]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[ie/CloudflareStream] Improve embed detection (#9287)
[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
ac668111 18import urllib.parse
c5e8d7af 19
b05654f0 20from .common import InfoExtractor, SearchInfoExtractor
25836db6 21from .openload import PhantomJSwrapper
14f25df2 22from ..compat import functools
545cc85d 23from ..jsinterp import JSInterpreter
3d2623a8 24from ..networking.exceptions import HTTPError, network_exceptions
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,
11f9be09 44 orderedSet,
6310acf5 45 parse_codecs,
49bd8c66 46 parse_count,
7c80519c 47 parse_duration,
7ea65411 48 parse_iso8601,
4dfbf869 49 parse_qs,
dca3ff4a 50 qualities,
3995d37d 51 remove_start,
cf7e015f 52 smuggle_url,
dbdaaa23 53 str_or_none,
c93d53f5 54 str_to_int,
f3aa3c3f 55 strftime_or_none,
7c365c21 56 traverse_obj,
556dbe7f 57 try_get,
c5e8d7af
PH
58 unescapeHTML,
59 unified_strdate,
f0d785d3 60 unified_timestamp,
cf7e015f 61 unsmuggle_url,
8bdd16b4 62 update_url_query,
21c340b8 63 url_or_none,
fe93e2c4 64 urljoin,
7c365c21 65 variadic,
c5e8d7af
PH
66)
67
c795c39f 68STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client'
962ffcf8 69# any clients starting with _ cannot be explicitly requested by the user
000c15a4 70INNERTUBE_CLIENTS = {
71 'web': {
72 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
73 'INNERTUBE_CONTEXT': {
74 'client': {
75 'clientName': 'WEB',
a0c830f4 76 'clientVersion': '2.20220801.00.00',
000c15a4 77 }
78 },
79 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
80 },
81 'web_embedded': {
82 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
83 'INNERTUBE_CONTEXT': {
84 'client': {
85 'clientName': 'WEB_EMBEDDED_PLAYER',
a0c830f4 86 'clientVersion': '1.20220731.00.00',
000c15a4 87 },
88 },
89 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
90 },
91 'web_music': {
92 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
93 'INNERTUBE_HOST': 'music.youtube.com',
94 'INNERTUBE_CONTEXT': {
95 'client': {
96 'clientName': 'WEB_REMIX',
a0c830f4 97 'clientVersion': '1.20220727.01.00',
000c15a4 98 }
99 },
100 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
101 },
e7e94f2a 102 'web_creator': {
18c7683d 103 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
e7e94f2a
D
104 'INNERTUBE_CONTEXT': {
105 'client': {
106 'clientName': 'WEB_CREATOR',
a0c830f4 107 'clientVersion': '1.20220726.00.00',
e7e94f2a
D
108 }
109 },
110 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
111 },
000c15a4 112 'android': {
18c7683d 113 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
000c15a4 114 'INNERTUBE_CONTEXT': {
115 'client': {
116 'clientName': 'ANDROID',
50ac0e54 117 'clientVersion': '17.31.35',
118 'androidSdkVersion': 30,
119 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
000c15a4 120 }
121 },
122 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
b6de707d 123 'REQUIRE_JS_PLAYER': False
000c15a4 124 },
125 'android_embedded': {
18c7683d 126 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
000c15a4 127 'INNERTUBE_CONTEXT': {
128 'client': {
129 'clientName': 'ANDROID_EMBEDDED_PLAYER',
50ac0e54 130 'clientVersion': '17.31.35',
131 'androidSdkVersion': 30,
132 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
000c15a4 133 },
134 },
b6de707d 135 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
136 'REQUIRE_JS_PLAYER': False
000c15a4 137 },
138 'android_music': {
18c7683d 139 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
000c15a4 140 'INNERTUBE_CONTEXT': {
141 'client': {
142 'clientName': 'ANDROID_MUSIC',
a0c830f4 143 'clientVersion': '5.16.51',
50ac0e54 144 'androidSdkVersion': 30,
145 'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
000c15a4 146 }
147 },
148 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
b6de707d 149 'REQUIRE_JS_PLAYER': False
000c15a4 150 },
e7e94f2a 151 'android_creator': {
18c7683d 152 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
e7e94f2a
D
153 'INNERTUBE_CONTEXT': {
154 'client': {
155 'clientName': 'ANDROID_CREATOR',
50ac0e54 156 'clientVersion': '22.30.100',
157 'androidSdkVersion': 30,
158 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
e7e94f2a
D
159 },
160 },
b6de707d 161 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
162 'REQUIRE_JS_PLAYER': False
e7e94f2a 163 },
18c7683d 164 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
165 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
000c15a4 166 'ios': {
18c7683d 167 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
000c15a4 168 'INNERTUBE_CONTEXT': {
169 'client': {
170 'clientName': 'IOS',
224b5a35 171 'clientVersion': '17.33.2',
18c7683d 172 'deviceModel': 'iPhone14,3',
224b5a35 173 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 174 }
175 },
b6de707d 176 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
177 'REQUIRE_JS_PLAYER': False
000c15a4 178 },
179 'ios_embedded': {
000c15a4 180 'INNERTUBE_CONTEXT': {
181 'client': {
182 'clientName': 'IOS_MESSAGES_EXTENSION',
224b5a35 183 'clientVersion': '17.33.2',
18c7683d 184 'deviceModel': 'iPhone14,3',
224b5a35 185 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 186 },
187 },
b6de707d 188 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
189 'REQUIRE_JS_PLAYER': False
000c15a4 190 },
191 'ios_music': {
18c7683d 192 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
000c15a4 193 'INNERTUBE_CONTEXT': {
194 'client': {
195 'clientName': 'IOS_MUSIC',
224b5a35
SF
196 'clientVersion': '5.21',
197 'deviceModel': 'iPhone14,3',
198 'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
000c15a4 199 },
200 },
b6de707d 201 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
202 'REQUIRE_JS_PLAYER': False
000c15a4 203 },
e7e94f2a
D
204 'ios_creator': {
205 'INNERTUBE_CONTEXT': {
206 'client': {
207 'clientName': 'IOS_CREATOR',
224b5a35
SF
208 'clientVersion': '22.33.101',
209 'deviceModel': 'iPhone14,3',
210 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
e7e94f2a
D
211 },
212 },
b6de707d 213 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
214 'REQUIRE_JS_PLAYER': False
e7e94f2a 215 },
3619f78d 216 # mweb has 'ultralow' formats
217 # See: https://github.com/yt-dlp/yt-dlp/pull/557
000c15a4 218 'mweb': {
18c7683d 219 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
000c15a4 220 'INNERTUBE_CONTEXT': {
221 'client': {
222 'clientName': 'MWEB',
a0c830f4 223 'clientVersion': '2.20220801.00.00',
000c15a4 224 }
225 },
226 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
e7870111
D
227 },
228 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
229 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
230 'tv_embedded': {
231 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
232 'INNERTUBE_CONTEXT': {
233 'client': {
234 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
235 'clientVersion': '2.0',
236 },
237 },
238 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
239 },
000c15a4 240}
241
242
e7870111
D
243def _split_innertube_client(client_name):
244 variant, *base = client_name.rsplit('.', 1)
245 if base:
246 return variant, base[0], variant
247 base, *variant = client_name.split('_', 1)
248 return client_name, base, variant[0] if variant else None
249
250
c795c39f
L
251def short_client_name(client_name):
252 main, *parts = _split_innertube_client(client_name)[0].replace('embedscreen', 'e_s').split('_')
253 return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper()
254
255
000c15a4 256def build_innertube_clients():
2e4cacd0 257 THIRD_PARTY = {
e7870111 258 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
65c2fde2 259 }
1e75d97d 260 BASE_CLIENTS = ('ios', 'android', 'web', 'tv', 'mweb')
2e4cacd0 261 priority = qualities(BASE_CLIENTS[::-1])
000c15a4 262
263 for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()):
eca330cb 264 ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
