]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[extractor/vk] VKPlay, VKPlayLive: Add extractors (#7358)
[yt-dlp.git] / yt_dlp / extractor / youtube.py
CommitLineData
6e634cbe 1import base64
d92f5d5a 2import calendar
a4894d3e 3import collections
109dd3b2 4import copy
fe93e2c4 5import datetime
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
46383212 14import sys
f8271158 15import threading
8a784c74 16import time
e0df6211 17import traceback
14f25df2 18import urllib.error
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
4bb4a188 25from ..utils import (
f8271158 26 NO_DEFAULT,
27 ExtractorError,
4d37720a 28 LazyList,
693f0600 29 UserNotLive,
720c3099 30 bug_reports_message,
82d02080 31 classproperty,
c5e8d7af 32 clean_html,
d92f5d5a 33 datetime_from_str,
11f9be09 34 dict_get,
7a32c70d 35 filter_dict,
2d30521a 36 float_or_none,
11f9be09 37 format_field,
ff91cf74 38 get_first,
dd27fd17 39 int_or_none,
641ad5d8 40 is_html,
34921b43 41 join_nonempty,
48416bc4 42 js_to_json,
94278f72 43 mimetype2ext,
9c0d7f49 44 network_exceptions,
11f9be09 45 orderedSet,
6310acf5 46 parse_codecs,
49bd8c66 47 parse_count,
7c80519c 48 parse_duration,
7ea65411 49 parse_iso8601,
4dfbf869 50 parse_qs,
dca3ff4a 51 qualities,
3995d37d 52 remove_start,
cf7e015f 53 smuggle_url,
dbdaaa23 54 str_or_none,
c93d53f5 55 str_to_int,
f3aa3c3f 56 strftime_or_none,
7c365c21 57 traverse_obj,
556dbe7f 58 try_get,
c5e8d7af
PH
59 unescapeHTML,
60 unified_strdate,
f0d785d3 61 unified_timestamp,
cf7e015f 62 unsmuggle_url,
8bdd16b4 63 update_url_query,
21c340b8 64 url_or_none,
fe93e2c4 65 urljoin,
7c365c21 66 variadic,
c5e8d7af
PH
67)
68
c795c39f 69STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client'
962ffcf8 70# any clients starting with _ cannot be explicitly requested by the user
000c15a4 71INNERTUBE_CLIENTS = {
72 'web': {
73 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
74 'INNERTUBE_CONTEXT': {
75 'client': {
76 'clientName': 'WEB',
a0c830f4 77 'clientVersion': '2.20220801.00.00',
000c15a4 78 }
79 },
80 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
81 },
82 'web_embedded': {
83 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
84 'INNERTUBE_CONTEXT': {
85 'client': {
86 'clientName': 'WEB_EMBEDDED_PLAYER',
a0c830f4 87 'clientVersion': '1.20220731.00.00',
000c15a4 88 },
89 },
90 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
91 },
92 'web_music': {
93 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
94 'INNERTUBE_HOST': 'music.youtube.com',
95 'INNERTUBE_CONTEXT': {
96 'client': {
97 'clientName': 'WEB_REMIX',
a0c830f4 98 'clientVersion': '1.20220727.01.00',
000c15a4 99 }
100 },
101 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
102 },
e7e94f2a 103 'web_creator': {
18c7683d 104 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
105 'INNERTUBE_CONTEXT': {
106 'client': {
107 'clientName': 'WEB_CREATOR',
a0c830f4 108 'clientVersion': '1.20220726.00.00',
e7e94f2a
D
109 }
110 },
111 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
112 },
000c15a4 113 'android': {
18c7683d 114 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 115 'INNERTUBE_CONTEXT': {
116 'client': {
117 'clientName': 'ANDROID',
50ac0e54 118 'clientVersion': '17.31.35',
119 'androidSdkVersion': 30,
120 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
000c15a4 121 }
122 },
123 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 124 'REQUIRE_JS_PLAYER': False
000c15a4 125 },
126 'android_embedded': {
18c7683d 127 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 128 'INNERTUBE_CONTEXT': {
129 'client': {
130 'clientName': 'ANDROID_EMBEDDED_PLAYER',
50ac0e54 131 'clientVersion': '17.31.35',
132 'androidSdkVersion': 30,
133 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
000c15a4 134 },
135 },
b6de707d 136 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
137 'REQUIRE_JS_PLAYER': False
000c15a4 138 },
139 'android_music': {
18c7683d 140 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 141 'INNERTUBE_CONTEXT': {
142 'client': {
143 'clientName': 'ANDROID_MUSIC',
a0c830f4 144 'clientVersion': '5.16.51',
50ac0e54 145 'androidSdkVersion': 30,
146 'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
000c15a4 147 }
148 },
149 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 150 'REQUIRE_JS_PLAYER': False
000c15a4 151 },
e7e94f2a 152 'android_creator': {
18c7683d 153 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
154 'INNERTUBE_CONTEXT': {
155 'client': {
156 'clientName': 'ANDROID_CREATOR',
50ac0e54 157 'clientVersion': '22.30.100',
158 'androidSdkVersion': 30,
159 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
e7e94f2a
D
160 },
161 },
b6de707d 162 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
163 'REQUIRE_JS_PLAYER': False
e7e94f2a 164 },
18c7683d 165 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
166 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 167 'ios': {
18c7683d 168 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 169 'INNERTUBE_CONTEXT': {
170 'client': {
171 'clientName': 'IOS',
224b5a35 172 'clientVersion': '17.33.2',
18c7683d 173 'deviceModel': 'iPhone14,3',
224b5a35 174 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 175 }
176 },
b6de707d 177 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
178 'REQUIRE_JS_PLAYER': False
000c15a4 179 },
180 'ios_embedded': {
000c15a4 181 'INNERTUBE_CONTEXT': {
182 'client': {
183 'clientName': 'IOS_MESSAGES_EXTENSION',
224b5a35 184 'clientVersion': '17.33.2',
18c7683d 185 'deviceModel': 'iPhone14,3',
224b5a35 186 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 187 },
188 },
b6de707d 189 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
190 'REQUIRE_JS_PLAYER': False
000c15a4 191 },
192 'ios_music': {
18c7683d 193 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 194 'INNERTUBE_CONTEXT': {
195 'client': {
196 'clientName': 'IOS_MUSIC',
224b5a35
SF
197 'clientVersion': '5.21',
198 'deviceModel': 'iPhone14,3',
199 'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 200 },
201 },
b6de707d 202 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
203 'REQUIRE_JS_PLAYER': False
000c15a4 204 },
e7e94f2a
D
205 'ios_creator': {
206 'INNERTUBE_CONTEXT': {
207 'client': {
208 'clientName': 'IOS_CREATOR',
224b5a35
SF
209 'clientVersion': '22.33.101',
210 'deviceModel': 'iPhone14,3',
211 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
e7e94f2a
D
212 },
213 },
b6de707d 214 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
215 'REQUIRE_JS_PLAYER': False
e7e94f2a 216 },
3619f78d 217 # mweb has 'ultralow' formats
218 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 219 'mweb': {
18c7683d 220 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 221 'INNERTUBE_CONTEXT': {
222 'client': {
223 'clientName': 'MWEB',
a0c830f4 224 'clientVersion': '2.20220801.00.00',
000c15a4 225 }
226 },
227 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
228 },
229 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
230 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
231 'tv_embedded': {
232 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
233 'INNERTUBE_CONTEXT': {
234 'client': {
235 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
236 'clientVersion': '2.0',
237 },
238 },
239 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
240 },
000c15a4 241}
242
243
e7870111
D
244def _split_innertube_client(client_name):
245 variant, *base = client_name.rsplit('.', 1)
246 if base:
247 return variant, base[0], variant
248 base, *variant = client_name.split('_', 1)
249 return client_name, base, variant[0] if variant else None
250
251
c795c39f
L
252def short_client_name(client_name):
253 main, *parts = _split_innertube_client(client_name)[0].replace('embedscreen', 'e_s').split('_')
254 return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper()
255
256
000c15a4 257def build_innertube_clients():
2e4cacd0 258 THIRD_PARTY = {
e7870111 259 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 260 }
1e75d97d 261 BASE_CLIENTS = ('ios', 'android', 'web', 'tv', 'mweb')
2e4cacd0 262 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 263
264 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 265 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 266 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 267 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 268 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 269
e7870111 270 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 271 ytcfg['priority'] = 10 * priority(base_client)
272
e48b3875 273 if not variant:
e7870111
D
274 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
275 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
276 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
277 embedscreen['priority'] -= 3
278 elif variant == 'embedded':
e48b3875 279 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 280 ytcfg['priority'] -= 2
e48b3875 281 else:
000c15a4 282 ytcfg['priority'] -= 3
283
284
285build_innertube_clients()
286
287
c26f9b99 288class BadgeType(enum.Enum):
289 AVAILABILITY_UNLISTED = enum.auto()
290 AVAILABILITY_PRIVATE = enum.auto()
291 AVAILABILITY_PUBLIC = enum.auto()
292 AVAILABILITY_PREMIUM = enum.auto()
293 AVAILABILITY_SUBSCRIPTION = enum.auto()
294 LIVE_NOW = enum.auto()
14a14335 295 VERIFIED = enum.auto()
c26f9b99 296
297
de7f3446 298class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 299 """Provide base functions for Youtube extractors"""
e00eb564 300
3462ffa8 301 _RESERVED_NAMES = (
08e29b9f 302 r'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|'
182bda88 303 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
1dd18a88 304 r'browse|oembed|get_video_info|iframe_api|s/player|source|'
0a5095fe 305 r'storefront|oops|index|account|t/terms|about|upload|signin|logout')
3462ffa8 306
3619f78d 307 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
308
52efa4b3 309 # _NETRC_MACHINE = 'youtube'
3619f78d 310
b2e8bc1b
JMF
311 # If True it will raise an error if no login info is provided
312 _LOGIN_REQUIRED = False
313
d9190e44
RH
314 _INVIDIOUS_SITES = (
315 # invidious-redirect websites
316 r'(?:www\.)?redirect\.invidious\.io',
317 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 318 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
319 r'(?:www\.)?invidious\.pussthecat\.org',
320 r'(?:www\.)?invidious\.zee\.li',
321 r'(?:www\.)?invidious\.ethibox\.fr',
05799a48
RH
322 r'(?:www\.)?iv\.ggtyler\.dev',
323 r'(?:www\.)?inv\.vern\.i2p',
324 r'(?:www\.)?am74vkcrjp2d5v36lcdqgsj2m6x36tbrkhsruoegwfcizzabnfgf5zyd\.onion',
325 r'(?:www\.)?inv\.riverside\.rocks',
326 r'(?:www\.)?invidious\.silur\.me',
327 r'(?:www\.)?inv\.bp\.projectsegfau\.lt',
328 r'(?:www\.)?invidious\.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid\.onion',
329 r'(?:www\.)?invidious\.slipfox\.xyz',
330 r'(?:www\.)?invidious\.esmail5pdn24shtvieloeedh7ehz3nrwcdivnfhfcedl7gf4kwddhkqd\.onion',
331 r'(?:www\.)?inv\.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad\.onion',
332 r'(?:www\.)?invidious\.tiekoetter\.com',
333 r'(?:www\.)?iv\.odysfvr23q5wgt7i456o5t3trw2cw5dgn56vbjfbq2m7xsc5vqbqpcyd\.onion',
334 r'(?:www\.)?invidious\.nerdvpn\.de',
335 r'(?:www\.)?invidious\.weblibre\.org',
336 r'(?:www\.)?inv\.odyssey346\.dev',
337 r'(?:www\.)?invidious\.dhusch\.de',
338 r'(?:www\.)?iv\.melmac\.space',
339 r'(?:www\.)?watch\.thekitty\.zone',
340 r'(?:www\.)?invidious\.privacydev\.net',
341 r'(?:www\.)?ng27owmagn5amdm7l5s3rsqxwscl5ynppnis5dqcasogkyxcfqn7psid\.onion',
342 r'(?:www\.)?invidious\.drivet\.xyz',
343 r'(?:www\.)?vid\.priv\.au',
344 r'(?:www\.)?euxxcnhsynwmfidvhjf6uzptsmh4dipkmgdmcmxxuo7tunp3ad2jrwyd\.onion',
345 r'(?:www\.)?inv\.vern\.cc',
346 r'(?:www\.)?invidious\.esmailelbob\.xyz',
347 r'(?:www\.)?invidious\.sethforprivacy\.com',
348 r'(?:www\.)?yt\.oelrichsgarcia\.de',
349 r'(?:www\.)?yt\.artemislena\.eu',
350 r'(?:www\.)?invidious\.flokinet\.to',
351 r'(?:www\.)?invidious\.baczek\.me',
352 r'(?:www\.)?y\.com\.sb',
353 r'(?:www\.)?invidious\.epicsite\.xyz',
354 r'(?:www\.)?invidious\.lidarshield\.cloud',
355 r'(?:www\.)?yt\.funami\.tech',
d9190e44 356 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
357 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
358 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
359 # youtube-dl invidious instances list
360 r'(?:(?:www|no)\.)?invidiou\.sh',
361 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
362 r'(?:www\.)?invidious\.kabi\.tk',
363 r'(?:www\.)?invidious\.mastodon\.host',
364 r'(?:www\.)?invidious\.zapashcanon\.fr',
365 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
366 r'(?:www\.)?invidious\.tinfoil-hat\.net',
367 r'(?:www\.)?invidious\.himiko\.cloud',
368 r'(?:www\.)?invidious\.reallyancient\.tech',
369 r'(?:www\.)?invidious\.tube',
370 r'(?:www\.)?invidiou\.site',
371 r'(?:www\.)?invidious\.site',
372 r'(?:www\.)?invidious\.xyz',
373 r'(?:www\.)?invidious\.nixnet\.xyz',
374 r'(?:www\.)?invidious\.048596\.xyz',
375 r'(?:www\.)?invidious\.drycat\.fr',
376 r'(?:www\.)?inv\.skyn3t\.in',
377 r'(?:www\.)?tube\.poal\.co',
378 r'(?:www\.)?tube\.connect\.cafe',
379 r'(?:www\.)?vid\.wxzm\.sx',
380 r'(?:www\.)?vid\.mint\.lgbt',
381 r'(?:www\.)?vid\.puffyan\.us',
382 r'(?:www\.)?yewtu\.be',
383 r'(?:www\.)?yt\.elukerio\.org',
384 r'(?:www\.)?yt\.lelux\.fi',
385 r'(?:www\.)?invidious\.ggc-project\.de',
386 r'(?:www\.)?yt\.maisputain\.ovh',
387 r'(?:www\.)?ytprivate\.com',
388 r'(?:www\.)?invidious\.13ad\.de',
389 r'(?:www\.)?invidious\.toot\.koeln',
390 r'(?:www\.)?invidious\.fdn\.fr',
391 r'(?:www\.)?watch\.nettohikari\.com',
392 r'(?:www\.)?invidious\.namazso\.eu',
393 r'(?:www\.)?invidious\.silkky\.cloud',
394 r'(?:www\.)?invidious\.exonip\.de',
395 r'(?:www\.)?invidious\.riverside\.rocks',
396 r'(?:www\.)?invidious\.blamefran\.net',
397 r'(?:www\.)?invidious\.moomoo\.de',
398 r'(?:www\.)?ytb\.trom\.tf',
399 r'(?:www\.)?yt\.cyberhost\.uk',
400 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
401 r'(?:www\.)?qklhadlycap4cnod\.onion',
402 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
403 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
404 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
405 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
406 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
407 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
408 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
409 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
410 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
411 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
412 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
413 r'(?:www\.)?piped\.kavin\.rocks',
d1c4f6d4 414 r'(?:www\.)?piped\.tokhmi\.xyz',
e14ea7fb 415 r'(?:www\.)?piped\.syncpundit\.io',
d1c4f6d4 416 r'(?:www\.)?piped\.mha\.fi',
e14ea7fb
BG
417 r'(?:www\.)?watch\.whatever\.social',
418 r'(?:www\.)?piped\.garudalinux\.org',
419 r'(?:www\.)?piped\.rivo\.lol',
420 r'(?:www\.)?piped-libre\.kavin\.rocks',
421 r'(?:www\.)?yt\.jae\.fi',
d1c4f6d4 422 r'(?:www\.)?piped\.mint\.lgbt',
e14ea7fb
BG
423 r'(?:www\.)?il\.ax',
424 r'(?:www\.)?piped\.esmailelbob\.xyz',
425 r'(?:www\.)?piped\.projectsegfau\.lt',
426 r'(?:www\.)?piped\.privacydev\.net',
427 r'(?:www\.)?piped\.palveluntarjoaja\.eu',
428 r'(?:www\.)?piped\.smnz\.de',
429 r'(?:www\.)?piped\.adminforge\.de',
430 r'(?:www\.)?watch\.whatevertinfoil\.de',
431 r'(?:www\.)?piped\.qdi\.fi',
bc87dac7
B
432 r'(?:www\.)?piped\.video',
433 r'(?:www\.)?piped\.aeong\.one',
05799a48
RH
434 r'(?:www\.)?piped\.moomoo\.me',
435 r'(?:www\.)?piped\.chauvet\.pro',
436 r'(?:www\.)?watch\.leptons\.xyz',
437 r'(?:www\.)?pd\.vern\.cc',
438 r'(?:www\.)?piped\.hostux\.net',
439 r'(?:www\.)?piped\.lunar\.icu',
78a78fa7
BG
440 # Hyperpipe instances from https://hyperpipe.codeberg.page/
441 r'(?:www\.)?hyperpipe\.surge\.sh',
442 r'(?:www\.)?hyperpipe\.esmailelbob\.xyz',
443 r'(?:www\.)?listen\.whatever\.social',
444 r'(?:www\.)?music\.adminforge\.de',
d9190e44
RH
445 )
446
c26f9b99 447 # extracted from account/account_menu ep
448 # XXX: These are the supported YouTube UI and API languages,
449 # which is slightly different from languages supported for translation in YouTube studio
450 _SUPPORTED_LANG_CODES = [
451 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es',
452 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv',
453 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi',
454 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw',
455 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml',
456 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko'
457 ]
458
a057779d 459 _IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
460
7666b936 461 _YT_HANDLE_RE = r'@[\w.-]{3,30}' # https://support.google.com/youtube/answer/11585688?hl=en
462 _YT_CHANNEL_UCID_RE = r'UC[\w-]{22}'
463
464 def ucid_or_none(self, ucid):
465 return self._search_regex(rf'^({self._YT_CHANNEL_UCID_RE})$', ucid, 'UC-id', default=None)
466
467 def handle_or_none(self, handle):
468 return self._search_regex(rf'^({self._YT_HANDLE_RE})$', handle, '@-handle', default=None)
469
470 def handle_from_url(self, url):
471 return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_HANDLE_RE})',
472 url, 'channel handle', default=None)
473
474 def ucid_from_url(self, url):
475 return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_CHANNEL_UCID_RE})',
476 url, 'channel id', default=None)
477
c26f9b99 478 @functools.cached_property
479 def _preferred_lang(self):
480 """
481 Returns a language code supported by YouTube for the user preferred language.
482 Returns None if no preferred language set.
483 """
484 preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0]
485 if not preferred_lang:
486 return
487 if preferred_lang not in self._SUPPORTED_LANG_CODES:
488 raise ExtractorError(
489 f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.',
490 expected=True)
491 elif preferred_lang != 'en':
492 self.report_warning(
493 f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.')
494 return preferred_lang
495
cce889b9 496 def _initialize_consent(self):
497 cookies = self._get_cookies('https://www.youtube.com/')
498 if cookies.get('__Secure-3PSID'):
499 return
500 consent_id = None
501 consent = cookies.get('CONSENT')
502 if consent:
503 if 'YES' in consent.value:
504 return
505 consent_id = self._search_regex(
506 r'PENDING\+(\d+)', consent.value, 'consent', default=None)
507 if not consent_id:
508 consent_id = random.randint(100, 999)
509 self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id)
8d81f3e3 510
f3aa3c3f 511 def _initialize_pref(self):
512 cookies = self._get_cookies('https://www.youtube.com/')
513 pref_cookie = cookies.get('PREF')
514 pref = {}
515 if pref_cookie:
516 try:
14f25df2 517 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 518 except ValueError:
519 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
c26f9b99 520 pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'})
14f25df2 521 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 522
b2e8bc1b 523 def _real_initialize(self):
f3aa3c3f 524 self._initialize_pref()
cce889b9 525 self._initialize_consent()
a25bca9f 526 self._check_login_required()
527
528 def _check_login_required(self):
24146491 529 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 530 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 531
b7c47b74 532 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
533 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 534
000c15a4 535 def _get_default_ytcfg(self, client='web'):
536 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 537
000c15a4 538 def _get_innertube_host(self, client='web'):
539 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 540
000c15a4 541 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 542 # try_get but with fallback to default ytcfg client values when present
543 _func = lambda y: try_get(y, getter, expected_type)
544 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
545
000c15a4 546 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 547 return self._ytcfg_get_safe(
548 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 549 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 550
000c15a4 551 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 552 return self._ytcfg_get_safe(
553 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 554 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 555
2ae778b8 556 def _select_api_hostname(self, req_api_hostname, default_client=None):
557 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
558 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
559
000c15a4 560 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 561 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 562
000c15a4 563 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 564 context = get_first(
565 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 566 # Enforce language and tz for extraction
567 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
c26f9b99 568 client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 569 return context
570
cf87314d 571 _SAPISID = None
572
109dd3b2 573 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 574 time_now = round(time.time())
cf87314d 575 if self._SAPISID is None:
576 yt_cookies = self._get_cookies('https://www.youtube.com')
577 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
578 # See: https://github.com/yt-dlp/yt-dlp/issues/393
579 sapisid_cookie = dict_get(
580 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
581 if sapisid_cookie and sapisid_cookie.value:
582 self._SAPISID = sapisid_cookie.value
583 self.write_debug('Extracted SAPISID cookie')
584 # SAPISID cookie is required if not already present
585 if not yt_cookies.get('SAPISID'):
586 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
587 self._set_cookie(
588 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
589 else:
590 self._SAPISID = False
591 if not self._SAPISID:
592 return None
1974e99f 593 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
594 sapisidhash = hashlib.sha1(
86e5f3ed 595 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 596 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
597
598 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 599 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 600 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 601
109dd3b2 602 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 603 data.update(query)
11f9be09 604 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 605 real_headers.update({'content-type': 'application/json'})
606 if headers:
607 real_headers.update(headers)
2ae778b8 608 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
609 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 610 return self._download_json(
2ae778b8 611 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 612 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 613 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 614 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 615
65141660 616 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
617 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 618
99e9e001 619 @staticmethod
620 def _extract_session_index(*data):
621 """
622 Index of current account in account list.
623 See: https://github.com/yt-dlp/yt-dlp/pull/519
624 """
625 for ytcfg in data:
626 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
627 if session_index is not None:
628 return session_index
629
630 # Deprecated?
631 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 632 if ytcfg:
14f25df2 633 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
634 if token:
635 return token
99e9e001 636 if webpage:
637 return self._search_regex(
638 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
639 'identity token', default=None, fatal=False)
a1c5d2ca
M
640
641 @staticmethod
fe93e2c4 642 def _extract_account_syncid(*args):
8ea3f7b9 643 """
644 Extract syncId required to download private playlists of secondary channels
fe93e2c4 645 @params response and/or ytcfg
8ea3f7b9 646 """
fe93e2c4 647 for data in args:
648 # ytcfg includes channel_syncid if on secondary channel
14f25df2 649 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 650 if delegated_sid:
651 return delegated_sid
652 sync_ids = (try_get(
653 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 654 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 655 if len(sync_ids) >= 2 and sync_ids[1]:
656 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
657 # and just "user_syncid||" for primary channel. We only want the channel_syncid
658 return sync_ids[0]
a1c5d2ca 659
ac56cf38 660 @staticmethod
661 def _extract_visitor_data(*args):
662 """
663 Extracts visitorData from an API response or ytcfg
664 Appears to be used to track session state
665 """
9222c381 666 return get_first(
6c73052c 667 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 668 expected_type=str)
ac56cf38 669
2762dbb1 670 @functools.cached_property
99e9e001 671 def is_authenticated(self):
672 return bool(self._generate_sapisidhash_header())
673
11f9be09 674 def extract_ytcfg(self, video_id, webpage):
8c54a305 675 if not webpage:
676 return {}
29f7c58a 677 return self._parse_json(
678 self._search_regex(
679 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 680 default='{}'), video_id, fatal=False) or {}
681
11f9be09 682 def generate_api_headers(
99e9e001 683 self, *, ytcfg=None, account_syncid=None, session_index=None,
684 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
685
2ae778b8 686 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 687 headers = {
14f25df2 688 'X-YouTube-Client-Name': str(
11f9be09 689 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
690 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 691 'Origin': origin,
692 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
693 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
50ac0e54 694 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
695 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
99e9e001 696 }
697 if session_index is None:
314ee305 698 session_index = self._extract_session_index(ytcfg)
699 if account_syncid or session_index is not None:
700 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 701
109dd3b2 702 auth = self._generate_sapisidhash_header(origin)
f4f751af 703 if auth is not None:
704 headers['Authorization'] = auth
109dd3b2 705 headers['X-Origin'] = origin
7a32c70d 706 return filter_dict(headers)
29f7c58a 707
a25bca9f 708 def _download_ytcfg(self, client, video_id):
709 url = {
710 'web': 'https://www.youtube.com',
711 'web_music': 'https://music.youtube.com',
712 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
713 }.get(client)
714 if not url:
715 return {}
716 webpage = self._download_webpage(
717 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
718 return self.extract_ytcfg(video_id, webpage) or {}
719
2d6659b9 720 @staticmethod
721 def _build_api_continuation_query(continuation, ctp=None):
722 query = {
723 'continuation': continuation
724 }
725 # TODO: Inconsistency with clickTrackingParams.
726 # Currently we have a fixed ctp contained within context (from ytcfg)
727 # and a ctp in root query for continuation.
728 if ctp:
729 query['clickTracking'] = {'clickTrackingParams': ctp}
730 return query
731
2d6659b9 732 @classmethod
733 def _extract_next_continuation_data(cls, renderer):
734 next_continuation = try_get(
735 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
736 lambda x: x['continuation']['reloadContinuationData']), dict)
737 if not next_continuation:
738 return
739 continuation = next_continuation.get('continuation')
740 if not continuation:
741 return
742 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 743 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 744
745 @classmethod
746 def _extract_continuation_ep_data(cls, continuation_ep: dict):
747 if isinstance(continuation_ep, dict):
748 continuation = try_get(
14f25df2 749 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 750 if not continuation:
751 return
752 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 753 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 754
755 @classmethod
756 def _extract_continuation(cls, renderer):
757 next_continuation = cls._extract_next_continuation_data(renderer)
758 if next_continuation:
759 return next_continuation
fe93e2c4 760
7a32c70d 761 return traverse_obj(renderer, (
762 ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
763 ('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
764 ), get_all=False, expected_type=cls._extract_continuation_ep_data)
2d6659b9 765
fe93e2c4 766 @classmethod
767 def _extract_alerts(cls, data):
109dd3b2 768 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
769 if not isinstance(alert_dict, dict):
770 continue
771 for alert in alert_dict.values():
772 alert_type = alert.get('type')
773 if not alert_type:
774 continue
052e1350 775 message = cls._get_text(alert, 'text')
109dd3b2 776 if message:
777 yield alert_type, message
778
c0ac49bc 779 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
a057779d 780 errors, warnings = [], []
109dd3b2 781 for alert_type, alert_message in alerts:
641ad5d8 782 if alert_type.lower() == 'error' and fatal:
109dd3b2 783 errors.append([alert_type, alert_message])
a057779d 784 elif alert_message not in self._IGNORED_WARNINGS:
109dd3b2 785 warnings.append([alert_type, alert_message])
786
787 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 788 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 789 if errors:
790 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
791
792 def _extract_and_report_alerts(self, data, *args, **kwargs):
793 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
794
14a14335 795 def _extract_badges(self, badge_list: list):
796 """
797 Extract known BadgeType's from a list of badge renderers.
798 @returns [{'type': BadgeType}]
799 """
800 icon_type_map = {
c26f9b99 801 'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED,
802 'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE,
14a14335 803 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC,
804 'CHECK_CIRCLE_THICK': BadgeType.VERIFIED,
805 'OFFICIAL_ARTIST_BADGE': BadgeType.VERIFIED,
8213ce28 806 'CHECK': BadgeType.VERIFIED,
c26f9b99 807 }
808
809 badge_style_map = {
810 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION,
811 'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM,
14a14335 812 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW,
8213ce28 813 'BADGE_STYLE_TYPE_VERIFIED': BadgeType.VERIFIED,
ad54c913 814 'BADGE_STYLE_TYPE_VERIFIED_ARTIST': BadgeType.VERIFIED,
c26f9b99 815 }
816
817 label_map = {
818 'unlisted': BadgeType.AVAILABILITY_UNLISTED,
819 'private': BadgeType.AVAILABILITY_PRIVATE,
820 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION,
821 'live': BadgeType.LIVE_NOW,
14a14335 822 'premium': BadgeType.AVAILABILITY_PREMIUM,
8213ce28 823 'verified': BadgeType.VERIFIED,
ad54c913 824 'official artist channel': BadgeType.VERIFIED,
c26f9b99 825 }
826
827 badges = []
14a14335 828 for badge in traverse_obj(badge_list, (..., lambda key, _: re.search(r'[bB]adgeRenderer$', key))):
c26f9b99 829 badge_type = (
14a14335 830 icon_type_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
c26f9b99 831 or badge_style_map.get(traverse_obj(badge, 'style'))
832 )
833 if badge_type:
834 badges.append({'type': badge_type})
835 continue
836
837 # fallback, won't work in some languages
14a14335 838 label = traverse_obj(
839 badge, 'label', ('accessibilityData', 'label'), 'tooltip', 'iconTooltip', get_all=False, expected_type=str, default='')
c26f9b99 840 for match, label_badge_type in label_map.items():
841 if match in label.lower():
14a14335 842 badges.append({'type': label_badge_type})
843 break
c26f9b99 844
47193e02 845 return badges
846
c26f9b99 847 @staticmethod
848 def _has_badge(badges, badge_type):
849 return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type))
850
47193e02 851 @staticmethod
052e1350 852 def _get_text(data, *path_list, max_runs=None):
853 for path in path_list or [None]:
854 if path is None:
855 obj = [data]
856 else:
857 obj = traverse_obj(data, path, default=[])
858 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
859 obj = [obj]
860 for item in obj:
14f25df2 861 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 862 if text:
863 return text
864 runs = try_get(item, lambda x: x['runs'], list) or []
865 if not runs and isinstance(item, list):
866 runs = item
867
868 runs = runs[:min(len(runs), max_runs or len(runs))]
6839ae1f 869 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str))
052e1350 870 if text:
871 return text
47193e02 872
f0d785d3 873 def _get_count(self, data, *path_list):
874 count_text = self._get_text(data, *path_list) or ''
875 count = parse_count(count_text)
876 if count is None:
877 count = str_to_int(
878 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
879 return count
880
a709d873 881 @staticmethod
882 def _extract_thumbnails(data, *path_list):
883 """
884 Extract thumbnails from thumbnails dict
885 @param path_list: path list to level that contains 'thumbnails' key
886 """
887 thumbnails = []
888 for path in path_list or [()]:
6839ae1f 889 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...)):
a709d873 890 thumbnail_url = url_or_none(thumbnail.get('url'))
891 if not thumbnail_url:
892 continue
893 # Sometimes youtube gives a wrong thumbnail URL. See:
894 # https://github.com/yt-dlp/yt-dlp/issues/233
895 # https://github.com/ytdl-org/youtube-dl/issues/28023
896 if 'maxresdefault' in thumbnail_url:
897 thumbnail_url = thumbnail_url.split('?')[0]
898 thumbnails.append({
899 'url': thumbnail_url,
900 'height': int_or_none(thumbnail.get('height')),
901 'width': int_or_none(thumbnail.get('width')),
902 })
903 return thumbnails
904
f3aa3c3f 905 @staticmethod
906 def extract_relative_time(relative_time_text):
907 """
908 Extracts a relative time from string and converts to dt object
2fb35f60 909 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today', '8 yr ago'
f3aa3c3f 910 """
2fb35f60 911
912 # XXX: this could be moved to a general function in utils.py
913 # The relative time text strings are roughly the same as what
914 # Javascript's Intl.RelativeTimeFormat function generates.
