict):
4795 continue
4796 video_id = renderer.get('videoId')
4797 if not video_id:
4798 continue
4799 yield self._extract_video(renderer)
07aeced6 4800
3462ffa8 4801 def _rich_entries(self, rich_grid_renderer):
80eb0bd9 4802 renderer = traverse_obj(
447afb9e 4803 rich_grid_renderer,
4804 ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer')), get_all=False) or {}
3462ffa8 4805 video_id = renderer.get('videoId')
447afb9e 4806 if video_id:
4807 yield self._extract_video(renderer)
4808 return
4809 playlist_id = renderer.get('playlistId')
4810 if playlist_id:
4811 yield self.url_result(
4812 f'https://www.youtube.com/playlist?list={playlist_id}',
4813 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4814 video_title=self._get_text(renderer, 'title'))
3462ffa8 4815 return
3462ffa8 4816
8bdd16b4 4817 def _video_entry(self, video_renderer):
4818 video_id = video_renderer.get('videoId')
4819 if video_id:
4820 return self._extract_video(video_renderer)
dacb3a86 4821
ad210f4f 4822 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4823 url = urljoin('https://youtube.com', traverse_obj(
4824 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4825 if url:
4826 return self.url_result(
4827 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4828
8bdd16b4 4829 def _post_thread_entries(self, post_thread_renderer):
4830 post_renderer = try_get(
4831 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4832 if not post_renderer:
4833 return
4834 # video attachment
4835 video_renderer = try_get(
895b0931 4836 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4837 video_id = video_renderer.get('videoId')
4838 if video_id:
4839 entry = self._extract_video(video_renderer)
8bdd16b4 4840 if entry:
4841 yield entry
895b0931 4842 # playlist attachment
4843 playlist_id = try_get(
14f25df2 4844 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4845 if playlist_id:
4846 yield self.url_result(
e28f1c0a 4847 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4848 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4849 # inline video links
4850 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4851 for run in runs:
4852 if not isinstance(run, dict):
4853 continue
4854 ep_url = try_get(
14f25df2 4855 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4856 if not ep_url:
4857 continue
4858 if not YoutubeIE.suitable(ep_url):
4859 continue
4860 ep_video_id = YoutubeIE._match_id(ep_url)
4861 if video_id == ep_video_id:
4862 continue
895b0931 4863 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4864
8bdd16b4 4865 def _post_thread_continuation_entries(self, post_thread_continuation):
4866 contents = post_thread_continuation.get('contents')
4867 if not isinstance(contents, list):
4868 return
4869 for content in contents:
4870 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4871 if isinstance(renderer, dict):
4872 yield from self._post_thread_entries(renderer)
8bdd16b4 4873 continue
6b0b0a28 4874 renderer = content.get('videoRenderer')
4875 if isinstance(renderer, dict):
4876 yield self._video_entry(renderer)
07aeced6 4877
39ed931e 4878 r''' # unused
4879 def _rich_grid_entries(self, contents):
4880 for content in contents:
4881 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4882 if video_renderer:
4883 entry = self._video_entry(video_renderer)
4884 if entry:
4885 yield entry
4886 '''
52efa4b3 4887
0a5095fe 4888 def _report_history_entries(self, renderer):
4889 for url in traverse_obj(renderer, (
7a32c70d 4890 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4891 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
0a5095fe 4892 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4893 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4894
a6213a49 4895 def _extract_entries(self, parent_renderer, continuation_list):
4896 # continuation_list is modified in-place with continuation_list = [continuation_token]
4897 continuation_list[:] = [None]
4898 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4899 for content in contents:
4900 if not isinstance(content, dict):
4901 continue
16aa9ea4 4902 is_renderer = traverse_obj(
4903 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4904 expected_type=dict)
a6213a49 4905 if not is_renderer:
0a5095fe 4906 if content.get('richItemRenderer'):
4907 for entry in self._rich_entries(content['richItemRenderer']):
a6213a49 4908 yield entry
4909 continuation_list[0] = self._extract_continuation(parent_renderer)
0a5095fe 4910 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4911 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4912 yield from self._report_history_entries(table)
4913 continuation_list[0] = self._extract_continuation(table)
a6213a49 4914 continue
0a5095fe 4915
a6213a49 4916 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4917 for isr_content in isr_contents:
4918 if not isinstance(isr_content, dict):
8bdd16b4 4919 continue
69184e41 4920
a6213a49 4921 known_renderers = {
4922 'playlistVideoListRenderer': self._playlist_entries,
4923 'gridRenderer': self._grid_entries,
a17526e4 4924 'reelShelfRenderer': self._grid_entries,
4925 'shelfRenderer': self._shelf_entries,
16aa9ea4 4926 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4927 'backstagePostThreadRenderer': self._post_thread_entries,
4928 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4929 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4930 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
fcbc9ed7 4931 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)],
4932 'richGridRenderer': lambda x: self._extract_entries(x, continuation_list),
a6213a49 4933 }
4934 for key, renderer in isr_content.items():
4935 if key not in known_renderers:
4936 continue
4937 for entry in known_renderers[key](renderer):
4938 if entry:
4939 yield entry
4940 continuation_list[0] = self._extract_continuation(renderer)
4941 break
70d5c17b 4942
4943 if not continuation_list[0]:
a6213a49 4944 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4945
a6213a49 4946 if not continuation_list[0]:
4947 continuation_list[0] = self._extract_continuation(parent_renderer)
4948
4949 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4950 continuation_list = [None]
4951 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4952 tab_content = try_get(tab, lambda x: x['content'], dict)
4953 if not tab_content:
4954 return
3462ffa8 4955 parent_renderer = (
29f7c58a 4956 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4957 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4958 yield from extract_entries(parent_renderer)
3462ffa8 4959 continuation = continuation_list[0]
1ba6fe9d 4960 seen_continuations = set()
8bdd16b4 4961 for page_num in itertools.count(1):
4962 if not continuation:
4963 break
1ba6fe9d 4964 continuation_token = continuation.get('continuation')
4965 if continuation_token is not None and continuation_token in seen_continuations:
4966 self.write_debug('Detected YouTube feed looping - assuming end of feed.')
4967 break
4968 seen_continuations.add(continuation_token)
99e9e001 4969 headers = self.generate_api_headers(
4970 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4971 response = self._extract_response(
86e5f3ed 4972 item_id=f'{item_id} page {page_num}',
fe93e2c4 4973 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4974 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4975
4976 if not response:
8bdd16b4 4977 break
ac56cf38 4978 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4979 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4980 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4981
a1b535bd 4982 known_renderers = {
e4b98809 4983 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4984 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4985 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4986 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4987 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4988 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4989 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
0a5095fe 4990 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4991 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
1fb53b94 4992 'playlistVideoListContinuation': (self._playlist_entries, None),
4993 'gridContinuation': (self._grid_entries, None),
4994 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4995 'sectionListContinuation': (extract_entries, None), # for feeds
a1b535bd 4996 }
1fb53b94 4997
4998 continuation_items = traverse_obj(response, (
4999 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
5000 'appendContinuationItemsAction', 'continuationItems'
5001 ), 'continuationContents', get_all=False)
5002 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
5003
a1b535bd 5004 video_items_renderer = None
1fb53b94 5005 for key in continuation_item.keys():
a1b535bd 5006 if key not in known_renderers:
8bdd16b4 5007 continue
1fb53b94 5008 func, parent_key = known_renderers[key]
5009 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
9ba5705a 5010 continuation_list = [None]
1fb53b94 5011 yield from func(video_items_renderer)
9ba5705a 5012 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
1fb53b94 5013
5014 if not video_items_renderer:
a1b535bd 5015 break
9558dcec 5016
8bdd16b4 5017 @staticmethod
7c219ea6 5018 def _extract_selected_tab(tabs, fatal=True):
86973308
M
5019 for tab_renderer in tabs:
5020 if tab_renderer.get('selected'):
5021 return tab_renderer
5022 if fatal:
5023 raise ExtractorError('Unable to find selected tab')
5024
5025 @staticmethod
5026 def _extract_tab_renderers(response):
5027 return traverse_obj(
5028 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
b82f815f 5029
ac56cf38 5030 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
bd7e919a 5031 metadata = self._extract_metadata_from_tabs(item_id, data)
b60419c5 5032
8bdd16b4 5033 selected_tab = self._extract_selected_tab(tabs)
bd7e919a 5034 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
5035 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
5036
5037 return self.playlist_result(
5038 self._entries(
5039 selected_tab, metadata['id'], ytcfg,
5040 self._extract_account_syncid(ytcfg, data),
5041 self._extract_visitor_data(data, ytcfg)),
5042 **metadata)
39ed931e 5043
bd7e919a 5044 def _extract_metadata_from_tabs(self, item_id, data):
5045 info = {'id': item_id}
5046
5047 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
6141346d 5048 if metadata_renderer:
7666b936 5049 channel_id = traverse_obj(metadata_renderer, ('externalId', {self.ucid_or_none}),
4823ec9f 5050 ('channelUrl', {self.ucid_from_url}))
bd7e919a 5051 info.update({
7666b936 5052 'channel': metadata_renderer.get('title'),
5053 'channel_id': channel_id,
bd7e919a 5054 })
7666b936 5055 if info['channel_id']:
5056 info['id'] = info['channel_id']
bd7e919a 5057 else:
5058 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
b60419c5 5059
301d07fc 5060 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
5061 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
5062 def _get_uncropped(url):
5063 return url_or_none((url or '').split('=')[0] + '=s0')
5064
6141346d 5065 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
301d07fc 5066 if avatar_thumbnails:
5067 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
5068 if uncropped_avatar:
5069 avatar_thumbnails.append({
5070 'url': uncropped_avatar,
5071 'id': 'avatar_uncropped',
5072 'preference': 1
5073 })
5074
5075 channel_banners = self._extract_thumbnails(
bd7e919a 5076 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
301d07fc 5077 for banner in channel_banners:
5078 banner['preference'] = -10
5079
5080 if channel_banners:
5081 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
5082 if uncropped_banner:
5083 channel_banners.append({
5084 'url': uncropped_banner,
5085 'id': 'banner_uncropped',
5086 'preference': -5
5087 })
5088
bd7e919a 5089 # Deprecated - remove primary_sidebar_renderer when layout discontinued
5090 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
5091 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
5092
301d07fc 5093 primary_thumbnails = self._extract_thumbnails(
a17526e4 5094 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
6141346d
M
5095 playlist_thumbnails = self._extract_thumbnails(
5096 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
5097
bd7e919a 5098 info.update({
5099 'title': (traverse_obj(metadata_renderer, 'title')
5100 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
5101 or info['id']),
5102 'availability': self._extract_availability(data),
5103 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
5104 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
8828f457 5105 'tags': (traverse_obj(data, ('microformat', 'microformatDataRenderer', 'tags', ..., {str}))
5106 or traverse_obj(metadata_renderer, ('keywords', {lambda x: x and shlex.split(x)}, ...))),
bd7e919a 5107 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
5108 })
f0d785d3 5109
7666b936 5110 channel_handle = (
5111 traverse_obj(metadata_renderer, (('vanityChannelUrl', ('ownerUrls', ...)), {self.handle_from_url}), get_all=False)
5112 or traverse_obj(data, ('header', ..., 'channelHandleText', {self.handle_or_none}), get_all=False))
5113
5114 if channel_handle:
5115 info.update({
5116 'uploader_id': channel_handle,
5117 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
5118 })
8213ce28 5119
5120 channel_badges = self._extract_badges(traverse_obj(data, ('header', ..., 'badges'), get_all=False))
5121 if self._has_badge(channel_badges, BadgeType.VERIFIED):
5122 info['channel_is_verified'] = True
6141346d
M
5123 # Playlist stats is a text runs array containing [video count, view count, last updated].