000c15a4 265 ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com')
b6de707d 266 ytcfg.setdefault('REQUIRE_JS_PLAYER', True)
000c15a4 267 ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
000c15a4 268
e7870111 269 _, base_client, variant = _split_innertube_client(client)
2e4cacd0 270 ytcfg['priority'] = 10 * priority(base_client)
271
e48b3875 272 if not variant:
e7870111
D
273 INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg)
274 embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
275 embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
276 embedscreen['priority'] -= 3
277 elif variant == 'embedded':
e48b3875 278 ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
000c15a4 279 ytcfg['priority'] -= 2
e48b3875 280 else:
000c15a4 281 ytcfg['priority'] -= 3
282
283
284build_innertube_clients()
285
286
c26f9b99 287class BadgeType(enum.Enum):
288 AVAILABILITY_UNLISTED = enum.auto()
289 AVAILABILITY_PRIVATE = enum.auto()
290 AVAILABILITY_PUBLIC = enum.auto()
291 AVAILABILITY_PREMIUM = enum.auto()
292 AVAILABILITY_SUBSCRIPTION = enum.auto()
293 LIVE_NOW = enum.auto()
14a14335 294 VERIFIED = enum.auto()
c26f9b99 295
296
de7f3446 297class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b 298 """Provide base functions for Youtube extractors"""
e00eb564 299
3462ffa8 300 _RESERVED_NAMES = (
08e29b9f 301 r'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|'
182bda88 302 r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
1dd18a88 303 r'browse|oembed|get_video_info|iframe_api|s/player|source|'
0a5095fe 304 r'storefront|oops|index|account|t/terms|about|upload|signin|logout')
3462ffa8 305
3619f78d 306 _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
307
52efa4b3 308 # _NETRC_MACHINE = 'youtube'
3619f78d 309
b2e8bc1b
JMF
310 # If True it will raise an error if no login info is provided
311 _LOGIN_REQUIRED = False
312
d9190e44
RH
313 _INVIDIOUS_SITES = (
314 # invidious-redirect websites
315 r'(?:www\.)?redirect\.invidious\.io',
316 r'(?:(?:www|dev)\.)?invidio\.us',
0a41f331 317 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
d9190e44
RH
318 r'(?:www\.)?invidious\.pussthecat\.org',
319 r'(?:www\.)?invidious\.zee\.li',
320 r'(?:www\.)?invidious\.ethibox\.fr',
05799a48
RH
321 r'(?:www\.)?iv\.ggtyler\.dev',
322 r'(?:www\.)?inv\.vern\.i2p',
323 r'(?:www\.)?am74vkcrjp2d5v36lcdqgsj2m6x36tbrkhsruoegwfcizzabnfgf5zyd\.onion',
324 r'(?:www\.)?inv\.riverside\.rocks',
325 r'(?:www\.)?invidious\.silur\.me',
326 r'(?:www\.)?inv\.bp\.projectsegfau\.lt',
327 r'(?:www\.)?invidious\.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid\.onion',
328 r'(?:www\.)?invidious\.slipfox\.xyz',
329 r'(?:www\.)?invidious\.esmail5pdn24shtvieloeedh7ehz3nrwcdivnfhfcedl7gf4kwddhkqd\.onion',
330 r'(?:www\.)?inv\.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad\.onion',
331 r'(?:www\.)?invidious\.tiekoetter\.com',
332 r'(?:www\.)?iv\.odysfvr23q5wgt7i456o5t3trw2cw5dgn56vbjfbq2m7xsc5vqbqpcyd\.onion',
333 r'(?:www\.)?invidious\.nerdvpn\.de',
334 r'(?:www\.)?invidious\.weblibre\.org',
335 r'(?:www\.)?inv\.odyssey346\.dev',
336 r'(?:www\.)?invidious\.dhusch\.de',
337 r'(?:www\.)?iv\.melmac\.space',
338 r'(?:www\.)?watch\.thekitty\.zone',
339 r'(?:www\.)?invidious\.privacydev\.net',
340 r'(?:www\.)?ng27owmagn5amdm7l5s3rsqxwscl5ynppnis5dqcasogkyxcfqn7psid\.onion',
341 r'(?:www\.)?invidious\.drivet\.xyz',
342 r'(?:www\.)?vid\.priv\.au',
343 r'(?:www\.)?euxxcnhsynwmfidvhjf6uzptsmh4dipkmgdmcmxxuo7tunp3ad2jrwyd\.onion',
344 r'(?:www\.)?inv\.vern\.cc',
345 r'(?:www\.)?invidious\.esmailelbob\.xyz',
346 r'(?:www\.)?invidious\.sethforprivacy\.com',
347 r'(?:www\.)?yt\.oelrichsgarcia\.de',
348 r'(?:www\.)?yt\.artemislena\.eu',
349 r'(?:www\.)?invidious\.flokinet\.to',
350 r'(?:www\.)?invidious\.baczek\.me',
351 r'(?:www\.)?y\.com\.sb',
352 r'(?:www\.)?invidious\.epicsite\.xyz',
353 r'(?:www\.)?invidious\.lidarshield\.cloud',
354 r'(?:www\.)?yt\.funami\.tech',
d9190e44 355 r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
4c968755
U
356 r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
357 r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
d9190e44
RH
358 # youtube-dl invidious instances list
359 r'(?:(?:www|no)\.)?invidiou\.sh',
360 r'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
361 r'(?:www\.)?invidious\.kabi\.tk',
362 r'(?:www\.)?invidious\.mastodon\.host',
363 r'(?:www\.)?invidious\.zapashcanon\.fr',
364 r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
365 r'(?:www\.)?invidious\.tinfoil-hat\.net',
366 r'(?:www\.)?invidious\.himiko\.cloud',
367 r'(?:www\.)?invidious\.reallyancient\.tech',
368 r'(?:www\.)?invidious\.tube',
369 r'(?:www\.)?invidiou\.site',
370 r'(?:www\.)?invidious\.site',
371 r'(?:www\.)?invidious\.xyz',
372 r'(?:www\.)?invidious\.nixnet\.xyz',
373 r'(?:www\.)?invidious\.048596\.xyz',
374 r'(?:www\.)?invidious\.drycat\.fr',
375 r'(?:www\.)?inv\.skyn3t\.in',
376 r'(?:www\.)?tube\.poal\.co',
377 r'(?:www\.)?tube\.connect\.cafe',
378 r'(?:www\.)?vid\.wxzm\.sx',
379 r'(?:www\.)?vid\.mint\.lgbt',
380 r'(?:www\.)?vid\.puffyan\.us',
381 r'(?:www\.)?yewtu\.be',
382 r'(?:www\.)?yt\.elukerio\.org',
383 r'(?:www\.)?yt\.lelux\.fi',
384 r'(?:www\.)?invidious\.ggc-project\.de',
385 r'(?:www\.)?yt\.maisputain\.ovh',
386 r'(?:www\.)?ytprivate\.com',
387 r'(?:www\.)?invidious\.13ad\.de',
388 r'(?:www\.)?invidious\.toot\.koeln',
389 r'(?:www\.)?invidious\.fdn\.fr',
390 r'(?:www\.)?watch\.nettohikari\.com',
391 r'(?:www\.)?invidious\.namazso\.eu',
392 r'(?:www\.)?invidious\.silkky\.cloud',
393 r'(?:www\.)?invidious\.exonip\.de',
394 r'(?:www\.)?invidious\.riverside\.rocks',
395 r'(?:www\.)?invidious\.blamefran\.net',
396 r'(?:www\.)?invidious\.moomoo\.de',
397 r'(?:www\.)?ytb\.trom\.tf',
398 r'(?:www\.)?yt\.cyberhost\.uk',
399 r'(?:www\.)?kgg2m7yk5aybusll\.onion',
400 r'(?:www\.)?qklhadlycap4cnod\.onion',
401 r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
402 r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
403 r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
404 r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
405 r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
406 r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
407 r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
408 r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
409 r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
410 r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
d1c4f6d4
JW
411 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
412 r'(?:www\.)?piped\.kavin\.rocks',
d1c4f6d4 413 r'(?:www\.)?piped\.tokhmi\.xyz',
e14ea7fb 414 r'(?:www\.)?piped\.syncpundit\.io',
d1c4f6d4 415 r'(?:www\.)?piped\.mha\.fi',
e14ea7fb
BG
416 r'(?:www\.)?watch\.whatever\.social',
417 r'(?:www\.)?piped\.garudalinux\.org',
418 r'(?:www\.)?piped\.rivo\.lol',
419 r'(?:www\.)?piped-libre\.kavin\.rocks',
420 r'(?:www\.)?yt\.jae\.fi',
d1c4f6d4 421 r'(?:www\.)?piped\.mint\.lgbt',
e14ea7fb
BG
422 r'(?:www\.)?il\.ax',
423 r'(?:www\.)?piped\.esmailelbob\.xyz',
424 r'(?:www\.)?piped\.projectsegfau\.lt',
425 r'(?:www\.)?piped\.privacydev\.net',
426 r'(?:www\.)?piped\.palveluntarjoaja\.eu',
427 r'(?:www\.)?piped\.smnz\.de',
428 r'(?:www\.)?piped\.adminforge\.de',
429 r'(?:www\.)?watch\.whatevertinfoil\.de',
430 r'(?:www\.)?piped\.qdi\.fi',
6a9c7a2b 431 r'(?:(?:www|cf)\.)?piped\.video',
bc87dac7 432 r'(?:www\.)?piped\.aeong\.one',
05799a48
RH
433 r'(?:www\.)?piped\.moomoo\.me',
434 r'(?:www\.)?piped\.chauvet\.pro',
435 r'(?:www\.)?watch\.leptons\.xyz',
436 r'(?:www\.)?pd\.vern\.cc',
437 r'(?:www\.)?piped\.hostux\.net',
438 r'(?:www\.)?piped\.lunar\.icu',
78a78fa7
BG
439 # Hyperpipe instances from https://hyperpipe.codeberg.page/
440 r'(?:www\.)?hyperpipe\.surge\.sh',
441 r'(?:www\.)?hyperpipe\.esmailelbob\.xyz',
442 r'(?:www\.)?listen\.whatever\.social',
443 r'(?:www\.)?music\.adminforge\.de',
d9190e44
RH
444 )
445