915 # See: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Intl/RelativeTimeFormat
916 mobj = re.search(
917 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',
918 relative_time_text)
f3aa3c3f 919 if mobj:
f0d785d3 920 start = mobj.group('start')
921 if start:
922 return datetime_from_str(start)
f3aa3c3f 923 try:
f0d785d3 924 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 925 except ValueError:
926 return None
927
c26f9b99 928 def _parse_time_text(self, text):
929 if not text:
930 return
f3aa3c3f 931 dt = self.extract_relative_time(text)
932 timestamp = None
933 if isinstance(dt, datetime.datetime):
934 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 935
936 if timestamp is None:
937 timestamp = (
938 unified_timestamp(text) or unified_timestamp(
939 self._search_regex(
17322130 940 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 941 text.lower(), 'time text', default=None)))
f0d785d3 942
c26f9b99 943 if text and timestamp is None and self._preferred_lang in (None, 'en'):
944 self.report_warning(
945 f'Cannot parse localized time text "{text}"', only_once=True)
946 return timestamp
f3aa3c3f 947
109dd3b2 948 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
949 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 950 default_client='web'):
be5c1ae8 951 for retry in self.RetryManager():
109dd3b2 952 try:
953 response = self._call_api(
954 ep=ep, fatal=True, headers=headers,
be5c1ae8 955 video_id=item_id, query=query, note=note,
109dd3b2 956 context=self._extract_context(ytcfg, default_client),
957 api_key=self._extract_api_key(ytcfg, default_client),
be5c1ae8 958 api_hostname=api_hostname, default_client=default_client)
109dd3b2 959 except ExtractorError as e:
be5c1ae8 960 if not isinstance(e.cause, network_exceptions):
961 return self._error_or_warning(e, fatal=fatal)
962 elif not isinstance(e.cause, urllib.error.HTTPError):
963 retry.error = e
964 continue
109dd3b2 965
be5c1ae8 966 first_bytes = e.cause.read(512)
967 if not is_html(first_bytes):
968 yt_error = try_get(
969 self._parse_json(
970 self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
971 lambda x: x['error']['message'], str)
972 if yt_error:
973 self._report_alerts([('ERROR', yt_error)], fatal=False)
974 # Downloading page may result in intermittent 5xx HTTP error
975 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
976 # We also want to catch all other network exceptions since errors in later pages can be troublesome
977 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
978 if e.cause.code not in (403, 429):
979 retry.error = e
980 continue
981 return self._error_or_warning(e, fatal=fatal)
982
983 try:
984 self._extract_and_report_alerts(response, only_once=True)
985 except ExtractorError as e:
986 # YouTube servers may return errors we want to retry on in a 200 OK response
987 # See: https://github.com/yt-dlp/yt-dlp/issues/839
988 if 'unknown error' in e.msg.lower():
989 retry.error = e
990 continue
991 return self._error_or_warning(e, fatal=fatal)
992 # Youtube sometimes sends incomplete data
993 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
994 if not traverse_obj(response, *variadic(check_get_keys)):
3ce29336 995 retry.error = ExtractorError('Incomplete data received', expected=True)
be5c1ae8 996 continue
997
998 return response
109dd3b2 999
9297939e 1000 @staticmethod
1001 def is_music_url(url):
5b28cef7 1002 return re.match(r'(https?://)?music\.youtube\.com/', url) is not None
9297939e 1003
30a074c2 1004 def _extract_video(self, renderer):
1005 video_id = renderer.get('videoId')
4dc23a80
M
1006
1007 reel_header_renderer = traverse_obj(renderer, (
1008 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer',
1009 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer'))
1010
1011 title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText')
052e1350 1012 description = self._get_text(renderer, 'descriptionSnippet')
6141346d
M
1013
1014 duration = int_or_none(renderer.get('lengthSeconds'))
1015 if duration is None:
1016 duration = parse_duration(self._get_text(
1017 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 1018 if duration is None:
4dc23a80 1019 # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab)
1c1b2f96 1020 duration = parse_duration(self._search_regex(
1021 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
1022 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
1023 video_id, default=None, group='duration'))
1024
f3aa3c3f 1025 channel_id = traverse_obj(
a44ca5a4 1026 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
1027 expected_type=str, get_all=False)
4dc23a80
M
1028 if not channel_id:
1029 channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId'))
1030
7666b936 1031 channel_id = self.ucid_or_none(channel_id)
1032
f3aa3c3f 1033 overlay_style = traverse_obj(
a44ca5a4 1034 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
1035 get_all=False, expected_type=str)
14a14335 1036 badges = self._extract_badges(traverse_obj(renderer, 'badges'))
8213ce28 1037 owner_badges = self._extract_badges(traverse_obj(renderer, 'ownerBadges'))
fd2ad7cb 1038 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 1039 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
1040 expected_type=str)) or ''
fd2ad7cb 1041 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 1042 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 1043 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 1044
4dc23a80
M
1045 time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo')
1046 or self._get_text(reel_header_renderer, 'timestampText') or '')
1047 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
1048
867c66ff
M
1049 live_status = (
1050 'is_upcoming' if scheduled_timestamp is not None
1051 else 'was_live' if 'streamed' in time_text.lower()
1052 else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW)
1053 else None)
1054
4dc23a80
M
1055 # videoInfo is a string like '50K views • 10 years ago'.
1056 view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or ''
1057 view_count = (0 if 'no views' in view_count_text.lower()
1058 else self._get_count({'simpleText': view_count_text}))
1059 view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count'
1060
93e12ed7 1061 channel = (self._get_text(renderer, 'ownerText', 'shortBylineText')
1062 or self._get_text(reel_header_renderer, 'channelTitleText'))
1063
1064 channel_handle = traverse_obj(renderer, (
1065 'shortBylineText', 'runs', ..., 'navigationEndpoint',
1066 (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl'))),
1067 expected_type=self.handle_from_url, get_all=False)
30a074c2 1068 return {
39ed931e 1069 '_type': 'url',
30a074c2 1070 'ie_key': YoutubeIE.ie_key(),
1071 'id': video_id,
fd2ad7cb 1072 'url': url,
30a074c2 1073 'title': title,
1074 'description': description,
1075 'duration': duration,
f3aa3c3f 1076 'channel_id': channel_id,
93e12ed7 1077 'channel': channel,
4dc23a80 1078 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
93e12ed7 1079 'uploader': channel,
1080 'uploader_id': channel_handle,
1081 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
4dc23a80 1082 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
5225df50 1083 'timestamp': (self._parse_time_text(time_text)
1084 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
1085 else None),
f3aa3c3f 1086 'release_timestamp': scheduled_timestamp,
c26f9b99 1087 'availability':
1088 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
1089 else self._availability(
1090 is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None,
1091 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
1092 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
867c66ff 1093 is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
4dc23a80 1094 view_count_field: view_count,
14a14335 1095 'live_status': live_status,
8213ce28 1096 'channel_is_verified': True if self._has_badge(owner_badges, BadgeType.VERIFIED) else None
30a074c2 1097 }
1098
0c148415 1099
360e1ca5 1100class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 1101 IE_DESC = 'YouTube'
cb7dfeea 1102 _VALID_URL = r"""(?x)^
c5e8d7af 1103 (
edb53e2d 1104 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 1105 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
1106 (?:www\.)?deturl\.com/www\.youtube\.com|
1107 (?:www\.)?pwnyoutube\.com|
1108 (?:www\.)?hooktube\.com|
1109 (?:www\.)?yourepeat\.com|
1110 tube\.majestyc\.net|
1111 %(invidious)s|
1112 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
1113 (?:.*?\#/)? # handle anchor (#/) redirect urls
1114 (?: # the various things that can precede the ID:
dad2210c 1115 (?:(?:v|embed|e|shorts|live)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 1116 |(?: # or the v= param in all its forms
f7000f3a 1117 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 1118 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 1119 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
1120 v=
1121 )
f4b05232 1122 ))
cbaed4bb
S
1123 |(?:
1124 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
1125 vid\.plus| # or vid.plus/xxxx
1126 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 1127 %(invidious)s
cbaed4bb 1128 )/
edb53e2d 1129 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 1130 )
c5e8d7af 1131 )? # all until now is optional -> you can pass the naked ID
201c1459 1132 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 1133 (?(1).+)? # if we found the ID, everything can follow
9297939e 1134 (?:\#|$)""" % {
d9190e44 1135 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 1136 }
7c6eb424 1137 _EMBED_REGEX = [
1138 r'''(?x)
1139 (?:
0ca0f881 1140 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
7c6eb424 1141 data-video-url=|
1142 <embed[^>]+?src=|
1143 embedSWF\(?:\s*|
1144 <object[^>]+data=|
1145 new\s+SWFObject\(
1146 )
1147 (["\'])
1148 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1149 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1150 \1''',
1151 # https://wordpress.org/plugins/lazy-load-for-videos/
1152 r'''(?xs)
1153 <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1154 \s[^>]*\bclass="[^"]*\blazy-load-youtube''',
1155 ]
6368e2e6 1156 _RETURN_TYPE = 'video' # XXX: How to handle multifeed?
7c6eb424 1157
e40c758c 1158 _PLAYER_INFO_RE = (
cc2db878 1159 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1160 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$',
545cc85d 1161 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 1162 )
2c62dc26 1163 _formats = {
c2d3cb4c 1164 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1165 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1166 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1167 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1168 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1169 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1170 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1171 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 1172 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 1173 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1174 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1175 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1176 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1177 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1178 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 1179 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 1180 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1181 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 1182
1183
1184 # 3D videos
c2d3cb4c 1185 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1186 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1187 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1188 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 1189 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1190 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1191 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 1192
96fb5605 1193 # Apple HTTP Live Streaming
11f12195 1194 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 1195 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1196 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1197 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1198 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1199 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 1200 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1201 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
1202
1203 # DASH mp4 video
d23028a8
S
1204 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1205 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1206 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1207 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1208 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 1209 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
1210 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1211 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1212 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1213 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1214 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1215 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 1216
f6f1fc92 1217 # Dash mp4 audio
d23028a8
S
1218 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1219 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1220 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1221 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1222 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1223 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1224 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1225
1226 # Dash webm
d23028a8
S
1227 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1228 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1229 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1230 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1231 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1232 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1233 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1234 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1235 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1236 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1237 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1238 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1239 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1240 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1241 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1242 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1243 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1244 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1245 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1246 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1247 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1248 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1249
1250 # Dash webm audio
d23028a8
S
1251 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1252 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1253
0857baad 1254 # Dash webm audio with opus inside
d23028a8
S
1255 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1256 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1257 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1258
ce6b9a2d
PH
1259 # RTMP (unnamed)
1260 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1261
1262 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1263 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1264 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1265 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1266 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1267 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1268 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1269 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1270 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1271 }
29f7c58a 1272 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1273
fd5c4aab
S
1274 _GEO_BYPASS = False
1275
78caa52a 1276 IE_NAME = 'youtube'
2eb88d95
PH
1277 _TESTS = [
1278 {
2d3d2997 1279 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1280 'info_dict': {
1281 'id': 'BaW_jenozKc',
1282 'ext': 'mp4',
3867038a 1283 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
ff9f925b 1284 'channel': 'Philipp Hagemeister',
dd4c4492
S
1285 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1286 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1287 'upload_date': '20121002',
ff9f925b 1288 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1289 'categories': ['Science & Technology'],
3867038a 1290 'tags': ['youtube-dl'],
556dbe7f 1291 'duration': 10,
dbdaaa23 1292 'view_count': int,
3e7c1224 1293 'like_count': int,
ff9f925b 1294 'availability': 'public',
1295 'playable_in_embed': True,
1296 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1297 'live_status': 'not_live',
1298 'age_limit': 0,
7c80519c 1299 'start_time': 1,
297a564b 1300 'end_time': 9,
12a1b225 1301 'comment_count': int,
7666b936 1302 'channel_follower_count': int,
1303 'uploader': 'Philipp Hagemeister',
1304 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
1305 'uploader_id': '@PhilippHagemeister',
5caf30db 1306 'heatmap': 'count:100',
2eb88d95 1307 }
0e853ca4 1308 },
fccd3771 1309 {
4bc3a23e
PH
1310 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1311 'note': 'Embed-only video (#1746)',
1312 'info_dict': {
1313 'id': 'yZIXLfi8CZQ',
1314 'ext': 'mp4',
1315 'upload_date': '20120608',
1316 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1317 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
94bfcd23 1318 'age_limit': 18,
545cc85d 1319 },
1320 'skip': 'Private video',
fccd3771 1321 },
11b56058 1322 {
8bdd16b4 1323 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1324 'note': 'Use the first video ID in the URL',
1325 'info_dict': {
1326 'id': 'BaW_jenozKc',
1327 'ext': 'mp4',
3867038a 1328 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
976ae3ea 1329 'channel': 'Philipp Hagemeister',
1330 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1331 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1332 'upload_date': '20121002',
976ae3ea 1333 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1334 'categories': ['Science & Technology'],
3867038a 1335 'tags': ['youtube-dl'],
556dbe7f 1336 'duration': 10,
dbdaaa23 1337 'view_count': int,
11b56058 1338 'like_count': int,
976ae3ea 1339 'availability': 'public',
1340 'playable_in_embed': True,
1341 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1342 'live_status': 'not_live',
1343 'age_limit': 0,
12a1b225 1344 'comment_count': int,
7666b936 1345 'channel_follower_count': int,
1346 'uploader': 'Philipp Hagemeister',
1347 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
1348 'uploader_id': '@PhilippHagemeister',
14a14335 1349 'heatmap': 'count:100',
34a7de29
S
1350 },
1351 'params': {
1352 'skip_download': True,
1353 },
11b56058 1354 },
dd27fd17 1355 {
2d3d2997 1356 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1357 'note': '256k DASH audio (format 141) via DASH manifest',
1358 'info_dict': {
1359 'id': 'a9LDPn-MO4I',
1360 'ext': 'm4a',
1361 'upload_date': '20121002',
4bc3a23e 1362 'description': '',
4bc3a23e 1363 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1364 },
4bc3a23e
PH
1365 'params': {
1366 'youtube_include_dash_manifest': True,
1367 'format': '141',
4919603f 1368 },
de3c7fe0 1369 'skip': 'format 141 not served anymore',
dd27fd17 1370 },
8bdd16b4 1371 # DASH manifest with encrypted signature
1372 {
1373 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1374 'info_dict': {
1375 'id': 'IB3lcPjvWLA',
1376 'ext': 'm4a',
1377 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1378 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1379 'duration': 244,
8bdd16b4 1380 'upload_date': '20131011',
cc2db878 1381 'abr': 129.495,
976ae3ea 1382 'like_count': int,
1383 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1384 'playable_in_embed': True,
1385 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1386 'view_count': int,
1387 'track': 'The Spark',
1388 'live_status': 'not_live',
1389 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1390 'channel': 'Afrojack',
976ae3ea 1391 'tags': 'count:19',
1392 'availability': 'public',
1393 'categories': ['Music'],
1394 'age_limit': 0,
1395 'alt_title': 'The Spark',
7666b936 1396 'channel_follower_count': int,
1397 'uploader': 'Afrojack',
1398 'uploader_url': 'https://www.youtube.com/@Afrojack',
1399 'uploader_id': '@Afrojack',
8bdd16b4 1400 },
1401 'params': {
1402 'youtube_include_dash_manifest': True,
1403 'format': '141/bestaudio[ext=m4a]',
1404 },
1405 },
65c2fde2 1406 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1407 {
65c2fde2 1408 'note': 'Embed allowed age-gate video',
2d3d2997 1409 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1410 'info_dict': {
1411 'id': 'HtVdAasjOgU',
1412 'ext': 'mp4',
1413 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1414 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1415 'duration': 142,
c522adb1 1416 'upload_date': '20140605',
34952f09 1417 'age_limit': 18,
976ae3ea 1418 'categories': ['Gaming'],
1419 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1420 'availability': 'needs_auth',
1421 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1422 'like_count': int,
1423 'channel': 'The Witcher',
1424 'live_status': 'not_live',
1425 'tags': 'count:17',
1426 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1427 'playable_in_embed': True,
1428 'view_count': int,
7666b936 1429 'channel_follower_count': int,
1430 'uploader': 'The Witcher',
1431 'uploader_url': 'https://www.youtube.com/@thewitcher',
1432 'uploader_id': '@thewitcher',
14a14335 1433 'comment_count': int,
8213ce28 1434 'channel_is_verified': True,
14a14335 1435 'heatmap': 'count:100',
c522adb1
JMF
1436 },
1437 },
65c2fde2 1438 {
1439 'note': 'Age-gate video with embed allowed in public site',
1440 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1441 'info_dict': {
1442 'id': 'HsUATh_Nc2U',
1443 'ext': 'mp4',
1444 'title': 'Godzilla 2 (Official Video)',
1445 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1446 'upload_date': '20200408',
65c2fde2 1447 'age_limit': 18,
976ae3ea 1448 'availability': 'needs_auth',
1449 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
976ae3ea 1450 'channel': 'FlyingKitty',
1451 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1452 'view_count': int,
1453 'categories': ['Entertainment'],
1454 'live_status': 'not_live',
1455 'tags': ['Flyingkitty', 'godzilla 2'],
1456 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1457 'like_count': int,
1458 'duration': 177,
1459 'playable_in_embed': True,
7666b936 1460 'channel_follower_count': int,
1461 'uploader': 'FlyingKitty',
1462 'uploader_url': 'https://www.youtube.com/@FlyingKitty900',
1463 'uploader_id': '@FlyingKitty900',
5caf30db 1464 'comment_count': int,
8213ce28 1465 'channel_is_verified': True,
65c2fde2 1466 },
1467 },
1468 {
1469 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1470 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1471 'info_dict': {
1472 'id': 'Tq92D6wQ1mg',
1473 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1474 'ext': 'mp4',
17322130 1475 'upload_date': '20191228',
65c2fde2 1476 'description': 'md5:17eccca93a786d51bc67646756894066',
1477 'age_limit': 18,
976ae3ea 1478 'like_count': int,
1479 'availability': 'needs_auth',
976ae3ea 1480 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1481 'view_count': int,
1482 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1483 'channel': 'Projekt Melody',
1484 'live_status': 'not_live',
1485 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1486 'playable_in_embed': True,
1487 'categories': ['Entertainment'],
1488 'duration': 106,
1489 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1490 'comment_count': int,
7666b936 1491 'channel_follower_count': int,
1492 'uploader': 'Projekt Melody',
1493 'uploader_url': 'https://www.youtube.com/@ProjektMelody',
1494 'uploader_id': '@ProjektMelody',
65c2fde2 1495 },
1496 },
1497 {
1498 'note': 'Non-Agegated non-embeddable video',
1499 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1500 'info_dict': {
1501 'id': 'MeJVWBSsPAY',
1502 'ext': 'mp4',
1503 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
65c2fde2 1504 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1505 'upload_date': '20130730',
976ae3ea 1506 'track': 'Such mich find mich',
1507 'age_limit': 0,
1508 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1509 'like_count': int,
1510 'playable_in_embed': False,
1511 'creator': 'OOMPH!',
1512 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1513 'view_count': int,
1514 'alt_title': 'Such mich find mich',
1515 'duration': 210,
1516 'channel': 'Herr Lurik',
1517 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1518 'categories': ['Music'],
1519 'availability': 'public',
976ae3ea 1520 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1521 'live_status': 'not_live',
1522 'artist': 'OOMPH!',
7666b936 1523 'channel_follower_count': int,
1524 'uploader': 'Herr Lurik',
1525 'uploader_url': 'https://www.youtube.com/@HerrLurik',
1526 'uploader_id': '@HerrLurik',
65c2fde2 1527 },
1528 },
1529 {
1530 'note': 'Non-bypassable age-gated video',
1531 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1532 'only_matching': True,
1533 },
8bdd16b4 1534 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1535 # YouTube Red ad is not captured for creator
1536 {
1537 'url': '__2ABJjxzNo',
1538 'info_dict': {
1539 'id': '__2ABJjxzNo',
1540 'ext': 'mp4',
1541 'duration': 266,
1542 'upload_date': '20100430',
545cc85d 1543 'creator': 'deadmau5',
1544 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1545 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1546 'alt_title': 'Some Chords',
976ae3ea 1547 'availability': 'public',
1548 'tags': 'count:14',
1549 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1550 'view_count': int,
1551 'live_status': 'not_live',
1552 'channel': 'deadmau5',
1553 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1554 'like_count': int,
1555 'track': 'Some Chords',
1556 'artist': 'deadmau5',
1557 'playable_in_embed': True,
1558 'age_limit': 0,
1559 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1560 'categories': ['Music'],
1561 'album': 'Some Chords',
7666b936 1562 'channel_follower_count': int,
1563 'uploader': 'deadmau5',
1564 'uploader_url': 'https://www.youtube.com/@deadmau5',
1565 'uploader_id': '@deadmau5',
8bdd16b4 1566 },
1567 'expected_warnings': [
1568 'DASH manifest missing',
1569 ]
1570 },
067aa17e 1571 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1572 {
1573 'url': 'lqQg6PlCWgI',
1574 'info_dict': {
1575 'id': 'lqQg6PlCWgI',
1576 'ext': 'mp4',
556dbe7f 1577 'duration': 6085,
90227264 1578 'upload_date': '20150827',
12a1b225 1579 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
cbe2bd91 1580 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1581 'like_count': int,
1582 'release_timestamp': 1343767800,
1583 'playable_in_embed': True,
1584 'categories': ['Sports'],
1585 'release_date': '20120731',
1586 'channel': 'Olympics',
1587 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1588 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1589 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1590 'age_limit': 0,
1591 'availability': 'public',
1592 'live_status': 'was_live',
1593 'view_count': int,
1594 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
7666b936 1595 'channel_follower_count': int,
1596 'uploader': 'Olympics',
1597 'uploader_url': 'https://www.youtube.com/@Olympics',
1598 'uploader_id': '@Olympics',
8213ce28 1599 'channel_is_verified': True,
cbe2bd91
PH
1600 },
1601 'params': {
1602 'skip_download': 'requires avconv',
e52a40ab 1603 }
cbe2bd91 1604 },
6271f1ca
PH
1605 # Non-square pixels
1606 {
1607 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1608 'info_dict': {
1609 'id': '_b-2C3KPAM0',
1610 'ext': 'mp4',
1611 'stretched_ratio': 16 / 9.,
556dbe7f 1612 'duration': 85,
6271f1ca 1613 'upload_date': '20110310',
6271f1ca 1614 '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 1615 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1616 'playable_in_embed': True,
1617 'channel': '孫ᄋᄅ',
1618 'age_limit': 0,
1619 'tags': 'count:11',
1620 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1621 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1622 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1623 'view_count': int,
1624 'categories': ['People & Blogs'],
1625 'like_count': int,
1626 'live_status': 'not_live',
1627 'availability': 'unlisted',
12a1b225 1628 'comment_count': int,
7666b936 1629 'channel_follower_count': int,
1630 'uploader': '孫ᄋᄅ',
1631 'uploader_url': 'https://www.youtube.com/@AllenMeow',
1632 'uploader_id': '@AllenMeow',
6271f1ca 1633 },
06b491eb
S
1634 },
1635 # url_encoded_fmt_stream_map is empty string
1636 {
1637 'url': 'qEJwOuvDf7I',
1638 'info_dict': {
1639 'id': 'qEJwOuvDf7I',
f57b7835 1640 'ext': 'webm',
06b491eb
S
1641 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1642 'description': '',
1643 'upload_date': '20150404',
06b491eb
S
1644 },
1645 'params': {
1646 'skip_download': 'requires avconv',
e323cf3f
S
1647 },
1648 'skip': 'This live event has ended.',
06b491eb 1649 },
067aa17e 1650 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1651 {
1652 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1653 'info_dict': {
1654 'id': 'FIl7x6_3R5Y',
eb6793ba 1655 'ext': 'webm',
da77d856
S
1656 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1657 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1658 'duration': 220,
da77d856 1659 'upload_date': '20150625',
eb6793ba 1660 'formats': 'mincount:31',
da77d856 1661 },
eb6793ba 1662 'skip': 'not actual anymore',
2ee8f5d8 1663 },
8a1a26ce
YCH
1664 # DASH manifest with segment_list
1665 {
1666 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1667 'md5': '8ce563a1d667b599d21064e982ab9e31',
1668 'info_dict': {
1669 'id': 'CsmdDsKjzN8',
1670 'ext': 'mp4',
17ee98e1 1671 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce 1672 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
8a1a26ce
YCH
1673 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1674 },
1675 'params': {
1676 'youtube_include_dash_manifest': True,
1677 'format': '135', # bestvideo
be49068d
S
1678 },
1679 'skip': 'This live event has ended.',
2ee8f5d8 1680 },
cf7e015f 1681 {
6368e2e6 1682 # Multifeed videos (multiple cameras), URL can be of any Camera
7666b936 1683 # TODO: fix multifeed titles
6368e2e6 1684 'url': 'https://www.youtube.com/watch?v=zaPI8MvL8pg',
cf7e015f 1685 'info_dict': {
6368e2e6 1686 'id': 'zaPI8MvL8pg',
1687 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04',
1688 'description': 'md5:563ccbc698b39298481ca3c571169519',
cf7e015f
S
1689 },
1690 'playlist': [{
1691 'info_dict': {
6368e2e6 1692 'id': 'j5yGuxZ8lLU',
cf7e015f 1693 'ext': 'mp4',
6368e2e6 1694 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Chris)',
6368e2e6 1695 'description': 'md5:563ccbc698b39298481ca3c571169519',
6368e2e6 1696 'duration': 10120,
1697 'channel_follower_count': int,
1698 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1699 'availability': 'public',
1700 'playable_in_embed': True,
1701 'upload_date': '20131105',
6368e2e6 1702 'categories': ['Gaming'],
1703 'live_status': 'was_live',
1704 'tags': 'count:24',
1705 'release_timestamp': 1383701910,
1706 'thumbnail': 'https://i.ytimg.com/vi/j5yGuxZ8lLU/maxresdefault.jpg',
1707 'comment_count': int,
1708 'age_limit': 0,
1709 'like_count': int,
1710 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1711 'channel': 'WiiLikeToPlay',
1712 'view_count': int,
1713 'release_date': '20131106',
7666b936 1714 'uploader': 'WiiLikeToPlay',
1715 'uploader_id': '@WLTP',
1716 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1717 },
1718 }, {
1719 'info_dict': {
6368e2e6 1720 'id': 'zaPI8MvL8pg',
cf7e015f 1721 'ext': 'mp4',
6368e2e6 1722 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Tyson)',
6368e2e6 1723 'availability': 'public',
1724 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1725 'channel': 'WiiLikeToPlay',
6368e2e6 1726 'channel_follower_count': int,
1727 'description': 'md5:563ccbc698b39298481ca3c571169519',
1728 'duration': 10108,
1729 'age_limit': 0,
1730 'like_count': int,
1731 'tags': 'count:24',
1732 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
6368e2e6 1733 'release_timestamp': 1383701915,
1734 'comment_count': int,
1735 'upload_date': '20131105',
1736 'thumbnail': 'https://i.ytimg.com/vi/zaPI8MvL8pg/maxresdefault.jpg',
1737 'release_date': '20131106',
1738 'playable_in_embed': True,
1739 'live_status': 'was_live',
1740 'categories': ['Gaming'],
1741 'view_count': int,
7666b936 1742 'uploader': 'WiiLikeToPlay',
1743 'uploader_id': '@WLTP',
1744 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1745 },
1746 }, {
1747 'info_dict': {
6368e2e6 1748 'id': 'R7r3vfO7Hao',
cf7e015f 1749 'ext': 'mp4',
6368e2e6 1750 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Spencer)',
1751 'thumbnail': 'https://i.ytimg.com/vi/R7r3vfO7Hao/maxresdefault.jpg',
1752 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1753 'like_count': int,
1754 'availability': 'public',
1755 'playable_in_embed': True,
1756 'upload_date': '20131105',
1757 'description': 'md5:563ccbc698b39298481ca3c571169519',
6368e2e6 1758 'channel_follower_count': int,
1759 'tags': 'count:24',
1760 'release_date': '20131106',
6368e2e6 1761 'comment_count': int,
1762 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1763 'channel': 'WiiLikeToPlay',
1764 'categories': ['Gaming'],
1765 'release_timestamp': 1383701914,
1766 'live_status': 'was_live',
1767 'age_limit': 0,
1768 'duration': 10128,
1769 'view_count': int,
7666b936 1770 'uploader': 'WiiLikeToPlay',
1771 'uploader_id': '@WLTP',
1772 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1773 },
1774 }],
6368e2e6 1775 'params': {'skip_download': True},
cbaed4bb 1776 },
f9f49d87 1777 {
067aa17e 1778 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1779 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1780 'info_dict': {
1781 'id': 'gVfLd0zydlo',
1782 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1783 },
1784 'playlist_count': 2,
be49068d 1785 'skip': 'Not multifeed anymore',
f9f49d87 1786 },
cbaed4bb 1787 {
2d3d2997 1788 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1789 'only_matching': True,
0e49d9a6 1790 },
6d4fc66b 1791 {
2d3d2997 1792 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1793 'only_matching': True,
1794 },
0e49d9a6 1795 {
067aa17e 1796 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1797 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1798 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1799 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1800 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1801 'info_dict': {
1802 'id': 'lsguqyKfVQg',
1803 'ext': 'mp4',
1804 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1805 'alt_title': 'Dark Walk',
0e49d9a6 1806 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1807 'duration': 133,
0e49d9a6 1808 'upload_date': '20151119',
11f9be09 1809 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1810 'track': 'Dark Walk',
1811 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1812 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1813 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1814 'categories': ['Film & Animation'],
1815 'view_count': int,
1816 'live_status': 'not_live',
1817 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1818 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1819 'tags': 'count:13',
1820 'availability': 'public',
1821 'channel': 'IronSoulElf',
1822 'playable_in_embed': True,
1823 'like_count': int,
1824 'age_limit': 0,
6c73052c 1825 'channel_follower_count': int
0e49d9a6
LL
1826 },
1827 'params': {
1828 'skip_download': True,
1829 },
1830 },
61f92af1 1831 {
067aa17e 1832 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1833 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1834 'only_matching': True,
1835 },
313dfc45
LL
1836 {
1837 # Video with yt:stretch=17:0
1838 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1839 'info_dict': {
1840 'id': 'Q39EVAstoRM',
1841 'ext': 'mp4',
1842 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1843 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1844 'upload_date': '20151107',
313dfc45
LL
1845 },
1846 'params': {
1847 'skip_download': True,
1848 },
be49068d 1849 'skip': 'This video does not exist.',
313dfc45 1850 },
201c1459 1851 {
1852 # Video with incomplete 'yt:stretch=16:'
1853 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1854 'only_matching': True,
1855 },
7caf9830
S
1856 {
1857 # Video licensed under Creative Commons
1858 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1859 'info_dict': {
1860 'id': 'M4gD1WSo5mA',
1861 'ext': 'mp4',
1862 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1863 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1864 'duration': 721,
17322130 1865 'upload_date': '20150128',
7caf9830 1866 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1867 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1868 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1869 'like_count': int,
1870 'age_limit': 0,
1871 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1872 'channel': 'The Berkman Klein Center for Internet & Society',
1873 'availability': 'public',
1874 'view_count': int,
1875 'categories': ['Education'],
1876 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1877 'live_status': 'not_live',
1878 'playable_in_embed': True,
d5d1df8a 1879 'channel_follower_count': int,
1880 'chapters': list,
7666b936 1881 'uploader': 'The Berkman Klein Center for Internet & Society',
1882 'uploader_id': '@BKCHarvard',
1883 'uploader_url': 'https://www.youtube.com/@BKCHarvard',
7caf9830
S
1884 },
1885 'params': {
1886 'skip_download': True,
1887 },
1888 },
fd050249 1889 {
fd050249
S
1890 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1891 'info_dict': {
1892 'id': 'eQcmzGIKrzg',
1893 'ext': 'mp4',
1894 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1895 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1896 'duration': 4060,
17322130 1897 'upload_date': '20151120',
fd050249 1898 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1899 'playable_in_embed': True,
1900 'tags': 'count:12',
1901 'like_count': int,
1902 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1903 'age_limit': 0,
1904 'availability': 'public',
1905 'categories': ['News & Politics'],
1906 'channel': 'Bernie Sanders',
1907 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1908 'view_count': int,
1909 'live_status': 'not_live',
1910 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1911 'comment_count': int,
d5d1df8a 1912 'channel_follower_count': int,
1913 'chapters': list,
7666b936 1914 'uploader': 'Bernie Sanders',
1915 'uploader_url': 'https://www.youtube.com/@BernieSanders',
1916 'uploader_id': '@BernieSanders',
8213ce28 1917 'channel_is_verified': True,
14a14335 1918 'heatmap': 'count:100',
fd050249
S
1919 },
1920 'params': {
1921 'skip_download': True,
1922 },
1923 },
040ac686
S
1924 {
1925 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1926 'only_matching': True,
7f29cf54
S
1927 },
1928 {
067aa17e 1929 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1930 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1931 'only_matching': True,
6496ccb4
S
1932 },
1933 {
1934 # Rental video preview
1935 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1936 'info_dict': {
1937 'id': 'uGpuVWrhIzE',
1938 'ext': 'mp4',
1939 'title': 'Piku - Trailer',
1940 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1941 'upload_date': '20150811',
6496ccb4
S
1942 'license': 'Standard YouTube License',
1943 },
1944 'params': {
1945 'skip_download': True,
1946 },
eb6793ba 1947 'skip': 'This video is not available.',
022a5d66 1948 },
12afdc2a
S
1949 {
1950 # YouTube Red video with episode data
1951 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1952 'info_dict': {
1953 'id': 'iqKdEhx-dD4',
1954 'ext': 'mp4',
1955 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1956 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1957 'duration': 2085,
12afdc2a 1958 'upload_date': '20170118',
12afdc2a
S
1959 'series': 'Mind Field',
1960 'season_number': 1,
1961 'episode_number': 1,
976ae3ea 1962 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1963 'tags': 'count:12',
1964 'view_count': int,
1965 'availability': 'public',
1966 'age_limit': 0,
1967 'channel': 'Vsauce',
1968 'episode': 'Episode 1',
1969 'categories': ['Entertainment'],
1970 'season': 'Season 1',
1971 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1972 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1973 'like_count': int,
1974 'playable_in_embed': True,
1975 'live_status': 'not_live',
7666b936 1976 'channel_follower_count': int,
1977 'uploader': 'Vsauce',
1978 'uploader_url': 'https://www.youtube.com/@Vsauce',
1979 'uploader_id': '@Vsauce',
14a14335 1980 'comment_count': int,
8213ce28 1981 'channel_is_verified': True,
12afdc2a
S
1982 },
1983 'params': {
1984 'skip_download': True,
1985 },
1986 'expected_warnings': [
1987 'Skipping DASH manifest',
1988 ],
1989 },
c7121fa7
S
1990 {
1991 # The following content has been identified by the YouTube community
1992 # as inappropriate or offensive to some audiences.