5124 # last updated or (view count and last updated) may be missing.
5125 playlist_stats = get_first(
bd7e919a 5126 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
5127
6141346d
M
5128 last_updated_unix = self._parse_time_text(
5129 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
5130 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
ad54c913 5131 info['modified_date'] = strftime_or_none(last_updated_unix)
6141346d 5132
bd7e919a 5133 info['view_count'] = self._get_count(playlist_stats, 1)
5134 if info['view_count'] is None: # 0 is allowed
5135 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
31e18355 5136 if info['view_count'] is None:
5137 info['view_count'] = self._get_count(data, (
5138 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer',
5139 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText'))
bd7e919a 5140
5141 info['playlist_count'] = self._get_count(playlist_stats, 0)
5142 if info['playlist_count'] is None: # 0 is allowed
5143 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
5144
7666b936 5145 if not info.get('channel_id'):
6141346d 5146 owner = traverse_obj(playlist_header_renderer, 'ownerText')
bd7e919a 5147 if not owner: # Deprecated
6141346d
M
5148 owner = traverse_obj(
5149 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
5150 ('videoOwner', 'videoOwnerRenderer', 'title'))
5151 owner_text = self._get_text(owner)
5152 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
bd7e919a 5153 info.update({
7666b936 5154 'channel': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
5155 'channel_id': self.ucid_or_none(browse_ep.get('browseId')),
5156 'uploader_id': self.handle_from_url(urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl')))
bd7e919a 5157 })
6141346d 5158
bd7e919a 5159 info.update({
7666b936 5160 'uploader': info['channel'],
5161 'channel_url': format_field(info.get('channel_id'), None, 'https://www.youtube.com/channel/%s', default=None),
5162 'uploader_url': format_field(info.get('uploader_id'), None, 'https://www.youtube.com/%s', default=None),
bd7e919a 5163 })
7666b936 5164
bd7e919a 5165 return info
73c4ac2c 5166
6e634cbe 5167 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 5168 first_id = last_id = response = None
2be71994 5169 for page_num in itertools.count(1):
cd7c66cf 5170 videos = list(self._playlist_entries(playlist))
5171 if not videos:
5172 return
2be71994 5173 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
5174 if start >= len(videos):
5175 return
24146491 5176 yield from videos[start:]
2be71994 5177 first_id = first_id or videos[0]['id']
5178 last_id = videos[-1]['id']
79360d99 5179 watch_endpoint = try_get(
5180 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 5181 headers = self.generate_api_headers(
5182 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
5183 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 5184 query = {
5185 'playlistId': playlist_id,
5186 'videoId': watch_endpoint.get('videoId') or last_id,
5187 'index': watch_endpoint.get('index') or len(videos),
5188 'params': watch_endpoint.get('params') or 'OAE%3D'
5189 }
5190 response = self._extract_response(
5191 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 5192 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 5193 check_get_keys='contents'
5194 )
cd7c66cf 5195 playlist = try_get(
79360d99 5196 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 5197
ac56cf38 5198 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 5199 title = playlist.get('title') or try_get(
14f25df2 5200 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 5201 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 5202
5203 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 5204 playlist_url = urljoin(url, try_get(
5205 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 5206 str))
6e634cbe 5207
5208 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
5209 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
5210 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
5211
5212 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 5213 return self.url_result(
5214 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
5215 video_title=title)
cd7c66cf 5216
8bdd16b4 5217 return self.playlist_result(
6e634cbe 5218 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 5219 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 5220
47193e02 5221 def _extract_availability(self, data):
5222 """
5223 Gets the availability of a given playlist/tab.
5224 Note: Unless YouTube tells us explicitly, we do not assume it is public
5225 @param data: response
5226 """
6141346d
M
5227 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
5228 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
5229 player_header_privacy = playlist_header_renderer.get('privacy')
c26f9b99 5230
14a14335 5231 badges = self._extract_badges(traverse_obj(sidebar_renderer, 'badges'))
47193e02 5232
5233 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
6141346d
M
5234 privacy_setting_icon = get_first(
5235 (playlist_header_renderer, sidebar_renderer),
5236 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
5237 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
5238 expected_type=str)
5239
5240 microformats_is_unlisted = traverse_obj(
5241 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
47193e02 5242
c26f9b99 5243 return (
5244 'public' if (
5245 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
5246 or player_header_privacy == 'PUBLIC'
5247 or privacy_setting_icon == 'PRIVACY_PUBLIC')
5248 else self._availability(
5249 is_private=(
5250 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
5251 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
5252 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
5253 is_unlisted=(
5254 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
5255 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
6141346d
M
5256 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
5257 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
c26f9b99 5258 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
5259 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
5260 needs_auth=False))
47193e02 5261
5262 @staticmethod
5263 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
5264 sidebar_renderer = try_get(
5265 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
5266 for item in sidebar_renderer:
5267 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
5268 if renderer:
5269 return renderer
5270
ac56cf38 5271 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 5272 """
6141346d 5273 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
358de58c 5274 """
6141346d
M
5275 is_playlist = bool(traverse_obj(
5276 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5277 if not is_playlist:
47193e02 5278 return
11f9be09 5279 headers = self.generate_api_headers(
99e9e001 5280 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 5281 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 5282 query = {
6141346d
M
5283 'params': 'wgYCCAA=',
5284 'browseId': f'VL{item_id}'
47193e02 5285 }
5286 return self._extract_response(
5287 item_id=item_id, headers=headers, query=query,
fe93e2c4 5288 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
6141346d 5289 note='Redownloading playlist API JSON with unavailable videos')
358de58c 5290
2762dbb1 5291 @functools.cached_property
a25bca9f 5292 def skip_webpage(self):
5293 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
5294
ac56cf38 5295 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 5296 webpage, data = None, None
5297 for retry in self.RetryManager(fatal=fatal):
ac56cf38 5298 try:
be5c1ae8 5299 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 5300 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5301 except ExtractorError as e:
5302 if isinstance(e.cause, network_exceptions):
3d2623a8 5303 if not isinstance(e.cause, HTTPError) or e.cause.status not in (403, 429):
be5c1ae8 5304 retry.error = e
5305 continue
5306 self._error_or_warning(e, fatal=fatal)
14fdfea9 5307 break
ac56cf38 5308
be5c1ae8 5309 try:
5310 self._extract_and_report_alerts(data)
5311 except ExtractorError as e:
5312 self._error_or_warning(e, fatal=fatal)
5313 break
ac56cf38 5314
be5c1ae8 5315 # Sometimes youtube returns a webpage with incomplete ytInitialData
5316 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5317 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5318 retry.error = ExtractorError('Incomplete yt initial data received')
f9fb3ce8 5319 data = None
be5c1ae8 5320 continue
ac56cf38 5321
cd7c66cf 5322 return webpage, data
5323
a25bca9f 5324 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5325 """Use if failed to extract ytcfg (and data) from initial webpage"""
5326 if not ytcfg and self.is_authenticated:
5327 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5328 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5329 raise ExtractorError(
5330 f'{msg}. If you are not downloading private content, or '
5331 'your cookies are only for the first account and channel,'
5332 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5333 expected=True)
5334 self.report_warning(msg, only_once=True)
5335
ac56cf38 5336 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5337 data = None
a25bca9f 5338 if not self.skip_webpage:
ac56cf38 5339 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5340 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 5341 # Reject webpage data if redirected to home page without explicitly requesting
86973308 5342 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
1108613f 5343 if (url != 'https://www.youtube.com/feed/recommended'
5344 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5345 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5346 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5347 if fatal:
5348 raise ExtractorError(msg, expected=True)
5349 self.report_warning(msg, only_once=True)
ac56cf38 5350 if not data:
a25bca9f 5351 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 5352 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5353 return data, ytcfg
5354
5355 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5356 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5357 resolve_response = self._extract_response(
5358 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5359 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5360 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5361 for ep_key, ep in endpoints.items():
5362 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5363 if params:
5364 return self._extract_response(
5365 item_id=item_id, query=params, ep=ep, headers=headers,
5366 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 5367 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 5368 err_note = 'Failed to resolve url (does the playlist exist?)'
5369 if fatal:
5370 raise ExtractorError(err_note, expected=True)
5371 self.report_warning(err_note, item_id)
5372
a6213a49 5373 _SEARCH_PARAMS = None
5374
af5c1c55 5375 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 5376 data = {'query': query}
5377 if params is NO_DEFAULT:
5378 params = self._SEARCH_PARAMS
5379 if params:
5380 data['params'] = params
16aa9ea4 5381
5382 content_keys = (
5383 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5384 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5385 # ytmusic search
5386 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5387 ('continuationContents', ),
5388 )
a25bca9f 5389 display_id = f'query "{query}"'
86e5f3ed 5390 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 5391 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5392 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 5393
a61fd4cf 5394 continuation_list = [None]
a25bca9f 5395 search = None
a6213a49 5396 for page_num in itertools.count(1):
a61fd4cf 5397 data.update(continuation_list[0] or {})
a25bca9f 5398 headers = self.generate_api_headers(
5399 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 5400 search = self._extract_response(
a25bca9f 5401 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5402 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 5403 slr_contents = traverse_obj(search, *content_keys)
5404 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 5405 if not continuation_list[0]:
a6213a49 5406 break
5407
5408
5409class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5410 IE_DESC = 'YouTube Tabs'
5411 _VALID_URL = r'''(?x:
5412 https?://
b032ff0f 5413 (?!consent\.)(?:\w+\.)?