c26f9b99 446 # extracted from account/account_menu ep
447 # XXX: These are the supported YouTube UI and API languages,
448 # which is slightly different from languages supported for translation in YouTube studio
449 _SUPPORTED_LANG_CODES = [
450 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es',
451 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv',
452 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi',
453 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw',
454 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml',
455 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko'
456 ]
457
a057779d 458 _IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'}
459
7666b936 460 _YT_HANDLE_RE = r'@[\w.-]{3,30}' # https://support.google.com/youtube/answer/11585688?hl=en
461 _YT_CHANNEL_UCID_RE = r'UC[\w-]{22}'
462
463 def ucid_or_none(self, ucid):
464 return self._search_regex(rf'^({self._YT_CHANNEL_UCID_RE})$', ucid, 'UC-id', default=None)
465
466 def handle_or_none(self, handle):
467 return self._search_regex(rf'^({self._YT_HANDLE_RE})$', handle, '@-handle', default=None)
468
469 def handle_from_url(self, url):
470 return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_HANDLE_RE})',
471 url, 'channel handle', default=None)
472
473 def ucid_from_url(self, url):
474 return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_CHANNEL_UCID_RE})',
475 url, 'channel id', default=None)
476
c26f9b99 477 @functools.cached_property
478 def _preferred_lang(self):
479 """
480 Returns a language code supported by YouTube for the user preferred language.
481 Returns None if no preferred language set.
482 """
483 preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0]
484 if not preferred_lang:
485 return
486 if preferred_lang not in self._SUPPORTED_LANG_CODES:
487 raise ExtractorError(
488 f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.',
489 expected=True)
490 elif preferred_lang != 'en':
491 self.report_warning(
492 f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.')
493 return preferred_lang
494
cce889b9 495 def _initialize_consent(self):
496 cookies = self._get_cookies('https://www.youtube.com/')
497 if cookies.get('__Secure-3PSID'):
498 return
378ae9f9 499 socs = cookies.get('SOCS')
500 if socs and not socs.value.startswith('CAA'): # not consented
501 return
502 self._set_cookie('.youtube.com', 'SOCS', 'CAI', secure=True) # accept all (required for mixes)
8d81f3e3 503
f3aa3c3f 504 def _initialize_pref(self):
505 cookies = self._get_cookies('https://www.youtube.com/')
506 pref_cookie = cookies.get('PREF')
507 pref = {}
508 if pref_cookie:
509 try:
14f25df2 510 pref = dict(urllib.parse.parse_qsl(pref_cookie.value))
f3aa3c3f 511 except ValueError:
512 self.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
c26f9b99 513 pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'})
14f25df2 514 self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref))
f3aa3c3f 515
b2e8bc1b 516 def _real_initialize(self):
f3aa3c3f 517 self._initialize_pref()
cce889b9 518 self._initialize_consent()
a25bca9f 519 self._check_login_required()
520
521 def _check_login_required(self):
24146491 522 if self._LOGIN_REQUIRED and not self._cookies_passed:
52efa4b3 523 self.raise_login_required('Login details are needed to download this content', method='cookies')
c5e8d7af 524
b7c47b74 525 _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
526 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
a0566bbf 527
000c15a4 528 def _get_default_ytcfg(self, client='web'):
529 return copy.deepcopy(INNERTUBE_CLIENTS[client])
109dd3b2 530
000c15a4 531 def _get_innertube_host(self, client='web'):
532 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
109dd3b2 533
000c15a4 534 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
109dd3b2 535 # try_get but with fallback to default ytcfg client values when present
536 _func = lambda y: try_get(y, getter, expected_type)
537 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
538
000c15a4 539 def _extract_client_name(self, ytcfg, default_client='web'):
3619f78d 540 return self._ytcfg_get_safe(
541 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
14f25df2 542 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
109dd3b2 543
000c15a4 544 def _extract_client_version(self, ytcfg, default_client='web'):
3619f78d 545 return self._ytcfg_get_safe(
546 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
14f25df2 547 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
109dd3b2 548
2ae778b8 549 def _select_api_hostname(self, req_api_hostname, default_client=None):
550 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
551 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
552
000c15a4 553 def _extract_api_key(self, ytcfg=None, default_client='web'):
14f25df2 554 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
109dd3b2 555
000c15a4 556 def _extract_context(self, ytcfg=None, default_client='web'):
f3aa3c3f 557 context = get_first(
558 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
396a76f7 559 # Enforce language and tz for extraction
560 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
c26f9b99 561 client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
109dd3b2 562 return context
563
cf87314d 564 _SAPISID = None
565
109dd3b2 566 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
a5c56234 567 time_now = round(time.time())
cf87314d 568 if self._SAPISID is None:
569 yt_cookies = self._get_cookies('https://www.youtube.com')
570 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
571 # See: https://github.com/yt-dlp/yt-dlp/issues/393
572 sapisid_cookie = dict_get(
573 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
574 if sapisid_cookie and sapisid_cookie.value:
575 self._SAPISID = sapisid_cookie.value
576 self.write_debug('Extracted SAPISID cookie')
577 # SAPISID cookie is required if not already present
578 if not yt_cookies.get('SAPISID'):
579 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
580 self._set_cookie(
581 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
582 else:
583 self._SAPISID = False
584 if not self._SAPISID:
585 return None
1974e99f 586 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
587 sapisidhash = hashlib.sha1(
86e5f3ed 588 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
1974e99f 589 return f'SAPISIDHASH {time_now}_{sapisidhash}'
a5c56234
M
590
591 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
f4f751af 592 note='Downloading API JSON', errnote='Unable to download API page',
000c15a4 593 context=None, api_key=None, api_hostname=None, default_client='web'):
f4f751af 594
109dd3b2 595 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
8bdd16b4 596 data.update(query)
11f9be09 597 real_headers = self.generate_api_headers(default_client=default_client)
f4f751af 598 real_headers.update({'content-type': 'application/json'})
599 if headers:
600 real_headers.update(headers)
2ae778b8 601 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
602 or api_key or self._extract_api_key(default_client=default_client))
545cc85d 603 return self._download_json(
2ae778b8 604 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
a5c56234 605 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
f4f751af 606 data=json.dumps(data).encode('utf8'), headers=real_headers,
2ae778b8 607 query={'key': api_key, 'prettyPrint': 'false'})
f4f751af 608
65141660 609 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
610 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
1890fc63 611
99e9e001 612 @staticmethod
613 def _extract_session_index(*data):
614 """
615 Index of current account in account list.
616 See: https://github.com/yt-dlp/yt-dlp/pull/519
617 """
618 for ytcfg in data:
619 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
620 if session_index is not None:
621 return session_index
622
623 # Deprecated?