1993 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1994 'info_dict': {
1995 'id': '6SJNVb0GnPI',
1996 'ext': 'mp4',
1997 'title': 'Race Differences in Intelligence',
1998 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1999 'duration': 965,
2000 'upload_date': '20140124',
c7121fa7
S
2001 },
2002 'params': {
2003 'skip_download': True,
2004 },
545cc85d 2005 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 2006 },
022a5d66
S
2007 {
2008 # itag 212
2009 'url': '1t24XAntNCY',
2010 'only_matching': True,
fd5c4aab
S
2011 },
2012 {
2013 # geo restricted to JP
2014 'url': 'sJL6WA-aGkQ',
2015 'only_matching': True,
2016 },
cd5a74a2
S
2017 {
2018 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
2019 'only_matching': True,
2020 },
bc2ca1bb 2021 {
2022 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
2023 'only_matching': True,
2024 },
2025 {
2026 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
2027 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
2028 'only_matching': True,
2029 },
825cd268
RA
2030 {
2031 # DRM protected
2032 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
2033 'only_matching': True,
4fe54c12
S
2034 },
2035 {
2036 # Video with unsupported adaptive stream type formats
2037 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
2038 'info_dict': {
2039 'id': 'Z4Vy8R84T1U',
2040 'ext': 'mp4',
2041 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
2042 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2043 'duration': 433,
2044 'upload_date': '20130923',
4fe54c12
S
2045 'formats': 'maxcount:10',
2046 },
2047 'params': {
2048 'skip_download': True,
2049 'youtube_include_dash_manifest': False,
2050 },
5429d6a9 2051 'skip': 'not actual anymore',
5caabd3c 2052 },
2053 {
822b9d9c 2054 # Youtube Music Auto-generated description
7666b936 2055 # TODO: fix metadata extraction
5caabd3c 2056 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2057 'info_dict': {
2058 'id': 'MgNrAu2pzNs',
2059 'ext': 'mp4',
2060 'title': 'Voyeur Girl',
2061 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
2062 'upload_date': '20190312',
5caabd3c 2063 'artist': 'Stephen',
2064 'track': 'Voyeur Girl',
2065 'album': 'it\'s too much love to know my dear',
2066 'release_date': '20190313',
2067 'release_year': 2019,
976ae3ea 2068 'alt_title': 'Voyeur Girl',
2069 'view_count': int,
976ae3ea 2070 'playable_in_embed': True,
2071 'like_count': int,
2072 'categories': ['Music'],
2073 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
7666b936 2074 'channel': 'Stephen', # TODO: should be "Stephen - Topic"
2075 'uploader': 'Stephen',
976ae3ea 2076 'availability': 'public',
2077 'creator': 'Stephen',
2078 'duration': 169,
2079 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
2080 'age_limit': 0,
2081 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2082 'tags': 'count:11',
2083 'live_status': 'not_live',
6c73052c 2084 'channel_follower_count': int
5caabd3c 2085 },
2086 'params': {
2087 'skip_download': True,
2088 },
2089 },
66b48727
RA
2090 {
2091 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
2092 'only_matching': True,
2093 },
011e75e6
S
2094 {
2095 # invalid -> valid video id redirection
2096 'url': 'DJztXj2GPfl',
2097 'info_dict': {
2098 'id': 'DJztXj2GPfk',
2099 'ext': 'mp4',
2100 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
2101 'description': 'md5:bf577a41da97918e94fa9798d9228825',
2102 'upload_date': '20090125',
011e75e6
S
2103 'artist': 'Panjabi MC',
2104 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
2105 'album': 'Beware of the Boys (Mundian To Bach Ke)',
2106 },
2107 'params': {
2108 'skip_download': True,
2109 },
545cc85d 2110 'skip': 'Video unavailable',
ea74e00b
DP
2111 },
2112 {
2113 # empty description results in an empty string
2114 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
2115 'info_dict': {
2116 'id': 'x41yOUIvK2k',
2117 'ext': 'mp4',
2118 'title': 'IMG 3456',
2119 'description': '',
2120 'upload_date': '20170613',
976ae3ea 2121 'view_count': int,
2122 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
976ae3ea 2123 'like_count': int,
2124 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
2125 'tags': [],
2126 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
2127 'availability': 'public',
2128 'age_limit': 0,
2129 'categories': ['Pets & Animals'],
2130 'duration': 7,
2131 'playable_in_embed': True,
2132 'live_status': 'not_live',
7666b936 2133 'channel': 'l\'Or Vert asbl',
2134 'channel_follower_count': int,
2135 'uploader': 'l\'Or Vert asbl',
2136 'uploader_url': 'https://www.youtube.com/@ElevageOrVert',
2137 'uploader_id': '@ElevageOrVert',
ea74e00b
DP
2138 },
2139 'params': {
2140 'skip_download': True,
2141 },
2142 },
a0566bbf 2143 {
29f7c58a 2144 # with '};' inside yt initial data (see [1])
2145 # see [2] for an example with '};' inside ytInitialPlayerResponse
2146 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2147 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 2148 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2149 'info_dict': {
2150 'id': 'CHqg6qOn4no',
2151 'ext': 'mp4',
2152 'title': 'Part 77 Sort a list of simple types in c#',
2153 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2154 'upload_date': '20130831',
976ae3ea 2155 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2156 'like_count': int,
976ae3ea 2157 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2158 'live_status': 'not_live',
2159 'categories': ['Education'],
2160 'availability': 'public',
2161 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2162 'tags': 'count:12',
2163 'playable_in_embed': True,
2164 'age_limit': 0,
2165 'view_count': int,
2166 'duration': 522,
2167 'channel': 'kudvenkat',
12a1b225 2168 'comment_count': int,
d5d1df8a 2169 'channel_follower_count': int,
2170 'chapters': list,
7666b936 2171 'uploader': 'kudvenkat',
2172 'uploader_url': 'https://www.youtube.com/@Csharp-video-tutorialsBlogspot',
2173 'uploader_id': '@Csharp-video-tutorialsBlogspot',
8213ce28 2174 'channel_is_verified': True,
14a14335 2175 'heatmap': 'count:100',
a0566bbf 2176 },
2177 'params': {
2178 'skip_download': True,
2179 },
2180 },
29f7c58a 2181 {
2182 # another example of '};' in ytInitialData
2183 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2184 'only_matching': True,
2185 },
2186 {
2187 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2188 'only_matching': True,
2189 },
545cc85d 2190 {
cc2db878 2191 # https://github.com/ytdl-org/youtube-dl/pull/28094
2192 'url': 'OtqTfy26tG0',
2193 'info_dict': {
2194 'id': 'OtqTfy26tG0',
2195 'ext': 'mp4',
2196 'title': 'Burn Out',
2197 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2198 'upload_date': '20141120',
cc2db878 2199 'artist': 'The Cinematic Orchestra',
2200 'track': 'Burn Out',
2201 'album': 'Every Day',
976ae3ea 2202 'like_count': int,
2203 'live_status': 'not_live',
2204 'alt_title': 'Burn Out',
2205 'duration': 614,
2206 'age_limit': 0,
2207 'view_count': int,
2208 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2209 'creator': 'The Cinematic Orchestra',
2210 'channel': 'The Cinematic Orchestra',
2211 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2212 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2213 'availability': 'public',
2214 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2215 'categories': ['Music'],
2216 'playable_in_embed': True,
7666b936 2217 'channel_follower_count': int,
2218 'uploader': 'The Cinematic Orchestra',
2219 'comment_count': int,
cc2db878 2220 },
2221 'params': {
2222 'skip_download': True,
2223 },
545cc85d 2224 },
bc2ca1bb 2225 {
2226 # controversial video, only works with bpctr when authenticated with cookies
2227 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2228 'only_matching': True,
2229 },
a1a7907b 2230 {
2231 # controversial video, requires bpctr/contentCheckOk
2232 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2233 'info_dict': {
2234 'id': 'SZJvDhaSDnc',
2235 'ext': 'mp4',
2236 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2237 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
a1a7907b 2238 'upload_date': '20140716',
976ae3ea 2239 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2240 'duration': 170,
2241 'categories': ['News & Politics'],
976ae3ea 2242 'view_count': int,
2243 'channel': 'CBS Mornings',
2244 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2245 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2246 'age_limit': 18,
2247 'availability': 'needs_auth',
2248 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2249 'like_count': int,
2250 'live_status': 'not_live',
2251 'playable_in_embed': True,
7666b936 2252 'channel_follower_count': int,
2253 'uploader': 'CBS Mornings',
2254 'uploader_url': 'https://www.youtube.com/@CBSMornings',
2255 'uploader_id': '@CBSMornings',
14a14335 2256 'comment_count': int,
8213ce28 2257 'channel_is_verified': True,
a1a7907b 2258 }
2259 },
f7ad7160 2260 {
2261 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2262 'url': 'cBvYw8_A0vQ',
2263 'info_dict': {
2264 'id': 'cBvYw8_A0vQ',
2265 'ext': 'mp4',
2266 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2267 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2268 'upload_date': '20201120',
976ae3ea 2269 'duration': 1456,
2270 'categories': ['Travel & Events'],
2271 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2272 'view_count': int,
2273 'channel': 'Walk around Japan',
2274 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2275 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2276 'age_limit': 0,
2277 'availability': 'public',
2278 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2279 'live_status': 'not_live',
2280 'playable_in_embed': True,
7666b936 2281 'channel_follower_count': int,
2282 'uploader': 'Walk around Japan',
2283 'uploader_url': 'https://www.youtube.com/@walkaroundjapan7124',
2284 'uploader_id': '@walkaroundjapan7124',
f7ad7160 2285 },
2286 'params': {
2287 'skip_download': True,
2288 },
0fb983f6 2289 }, {
2290 # Has multiple audio streams
2291 'url': 'WaOKSUlf4TM',
2292 'only_matching': True
9297939e 2293 }, {
2294 # Requires Premium: has format 141 when requested using YTM url
2295 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2296 'only_matching': True
2297 }, {
120916da 2298 # multiple subtitles with same lang_code
2299 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2300 'only_matching': True,
109dd3b2 2301 }, {
2302 # Force use android client fallback
2303 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2304 'info_dict': {
2305 'id': 'YOelRv7fMxY',
11f9be09 2306 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2307 'ext': '3gp',
2308 'upload_date': '20210624',
2309 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
109dd3b2 2310 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2311 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2312 'duration': 596,
2313 'categories': ['Entertainment'],
976ae3ea 2314 'view_count': int,
2315 'channel': 'colinfurze',
2316 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2317 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2318 'age_limit': 0,
2319 'availability': 'public',
2320 'like_count': int,
2321 'live_status': 'not_live',
2322 'playable_in_embed': True,
d5d1df8a 2323 'channel_follower_count': int,
2324 'chapters': list,
7666b936 2325 'uploader': 'colinfurze',
2326 'uploader_url': 'https://www.youtube.com/@colinfurze',
2327 'uploader_id': '@colinfurze',
14a14335 2328 'comment_count': int,
8213ce28 2329 'channel_is_verified': True,
14a14335 2330 'heatmap': 'count:100',
109dd3b2 2331 },
2332 'params': {
2333 'format': '17', # 3gp format available on android
2334 'extractor_args': {'youtube': {'player_client': ['android']}},
2335 },
120916da 2336 },
109dd3b2 2337 {
2338 # Skip download of additional client configs (remix client config in this case)
2339 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2340 'only_matching': True,
2341 'params': {
2342 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2343 },
8fc54b12 2344 }, {
2345 # shorts
2346 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2347 'only_matching': True,
9222c381 2348 }, {
2349 'note': 'Storyboards',
2350 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2351 'info_dict': {
2352 'id': '5KLPxDtMqe8',
2353 'ext': 'mhtml',
2354 'format_id': 'sb0',
2355 'title': 'Your Brain is Plastic',
9222c381 2356 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2357 'upload_date': '20140324',
976ae3ea 2358 'like_count': int,
2359 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2360 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2361 'view_count': int,
2362 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2363 'playable_in_embed': True,
2364 'tags': 'count:12',
976ae3ea 2365 'availability': 'public',
2366 'channel': 'SciShow',
2367 'live_status': 'not_live',
2368 'duration': 248,
2369 'categories': ['Education'],
2370 'age_limit': 0,
d5d1df8a 2371 'channel_follower_count': int,
2372 'chapters': list,
7666b936 2373 'uploader': 'SciShow',
2374 'uploader_url': 'https://www.youtube.com/@SciShow',
2375 'uploader_id': '@SciShow',
14a14335 2376 'comment_count': int,
8213ce28 2377 'channel_is_verified': True,
14a14335 2378 'heatmap': 'count:100',
9222c381 2379 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2380 }, {
2381 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2382 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2383 'info_dict': {
2384 'id': '2NUZ8W2llS4',
2385 'ext': 'mp4',
2386 'title': 'The NP that test your phone performance 🙂',
2387 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
992f9a73 2388 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2389 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2390 'duration': 21,
2391 'view_count': int,
2392 'age_limit': 0,
2393 'categories': ['Gaming'],
2394 'tags': 'count:23',
2395 'playable_in_embed': True,
2396 'live_status': 'not_live',
2397 'upload_date': '20220103',
2398 'like_count': int,
2399 'availability': 'public',
2400 'channel': 'Leon Nguyen',
2401 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2402 'comment_count': int,
7666b936 2403 'channel_follower_count': int,
2404 'uploader': 'Leon Nguyen',
2405 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
2406 'uploader_id': '@LeonNguyen',
14a14335 2407 'heatmap': 'count:100',
992f9a73 2408 }
1ff88b7a 2409 }, {
2410 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2411 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2412 'info_dict': {
2413 'id': '2NUZ8W2llS4',
2414 'ext': 'mp4',
2415 'title': 'The NP that test your phone performance 🙂',
2416 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
1ff88b7a 2417 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2418 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2419 'duration': 21,
2420 'view_count': int,
2421 'age_limit': 0,
2422 'categories': ['Gaming'],
2423 'tags': 'count:23',
2424 'playable_in_embed': True,
2425 'live_status': 'not_live',
2426 'upload_date': '20220102',
2427 'like_count': int,
2428 'availability': 'public',
2429 'channel': 'Leon Nguyen',
2430 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2431 'comment_count': int,
7666b936 2432 'channel_follower_count': int,
2433 'uploader': 'Leon Nguyen',
2434 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
2435 'uploader_id': '@LeonNguyen',
14a14335 2436 'heatmap': 'count:100',
1ff88b7a 2437 },
2438 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
992f9a73 2439 }, {
2440 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2441 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2442 'info_dict': {
2443 'id': 'mzZzzBU6lrM',
2444 'ext': 'mp4',
2445 'title': 'I Met GeorgeNotFound In Real Life...',
7666b936 2446 'description': 'md5:978296ec9783a031738b684d4ebf302d',
992f9a73 2447 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2448 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2449 'duration': 955,
2450 'view_count': int,
2451 'age_limit': 0,
2452 'categories': ['Entertainment'],
2453 'tags': 'count:26',
2454 'playable_in_embed': True,
2455 'live_status': 'not_live',
2456 'release_timestamp': 1641172509,
2457 'release_date': '20220103',
2458 'upload_date': '20220103',
2459 'like_count': int,
2460 'availability': 'public',
2461 'channel': 'Quackity',
2462 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
7666b936 2463 'channel_follower_count': int,
2464 'uploader': 'Quackity',
2465 'uploader_id': '@Quackity',
2466 'uploader_url': 'https://www.youtube.com/@Quackity',
14a14335 2467 'comment_count': int,
8213ce28 2468 'channel_is_verified': True,
14a14335 2469 'heatmap': 'count:100',
992f9a73 2470 }
2471 },
2472 { # continuous livestream. Microformat upload date should be preferred.
2473 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2474 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2475 'info_dict': {
2476 'id': 'kgx4WGK0oNU',
2477 '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}',
2478 'ext': 'mp4',
2479 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2480 'availability': 'public',
2481 'age_limit': 0,
2482 'release_timestamp': 1637975704,
2483 'upload_date': '20210619',
2484 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2485 'live_status': 'is_live',
2486 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
992f9a73 2487 'channel': 'Abao in Tokyo',
2488 'channel_follower_count': int,
2489 'release_date': '20211127',
2490 'tags': 'count:39',
2491 'categories': ['People & Blogs'],
2492 'like_count': int,
992f9a73 2493 'view_count': int,
2494 'playable_in_embed': True,
2495 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
867c66ff 2496 'concurrent_view_count': int,
7666b936 2497 'uploader': 'Abao in Tokyo',
2498 'uploader_url': 'https://www.youtube.com/@abaointokyo',
2499 'uploader_id': '@abaointokyo',
992f9a73 2500 },
2501 'params': {'skip_download': True}
6e634cbe 2502 }, {
2503 # Story. Requires specific player params to work.
ee27297f 2504 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
6e634cbe 2505 'info_dict': {
ee27297f 2506 'id': 'vv8qTUWmulI',
6e634cbe 2507 'ext': 'mp4',
ee27297f 2508 'availability': 'unlisted',
2509 'view_count': int,
2510 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2511 'upload_date': '20220526',
2512 'categories': ['Education'],
2513 'title': 'Story',
2514 'channel': 'IT\'S HISTORY',
2515 'description': '',
ee27297f 2516 'duration': 12,
6e634cbe 2517 'playable_in_embed': True,
6e634cbe 2518 'age_limit': 0,
6e634cbe 2519 'live_status': 'not_live',
ee27297f 2520 'tags': [],
2521 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
ee27297f 2522 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
12a1b225
A
2523 },
2524 'skip': 'stories get removed after some period of time',
ee27297f 2525 }, {
2526 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2527 'info_dict': {
2528 'id': 'tjjjtzRLHvA',
2529 'ext': 'mp4',
2530 'title': 'ハッシュタグ無し };if window.ytcsi',
2531 'upload_date': '20220323',
2532 'like_count': int,
2533 'availability': 'unlisted',
7666b936 2534 'channel': 'Lesmiscore',
2535 'thumbnail': r're:^https?://.*\.jpg',
ee27297f 2536 'age_limit': 0,
ee27297f 2537 'categories': ['Music'],
6e634cbe 2538 'view_count': int,
2539 'description': '',
ee27297f 2540 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2541 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2542 'live_status': 'not_live',
2543 'playable_in_embed': True,
2544 'channel_follower_count': int,
2545 'duration': 6,
2546 'tags': [],
7666b936 2547 'uploader_id': '@lesmiscore',
2548 'uploader': 'Lesmiscore',
2549 'uploader_url': 'https://www.youtube.com/@lesmiscore',
6e634cbe 2550 }
c26f9b99 2551 }, {
2552 # Prefer primary title+description language metadata by default
2553 # Do not prefer translated description if primary is empty
2554 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2555 'info_dict': {
2556 'id': 'el3E4MbxRqQ',
2557 'ext': 'mp4',
2558 'title': 'dlp test video 2 - primary sv no desc',
2559 'description': '',
2560 'channel': 'cole-dlp-test-acc',
2561 'tags': [],
2562 'view_count': int,
2563 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2564 'like_count': int,
2565 'playable_in_embed': True,
2566 'availability': 'unlisted',
7666b936 2567 'thumbnail': r're:^https?://.*\.jpg',
c26f9b99 2568 'age_limit': 0,
2569 'duration': 5,
c26f9b99 2570 'live_status': 'not_live',
2571 'upload_date': '20220908',
2572 'categories': ['People & Blogs'],
c26f9b99 2573 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
7666b936 2574 'uploader_url': 'https://www.youtube.com/@coletdjnz',
2575 'uploader_id': '@coletdjnz',
2576 'uploader': 'cole-dlp-test-acc',
c26f9b99 2577 },
2578 'params': {'skip_download': True}
2579 }, {
2580 # Extractor argument: prefer translated title+description
2581 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2582 'info_dict': {
2583 'id': 'gHKT4uU8Zng',
2584 'ext': 'mp4',
2585 'channel': 'cole-dlp-test-acc',
2586 'tags': [],
2587 'duration': 5,
2588 'live_status': 'not_live',
2589 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2590 'upload_date': '20220728',
c26f9b99 2591 'view_count': int,
2592 'categories': ['People & Blogs'],
7666b936 2593 'thumbnail': r're:^https?://.*\.jpg',
c26f9b99 2594 'title': 'dlp test video title translated (fr)',
2595 'availability': 'public',
c26f9b99 2596 'age_limit': 0,
2597 'description': 'dlp test video description translated (fr)',
2598 'playable_in_embed': True,
2599 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
7666b936 2600 'uploader_url': 'https://www.youtube.com/@coletdjnz',
2601 'uploader_id': '@coletdjnz',
2602 'uploader': 'cole-dlp-test-acc',
c26f9b99 2603 },
2604 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2605 'expected_warnings': [r'Preferring "fr" translated fields'],
a4166234 2606 }, {
2607 'note': '6 channel audio',
2608 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2609 'only_matching': True,
a4894d3e 2610 }, {
2611 'note': 'Multiple HLS formats with same itag',
2612 'url': 'https://www.youtube.com/watch?v=kX3nB4PpJko',
2613 'info_dict': {
2614 'id': 'kX3nB4PpJko',
2615 'ext': 'mp4',
2616 'categories': ['Entertainment'],
2617 'description': 'md5:e8031ff6e426cdb6a77670c9b81f6fa6',
a4894d3e 2618 'live_status': 'not_live',
2619 'duration': 937,
2620 'channel_follower_count': int,
2621 'thumbnail': 'https://i.ytimg.com/vi_webp/kX3nB4PpJko/maxresdefault.webp',
2622 'title': 'Last To Take Hand Off Jet, Keeps It!',
2623 'channel': 'MrBeast',
2624 'playable_in_embed': True,
2625 'view_count': int,
2626 'upload_date': '20221112',
a4894d3e 2627 'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA',
2628 'age_limit': 0,
2629 'availability': 'public',
2630 'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA',
2631 'like_count': int,
2632 'tags': [],
7666b936 2633 'uploader': 'MrBeast',
2634 'uploader_url': 'https://www.youtube.com/@MrBeast',
2635 'uploader_id': '@MrBeast',
14a14335 2636 'comment_count': int,
8213ce28 2637 'channel_is_verified': True,
14a14335 2638 'heatmap': 'count:100',
a4894d3e 2639 },
2640 'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
9bb85699 2641 }, {
2642 'note': 'Audio formats with Dynamic Range Compression',
2643 'url': 'https://www.youtube.com/watch?v=Tq92D6wQ1mg',
2644 'info_dict': {
2645 'id': 'Tq92D6wQ1mg',
7666b936 2646 'ext': 'webm',
9bb85699 2647 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
2648 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2649 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2650 'channel_follower_count': int,
2651 'description': 'md5:17eccca93a786d51bc67646756894066',
2652 'upload_date': '20191228',
9bb85699 2653 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
2654 'playable_in_embed': True,
2655 'like_count': int,
2656 'categories': ['Entertainment'],
2657 'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
2658 'age_limit': 18,
2659 'channel': 'Projekt Melody',
9bb85699 2660 'view_count': int,
2661 'availability': 'needs_auth',
2662 'comment_count': int,
2663 'live_status': 'not_live',
9bb85699 2664 'duration': 106,
7666b936 2665 'uploader': 'Projekt Melody',
2666 'uploader_id': '@ProjektMelody',
2667 'uploader_url': 'https://www.youtube.com/@ProjektMelody',
9bb85699 2668 },
2669 'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
dad2210c 2670 },
2671 {
2672 'url': 'https://www.youtube.com/live/qVv6vCqciTM',
2673 'info_dict': {
2674 'id': 'qVv6vCqciTM',
2675 'ext': 'mp4',
2676 'age_limit': 0,
dad2210c 2677 'comment_count': int,
2678 'chapters': 'count:13',
2679 'upload_date': '20221223',
2680 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
2681 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
dad2210c 2682 'like_count': int,
2683 'release_date': '20221223',
2684 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
2685 '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】',
2686 'view_count': int,
2687 'playable_in_embed': True,
2688 'duration': 4438,
2689 'availability': 'public',
2690 'channel_follower_count': int,
2691 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2692 'categories': ['Entertainment'],
2693 'live_status': 'was_live',
2694 'release_timestamp': 1671793345,
2695 'channel': 'さなちゃんねる',
2696 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
2697 'uploader': 'さなちゃんねる',
7666b936 2698 'uploader_url': 'https://www.youtube.com/@sana_natori',
2699 'uploader_id': '@sana_natori',
8213ce28 2700 'channel_is_verified': True,
14a14335 2701 'heatmap': 'count:100',
7666b936 2702 },
2703 },
2704 {
2705 # Fallbacks when webpage and web client is unavailable
2706 'url': 'https://www.youtube.com/watch?v=wSSmNUl9Snw',
2707 'info_dict': {
2708 'id': 'wSSmNUl9Snw',
2709 'ext': 'mp4',
2710 # 'categories': ['Science & Technology'],
2711 'view_count': int,
2712 'chapters': 'count:2',
2713 'channel': 'Scott Manley',
2714 'like_count': int,
2715 'age_limit': 0,
2716 # 'availability': 'public',
2717 'channel_follower_count': int,
2718 'live_status': 'not_live',
2719 'upload_date': '20170831',
2720 'duration': 682,
2721 'tags': 'count:8',
2722 'uploader_url': 'https://www.youtube.com/@scottmanley',
2723 'description': 'md5:f4bed7b200404b72a394c2f97b782c02',
2724 'uploader': 'Scott Manley',
2725 'uploader_id': '@scottmanley',
2726 'title': 'The Computer Hack That Saved Apollo 14',
2727 'channel_id': 'UCxzC4EngIsMrPmbm6Nxvb-A',
2728 'thumbnail': r're:^https?://.*\.webp',
2729 'channel_url': 'https://www.youtube.com/channel/UCxzC4EngIsMrPmbm6Nxvb-A',
2730 'playable_in_embed': True,
14a14335 2731 'comment_count': int,
8213ce28 2732 'channel_is_verified': True,
14a14335 2733 'heatmap': 'count:100',
7666b936 2734 },
2735 'params': {
2736 'extractor_args': {'youtube': {'player_client': ['android'], 'player_skip': ['webpage']}},
dad2210c 2737 },
2738 },
2eb88d95
PH
2739 ]
2740
f2e8dbcc 2741 _WEBPAGE_TESTS = [
2742 # YouTube <object> embed
2743 {
2744 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2745 'md5': '873c81d308b979f0e23ee7e620b312a3',
2746 'info_dict': {
2747 'id': 'msN87y-iEx0',
2748 'ext': 'mp4',
2749 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2750 'upload_date': '20080526',
2751 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
f2e8dbcc 2752 'age_limit': 0,
2753 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2754 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2755 'playable_in_embed': True,
2756 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2757 'like_count': int,
2758 'comment_count': int,
2759 'channel': 'Christopher Sykes',
2760 'live_status': 'not_live',
2761 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2762 'availability': 'public',
2763 'duration': 195,
2764 'view_count': int,
2765 'categories': ['Science & Technology'],
2766 'channel_follower_count': int,
7666b936 2767 'uploader': 'Christopher Sykes',
2768 'uploader_url': 'https://www.youtube.com/@ChristopherSykesDocumentaries',
2769 'uploader_id': '@ChristopherSykesDocumentaries',
14a14335 2770 'heatmap': 'count:100',
f2e8dbcc 2771 },
2772 'params': {
2773 'skip_download': True,
2774 }
2775 },
2776 ]
2777
201c1459 2778 @classmethod
2779 def suitable(cls, url):
4dfbf869 2780 from ..utils import parse_qs
2781
201c1459 2782 qs = parse_qs(url)
2783 if qs.get('list', [None])[0]:
2784 return False
86e5f3ed 2785 return super().suitable(url)
201c1459 2786
e0df6211 2787 def __init__(self, *args, **kwargs):
86e5f3ed 2788 super().__init__(*args, **kwargs)
545cc85d 2789 self._code_cache = {}
83799698 2790 self._player_cache = {}
e0df6211 2791
4d37720a 2792 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
adbc4ec4 2793 lock = threading.Lock()
185bf310 2794 start_time = time.time()
adbc4ec4
THD
2795 formats = [f for f in formats if f.get('is_from_start')]
2796
185bf310 2797 def refetch_manifest(format_id, delay):
2798 nonlocal formats, start_time, is_live
2799 if time.time() <= start_time + delay:
adbc4ec4
THD
2800 return
2801
2802 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
6839ae1f 2803 video_details = traverse_obj(prs, (..., 'videoDetails'), expected_type=dict)
adbc4ec4
THD
2804 microformats = traverse_obj(
2805 prs, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 2806 expected_type=dict)
4d37720a
L
2807 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2808 is_live = live_status == 'is_live'
185bf310 2809 start_time = time.time()
adbc4ec4 2810
185bf310 2811 def mpd_feed(format_id, delay):
adbc4ec4
THD
2812 """
2813 @returns (manifest_url, manifest_stream_number, is_live) or None
2814 """
253ac4ba 2815 for retry in self.RetryManager(fatal=False):
2816 with lock:
2817 refetch_manifest(format_id, delay)
2818
2819 f = next((f for f in formats if f['format_id'] == format_id), None)
2820 if not f:
2821 if not is_live:
2822 retry.error = f'{video_id}: Video is no longer live'
2823 else:
2824 retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
2825 continue
2826 return f['manifest_url'], f['manifest_stream_number'], is_live
2827 return None
adbc4ec4
THD
2828
2829 for f in formats:
4d37720a
L
2830 f['is_live'] = is_live
2831 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2832 live_start_time, mpd_feed, not is_live and f.copy())
2833 if is_live:
2834 f['fragments'] = gen
2835 f['protocol'] = 'http_dash_segments_generator'
2836 else:
2837 f['fragments'] = LazyList(gen({}))
2838 del f['is_from_start']
adbc4ec4 2839
4d37720a 2840 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
adbc4ec4
THD
2841 FETCH_SPAN, MAX_DURATION = 5, 432000
2842
2843 mpd_url, stream_number, is_live = None, None, True
2844
2845 begin_index = 0
2846 download_start_time = ctx.get('start') or time.time()
2847
2848 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2849 if lack_early_segments:
2850 self.report_warning(bug_reports_message(
2851 'Starting download from the last 120 hours of the live stream since '
2852 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2853 lack_early_segments = True
2854
2855 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2856 fragments, fragment_base_url = None, None
2857
a539f065 2858 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2859 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2860 # Obtain from MPD's maximum seq value
2861 old_mpd_url = mpd_url
185bf310 2862 last_error = ctx.pop('last_error', None)
14f25df2 2863 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
185bf310 2864 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2865 or (mpd_url, stream_number, False))
2866 if not refresh_sequence:
2867 if expire_fast and not is_live:
2868 return False, last_seq
2869 elif old_mpd_url == mpd_url:
2870 return True, last_seq
4d37720a
L
2871 if manifestless_orig_fmt:
2872 fmt_info = manifestless_orig_fmt
2873 else:
2874 try:
2875 fmts, _ = self._extract_mpd_formats_and_subtitles(
2876 mpd_url, None, note=False, errnote=False, fatal=False)
2877 except ExtractorError:
2878 fmts = None
2879 if not fmts:
2880 no_fragment_score += 2
2881 return False, last_seq
2882 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
adbc4ec4
THD
2883 fragments = fmt_info['fragments']
2884 fragment_base_url = fmt_info['fragment_base_url']
2885 assert fragment_base_url
2886
2887 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2888 return True, _last_seq
2889
4d37720a 2890 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
adbc4ec4
THD
2891 while is_live:
2892 fetch_time = time.time()
2893 if no_fragment_score > 30:
2894 return
2895 if last_segment_url:
2896 # Obtain from "X-Head-Seqnum" header value from each segment