a6213a49 5414 (?:
5415 youtube(?:kids)?\.com|
5416 %(invidious)s
5417 )/
5418 (?:
5419 (?P<channel_type>channel|c|user|browse)/|
5420 (?P<not_channel>
5421 feed/|hashtag/|
5422 (?:playlist|watch)\?.*?\blist=
5423 )|
5424 (?!(?:%(reserved_names)s)\b) # Direct URLs
5425 )
5426 (?P<id>[^/?\#&]+)
5427 )''' % {
5428 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5429 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5430 }
5431 IE_NAME = 'youtube:tab'
5432
5433 _TESTS = [{
5434 'note': 'playlists, multipage',
5435 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5436 'playlist_mincount': 94,
5437 'info_dict': {
5438 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
8828f457 5439 'title': 'Igor Kleiner Ph.D. - Playlists',
5440 'description': 'md5:15d7dd9e333cb987907fcb0d604b233a',
5441 'uploader': 'Igor Kleiner Ph.D.',
7666b936 5442 'uploader_id': '@IgorDataScience',
5443 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
8828f457 5444 'channel': 'Igor Kleiner Ph.D.',
976ae3ea 5445 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
8828f457 5446 'tags': ['критическое мышление', 'наука просто', 'математика', 'анализ данных'],
976ae3ea 5447 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5448 'channel_follower_count': int
a6213a49 5449 },
5450 }, {
5451 'note': 'playlists, multipage, different order',
5452 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5453 'playlist_mincount': 94,
5454 'info_dict': {
5455 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
8828f457 5456 'title': 'Igor Kleiner Ph.D. - Playlists',
5457 'description': 'md5:15d7dd9e333cb987907fcb0d604b233a',
5458 'uploader': 'Igor Kleiner Ph.D.',
7666b936 5459 'uploader_id': '@IgorDataScience',
5460 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
8828f457 5461 'tags': ['критическое мышление', 'наука просто', 'математика', 'анализ данных'],
976ae3ea 5462 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
8828f457 5463 'channel': 'Igor Kleiner Ph.D.',
976ae3ea 5464 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5465 'channel_follower_count': int
a6213a49 5466 },
5467 }, {
5468 'note': 'playlists, series',
5469 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5470 'playlist_mincount': 5,
5471 'info_dict': {
5472 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5473 'title': '3Blue1Brown - Playlists',
8828f457 5474 'description': 'md5:4d1da95432004b7ba840ebc895b6b4c9',
976ae3ea 5475 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5476 'channel': '3Blue1Brown',
5477 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
7666b936 5478 'uploader_id': '@3blue1brown',
5479 'uploader_url': 'https://www.youtube.com/@3blue1brown',
5480 'uploader': '3Blue1Brown',
976ae3ea 5481 'tags': ['Mathematics'],
14a14335 5482 'channel_follower_count': int,
8213ce28 5483 'channel_is_verified': True,
a6213a49 5484 },
5485 }, {
5486 'note': 'playlists, singlepage',
5487 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5488 'playlist_mincount': 4,
5489 'info_dict': {
5490 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5491 'title': 'ThirstForScience - Playlists',
5492 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5493 'uploader': 'ThirstForScience',
7666b936 5494 'uploader_url': 'https://www.youtube.com/@ThirstForScience',
5495 'uploader_id': '@ThirstForScience',
976ae3ea 5496 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
7666b936 5497 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
8828f457 5498 'tags': 'count:12',
976ae3ea 5499 'channel': 'ThirstForScience',
6c73052c 5500 'channel_follower_count': int
a6213a49 5501 }
5502 }, {
5503 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5504 'only_matching': True,
5505 }, {
5506 'note': 'basic, single video playlist',
5507 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5508 'info_dict': {
a6213a49 5509 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5510 'title': 'youtube-dl public playlist',
976ae3ea 5511 'description': '',
5512 'tags': [],
5513 'view_count': int,
5514 'modified_date': '20201130',
5515 'channel': 'Sergey M.',
5516 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
976ae3ea 5517 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5518 'availability': 'public',
7666b936 5519 'uploader': 'Sergey M.',
5520 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
5521 'uploader_id': '@sergeym.6173',
a6213a49 5522 },
5523 'playlist_count': 1,
5524 }, {
5525 'note': 'empty playlist',
5526 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5527 'info_dict': {
a6213a49 5528 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5529 'title': 'youtube-dl empty playlist',
976ae3ea 5530 'tags': [],
5531 'channel': 'Sergey M.',
5532 'description': '',
8828f457 5533 'modified_date': '20230921',
976ae3ea 5534 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5535 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
8828f457 5536 'availability': 'unlisted',
7666b936 5537 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
5538 'uploader_id': '@sergeym.6173',
5539 'uploader': 'Sergey M.',
a6213a49 5540 },
5541 'playlist_count': 0,
5542 }, {
5543 'note': 'Home tab',
5544 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5545 'info_dict': {
5546 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5547 'title': 'lex will - Home',
5548 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5549 'uploader': 'lex will',
7666b936 5550 'uploader_id': '@lexwill718',
976ae3ea 5551 'channel': 'lex will',
5552 'tags': ['bible', 'history', 'prophesy'],
7666b936 5553 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5554 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5555 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5556 'channel_follower_count': int
a6213a49 5557 },
5558 'playlist_mincount': 2,
5559 }, {
5560 'note': 'Videos tab',
5561 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5562 'info_dict': {
5563 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5564 'title': 'lex will - Videos',
5565 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5566 'uploader': 'lex will',
7666b936 5567 'uploader_id': '@lexwill718',
976ae3ea 5568 'tags': ['bible', 'history', 'prophesy'],
5569 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5570 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
7666b936 5571 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5572 'channel': 'lex will',
6c73052c 5573 'channel_follower_count': int
a6213a49 5574 },
5575 'playlist_mincount': 975,
5576 }, {
5577 'note': 'Videos tab, sorted by popular',
5578 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5579 'info_dict': {
5580 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5581 'title': 'lex will - Videos',
5582 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5583 'uploader': 'lex will',
7666b936 5584 'uploader_id': '@lexwill718',
976ae3ea 5585 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
7666b936 5586 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5587 'channel': 'lex will',
5588 'tags': ['bible', 'history', 'prophesy'],
5589 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5590 'channel_follower_count': int
a6213a49 5591 },
5592 'playlist_mincount': 199,
5593 }, {
5594 'note': 'Playlists tab',
5595 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5596 'info_dict': {
5597 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5598 'title': 'lex will - Playlists',
5599 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5600 'uploader': 'lex will',
7666b936 5601 'uploader_id': '@lexwill718',
5602 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5603 'channel': 'lex will',
5604 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5605 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5606 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5607 'channel_follower_count': int
a6213a49 5608 },
5609 'playlist_mincount': 17,
5610 }, {
5611 'note': 'Community tab',
5612 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5613 'info_dict': {
5614 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5615 'title': 'lex will - Community',
5616 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
976ae3ea 5617 'channel': 'lex will',
5618 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5619 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5620 'tags': ['bible', 'history', 'prophesy'],
7666b936 5621 'channel_follower_count': int,
5622 'uploader_url': 'https://www.youtube.com/@lexwill718',
5623 'uploader_id': '@lexwill718',
5624 'uploader': 'lex will',
a6213a49 5625 },
5626 'playlist_mincount': 18,
5627 }, {
5628 'note': 'Channels tab',
5629 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5630 'info_dict': {
5631 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5632 'title': 'lex will - Channels',
5633 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
976ae3ea 5634 'channel': 'lex will',
5635 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5636 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5637 'tags': ['bible', 'history', 'prophesy'],
7666b936 5638 'channel_follower_count': int,
5639 'uploader_url': 'https://www.youtube.com/@lexwill718',
5640 'uploader_id': '@lexwill718',
5641 'uploader': 'lex will',
a6213a49 5642 },
5643 'playlist_mincount': 12,
5644 }, {
5645 'note': 'Search tab',
5646 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5647 'playlist_mincount': 40,
5648 'info_dict': {
5649 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5650 'title': '3Blue1Brown - Search - linear algebra',
8828f457 5651 'description': 'md5:4d1da95432004b7ba840ebc895b6b4c9',
976ae3ea 5652 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5653 'tags': ['Mathematics'],
5654 'channel': '3Blue1Brown',
5655 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
7666b936 5656 'channel_follower_count': int,
5657 'uploader_url': 'https://www.youtube.com/@3blue1brown',
5658 'uploader_id': '@3blue1brown',
5659 'uploader': '3Blue1Brown',
8213ce28 5660 'channel_is_verified': True,
a6213a49 5661 },
5662 }, {
5663 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5664 'only_matching': True,
5665 }, {
5666 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5667 'only_matching': True,
5668 }, {
5669 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5670 'only_matching': True,
5671 }, {
5672 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5673 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5674 'info_dict': {
5675 'title': '29C3: Not my department',
5676 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
a6213a49 5677 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 5678 'tags': [],
976ae3ea 5679 'view_count': int,
5680 'modified_date': '20150605',
5681 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
7666b936 5682 'channel_url': 'https://www.youtube.com/channel/UCEPzS1rYsrkqzSLNp76nrcg',
976ae3ea 5683 'channel': 'Christiaan008',
c26f9b99 5684 'availability': 'public',
7666b936 5685 'uploader_id': '@ChRiStIaAn008',
5686 'uploader': 'Christiaan008',
5687 'uploader_url': 'https://www.youtube.com/@ChRiStIaAn008',
a6213a49 5688 },
5689 'playlist_count': 96,
5690 }, {
5691 'note': 'Large playlist',
5692 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5693 'info_dict': {
5694 'title': 'Uploads from Cauchemar',
5695 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
7666b936 5696 'channel_url': 'https://www.youtube.com/channel/UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5697 'tags': [],
5698 'modified_date': r're:\d{8}',
5699 'channel': 'Cauchemar',
976ae3ea 5700 'view_count': int,
5701 'description': '',
5702 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
c26f9b99 5703 'availability': 'public',
7666b936 5704 'uploader_id': '@Cauchemar89',
5705 'uploader': 'Cauchemar',
5706 'uploader_url': 'https://www.youtube.com/@Cauchemar89',
a6213a49 5707 },
5708 'playlist_mincount': 1123,
976ae3ea 5709 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5710 }, {
5711 'note': 'even larger playlist, 8832 videos',
5712 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5713 'only_matching': True,
5714 }, {
5715 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5716 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5717 'info_dict': {
5718 'title': 'Uploads from Interstellar Movie',
5719 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5720 'tags': [],
5721 'view_count': int,
5722 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
7666b936 5723 'channel_url': 'https://www.youtube.com/channel/UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5724 'channel': 'Interstellar Movie',
5725 'description': '',
5726 'modified_date': r're:\d{8}',
c26f9b99 5727 'availability': 'public',
7666b936 5728 'uploader_id': '@InterstellarMovie',
5729 'uploader': 'Interstellar Movie',
5730 'uploader_url': 'https://www.youtube.com/@InterstellarMovie',
a6213a49 5731 },
5732 'playlist_mincount': 21,
5733 }, {
5734 'note': 'Playlist with "show unavailable videos" button',
5735 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5736 'info_dict': {
5737 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5738 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5739 'view_count': int,
5740 'channel': 'Phim Siêu Nhân Nhật Bản',
5741 'tags': [],
976ae3ea 5742 'description': '',
5743 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5744 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5745 'modified_date': r're:\d{8}',
c26f9b99 5746 'availability': 'public',
7666b936 5747 'uploader_url': 'https://www.youtube.com/@phimsieunhannhatban',
5748 'uploader_id': '@phimsieunhannhatban',
5749 'uploader': 'Phim Siêu Nhân Nhật Bản',
a6213a49 5750 },
5751 'playlist_mincount': 200,
976ae3ea 5752 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5753 }, {
5754 'note': 'Playlist with unavailable videos in page 7',
5755 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5756 'info_dict': {
5757 'title': 'Uploads from BlankTV',
5758 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5759 'channel': 'BlankTV',
7666b936 5760 'channel_url': 'https://www.youtube.com/channel/UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5761 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5762 'view_count': int,
5763 'tags': [],
976ae3ea 5764 'modified_date': r're:\d{8}',
5765 'description': '',
c26f9b99 5766 'availability': 'public',
7666b936 5767 'uploader_id': '@blanktv',
5768 'uploader': 'BlankTV',
5769 'uploader_url': 'https://www.youtube.com/@blanktv',
a6213a49 5770 },
5771 'playlist_mincount': 1000,
976ae3ea 5772 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5773 }, {