624 def _extract_identity_token(self, ytcfg=None, webpage=None):
a1c5d2ca 625 if ytcfg:
14f25df2 626 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
a1c5d2ca
M
627 if token:
628 return token
99e9e001 629 if webpage:
630 return self._search_regex(
631 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
632 'identity token', default=None, fatal=False)
a1c5d2ca
M
633
634 @staticmethod
fe93e2c4 635 def _extract_account_syncid(*args):
8ea3f7b9 636 """
637 Extract syncId required to download private playlists of secondary channels
fe93e2c4 638 @params response and/or ytcfg
8ea3f7b9 639 """
fe93e2c4 640 for data in args:
641 # ytcfg includes channel_syncid if on secondary channel
14f25df2 642 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str)
fe93e2c4 643 if delegated_sid:
644 return delegated_sid
645 sync_ids = (try_get(
646 data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'],
14f25df2 647 lambda x: x['DATASYNC_ID']), str) or '').split('||')
fe93e2c4 648 if len(sync_ids) >= 2 and sync_ids[1]:
649 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
650 # and just "user_syncid||" for primary channel. We only want the channel_syncid
651 return sync_ids[0]
a1c5d2ca 652
ac56cf38 653 @staticmethod
654 def _extract_visitor_data(*args):
655 """
656 Extracts visitorData from an API response or ytcfg
657 Appears to be used to track session state
658 """
9222c381 659 return get_first(
6c73052c 660 args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))],
9222c381 661 expected_type=str)
ac56cf38 662
2762dbb1 663 @functools.cached_property
99e9e001 664 def is_authenticated(self):
665 return bool(self._generate_sapisidhash_header())
666
11f9be09 667 def extract_ytcfg(self, video_id, webpage):
8c54a305 668 if not webpage:
669 return {}
29f7c58a 670 return self._parse_json(
671 self._search_regex(
672 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
f4f751af 673 default='{}'), video_id, fatal=False) or {}
674
11f9be09 675 def generate_api_headers(
99e9e001 676 self, *, ytcfg=None, account_syncid=None, session_index=None,
677 visitor_data=None, identity_token=None, api_hostname=None, default_client='web'):
678
2ae778b8 679 origin = 'https://' + (self._select_api_hostname(api_hostname, default_client))
f4f751af 680 headers = {
14f25df2 681 'X-YouTube-Client-Name': str(
11f9be09 682 self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)),
683 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client),
99e9e001 684 'Origin': origin,
685 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg),
686 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg),
50ac0e54 687 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg),
688 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client)
99e9e001 689 }
690 if session_index is None:
314ee305 691 session_index = self._extract_session_index(ytcfg)
692 if account_syncid or session_index is not None:
693 headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0
99e9e001 694
109dd3b2 695 auth = self._generate_sapisidhash_header(origin)
f4f751af 696 if auth is not None:
697 headers['Authorization'] = auth
109dd3b2 698 headers['X-Origin'] = origin
7a32c70d 699 return filter_dict(headers)
29f7c58a 700
a25bca9f 701 def _download_ytcfg(self, client, video_id):
702 url = {
703 'web': 'https://www.youtube.com',
704 'web_music': 'https://music.youtube.com',
705 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
706 }.get(client)
707 if not url:
708 return {}
709 webpage = self._download_webpage(
710 url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config')
711 return self.extract_ytcfg(video_id, webpage) or {}
712
2d6659b9 713 @staticmethod
714 def _build_api_continuation_query(continuation, ctp=None):
715 query = {
716 'continuation': continuation
717 }
718 # TODO: Inconsistency with clickTrackingParams.
719 # Currently we have a fixed ctp contained within context (from ytcfg)
720 # and a ctp in root query for continuation.
721 if ctp:
722 query['clickTracking'] = {'clickTrackingParams': ctp}
723 return query
724
2d6659b9 725 @classmethod
726 def _extract_next_continuation_data(cls, renderer):
727 next_continuation = try_get(
728 renderer, (lambda x: x['continuations'][0]['nextContinuationData'],
729 lambda x: x['continuation']['reloadContinuationData']), dict)
730 if not next_continuation:
731 return
732 continuation = next_continuation.get('continuation')
733 if not continuation:
734 return
735 ctp = next_continuation.get('clickTrackingParams')
fe93e2c4 736 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 737
738 @classmethod
739 def _extract_continuation_ep_data(cls, continuation_ep: dict):
740 if isinstance(continuation_ep, dict):
741 continuation = try_get(
14f25df2 742 continuation_ep, lambda x: x['continuationCommand']['token'], str)
2d6659b9 743 if not continuation:
744 return
745 ctp = continuation_ep.get('clickTrackingParams')
fe93e2c4 746 return cls._build_api_continuation_query(continuation, ctp)
2d6659b9 747
748 @classmethod
749 def _extract_continuation(cls, renderer):
750 next_continuation = cls._extract_next_continuation_data(renderer)
751 if next_continuation:
752 return next_continuation
fe93e2c4 753
7a32c70d 754 return traverse_obj(renderer, (
755 ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
756 ('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
757 ), get_all=False, expected_type=cls._extract_continuation_ep_data)
2d6659b9 758
fe93e2c4 759 @classmethod
760 def _extract_alerts(cls, data):
109dd3b2 761 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
762 if not isinstance(alert_dict, dict):
763 continue
764 for alert in alert_dict.values():
765 alert_type = alert.get('type')
766 if not alert_type:
767 continue
052e1350 768 message = cls._get_text(alert, 'text')
109dd3b2 769 if message:
770 yield alert_type, message
771
c0ac49bc 772 def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False):
a057779d 773 errors, warnings = [], []
109dd3b2 774 for alert_type, alert_message in alerts:
641ad5d8 775 if alert_type.lower() == 'error' and fatal:
109dd3b2 776 errors.append([alert_type, alert_message])
a057779d 777 elif alert_message not in self._IGNORED_WARNINGS:
109dd3b2 778 warnings.append([alert_type, alert_message])
779
780 for alert_type, alert_message in (warnings + errors[:-1]):
86e5f3ed 781 self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once)
109dd3b2 782 if errors:
783 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
784
785 def _extract_and_report_alerts(self, data, *args, **kwargs):
786 return self._report_alerts(self._extract_alerts(data), *args, **kwargs)
787
14a14335 788 def _extract_badges(self, badge_list: list):
789 """