2897 try:
2898 urlh = self._request_webpage(
2899 last_segment_url, None, note=False, errnote=False, fatal=False)
2900 except ExtractorError:
2901 urlh = None
2902 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2903 if last_seq is None:
a539f065 2904 no_fragment_score += 2
adbc4ec4
THD
2905 last_segment_url = None
2906 continue
2907 else:
a539f065
LNO
2908 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2909 no_fragment_score += 2
185bf310 2910 if not should_continue:
adbc4ec4
THD
2911 continue
2912
2913 if known_idx > last_seq:
2914 last_segment_url = None
2915 continue
2916
2917 last_seq += 1
2918
2919 if begin_index < 0 and known_idx < 0:
2920 # skip from the start when it's negative value
2921 known_idx = last_seq + begin_index
2922 if lack_early_segments:
2923 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2924 try:
2925 for idx in range(known_idx, last_seq):
2926 # do not update sequence here or you'll get skipped some part of it
a539f065 2927 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2928 if not should_continue:
adbc4ec4
THD
2929 known_idx = idx - 1
2930 raise ExtractorError('breaking out of outer loop')
2931 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2932 yield {
2933 'url': last_segment_url,
36195c44 2934 'fragment_count': last_seq,
adbc4ec4
THD
2935 }
2936 if known_idx == last_seq:
2937 no_fragment_score += 5
2938 else:
2939 no_fragment_score = 0
2940 known_idx = last_seq
2941 except ExtractorError:
2942 continue
2943
4d37720a
L
2944 if manifestless_orig_fmt:
2945 # Stop at the first iteration if running for post-live manifestless;
2946 # fragment count no longer increase since it starts
2947 break
2948
adbc4ec4
THD
2949 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2950
b6de707d 2951 def _extract_player_url(self, *ytcfgs, webpage=None):
2952 player_url = traverse_obj(
2953 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2954 get_all=False, expected_type=str)
11f9be09 2955 if not player_url:
b6de707d 2956 return
60f393e4 2957 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2958
b6de707d 2959 def _download_player_url(self, video_id, fatal=False):
2960 res = self._download_webpage(
2961 'https://www.youtube.com/iframe_api',
2962 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2963 if res:
2964 player_version = self._search_regex(
2965 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2966 if player_version:
2967 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2968
60064c53
PH
2969 def _signature_cache_id(self, example_sig):
2970 """ Return a string representation of a signature """
14f25df2 2971 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2972
e40c758c
S
2973 @classmethod
2974 def _extract_player_info(cls, player_url):
2975 for player_re in cls._PLAYER_INFO_RE:
2976 id_m = re.search(player_re, player_url)
2977 if id_m:
2978 break
2979 else:
c081b35c 2980 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2981 return id_m.group('id')
e40c758c 2982
404f611f 2983 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2984 player_id = self._extract_player_info(player_url)
2985 if player_id not in self._code_cache:
1276a43a 2986 code = self._download_webpage(
109dd3b2 2987 player_url, video_id, fatal=fatal,
2988 note='Downloading player ' + player_id,
2989 errnote='Download of %s failed' % player_url)
1276a43a 2990 if code:
2991 self._code_cache[player_id] = code
404f611f 2992 return self._code_cache.get(player_id)
109dd3b2 2993
e40c758c 2994 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2995 player_id = self._extract_player_info(player_url)
e0df6211 2996
c4417ddb 2997 # Read from filesystem cache
86e5f3ed 2998 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2999 assert os.path.basename(func_id) == func_id
a0e07d31 3000
ae61d108 3001 self.write_debug(f'Extracting signature function {func_id}')
580ce007 3002 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 3003
580ce007 3004 if not cache_spec:
3005 code = self._load_player(video_id, player_url)
404f611f 3006 if code:
109dd3b2 3007 res = self._parse_sig_js(code)
ac668111 3008 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 3009 cache_spec = [ord(c) for c in res(test_string)]
9809740b 3010 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 3011
3012 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 3013
60064c53 3014 def _print_sig_code(self, func, example_sig):
404f611f 3015 if not self.get_param('youtube_print_sig_code'):
3016 return
3017
edf3e38e
PH
3018 def gen_sig_code(idxs):
3019 def _genslice(start, end, step):
78caa52a 3020 starts = '' if start == 0 else str(start)
8bcc8756 3021 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 3022 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 3023 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
3024
3025 step = None
7af808a5
PH
3026 # Quelch pyflakes warnings - start will be set when step is set
3027 start = '(Never used)'
edf3e38e
PH
3028 for i, prev in zip(idxs[1:], idxs[:-1]):
3029 if step is not None:
3030 if i - prev == step:
3031 continue
3032 yield _genslice(start, prev, step)
3033 step = None
3034 continue
3035 if i - prev in [-1, 1]:
3036 step = i - prev
3037 start = prev
3038 continue
3039 else:
78caa52a 3040 yield 's[%d]' % prev
edf3e38e 3041 if step is None:
78caa52a 3042 yield 's[%d]' % i
edf3e38e
PH
3043 else:
3044 yield _genslice(start, i, step)
3045
ac668111 3046 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 3047 cache_res = func(test_string)
edf3e38e 3048 cache_spec = [ord(c) for c in cache_res]
78caa52a 3049 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 3050 signature_id_tuple = '(%s)' % (
14f25df2 3051 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 3052 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 3053 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 3054 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 3055
e0df6211
PH
3056 def _parse_sig_js(self, jscode):
3057 funcname = self._search_regex(
abefc03f
S
3058 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3059 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
3060 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
3061 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
4823ec9f 3062 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 3063 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f 3064 # Obsolete patterns
4823ec9f 3065 r'("|\')signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 3066 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
3067 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3068 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3069 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f 3070 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 3071 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
3072
3073 jsi = JSInterpreter(jscode)
3074 initial_function = jsi.extract_function(funcname)
e0df6211
PH
3075 return lambda s: initial_function([s])
3076
580ce007 3077 def _cached(self, func, *cache_id):
3078 def inner(*args, **kwargs):
3079 if cache_id not in self._player_cache:
3080 try:
3081 self._player_cache[cache_id] = func(*args, **kwargs)
3082 except ExtractorError as e:
3083 self._player_cache[cache_id] = e
3084 except Exception as e:
3085 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
3086
3087 ret = self._player_cache[cache_id]
3088 if isinstance(ret, Exception):
3089 raise ret
3090 return ret
3091 return inner
3092
545cc85d 3093 def _decrypt_signature(self, s, video_id, player_url):
257a2501 3094 """Turn the encrypted s field into a working signature"""
580ce007 3095 extract_sig = self._cached(
3096 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
3097 func = extract_sig(video_id, player_url, s)
3098 self._print_sig_code(func, s)
3099 return func(s)
404f611f 3100
3101 def _decrypt_nsig(self, s, video_id, player_url):
3102 """Turn the encrypted n field into a working signature"""
3103 if player_url is None:
3104 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 3105 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 3106
b505e851 3107 try:
3108 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
3109 except ExtractorError as e:
3110 raise ExtractorError('Unable to extract nsig function code', cause=e)
580ce007 3111 if self.get_param('youtube_print_sig_code'):
3112 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 3113
25836db6 3114 try:
3115 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
3116 ret = extract_nsig(jsi, func_code)(s)
3117 except JSInterpreter.Exception as e:
3118 try:
992dc6b4 3119 jsi = PhantomJSwrapper(self, timeout=5000)
25836db6 3120 except ExtractorError:
3121 raise e
3122 self.report_warning(
3123 f'Native nsig extraction failed: Trying with PhantomJS\n'
3124 f' n = {s} ; player = {player_url}', video_id)
0468a3b3 3125 self.write_debug(e, only_once=True)
25836db6 3126
3127 args, func_body = func_code
3128 ret = jsi.execute(
3129 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
3130 video_id=video_id, note='Executing signature code').strip()
580ce007 3131
3132 self.write_debug(f'Decrypted nsig {s} => {ret}')
3133 return ret
3134
90a1df30 3135 def _extract_n_function_name(self, jscode):
3136 funcname, idx = self._search_regex(
3137 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
3138 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
3139 if not idx:
3140 return funcname
3141
3142 return json.loads(js_to_json(self._search_regex(
cd810afe 3143 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])[,;]', jscode,
90a1df30 3144 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
3145
580ce007 3146 def _extract_n_function_code(self, video_id, player_url):
404f611f 3147 player_id = self._extract_player_info(player_url)
05deb747 3148 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
580ce007 3149 jscode = func_code or self._load_player(video_id, player_url)
3150 jsi = JSInterpreter(jscode)
404f611f 3151
3152 if func_code:
580ce007 3153 return jsi, player_id, func_code
404f611f 3154
b505e851 3155 func_name = self._extract_n_function_name(jscode)
3156
3157 # For redundancy
3158 func_code = self._search_regex(
3159 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
3160 # NB: The end of the regex is intentionally kept strict
3161 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
3162 jscode, 'nsig function', group=('var', 'code'), default=None)
3163 if func_code:
3164 func_code = ([func_code[0]], func_code[1])
3165 else:
3166 self.write_debug('Extracting nsig function with jsinterp')
3167 func_code = jsi.extract_function_code(func_name)
3168
580ce007 3169 self.cache.store('youtube-nsig', player_id, func_code)
3170 return jsi, player_id, func_code
3171
3172 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 3173 func = jsi.extract_function_from_code(*func_code)
f6ca640b 3174
580ce007 3175 def extract_nsig(s):
25836db6 3176 try:
3177 ret = func([s])
3178 except JSInterpreter.Exception:
3179 raise
3180 except Exception as e:
3181 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
3182
f6ca640b 3183 if ret.startswith('enhanced_except_'):
25836db6 3184 raise JSInterpreter.Exception('Signature function returned an exception')
f6ca640b 3185 return ret
580ce007 3186
3187 return extract_nsig
e0df6211 3188
109dd3b2 3189 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
3190 """
3191 Extract signatureTimestamp (sts)
3192 Required to tell API what sig/player version is in use.
3193 """
3194 sts = None
3195 if isinstance(ytcfg, dict):
3196 sts = int_or_none(ytcfg.get('STS'))
3197
3198 if not sts:
3199 # Attempt to extract from player
3200 if player_url is None:
3201 error_msg = 'Cannot extract signature timestamp without player_url.'
3202 if fatal:
3203 raise ExtractorError(error_msg)
3204 self.report_warning(error_msg)
3205 return
404f611f 3206 code = self._load_player(video_id, player_url, fatal=fatal)
3207 if code:
109dd3b2 3208 sts = int_or_none(self._search_regex(
3209 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
3210 'JS player signature timestamp', group='sts', fatal=fatal))
3211 return sts
3212
11f9be09 3213 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
3214 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
3215 label = 'fully ' if is_full else ''
3216 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
3217 expected_type=url_or_none)
3218 if not url:
3219 self.report_warning(f'Unable to mark {label}watched')
3220 return
14f25df2 3221 parsed_url = urllib.parse.urlparse(url)
3222 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
3223
3224 # cpn generation algorithm is reverse engineered from base.js.
3225 # In fact it works even with dummy cpn.
3226 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
3227 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
3228
3229 # # more consistent results setting it to right before the end
3230 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
3231
3232 qs.update({
3233 'ver': ['2'],
3234 'cpn': [cpn],
3235 'cmt': video_length,
3236 'el': 'detailpage', # otherwise defaults to "shorts"
3237 })
3238
3239 if is_full:
3240 # these seem to mark watchtime "history" in the real world
3241 # they're required, so send in a single value
3242 qs.update({
5318156f 3243 'st': 0,
06cc8f10
B
3244 'et': video_length,
3245 })
3246
14f25df2 3247 url = urllib.parse.urlunparse(
3248 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
3249
3250 self._download_webpage(
3251 url, video_id, f'Marking {label}watched',
3252 'Unable to mark watched', fatal=False)
d77ab8e2 3253
bfd973ec 3254 @classmethod
3255 def _extract_from_webpage(cls, url, webpage):
3256 # Invidious Instances
3257 # https://github.com/yt-dlp/yt-dlp/issues/195
3258 # https://github.com/iv-org/invidious/pull/1730
3259 mobj = re.search(
3260 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
3261 webpage)
3262 if mobj:
3263 yield cls.url_result(mobj.group('url'), cls)
3264 raise cls.StopExtraction()
3265
3266 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
3267
3268 # lazyYT YouTube embed
bfd973ec 3269 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3270 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
3271
3272 # Wordpress "YouTube Video Importer" plugin
bfd973ec 3273 for m in re.findall(r'''(?x)<div[^>]+
3274 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
3275 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
3276 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 3277
97665381
PH
3278 @classmethod
3279 def extract_id(cls, url):
ae61d108 3280 video_id = cls.get_temp_id(url)
3281 if not video_id:
3282 raise ExtractorError(f'Invalid URL: {url}')
3283 return video_id
c5e8d7af 3284
7c365c21 3285 def _extract_chapters_from_json(self, data, duration):
3286 chapter_list = traverse_obj(
3287 data, (
3288 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3289 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3290 ), expected_type=list)
3291
22ccd542 3292 return self._extract_chapters_helper(
7c365c21 3293 chapter_list,
22ccd542 3294 start_function=lambda chapter: float_or_none(
7c365c21 3295 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
22ccd542 3296 title_function=lambda chapter: traverse_obj(
7c365c21 3297 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3298 duration=duration)
3299
3300 def _extract_chapters_from_engagement_panel(self, data, duration):
3301 content_list = traverse_obj(
8bdd16b4 3302 data,
7c365c21 3303 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
6839ae1f 3304 expected_type=list)
052e1350 3305 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3306 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 3307
1890fc63 3308 return next(filter(None, (
22ccd542 3309 self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3310 chapter_time, chapter_title, duration)
1890fc63 3311 for contents in content_list)), [])
7c365c21 3312
5caf30db
A
3313 def _extract_heatmap_from_player_overlay(self, data):
3314 content_list = traverse_obj(data, (
3315 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer', 'decoratedPlayerBarRenderer', 'playerBar',
3316 'multiMarkersPlayerBarRenderer', 'markersMap', ..., 'value', 'heatmap', 'heatmapRenderer', 'heatMarkers', {list}))
3317 return next(filter(None, (
3318 traverse_obj(contents, (..., 'heatMarkerRenderer', {
3319 'start_time': ('timeRangeStartMillis', {functools.partial(float_or_none, scale=1000)}),
3320 'end_time': {lambda x: (x['timeRangeStartMillis'] + x['markerDurationMillis']) / 1000},
3321 'value': ('heatMarkerIntensityScoreNormalized', {float_or_none}),
3322 })) for contents in content_list)), None)
3323
a1c5d2ca
M
3324 def _extract_comment(self, comment_renderer, parent=None):
3325 comment_id = comment_renderer.get('commentId')
3326 if not comment_id:
3327 return
fe93e2c4 3328
c35448b7 3329 info = {
3330 'id': comment_id,
3331 'text': self._get_text(comment_renderer, 'contentText'),
3332 'like_count': self._get_count(comment_renderer, 'voteCount'),
3333 'author_id': traverse_obj(comment_renderer, ('authorEndpoint', 'browseEndpoint', 'browseId', {self.ucid_or_none})),
3334 'author': self._get_text(comment_renderer, 'authorText'),
3335 'author_thumbnail': traverse_obj(comment_renderer, ('authorThumbnail', 'thumbnails', -1, 'url', {url_or_none})),
3336 'parent': parent or 'root',
3337 }
fe93e2c4 3338
c26f9b99 3339 # Timestamp is an estimate calculated from the current time and time_text
3340 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3341 timestamp = self._parse_time_text(time_text)
3342
c35448b7 3343 info.update({
3344 # FIXME: non-standard, but we need a way of showing that it is an estimate.
3345 '_time_text': time_text,
3346 'timestamp': timestamp,
3347 })
fe93e2c4 3348
c35448b7 3349 info['author_url'] = urljoin(
3350 'https://www.youtube.com', traverse_obj(comment_renderer, ('authorEndpoint', (
3351 ('browseEndpoint', 'canonicalBaseUrl'), ('commandMetadata', 'webCommandMetadata', 'url'))),
3352 expected_type=str, get_all=False))
a1c5d2ca 3353
c35448b7 3354 author_is_uploader = traverse_obj(comment_renderer, 'authorIsChannelOwner')
3355 if author_is_uploader is not None:
3356 info['author_is_uploader'] = author_is_uploader
3357
3358 comment_abr = traverse_obj(
89bed013 3359 comment_renderer, ('actionButtons', 'commentActionButtonsRenderer'), expected_type=dict)
c35448b7 3360 if comment_abr is not None:
3361 info['is_favorited'] = 'creatorHeart' in comment_abr
3362
14a14335 3363 badges = self._extract_badges([traverse_obj(comment_renderer, 'authorCommentBadge')])
3364 if self._has_badge(badges, BadgeType.VERIFIED):
3365 info['author_is_verified'] = True
c35448b7 3366
3367 is_pinned = traverse_obj(comment_renderer, 'pinnedCommentBadge')
3368 if is_pinned:
3369 info['is_pinned'] = True
3370
3371 return info
a1c5d2ca 3372
46383212 3373 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3374
3375 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 3376
3377 def extract_header(contents):
2d6659b9 3378 _continuation = None
3379 for content in contents:
46383212 3380 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 3381 expected_comment_count = self._get_count(
3382 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 3383
18f8fba7 3384 if expected_comment_count is not None:
46383212 3385 tracker['est_total'] = expected_comment_count
3386 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3387 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 3388
3389 sort_menu_item = try_get(
3390 comments_header_renderer,
3391 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3392 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3393
3394 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3395 if not _continuation:
3396 continue
3397
46383212 3398 sort_text = str_or_none(sort_menu_item.get('title'))
3399 if not sort_text:
2d6659b9 3400 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 3401 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 3402 break
a2160aa4 3403 return _continuation
a1c5d2ca 3404
2d6659b9 3405 def extract_thread(contents):
a1c5d2ca 3406 if not parent:
46383212 3407 tracker['current_page_thread'] = 0
a1c5d2ca 3408 for content in contents:
46383212 3409 if not parent and tracker['total_parent_comments'] >= max_parents:
3410 yield
a1c5d2ca 3411 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 3412 comment_renderer = get_first(
3413 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3414 expected_type=dict, default={})
a1c5d2ca 3415
a1c5d2ca
M
3416 comment = self._extract_comment(comment_renderer, parent)
3417 if not comment:
3418 continue
141a8dff 3419 comment_id = comment['id']
c35448b7 3420 if comment.get('is_pinned'):
141a8dff 3421 tracker['pinned_comment_ids'].add(comment_id)
7f51861b 3422 # Sometimes YouTube may break and give us infinite looping comments.
3423 # See: https://github.com/yt-dlp/yt-dlp/issues/6290
141a8dff 3424 if comment_id in tracker['seen_comment_ids']:
c35448b7 3425 if comment_id in tracker['pinned_comment_ids'] and not comment.get('is_pinned'):
141a8dff 3426 # Pinned comments may appear a second time in newest first sort
3427 # See: https://github.com/yt-dlp/yt-dlp/issues/6712
3428 continue
7f51861b 3429 self.report_warning('Detected YouTube comments looping. Stopping comment extraction as we probably cannot get any more.')
3430 yield
3431 else:
3432 tracker['seen_comment_ids'].add(comment['id'])
46383212 3433
3434 tracker['running_total'] += 1
3435 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 3436 yield comment
46383212 3437
a1c5d2ca
M
3438 # Attempt to get the replies
3439 comment_replies_renderer = try_get(
3440 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3441
3442 if comment_replies_renderer:
46383212 3443 tracker['current_page_thread'] += 1
a1c5d2ca 3444 comment_entries_iter = self._comment_entries(
99e9e001 3445 comment_replies_renderer, ytcfg, video_id,
46383212 3446 parent=comment.get('id'), tracker=tracker)
86e5f3ed 3447 yield from itertools.islice(comment_entries_iter, min(
3448 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 3449
46383212 3450 # Keeps track of counts across recursive calls
3451 if not tracker:
3452 tracker = dict(
3453 running_total=0,
18f8fba7 3454 est_total=None,
46383212 3455 current_page_thread=0,
3456 total_parent_comments=0,
7f51861b 3457 total_reply_comments=0,
141a8dff 3458 seen_comment_ids=set(),
3459 pinned_comment_ids=set()
3460 )
46383212 3461
3462 # TODO: Deprecated
2d6659b9 3463 # YouTube comments have a max depth of 2
46383212 3464 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3465 if max_depth:
da4db748 3466 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3467 'Set max replies in the max-comments extractor argument instead')
2d6659b9 3468 if max_depth == 1 and parent:
3469 return
a1c5d2ca 3470
46383212 3471 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3472 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 3473
46383212 3474 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 3475
46383212 3476 response = None
6e634cbe 3477 is_forced_continuation = False
2d6659b9 3478 is_first_continuation = parent is None
6e634cbe 3479 if is_first_continuation and not continuation:
3480 # Sometimes you can get comments by generating the continuation yourself,
3481 # even if YouTube initially reports them being disabled - e.g. stories comments.
3482 # Note: if the comment section is actually disabled, YouTube may return a response with
3483 # required check_get_keys missing. So we will disable that check initially in this case.
3484 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3485 is_forced_continuation = True
a1c5d2ca 3486
18f8fba7 3487 continuation_items_path = (
3488 'onResponseReceivedEndpoints', ..., ('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems')
a1c5d2ca
M
3489 for page_num in itertools.count(0):
3490 if not continuation:
3491 break
46383212 3492 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
18f8fba7 3493 comment_prog_str = f"({tracker['running_total']}/~{tracker['est_total']})"
2d6659b9 3494 if page_num == 0:
3495 if is_first_continuation:
3496 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 3497 else:
2d6659b9 3498 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 3499 tracker['current_page_thread'], comment_prog_str)
2d6659b9 3500 else:
3501 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3502 ' ' if parent else '', ' replies' if parent else '',
3503 page_num, comment_prog_str)
18f8fba7 3504
3505 # Do a deep check for incomplete data as sometimes YouTube may return no comments for a continuation
3506 # Ignore check if YouTube says the comment count is 0.
3507 check_get_keys = None
3508 if not is_forced_continuation and not (tracker['est_total'] == 0 and tracker['running_total'] == 0):
3509 check_get_keys = [[*continuation_items_path, ..., (
3510 'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentRenderer'))]]
e72e48c5
M
3511 try:
3512 response = self._extract_response(
3513 item_id=None, query=continuation,
3514 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
18f8fba7 3515 check_get_keys=check_get_keys)
e72e48c5
M
3516 except ExtractorError as e:
3517 # Ignore incomplete data error for replies if retries didn't work.
3518 # This is to allow any other parent comments and comment threads to be downloaded.
3519 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
3520 if 'incomplete data' in str(e).lower() and parent and self.get_param('ignoreerrors') is True:
3521 self.report_warning(
3522 'Received incomplete data for a comment reply thread and retrying did not help. '
3523 'Ignoring to let other comments be downloaded.')
3524 else:
3525 raise
6e634cbe 3526 is_forced_continuation = False
2d6659b9 3527 continuation = None
18f8fba7 3528 for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]):
46383212 3529 if is_first_continuation:
3530 continuation = extract_header(continuation_items)
3531 is_first_continuation = False
2d6659b9 3532 if continuation:
a1c5d2ca 3533 break
46383212 3534 continue
a1c5d2ca 3535
46383212 3536 for entry in extract_thread(continuation_items):
3537 if not entry:
3538 return
3539 yield entry
3540 continuation = self._extract_continuation({'contents': continuation_items})
3541 if continuation:
2d6659b9 3542 break
a1c5d2ca 3543
6e634cbe 3544 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3545 if message and not parent and tracker['running_total'] == 0:
3546 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
0cf643b2 3547 raise self.CommentsDisabled
6e634cbe 3548
3549 @staticmethod
3550 def _generate_comment_continuation(video_id):
3551 """
3552 Generates initial comment section continuation token from given video id
3553 """
3554 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3555 return base64.b64encode(token.encode()).decode()
3556
a2160aa4 3557 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3558 """Entry for comment extraction"""
2d6659b9 3559 def _real_comment_extract(contents):
aae16f6e 3560 renderer = next((
3561 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3562 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3563 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3564
a2160aa4 3565 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3566 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3567
109dd3b2 3568 @staticmethod
99e9e001 3569 def _get_checkok_params():
3570 return {'contentCheckOk': True, 'racyCheckOk': True}
3571
3572 @classmethod
3573 def _generate_player_context(cls, sts=None):
109dd3b2 3574 context = {
3575 'html5Preference': 'HTML5_PREF_WANTS',
3576 }
3577 if sts is not None:
3578 context['signatureTimestamp'] = sts
3579 return {
3580 'playbackContext': {
3581 'contentPlaybackContext': context
a1a7907b 3582 },
99e9e001 3583 **cls._get_checkok_params()
109dd3b2 3584 }
3585
e7e94f2a
D
3586 @staticmethod
3587 def _is_agegated(player_response):
3588 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3589 return True
e7e94f2a 3590
6839ae1f 3591 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')))
e7e94f2a
D
3592 AGE_GATE_REASONS = (
3593 'confirm your age', 'age-restricted', 'inappropriate', # reason
3594 'age_verification_required', 'age_check_required', # status
3595 )
3596 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3597
3598 @staticmethod
3599 def _is_unplayable(player_response):
3600 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3601
81ca4514 3602 _PLAYER_PARAMS = 'CgIQBg=='
50ac0e54 3603
3604 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3605
11f9be09 3606 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3607 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3608 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3609 headers = self.generate_api_headers(
99e9e001 3610 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3611
6e634cbe 3612 yt_query = {
3613 'videoId': video_id,
6e634cbe 3614 }
50ac0e54 3615 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
81ca4514 3616 yt_query['params'] = self._PLAYER_PARAMS
50ac0e54 3617
11f9be09 3618 yt_query.update(self._generate_player_context(sts))
3619 return self._extract_response(
3620 item_id=video_id, ep='player', query=yt_query,
379e44ed 3621 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3622 default_client=client,
11f9be09 3623 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3624 ) or None
3625
11f9be09 3626 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3627 requested_clients = []
1e75d97d 3628 default = ['ios', 'android', 'web']
000c15a4 3629 allowed_clients = sorted(
86e5f3ed 3630 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3631 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3632 for client in self._configuration_arg('player_client'):
3633 if client in allowed_clients:
3634 requested_clients.append(client)
d0d012d4 3635 elif client == 'default':
3636 requested_clients.extend(default)
b4c055ba 3637 elif client == 'all':
3638 requested_clients.extend(allowed_clients)
3639 else:
3640 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3641 if not requested_clients:
d0d012d4 3642 requested_clients = default
cf7e015f 3643
11f9be09 3644 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3645 requested_clients.extend(
e7e94f2a 3646 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3647
11f9be09 3648 return orderedSet(requested_clients)
cf7e015f 3649
50ac0e54 3650 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3651 initial_pr = None
3652 if webpage:
b7c47b74 3653 initial_pr = self._search_json(
3654 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3655
ae729626 3656 all_clients = set(clients)
c0bc527b 3657 clients = clients[::-1]
b6de707d 3658 prs = []
e7e94f2a 3659
ae729626 3660 def append_client(*client_names):
e7870111 3661 """ Append the first client name that exists but not already used """
ae729626 3662 for client_name in client_names:
e7870111
D
3663 actual_client = _split_innertube_client(client_name)[0]
3664 if actual_client in INNERTUBE_CLIENTS:
3665 if actual_client not in all_clients:
ae729626 3666 clients.append(client_name)
e7870111
D
3667 all_clients.add(actual_client)
3668 return
e7e94f2a 3669
379e44ed 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
379e44ed 3674 if initial_pr:
3675 pr = dict(initial_pr)
3676 pr['streamingData'] = None
b6de707d 3677 prs.append(pr)
379e44ed 3678
3679 last_error = None
b6de707d 3680 tried_iframe_fallback = False
3681 player_url = None
c0bc527b 3682 while clients:
e7870111 3683 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3684 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3685 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3686 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3687
b6de707d 3688 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3689 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3690 if 'js' in self._configuration_arg('player_skip'):
3691 require_js_player = False
3692 player_url = None
3693
3694 if not player_url and not tried_iframe_fallback and require_js_player:
3695 player_url = self._download_player_url(video_id)
3696 tried_iframe_fallback = True
3697
379e44ed 3698 try:
3699 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3700 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3701 except ExtractorError as e:
3702 if last_error:
3703 self.report_warning(last_error)
3704 last_error = e
3705 continue
3706
11f9be09 3707 if pr:
a3e96421 3708 # YouTube may return a different video player response than expected.