5774 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5775 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5776 'info_dict': {
5777 'title': 'Data Analysis with Dr Mike Pound',
5778 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
a6213a49 5779 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5780 'tags': [],
5781 'view_count': int,
5782 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
7666b936 5783 'channel_url': 'https://www.youtube.com/channel/UC9-y-6csu5WGm29I7JiwpnA',
976ae3ea 5784 'channel': 'Computerphile',
c26f9b99 5785 'availability': 'public',
6141346d 5786 'modified_date': '20190712',
7666b936 5787 'uploader_id': '@Computerphile',
5788 'uploader': 'Computerphile',
5789 'uploader_url': 'https://www.youtube.com/@Computerphile',
a6213a49 5790 },
5791 'playlist_mincount': 11,
5792 }, {
5793 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5794 'only_matching': True,
5795 }, {
5796 'note': 'Playlist URL that does not actually serve a playlist',
5797 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5798 'info_dict': {
5799 'id': 'FqZTN594JQw',
5800 'ext': 'webm',
5801 'title': "Smiley's People 01 detective, Adventure Series, Action",
a6213a49 5802 'upload_date': '20150526',
5803 'license': 'Standard YouTube License',
5804 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5805 'categories': ['People & Blogs'],
5806 'tags': list,
5807 'view_count': int,
5808 'like_count': int,
a6213a49 5809 },
5810 'params': {
5811 'skip_download': True,
5812 },
5813 'skip': 'This video is not available.',
5814 'add_ie': [YoutubeIE.ie_key()],
5815 }, {
5816 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5817 'only_matching': True,
5818 }, {
5819 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5820 'only_matching': True,
5821 }, {
5822 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5823 'info_dict': {
14a14335 5824 'id': 'hGkQjiJLjWQ', # This will keep changing
a6213a49 5825 'ext': 'mp4',
976ae3ea 5826 'title': str,
a6213a49 5827 'upload_date': r're:\d{8}',
976ae3ea 5828 'description': str,
a6213a49 5829 'categories': ['News & Politics'],
5830 'tags': list,
5831 'like_count': int,
86973308 5832 'release_timestamp': int,
976ae3ea 5833 'channel': 'Sky News',
5834 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5835 'age_limit': 0,
5836 'view_count': int,
86973308 5837 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
976ae3ea 5838 'playable_in_embed': True,
86973308 5839 'release_date': r're:\d+',
976ae3ea 5840 'availability': 'public',
5841 'live_status': 'is_live',
5842 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
86973308
M
5843 'channel_follower_count': int,
5844 'concurrent_view_count': int,
7666b936 5845 'uploader_url': 'https://www.youtube.com/@SkyNews',
5846 'uploader_id': '@SkyNews',
5847 'uploader': 'Sky News',
8213ce28 5848 'channel_is_verified': True,
a6213a49 5849 },
5850 'params': {
5851 'skip_download': True,
5852 },
976ae3ea 5853 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5854 }, {
5855 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5856 'info_dict': {
5857 'id': 'a48o2S1cPoo',
5858 'ext': 'mp4',
5859 'title': 'The Young Turks - Live Main Show',
a6213a49 5860 'upload_date': '20150715',
5861 'license': 'Standard YouTube License',
5862 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5863 'categories': ['News & Politics'],
5864 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5865 'like_count': int,
a6213a49 5866 },
5867 'params': {
5868 'skip_download': True,
5869 },
5870 'only_matching': True,
5871 }, {
5872 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5873 'only_matching': True,
5874 }, {
5875 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5876 'only_matching': True,
5877 }, {
5878 'note': 'A channel that is not live. Should raise error',
5879 'url': 'https://www.youtube.com/user/numberphile/live',
5880 'only_matching': True,
5881 }, {
5882 'url': 'https://www.youtube.com/feed/trending',
5883 'only_matching': True,
5884 }, {
5885 'url': 'https://www.youtube.com/feed/library',
5886 'only_matching': True,
5887 }, {
5888 'url': 'https://www.youtube.com/feed/history',
5889 'only_matching': True,
5890 }, {
5891 'url': 'https://www.youtube.com/feed/subscriptions',
5892 'only_matching': True,
5893 }, {
5894 'url': 'https://www.youtube.com/feed/watch_later',
5895 'only_matching': True,
5896 }, {
5897 'note': 'Recommended - redirects to home page.',
5898 'url': 'https://www.youtube.com/feed/recommended',
5899 'only_matching': True,
5900 }, {
5901 'note': 'inline playlist with not always working continuations',
5902 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5903 'only_matching': True,
5904 }, {
5905 'url': 'https://www.youtube.com/course',
5906 'only_matching': True,
5907 }, {
5908 'url': 'https://www.youtube.com/zsecurity',
5909 'only_matching': True,
5910 }, {
5911 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5912 'only_matching': True,
5913 }, {
5914 'url': 'https://www.youtube.com/TheYoungTurks/live',
5915 'only_matching': True,
5916 }, {
5917 'url': 'https://www.youtube.com/hashtag/cctv9',
5918 'info_dict': {
5919 'id': 'cctv9',
8828f457 5920 'title': 'cctv9 - All',
976ae3ea 5921 'tags': [],
a6213a49 5922 },
4dc23a80 5923 'playlist_mincount': 300, # not consistent but should be over 300
a6213a49 5924 }, {
5925 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5926 'only_matching': True,
5927 }, {
5928 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5929 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5930 'only_matching': True
5931 }, {
5932 'note': '/browse/ should redirect to /channel/',
5933 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5934 'only_matching': True
5935 }, {
5936 'note': 'VLPL, should redirect to playlist?list=PL...',
5937 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5938 'info_dict': {
5939 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
a6213a49 5940 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
12a1b225 5941 'title': 'NCS : All Releases 💿',
7666b936 5942 'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
976ae3ea 5943 'modified_date': r're:\d{8}',
5944 'view_count': int,
5945 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5946 'tags': [],
5947 'channel': 'NoCopyrightSounds',
c26f9b99 5948 'availability': 'public',
7666b936 5949 'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds',
5950 'uploader': 'NoCopyrightSounds',
5951 'uploader_id': '@NoCopyrightSounds',
a6213a49 5952 },
5953 'playlist_mincount': 166,
7666b936 5954 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden', 'YouTube Music is not directly supported'],
a6213a49 5955 }, {
7666b936 5956 # TODO: fix 'unviewable' issue with this playlist when reloading with unavailable videos
a6213a49 5957 'note': 'Topic, should redirect to playlist?list=UU...',
5958 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5959 'info_dict': {
5960 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5961 'title': 'Uploads from Royalty Free Music - Topic',
976ae3ea 5962 'tags': [],
5963 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5964 'channel': 'Royalty Free Music - Topic',
5965 'view_count': int,
5966 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
976ae3ea 5967 'modified_date': r're:\d{8}',
976ae3ea 5968 'description': '',
c26f9b99 5969 'availability': 'public',
7666b936 5970 'uploader': 'Royalty Free Music - Topic',
a6213a49 5971 },
a6213a49 5972 'playlist_mincount': 101,
7666b936 5973 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5974 }, {
86973308
M
5975 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5976 # Treat as a general feed
a6213a49 5977 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5978 'info_dict': {
5979 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5980 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5981 'tags': [],
a6213a49 5982 },
a6213a49 5983 'playlist_mincount': 9,
5984 }, {
5985 'note': 'Youtube music Album',
5986 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5987 'info_dict': {
5988 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5989 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5990 'tags': [],
5991 'view_count': int,
5992 'description': '',
5993 'availability': 'unlisted',
5994 'modified_date': r're:\d{8}',
a6213a49 5995 },
5996 'playlist_count': 50,
7666b936 5997 'expected_warnings': ['YouTube Music is not directly supported'],
a6213a49 5998 }, {
5999 'note': 'unlisted single video playlist',
6000 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
6001 'info_dict': {
a6213a49 6002 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
6003 'title': 'yt-dlp unlisted playlist test',
976ae3ea 6004 'availability': 'unlisted',
6005 'tags': [],
12a1b225 6006 'modified_date': '20220418',
976ae3ea 6007 'channel': 'colethedj',
6008 'view_count': int,
6009 'description': '',
976ae3ea 6010 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
6011 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
7666b936 6012 'uploader_url': 'https://www.youtube.com/@colethedj1894',
6013 'uploader_id': '@colethedj1894',
6014 'uploader': 'colethedj',
a6213a49 6015 },
93e12ed7 6016 'playlist': [{
6017 'info_dict': {
6018 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
6019 'id': 'BaW_jenozKc',
6020 '_type': 'url',
6021 'ie_key': 'Youtube',
6022 'duration': 10,
6023 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
6024 'channel_url': 'https://www.youtube.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
6025 'view_count': int,
6026 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc',
6027 'channel': 'Philipp Hagemeister',
6028 'uploader_id': '@PhilippHagemeister',
6029 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
6030 'uploader': 'Philipp Hagemeister',
6031 }
6032 }],
a6213a49 6033 'playlist_count': 1,
93e12ed7 6034 'params': {'extract_flat': True},
a6213a49 6035 }, {
6036 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
6037 'url': 'https://www.youtube.com/feed/recommended',
6038 'info_dict': {
6039 'id': 'recommended',
6040 'title': 'recommended',
6c73052c 6041 'tags': [],
a6213a49 6042 },
6043 'playlist_mincount': 50,
6044 'params': {
6045 'skip_download': True,
6046 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6047 },
6048 }, {
6049 'note': 'API Fallback: /videos tab, sorted by oldest first',
6050 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
6051 'info_dict': {
6052 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
6053 'title': 'Cody\'sLab - Videos',
6054 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
976ae3ea 6055 'channel': 'Cody\'sLab',
6056 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
6057 'tags': [],
6058 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 6059 'channel_follower_count': int
a6213a49 6060 },
6061 'playlist_mincount': 650,
6062 'params': {
6063 'skip_download': True,
6064 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6065 },
86973308 6066 'skip': 'Query for sorting no longer works',
a6213a49 6067 }, {
6068 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
6069 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
6070 'info_dict': {
6071 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 6072 'title': 'Uploads from Royalty Free Music - Topic',
976ae3ea 6073 'modified_date': r're:\d{8}',
6074 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
6075 'description': '',
6076 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
6077 'tags': [],
6078 'channel': 'Royalty Free Music - Topic',
6079 'view_count': int,
c26f9b99 6080 'availability': 'public',
7666b936 6081 'uploader': 'Royalty Free Music - Topic',
a6213a49 6082 },
a6213a49 6083 'playlist_mincount': 101,
6084 'params': {
6085 'skip_download': True,
6086 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6087 },
7666b936 6088 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
7c219ea6 6089 }, {
6090 'note': 'non-standard redirect to regional channel',
6091 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
6092 'only_matching': True
61d3665d 6093 }, {
6094 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
6095 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
6096 'info_dict': {
6097 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
6098 'modified_date': '20220407',
6099 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
6100 'tags': [],
61d3665d 6101 'availability': 'unlisted',
6102 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
6103 'channel': 'pukkandan',
6104 'description': 'Test for collaborative playlist',
6105 'title': 'yt-dlp test - collaborative playlist',
12a1b225 6106 'view_count': int,
7666b936 6107 'uploader_url': 'https://www.youtube.com/@pukkandan',
6108 'uploader_id': '@pukkandan',
6109 'uploader': 'pukkandan',
61d3665d 6110 },
6111 'playlist_mincount': 2
c26f9b99 6112 }, {
6113 'note': 'translated tab name',
6114 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
6115 'info_dict': {
6116 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6117 'tags': [],
c26f9b99 6118 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
4dc23a80 6119 'description': 'test description',
c26f9b99 6120 'title': 'cole-dlp-test-acc - 再生リスト',
c26f9b99 6121 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6122 'channel': 'cole-dlp-test-acc',
7666b936 6123 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6124 'uploader_id': '@coletdjnz',
6125 'uploader': 'cole-dlp-test-acc',
c26f9b99 6126 },
6127 'playlist_mincount': 1,
6128 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
6129 'expected_warnings': ['Preferring "ja"'],
6130 }, {
6131 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
6132 'note': 'preferred lang set with playlist with translated video titles',
6133 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
6134 'info_dict': {
6135 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
6136 'tags': [],
6137 'view_count': int,
6138 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
c26f9b99 6139 'channel': 'cole-dlp-test-acc',
6140 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6141 'description': 'test',
c26f9b99 6142 'title': 'dlp test playlist',
6143 'availability': 'public',
7666b936 6144 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6145 'uploader_id': '@coletdjnz',
6146 'uploader': 'cole-dlp-test-acc',
c26f9b99 6147 },
6148 'playlist_mincount': 1,
6149 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
6150 'expected_warnings': ['Preferring "ja"'],
80eb0bd9 6151 }, {
6152 # shorts audio pivot for 2GtVksBMYFM.