790 Extract known BadgeType's from a list of badge renderers.
791 @returns [{'type': BadgeType}]
792 """
793 icon_type_map = {
c26f9b99 794 'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED,
795 'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE,
14a14335 796 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC,
797 'CHECK_CIRCLE_THICK': BadgeType.VERIFIED,
798 'OFFICIAL_ARTIST_BADGE': BadgeType.VERIFIED,
8213ce28 799 'CHECK': BadgeType.VERIFIED,
c26f9b99 800 }
801
802 badge_style_map = {
803 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION,
804 'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM,
14a14335 805 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW,
8213ce28 806 'BADGE_STYLE_TYPE_VERIFIED': BadgeType.VERIFIED,
ad54c913 807 'BADGE_STYLE_TYPE_VERIFIED_ARTIST': BadgeType.VERIFIED,
c26f9b99 808 }
809
810 label_map = {
811 'unlisted': BadgeType.AVAILABILITY_UNLISTED,
812 'private': BadgeType.AVAILABILITY_PRIVATE,
813 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION,
814 'live': BadgeType.LIVE_NOW,
14a14335 815 'premium': BadgeType.AVAILABILITY_PREMIUM,
8213ce28 816 'verified': BadgeType.VERIFIED,
ad54c913 817 'official artist channel': BadgeType.VERIFIED,
c26f9b99 818 }
819
820 badges = []
14a14335 821 for badge in traverse_obj(badge_list, (..., lambda key, _: re.search(r'[bB]adgeRenderer$', key))):
c26f9b99 822 badge_type = (
14a14335 823 icon_type_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str))
c26f9b99 824 or badge_style_map.get(traverse_obj(badge, 'style'))
825 )
826 if badge_type:
827 badges.append({'type': badge_type})
828 continue
829
830 # fallback, won't work in some languages
14a14335 831 label = traverse_obj(
832 badge, 'label', ('accessibilityData', 'label'), 'tooltip', 'iconTooltip', get_all=False, expected_type=str, default='')
c26f9b99 833 for match, label_badge_type in label_map.items():
834 if match in label.lower():
14a14335 835 badges.append({'type': label_badge_type})
836 break
c26f9b99 837
47193e02 838 return badges
839
c26f9b99 840 @staticmethod
841 def _has_badge(badges, badge_type):
842 return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type))
843
47193e02 844 @staticmethod
052e1350 845 def _get_text(data, *path_list, max_runs=None):
846 for path in path_list or [None]:
847 if path is None:
848 obj = [data]
849 else:
850 obj = traverse_obj(data, path, default=[])
851 if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)):
852 obj = [obj]
853 for item in obj:
14f25df2 854 text = try_get(item, lambda x: x['simpleText'], str)
052e1350 855 if text:
856 return text
857 runs = try_get(item, lambda x: x['runs'], list) or []
858 if not runs and isinstance(item, list):
859 runs = item
860
861 runs = runs[:min(len(runs), max_runs or len(runs))]
6839ae1f 862 text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str))
052e1350 863 if text:
864 return text
47193e02 865
f0d785d3 866 def _get_count(self, data, *path_list):
867 count_text = self._get_text(data, *path_list) or ''
868 count = parse_count(count_text)
869 if count is None:
870 count = str_to_int(
871 self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None))
872 return count
873
a709d873 874 @staticmethod
875 def _extract_thumbnails(data, *path_list):
876 """
877 Extract thumbnails from thumbnails dict
878 @param path_list: path list to level that contains 'thumbnails' key
879 """
880 thumbnails = []
881 for path in path_list or [()]:
6839ae1f 882 for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...)):
a709d873 883 thumbnail_url = url_or_none(thumbnail.get('url'))
884 if not thumbnail_url:
885 continue
886 # Sometimes youtube gives a wrong thumbnail URL. See:
887 # https://github.com/yt-dlp/yt-dlp/issues/233
888 # https://github.com/ytdl-org/youtube-dl/issues/28023
889 if 'maxresdefault' in thumbnail_url:
890 thumbnail_url = thumbnail_url.split('?')[0]
891 thumbnails.append({
892 'url': thumbnail_url,
893 'height': int_or_none(thumbnail.get('height')),
894 'width': int_or_none(thumbnail.get('width')),
895 })
896 return thumbnails
897
f3aa3c3f 898 @staticmethod
899 def extract_relative_time(relative_time_text):
900 """
901 Extracts a relative time from string and converts to dt object
2fb35f60 902 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today', '8 yr ago'
f3aa3c3f 903 """
2fb35f60 904
5ca095cb 905 # XXX: this could be moved to a general function in utils/_utils.py
2fb35f60 906 # The relative time text strings are roughly the same as what
907 # Javascript's Intl.RelativeTimeFormat function generates.
908 # See: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Intl/RelativeTimeFormat
909 mobj = re.search(
910 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',
911 relative_time_text)
f3aa3c3f 912 if mobj:
f0d785d3 913 start = mobj.group('start')
914 if start:
915 return datetime_from_str(start)
f3aa3c3f 916 try:
f0d785d3 917 return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit')))
f3aa3c3f 918 except ValueError:
919 return None
920
c26f9b99 921 def _parse_time_text(self, text):
922 if not text:
923 return
f3aa3c3f 924 dt = self.extract_relative_time(text)
925 timestamp = None
926 if isinstance(dt, datetime.datetime):
927 timestamp = calendar.timegm(dt.timetuple())
f0d785d3 928
929 if timestamp is None:
930 timestamp = (
931 unified_timestamp(text) or unified_timestamp(
932 self._search_regex(
17322130 933 (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
396a76f7 934 text.lower(), 'time text', default=None)))
f0d785d3 935
c26f9b99 936 if text and timestamp is None and self._preferred_lang in (None, 'en'):
937 self.report_warning(
938 f'Cannot parse localized time text "{text}"', only_once=True)
939 return timestamp
f3aa3c3f 940
109dd3b2 941 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
942 ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None,
000c15a4 943 default_client='web'):
eb5bdbfa 944 raise_for_incomplete = bool(self._configuration_arg('raise_incomplete_data', ie_key=YoutubeIE))
945 # Incomplete Data should be a warning by default when retries are exhausted, while other errors should be fatal.
946 icd_retries = iter(self.RetryManager(fatal=raise_for_incomplete))
947 icd_rm = next(icd_retries)
948 main_retries = iter(self.RetryManager())
949 main_rm = next(main_retries)
feebf6d0
SS
950 # Manual retry loop for multiple RetryManagers
951 # The proper RetryManager MUST be advanced after an error
b634ba74 952 # and its result MUST be checked if the manager is non fatal
feebf6d0 953 while True:
109dd3b2 954 try:
955 response = self._call_api(
956 ep=ep, fatal=True, headers=headers,
be5c1ae8 957 video_id=item_id, query=query, note=note,
109dd3b2 958 context=self._extract_context(ytcfg, default_client),
959 api_key=self._extract_api_key(ytcfg, default_client),
be5c1ae8 960 api_hostname=api_hostname, default_client=default_client)
109dd3b2 961 except ExtractorError as e:
be5c1ae8 962 if not isinstance(e.cause, network_exceptions):
963 return self._error_or_warning(e, fatal=fatal)
3d2623a8 964 elif not isinstance(e.cause, HTTPError):
eb5bdbfa 965 main_rm.error = e
966 next(main_retries)
be5c1ae8 967 continue
109dd3b2 968
3d2623a8 969 first_bytes = e.cause.response.read(512)
be5c1ae8 970 if not is_html(first_bytes):
971 yt_error = try_get(
972 self._parse_json(
3d2623a8 973 self._webpage_read_content(e.cause.response, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
be5c1ae8 974 lambda x: x['error']['message'], str)
975 if yt_error:
976 self._report_alerts([('ERROR', yt_error)], fatal=False)
977 # Downloading page may result in intermittent 5xx HTTP error
eb5bdbfa 978 # Sometimes a 404 is also received. See: https://github.com/ytdl-org/youtube-dl/issues/28289
be5c1ae8 979 # We also want to catch all other network exceptions since errors in later pages can be troublesome
980 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