3709 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3710 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3711 if pr_video_id and pr_video_id != video_id:
3712 self.report_warning(
c7dcf0b3 3713 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3714 else:
c795c39f
L
3715 # Save client name for introspection later
3716 name = short_client_name(client)
3717 sd = traverse_obj(pr, ('streamingData', {dict})) or {}
3718 sd[STREAMING_DATA_CLIENT_NAME] = name
3719 for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})):
3720 f[STREAMING_DATA_CLIENT_NAME] = name
a3e96421 3721 prs.append(pr)
c0bc527b 3722
e7e94f2a 3723 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3724 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3725 append_client(f'{base_client}_creator')
e7e94f2a 3726 elif self._is_agegated(pr):
e7870111
D
3727 if variant == 'tv_embedded':
3728 append_client(f'{base_client}_embedded')
3729 elif not variant:
3730 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3731
379e44ed 3732 if last_error:
b6de707d 3733 if not len(prs):
379e44ed 3734 raise last_error
3735 self.report_warning(last_error)
b6de707d 3736 return prs, player_url
11f9be09 3737
4d37720a
L
3738 def _needs_live_processing(self, live_status, duration):
3739 if (live_status == 'is_live' and self.get_param('live_from_start')
d949c10c 3740 or live_status == 'post_live' and (duration or 0) > 2 * 3600):
4d37720a
L
3741 return live_status
3742
3743 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
e389d172 3744 CHUNK_SIZE = 10 << 20
a4894d3e 3745 itags, stream_ids = collections.defaultdict(set), []
b25cac65 3746 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3747 q = qualities([
2a9c6dcd 3748 # Normally tiny is the smallest video-only formats. But
3749 # audio-only formats with unknown quality may get tagged as tiny
3750 'tiny',
3751 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3752 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3753 ])
6839ae1f 3754 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
58786a10 3755 format_types = self._configuration_arg('formats')
3756 all_formats = 'duplicate' in format_types
3757 if self._configuration_arg('include_duplicate_formats'):
3758 all_formats = True
3759 self._downloader.deprecated_feature('[youtube] include_duplicate_formats extractor argument is deprecated. '
3760 'Use formats=duplicate extractor argument instead')
9297939e 3761
e389d172 3762 def build_fragments(f):
3763 return LazyList({
3764 'url': update_url_query(f['url'], {
3765 'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, f["filesize"])}'
3766 })
3767 } for range_start in range(0, f['filesize'], CHUNK_SIZE))
3768
545cc85d 3769 for fmt in streaming_formats:
727029c5 3770 if fmt.get('targetDurationSec'):
545cc85d 3771 continue
321bf820 3772
cc2db878 3773 itag = str_or_none(fmt.get('itag'))
9297939e 3774 audio_track = fmt.get('audioTrack') or {}
9bb85699 3775 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
86cb9221 3776 if not all_formats:
3777 if stream_id in stream_ids:
3778 continue
9297939e 3779
cc2db878 3780 quality = fmt.get('quality')
2a9c6dcd 3781 height = int_or_none(fmt.get('height'))
d3fc8074 3782 if quality == 'tiny' or not quality:
3783 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3784 # The 3gp format (17) in android client has a quality of "small",
3785 # but is actually worse than other formats
3786 if itag == '17':
3787 quality = 'tiny'
3788 if quality:
3789 if itag:
3790 itag_qualities[itag] = quality
3791 if height:
3792 res_qualities[height] = quality
cc2db878 3793 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3794 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3795 # number of fragment that would subsequently requested with (`&sq=N`)
3796 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3797 continue
3798
545cc85d 3799 fmt_url = fmt.get('url')
3800 if not fmt_url:
14f25df2 3801 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3802 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3803 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3804 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3805 continue
52023f12 3806 try:
3807 fmt_url += '&%s=%s' % (
3808 traverse_obj(sc, ('sp', -1)) or 'signature',
3809 self._decrypt_signature(encrypted_sig, video_id, player_url)
3810 )
3811 except ExtractorError as e:
580ce007 3812 self.report_warning('Signature extraction failed: Some formats may be missing',
3813 video_id=video_id, only_once=True)
52023f12 3814 self.write_debug(e, only_once=True)
201e9eaa 3815 continue
545cc85d 3816
404f611f 3817 query = parse_qs(fmt_url)
3818 throttled = False
b2916526 3819 if query.get('n'):
404f611f 3820 try:
580ce007 3821 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3822 fmt_url = update_url_query(fmt_url, {
580ce007 3823 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3824 })
404f611f 3825 except ExtractorError as e:
25836db6 3826 phantomjs_hint = ''
3827 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3828 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3829 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
17ffed18 3830 if player_url:
3831 self.report_warning(
3832 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3833 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3834 self.write_debug(e, only_once=True)
3835 else:
3836 self.report_warning(
3837 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3838 video_id=video_id, only_once=True)
404f611f 3839 throttled = True
3840
0ad92dfb 3841 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3842 language_preference = (
3843 10 if audio_track.get('audioIsDefault') and 10
3844 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3845 else -1)
0ad92dfb 3846 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3847 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3848 # Make sure to avoid false positives with small duration differences.
62b58c09 3849 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3850 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3851 if is_damaged:
0f06bcd7 3852 self.report_warning(
3853 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
c795c39f
L
3854
3855 client_name = fmt.get(STREAMING_DATA_CLIENT_NAME)
51a07b0d 3856 name = fmt.get('qualityLabel') or quality.replace('audio_quality_', '') or ''
97afb093 3857 fps = int_or_none(fmt.get('fps')) or 0
545cc85d 3858 dct = {
3859 'asr': int_or_none(fmt.get('audioSampleRate')),
3860 'filesize': int_or_none(fmt.get('contentLength')),
9bb85699 3861 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
34921b43 3862 'format_note': join_nonempty(
392389b7 3863 join_nonempty(audio_track.get('displayName'),
3864 language_preference > 0 and ' (default)', delim=''),
51a07b0d 3865 name, fmt.get('isDrc') and 'DRC',
a4166234 3866 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3867 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
c795c39f 3868 throttled and 'THROTTLED', is_damaged and 'DAMAGED',
86cb9221 3869 (self.get_param('verbose') or all_formats) and client_name,
c795c39f 3870 delim=', '),
91e5e839 3871 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
51a07b0d 3872 'source_preference': ((-10 if throttled else -5 if itag == '22' else -1)
3873 + (100 if 'Premium' in name else 0)),
97afb093 3874 'fps': fps if fps > 1 else None, # For some formats, fps is wrongly returned as 1
a4166234 3875 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3876 'height': height,
9bb85699 3877 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
727029c5 3878 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3879 'tbr': tbr,
545cc85d 3880 'url': fmt_url,
2a9c6dcd 3881 'width': int_or_none(fmt.get('width')),
ab6df717 3882 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
08e29b9f 3883 'desc' if language_preference < -1 else '') or None,
ab6df717 3884 'language_preference': language_preference,
a405b38f 3885 # Strictly de-prioritize damaged and 3gp formats
3886 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3887 }
60bdb7bd 3888 mime_mobj = re.match(
3889 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3890 if mime_mobj:
3891 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3892 dct.update(parse_codecs(mime_mobj.group(2)))
86cb9221 3893 if itag:
3894 itags[itag].add(('https', dct.get('language')))
3895 stream_ids.append(stream_id)
c9abebb8 3896 single_stream = 'none' in (dct.get('acodec'), dct.get('vcodec'))
3897 if single_stream and dct.get('ext'):
3898 dct['container'] = dct['ext'] + '_dash'
86cb9221 3899
58786a10 3900 if (all_formats or 'dashy' in format_types) and dct['filesize']:
86cb9221 3901 yield {
3902 **dct,
3903 'format_id': f'{dct["format_id"]}-dashy' if all_formats else dct['format_id'],
5038f6d7 3904 'protocol': 'http_dash_segments',
e389d172 3905 'fragments': build_fragments(dct),
86cb9221 3906 }
58786a10 3907 if all_formats or 'dashy' not in format_types:
3908 dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE}
3909 yield dct
545cc85d 3910
4d37720a 3911 needs_live_processing = self._needs_live_processing(live_status, duration)
58786a10 3912 skip_bad_formats = 'incomplete' not in format_types
3913 if self._configuration_arg('include_incomplete_formats'):
3914 skip_bad_formats = False
3915 self._downloader.deprecated_feature('[youtube] include_incomplete_formats extractor argument is deprecated. '
3916 'Use formats=incomplete extractor argument instead')
4d37720a
L
3917
3918 skip_manifests = set(self._configuration_arg('skip'))
3919 if (not self.get_param('youtube_include_hls_manifest', True)
3920 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3921 or needs_live_processing and skip_bad_formats):
3922 skip_manifests.add('hls')
3923
0f06bcd7 3924 if not self.get_param('youtube_include_dash_manifest', True):
4d37720a
L
3925 skip_manifests.add('dash')
3926 if self._configuration_arg('include_live_dash'):
3927 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
58786a10 3928 'Use formats=incomplete extractor argument instead')
4d37720a
L
3929 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3930 skip_manifests.add('dash')
5d3a0e79 3931
c795c39f 3932 def process_manifest_format(f, proto, client_name, itag):
a4894d3e 3933 key = (proto, f.get('language'))
86cb9221 3934 if not all_formats and key in itags[itag]:
a4894d3e 3935 return False
3936 itags[itag].add(key)
3937
86cb9221 3938 if itag and all_formats:
3939 f['format_id'] = f'{itag}-{proto}'
3940 elif any(p != proto for p, _ in itags[itag]):
a4894d3e 3941 f['format_id'] = f'{itag}-{proto}'
3942 elif itag:
a0bb6ce5 3943 f['format_id'] = itag
a0bb6ce5 3944
1e75d97d 3945 if itag in ('616', '235'):
3946 f['format_note'] = join_nonempty(f.get('format_note'), 'Premium', delim=' ')
3947 f['source_preference'] = (f.get('source_preference') or -1) + 100
3948
b25cac65 3949 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3950 if f['quality'] == -1 and f.get('height'):
3951 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
ad54c913 3952 if self.get_param('verbose') or all_formats:
c795c39f 3953 f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ')
97afb093 3954 if f.get('fps') and f['fps'] <= 1:
3955 del f['fps']
a0bb6ce5 3956 return True
2a9c6dcd 3957
c646d76f 3958 subtitles = {}
11f9be09 3959 for sd in streaming_data:
c795c39f
L
3960 client_name = sd.get(STREAMING_DATA_CLIENT_NAME)
3961
4d37720a 3962 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
9297939e 3963 if hls_manifest_url:
4d37720a
L
3964 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3965 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
c646d76f 3966 subtitles = self._merge_subtitles(subs, subtitles)
3967 for f in fmts:
c795c39f 3968 if process_manifest_format(f, 'hls', client_name, self._search_regex(
a0bb6ce5 3969 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3970 yield f
545cc85d 3971
4d37720a 3972 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
5d3a0e79 3973 if dash_manifest_url:
c646d76f 3974 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3975 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3976 for f in formats:
c795c39f 3977 if process_manifest_format(f, 'dash', client_name, f['format_id']):
a0bb6ce5 3978 f['filesize'] = int_or_none(self._search_regex(
3979 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
4d37720a 3980 if needs_live_processing:
adbc4ec4
THD
3981 f['is_from_start'] = True
3982
a0bb6ce5 3983 yield f
c646d76f 3984 yield subtitles
11f9be09 3985
720c3099 3986 def _extract_storyboard(self, player_responses, duration):
3987 spec = get_first(
3988 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3989 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3990 if not base_url:
720c3099 3991 return
720c3099 3992 L = len(spec) - 1
3993 for i, args in enumerate(spec):
3994 args = args.split('#')
3995 counts = list(map(int_or_none, args[:5]))
3996 if len(args) != 8 or not all(counts):
3997 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3998 continue
3999 width, height, frame_count, cols, rows = counts
4000 N, sigh = args[6:]
4001
4002 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
4003 fragment_count = frame_count / (cols * rows)
4004 fragment_duration = duration / fragment_count
4005 yield {
4006 'format_id': f'sb{i}',
4007 'format_note': 'storyboard',
4008 'ext': 'mhtml',
4009 'protocol': 'mhtml',
4010 'acodec': 'none',
4011 'vcodec': 'none',
4012 'url': url,
4013 'width': width,
4014 'height': height,
45e8a04e 4015 'fps': frame_count / duration,
4016 'rows': rows,
4017 'columns': cols,
720c3099 4018 'fragments': [{
b3edc806 4019 'url': url.replace('$M', str(j)),
720c3099 4020 'duration': min(fragment_duration, duration - (j * fragment_duration)),
4021 } for j in range(math.ceil(fragment_count))],
4022 }
4023
adbc4ec4 4024 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 4025 webpage = None
4026 if 'webpage' not in self._configuration_arg('player_skip'):
50ac0e54 4027 query = {'bpctr': '9999999999', 'has_verified': '1'}
81ca4514 4028 if smuggled_data.get('is_story'): # XXX: Deprecated
4029 query['pp'] = self._PLAYER_PARAMS
b6de707d 4030 webpage = self._download_webpage(
50ac0e54 4031 webpage_url, video_id, fatal=False, query=query)
11f9be09 4032
4033 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 4034
b6de707d 4035 player_responses, player_url = self._extract_player_responses(
11f9be09 4036 self._get_requested_clients(url, smuggled_data),
50ac0e54 4037 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 4038
adbc4ec4
THD
4039 return webpage, master_ytcfg, player_responses, player_url
4040
a1b2d843 4041 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
4042 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
4043 is_live = get_first(video_details, 'isLive')
4044 if is_live is None:
4045 is_live = get_first(live_broadcast_details, 'isLiveNow')
4d37720a
L
4046 live_content = get_first(video_details, 'isLiveContent')
4047 is_upcoming = get_first(video_details, 'isUpcoming')
4d37720a
L
4048 post_live = get_first(video_details, 'isPostLiveDvr')
4049 live_status = ('post_live' if post_live
4050 else 'is_live' if is_live
4051 else 'is_upcoming' if is_upcoming
6678a4f0 4052 else 'was_live' if live_content
4053 else 'not_live' if False in (is_live, live_content)
4054 else None)
6839ae1f 4055 streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
4d37720a 4056 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
adbc4ec4 4057
4d37720a 4058 return live_broadcast_details, live_status, streaming_data, formats, subtitles
adbc4ec4
THD
4059
4060 def _real_extract(self, url):
4061 url, smuggled_data = unsmuggle_url(url, {})
4062 video_id = self._match_id(url)
4063
4064 base_url = self.http_scheme() + '//www.youtube.com/'
4065 webpage_url = base_url + 'watch?v=' + video_id
4066
4067 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
4068
11f9be09 4069 playability_statuses = traverse_obj(
6839ae1f 4070 player_responses, (..., 'playabilityStatus'), expected_type=dict)
11f9be09 4071
4072 trailer_video_id = get_first(
4073 playability_statuses,
4074 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
4075 expected_type=str)
4076 if trailer_video_id:
4077 return self.url_result(
4078 trailer_video_id, self.ie_key(), trailer_video_id)
4079
4080 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
4081 if webpage else (lambda x: None))
4082
6839ae1f 4083 video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict)
11f9be09 4084 microformats = traverse_obj(
4085 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 4086 expected_type=dict)
c26f9b99 4087
4088 translated_title = self._get_text(microformats, (..., 'title'))
4089 video_title = (self._preferred_lang and translated_title
4090 or get_first(video_details, 'title') # primary
4091 or translated_title
4092 or search_meta(['og:title', 'twitter:title', 'title']))
4093 translated_description = self._get_text(microformats, (..., 'description'))
4094 original_description = get_first(video_details, 'shortDescription')
4095 video_description = (
4096 self._preferred_lang and translated_description
4097 # If original description is blank, it will be an empty string.
4098 # Do not prefer translated description in this case.
4099 or original_description if original_description is not None else translated_description)
11f9be09 4100
d89257f3 4101 multifeed_metadata_list = get_first(
4102 player_responses,
4103 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
4104 expected_type=str)
4105 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
4106 if self.get_param('noplaylist'):
11f9be09 4107 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 4108 else:
4109 entries = []
4110 feed_ids = []
4111 for feed in multifeed_metadata_list.split(','):
4112 # Unquote should take place before split on comma (,) since textual
4113 # fields may contain comma as well (see
4114 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 4115 feed_data = urllib.parse.parse_qs(
ac668111 4116 urllib.parse.unquote_plus(feed))
d89257f3 4117
4118 def feed_entry(name):
4119 return try_get(
14f25df2 4120 feed_data, lambda x: x[name][0], str)
d89257f3 4121
4122 feed_id = feed_entry('id')
4123 if not feed_id:
4124 continue
4125 feed_title = feed_entry('title')
4126 title = video_title
4127 if feed_title:
4128 title += ' (%s)' % feed_title
4129 entries.append({
4130 '_type': 'url_transparent',
4131 'ie_key': 'Youtube',
4132 'url': smuggle_url(
4133 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
4134 {'force_singlefeed': True}),
4135 'title': title,
4136 })
4137 feed_ids.append(feed_id)
4138 self.to_screen(
4139 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
4140 % (', '.join(feed_ids), video_id))
4141 return self.playlist_result(
4142 entries, video_id, video_title, video_description)
11f9be09 4143
9da6612b 4144 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
4145 or int_or_none(get_first(microformats, 'lengthSeconds'))
4146 or parse_duration(search_meta('duration')) or None)
a1b2d843 4147
4d37720a
L
4148 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
4149 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
4150 if live_status == 'post_live':
4151 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
bf1317d2 4152
545cc85d 4153 if not formats:
11f9be09 4154 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 4155 self.report_drm(video_id)
11f9be09 4156 pemr = get_first(
4157 playability_statuses,
4158 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
4159 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
4160 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 4161 if subreason:
545cc85d 4162 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 4163 countries = get_first(microformats, 'availableCountries')
545cc85d 4164 if not countries:
4165 regions_allowed = search_meta('regionsAllowed')
4166 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 4167 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 4168 reason += f'. {subreason}'
545cc85d 4169 if reason:
b7da73eb 4170 self.raise_no_formats(reason, expected=True)
bf1317d2 4171
11f9be09 4172 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 4173 if not keywords and webpage:
4174 keywords = [
4175 unescapeHTML(m.group('content'))
4176 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
4177 for keyword in keywords:
4178 if keyword.startswith('yt:stretch='):
201c1459 4179 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
4180 if mobj:
4181 # NB: float is intentional for forcing float division
4182 w, h = (float(v) for v in mobj.groups())
4183 if w > 0 and h > 0:
4184 ratio = w / h
4185 for f in formats:
4186 if f.get('vcodec') != 'none':
4187 f['stretched_ratio'] = ratio
4188 break
a709d873 4189 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 4190 thumbnail_url = search_meta(['og:image', 'twitter:image'])
4191 if thumbnail_url:
4192 thumbnails.append({
4193 'url': thumbnail_url,
ff2751ac 4194 })
fccf5021 4195 original_thumbnails = thumbnails.copy()
4196
0ba692ac 4197 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 4198 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 4199 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 4200 thumbnail_names = [
962ffcf8 4201 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 4202 # in resolution, these are not the custom thumbnail. So de-prioritize them
4203 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4204 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 4205 ]
cca80fe6 4206 n_thumbnail_names = len(thumbnail_names)
0ba692ac 4207 thumbnails.extend({
4208 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4209 video_id=video_id, name=name, ext=ext,
4d37720a 4210 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
cca80fe6 4211 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 4212 for thumb in thumbnails:
cca80fe6 4213 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 4214 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 4215 self._remove_duplicate_formats(thumbnails)
fccf5021 4216 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 4217
7ea65411 4218 category = get_first(microformats, 'category') or search_meta('genre')
7666b936 4219 channel_id = self.ucid_or_none(str_or_none(
7ea65411 4220 get_first(video_details, 'channelId')
4221 or get_first(microformats, 'externalChannelId')
7666b936 4222 or search_meta('channelId')))
7ea65411 4223 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4224
adbc4ec4
THD
4225 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4226 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4227 if not duration and live_end_time and live_start_time:
4228 duration = live_end_time - live_start_time
4229
4d37720a
L
4230 needs_live_processing = self._needs_live_processing(live_status, duration)
4231
4232 def is_bad_format(fmt):
4233 if needs_live_processing and not fmt.get('is_from_start'):
4234 return True
4235 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4236 and fmt.get('protocol') == 'http_dash_segments'):
4237 return True
4238
4239 for fmt in filter(is_bad_format, formats):
4240 fmt['preference'] = (fmt.get('preference') or -1) - 10
d949c10c 4241 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 2 hours)', delim=' ')
4d37720a
L
4242
4243 if needs_live_processing:
4244 self._prepare_live_from_start_formats(
4245 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
7ea65411 4246
720c3099 4247 formats.extend(self._extract_storyboard(player_responses, duration))
4248
7666b936 4249 channel_handle = self.handle_from_url(owner_profile_url)
4250
545cc85d 4251 info = {
4252 'id': video_id,
39ca3b5c 4253 'title': video_title,
545cc85d 4254 'formats': formats,
4255 'thumbnails': thumbnails,
fccf5021 4256 # The best thumbnail that we are sure exists. Prevents unnecessary
4257 # URL checking if user don't care about getting the best possible thumbnail
4258 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 4259 'description': video_description,
545cc85d 4260 'channel_id': channel_id,
7666b936 4261 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None),
545cc85d 4262 'duration': duration,
4263 'view_count': int_or_none(
11f9be09 4264 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 4265 or search_meta('interactionCount')),
11f9be09 4266 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 4267 'age_limit': 18 if (
11f9be09 4268 get_first(microformats, 'isFamilySafe') is False
545cc85d 4269 or search_meta('isFamilyFriendly') == 'false'
4270 or search_meta('og:restrictions:age') == '18+') else 0,
4271 'webpage_url': webpage_url,
4272 'categories': [category] if category else None,
4273 'tags': keywords,
11f9be09 4274 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4d37720a 4275 'live_status': live_status,
adbc4ec4 4276 'release_timestamp': live_start_time,
9f14daf2 4277 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4278 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
545cc85d 4279 }
b477fc13 4280
c646d76f 4281 subtitles = {}
3944e7af 4282 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 4283 if pctr:
ecdc9049 4284 def get_lang_code(track):
4285 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4286 or track.get('languageCode'))
4287
4288 # Converted into dicts to remove duplicates
4289 captions = {
4290 get_lang_code(sub): sub
6839ae1f 4291 for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
ecdc9049 4292 translation_languages = {
4293 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
6839ae1f 4294 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
ecdc9049 4295
774d79cc 4296 def process_language(container, base_url, lang_code, sub_name, query):
120916da 4297 lang_subs = container.setdefault(lang_code, [])
545cc85d 4298 for fmt in self._SUBTITLE_FORMATS:
4299 query.update({
4300 'fmt': fmt,
4301 })
4302 lang_subs.append({
4303 'ext': fmt,
60f393e4 4304 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 4305 'name': sub_name,
545cc85d 4306 })
7e72694b 4307
07b47084 4308 # NB: Constructing the full subtitle dictionary is slow
4309 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4310 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 4311 for lang_code, caption_track in captions.items():
4312 base_url = caption_track.get('baseUrl')
1235d333 4313 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 4314 if not base_url:
4315 continue
ecdc9049 4316 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 4317 if caption_track.get('kind') != 'asr':
545cc85d 4318 if not lang_code:
4319 continue
4320 process_language(
ecdc9049 4321 subtitles, base_url, lang_code, lang_name, {})
4322 if not caption_track.get('isTranslatable'):
4323 continue
3944e7af 4324 for trans_code, trans_name in translation_languages.items():
4325 if not trans_code:
545cc85d 4326 continue
1235d333 4327 orig_trans_code = trans_code
71eb82d1 4328 if caption_track.get('kind') != 'asr' and trans_code != 'und':
07b47084 4329 if not get_translated_subs:
18e49408 4330 continue
ecdc9049 4331 trans_code += f'-{lang_code}'
a70635b8 4332 trans_name += format_field(lang_name, None, ' from %s')
1235d333 4333 if lang_code == f'a-{orig_trans_code}':
ff9b0e07 4334 # Set audio language based on original subtitles
4335 for f in formats:
4336 if f.get('acodec') != 'none' and not f.get('language'):
4337 f['language'] = orig_trans_code
4338 # Add an "-orig" label to the original language so that it can be distinguished.
4339 # The subs are returned without "-orig" as well for compatibility
0c8d9e5f 4340 process_language(
d49669ac 4341 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4342 # Setting tlang=lang returns damaged subtitles.
d49669ac 4343 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 4344 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 4345
4346 info['automatic_captions'] = automatic_captions
4347 info['subtitles'] = subtitles
7e72694b 4348
14f25df2 4349 parsed_url = urllib.parse.urlparse(url)
545cc85d 4350 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 4351 query = urllib.parse.parse_qs(component)
545cc85d 4352 for k, v in query.items():
4353 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4354 d_k += '_time'
4355 if d_k not in info and k in s_ks:
4356 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
4357
4358 # Youtube Music Auto-generated description
71dc18fa
BT
4359 if (video_description or '').strip().endswith('\nAuto-generated by YouTube.'):
4360 # XXX: Causes catastrophic backtracking if description has "·"
4361 # E.g. https://www.youtube.com/watch?v=DoPaAxMQoiI
4362 # Simulating atomic groups: (?P<a>[^xy]+)x => (?=(?P<a>[^xy]+))(?P=a)x
4363 # reduces it, but does not fully fix it. https://regex101.com/r/8Ssf2h/2
1890fc63 4364 mobj = re.search(
4365 r'''(?xs)
71dc18fa
BT
4366 (?=(?P<track>[^\n·]+))(?P=track)·
4367 (?=(?P<artist>[^\n]+))(?P=artist)\n+
4368 (?=(?P<album>[^\n]+))(?P=album)\n
1890fc63 4369 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4370 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
71dc18fa
BT
4371 (.+?\nArtist\s*:\s*
4372 (?=(?P<clean_artist>[^\n]+))(?P=clean_artist)\n
4373 )?.+\nAuto-generated\ by\ YouTube\.\s*$
1890fc63 4374 ''', video_description)
822b9d9c 4375 if mobj:
822b9d9c
RA
4376 release_year = mobj.group('release_year')
4377 release_date = mobj.group('release_date')
4378 if release_date:
4379 release_date = release_date.replace('-', '')
4380 if not release_year:
545cc85d 4381 release_year = release_date[:4]
4382 info.update({
4383 'album': mobj.group('album'.strip()),
4384 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4385 'track': mobj.group('track').strip(),
4386 'release_date': release_date,
cc2db878 4387 'release_year': int_or_none(release_year),
545cc85d 4388 })
7e72694b 4389
545cc85d 4390 initial_data = None
4391 if webpage:
56ba69e4 4392 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
607510b9 4393 if not traverse_obj(initial_data, 'contents'):
4394 self.report_warning('Incomplete data received in embedded initial data; re-fetching using API.')
4395 initial_data = None
545cc85d 4396 if not initial_data:
99e9e001 4397 query = {'videoId': video_id}
4398 query.update(self._get_checkok_params())
109dd3b2 4399 initial_data = self._extract_response(
4400 item_id=video_id, ep='next', fatal=False,
607510b9 4401 ytcfg=master_ytcfg, query=query, check_get_keys='contents',
99e9e001 4402 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 4403 note='Downloading initial data API JSON')
545cc85d 4404
0df111a3 4405 info['comment_count'] = traverse_obj(initial_data, (
4406 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
071670cb 4407 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount'
0df111a3 4408 ), (
4409 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
071670cb
ND
4410 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo'
4411 ), expected_type=self._get_count, get_all=False)
0df111a3 4412
19a03940 4413 try: # This will error if there is no livechat
c60ee3a2 4414 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 4415 except (KeyError, IndexError, TypeError):
4416 pass
4417 else:
ecdc9049 4418 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 4419 # url is needed to set cookies
4420 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 4421 'video_id': video_id,
4422 'ext': 'json',
4d37720a
L
4423 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4424 else 'youtube_live_chat_replay'),
c60ee3a2 4425 }]
545cc85d 4426
4427 if initial_data:
7c365c21 4428 info['chapters'] = (
4429 self._extract_chapters_from_json(initial_data, duration)
4430 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 4431 or self._extract_chapters_from_description(video_description, duration)
7c365c21 4432 or None)
545cc85d 4433
5caf30db
A
4434 info['heatmap'] = self._extract_heatmap_from_player_overlay(initial_data)
4435
17322130 4436 contents = traverse_obj(
4437 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4438 expected_type=list, default=[])
4439
4440 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4441 if vpir:
4442 stl = vpir.get('superTitleLink')
4443 if stl:
4444 stl = self._get_text(stl)
4445 if try_get(
4446 vpir,
4447 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4448 info['location'] = stl
4449 else:
affc4fef 4450 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 4451 if mobj:
545cc85d 4452 info.update({
17322130 4453 'series': mobj.group(1),
4454 'season_number': int(mobj.group(2)),
4455 'episode_number': int(mobj.group(3)),
545cc85d 4456 })
17322130 4457 for tlb in (try_get(
4458 vpir,
4459 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4460 list) or []):
3ffb2f5b 4461 tbrs = variadic(
4462 traverse_obj(
6839ae1f
SS
4463 tlb, ('toggleButtonRenderer', ...),
4464 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
3ffb2f5b 4465 for tbr in tbrs:
4466 for getter, regex in [(
4467 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4468 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4469 lambda x: x['accessibility'],
4470 lambda x: x['accessibilityData']['accessibilityData'],
4471 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4472 label = (try_get(tbr, getter, dict) or {}).get('label')
4473 if label:
4474 mobj = re.match(regex, label)
4475 if mobj:
4476 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4477 break
17322130 4478 sbr_tooltip = try_get(
4479 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4480 if sbr_tooltip:
4481 like_count, dislike_count = sbr_tooltip.split(' / ')
4482 info.update({
4483 'like_count': str_to_int(like_count),
4484 'dislike_count': str_to_int(dislike_count),
4485 })
867c66ff
M
4486 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4487 if vcr:
4488 vc = self._get_count(vcr, 'viewCount')
4489 # Upcoming premieres with waiting count are treated as live here
4490 if vcr.get('isLive'):
4491 info['concurrent_view_count'] = vc
4492 elif info.get('view_count') is None:
4493 info['view_count'] = vc
4494
17322130 4495 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4496 if vsir:
4497 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4498 info.update({
4499 'channel': self._get_text(vor, 'title'),
4500 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4501
7666b936 4502 if not channel_handle:
4503 channel_handle = self.handle_from_url(
4504 traverse_obj(vor, (
4505 ('navigationEndpoint', ('title', 'runs', ..., 'navigationEndpoint')),
4506 (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl')),
4507 {str}), get_all=False))
4508
17322130 4509 rows = try_get(
4510 vsir,
4511 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4512 list) or []
4513 multiple_songs = False
4514 for row in rows:
4515 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4516 multiple_songs = True
4517 break
4518 for row in rows:
4519 mrr = row.get('metadataRowRenderer') or {}
4520 mrr_title = mrr.get('title')
4521 if not mrr_title:
4522 continue
4523 mrr_title = self._get_text(mrr, 'title')
4524 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4525 if mrr_title == 'License':
4526 info['license'] = mrr_contents_text
4527 elif not multiple_songs:
4528 if mrr_title == 'Album':
4529 info['album'] = mrr_contents_text
4530 elif mrr_title == 'Artist':
4531 info['artist'] = mrr_contents_text
4532 elif mrr_title == 'Song':
4533 info['track'] = mrr_contents_text
8213ce28 4534 owner_badges = self._extract_badges(traverse_obj(vsir, ('owner', 'videoOwnerRenderer', 'badges')))
4535 if self._has_badge(owner_badges, BadgeType.VERIFIED):
4536 info['channel_is_verified'] = True
545cc85d 4537
7666b936 4538 info.update({
4539 'uploader': info.get('channel'),
4540 'uploader_id': channel_handle,
4541 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
4542 })
17322130 4543 # The upload date for scheduled, live and past live streams / premieres in microformats
4544 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 4545 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 4546 upload_date = (
4547 unified_strdate(get_first(microformats, 'uploadDate'))
4548 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 4549 if not upload_date or (
4d37720a 4550 live_status in ('not_live', None)
1ff88b7a 4551 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4552 ):
c26f9b99 4553 upload_date = strftime_or_none(
ad54c913 4554 self._parse_time_text(self._get_text(vpir, 'dateText'))) or upload_date
17322130 4555 info['upload_date'] = upload_date
992f9a73 4556
545cc85d 4557 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4558 v = info.get(s_k)
4559 if v:
4560 info[d_k] = v
b84071c0 4561
14a14335 4562 badges = self._extract_badges(traverse_obj(vpir, 'badges'))
c26f9b99 4563
4564 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4565 or get_first(video_details, 'isPrivate', expected_type=bool))
4566
4567 info['availability'] = (
4568 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4569 else self._availability(
4570 is_private=is_private,
4571 needs_premium=(
4572 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4573 or False if initial_data and is_private is not None else None),
4574 needs_subscription=(
4575 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4576 or False if initial_data and is_private is not None else None),
4577 needs_auth=info['age_limit'] >= 18,
4578 is_unlisted=None if is_private is None else (
4579 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4580 or get_first(microformats, 'isUnlisted', expected_type=bool))))
c224251a 4581
a2160aa4 4582 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 4583
11f9be09 4584 self.mark_watched(video_id, player_responses)
d77ab8e2 4585
545cc85d 4586 return info
c5e8d7af 4587
a61fd4cf 4588
a6213a49 4589class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
182bda88 4590 @staticmethod
4591 def passthrough_smuggled_data(func):
bd7e919a 4592 def _smuggle(info, smuggled_data):
4593 if info.get('_type') not in ('url', 'url_transparent'):
4594 return info
4595 if smuggled_data.get('is_music_url'):
4596 parsed_url = urllib.parse.urlparse(info['url'])
4597 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4598 smuggled_data.pop('is_music_url')
4599 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4600 if smuggled_data:
4601 info['url'] = smuggle_url(info['url'], smuggled_data)
4602 return info
182bda88 4603
4604 @functools.wraps(func)
4605 def wrapper(self, url):
4606 url, smuggled_data = unsmuggle_url(url, {})
4607 if self.is_music_url(url):
4608 smuggled_data['is_music_url'] = True
4609 info_dict = func(self, url, smuggled_data)
bd7e919a 4610 if smuggled_data:
4611 _smuggle(info_dict, smuggled_data)
4612 if info_dict.get('entries'):
a8c754cc 4613 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
182bda88 4614 return info_dict
4615 return wrapper
4616
8bdd16b4 4617 @staticmethod
cd7c66cf 4618 def _extract_basic_item_renderer(item):
4619 # Modified from _extract_grid_item_renderer
201c1459 4620 known_basic_renderers = (
a17526e4 4621 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4622 )
4623 for key, renderer in item.items():
201c1459 4624 if not isinstance(renderer, dict):
cd7c66cf 4625 continue
201c1459 4626 elif key in known_basic_renderers:
4627 return renderer
4628 elif key.startswith('grid') and key.endswith('Renderer'):
4629 return renderer
8bdd16b4 4630
c7335551 4631 def _extract_channel_renderer(self, renderer):
7666b936 4632 channel_id = self.ucid_or_none(renderer['channelId'])
c7335551 4633 title = self._get_text(renderer, 'title')
7666b936 4634 channel_url = format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None)
7666b936 4635 channel_handle = self.handle_from_url(
4636 traverse_obj(renderer, (
4637 'navigationEndpoint', (('commandMetadata', 'webCommandMetadata', 'url'),
4638 ('browseEndpoint', 'canonicalBaseUrl')),
4639 {str}), get_all=False))
14a14335 4640 if not channel_handle:
4641 # As of 2023-06-01, YouTube sets subscriberCountText to the handle in search
4642 channel_handle = self.handle_or_none(self._get_text(renderer, 'subscriberCountText'))
c7335551
M
4643 return {
4644 '_type': 'url',
4645 'url': channel_url,
4646 'id': channel_id,
4647 'ie_key': YoutubeTabIE.ie_key(),
4648 'channel': title,
7666b936 4649 'uploader': title,
c7335551
M
4650 'channel_id': channel_id,
4651 'channel_url': channel_url,
4652 'title': title,
7666b936 4653 'uploader_id': channel_handle,
4654 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
14a14335 4655 # See above. YouTube sets videoCountText to the subscriber text in search channel renderers.