6153 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
6154 'info_dict': {
6155 'id': 'sfv_audio_pivot',
6156 'title': 'sfv_audio_pivot',
6157 'tags': [],
6158 },
6159 'playlist_mincount': 50,
6160
86973308
M
6161 }, {
6162 # Channel with a real live tab (not to be mistaken with streams tab)
6163 # Do not treat like it should redirect to live stream
6164 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
6165 'info_dict': {
6166 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
6167 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
6168 'tags': [],
6169 },
6170 'playlist_mincount': 20,
6171 }, {
6172 # Tab name is not the same as tab id
6173 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
6174 'info_dict': {
6175 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6176 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
6177 'tags': [],
6178 },
6179 'playlist_mincount': 8,
6180 }, {
6181 # Home tab id is literally home. Not to get mistaken with featured
6182 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
6183 'info_dict': {
6184 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6185 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
6186 'tags': [],
6187 },
6188 'playlist_mincount': 8,
6189 }, {
6190 # Should get three playlists for videos, shorts and streams tabs
6191 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
6192 'info_dict': {
6193 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
bd7e919a 6194 'title': 'Polka Ch. 尾丸ポルカ',
6195 'channel_follower_count': int,
6196 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
6197 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
8828f457 6198 'description': 'md5:49809d8bf9da539bc48ed5d1f83c33f2',
bd7e919a 6199 'channel': 'Polka Ch. 尾丸ポルカ',
6200 'tags': 'count:35',
7666b936 6201 'uploader_url': 'https://www.youtube.com/@OmaruPolka',
6202 'uploader': 'Polka Ch. 尾丸ポルカ',
6203 'uploader_id': '@OmaruPolka',
8828f457 6204 'channel_is_verified': True,
86973308
M
6205 },
6206 'playlist_count': 3,
6207 }, {
6208 # Shorts tab with channel with handle
7666b936 6209 # TODO: fix channel description
86973308
M
6210 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
6211 'info_dict': {
6212 'id': 'UC0intLFzLaudFG-xAvUEO-A',
6213 'title': 'Not Just Bikes - Shorts',
8828f457 6214 'tags': 'count:10',
86973308 6215 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
8828f457 6216 'description': 'md5:5e82545b3a041345927a92d0585df247',
86973308 6217 'channel_follower_count': int,
86973308 6218 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
86973308 6219 'channel': 'Not Just Bikes',
7666b936 6220 'uploader_url': 'https://www.youtube.com/@NotJustBikes',
6221 'uploader': 'Not Just Bikes',
6222 'uploader_id': '@NotJustBikes',
8828f457 6223 'channel_is_verified': True,
86973308
M
6224 },
6225 'playlist_mincount': 10,
6226 }, {
6227 # Streams tab
6228 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
6229 'info_dict': {
6230 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6231 'title': '中村悠一 - Live',
6232 'tags': 'count:7',
6233 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6234 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
86973308 6235 'channel': '中村悠一',
86973308 6236 'channel_follower_count': int,
86973308 6237 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
7666b936 6238 'uploader_url': 'https://www.youtube.com/@Yuichi-Nakamura',
6239 'uploader_id': '@Yuichi-Nakamura',
6240 'uploader': '中村悠一',
86973308
M
6241 },
6242 'playlist_mincount': 60,
6243 }, {
6244 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
6245 # See test_youtube_lists
6246 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
6247 'only_matching': True,
6248 }, {
6249 # No uploads and no UCID given. Should fail with no uploads error
6250 # See test_youtube_lists
6251 'url': 'https://www.youtube.com/news',
6252 'only_matching': True
6253 }, {
6254 # No videos tab but has a shorts tab
6255 'url': 'https://www.youtube.com/c/TKFShorts',
6256 'info_dict': {
6257 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6258 'title': 'Shorts Break - Shorts',
7666b936 6259 'tags': 'count:48',
86973308
M
6260 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6261 'channel': 'Shorts Break',
7666b936 6262 'description': 'md5:6de33c5e7ba686e5f3efd4e19c7ef499',
86973308 6263 'channel_follower_count': int,
86973308 6264 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
7666b936 6265 'uploader_url': 'https://www.youtube.com/@ShortsBreak_Official',
6266 'uploader': 'Shorts Break',
6267 'uploader_id': '@ShortsBreak_Official',
86973308
M
6268 },
6269 'playlist_mincount': 30,
6270 }, {
6271 # Trending Now Tab. tab id is empty
6272 'url': 'https://www.youtube.com/feed/trending',
6273 'info_dict': {
6274 'id': 'trending',
6275 'title': 'trending - Now',
6276 'tags': [],
6277 },
6278 'playlist_mincount': 30,
6279 }, {
6280 # Trending Gaming Tab. tab id is empty
6281 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
6282 'info_dict': {
6283 'id': 'trending',
6284 'title': 'trending - Gaming',
6285 'tags': [],
6286 },
6287 'playlist_mincount': 30,
4dc23a80
M
6288 }, {
6289 # Shorts url result in shorts tab
7666b936 6290 # TODO: Fix channel id extraction
4dc23a80
M
6291 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6292 'info_dict': {
6293 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6294 'title': 'cole-dlp-test-acc - Shorts',
4dc23a80 6295 'channel': 'cole-dlp-test-acc',
4dc23a80
M
6296 'description': 'test description',
6297 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6298 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6299 'tags': [],
7666b936 6300 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6301 'uploader_id': '@coletdjnz',
4dc23a80 6302 'uploader': 'cole-dlp-test-acc',
4dc23a80
M
6303 },
6304 'playlist': [{
6305 'info_dict': {
7666b936 6306 # Channel data is not currently available for short renderers (as of 2023-03-01)
4dc23a80
M
6307 '_type': 'url',
6308 'ie_key': 'Youtube',
6309 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6310 'id': 'sSM9J5YH_60',
4dc23a80 6311 'title': 'SHORT short',
4dc23a80
M
6312 'view_count': int,
6313 'thumbnails': list,
6314 }
6315 }],
6316 'params': {'extract_flat': True},
6317 }, {
6318 # Live video status should be extracted
6319 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6320 'info_dict': {
6321 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6322 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6323 'tags': []
6324 },
6325 'playlist': [{
6326 'info_dict': {
6327 '_type': 'url',
6328 'ie_key': 'Youtube',
6329 'url': 'startswith:https://www.youtube.com/watch?v=',
6330 'id': str,
6331 'title': str,
6332 'live_status': 'is_live',
6333 'channel_id': str,
6334 'channel_url': str,
6335 'concurrent_view_count': int,
6336 'channel': str,
93e12ed7 6337 'uploader': str,
6338 'uploader_url': str,
14a14335 6339 'uploader_id': str,
8213ce28 6340 'channel_is_verified': bool, # this will keep changing
4dc23a80
M
6341 }
6342 }],
c7335551 6343 'params': {'extract_flat': True, 'playlist_items': '1'},
4dc23a80 6344 'playlist_mincount': 1
c7335551
M
6345 }, {
6346 # Channel renderer metadata. Contains number of videos on the channel
6347 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6348 'info_dict': {
6349 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6350 'title': 'cole-dlp-test-acc - Channels',
c7335551
M
6351 'channel': 'cole-dlp-test-acc',
6352 'description': 'test description',
6353 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6354 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6355 'tags': [],
7666b936 6356 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6357 'uploader_id': '@coletdjnz',
c7335551 6358 'uploader': 'cole-dlp-test-acc',
c7335551
M
6359 },
6360 'playlist': [{
6361 'info_dict': {
6362 '_type': 'url',
6363 'ie_key': 'YoutubeTab',
6364 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6365 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6366 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6367 'title': 'PewDiePie',
6368 'channel': 'PewDiePie',
6369 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6370 'thumbnails': list,
6371 'channel_follower_count': int,
7666b936 6372 'playlist_count': int,
6373 'uploader': 'PewDiePie',
6374 'uploader_url': 'https://www.youtube.com/@PewDiePie',
6375 'uploader_id': '@PewDiePie',
8213ce28 6376 'channel_is_verified': True,
c7335551
M
6377 }
6378 }],
6379 'params': {'extract_flat': True},
31e18355 6380 }, {
6381 'url': 'https://www.youtube.com/@3blue1brown/about',
6382 'info_dict': {
8828f457 6383 'id': '@3blue1brown',
31e18355 6384 'tags': ['Mathematics'],
8828f457 6385 'title': '3Blue1Brown',
31e18355 6386 'channel_follower_count': int,
6387 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
31e18355 6388 'channel': '3Blue1Brown',
31e18355 6389 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
8828f457 6390 'description': 'md5:4d1da95432004b7ba840ebc895b6b4c9',
7666b936 6391 'uploader_url': 'https://www.youtube.com/@3blue1brown',
6392 'uploader_id': '@3blue1brown',
6393 'uploader': '3Blue1Brown',
8213ce28 6394 'channel_is_verified': True,
31e18355 6395 },
6396 'playlist_count': 0,
447afb9e 6397 }, {
6398 # Podcasts tab, with rich entry playlistRenderers
6399 'url': 'https://www.youtube.com/@99percentinvisiblepodcast/podcasts',
6400 'info_dict': {
6401 'id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6402 'channel_id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6403 'uploader_url': 'https://www.youtube.com/@99percentinvisiblepodcast',
6404 'description': 'md5:3a0ed38f1ad42a68ef0428c04a15695c',
6405 'title': '99 Percent Invisible - Podcasts',
6406 'uploader': '99 Percent Invisible',
6407 'channel_follower_count': int,
6408 'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6409 'tags': [],
6410 'channel': '99 Percent Invisible',
6411 'uploader_id': '@99percentinvisiblepodcast',
6412 },
8828f457 6413 'playlist_count': 0,
447afb9e 6414 }, {
6415 # Releases tab, with rich entry playlistRenderers (same as Podcasts tab)
6416 'url': 'https://www.youtube.com/@AHimitsu/releases',
6417 'info_dict': {
6418 'id': 'UCgFwu-j5-xNJml2FtTrrB3A',
6419 'channel': 'A Himitsu',
6420 'uploader_url': 'https://www.youtube.com/@AHimitsu',
6421 'title': 'A Himitsu - Releases',
6422 'uploader_id': '@AHimitsu',
6423 'uploader': 'A Himitsu',
6424 'channel_id': 'UCgFwu-j5-xNJml2FtTrrB3A',
8828f457 6425 'tags': 'count:12',
447afb9e 6426 'description': 'I make music',
6427 'channel_url': 'https://www.youtube.com/channel/UCgFwu-j5-xNJml2FtTrrB3A',
6428 'channel_follower_count': int,
8213ce28 6429 'channel_is_verified': True,
447afb9e 6430 },
6431 'playlist_mincount': 10,
fcbc9ed7 6432 }, {
6433 # Playlist with only shorts, shown as reel renderers
6434 # FIXME: future: YouTube currently doesn't give continuation for this,
6435 # may do in future.