3d2623a8 981 if e.cause.status not in (403, 429):
eb5bdbfa 982 main_rm.error = e
983 next(main_retries)
be5c1ae8 984 continue
985 return self._error_or_warning(e, fatal=fatal)
986
987 try:
988 self._extract_and_report_alerts(response, only_once=True)
989 except ExtractorError as e:
eb5bdbfa 990 # YouTube's servers may return errors we want to retry on in a 200 OK response
be5c1ae8 991 # See: https://github.com/yt-dlp/yt-dlp/issues/839
992 if 'unknown error' in e.msg.lower():
eb5bdbfa 993 main_rm.error = e
994 next(main_retries)
be5c1ae8 995 continue
996 return self._error_or_warning(e, fatal=fatal)
997 # Youtube sometimes sends incomplete data
998 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
999 if not traverse_obj(response, *variadic(check_get_keys)):
eb5bdbfa 1000 icd_rm.error = ExtractorError('Incomplete data received', expected=True)
1001 should_retry = next(icd_retries, None)
1002 if not should_retry:
1003 return None
be5c1ae8 1004 continue
1005
1006 return response
109dd3b2 1007
9297939e 1008 @staticmethod
1009 def is_music_url(url):
5b28cef7 1010 return re.match(r'(https?://)?music\.youtube\.com/', url) is not None
9297939e 1011
30a074c2 1012 def _extract_video(self, renderer):
1013 video_id = renderer.get('videoId')
4dc23a80
M
1014
1015 reel_header_renderer = traverse_obj(renderer, (
1016 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer',
1017 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer'))
1018
1019 title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText')
052e1350 1020 description = self._get_text(renderer, 'descriptionSnippet')
6141346d
M
1021
1022 duration = int_or_none(renderer.get('lengthSeconds'))
1023 if duration is None:
1024 duration = parse_duration(self._get_text(
1025 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 1026 if duration is None:
4dc23a80 1027 # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab)
1c1b2f96 1028 duration = parse_duration(self._search_regex(
1029 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
1030 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
1031 video_id, default=None, group='duration'))
1032
f3aa3c3f 1033 channel_id = traverse_obj(
a44ca5a4 1034 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
1035 expected_type=str, get_all=False)
4dc23a80
M
1036 if not channel_id:
1037 channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId'))
1038
7666b936 1039 channel_id = self.ucid_or_none(channel_id)
1040
f3aa3c3f 1041 overlay_style = traverse_obj(
a44ca5a4 1042 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
1043 get_all=False, expected_type=str)
14a14335 1044 badges = self._extract_badges(traverse_obj(renderer, 'badges'))
8213ce28 1045 owner_badges = self._extract_badges(traverse_obj(renderer, 'ownerBadges'))
fd2ad7cb 1046 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 1047 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
1048 expected_type=str)) or ''
fd2ad7cb 1049 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 1050 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 1051 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 1052
4dc23a80
M
1053 time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo')
1054 or self._get_text(reel_header_renderer, 'timestampText') or '')
1055 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
1056
867c66ff
M
1057 live_status = (
1058 'is_upcoming' if scheduled_timestamp is not None
1059 else 'was_live' if 'streamed' in time_text.lower()
1060 else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW)
1061 else None)
1062
4dc23a80
M
1063 # videoInfo is a string like '50K views • 10 years ago'.
1064 view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or ''
1065 view_count = (0 if 'no views' in view_count_text.lower()
1066 else self._get_count({'simpleText': view_count_text}))
1067 view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count'
1068
93e12ed7 1069 channel = (self._get_text(renderer, 'ownerText', 'shortBylineText')
1070 or self._get_text(reel_header_renderer, 'channelTitleText'))
1071
1072 channel_handle = traverse_obj(renderer, (
1073 'shortBylineText', 'runs', ..., 'navigationEndpoint',
1074 (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl'))),
1075 expected_type=self.handle_from_url, get_all=False)
30a074c2 1076 return {
39ed931e 1077 '_type': 'url',
30a074c2 1078 'ie_key': YoutubeIE.ie_key(),
1079 'id': video_id,
fd2ad7cb 1080 'url': url,
30a074c2 1081 'title': title,
1082 'description': description,
1083 'duration': duration,
f3aa3c3f 1084 'channel_id': channel_id,
93e12ed7 1085 'channel': channel,
4dc23a80 1086 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
93e12ed7 1087 'uploader': channel,
1088 'uploader_id': channel_handle,
1089 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
4dc23a80 1090 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
5225df50 1091 'timestamp': (self._parse_time_text(time_text)
1092 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
1093 else None),
f3aa3c3f 1094 'release_timestamp': scheduled_timestamp,
c26f9b99 1095 'availability':
1096 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
1097 else self._availability(
1098 is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None,
1099 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
1100 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
867c66ff 1101 is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
4dc23a80 1102 view_count_field: view_count,
14a14335 1103 'live_status': live_status,
8213ce28 1104 'channel_is_verified': True if self._has_badge(owner_badges, BadgeType.VERIFIED) else None
30a074c2 1105 }
1106
0c148415 1107
360e1ca5 1108class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 1109 IE_DESC = 'YouTube'
cb7dfeea 1110 _VALID_URL = r"""(?x)^
c5e8d7af 1111 (
edb53e2d 1112 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 1113 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
1114 (?:www\.)?deturl\.com/www\.youtube\.com|
1115 (?:www\.)?pwnyoutube\.com|
1116 (?:www\.)?hooktube\.com|
1117 (?:www\.)?yourepeat\.com|
1118 tube\.majestyc\.net|
1119 %(invidious)s|
1120 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
1121 (?:.*?\#/)? # handle anchor (#/) redirect urls
1122 (?: # the various things that can precede the ID:
dad2210c 1123 (?:(?:v|embed|e|shorts|live)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 1124 |(?: # or the v= param in all its forms
f7000f3a 1125 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 1126 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 1127 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
1128 v=
1129 )
f4b05232 1130 ))
cbaed4bb
S
1131 |(?:
1132 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
1133 vid\.plus| # or vid.plus/xxxx
1134 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 1135 %(invidious)s
cbaed4bb 1136 )/
edb53e2d 1137 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 1138 )
c5e8d7af 1139 )? # all until now is optional -> you can pass the naked ID
201c1459 1140 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 1141 (?(1).+)? # if we found the ID, everything can follow
9297939e 1142 (?:\#|$)""" % {
d9190e44 1143 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 1144 }
7c6eb424 1145 _EMBED_REGEX = [
1146 r'''(?x)
1147 (?:
0ca0f881 1148 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
7c6eb424 1149 data-video-url=|
1150 <embed[^>]+?src=|
1151 embedSWF\(?:\s*|
1152 <object[^>]+data=|
1153 new\s+SWFObject\(
1154 )
1155 (["\'])
1156 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1157 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1158 \1''',
1159 # https://wordpress.org/plugins/lazy-load-for-videos/
1160 r'''(?xs)
1161 <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1162 \s[^>]*\bclass="[^"]*\blazy-load-youtube''',
1163 ]
6368e2e6 1164 _RETURN_TYPE = 'video' # XXX: How to handle multifeed?