4656 # However, in feed/channels this is set correctly to the subscriber count
4657 'channel_follower_count': traverse_obj(
4658 renderer, 'subscriberCountText', 'videoCountText', expected_type=self._get_count),
c7335551 4659 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
14a14335 4660 'playlist_count': (
4661 # videoCountText may be the subscriber count
4662 self._get_count(renderer, 'videoCountText')
4663 if self._get_count(renderer, 'subscriberCountText') is not None else None),
c7335551 4664 'description': self._get_text(renderer, 'descriptionSnippet'),
8213ce28 4665 'channel_is_verified': True if self._has_badge(
4666 self._extract_badges(traverse_obj(renderer, 'ownerBadges')), BadgeType.VERIFIED) else None,
c7335551
M
4667 }
4668
8bdd16b4 4669 def _grid_entries(self, grid_renderer):
4670 for item in grid_renderer['items']:
4671 if not isinstance(item, dict):
39b62db1 4672 continue
cd7c66cf 4673 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4674 if not isinstance(renderer, dict):
4675 continue
052e1350 4676 title = self._get_text(renderer, 'title')
fe93e2c4 4677
8bdd16b4 4678 # playlist
4679 playlist_id = renderer.get('playlistId')
4680 if playlist_id:
4681 yield self.url_result(
4682 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4683 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4684 video_title=title)
201c1459 4685 continue
8bdd16b4 4686 # video
4687 video_id = renderer.get('videoId')
4688 if video_id:
4689 yield self._extract_video(renderer)
201c1459 4690 continue
8bdd16b4 4691 # channel
4692 channel_id = renderer.get('channelId')
4693 if channel_id:
c7335551 4694 yield self._extract_channel_renderer(renderer)
201c1459 4695 continue
4696 # generic endpoint URL support
4697 ep_url = urljoin('https://www.youtube.com/', try_get(
4698 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4699 str))
201c1459 4700 if ep_url:
4701 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4702 if ie.suitable(ep_url):
4703 yield self.url_result(
4704 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4705 break
8bdd16b4 4706
16aa9ea4 4707 def _music_reponsive_list_entry(self, renderer):
4708 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4709 if video_id:
69a40e4a 4710 title = traverse_obj(renderer, (
4711 'flexColumns', 0, 'musicResponsiveListItemFlexColumnRenderer',
4712 'text', 'runs', 0, 'text'))
16aa9ea4 4713 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
69a40e4a 4714 ie=YoutubeIE.ie_key(), video_id=video_id, title=title)
16aa9ea4 4715 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4716 if playlist_id:
4717 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4718 if video_id:
4719 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4720 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4721 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4722 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4723 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4724 if browse_id:
4725 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4726 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4727
3d3dddc9 4728 def _shelf_entries_from_content(self, shelf_renderer):
4729 content = shelf_renderer.get('content')
4730 if not isinstance(content, dict):
8bdd16b4 4731 return
cd7c66cf 4732 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4733 if renderer:
4734 # TODO: add support for nested playlists so each shelf is processed
4735 # as separate playlist
4736 # TODO: this includes only first N items
86e5f3ed 4737 yield from self._grid_entries(renderer)
3d3dddc9 4738 renderer = content.get('horizontalListRenderer')
4739 if renderer:
4740 # TODO
4741 pass
8bdd16b4 4742
29f7c58a 4743 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4744 ep = try_get(
4745 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4746 str)
8bdd16b4 4747 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4748 if shelf_url:
29f7c58a 4749 # Skipping links to another channels, note that checking for
4750 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4751 # will not work
4752 if skip_channels and '/channels?' in shelf_url:
4753 return
052e1350 4754 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4755 yield self.url_result(shelf_url, video_title=title)
4756 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4757 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4758
8bdd16b4 4759 def _playlist_entries(self, video_list_renderer):
4760 for content in video_list_renderer['contents']:
4761 if not isinstance(content, dict):
4762 continue
4763 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4764 if not isinstance(renderer, dict):
4765 continue
4766 video_id = renderer.get('videoId')
4767 if not video_id:
4768 continue
4769 yield self._extract_video(renderer)
07aeced6 4770
3462ffa8 4771 def _rich_entries(self, rich_grid_renderer):
80eb0bd9 4772 renderer = traverse_obj(
447afb9e 4773 rich_grid_renderer,
4774 ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer')), get_all=False) or {}
3462ffa8 4775 video_id = renderer.get('videoId')
447afb9e 4776 if video_id:
4777 yield self._extract_video(renderer)
4778 return
4779 playlist_id = renderer.get('playlistId')
4780 if playlist_id:
4781 yield self.url_result(
4782 f'https://www.youtube.com/playlist?list={playlist_id}',
4783 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4784 video_title=self._get_text(renderer, 'title'))
3462ffa8 4785 return
3462ffa8 4786
8bdd16b4 4787 def _video_entry(self, video_renderer):
4788 video_id = video_renderer.get('videoId')
4789 if video_id:
4790 return self._extract_video(video_renderer)
dacb3a86 4791
ad210f4f 4792 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4793 url = urljoin('https://youtube.com', traverse_obj(
4794 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4795 if url:
4796 return self.url_result(
4797 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4798
8bdd16b4 4799 def _post_thread_entries(self, post_thread_renderer):
4800 post_renderer = try_get(
4801 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4802 if not post_renderer:
4803 return
4804 # video attachment
4805 video_renderer = try_get(
895b0931 4806 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4807 video_id = video_renderer.get('videoId')
4808 if video_id:
4809 entry = self._extract_video(video_renderer)
8bdd16b4 4810 if entry:
4811 yield entry
895b0931 4812 # playlist attachment
4813 playlist_id = try_get(
14f25df2 4814 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4815 if playlist_id:
4816 yield self.url_result(
e28f1c0a 4817 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4818 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4819 # inline video links
4820 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4821 for run in runs:
4822 if not isinstance(run, dict):
4823 continue
4824 ep_url = try_get(
14f25df2 4825 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4826 if not ep_url:
4827 continue
4828 if not YoutubeIE.suitable(ep_url):
4829 continue
4830 ep_video_id = YoutubeIE._match_id(ep_url)
4831 if video_id == ep_video_id:
4832 continue
895b0931 4833 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4834
8bdd16b4 4835 def _post_thread_continuation_entries(self, post_thread_continuation):
4836 contents = post_thread_continuation.get('contents')
4837 if not isinstance(contents, list):
4838 return
4839 for content in contents:
4840 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4841 if isinstance(renderer, dict):
4842 yield from self._post_thread_entries(renderer)
8bdd16b4 4843 continue
6b0b0a28 4844 renderer = content.get('videoRenderer')
4845 if isinstance(renderer, dict):
4846 yield self._video_entry(renderer)
07aeced6 4847
39ed931e 4848 r''' # unused
4849 def _rich_grid_entries(self, contents):
4850 for content in contents:
4851 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4852 if video_renderer:
4853 entry = self._video_entry(video_renderer)
4854 if entry:
4855 yield entry
4856 '''
52efa4b3 4857
0a5095fe 4858 def _report_history_entries(self, renderer):
4859 for url in traverse_obj(renderer, (
7a32c70d 4860 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4861 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
0a5095fe 4862 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4863 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4864
a6213a49 4865 def _extract_entries(self, parent_renderer, continuation_list):
4866 # continuation_list is modified in-place with continuation_list = [continuation_token]
4867 continuation_list[:] = [None]
4868 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4869 for content in contents:
4870 if not isinstance(content, dict):
4871 continue
16aa9ea4 4872 is_renderer = traverse_obj(
4873 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4874 expected_type=dict)
a6213a49 4875 if not is_renderer:
0a5095fe 4876 if content.get('richItemRenderer'):
4877 for entry in self._rich_entries(content['richItemRenderer']):
a6213a49 4878 yield entry
4879 continuation_list[0] = self._extract_continuation(parent_renderer)
0a5095fe 4880 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4881 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4882 yield from self._report_history_entries(table)
4883 continuation_list[0] = self._extract_continuation(table)
a6213a49 4884 continue
0a5095fe 4885
a6213a49 4886 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4887 for isr_content in isr_contents:
4888 if not isinstance(isr_content, dict):
8bdd16b4 4889 continue
69184e41 4890
a6213a49 4891 known_renderers = {
4892 'playlistVideoListRenderer': self._playlist_entries,
4893 'gridRenderer': self._grid_entries,
a17526e4 4894 'reelShelfRenderer': self._grid_entries,
4895 'shelfRenderer': self._shelf_entries,
16aa9ea4 4896 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4897 'backstagePostThreadRenderer': self._post_thread_entries,
4898 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4899 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4900 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
fcbc9ed7 4901 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)],
4902 'richGridRenderer': lambda x: self._extract_entries(x, continuation_list),
a6213a49 4903 }
4904 for key, renderer in isr_content.items():
4905 if key not in known_renderers:
4906 continue
4907 for entry in known_renderers[key](renderer):
4908 if entry:
4909 yield entry
4910 continuation_list[0] = self._extract_continuation(renderer)
4911 break
70d5c17b 4912
4913 if not continuation_list[0]:
a6213a49 4914 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4915
a6213a49 4916 if not continuation_list[0]:
4917 continuation_list[0] = self._extract_continuation(parent_renderer)
4918
4919 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4920 continuation_list = [None]
4921 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4922 tab_content = try_get(tab, lambda x: x['content'], dict)
4923 if not tab_content:
4924 return
3462ffa8 4925 parent_renderer = (
29f7c58a 4926 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4927 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4928 yield from extract_entries(parent_renderer)
3462ffa8 4929 continuation = continuation_list[0]
d069eca7 4930
8bdd16b4 4931 for page_num in itertools.count(1):
4932 if not continuation:
4933 break
99e9e001 4934 headers = self.generate_api_headers(
4935 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4936 response = self._extract_response(
86e5f3ed 4937 item_id=f'{item_id} page {page_num}',
fe93e2c4 4938 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4939 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4940
4941 if not response:
8bdd16b4 4942 break
ac56cf38 4943 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4944 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4945 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4946
a1b535bd 4947 known_renderers = {
e4b98809 4948 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4949 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4950 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4951 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4952 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4953 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4954 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
0a5095fe 4955 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4956 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
1fb53b94 4957 'playlistVideoListContinuation': (self._playlist_entries, None),
4958 'gridContinuation': (self._grid_entries, None),
4959 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4960 'sectionListContinuation': (extract_entries, None), # for feeds
a1b535bd 4961 }
1fb53b94 4962
4963 continuation_items = traverse_obj(response, (
4964 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4965 'appendContinuationItemsAction', 'continuationItems'
4966 ), 'continuationContents', get_all=False)
4967 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4968
a1b535bd 4969 video_items_renderer = None
1fb53b94 4970 for key in continuation_item.keys():
a1b535bd 4971 if key not in known_renderers:
8bdd16b4 4972 continue
1fb53b94 4973 func, parent_key = known_renderers[key]
4974 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
9ba5705a 4975 continuation_list = [None]
1fb53b94 4976 yield from func(video_items_renderer)
9ba5705a 4977 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
1fb53b94 4978
4979 if not video_items_renderer:
a1b535bd 4980 break
9558dcec 4981
8bdd16b4 4982 @staticmethod
7c219ea6 4983 def _extract_selected_tab(tabs, fatal=True):
86973308
M
4984 for tab_renderer in tabs:
4985 if tab_renderer.get('selected'):
4986 return tab_renderer
4987 if fatal:
4988 raise ExtractorError('Unable to find selected tab')
4989
4990 @staticmethod
4991 def _extract_tab_renderers(response):
4992 return traverse_obj(
4993 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
b82f815f 4994
ac56cf38 4995 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
bd7e919a 4996 metadata = self._extract_metadata_from_tabs(item_id, data)
b60419c5 4997
8bdd16b4 4998 selected_tab = self._extract_selected_tab(tabs)
bd7e919a 4999 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
5000 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
5001
5002 return self.playlist_result(
5003 self._entries(
5004 selected_tab, metadata['id'], ytcfg,
5005 self._extract_account_syncid(ytcfg, data),
5006 self._extract_visitor_data(data, ytcfg)),
5007 **metadata)
39ed931e 5008
bd7e919a 5009 def _extract_metadata_from_tabs(self, item_id, data):
5010 info = {'id': item_id}
5011
5012 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
6141346d 5013 if metadata_renderer:
7666b936 5014 channel_id = traverse_obj(metadata_renderer, ('externalId', {self.ucid_or_none}),
4823ec9f 5015 ('channelUrl', {self.ucid_from_url}))
bd7e919a 5016 info.update({
7666b936 5017 'channel': metadata_renderer.get('title'),
5018 'channel_id': channel_id,
bd7e919a 5019 })
7666b936 5020 if info['channel_id']:
5021 info['id'] = info['channel_id']
bd7e919a 5022 else:
5023 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
b60419c5 5024
301d07fc 5025 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
5026 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
5027 def _get_uncropped(url):
5028 return url_or_none((url or '').split('=')[0] + '=s0')
5029
6141346d 5030 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
301d07fc 5031 if avatar_thumbnails:
5032 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
5033 if uncropped_avatar:
5034 avatar_thumbnails.append({
5035 'url': uncropped_avatar,
5036 'id': 'avatar_uncropped',
5037 'preference': 1
5038 })
5039
5040 channel_banners = self._extract_thumbnails(
bd7e919a 5041 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
301d07fc 5042 for banner in channel_banners:
5043 banner['preference'] = -10
5044
5045 if channel_banners:
5046 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
5047 if uncropped_banner:
5048 channel_banners.append({
5049 'url': uncropped_banner,
5050 'id': 'banner_uncropped',
5051 'preference': -5
5052 })
5053
bd7e919a 5054 # Deprecated - remove primary_sidebar_renderer when layout discontinued
5055 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
5056 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
5057
301d07fc 5058 primary_thumbnails = self._extract_thumbnails(
a17526e4 5059 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
6141346d
M
5060 playlist_thumbnails = self._extract_thumbnails(
5061 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
5062
bd7e919a 5063 info.update({
5064 'title': (traverse_obj(metadata_renderer, 'title')
5065 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
5066 or info['id']),
5067 'availability': self._extract_availability(data),
5068 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
5069 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
5070 'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
5071 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
5072 })
f0d785d3 5073
7666b936 5074 channel_handle = (
5075 traverse_obj(metadata_renderer, (('vanityChannelUrl', ('ownerUrls', ...)), {self.handle_from_url}), get_all=False)
5076 or traverse_obj(data, ('header', ..., 'channelHandleText', {self.handle_or_none}), get_all=False))
5077
5078 if channel_handle:
5079 info.update({
5080 'uploader_id': channel_handle,
5081 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
5082 })
8213ce28 5083
5084 channel_badges = self._extract_badges(traverse_obj(data, ('header', ..., 'badges'), get_all=False))
5085 if self._has_badge(channel_badges, BadgeType.VERIFIED):
5086 info['channel_is_verified'] = True
6141346d
M
5087 # Playlist stats is a text runs array containing [video count, view count, last updated].
5088 # last updated or (view count and last updated) may be missing.
5089 playlist_stats = get_first(
bd7e919a 5090 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
5091
6141346d
M
5092 last_updated_unix = self._parse_time_text(
5093 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
5094 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
ad54c913 5095 info['modified_date'] = strftime_or_none(last_updated_unix)
6141346d 5096
bd7e919a 5097 info['view_count'] = self._get_count(playlist_stats, 1)
5098 if info['view_count'] is None: # 0 is allowed
5099 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
31e18355 5100 if info['view_count'] is None:
5101 info['view_count'] = self._get_count(data, (
5102 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer',
5103 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText'))
bd7e919a 5104
5105 info['playlist_count'] = self._get_count(playlist_stats, 0)
5106 if info['playlist_count'] is None: # 0 is allowed
5107 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
5108
7666b936 5109 if not info.get('channel_id'):
6141346d 5110 owner = traverse_obj(playlist_header_renderer, 'ownerText')
bd7e919a 5111 if not owner: # Deprecated
6141346d
M
5112 owner = traverse_obj(
5113 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
5114 ('videoOwner', 'videoOwnerRenderer', 'title'))
5115 owner_text = self._get_text(owner)
5116 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
bd7e919a 5117 info.update({
7666b936 5118 'channel': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
5119 'channel_id': self.ucid_or_none(browse_ep.get('browseId')),
5120 'uploader_id': self.handle_from_url(urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl')))
bd7e919a 5121 })
6141346d 5122
bd7e919a 5123 info.update({
7666b936 5124 'uploader': info['channel'],
5125 'channel_url': format_field(info.get('channel_id'), None, 'https://www.youtube.com/channel/%s', default=None),
5126 'uploader_url': format_field(info.get('uploader_id'), None, 'https://www.youtube.com/%s', default=None),
bd7e919a 5127 })
7666b936 5128
bd7e919a 5129 return info
73c4ac2c 5130
6e634cbe 5131 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 5132 first_id = last_id = response = None
2be71994 5133 for page_num in itertools.count(1):
cd7c66cf 5134 videos = list(self._playlist_entries(playlist))
5135 if not videos:
5136 return
2be71994 5137 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
5138 if start >= len(videos):
5139 return
24146491 5140 yield from videos[start:]
2be71994 5141 first_id = first_id or videos[0]['id']
5142 last_id = videos[-1]['id']
79360d99 5143 watch_endpoint = try_get(
5144 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 5145 headers = self.generate_api_headers(
5146 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
5147 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 5148 query = {
5149 'playlistId': playlist_id,
5150 'videoId': watch_endpoint.get('videoId') or last_id,
5151 'index': watch_endpoint.get('index') or len(videos),
5152 'params': watch_endpoint.get('params') or 'OAE%3D'
5153 }
5154 response = self._extract_response(
5155 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 5156 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 5157 check_get_keys='contents'
5158 )
cd7c66cf 5159 playlist = try_get(
79360d99 5160 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 5161
ac56cf38 5162 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 5163 title = playlist.get('title') or try_get(
14f25df2 5164 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 5165 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 5166
5167 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 5168 playlist_url = urljoin(url, try_get(
5169 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 5170 str))
6e634cbe 5171
5172 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
5173 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
5174 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
5175
5176 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 5177 return self.url_result(
5178 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
5179 video_title=title)
cd7c66cf 5180
8bdd16b4 5181 return self.playlist_result(
6e634cbe 5182 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 5183 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 5184
47193e02 5185 def _extract_availability(self, data):
5186 """
5187 Gets the availability of a given playlist/tab.
5188 Note: Unless YouTube tells us explicitly, we do not assume it is public
5189 @param data: response
5190 """
6141346d
M
5191 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
5192 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
5193 player_header_privacy = playlist_header_renderer.get('privacy')
c26f9b99 5194
14a14335 5195 badges = self._extract_badges(traverse_obj(sidebar_renderer, 'badges'))
47193e02 5196
5197 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
6141346d
M
5198 privacy_setting_icon = get_first(
5199 (playlist_header_renderer, sidebar_renderer),
5200 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
5201 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
5202 expected_type=str)
5203
5204 microformats_is_unlisted = traverse_obj(
5205 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
47193e02 5206
c26f9b99 5207 return (
5208 'public' if (
5209 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
5210 or player_header_privacy == 'PUBLIC'
5211 or privacy_setting_icon == 'PRIVACY_PUBLIC')
5212 else self._availability(
5213 is_private=(
5214 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
5215 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
5216 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
5217 is_unlisted=(
5218 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
5219 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
6141346d
M
5220 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
5221 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
c26f9b99 5222 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
5223 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
5224 needs_auth=False))
47193e02 5225
5226 @staticmethod
5227 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
5228 sidebar_renderer = try_get(
5229 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
5230 for item in sidebar_renderer:
5231 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
5232 if renderer:
5233 return renderer
5234
ac56cf38 5235 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 5236 """
6141346d 5237 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
358de58c 5238 """
6141346d
M
5239 is_playlist = bool(traverse_obj(
5240 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5241 if not is_playlist:
47193e02 5242 return
11f9be09 5243 headers = self.generate_api_headers(
99e9e001 5244 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 5245 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 5246 query = {
6141346d
M
5247 'params': 'wgYCCAA=',
5248 'browseId': f'VL{item_id}'
47193e02 5249 }
5250 return self._extract_response(
5251 item_id=item_id, headers=headers, query=query,
fe93e2c4 5252 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
6141346d 5253 note='Redownloading playlist API JSON with unavailable videos')
358de58c 5254
2762dbb1 5255 @functools.cached_property
a25bca9f 5256 def skip_webpage(self):
5257 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
5258
ac56cf38 5259 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 5260 webpage, data = None, None
5261 for retry in self.RetryManager(fatal=fatal):
ac56cf38 5262 try:
be5c1ae8 5263 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 5264 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5265 except ExtractorError as e:
5266 if isinstance(e.cause, network_exceptions):
14f25df2 5267 if not isinstance(e.cause, urllib.error.HTTPError) or e.cause.code not in (403, 429):
be5c1ae8 5268 retry.error = e
5269 continue
5270 self._error_or_warning(e, fatal=fatal)
14fdfea9 5271 break
ac56cf38 5272
be5c1ae8 5273 try:
5274 self._extract_and_report_alerts(data)
5275 except ExtractorError as e:
5276 self._error_or_warning(e, fatal=fatal)
5277 break
ac56cf38 5278
be5c1ae8 5279 # Sometimes youtube returns a webpage with incomplete ytInitialData
5280 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5281 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5282 retry.error = ExtractorError('Incomplete yt initial data received')
5283 continue
ac56cf38 5284
cd7c66cf 5285 return webpage, data
5286
a25bca9f 5287 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5288 """Use if failed to extract ytcfg (and data) from initial webpage"""
5289 if not ytcfg and self.is_authenticated:
5290 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5291 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5292 raise ExtractorError(
5293 f'{msg}. If you are not downloading private content, or '
5294 'your cookies are only for the first account and channel,'
5295 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5296 expected=True)
5297 self.report_warning(msg, only_once=True)
5298
ac56cf38 5299 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5300 data = None
a25bca9f 5301 if not self.skip_webpage:
ac56cf38 5302 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5303 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 5304 # Reject webpage data if redirected to home page without explicitly requesting
86973308 5305 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
1108613f 5306 if (url != 'https://www.youtube.com/feed/recommended'
5307 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5308 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5309 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5310 if fatal:
5311 raise ExtractorError(msg, expected=True)
5312 self.report_warning(msg, only_once=True)
ac56cf38 5313 if not data:
a25bca9f 5314 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 5315 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5316 return data, ytcfg
5317
5318 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5319 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5320 resolve_response = self._extract_response(
5321 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5322 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5323 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5324 for ep_key, ep in endpoints.items():
5325 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5326 if params:
5327 return self._extract_response(
5328 item_id=item_id, query=params, ep=ep, headers=headers,
5329 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 5330 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 5331 err_note = 'Failed to resolve url (does the playlist exist?)'