6436 'url': 'https://www.youtube.com/playlist?list=UUxqPAgubo4coVn9Lx1FuKcg',
6437 'info_dict': {
6438 'id': 'UUxqPAgubo4coVn9Lx1FuKcg',
6439 'channel_url': 'https://www.youtube.com/channel/UCxqPAgubo4coVn9Lx1FuKcg',
6440 'view_count': int,
6441 'uploader_id': '@BangyShorts',
6442 'description': '',
6443 'uploader_url': 'https://www.youtube.com/@BangyShorts',
6444 'channel_id': 'UCxqPAgubo4coVn9Lx1FuKcg',
6445 'channel': 'Bangy Shorts',
6446 'uploader': 'Bangy Shorts',
6447 'tags': [],
6448 'availability': 'public',
8828f457 6449 'modified_date': r're:\d{8}',
fcbc9ed7 6450 'title': 'Uploads from Bangy Shorts',
6451 },
6452 'playlist_mincount': 100,
6453 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
8828f457 6454 }, {
6455 'note': 'Tags containing spaces',
6456 'url': 'https://www.youtube.com/channel/UC7_YxT-KID8kRbqZo7MyscQ',
6457 'playlist_count': 3,
6458 'info_dict': {
6459 'id': 'UC7_YxT-KID8kRbqZo7MyscQ',
6460 'channel': 'Markiplier',
6461 'channel_id': 'UC7_YxT-KID8kRbqZo7MyscQ',
6462 'title': 'Markiplier',
6463 'channel_follower_count': int,
6464 'description': 'md5:0c010910558658824402809750dc5d97',
6465 'uploader_id': '@markiplier',
6466 'uploader_url': 'https://www.youtube.com/@markiplier',
6467 'uploader': 'Markiplier',
6468 'channel_url': 'https://www.youtube.com/channel/UC7_YxT-KID8kRbqZo7MyscQ',
6469 'channel_is_verified': True,
6470 'tags': ['markiplier', 'comedy', 'gaming', 'funny videos', 'funny moments',
6471 'sketch comedy', 'laughing', 'lets play', 'challenge videos', 'hilarious',
6472 'challenges', 'sketches', 'scary games', 'funny games', 'rage games',
6473 'mark fischbach'],
6474 },
a6213a49 6475 }]
6476
6477 @classmethod
6478 def suitable(cls, url):
86e5f3ed 6479 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 6480
86973308
M
6481 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6482
6483 def _get_url_mobj(self, url):
6484 mobj = self._URL_RE.match(url).groupdict()
6485 mobj.update((k, '') for k, v in mobj.items() if v is None)
6486 return mobj
6487
6488 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6489 tab_name = (tab.get('title') or '').lower()
6490 tab_url = urljoin(base_url, traverse_obj(
6491 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6492
bd7e919a 6493 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6494 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
86973308 6495 if tab_id:
bd7e919a 6496 return {
6497 'TAB_ID_SPONSORSHIPS': 'membership',
6498 }.get(tab_id, tab_id), tab_name
86973308
M
6499
6500 # Fallback to tab name if we cannot get the tab id.
6501 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6502 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
bd7e919a 6503 if tab_name:
6504 self.write_debug(f'Falling back to selected tab name: {tab_name}')
86973308
M
6505 return {
6506 'home': 'featured',
6507 'live': 'streams',
6508 }.get(tab_name, tab_name), tab_name
6509
6510 def _has_tab(self, tabs, tab_id):
6511 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
fe03a6cd 6512
044886c2 6513 def _empty_playlist(self, item_id, data):
6514 return self.playlist_result([], item_id, **self._extract_metadata_from_tabs(item_id, data))
6515
182bda88 6516 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6517 def _real_extract(self, url, smuggled_data):
cd7c66cf 6518 item_id = self._match_id(url)
14f25df2 6519 url = urllib.parse.urlunparse(
6520 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 6521 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 6522
86973308
M
6523 mobj = self._get_url_mobj(url)
6524 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
bd7e919a 6525 if is_channel and smuggled_data.get('is_music_url'):
6526 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6527 return self.url_result(
6528 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6529 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6530 mdata = self._extract_tab_endpoint(
6531 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6532 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6533 get_all=False, expected_type=str)
6534 if not murl:
6535 raise ExtractorError('Failed to resolve album to playlist')
6536 return self.url_result(murl, YoutubeTabIE)
6537 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6538 return self.url_result(
6539 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6540
6541 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
fe03a6cd 6542 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6543 url = f'{pre}/videos{post}'
5b28cef7 6544 if smuggled_data.get('is_music_url'):
6545 self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}')
cd7c66cf 6546
6547 # Handle both video/playlist URLs
201c1459 6548 qs = parse_qs(url)
bd7e919a 6549 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
fe03a6cd 6550 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 6551 if not playlist_id:
fe03a6cd 6552 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
bd7e919a 6553 raise ExtractorError('A video URL was given without video ID', expected=True)
fe03a6cd 6554 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 6555 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
bd7e919a 6556 return self.url_result(
6557 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
cd7c66cf 6558
86973308
M
6559 if not self._yes_playlist(playlist_id, video_id):
6560 return self.url_result(
6561 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6562
bd7e919a 6563 data, ytcfg = self._extract_data(url, display_id)
14fdfea9 6564
7c219ea6 6565 # YouTube may provide a non-standard redirect to the regional channel
6566 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
86973308 6567 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
7c219ea6 6568 redirect_url = traverse_obj(
6569 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6570 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6571 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
86973308
M
6572 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6573 return self.url_result(redirect_url, YoutubeTabIE)
7c219ea6 6574
bd7e919a 6575 tabs, extra_tabs = self._extract_tab_renderers(data), []
86973308 6576 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
18db7548 6577 selected_tab = self._extract_selected_tab(tabs)
86973308
M
6578 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6579 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6580
044886c2 6581 # /about is no longer a tab
6582 if original_tab_id == 'about':
6583 return self._empty_playlist(item_id, data)
6584
86973308 6585 if not original_tab_id and selected_tab_name:
bd7e919a 6586 self.to_screen('Downloading all uploads of the channel. '
86973308
M
6587 'To download only the videos in a specific tab, pass the tab\'s URL')
6588 if self._has_tab(tabs, 'streams'):
bd7e919a 6589 extra_tabs.append(''.join((pre, '/streams', post)))
86973308 6590 if self._has_tab(tabs, 'shorts'):
bd7e919a 6591 extra_tabs.append(''.join((pre, '/shorts', post)))
86973308
M
6592 # XXX: Members-only tab should also be extracted
6593
bd7e919a 6594 if not extra_tabs and selected_tab_id != 'videos':
86973308
M
6595 # Channel does not have streams, shorts or videos tabs
6596 if item_id[:2] != 'UC':
044886c2 6597 return self._empty_playlist(item_id, data)
86973308
M
6598
6599 # Topic channels don't have /videos. Use the equivalent playlist instead
6600 pl_id = f'UU{item_id[2:]}'
6601 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6602 try:
6603 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6604 except ExtractorError:
044886c2 6605 return self._empty_playlist(item_id, data)
64f36541 6606 else:
86973308
M
6607 item_id, url = pl_id, pl_url
6608 self.to_screen(
6609 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6610
bd7e919a 6611 elif extra_tabs and selected_tab_id != 'videos':
86973308 6612 # When there are shorts/live tabs but not videos tab
bd7e919a 6613 url, data = f'{pre}{post}', None
86973308
M
6614
6615 elif (original_tab_id or 'videos') != selected_tab_id:
6616 if original_tab_id == 'live':
6617 # Live tab should have redirected to the video
6618 # Except in the case the channel has an actual live tab
6619 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
bd7e919a 6620 raise UserNotLive(video_id=item_id)
86973308
M
6621 elif selected_tab_name:
6622 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6623
6624 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6625 url = f'{pre}{post}'
18db7548 6626
358de58c 6627 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 6628 if 'no-youtube-unavailable-videos' not in compat_opts:
bd7e919a 6629 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
c0ac49bc 6630 self._extract_and_report_alerts(data, only_once=True)
86973308 6631
bd7e919a 6632 tabs, entries = self._extract_tab_renderers(data), []
8bdd16b4 6633 if tabs:
bd7e919a 6634 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6635 entries[0].update({
86973308
M
6636 'extractor_key': YoutubeTabIE.ie_key(),
6637 'extractor': YoutubeTabIE.IE_NAME,
6638 'webpage_url': url,
6639 })
bd7e919a 6640 if self.get_param('playlist_items') == '0':
6641 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6642 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6643 entries.extend(map(self._real_extract, extra_tabs))
6644
6645 if len(entries) == 1:
6646 return entries[0]
6647 elif entries:
6648 metadata = self._extract_metadata_from_tabs(item_id, data)
6649 uploads_url = 'the Uploads (UU) playlist URL'
6650 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6651 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6652 self.to_screen(
6653 'Downloading as multiple playlists, separated by tabs. '
6654 f'To download as a single playlist instead, pass {uploads_url}')
6655 return self.playlist_result(entries, item_id, **metadata)
6656
6657 # Inline playlist
37e57a9f 6658 playlist = traverse_obj(
6659 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 6660 if playlist:
ac56cf38 6661 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 6662
37e57a9f 6663 video_id = traverse_obj(
6664 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 6665 if video_id:
bd7e919a 6666 if tab != '/live': # live tab is expected to redirect to video
37e57a9f 6667 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
86973308 6668 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6669
8bdd16b4 6670 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 6671
c5e8d7af 6672
8bdd16b4 6673class YoutubePlaylistIE(InfoExtractor):
96565c7e 6674 IE_DESC = 'YouTube playlists'
8bdd16b4 6675 _VALID_URL = r'''(?x)(?:
6676 (?:https?://)?
6677 (?:\w+\.)?
6678 (?:
6679 (?:
6680 youtube(?:kids)?\.com|
d9190e44 6681 %(invidious)s
8bdd16b4 6682 )
6683 /.*?\?.*?\blist=
6684 )?