7c6eb424 1165
e40c758c 1166 _PLAYER_INFO_RE = (
cc2db878 1167 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1168 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$',
545cc85d 1169 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 1170 )
2c62dc26 1171 _formats = {
c2d3cb4c 1172 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1173 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1174 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1175 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1176 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1177 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1178 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1179 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 1180 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 1181 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1182 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1183 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1184 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1185 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1186 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 1187 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 1188 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1189 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 1190
1191
1192 # 3D videos
c2d3cb4c 1193 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1194 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1195 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1196 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 1197 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1198 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1199 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 1200
96fb5605 1201 # Apple HTTP Live Streaming
11f12195 1202 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 1203 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1204 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1205 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1206 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1207 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 1208 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1209 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
1210
1211 # DASH mp4 video
d23028a8
S
1212 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1213 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1214 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1215 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1216 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 1217 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
1218 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1219 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1220 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1221 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1222 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1223 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 1224
f6f1fc92 1225 # Dash mp4 audio
d23028a8
S
1226 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1227 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1228 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1229 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1230 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1231 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1232 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1233
1234 # Dash webm
d23028a8
S
1235 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1236 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1237 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1238 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1239 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1240 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1241 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1242 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1243 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1244 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1245 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1246 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1247 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1248 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1249 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1250 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1251 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1252 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1253 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1254 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1255 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1256 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1257
1258 # Dash webm audio
d23028a8
S
1259 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1260 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1261
0857baad 1262 # Dash webm audio with opus inside
d23028a8
S
1263 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1264 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1265 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1266
ce6b9a2d
PH
1267 # RTMP (unnamed)
1268 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1269
1270 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1271 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1272 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1273 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1274 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1275 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1276 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1277 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1278 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1279 }
29f7c58a 1280 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1281
fd5c4aab
S
1282 _GEO_BYPASS = False
1283
78caa52a 1284 IE_NAME = 'youtube'
2eb88d95
PH
1285 _TESTS = [
1286 {
2d3d2997 1287 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1288 'info_dict': {
1289 'id': 'BaW_jenozKc',
1290 'ext': 'mp4',
3867038a 1291 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
ff9f925b 1292 'channel': 'Philipp Hagemeister',
dd4c4492
S
1293 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1294 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1295 'upload_date': '20121002',
ff9f925b 1296 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1297 'categories': ['Science & Technology'],
3867038a 1298 'tags': ['youtube-dl'],
556dbe7f 1299 'duration': 10,
dbdaaa23 1300 'view_count': int,
3e7c1224 1301 'like_count': int,
ff9f925b 1302 'availability': 'public',
1303 'playable_in_embed': True,
1304 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1305 'live_status': 'not_live',
1306 'age_limit': 0,
7c80519c 1307 'start_time': 1,
297a564b 1308 'end_time': 9,
12a1b225 1309 'comment_count': int,
7666b936 1310 'channel_follower_count': int,
1311 'uploader': 'Philipp Hagemeister',
1312 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
1313 'uploader_id': '@PhilippHagemeister',
5caf30db 1314 'heatmap': 'count:100',
2eb88d95 1315 }
0e853ca4 1316 },
fccd3771 1317 {
4bc3a23e
PH
1318 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1319 'note': 'Embed-only video (#1746)',
1320 'info_dict': {
1321 'id': 'yZIXLfi8CZQ',
1322 'ext': 'mp4',
1323 'upload_date': '20120608',
1324 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1325 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
94bfcd23 1326 'age_limit': 18,
545cc85d 1327 },
1328 'skip': 'Private video',
fccd3771 1329 },
11b56058 1330 {
8bdd16b4 1331 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1332 'note': 'Use the first video ID in the URL',
1333 'info_dict': {
1334 'id': 'BaW_jenozKc',
1335 'ext': 'mp4',
3867038a 1336 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
976ae3ea 1337 'channel': 'Philipp Hagemeister',
1338 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1339 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1340 'upload_date': '20121002',
976ae3ea 1341 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1342 'categories': ['Science & Technology'],
3867038a 1343 'tags': ['youtube-dl'],
556dbe7f 1344 'duration': 10,
dbdaaa23 1345 'view_count': int,
11b56058 1346 'like_count': int,
976ae3ea 1347 'availability': 'public',
1348 'playable_in_embed': True,
1349 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1350 'live_status': 'not_live',
1351 'age_limit': 0,
12a1b225 1352 'comment_count': int,
7666b936 1353 'channel_follower_count': int,
1354 'uploader': 'Philipp Hagemeister',
1355 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
1356 'uploader_id': '@PhilippHagemeister',
14a14335 1357 'heatmap': 'count:100',
34a7de29
S
1358 },
1359 'params': {
1360 'skip_download': True,
1361 },
11b56058 1362 },
dd27fd17 1363 {
2d3d2997 1364 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1365 'note': '256k DASH audio (format 141) via DASH manifest',
1366 'info_dict': {
1367 'id': 'a9LDPn-MO4I',
1368 'ext': 'm4a',
1369 'upload_date': '20121002',
4bc3a23e 1370 'description': '',
4bc3a23e 1371 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1372 },
4bc3a23e
PH
1373 'params': {
1374 'youtube_include_dash_manifest': True,
1375 'format': '141',
4919603f 1376 },
de3c7fe0 1377 'skip': 'format 141 not served anymore',
dd27fd17 1378 },
8bdd16b4 1379 # DASH manifest with encrypted signature
1380 {
1381 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1382 'info_dict': {
1383 'id': 'IB3lcPjvWLA',
1384 'ext': 'm4a',
1385 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1386 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1387 'duration': 244,
8bdd16b4 1388 'upload_date': '20131011',
cc2db878 1389 'abr': 129.495,
976ae3ea 1390 'like_count': int,
1391 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1392 'playable_in_embed': True,
1393 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1394 'view_count': int,
1395 'track': 'The Spark',
1396 'live_status': 'not_live',
1397 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1398 'channel': 'Afrojack',
976ae3ea 1399 'tags': 'count:19',
1400 'availability': 'public',
1401 'categories': ['Music'],
1402 'age_limit': 0,
1403 'alt_title': 'The Spark',
7666b936 1404 'channel_follower_count': int,
1405 'uploader': 'Afrojack',
1406 'uploader_url': 'https://www.youtube.com/@Afrojack',
1407 'uploader_id': '@Afrojack',
8bdd16b4 1408 },
1409 'params': {
1410 'youtube_include_dash_manifest': True,
1411 'format': '141/bestaudio[ext=m4a]',
1412 },
1413 },
65c2fde2 1414 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1415 {
65c2fde2 1416 'note': 'Embed allowed age-gate video',
2d3d2997 1417 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1418 'info_dict': {
1419 'id': 'HtVdAasjOgU',
1420 'ext': 'mp4',
1421 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1422 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1423 'duration': 142,