5332 if fatal:
5333 raise ExtractorError(err_note, expected=True)
5334 self.report_warning(err_note, item_id)
5335
a6213a49 5336 _SEARCH_PARAMS = None
5337
af5c1c55 5338 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 5339 data = {'query': query}
5340 if params is NO_DEFAULT:
5341 params = self._SEARCH_PARAMS
5342 if params:
5343 data['params'] = params
16aa9ea4 5344
5345 content_keys = (
5346 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5347 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5348 # ytmusic search
5349 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5350 ('continuationContents', ),
5351 )
a25bca9f 5352 display_id = f'query "{query}"'
86e5f3ed 5353 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 5354 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5355 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 5356
a61fd4cf 5357 continuation_list = [None]
a25bca9f 5358 search = None
a6213a49 5359 for page_num in itertools.count(1):
a61fd4cf 5360 data.update(continuation_list[0] or {})
a25bca9f 5361 headers = self.generate_api_headers(
5362 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 5363 search = self._extract_response(
a25bca9f 5364 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5365 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 5366 slr_contents = traverse_obj(search, *content_keys)
5367 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 5368 if not continuation_list[0]:
a6213a49 5369 break
5370
5371
5372class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5373 IE_DESC = 'YouTube Tabs'
5374 _VALID_URL = r'''(?x:
5375 https?://
b032ff0f 5376 (?!consent\.)(?:\w+\.)?
a6213a49 5377 (?:
5378 youtube(?:kids)?\.com|
5379 %(invidious)s
5380 )/
5381 (?:
5382 (?P<channel_type>channel|c|user|browse)/|
5383 (?P<not_channel>
5384 feed/|hashtag/|
5385 (?:playlist|watch)\?.*?\blist=
5386 )|
5387 (?!(?:%(reserved_names)s)\b) # Direct URLs
5388 )
5389 (?P<id>[^/?\#&]+)
5390 )''' % {
5391 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5392 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5393 }
5394 IE_NAME = 'youtube:tab'
5395
5396 _TESTS = [{
5397 'note': 'playlists, multipage',
5398 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5399 'playlist_mincount': 94,
5400 'info_dict': {
5401 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5402 'title': 'Igor Kleiner - Playlists',
a6213a49 5403 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5404 'uploader': 'Igor Kleiner',
7666b936 5405 'uploader_id': '@IgorDataScience',
5406 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
976ae3ea 5407 'channel': 'Igor Kleiner',
5408 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5409 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5410 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5411 'channel_follower_count': int
a6213a49 5412 },
5413 }, {
5414 'note': 'playlists, multipage, different order',
5415 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5416 'playlist_mincount': 94,
5417 'info_dict': {
5418 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5419 'title': 'Igor Kleiner - Playlists',
a6213a49 5420 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5421 'uploader': 'Igor Kleiner',
7666b936 5422 'uploader_id': '@IgorDataScience',
5423 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
976ae3ea 5424 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5425 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5426 'channel': 'Igor Kleiner',
5427 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5428 'channel_follower_count': int
a6213a49 5429 },
5430 }, {
5431 'note': 'playlists, series',
5432 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5433 'playlist_mincount': 5,
5434 'info_dict': {
5435 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5436 'title': '3Blue1Brown - Playlists',
5437 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
976ae3ea 5438 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5439 'channel': '3Blue1Brown',
5440 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
7666b936 5441 'uploader_id': '@3blue1brown',
5442 'uploader_url': 'https://www.youtube.com/@3blue1brown',
5443 'uploader': '3Blue1Brown',
976ae3ea 5444 'tags': ['Mathematics'],
14a14335 5445 'channel_follower_count': int,
8213ce28 5446 'channel_is_verified': True,
a6213a49 5447 },
5448 }, {
5449 'note': 'playlists, singlepage',
5450 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5451 'playlist_mincount': 4,
5452 'info_dict': {
5453 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5454 'title': 'ThirstForScience - Playlists',
5455 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5456 'uploader': 'ThirstForScience',
7666b936 5457 'uploader_url': 'https://www.youtube.com/@ThirstForScience',
5458 'uploader_id': '@ThirstForScience',
976ae3ea 5459 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
7666b936 5460 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 5461 'tags': 'count:13',
5462 'channel': 'ThirstForScience',
6c73052c 5463 'channel_follower_count': int
a6213a49 5464 }
5465 }, {
5466 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5467 'only_matching': True,
5468 }, {
5469 'note': 'basic, single video playlist',
5470 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5471 'info_dict': {
a6213a49 5472 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5473 'title': 'youtube-dl public playlist',
976ae3ea 5474 'description': '',
5475 'tags': [],
5476 'view_count': int,
5477 'modified_date': '20201130',
5478 'channel': 'Sergey M.',
5479 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
976ae3ea 5480 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5481 'availability': 'public',
7666b936 5482 'uploader': 'Sergey M.',
5483 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
5484 'uploader_id': '@sergeym.6173',
a6213a49 5485 },
5486 'playlist_count': 1,
5487 }, {
5488 'note': 'empty playlist',
5489 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5490 'info_dict': {
a6213a49 5491 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5492 'title': 'youtube-dl empty playlist',
976ae3ea 5493 'tags': [],
5494 'channel': 'Sergey M.',
5495 'description': '',
5496 'modified_date': '20160902',
5497 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5498 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5499 'availability': 'public',
7666b936 5500 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
5501 'uploader_id': '@sergeym.6173',
5502 'uploader': 'Sergey M.',
a6213a49 5503 },
5504 'playlist_count': 0,
5505 }, {
5506 'note': 'Home tab',
5507 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5508 'info_dict': {
5509 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5510 'title': 'lex will - Home',
5511 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5512 'uploader': 'lex will',
7666b936 5513 'uploader_id': '@lexwill718',
976ae3ea 5514 'channel': 'lex will',
5515 'tags': ['bible', 'history', 'prophesy'],
7666b936 5516 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5517 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5518 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5519 'channel_follower_count': int
a6213a49 5520 },
5521 'playlist_mincount': 2,
5522 }, {
5523 'note': 'Videos tab',
5524 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5525 'info_dict': {
5526 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5527 'title': 'lex will - Videos',
5528 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5529 'uploader': 'lex will',
7666b936 5530 'uploader_id': '@lexwill718',
976ae3ea 5531 'tags': ['bible', 'history', 'prophesy'],
5532 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5533 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
7666b936 5534 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5535 'channel': 'lex will',
6c73052c 5536 'channel_follower_count': int
a6213a49 5537 },
5538 'playlist_mincount': 975,
5539 }, {
5540 'note': 'Videos tab, sorted by popular',
5541 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5542 'info_dict': {
5543 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5544 'title': 'lex will - Videos',
5545 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5546 'uploader': 'lex will',
7666b936 5547 'uploader_id': '@lexwill718',
976ae3ea 5548 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
7666b936 5549 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5550 'channel': 'lex will',
5551 'tags': ['bible', 'history', 'prophesy'],
5552 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5553 'channel_follower_count': int
a6213a49 5554 },
5555 'playlist_mincount': 199,
5556 }, {
5557 'note': 'Playlists tab',
5558 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5559 'info_dict': {
5560 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5561 'title': 'lex will - Playlists',
5562 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5563 'uploader': 'lex will',
7666b936 5564 'uploader_id': '@lexwill718',
5565 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5566 'channel': 'lex will',
5567 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5568 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5569 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5570 'channel_follower_count': int
a6213a49 5571 },
5572 'playlist_mincount': 17,
5573 }, {
5574 'note': 'Community tab',
5575 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5576 'info_dict': {
5577 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5578 'title': 'lex will - Community',
5579 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
976ae3ea 5580 'channel': 'lex will',
5581 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5582 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5583 'tags': ['bible', 'history', 'prophesy'],
7666b936 5584 'channel_follower_count': int,
5585 'uploader_url': 'https://www.youtube.com/@lexwill718',
5586 'uploader_id': '@lexwill718',
5587 'uploader': 'lex will',
a6213a49 5588 },
5589 'playlist_mincount': 18,
5590 }, {
5591 'note': 'Channels tab',
5592 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5593 'info_dict': {
5594 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5595 'title': 'lex will - Channels',
5596 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
976ae3ea 5597 'channel': 'lex will',
5598 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5599 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5600 'tags': ['bible', 'history', 'prophesy'],
7666b936 5601 'channel_follower_count': int,
5602 'uploader_url': 'https://www.youtube.com/@lexwill718',
5603 'uploader_id': '@lexwill718',
5604 'uploader': 'lex will',
a6213a49 5605 },
5606 'playlist_mincount': 12,
5607 }, {
5608 'note': 'Search tab',
5609 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5610 'playlist_mincount': 40,
5611 'info_dict': {
5612 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5613 'title': '3Blue1Brown - Search - linear algebra',
5614 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
976ae3ea 5615 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5616 'tags': ['Mathematics'],
5617 'channel': '3Blue1Brown',
5618 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
7666b936 5619 'channel_follower_count': int,
5620 'uploader_url': 'https://www.youtube.com/@3blue1brown',
5621 'uploader_id': '@3blue1brown',
5622 'uploader': '3Blue1Brown',
8213ce28 5623 'channel_is_verified': True,
a6213a49 5624 },
5625 }, {
5626 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5627 'only_matching': True,
5628 }, {
5629 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5630 'only_matching': True,
5631 }, {
5632 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5633 'only_matching': True,
5634 }, {
5635 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5636 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5637 'info_dict': {
5638 'title': '29C3: Not my department',
5639 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
a6213a49 5640 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 5641 'tags': [],
976ae3ea 5642 'view_count': int,
5643 'modified_date': '20150605',
5644 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
7666b936 5645 'channel_url': 'https://www.youtube.com/channel/UCEPzS1rYsrkqzSLNp76nrcg',
976ae3ea 5646 'channel': 'Christiaan008',
c26f9b99 5647 'availability': 'public',
7666b936 5648 'uploader_id': '@ChRiStIaAn008',
5649 'uploader': 'Christiaan008',
5650 'uploader_url': 'https://www.youtube.com/@ChRiStIaAn008',
a6213a49 5651 },
5652 'playlist_count': 96,
5653 }, {
5654 'note': 'Large playlist',
5655 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5656 'info_dict': {
5657 'title': 'Uploads from Cauchemar',
5658 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
7666b936 5659 'channel_url': 'https://www.youtube.com/channel/UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5660 'tags': [],
5661 'modified_date': r're:\d{8}',
5662 'channel': 'Cauchemar',
976ae3ea 5663 'view_count': int,
5664 'description': '',
5665 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
c26f9b99 5666 'availability': 'public',
7666b936 5667 'uploader_id': '@Cauchemar89',
5668 'uploader': 'Cauchemar',
5669 'uploader_url': 'https://www.youtube.com/@Cauchemar89',
a6213a49 5670 },
5671 'playlist_mincount': 1123,
976ae3ea 5672 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5673 }, {
5674 'note': 'even larger playlist, 8832 videos',
5675 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5676 'only_matching': True,
5677 }, {
5678 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5679 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5680 'info_dict': {
5681 'title': 'Uploads from Interstellar Movie',
5682 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5683 'tags': [],
5684 'view_count': int,
5685 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
7666b936 5686 'channel_url': 'https://www.youtube.com/channel/UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5687 'channel': 'Interstellar Movie',
5688 'description': '',
5689 'modified_date': r're:\d{8}',
c26f9b99 5690 'availability': 'public',
7666b936 5691 'uploader_id': '@InterstellarMovie',
5692 'uploader': 'Interstellar Movie',
5693 'uploader_url': 'https://www.youtube.com/@InterstellarMovie',
a6213a49 5694 },
5695 'playlist_mincount': 21,
5696 }, {
5697 'note': 'Playlist with "show unavailable videos" button',
5698 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5699 'info_dict': {
5700 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5701 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5702 'view_count': int,
5703 'channel': 'Phim Siêu Nhân Nhật Bản',
5704 'tags': [],
976ae3ea 5705 'description': '',
5706 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5707 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5708 'modified_date': r're:\d{8}',
c26f9b99 5709 'availability': 'public',
7666b936 5710 'uploader_url': 'https://www.youtube.com/@phimsieunhannhatban',
5711 'uploader_id': '@phimsieunhannhatban',
5712 'uploader': 'Phim Siêu Nhân Nhật Bản',
a6213a49 5713 },
5714 'playlist_mincount': 200,
976ae3ea 5715 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5716 }, {
5717 'note': 'Playlist with unavailable videos in page 7',
5718 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5719 'info_dict': {
5720 'title': 'Uploads from BlankTV',
5721 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5722 'channel': 'BlankTV',
7666b936 5723 'channel_url': 'https://www.youtube.com/channel/UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5724 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5725 'view_count': int,
5726 'tags': [],
976ae3ea 5727 'modified_date': r're:\d{8}',
5728 'description': '',
c26f9b99 5729 'availability': 'public',
7666b936 5730 'uploader_id': '@blanktv',
5731 'uploader': 'BlankTV',
5732 'uploader_url': 'https://www.youtube.com/@blanktv',
a6213a49 5733 },
5734 'playlist_mincount': 1000,
976ae3ea 5735 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5736 }, {
5737 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5738 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5739 'info_dict': {
5740 'title': 'Data Analysis with Dr Mike Pound',
5741 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
a6213a49 5742 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5743 'tags': [],
5744 'view_count': int,
5745 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
7666b936 5746 'channel_url': 'https://www.youtube.com/channel/UC9-y-6csu5WGm29I7JiwpnA',
976ae3ea 5747 'channel': 'Computerphile',
c26f9b99 5748 'availability': 'public',
6141346d 5749 'modified_date': '20190712',
7666b936 5750 'uploader_id': '@Computerphile',
5751 'uploader': 'Computerphile',
5752 'uploader_url': 'https://www.youtube.com/@Computerphile',
a6213a49 5753 },
5754 'playlist_mincount': 11,
5755 }, {
5756 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5757 'only_matching': True,
5758 }, {
5759 'note': 'Playlist URL that does not actually serve a playlist',
5760 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5761 'info_dict': {
5762 'id': 'FqZTN594JQw',
5763 'ext': 'webm',
5764 'title': "Smiley's People 01 detective, Adventure Series, Action",
a6213a49 5765 'upload_date': '20150526',
5766 'license': 'Standard YouTube License',
5767 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5768 'categories': ['People & Blogs'],
5769 'tags': list,
5770 'view_count': int,
5771 'like_count': int,
a6213a49 5772 },
5773 'params': {
5774 'skip_download': True,
5775 },
5776 'skip': 'This video is not available.',
5777 'add_ie': [YoutubeIE.ie_key()],
5778 }, {
5779 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5780 'only_matching': True,
5781 }, {
5782 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5783 'only_matching': True,
5784 }, {
5785 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5786 'info_dict': {
14a14335 5787 'id': 'hGkQjiJLjWQ', # This will keep changing
a6213a49 5788 'ext': 'mp4',
976ae3ea 5789 'title': str,
a6213a49 5790 'upload_date': r're:\d{8}',
976ae3ea 5791 'description': str,
a6213a49 5792 'categories': ['News & Politics'],
5793 'tags': list,
5794 'like_count': int,
86973308 5795 'release_timestamp': int,
976ae3ea 5796 'channel': 'Sky News',
5797 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5798 'age_limit': 0,
5799 'view_count': int,
86973308 5800 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
976ae3ea 5801 'playable_in_embed': True,
86973308 5802 'release_date': r're:\d+',
976ae3ea 5803 'availability': 'public',
5804 'live_status': 'is_live',
5805 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
86973308
M
5806 'channel_follower_count': int,
5807 'concurrent_view_count': int,
7666b936 5808 'uploader_url': 'https://www.youtube.com/@SkyNews',
5809 'uploader_id': '@SkyNews',
5810 'uploader': 'Sky News',
8213ce28 5811 'channel_is_verified': True,
a6213a49 5812 },
5813 'params': {
5814 'skip_download': True,
5815 },
976ae3ea 5816 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5817 }, {
5818 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5819 'info_dict': {
5820 'id': 'a48o2S1cPoo',
5821 'ext': 'mp4',
5822 'title': 'The Young Turks - Live Main Show',
a6213a49 5823 'upload_date': '20150715',
5824 'license': 'Standard YouTube License',
5825 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5826 'categories': ['News & Politics'],
5827 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5828 'like_count': int,
a6213a49 5829 },
5830 'params': {
5831 'skip_download': True,
5832 },
5833 'only_matching': True,
5834 }, {
5835 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5836 'only_matching': True,
5837 }, {
5838 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5839 'only_matching': True,
5840 }, {
5841 'note': 'A channel that is not live. Should raise error',
5842 'url': 'https://www.youtube.com/user/numberphile/live',
5843 'only_matching': True,
5844 }, {
5845 'url': 'https://www.youtube.com/feed/trending',
5846 'only_matching': True,
5847 }, {
5848 'url': 'https://www.youtube.com/feed/library',
5849 'only_matching': True,
5850 }, {
5851 'url': 'https://www.youtube.com/feed/history',
5852 'only_matching': True,
5853 }, {
5854 'url': 'https://www.youtube.com/feed/subscriptions',
5855 'only_matching': True,
5856 }, {
5857 'url': 'https://www.youtube.com/feed/watch_later',
5858 'only_matching': True,
5859 }, {
5860 'note': 'Recommended - redirects to home page.',
5861 'url': 'https://www.youtube.com/feed/recommended',
5862 'only_matching': True,
5863 }, {
5864 'note': 'inline playlist with not always working continuations',
5865 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5866 'only_matching': True,
5867 }, {
5868 'url': 'https://www.youtube.com/course',
5869 'only_matching': True,
5870 }, {
5871 'url': 'https://www.youtube.com/zsecurity',
5872 'only_matching': True,
5873 }, {
5874 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5875 'only_matching': True,
5876 }, {
5877 'url': 'https://www.youtube.com/TheYoungTurks/live',
5878 'only_matching': True,
5879 }, {
5880 'url': 'https://www.youtube.com/hashtag/cctv9',
5881 'info_dict': {
5882 'id': 'cctv9',
5883 'title': '#cctv9',
976ae3ea 5884 'tags': [],
a6213a49 5885 },
4dc23a80 5886 'playlist_mincount': 300, # not consistent but should be over 300
a6213a49 5887 }, {
5888 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5889 'only_matching': True,
5890 }, {
5891 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5892 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5893 'only_matching': True
5894 }, {
5895 'note': '/browse/ should redirect to /channel/',
5896 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5897 'only_matching': True
5898 }, {
5899 'note': 'VLPL, should redirect to playlist?list=PL...',
5900 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5901 'info_dict': {
5902 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
a6213a49 5903 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
12a1b225 5904 'title': 'NCS : All Releases 💿',
7666b936 5905 'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
976ae3ea 5906 'modified_date': r're:\d{8}',
5907 'view_count': int,
5908 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5909 'tags': [],
5910 'channel': 'NoCopyrightSounds',
c26f9b99 5911 'availability': 'public',
7666b936 5912 'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds',
5913 'uploader': 'NoCopyrightSounds',
5914 'uploader_id': '@NoCopyrightSounds',
a6213a49 5915 },
5916 'playlist_mincount': 166,
7666b936 5917 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden', 'YouTube Music is not directly supported'],
a6213a49 5918 }, {
7666b936 5919 # TODO: fix 'unviewable' issue with this playlist when reloading with unavailable videos
a6213a49 5920 'note': 'Topic, should redirect to playlist?list=UU...',
5921 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5922 'info_dict': {
5923 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5924 'title': 'Uploads from Royalty Free Music - Topic',
976ae3ea 5925 'tags': [],
5926 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5927 'channel': 'Royalty Free Music - Topic',
5928 'view_count': int,
5929 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
976ae3ea 5930 'modified_date': r're:\d{8}',
976ae3ea 5931 'description': '',
c26f9b99 5932 'availability': 'public',
7666b936 5933 'uploader': 'Royalty Free Music - Topic',
a6213a49 5934 },
a6213a49 5935 'playlist_mincount': 101,
7666b936 5936 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5937 }, {
86973308
M
5938 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5939 # Treat as a general feed
a6213a49 5940 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5941 'info_dict': {
5942 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5943 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5944 'tags': [],
a6213a49 5945 },
a6213a49 5946 'playlist_mincount': 9,
5947 }, {
5948 'note': 'Youtube music Album',
5949 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5950 'info_dict': {
5951 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5952 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5953 'tags': [],
5954 'view_count': int,
5955 'description': '',
5956 'availability': 'unlisted',
5957 'modified_date': r're:\d{8}',
a6213a49 5958 },
5959 'playlist_count': 50,
7666b936 5960 'expected_warnings': ['YouTube Music is not directly supported'],
a6213a49 5961 }, {
5962 'note': 'unlisted single video playlist',
5963 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5964 'info_dict': {
a6213a49 5965 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5966 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5967 'availability': 'unlisted',
5968 'tags': [],
12a1b225 5969 'modified_date': '20220418',
976ae3ea 5970 'channel': 'colethedj',
5971 'view_count': int,
5972 'description': '',
976ae3ea 5973 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5974 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
7666b936 5975 'uploader_url': 'https://www.youtube.com/@colethedj1894',
5976 'uploader_id': '@colethedj1894',
5977 'uploader': 'colethedj',
a6213a49 5978 },
93e12ed7 5979 'playlist': [{
5980 'info_dict': {
5981 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
5982 'id': 'BaW_jenozKc',
5983 '_type': 'url',
5984 'ie_key': 'Youtube',
5985 'duration': 10,
5986 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
5987 'channel_url': 'https://www.youtube.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
5988 'view_count': int,
5989 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc',
5990 'channel': 'Philipp Hagemeister',
5991 'uploader_id': '@PhilippHagemeister',
5992 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
5993 'uploader': 'Philipp Hagemeister',
5994 }
5995 }],
a6213a49 5996 'playlist_count': 1,
93e12ed7 5997 'params': {'extract_flat': True},
a6213a49 5998 }, {
5999 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
6000 'url': 'https://www.youtube.com/feed/recommended',
6001 'info_dict': {
6002 'id': 'recommended',
6003 'title': 'recommended',
6c73052c 6004 'tags': [],
a6213a49 6005 },
6006 'playlist_mincount': 50,
6007 'params': {
6008 'skip_download': True,
6009 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6010 },
6011 }, {
6012 'note': 'API Fallback: /videos tab, sorted by oldest first',
6013 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
6014 'info_dict': {
6015 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
6016 'title': 'Cody\'sLab - Videos',
6017 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
976ae3ea 6018 'channel': 'Cody\'sLab',
6019 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
6020 'tags': [],
6021 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 6022 'channel_follower_count': int
a6213a49 6023 },
6024 'playlist_mincount': 650,
6025 'params': {
6026 'skip_download': True,
6027 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6028 },
86973308 6029 'skip': 'Query for sorting no longer works',
a6213a49 6030 }, {
6031 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
6032 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
6033 'info_dict': {
6034 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 6035 'title': 'Uploads from Royalty Free Music - Topic',
976ae3ea 6036 'modified_date': r're:\d{8}',
6037 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
6038 'description': '',
6039 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
6040 'tags': [],
6041 'channel': 'Royalty Free Music - Topic',
6042 'view_count': int,
c26f9b99 6043 'availability': 'public',
7666b936 6044 'uploader': 'Royalty Free Music - Topic',
a6213a49 6045 },
a6213a49 6046 'playlist_mincount': 101,
6047 'params': {
6048 'skip_download': True,
6049 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6050 },
7666b936 6051 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
7c219ea6 6052 }, {
6053 'note': 'non-standard redirect to regional channel',
6054 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
6055 'only_matching': True
61d3665d 6056 }, {
6057 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
6058 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
6059 'info_dict': {
6060 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
6061 'modified_date': '20220407',
6062 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
6063 'tags': [],
61d3665d 6064 'availability': 'unlisted',
6065 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
6066 'channel': 'pukkandan',
6067 'description': 'Test for collaborative playlist',
6068 'title': 'yt-dlp test - collaborative playlist',
12a1b225 6069 'view_count': int,
7666b936 6070 'uploader_url': 'https://www.youtube.com/@pukkandan',
6071 'uploader_id': '@pukkandan',
6072 'uploader': 'pukkandan',
61d3665d 6073 },
6074 'playlist_mincount': 2
c26f9b99 6075 }, {
6076 'note': 'translated tab name',
6077 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
6078 'info_dict': {
6079 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6080 'tags': [],
c26f9b99 6081 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
4dc23a80 6082 'description': 'test description',
c26f9b99 6083 'title': 'cole-dlp-test-acc - 再生リスト',
c26f9b99 6084 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6085 'channel': 'cole-dlp-test-acc',
7666b936 6086 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6087 'uploader_id': '@coletdjnz',
6088 'uploader': 'cole-dlp-test-acc',
c26f9b99 6089 },
6090 'playlist_mincount': 1,
6091 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
6092 'expected_warnings': ['Preferring "ja"'],
6093 }, {
6094 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
6095 'note': 'preferred lang set with playlist with translated video titles',
6096 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
6097 'info_dict': {
6098 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
6099 'tags': [],
6100 'view_count': int,
6101 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
c26f9b99 6102 'channel': 'cole-dlp-test-acc',
6103 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6104 'description': 'test',
c26f9b99 6105 'title': 'dlp test playlist',
6106 'availability': 'public',
7666b936 6107 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6108 'uploader_id': '@coletdjnz',
6109 'uploader': 'cole-dlp-test-acc',
c26f9b99 6110 },
6111 'playlist_mincount': 1,
6112 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
6113 'expected_warnings': ['Preferring "ja"'],
80eb0bd9 6114 }, {
6115 # shorts audio pivot for 2GtVksBMYFM.
6116 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
6117 'info_dict': {
6118 'id': 'sfv_audio_pivot',
6119 'title': 'sfv_audio_pivot',
6120 'tags': [],
6121 },
6122 'playlist_mincount': 50,
6123
86973308
M
6124 }, {
6125 # Channel with a real live tab (not to be mistaken with streams tab)
6126 # Do not treat like it should redirect to live stream
6127 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
6128 'info_dict': {
6129 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
6130 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
6131 'tags': [],
6132 },
6133 'playlist_mincount': 20,
6134 }, {
6135 # Tab name is not the same as tab id
6136 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
6137 'info_dict': {
6138 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6139 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
6140 'tags': [],
6141 },
6142 'playlist_mincount': 8,
6143 }, {
6144 # Home tab id is literally home. Not to get mistaken with featured
6145 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
6146 'info_dict': {
6147 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6148 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
6149 'tags': [],
6150 },
6151 'playlist_mincount': 8,
6152 }, {
6153 # Should get three playlists for videos, shorts and streams tabs
6154 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
6155 'info_dict': {
6156 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
bd7e919a 6157 'title': 'Polka Ch. 尾丸ポルカ',
6158 'channel_follower_count': int,
6159 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
6160 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
7666b936 6161 'description': 'md5:e56b74b5bb7e9c701522162e9abfb822',
bd7e919a 6162 'channel': 'Polka Ch. 尾丸ポルカ',
6163 'tags': 'count:35',
7666b936 6164 'uploader_url': 'https://www.youtube.com/@OmaruPolka',
6165 'uploader': 'Polka Ch. 尾丸ポルカ',
6166 'uploader_id': '@OmaruPolka',
86973308
M
6167 },
6168 'playlist_count': 3,
6169 }, {
6170 # Shorts tab with channel with handle
7666b936 6171 # TODO: fix channel description
86973308
M
6172 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
6173 'info_dict': {
6174 'id': 'UC0intLFzLaudFG-xAvUEO-A',
6175 'title': 'Not Just Bikes - Shorts',
6176 'tags': 'count:12',
86973308 6177 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
7666b936 6178 'description': 'md5:26bc55af26855a608a5cf89dfa595c8d',
86973308 6179 'channel_follower_count': int,
86973308 6180 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
86973308 6181 'channel': 'Not Just Bikes',
7666b936 6182 'uploader_url': 'https://www.youtube.com/@NotJustBikes',
6183 'uploader': 'Not Just Bikes',
6184 'uploader_id': '@NotJustBikes',
86973308
M
6185 },
6186 'playlist_mincount': 10,
6187 }, {
6188 # Streams tab
6189 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
6190 'info_dict': {
6191 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6192 'title': '中村悠一 - Live',
6193 'tags': 'count:7',
6194 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6195 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
86973308 6196 'channel': '中村悠一',
86973308 6197 'channel_follower_count': int,
86973308 6198 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
7666b936 6199 'uploader_url': 'https://www.youtube.com/@Yuichi-Nakamura',
6200 'uploader_id': '@Yuichi-Nakamura',
6201 'uploader': '中村悠一',
86973308
M
6202 },
6203 'playlist_mincount': 60,
6204 }, {
6205 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
6206 # See test_youtube_lists
6207 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
6208 'only_matching': True,
6209 }, {
6210 # No uploads and no UCID given. Should fail with no uploads error
6211 # See test_youtube_lists
6212 'url': 'https://www.youtube.com/news',
6213 'only_matching': True
6214 }, {
6215 # No videos tab but has a shorts tab
6216 'url': 'https://www.youtube.com/c/TKFShorts',
6217 'info_dict': {
6218 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6219 'title': 'Shorts Break - Shorts',
7666b936 6220 'tags': 'count:48',
86973308
M
6221 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6222 'channel': 'Shorts Break',
7666b936 6223 'description': 'md5:6de33c5e7ba686e5f3efd4e19c7ef499',
86973308 6224 'channel_follower_count': int,
86973308 6225 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
7666b936 6226 'uploader_url': 'https://www.youtube.com/@ShortsBreak_Official',
6227 'uploader': 'Shorts Break',
6228 'uploader_id': '@ShortsBreak_Official',
86973308
M
6229 },
6230 'playlist_mincount': 30,
6231 }, {
6232 # Trending Now Tab. tab id is empty
6233 'url': 'https://www.youtube.com/feed/trending',
6234 'info_dict': {
6235 'id': 'trending',
6236 'title': 'trending - Now',
6237 'tags': [],
6238 },
6239 'playlist_mincount': 30,
6240 }, {
6241 # Trending Gaming Tab. tab id is empty
6242 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
6243 'info_dict': {
6244 'id': 'trending',
6245 'title': 'trending - Gaming',
6246 'tags': [],
6247 },
6248 'playlist_mincount': 30,
4dc23a80
M
6249 }, {
6250 # Shorts url result in shorts tab
7666b936 6251 # TODO: Fix channel id extraction
4dc23a80
M
6252 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6253 'info_dict': {
6254 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6255 'title': 'cole-dlp-test-acc - Shorts',
4dc23a80 6256 'channel': 'cole-dlp-test-acc',
4dc23a80
M
6257 'description': 'test description',
6258 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6259 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6260 'tags': [],
7666b936 6261 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6262 'uploader_id': '@coletdjnz',
4dc23a80 6263 'uploader': 'cole-dlp-test-acc',
4dc23a80
M
6264 },
6265 'playlist': [{
6266 'info_dict': {
7666b936 6267 # Channel data is not currently available for short renderers (as of 2023-03-01)
4dc23a80
M
6268 '_type': 'url',
6269 'ie_key': 'Youtube',
6270 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6271 'id': 'sSM9J5YH_60',
4dc23a80 6272 'title': 'SHORT short',
4dc23a80
M
6273 'view_count': int,
6274 'thumbnails': list,
6275 }
6276 }],
6277 'params': {'extract_flat': True},
6278 }, {
6279 # Live video status should be extracted
6280 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6281 'info_dict': {
6282 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6283 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6284 'tags': []
6285 },
6286 'playlist': [{
6287 'info_dict': {
6288 '_type': 'url',
6289 'ie_key': 'Youtube',
6290 'url': 'startswith:https://www.youtube.com/watch?v=',
6291 'id': str,
6292 'title': str,
6293 'live_status': 'is_live',
6294 'channel_id': str,
6295 'channel_url': str,
6296 'concurrent_view_count': int,
6297 'channel': str,
93e12ed7 6298 'uploader': str,
6299 'uploader_url': str,
14a14335 6300 'uploader_id': str,
8213ce28 6301 'channel_is_verified': bool, # this will keep changing
4dc23a80
M
6302 }
6303 }],
c7335551 6304 'params': {'extract_flat': True, 'playlist_items': '1'},
4dc23a80 6305 'playlist_mincount': 1
c7335551
M
6306 }, {
6307 # Channel renderer metadata. Contains number of videos on the channel
6308 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6309 'info_dict': {
6310 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6311 'title': 'cole-dlp-test-acc - Channels',
c7335551
M
6312 'channel': 'cole-dlp-test-acc',
6313 'description': 'test description',
6314 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6315 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6316 'tags': [],
7666b936 6317 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6318 'uploader_id': '@coletdjnz',
c7335551 6319 'uploader': 'cole-dlp-test-acc',
c7335551
M
6320 },
6321 'playlist': [{
6322 'info_dict': {
6323 '_type': 'url',
6324 'ie_key': 'YoutubeTab',
6325 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6326 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6327 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6328 'title': 'PewDiePie',
6329 'channel': 'PewDiePie',
6330 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6331 'thumbnails': list,
6332 'channel_follower_count': int,
7666b936 6333 'playlist_count': int,
6334 'uploader': 'PewDiePie',
6335 'uploader_url': 'https://www.youtube.com/@PewDiePie',
6336 'uploader_id': '@PewDiePie',
8213ce28 6337 'channel_is_verified': True,
c7335551
M
6338 }
6339 }],
6340 'params': {'extract_flat': True},
31e18355 6341 }, {
6342 'url': 'https://www.youtube.com/@3blue1brown/about',
6343 'info_dict': {
6344 'id': 'UCYO_jab_esuFRV4b17AJtAw',
6345 'tags': ['Mathematics'],
6346 'title': '3Blue1Brown - About',
31e18355 6347 'channel_follower_count': int,
6348 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
31e18355 6349 'channel': '3Blue1Brown',
31e18355 6350 'view_count': int,
6351 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6352 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
7666b936 6353 'uploader_url': 'https://www.youtube.com/@3blue1brown',
6354 'uploader_id': '@3blue1brown',
6355 'uploader': '3Blue1Brown',
8213ce28 6356 'channel_is_verified': True,
31e18355 6357 },
6358 'playlist_count': 0,
447afb9e 6359 }, {
6360 # Podcasts tab, with rich entry playlistRenderers
6361 'url': 'https://www.youtube.com/@99percentinvisiblepodcast/podcasts',
6362 'info_dict': {
6363 'id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6364 'channel_id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6365 'uploader_url': 'https://www.youtube.com/@99percentinvisiblepodcast',
6366 'description': 'md5:3a0ed38f1ad42a68ef0428c04a15695c',
6367 'title': '99 Percent Invisible - Podcasts',
6368 'uploader': '99 Percent Invisible',
6369 'channel_follower_count': int,
6370 'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6371 'tags': [],
6372 'channel': '99 Percent Invisible',
6373 'uploader_id': '@99percentinvisiblepodcast',
6374 },
6375 'playlist_count': 1,
6376 }, {
6377 # Releases tab, with rich entry playlistRenderers (same as Podcasts tab)
6378 'url': 'https://www.youtube.com/@AHimitsu/releases',
6379 'info_dict': {
6380 'id': 'UCgFwu-j5-xNJml2FtTrrB3A',
6381 'channel': 'A Himitsu',
6382 'uploader_url': 'https://www.youtube.com/@AHimitsu',
6383 'title': 'A Himitsu - Releases',
6384 'uploader_id': '@AHimitsu',
6385 'uploader': 'A Himitsu',
6386 'channel_id': 'UCgFwu-j5-xNJml2FtTrrB3A',
6387 'tags': 'count:16',
6388 'description': 'I make music',
6389 'channel_url': 'https://www.youtube.com/channel/UCgFwu-j5-xNJml2FtTrrB3A',
6390 'channel_follower_count': int,
8213ce28 6391 'channel_is_verified': True,
447afb9e 6392 },
6393 'playlist_mincount': 10,
fcbc9ed7 6394 }, {
6395 # Playlist with only shorts, shown as reel renderers
6396 # FIXME: future: YouTube currently doesn't give continuation for this,
6397 # may do in future.