6685 (?P<id>%(playlist_id)s)
d9190e44
RH
6686 )''' % {
6687 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6688 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6689 }
8bdd16b4 6690 IE_NAME = 'youtube:playlist'
cdc628a4 6691 _TESTS = [{
8bdd16b4 6692 'note': 'issue #673',
6693 'url': 'PLBB231211A4F62143',
cdc628a4 6694 'info_dict': {
8bdd16b4 6695 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6696 'id': 'PLBB231211A4F62143',
976ae3ea 6697 'uploader': 'Wickman',
7666b936 6698 'uploader_id': '@WickmanVT',
11f9be09 6699 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 6700 'view_count': int,
7666b936 6701 'uploader_url': 'https://www.youtube.com/@WickmanVT',
976ae3ea 6702 'modified_date': r're:\d{8}',
6703 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6704 'channel': 'Wickman',
6705 'tags': [],
7666b936 6706 'channel_url': 'https://www.youtube.com/channel/UCKSpbfbl5kRQpTdL7kMc-1Q',
86973308 6707 'availability': 'public',
8bdd16b4 6708 },
6709 'playlist_mincount': 29,
6710 }, {
6711 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6712 'info_dict': {
6713 'title': 'YDL_safe_search',
6714 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6715 },
6716 'playlist_count': 2,
6717 'skip': 'This playlist is private',
9558dcec 6718 }, {
8bdd16b4 6719 'note': 'embedded',
6720 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6721 'playlist_count': 4,
9558dcec 6722 'info_dict': {
8bdd16b4 6723 'title': 'JODA15',
6724 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6725 'uploader': 'milan',
7666b936 6726 'uploader_id': '@milan5503',
976ae3ea 6727 'description': '',
6728 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6729 'tags': [],
6730 'modified_date': '20140919',
6731 'view_count': int,
6732 'channel': 'milan',
6733 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
7666b936 6734 'uploader_url': 'https://www.youtube.com/@milan5503',
c26f9b99 6735 'availability': 'public',
976ae3ea 6736 },
b012271d 6737 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden', 'Retrying', 'Giving up'],
cdc628a4 6738 }, {
8bdd16b4 6739 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 6740 'playlist_mincount': 455,
8bdd16b4 6741 'info_dict': {
6742 'title': '2018 Chinese New Singles (11/6 updated)',
6743 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6744 'uploader': 'LBK',
7666b936 6745 'uploader_id': '@music_king',
11f9be09 6746 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 6747 'channel': 'LBK',
6748 'view_count': int,
7666b936 6749 'channel_url': 'https://www.youtube.com/channel/UC21nz3_MesPLqtDqwdvnoxA',
976ae3ea 6750 'tags': [],
7666b936 6751 'uploader_url': 'https://www.youtube.com/@music_king',
976ae3ea 6752 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6753 'modified_date': r're:\d{8}',
c26f9b99 6754 'availability': 'public',
976ae3ea 6755 },
6756 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 6757 }, {
29f7c58a 6758 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6759 'only_matching': True,
6760 }, {
6761 # music album playlist
6762 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6763 'only_matching': True,
6764 }]
6765
6766 @classmethod
6767 def suitable(cls, url):
201c1459 6768 if YoutubeTabIE.suitable(url):
6769 return False
49a57e70 6770 from ..utils import parse_qs
201c1459 6771 qs = parse_qs(url)
6772 if qs.get('v', [None])[0]:
6773 return False
86e5f3ed 6774 return super().suitable(url)
29f7c58a 6775
6776 def _real_extract(self, url):
6777 playlist_id = self._match_id(url)
46953e7e 6778 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 6779 url = update_url_query(
6780 'https://www.youtube.com/playlist',
6781 parse_qs(url) or {'list': playlist_id})
6782 if is_music_url:
6783 url = smuggle_url(url, {'is_music_url': True})
6784 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 6785
6786
6787class YoutubeYtBeIE(InfoExtractor):
c76eb41b 6788 IE_DESC = 'youtu.be'
29f7c58a 6789 _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}
6790 _TESTS = [{
8bdd16b4 6791 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6792 'info_dict': {
6793 'id': 'yeWKywCrFtk',
6794 'ext': 'mp4',
6795 'title': 'Small Scale Baler and Braiding Rugs',
6796 'uploader': 'Backus-Page House Museum',
7666b936 6797 'uploader_id': '@backuspagemuseum',
6798 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@backuspagemuseum',
8bdd16b4 6799 'upload_date': '20161008',
6800 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6801 'categories': ['Nonprofits & Activism'],
6802 'tags': list,
6803 'like_count': int,
976ae3ea 6804 'age_limit': 0,
6805 'playable_in_embed': True,
7666b936 6806 'thumbnail': r're:^https?://.*\.webp',
976ae3ea 6807 'channel': 'Backus-Page House Museum',
6808 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6809 'live_status': 'not_live',
6810 'view_count': int,
6811 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6812 'availability': 'public',
6813 'duration': 59,
12a1b225
A
6814 'comment_count': int,
6815 'channel_follower_count': int
8bdd16b4 6816 },
6817 'params': {
6818 'noplaylist': True,
6819 'skip_download': True,
6820 },
39e7107d 6821 }, {
8bdd16b4 6822 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 6823 'only_matching': True,
cdc628a4
PH
6824 }]
6825
8bdd16b4 6826 def _real_extract(self, url):
5ad28e7f 6827 mobj = self._match_valid_url(url)
29f7c58a 6828 video_id = mobj.group('id')
6829 playlist_id = mobj.group('playlist_id')
8bdd16b4 6830 return self.url_result(
29f7c58a 6831 update_url_query('https://www.youtube.com/watch', {
6832 'v': video_id,
6833 'list': playlist_id,
6834 'feature': 'youtu.be',
6835 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 6836
6837
b6ce9bb0 6838class YoutubeLivestreamEmbedIE(InfoExtractor):
6839 IE_DESC = 'YouTube livestream embeds'
6840 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6841 _TESTS = [{
6842 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6843 'only_matching': True,
6844 }]
6845
6846 def _real_extract(self, url):
6847 channel_id = self._match_id(url)
6848 return self.url_result(
6849 f'https://www.youtube.com/channel/{channel_id}/live',
6850 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6851
6852
8bdd16b4 6853class YoutubeYtUserIE(InfoExtractor):
96565c7e 6854 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 6855 IE_NAME = 'youtube:user'
8bdd16b4 6856 _VALID_URL = r'ytuser:(?P<id>.+)'
6857 _TESTS = [{
6858 'url': 'ytuser:phihag',
6859 'only_matching': True,
6860 }]
6861
6862 def _real_extract(self, url):
6863 user_id = self._match_id(url)
08270da5 6864 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
9558dcec 6865
b05654f0 6866
3d3dddc9 6867class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 6868 IE_NAME = 'youtube:favorites'
96565c7e 6869 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 6870 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6871 _LOGIN_REQUIRED = True
6872 _TESTS = [{
6873 'url': ':ytfav',
6874 'only_matching': True,
6875 }, {
6876 'url': ':ytfavorites',
6877 'only_matching': True,
6878 }]
6879
6880 def _real_extract(self, url):
6881 return self.url_result(
6882 'https://www.youtube.com/playlist?list=LL',
6883 ie=YoutubeTabIE.ie_key())
6884
6885
ca5300c7 6886class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6887 IE_NAME = 'youtube:notif'
6888 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6889 _VALID_URL = r':ytnotif(?:ication)?s?'
6890 _LOGIN_REQUIRED = True
6891 _TESTS = [{
6892 'url': ':ytnotif',
6893 'only_matching': True,
6894 }, {
6895 'url': ':ytnotifications',
6896 'only_matching': True,
6897 }]
6898
6899 def _extract_notification_menu(self, response, continuation_list):
6900 notification_list = traverse_obj(
6901 response,
6902 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6903 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6904 expected_type=list) or []
6905 continuation_list[0] = None
6906 for item in notification_list:
6907 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6908 if entry:
6909 yield entry
6910 continuation = item.get('continuationItemRenderer')
6911 if continuation:
6912 continuation_list[0] = continuation
6913
6914 def _extract_notification_renderer(self, notification):
6915 video_id = traverse_obj(
6916 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6917 url = f'https://www.youtube.com/watch?v={video_id}'
6918 channel_id = None
6919 if not video_id:
6920 browse_ep = traverse_obj(
6921 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
7666b936 6922 channel_id = self.ucid_or_none(traverse_obj(browse_ep, 'browseId', expected_type=str))
ca5300c7 6923 post_id = self._search_regex(
6924 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6925 'post id', default=None)
6926 if not channel_id or not post_id:
6927 return
6928 # The direct /post url redirects to this in the browser
6929 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6930
6931 channel = traverse_obj(
6932 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6933 expected_type=str)
c7a7baaa 6934 notification_title = self._get_text(notification, 'shortMessage')
6935 if notification_title:
6936 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6937 # TODO: handle recommended videos
ca5300c7 6938 title = self._search_regex(
c7a7baaa 6939 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 6940 'video title', default=None)
5225df50 6941 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6942 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6943 else None)
ca5300c7 6944 return {
6945 '_type': 'url',
6946 'url': url,
6947 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6948 'video_id': video_id,
6949 'title': title,
6950 'channel_id': channel_id,
6951 'channel': channel,
7666b936 6952 'uploader': channel,
ca5300c7 6953 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5225df50 6954 'timestamp': timestamp,
ca5300c7 6955 }
6956
6957 def _notification_menu_entries(self, ytcfg):
6958 continuation_list = [None]
6959 response = None
6960 for page in itertools.count(1):
6961 ctoken = traverse_obj(
6962 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6963 response = self._extract_response(
6964 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6965 ep='notification/get_notification_menu', check_get_keys='actions',
6966 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6967 yield from self._extract_notification_menu(response, continuation_list)
6968 if not continuation_list[0]:
6969 break
6970
6971 def _real_extract(self, url):
6972 display_id = 'notifications'
6973 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6974 self._report_playlist_authcheck(ytcfg)
6975 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6976
6977
a6213a49 6978class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6979 IE_DESC = 'YouTube search'
78caa52a 6980 IE_NAME = 'youtube:search'
b05654f0 6981 _SEARCH_KEY = 'ytsearch'
17d248a5 6982 _SEARCH_PARAMS = 'EgIQAfABAQ==' # Videos only
84bbc545 6983 _TESTS = [{
6984 'url': 'ytsearch5:youtube-dl test video',
6985 'playlist_count': 5,
6986 'info_dict': {
6987 'id': 'youtube-dl test video',
6988 'title': 'youtube-dl test video',
6989 }
17d248a5
AB
6990 }, {
6991 'note': 'Suicide/self-harm search warning',
6992 'url': 'ytsearch1:i hate myself and i wanna die',
6993 'playlist_count': 1,
6994 'info_dict': {
6995 'id': 'i hate myself and i wanna die',
6996 'title': 'i hate myself and i wanna die',
6997 }
84bbc545 6998 }]
b05654f0 6999
a61fd4cf 7000
5f7cb91a 7001class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 7002 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 7003 _SEARCH_KEY = 'ytsearchdate'
a6213a49 7004 IE_DESC = 'YouTube search, newest videos first'
17d248a5 7005 _SEARCH_PARAMS = 'CAISAhAB8AEB' # Videos only, sorted by date
84bbc545 7006 _TESTS = [{
7007 'url': 'ytsearchdate5:youtube-dl test video',
7008 'playlist_count': 5,
7009 'info_dict': {
7010 'id': 'youtube-dl test video',
7011 'title': 'youtube-dl test video',
7012 }
7013 }]
75dff0ee 7014
c9ae7b95 7015
a6213a49 7016class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 7017 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 7018 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 7019 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 7020 _TESTS = [{
7021 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
7022 'playlist_mincount': 5,
7023 'info_dict': {
11f9be09 7024 'id': 'youtube-dl test video',
3462ffa8 7025 'title': 'youtube-dl test video',
7026 }
a61fd4cf 7027 }, {
7028 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
7029 'playlist_mincount': 5,
7030 'info_dict': {
7031 'id': 'python',
7032 'title': 'python',
7033 }
ad210f4f 7034 }, {
7035 'url': 'https://www.youtube.com/results?search_query=%23cats',
7036 'playlist_mincount': 1,
7037 'info_dict': {
7038 'id': '#cats',
7039 'title': '#cats',
12a1b225
A
7040 # The test suite does not have support for nested playlists
7041 # 'entries': [{
7042 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
7043 # 'title': '#cats',
7044 # }],
ad210f4f 7045 },
c7335551
M
7046 }, {
7047 # Channel results
7048 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
7049 'info_dict': {
7050 'id': 'kurzgesagt',
7051 'title': 'kurzgesagt',
7052 },
7053 'playlist': [{
7054 'info_dict': {
7055 '_type': 'url',
7056 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
7057 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
7058 'ie_key': 'YoutubeTab',
7059 'channel': 'Kurzgesagt – In a Nutshell',
7060 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
7061 'title': 'Kurzgesagt – In a Nutshell',
7062 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
14a14335 7063 # No longer available for search as it is set to the handle.