6398 'url': 'https://www.youtube.com/playlist?list=UUxqPAgubo4coVn9Lx1FuKcg',
6399 'info_dict': {
6400 'id': 'UUxqPAgubo4coVn9Lx1FuKcg',
6401 'channel_url': 'https://www.youtube.com/channel/UCxqPAgubo4coVn9Lx1FuKcg',
6402 'view_count': int,
6403 'uploader_id': '@BangyShorts',
6404 'description': '',
6405 'uploader_url': 'https://www.youtube.com/@BangyShorts',
6406 'channel_id': 'UCxqPAgubo4coVn9Lx1FuKcg',
6407 'channel': 'Bangy Shorts',
6408 'uploader': 'Bangy Shorts',
6409 'tags': [],
6410 'availability': 'public',
6411 'modified_date': '20230626',
6412 'title': 'Uploads from Bangy Shorts',
6413 },
6414 'playlist_mincount': 100,
6415 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 6416 }]
6417
6418 @classmethod
6419 def suitable(cls, url):
86e5f3ed 6420 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 6421
86973308
M
6422 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6423
6424 def _get_url_mobj(self, url):
6425 mobj = self._URL_RE.match(url).groupdict()
6426 mobj.update((k, '') for k, v in mobj.items() if v is None)
6427 return mobj
6428
6429 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6430 tab_name = (tab.get('title') or '').lower()
6431 tab_url = urljoin(base_url, traverse_obj(
6432 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6433
bd7e919a 6434 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6435 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
86973308 6436 if tab_id:
bd7e919a 6437 return {
6438 'TAB_ID_SPONSORSHIPS': 'membership',
6439 }.get(tab_id, tab_id), tab_name
86973308
M
6440
6441 # Fallback to tab name if we cannot get the tab id.
6442 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6443 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
bd7e919a 6444 if tab_name:
6445 self.write_debug(f'Falling back to selected tab name: {tab_name}')
86973308
M
6446 return {
6447 'home': 'featured',
6448 'live': 'streams',
6449 }.get(tab_name, tab_name), tab_name
6450
6451 def _has_tab(self, tabs, tab_id):
6452 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
fe03a6cd 6453
182bda88 6454 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6455 def _real_extract(self, url, smuggled_data):
cd7c66cf 6456 item_id = self._match_id(url)
14f25df2 6457 url = urllib.parse.urlunparse(
6458 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 6459 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 6460
86973308
M
6461 mobj = self._get_url_mobj(url)
6462 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
bd7e919a 6463 if is_channel and smuggled_data.get('is_music_url'):
6464 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6465 return self.url_result(
6466 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6467 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6468 mdata = self._extract_tab_endpoint(
6469 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6470 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6471 get_all=False, expected_type=str)
6472 if not murl:
6473 raise ExtractorError('Failed to resolve album to playlist')
6474 return self.url_result(murl, YoutubeTabIE)
6475 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6476 return self.url_result(
6477 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6478
6479 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
fe03a6cd 6480 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6481 url = f'{pre}/videos{post}'
5b28cef7 6482 if smuggled_data.get('is_music_url'):
6483 self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}')
cd7c66cf 6484
6485 # Handle both video/playlist URLs
201c1459 6486 qs = parse_qs(url)
bd7e919a 6487 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
fe03a6cd 6488 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 6489 if not playlist_id:
fe03a6cd 6490 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
bd7e919a 6491 raise ExtractorError('A video URL was given without video ID', expected=True)
fe03a6cd 6492 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 6493 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
bd7e919a 6494 return self.url_result(
6495 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
cd7c66cf 6496
86973308
M
6497 if not self._yes_playlist(playlist_id, video_id):
6498 return self.url_result(
6499 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6500
bd7e919a 6501 data, ytcfg = self._extract_data(url, display_id)
14fdfea9 6502
7c219ea6 6503 # YouTube may provide a non-standard redirect to the regional channel
6504 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
86973308 6505 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
7c219ea6 6506 redirect_url = traverse_obj(
6507 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6508 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6509 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
86973308
M
6510 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6511 return self.url_result(redirect_url, YoutubeTabIE)
7c219ea6 6512
bd7e919a 6513 tabs, extra_tabs = self._extract_tab_renderers(data), []
86973308 6514 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
18db7548 6515 selected_tab = self._extract_selected_tab(tabs)
86973308
M
6516 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6517 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6518
6519 if not original_tab_id and selected_tab_name:
bd7e919a 6520 self.to_screen('Downloading all uploads of the channel. '
86973308
M
6521 'To download only the videos in a specific tab, pass the tab\'s URL')
6522 if self._has_tab(tabs, 'streams'):
bd7e919a 6523 extra_tabs.append(''.join((pre, '/streams', post)))
86973308 6524 if self._has_tab(tabs, 'shorts'):
bd7e919a 6525 extra_tabs.append(''.join((pre, '/shorts', post)))
86973308
M
6526 # XXX: Members-only tab should also be extracted
6527
bd7e919a 6528 if not extra_tabs and selected_tab_id != 'videos':
86973308
M
6529 # Channel does not have streams, shorts or videos tabs
6530 if item_id[:2] != 'UC':
6531 raise ExtractorError('This channel has no uploads', expected=True)
6532
6533 # Topic channels don't have /videos. Use the equivalent playlist instead
6534 pl_id = f'UU{item_id[2:]}'
6535 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6536 try:
6537 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6538 except ExtractorError:
6539 raise ExtractorError('This channel has no uploads', expected=True)
64f36541 6540 else:
86973308
M
6541 item_id, url = pl_id, pl_url
6542 self.to_screen(
6543 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6544
bd7e919a 6545 elif extra_tabs and selected_tab_id != 'videos':
86973308 6546 # When there are shorts/live tabs but not videos tab
bd7e919a 6547 url, data = f'{pre}{post}', None
86973308
M
6548
6549 elif (original_tab_id or 'videos') != selected_tab_id:
6550 if original_tab_id == 'live':
6551 # Live tab should have redirected to the video
6552 # Except in the case the channel has an actual live tab
6553 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
bd7e919a 6554 raise UserNotLive(video_id=item_id)
86973308
M
6555 elif selected_tab_name:
6556 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6557
6558 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6559 url = f'{pre}{post}'
18db7548 6560
358de58c 6561 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 6562 if 'no-youtube-unavailable-videos' not in compat_opts:
bd7e919a 6563 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
c0ac49bc 6564 self._extract_and_report_alerts(data, only_once=True)
86973308 6565
bd7e919a 6566 tabs, entries = self._extract_tab_renderers(data), []
8bdd16b4 6567 if tabs:
bd7e919a 6568 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6569 entries[0].update({
86973308
M
6570 'extractor_key': YoutubeTabIE.ie_key(),
6571 'extractor': YoutubeTabIE.IE_NAME,
6572 'webpage_url': url,
6573 })
bd7e919a 6574 if self.get_param('playlist_items') == '0':
6575 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6576 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6577 entries.extend(map(self._real_extract, extra_tabs))
6578
6579 if len(entries) == 1:
6580 return entries[0]
6581 elif entries:
6582 metadata = self._extract_metadata_from_tabs(item_id, data)
6583 uploads_url = 'the Uploads (UU) playlist URL'
6584 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6585 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6586 self.to_screen(
6587 'Downloading as multiple playlists, separated by tabs. '
6588 f'To download as a single playlist instead, pass {uploads_url}')
6589 return self.playlist_result(entries, item_id, **metadata)
6590
6591 # Inline playlist
37e57a9f 6592 playlist = traverse_obj(
6593 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 6594 if playlist:
ac56cf38 6595 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 6596
37e57a9f 6597 video_id = traverse_obj(
6598 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 6599 if video_id:
bd7e919a 6600 if tab != '/live': # live tab is expected to redirect to video
37e57a9f 6601 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
86973308 6602 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6603
8bdd16b4 6604 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 6605
c5e8d7af 6606
8bdd16b4 6607class YoutubePlaylistIE(InfoExtractor):
96565c7e 6608 IE_DESC = 'YouTube playlists'
8bdd16b4 6609 _VALID_URL = r'''(?x)(?:
6610 (?:https?://)?
6611 (?:\w+\.)?
6612 (?:
6613 (?:
6614 youtube(?:kids)?\.com|
d9190e44 6615 %(invidious)s
8bdd16b4 6616 )
6617 /.*?\?.*?\blist=
6618 )?
6619 (?P<id>%(playlist_id)s)
d9190e44
RH
6620 )''' % {
6621 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6622 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6623 }
8bdd16b4 6624 IE_NAME = 'youtube:playlist'
cdc628a4 6625 _TESTS = [{
8bdd16b4 6626 'note': 'issue #673',
6627 'url': 'PLBB231211A4F62143',
cdc628a4 6628 'info_dict': {
8bdd16b4 6629 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6630 'id': 'PLBB231211A4F62143',
976ae3ea 6631 'uploader': 'Wickman',
7666b936 6632 'uploader_id': '@WickmanVT',
11f9be09 6633 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 6634 'view_count': int,
7666b936 6635 'uploader_url': 'https://www.youtube.com/@WickmanVT',
976ae3ea 6636 'modified_date': r're:\d{8}',
6637 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6638 'channel': 'Wickman',
6639 'tags': [],
7666b936 6640 'channel_url': 'https://www.youtube.com/channel/UCKSpbfbl5kRQpTdL7kMc-1Q',
86973308 6641 'availability': 'public',
8bdd16b4 6642 },
6643 'playlist_mincount': 29,
6644 }, {
6645 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6646 'info_dict': {
6647 'title': 'YDL_safe_search',
6648 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6649 },
6650 'playlist_count': 2,
6651 'skip': 'This playlist is private',
9558dcec 6652 }, {
8bdd16b4 6653 'note': 'embedded',
6654 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6655 'playlist_count': 4,
9558dcec 6656 'info_dict': {
8bdd16b4 6657 'title': 'JODA15',
6658 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6659 'uploader': 'milan',
7666b936 6660 'uploader_id': '@milan5503',
976ae3ea 6661 'description': '',
6662 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6663 'tags': [],
6664 'modified_date': '20140919',
6665 'view_count': int,
6666 'channel': 'milan',
6667 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
7666b936 6668 'uploader_url': 'https://www.youtube.com/@milan5503',
c26f9b99 6669 'availability': 'public',
976ae3ea 6670 },
86973308 6671 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
cdc628a4 6672 }, {
8bdd16b4 6673 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 6674 'playlist_mincount': 455,
8bdd16b4 6675 'info_dict': {
6676 'title': '2018 Chinese New Singles (11/6 updated)',
6677 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6678 'uploader': 'LBK',
7666b936 6679 'uploader_id': '@music_king',
11f9be09 6680 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 6681 'channel': 'LBK',
6682 'view_count': int,
7666b936 6683 'channel_url': 'https://www.youtube.com/channel/UC21nz3_MesPLqtDqwdvnoxA',
976ae3ea 6684 'tags': [],
7666b936 6685 'uploader_url': 'https://www.youtube.com/@music_king',
976ae3ea 6686 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6687 'modified_date': r're:\d{8}',
c26f9b99 6688 'availability': 'public',
976ae3ea 6689 },
6690 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 6691 }, {
29f7c58a 6692 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6693 'only_matching': True,
6694 }, {
6695 # music album playlist
6696 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6697 'only_matching': True,
6698 }]
6699
6700 @classmethod
6701 def suitable(cls, url):
201c1459 6702 if YoutubeTabIE.suitable(url):
6703 return False
49a57e70 6704 from ..utils import parse_qs
201c1459 6705 qs = parse_qs(url)
6706 if qs.get('v', [None])[0]:
6707 return False
86e5f3ed 6708 return super().suitable(url)
29f7c58a 6709
6710 def _real_extract(self, url):
6711 playlist_id = self._match_id(url)
46953e7e 6712 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 6713 url = update_url_query(
6714 'https://www.youtube.com/playlist',
6715 parse_qs(url) or {'list': playlist_id})
6716 if is_music_url:
6717 url = smuggle_url(url, {'is_music_url': True})
6718 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 6719
6720
6721class YoutubeYtBeIE(InfoExtractor):
c76eb41b 6722 IE_DESC = 'youtu.be'
29f7c58a 6723 _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}
6724 _TESTS = [{
8bdd16b4 6725 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6726 'info_dict': {
6727 'id': 'yeWKywCrFtk',
6728 'ext': 'mp4',
6729 'title': 'Small Scale Baler and Braiding Rugs',
6730 'uploader': 'Backus-Page House Museum',
7666b936 6731 'uploader_id': '@backuspagemuseum',
6732 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@backuspagemuseum',
8bdd16b4 6733 'upload_date': '20161008',
6734 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6735 'categories': ['Nonprofits & Activism'],
6736 'tags': list,
6737 'like_count': int,
976ae3ea 6738 'age_limit': 0,
6739 'playable_in_embed': True,
7666b936 6740 'thumbnail': r're:^https?://.*\.webp',
976ae3ea 6741 'channel': 'Backus-Page House Museum',
6742 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6743 'live_status': 'not_live',
6744 'view_count': int,
6745 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6746 'availability': 'public',
6747 'duration': 59,
12a1b225
A
6748 'comment_count': int,
6749 'channel_follower_count': int
8bdd16b4 6750 },
6751 'params': {
6752 'noplaylist': True,
6753 'skip_download': True,
6754 },
39e7107d 6755 }, {
8bdd16b4 6756 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 6757 'only_matching': True,
cdc628a4
PH
6758 }]
6759
8bdd16b4 6760 def _real_extract(self, url):
5ad28e7f 6761 mobj = self._match_valid_url(url)
29f7c58a 6762 video_id = mobj.group('id')
6763 playlist_id = mobj.group('playlist_id')
8bdd16b4 6764 return self.url_result(
29f7c58a 6765 update_url_query('https://www.youtube.com/watch', {
6766 'v': video_id,
6767 'list': playlist_id,
6768 'feature': 'youtu.be',
6769 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 6770
6771
b6ce9bb0 6772class YoutubeLivestreamEmbedIE(InfoExtractor):
6773 IE_DESC = 'YouTube livestream embeds'
6774 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6775 _TESTS = [{
6776 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6777 'only_matching': True,
6778 }]
6779
6780 def _real_extract(self, url):
6781 channel_id = self._match_id(url)
6782 return self.url_result(
6783 f'https://www.youtube.com/channel/{channel_id}/live',
6784 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6785
6786
8bdd16b4 6787class YoutubeYtUserIE(InfoExtractor):
96565c7e 6788 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 6789 IE_NAME = 'youtube:user'
8bdd16b4 6790 _VALID_URL = r'ytuser:(?P<id>.+)'
6791 _TESTS = [{
6792 'url': 'ytuser:phihag',
6793 'only_matching': True,
6794 }]
6795
6796 def _real_extract(self, url):
6797 user_id = self._match_id(url)
08270da5 6798 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
9558dcec 6799
b05654f0 6800
3d3dddc9 6801class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 6802 IE_NAME = 'youtube:favorites'
96565c7e 6803 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 6804 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6805 _LOGIN_REQUIRED = True
6806 _TESTS = [{
6807 'url': ':ytfav',
6808 'only_matching': True,
6809 }, {
6810 'url': ':ytfavorites',
6811 'only_matching': True,
6812 }]
6813
6814 def _real_extract(self, url):
6815 return self.url_result(
6816 'https://www.youtube.com/playlist?list=LL',
6817 ie=YoutubeTabIE.ie_key())
6818
6819
ca5300c7 6820class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6821 IE_NAME = 'youtube:notif'
6822 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6823 _VALID_URL = r':ytnotif(?:ication)?s?'
6824 _LOGIN_REQUIRED = True
6825 _TESTS = [{
6826 'url': ':ytnotif',
6827 'only_matching': True,
6828 }, {
6829 'url': ':ytnotifications',
6830 'only_matching': True,
6831 }]
6832
6833 def _extract_notification_menu(self, response, continuation_list):
6834 notification_list = traverse_obj(
6835 response,
6836 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6837 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6838 expected_type=list) or []
6839 continuation_list[0] = None
6840 for item in notification_list:
6841 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6842 if entry:
6843 yield entry
6844 continuation = item.get('continuationItemRenderer')
6845 if continuation:
6846 continuation_list[0] = continuation
6847
6848 def _extract_notification_renderer(self, notification):
6849 video_id = traverse_obj(
6850 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6851 url = f'https://www.youtube.com/watch?v={video_id}'
6852 channel_id = None
6853 if not video_id:
6854 browse_ep = traverse_obj(
6855 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
7666b936 6856 channel_id = self.ucid_or_none(traverse_obj(browse_ep, 'browseId', expected_type=str))
ca5300c7 6857 post_id = self._search_regex(
6858 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6859 'post id', default=None)
6860 if not channel_id or not post_id:
6861 return
6862 # The direct /post url redirects to this in the browser
6863 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6864
6865 channel = traverse_obj(
6866 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6867 expected_type=str)
c7a7baaa 6868 notification_title = self._get_text(notification, 'shortMessage')
6869 if notification_title:
6870 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6871 # TODO: handle recommended videos
ca5300c7 6872 title = self._search_regex(
c7a7baaa 6873 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 6874 'video title', default=None)
5225df50 6875 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6876 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6877 else None)
ca5300c7 6878 return {
6879 '_type': 'url',
6880 'url': url,
6881 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6882 'video_id': video_id,
6883 'title': title,
6884 'channel_id': channel_id,
6885 'channel': channel,
7666b936 6886 'uploader': channel,
ca5300c7 6887 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5225df50 6888 'timestamp': timestamp,
ca5300c7 6889 }
6890
6891 def _notification_menu_entries(self, ytcfg):
6892 continuation_list = [None]
6893 response = None
6894 for page in itertools.count(1):
6895 ctoken = traverse_obj(
6896 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6897 response = self._extract_response(
6898 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6899 ep='notification/get_notification_menu', check_get_keys='actions',
6900 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6901 yield from self._extract_notification_menu(response, continuation_list)
6902 if not continuation_list[0]:
6903 break
6904
6905 def _real_extract(self, url):
6906 display_id = 'notifications'
6907 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6908 self._report_playlist_authcheck(ytcfg)
6909 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6910
6911
a6213a49 6912class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6913 IE_DESC = 'YouTube search'
78caa52a 6914 IE_NAME = 'youtube:search'
b05654f0 6915 _SEARCH_KEY = 'ytsearch'
a61fd4cf 6916 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 6917 _TESTS = [{
6918 'url': 'ytsearch5:youtube-dl test video',
6919 'playlist_count': 5,
6920 'info_dict': {
6921 'id': 'youtube-dl test video',
6922 'title': 'youtube-dl test video',
6923 }
6924 }]
b05654f0 6925
a61fd4cf 6926
5f7cb91a 6927class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 6928 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 6929 _SEARCH_KEY = 'ytsearchdate'
a6213a49 6930 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 6931 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 6932 _TESTS = [{
6933 'url': 'ytsearchdate5:youtube-dl test video',
6934 'playlist_count': 5,
6935 'info_dict': {
6936 'id': 'youtube-dl test video',
6937 'title': 'youtube-dl test video',
6938 }
6939 }]
75dff0ee 6940
c9ae7b95 6941
a6213a49 6942class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 6943 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 6944 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 6945 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 6946 _TESTS = [{
6947 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6948 'playlist_mincount': 5,
6949 'info_dict': {
11f9be09 6950 'id': 'youtube-dl test video',
3462ffa8 6951 'title': 'youtube-dl test video',
6952 }
a61fd4cf 6953 }, {
6954 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6955 'playlist_mincount': 5,
6956 'info_dict': {
6957 'id': 'python',
6958 'title': 'python',
6959 }
ad210f4f 6960 }, {
6961 'url': 'https://www.youtube.com/results?search_query=%23cats',
6962 'playlist_mincount': 1,
6963 'info_dict': {
6964 'id': '#cats',
6965 'title': '#cats',
12a1b225
A
6966 # The test suite does not have support for nested playlists
6967 # 'entries': [{
6968 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6969 # 'title': '#cats',
6970 # }],
ad210f4f 6971 },
c7335551
M
6972 }, {
6973 # Channel results
6974 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
6975 'info_dict': {
6976 'id': 'kurzgesagt',
6977 'title': 'kurzgesagt',
6978 },
6979 'playlist': [{
6980 'info_dict': {
6981 '_type': 'url',
6982 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6983 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6984 'ie_key': 'YoutubeTab',
6985 'channel': 'Kurzgesagt – In a Nutshell',
6986 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
6987 'title': 'Kurzgesagt – In a Nutshell',
6988 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
14a14335 6989 # No longer available for search as it is set to the handle.
6990 # 'playlist_count': int,
c7335551 6991 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
7666b936 6992 'thumbnails': list,
6993 'uploader_id': '@kurzgesagt',
6994 'uploader_url': 'https://www.youtube.com/@kurzgesagt',
6995 'uploader': 'Kurzgesagt – In a Nutshell',
8213ce28 6996 'channel_is_verified': True,
14a14335 6997 'channel_follower_count': int,
c7335551
M
6998 }
6999 }],
7000 'params': {'extract_flat': True, 'playlist_items': '1'},
7001 'playlist_mincount': 1,
3462ffa8 7002 }, {
7003 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
7004 'only_matching': True,
7005 }]
7006
7007 def _real_extract(self, url):
4dfbf869 7008 qs = parse_qs(url)
386e1dd9 7009 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 7010 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 7011
7012
16aa9ea4 7013class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 7014 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 7015 IE_NAME = 'youtube:music:search_url'
7016 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
7017 _TESTS = [{
7018 'url': 'https://music.youtube.com/search?q=royalty+free+music',
7019 'playlist_count': 16,
7020 'info_dict': {
7021 'id': 'royalty free music',
7022 'title': 'royalty free music',
7023 }
7024 }, {
7025 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
7026 'playlist_mincount': 30,
7027 'info_dict': {
7028 'id': 'royalty free music - songs',
7029 'title': 'royalty free music - songs',
7030 },
7031 'params': {'extract_flat': 'in_playlist'}
7032 }, {
7033 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
7034 'playlist_mincount': 30,
7035 'info_dict': {
7036 'id': 'royalty free music - community playlists',
7037 'title': 'royalty free music - community playlists',
7038 },
7039 'params': {'extract_flat': 'in_playlist'}
7040 }]
7041
7042 _SECTIONS = {
7043 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
7044 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
7045 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
7046 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
7047 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
7048 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
7049 }
7050
7051 def _real_extract(self, url):
7052 qs = parse_qs(url)
7053 query = (qs.get('search_query') or qs.get('q'))[0]
7054 params = qs.get('sp', (None,))[0]
7055 if params:
7056 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
7057 else:
ac668111 7058 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 7059 params = self._SECTIONS.get(section)
7060 if not params:
7061 section = None
7062 title = join_nonempty(query, section, delim=' - ')
af5c1c55 7063 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 7064
7065
182bda88 7066class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 7067 """
25f14e9f 7068 Base class for feed extractors
82d02080 7069 Subclasses must re-define the _FEED_NAME property.
d7ae0639 7070 """
b2e8bc1b 7071 _LOGIN_REQUIRED = True
82d02080 7072 _FEED_NAME = 'feeds'
a25bca9f 7073
7074 def _real_initialize(self):
7075 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 7076
82d02080 7077 @classproperty
d7ae0639 7078 def IE_NAME(self):
82d02080 7079 return f'youtube:{self._FEED_NAME}'
04cc9617 7080
3853309f 7081 def _real_extract(self, url):
3d3dddc9 7082 return self.url_result(
182bda88 7083 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
7084
7085
ef2f3c7f 7086class YoutubeWatchLaterIE(InfoExtractor):
7087 IE_NAME = 'youtube:watchlater'
96565c7e 7088 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 7089 _VALID_URL = r':ytwatchlater'
bc7a9cd8 7090 _TESTS = [{
8bdd16b4 7091 'url': ':ytwatchlater',
bc7a9cd8
S
7092 'only_matching': True,
7093 }]
25f14e9f
S
7094
7095 def _real_extract(self, url):
ef2f3c7f 7096 return self.url_result(
7097 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 7098
7099
25f14e9f 7100class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 7101 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 7102 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 7103 _FEED_NAME = 'recommended'
45db527f 7104 _LOGIN_REQUIRED = False
3d3dddc9 7105 _TESTS = [{
7106 'url': ':ytrec',
7107 'only_matching': True,
7108 }, {
7109 'url': ':ytrecommended',
7110 'only_matching': True,
7111 }, {
7112 'url': 'https://youtube.com',
7113 'only_matching': True,
7114 }]
1ed5b5c9 7115
1ed5b5c9 7116
25f14e9f 7117class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 7118 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 7119 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 7120 _FEED_NAME = 'subscriptions'
3d3dddc9 7121 _TESTS = [{
7122 'url': ':ytsubs',
7123 'only_matching': True,
7124 }, {
7125 'url': ':ytsubscriptions',
7126 'only_matching': True,
7127 }]
1ed5b5c9 7128
1ed5b5c9 7129
25f14e9f 7130class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 7131 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 7132 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 7133 _FEED_NAME = 'history'
3d3dddc9 7134 _TESTS = [{
7135 'url': ':ythistory',
7136 'only_matching': True,
7137 }]
1ed5b5c9
JMF
7138
7139
6e634cbe 7140class YoutubeStoriesIE(InfoExtractor):
7141 IE_DESC = 'YouTube channel stories; "ytstories:" prefix'
7142 IE_NAME = 'youtube:stories'
7143 _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
7144 _TESTS = [{
7145 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
7146 'only_matching': True,
7147 }]
7148
7149 def _real_extract(self, url):
7150 playlist_id = f'RLTD{self._match_id(url)}'
7151 return self.url_result(
50ac0e54 7152 smuggle_url(f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}),
6e634cbe 7153 ie=YoutubeTabIE, video_id=playlist_id)
7154
7155
80eb0bd9 7156class YoutubeShortsAudioPivotIE(InfoExtractor):
1dd18a88 7157 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
80eb0bd9 7158 IE_NAME = 'youtube:shorts:pivot:audio'
1dd18a88 7159 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
80eb0bd9 7160 _TESTS = [{
1dd18a88 7161 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
80eb0bd9 7162 'only_matching': True,
7163 }]
7164
7165 @staticmethod
7166 def _generate_audio_pivot_params(video_id):
7167 """
7168 Generates sfv_audio_pivot browse params for this video id
7169 """
7170 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
7171 return urllib.parse.quote(base64.b64encode(pb_params).decode())
7172
7173 def _real_extract(self, url):
7174 video_id = self._match_id(url)
7175 return self.url_result(
7176 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
7177 ie=YoutubeTabIE)
7178
7179
15870e90
PH
7180class YoutubeTruncatedURLIE(InfoExtractor):
7181 IE_NAME = 'youtube:truncated_url'
7182 IE_DESC = False # Do not list
975d35db 7183 _VALID_URL = r'''(?x)
b95aab84
PH
7184 (?:https?://)?
7185 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
7186 (?:watch\?(?:
c4808c60 7187 feature=[a-z_]+|
b95aab84
PH
7188 annotation_id=annotation_[^&]+|
7189 x-yt-cl=[0-9]+|
c1708b89 7190 hl=[^&]*|
287be8c6 7191 t=[0-9]+
b95aab84
PH
7192 )?
7193 |
7194 attribution_link\?a=[^&]+
7195 )
7196 $
975d35db 7197 '''
15870e90 7198
c4808c60 7199 _TESTS = [{
2d3d2997 7200 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 7201 'only_matching': True,
dc2fc736 7202 }, {
2d3d2997 7203 'url': 'https://www.youtube.com/watch?',
dc2fc736 7204 'only_matching': True,
b95aab84
PH
7205 }, {
7206 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
7207 'only_matching': True,
7208 }, {
7209 'url': 'https://www.youtube.com/watch?feature=foo',
7210 'only_matching': True,
c1708b89
PH
7211 }, {
7212 'url': 'https://www.youtube.com/watch?hl=en-GB',
7213 'only_matching': True,
287be8c6
PH
7214 }, {
7215 'url': 'https://www.youtube.com/watch?t=2372',
7216 'only_matching': True,
c4808c60
PH
7217 }]
7218
15870e90
PH
7219 def _real_extract(self, url):
7220 raise ExtractorError(
78caa52a
PH
7221 'Did you forget to quote the URL? Remember that & is a meta '
7222 'character in most shells, so you want to put the URL in quotes, '
3867038a 7223 'like youtube-dl '
2d3d2997 7224 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 7225 ' or simply youtube-dl BaW_jenozKc .',
15870e90 7226 expected=True)
772fd5cc
PH
7227
7228
471d0367 7229class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 7230 IE_NAME = 'youtube:clip'
471d0367 7231 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
7232 _TESTS = [{
7233 # FIXME: Other metadata should be extracted from the clip, not from the base video
7234 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
7235 'info_dict': {
7236 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
7237 'ext': 'mp4',
7238 'section_start': 29.0,
7239 'section_end': 39.7,
7240 'duration': 10.7,
12a1b225
A
7241 'age_limit': 0,
7242 'availability': 'public',
7243 'categories': ['Gaming'],
7244 'channel': 'Scott The Woz',
7245 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
7246 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
7247 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
7248 'like_count': int,
7249 'playable_in_embed': True,
7250 'tags': 'count:17',
7251 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
7252 'title': 'Mobile Games on Console - Scott The Woz',
7253 'upload_date': '20210920',
7254 'uploader': 'Scott The Woz',
7666b936 7255 'uploader_id': '@ScottTheWoz',
7256 'uploader_url': 'https://www.youtube.com/@ScottTheWoz',
12a1b225
A
7257 'view_count': int,
7258 'live_status': 'not_live',
7666b936 7259 'channel_follower_count': int,
7260 'chapters': 'count:20',
14a14335 7261 'comment_count': int,
7262 'heatmap': 'count:100',
471d0367 7263 }
7264 }]
3cd786db 7265
7266 def _real_extract(self, url):
471d0367 7267 clip_id = self._match_id(url)
7268 _, data = self._extract_webpage(url, clip_id)
7269
7270 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
7271 if not video_id:
7272 raise ExtractorError('Unable to find video ID')
7273
7274 clip_data = traverse_obj(data, (
7275 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
7276 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
7277 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
7278 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
7279
7280 return {
7281 '_type': 'url_transparent',
7282 'url': f'https://www.youtube.com/watch?v={video_id}',
7283 'ie_key': YoutubeIE.ie_key(),
7284 'id': clip_id,
7285 'section_start': int(clip_data['startTimeMs']) / 1000,
7286 'section_end': int(clip_data['endTimeMs']) / 1000,
7287 }
3cd786db 7288
7289
b032ff0f 7290class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
7291 IE_NAME = 'youtube:consent'
7292 IE_DESC = False # Do not list
7293 _VALID_URL = r'https?://consent\.youtube\.com/m\?'
7294 _TESTS = [{
7295 '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',
7296 'info_dict': {
7297 'id': 'qVv6vCqciTM',
7298 'ext': 'mp4',
7299 'age_limit': 0,
7666b936 7300 'uploader_id': '@sana_natori',
b032ff0f 7301 'comment_count': int,
7302 'chapters': 'count:13',
7303 'upload_date': '20221223',
7304 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
7305 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7666b936 7306 'uploader_url': 'https://www.youtube.com/@sana_natori',
b032ff0f 7307 'like_count': int,
7308 'release_date': '20221223',
7309 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
7310 '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】',
7311 'view_count': int,
7312 'playable_in_embed': True,
7313 'duration': 4438,
7314 'availability': 'public',
7315 'channel_follower_count': int,
7316 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7317 'categories': ['Entertainment'],
7318 'live_status': 'was_live',
7319 'release_timestamp': 1671793345,
7320 'channel': 'さなちゃんねる',
7321 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
7322 'uploader': 'さなちゃんねる',
8213ce28 7323 'channel_is_verified': True,
14a14335 7324 'heatmap': 'count:100',
b032ff0f 7325 },
7326 'add_ie': ['Youtube'],
7327 'params': {'skip_download': 'Youtube'},
7328 }]
7329
7330 def _real_extract(self, url):
7331 redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
7332 if not redirect_url:
7333 raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
7334 return self.url_result(redirect_url)
7335
7336
772fd5cc
PH
7337class YoutubeTruncatedIDIE(InfoExtractor):
7338 IE_NAME = 'youtube:truncated_id'
7339 IE_DESC = False # Do not list
b95aab84 7340 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
7341
7342 _TESTS = [{
7343 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7344 'only_matching': True,
7345 }]
7346
7347 def _real_extract(self, url):
7348 video_id = self._match_id(url)
7349 raise ExtractorError(
86e5f3ed 7350 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 7351 expected=True)