7064 # 'playlist_count': int,
c7335551 7065 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
7666b936 7066 'thumbnails': list,
7067 'uploader_id': '@kurzgesagt',
7068 'uploader_url': 'https://www.youtube.com/@kurzgesagt',
7069 'uploader': 'Kurzgesagt – In a Nutshell',
8213ce28 7070 'channel_is_verified': True,
14a14335 7071 'channel_follower_count': int,
c7335551
M
7072 }
7073 }],
7074 'params': {'extract_flat': True, 'playlist_items': '1'},
7075 'playlist_mincount': 1,
3462ffa8 7076 }, {
7077 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
7078 'only_matching': True,
7079 }]
7080
7081 def _real_extract(self, url):
4dfbf869 7082 qs = parse_qs(url)
386e1dd9 7083 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 7084 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 7085
7086
16aa9ea4 7087class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 7088 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 7089 IE_NAME = 'youtube:music:search_url'
7090 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
7091 _TESTS = [{
7092 'url': 'https://music.youtube.com/search?q=royalty+free+music',
7093 'playlist_count': 16,
7094 'info_dict': {
7095 'id': 'royalty free music',
7096 'title': 'royalty free music',
7097 }
7098 }, {
7099 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
7100 'playlist_mincount': 30,
7101 'info_dict': {
7102 'id': 'royalty free music - songs',
7103 'title': 'royalty free music - songs',
7104 },
7105 'params': {'extract_flat': 'in_playlist'}
7106 }, {
7107 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
7108 'playlist_mincount': 30,
7109 'info_dict': {
7110 'id': 'royalty free music - community playlists',
7111 'title': 'royalty free music - community playlists',
7112 },
7113 'params': {'extract_flat': 'in_playlist'}
7114 }]
7115
7116 _SECTIONS = {
7117 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
7118 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
7119 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
7120 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
7121 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
7122 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
7123 }
7124
7125 def _real_extract(self, url):
7126 qs = parse_qs(url)
7127 query = (qs.get('search_query') or qs.get('q'))[0]
7128 params = qs.get('sp', (None,))[0]
7129 if params:
7130 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
7131 else:
ac668111 7132 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 7133 params = self._SECTIONS.get(section)
7134 if not params:
7135 section = None
7136 title = join_nonempty(query, section, delim=' - ')
af5c1c55 7137 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 7138
7139
182bda88 7140class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 7141 """
25f14e9f 7142 Base class for feed extractors
82d02080 7143 Subclasses must re-define the _FEED_NAME property.
d7ae0639 7144 """
b2e8bc1b 7145 _LOGIN_REQUIRED = True
82d02080 7146 _FEED_NAME = 'feeds'
a25bca9f 7147
7148 def _real_initialize(self):
7149 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 7150
82d02080 7151 @classproperty
d7ae0639 7152 def IE_NAME(self):
82d02080 7153 return f'youtube:{self._FEED_NAME}'
04cc9617 7154
3853309f 7155 def _real_extract(self, url):
3d3dddc9 7156 return self.url_result(
182bda88 7157 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
7158
7159
ef2f3c7f 7160class YoutubeWatchLaterIE(InfoExtractor):
7161 IE_NAME = 'youtube:watchlater'
96565c7e 7162 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 7163 _VALID_URL = r':ytwatchlater'
bc7a9cd8 7164 _TESTS = [{
8bdd16b4 7165 'url': ':ytwatchlater',
bc7a9cd8
S
7166 'only_matching': True,
7167 }]
25f14e9f
S
7168
7169 def _real_extract(self, url):
ef2f3c7f 7170 return self.url_result(
7171 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 7172
7173
25f14e9f 7174class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 7175 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 7176 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 7177 _FEED_NAME = 'recommended'
45db527f 7178 _LOGIN_REQUIRED = False
3d3dddc9 7179 _TESTS = [{
7180 'url': ':ytrec',
7181 'only_matching': True,
7182 }, {
7183 'url': ':ytrecommended',
7184 'only_matching': True,
7185 }, {
7186 'url': 'https://youtube.com',
7187 'only_matching': True,
7188 }]
1ed5b5c9 7189
1ed5b5c9 7190
25f14e9f 7191class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 7192 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 7193 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 7194 _FEED_NAME = 'subscriptions'
3d3dddc9 7195 _TESTS = [{
7196 'url': ':ytsubs',
7197 'only_matching': True,
7198 }, {
7199 'url': ':ytsubscriptions',
7200 'only_matching': True,
7201 }]
1ed5b5c9 7202
1ed5b5c9 7203
25f14e9f 7204class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 7205 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 7206 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 7207 _FEED_NAME = 'history'
3d3dddc9 7208 _TESTS = [{
7209 'url': ':ythistory',
7210 'only_matching': True,
7211 }]
1ed5b5c9
JMF
7212
7213
80eb0bd9 7214class YoutubeShortsAudioPivotIE(InfoExtractor):
1dd18a88 7215 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
80eb0bd9 7216 IE_NAME = 'youtube:shorts:pivot:audio'
1dd18a88 7217 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
80eb0bd9 7218 _TESTS = [{
1dd18a88 7219 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
80eb0bd9 7220 'only_matching': True,
7221 }]
7222
7223 @staticmethod
7224 def _generate_audio_pivot_params(video_id):
7225 """
7226 Generates sfv_audio_pivot browse params for this video id
7227 """
7228 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
7229 return urllib.parse.quote(base64.b64encode(pb_params).decode())
7230
7231 def _real_extract(self, url):
7232 video_id = self._match_id(url)
7233 return self.url_result(
7234 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
7235 ie=YoutubeTabIE)
7236
7237
15870e90
PH
7238class YoutubeTruncatedURLIE(InfoExtractor):
7239 IE_NAME = 'youtube:truncated_url'
7240 IE_DESC = False # Do not list
975d35db 7241 _VALID_URL = r'''(?x)
b95aab84
PH
7242 (?:https?://)?
7243 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
7244 (?:watch\?(?:
c4808c60 7245 feature=[a-z_]+|
b95aab84
PH
7246 annotation_id=annotation_[^&]+|
7247 x-yt-cl=[0-9]+|
c1708b89 7248 hl=[^&]*|
287be8c6 7249 t=[0-9]+
b95aab84
PH
7250 )?
7251 |
7252 attribution_link\?a=[^&]+
7253 )
7254 $
975d35db 7255 '''
15870e90 7256
c4808c60 7257 _TESTS = [{
2d3d2997 7258 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 7259 'only_matching': True,
dc2fc736 7260 }, {
2d3d2997 7261 'url': 'https://www.youtube.com/watch?',
dc2fc736 7262 'only_matching': True,
b95aab84
PH
7263 }, {
7264 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
7265 'only_matching': True,
7266 }, {
7267 'url': 'https://www.youtube.com/watch?feature=foo',
7268 'only_matching': True,
c1708b89
PH
7269 }, {
7270 'url': 'https://www.youtube.com/watch?hl=en-GB',
7271 'only_matching': True,
287be8c6
PH
7272 }, {
7273 'url': 'https://www.youtube.com/watch?t=2372',
7274 'only_matching': True,
c4808c60
PH
7275 }]
7276
15870e90
PH
7277 def _real_extract(self, url):
7278 raise ExtractorError(
78caa52a
PH
7279 'Did you forget to quote the URL? Remember that & is a meta '
7280 'character in most shells, so you want to put the URL in quotes, '
3867038a 7281 'like youtube-dl '
2d3d2997 7282 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 7283 ' or simply youtube-dl BaW_jenozKc .',
15870e90 7284 expected=True)
772fd5cc
PH
7285
7286
471d0367 7287class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 7288 IE_NAME = 'youtube:clip'
471d0367 7289 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
7290 _TESTS = [{
7291 # FIXME: Other metadata should be extracted from the clip, not from the base video
7292 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
7293 'info_dict': {
7294 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
7295 'ext': 'mp4',
7296 'section_start': 29.0,
7297 'section_end': 39.7,
7298 'duration': 10.7,
12a1b225
A
7299 'age_limit': 0,
7300 'availability': 'public',
7301 'categories': ['Gaming'],
7302 'channel': 'Scott The Woz',
7303 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
7304 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
7305 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
7306 'like_count': int,
7307 'playable_in_embed': True,
7308 'tags': 'count:17',
7309 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
7310 'title': 'Mobile Games on Console - Scott The Woz',
7311 'upload_date': '20210920',
7312 'uploader': 'Scott The Woz',
7666b936 7313 'uploader_id': '@ScottTheWoz',
7314 'uploader_url': 'https://www.youtube.com/@ScottTheWoz',
12a1b225
A
7315 'view_count': int,
7316 'live_status': 'not_live',
7666b936 7317 'channel_follower_count': int,
7318 'chapters': 'count:20',
14a14335 7319 'comment_count': int,
7320 'heatmap': 'count:100',
471d0367 7321 }
7322 }]
3cd786db 7323
7324 def _real_extract(self, url):
471d0367 7325 clip_id = self._match_id(url)
7326 _, data = self._extract_webpage(url, clip_id)
7327
7328 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
7329 if not video_id:
7330 raise ExtractorError('Unable to find video ID')
7331
7332 clip_data = traverse_obj(data, (
7333 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
7334 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
7335 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
7336 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
7337
7338 return {
7339 '_type': 'url_transparent',
7340 'url': f'https://www.youtube.com/watch?v={video_id}',
7341 'ie_key': YoutubeIE.ie_key(),
7342 'id': clip_id,
7343 'section_start': int(clip_data['startTimeMs']) / 1000,
7344 'section_end': int(clip_data['endTimeMs']) / 1000,
7345 }
3cd786db 7346
7347
b032ff0f 7348class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
7349 IE_NAME = 'youtube:consent'
7350 IE_DESC = False # Do not list
7351 _VALID_URL = r'https?://consent\.youtube\.com/m\?'
7352 _TESTS = [{
7353 'url': 'https://consent.youtube.com/m?continue=https%3A%2F%2Fwww.youtube.com%2Flive%2FqVv6vCqciTM%3Fcbrd%3D1&gl=NL&m=0&pc=yt&hl=en&src=1',
7354 'info_dict': {
7355 'id': 'qVv6vCqciTM',
7356 'ext': 'mp4',
7357 'age_limit': 0,
7666b936 7358 'uploader_id': '@sana_natori',
b032ff0f 7359 'comment_count': int,
7360 'chapters': 'count:13',
7361 'upload_date': '20221223',
7362 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
7363 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7666b936 7364 'uploader_url': 'https://www.youtube.com/@sana_natori',
b032ff0f 7365 'like_count': int,
7366 'release_date': '20221223',
7367 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
7368 'title': '【 #インターネット女クリスマス 】3Dで歌ってはしゃぐインターネットの女たち【月ノ美兎/名取さな】',
7369 'view_count': int,
7370 'playable_in_embed': True,
7371 'duration': 4438,
7372 'availability': 'public',
7373 'channel_follower_count': int,
7374 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7375 'categories': ['Entertainment'],
7376 'live_status': 'was_live',
7377 'release_timestamp': 1671793345,
7378 'channel': 'さなちゃんねる',
7379 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
7380 'uploader': 'さなちゃんねる',
8213ce28 7381 'channel_is_verified': True,
14a14335 7382 'heatmap': 'count:100',
b032ff0f 7383 },
7384 'add_ie': ['Youtube'],
7385 'params': {'skip_download': 'Youtube'},
7386 }]
7387
7388 def _real_extract(self, url):
7389 redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
7390 if not redirect_url:
7391 raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
7392 return self.url_result(redirect_url)
7393
7394
772fd5cc
PH
7395class YoutubeTruncatedIDIE(InfoExtractor):
7396 IE_NAME = 'youtube:truncated_id'
7397 IE_DESC = False # Do not list
b95aab84 7398 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
7399
7400 _TESTS = [{
7401 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7402 'only_matching': True,
7403 }]
7404
7405 def _real_extract(self, url):
7406 video_id = self._match_id(url)
7407 raise ExtractorError(
86e5f3ed 7408 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 7409 expected=True)