c522adb1 1424 'upload_date': '20140605',
34952f09 1425 'age_limit': 18,
976ae3ea 1426 'categories': ['Gaming'],
1427 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1428 'availability': 'needs_auth',
1429 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1430 'like_count': int,
1431 'channel': 'The Witcher',
1432 'live_status': 'not_live',
1433 'tags': 'count:17',
1434 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1435 'playable_in_embed': True,
1436 'view_count': int,
7666b936 1437 'channel_follower_count': int,
1438 'uploader': 'The Witcher',
1439 'uploader_url': 'https://www.youtube.com/@thewitcher',
1440 'uploader_id': '@thewitcher',
14a14335 1441 'comment_count': int,
8213ce28 1442 'channel_is_verified': True,
14a14335 1443 'heatmap': 'count:100',
c522adb1
JMF
1444 },
1445 },
65c2fde2 1446 {
1447 'note': 'Age-gate video with embed allowed in public site',
1448 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1449 'info_dict': {
1450 'id': 'HsUATh_Nc2U',
1451 'ext': 'mp4',
1452 'title': 'Godzilla 2 (Official Video)',
1453 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1454 'upload_date': '20200408',
65c2fde2 1455 'age_limit': 18,
976ae3ea 1456 'availability': 'needs_auth',
1457 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
976ae3ea 1458 'channel': 'FlyingKitty',
1459 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1460 'view_count': int,
1461 'categories': ['Entertainment'],
1462 'live_status': 'not_live',
1463 'tags': ['Flyingkitty', 'godzilla 2'],
1464 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1465 'like_count': int,
1466 'duration': 177,
1467 'playable_in_embed': True,
7666b936 1468 'channel_follower_count': int,
1469 'uploader': 'FlyingKitty',
1470 'uploader_url': 'https://www.youtube.com/@FlyingKitty900',
1471 'uploader_id': '@FlyingKitty900',
5caf30db 1472 'comment_count': int,
8213ce28 1473 'channel_is_verified': True,
65c2fde2 1474 },
1475 },
1476 {
1477 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1478 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1479 'info_dict': {
1480 'id': 'Tq92D6wQ1mg',
1481 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1482 'ext': 'mp4',
17322130 1483 'upload_date': '20191228',
65c2fde2 1484 'description': 'md5:17eccca93a786d51bc67646756894066',
1485 'age_limit': 18,
976ae3ea 1486 'like_count': int,
1487 'availability': 'needs_auth',
976ae3ea 1488 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1489 'view_count': int,
1490 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1491 'channel': 'Projekt Melody',
1492 'live_status': 'not_live',
1493 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1494 'playable_in_embed': True,
1495 'categories': ['Entertainment'],
1496 'duration': 106,
1497 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1498 'comment_count': int,
7666b936 1499 'channel_follower_count': int,
1500 'uploader': 'Projekt Melody',
1501 'uploader_url': 'https://www.youtube.com/@ProjektMelody',
1502 'uploader_id': '@ProjektMelody',
65c2fde2 1503 },
1504 },
1505 {
1506 'note': 'Non-Agegated non-embeddable video',
1507 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1508 'info_dict': {
1509 'id': 'MeJVWBSsPAY',
1510 'ext': 'mp4',
1511 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
65c2fde2 1512 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1513 'upload_date': '20130730',
976ae3ea 1514 'track': 'Such mich find mich',
1515 'age_limit': 0,
1516 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1517 'like_count': int,
1518 'playable_in_embed': False,
1519 'creator': 'OOMPH!',
1520 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1521 'view_count': int,
1522 'alt_title': 'Such mich find mich',
1523 'duration': 210,
1524 'channel': 'Herr Lurik',
1525 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1526 'categories': ['Music'],
1527 'availability': 'public',
976ae3ea 1528 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1529 'live_status': 'not_live',
1530 'artist': 'OOMPH!',
7666b936 1531 'channel_follower_count': int,
1532 'uploader': 'Herr Lurik',
1533 'uploader_url': 'https://www.youtube.com/@HerrLurik',
1534 'uploader_id': '@HerrLurik',
65c2fde2 1535 },
1536 },
1537 {
1538 'note': 'Non-bypassable age-gated video',
1539 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1540 'only_matching': True,
1541 },
8bdd16b4 1542 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1543 # YouTube Red ad is not captured for creator
1544 {
1545 'url': '__2ABJjxzNo',
1546 'info_dict': {
1547 'id': '__2ABJjxzNo',
1548 'ext': 'mp4',
1549 'duration': 266,
1550 'upload_date': '20100430',
545cc85d 1551 'creator': 'deadmau5',
1552 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1553 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1554 'alt_title': 'Some Chords',
976ae3ea 1555 'availability': 'public',
1556 'tags': 'count:14',
1557 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1558 'view_count': int,
1559 'live_status': 'not_live',
1560 'channel': 'deadmau5',
1561 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1562 'like_count': int,
1563 'track': 'Some Chords',
1564 'artist': 'deadmau5',
1565 'playable_in_embed': True,
1566 'age_limit': 0,
1567 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1568 'categories': ['Music'],
1569 'album': 'Some Chords',
7666b936 1570 'channel_follower_count': int,
1571 'uploader': 'deadmau5',
1572 'uploader_url': 'https://www.youtube.com/@deadmau5',
1573 'uploader_id': '@deadmau5',
8bdd16b4 1574 },
1575 'expected_warnings': [
1576 'DASH manifest missing',
1577 ]
1578 },
067aa17e 1579 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1580 {
1581 'url': 'lqQg6PlCWgI',
1582 'info_dict': {
1583 'id': 'lqQg6PlCWgI',
1584 'ext': 'mp4',
556dbe7f 1585 'duration': 6085,
90227264 1586 'upload_date': '20150827',
12a1b225 1587 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
cbe2bd91 1588 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1589 'like_count': int,
1590 'release_timestamp': 1343767800,
1591 'playable_in_embed': True,
1592 'categories': ['Sports'],
1593 'release_date': '20120731',
1594 'channel': 'Olympics',
1595 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1596 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1597 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1598 'age_limit': 0,
1599 'availability': 'public',
1600 'live_status': 'was_live',
1601 'view_count': int,
1602 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
7666b936 1603 'channel_follower_count': int,
1604 'uploader': 'Olympics',
1605 'uploader_url': 'https://www.youtube.com/@Olympics',
1606 'uploader_id': '@Olympics',
8213ce28 1607 'channel_is_verified': True,
cbe2bd91
PH
1608 },
1609 'params': {
1610 'skip_download': 'requires avconv',
e52a40ab 1611 }
cbe2bd91 1612 },
6271f1ca
PH
1613 # Non-square pixels
1614 {
1615 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1616 'info_dict': {
1617 'id': '_b-2C3KPAM0',
1618 'ext': 'mp4',
1619 'stretched_ratio': 16 / 9.,
556dbe7f 1620 'duration': 85,
6271f1ca 1621 'upload_date': '20110310',
6271f1ca 1622 '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 1623 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1624 'playable_in_embed': True,
1625 'channel': '孫ᄋᄅ',
1626 'age_limit': 0,
1627 'tags': 'count:11',
1628 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1629 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1630 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1631 'view_count': int,
1632 'categories': ['People & Blogs'],
1633 'like_count': int,
1634 'live_status': 'not_live',
1635 'availability': 'unlisted',
12a1b225 1636 'comment_count': int,
7666b936 1637 'channel_follower_count': int,
1638 'uploader': '孫ᄋᄅ',
1639 'uploader_url': 'https://www.youtube.com/@AllenMeow',
1640 'uploader_id': '@AllenMeow',
6271f1ca 1641 },
06b491eb
S
1642 },
1643 # url_encoded_fmt_stream_map is empty string
1644 {
1645 'url': 'qEJwOuvDf7I',
1646 'info_dict': {
1647 'id': 'qEJwOuvDf7I',
f57b7835 1648 'ext': 'webm',
06b491eb
S
1649 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1650 'description': '',
1651 'upload_date': '20150404',
06b491eb
S
1652 },
1653 'params': {
1654 'skip_download': 'requires avconv',
e323cf3f
S
1655 },
1656 'skip': 'This live event has ended.',
06b491eb 1657 },
067aa17e 1658 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1659 {
1660 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1661 'info_dict': {
1662 'id': 'FIl7x6_3R5Y',
eb6793ba 1663 'ext': 'webm',
da77d856
S
1664 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1665 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1666 'duration': 220,
da77d856 1667 'upload_date': '20150625',
eb6793ba 1668 'formats': 'mincount:31',
da77d856 1669 },
eb6793ba 1670 'skip': 'not actual anymore',
2ee8f5d8 1671 },
8a1a26ce
YCH
1672 # DASH manifest with segment_list
1673 {
1674 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1675 'md5': '8ce563a1d667b599d21064e982ab9e31',
1676 'info_dict': {
1677 'id': 'CsmdDsKjzN8',
1678 'ext': 'mp4',
17ee98e1 1679 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce 1680 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
8a1a26ce
YCH
1681 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1682 },
1683 'params': {
1684 'youtube_include_dash_manifest': True,
1685 'format': '135', # bestvideo
be49068d
S
1686 },
1687 'skip': 'This live event has ended.',
2ee8f5d8 1688 },
cf7e015f 1689 {
6368e2e6 1690 # Multifeed videos (multiple cameras), URL can be of any Camera
7666b936 1691 # TODO: fix multifeed titles
6368e2e6 1692 'url': 'https://www.youtube.com/watch?v=zaPI8MvL8pg',
cf7e015f 1693 'info_dict': {
6368e2e6 1694 'id': 'zaPI8MvL8pg',
1695 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04',
1696 'description': 'md5:563ccbc698b39298481ca3c571169519',
cf7e015f
S
1697 },
1698 'playlist': [{
1699 'info_dict': {
6368e2e6 1700 'id': 'j5yGuxZ8lLU',
cf7e015f 1701 'ext': 'mp4',
6368e2e6 1702 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Chris)',
6368e2e6 1703 'description': 'md5:563ccbc698b39298481ca3c571169519',
6368e2e6 1704 'duration': 10120,
1705 'channel_follower_count': int,
1706 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1707 'availability': 'public',
1708 'playable_in_embed': True,
1709 'upload_date': '20131105',
6368e2e6 1710 'categories': ['Gaming'],
1711 'live_status': 'was_live',
1712 'tags': 'count:24',
1713 'release_timestamp': 1383701910,
1714 'thumbnail': 'https://i.ytimg.com/vi/j5yGuxZ8lLU/maxresdefault.jpg',
1715 'comment_count': int,
1716 'age_limit': 0,
1717 'like_count': int,
1718 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1719 'channel': 'WiiLikeToPlay',
1720 'view_count': int,
1721 'release_date': '20131106',
7666b936 1722 'uploader': 'WiiLikeToPlay',
1723 'uploader_id': '@WLTP',
1724 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1725 },
1726 }, {
1727 'info_dict': {
6368e2e6 1728 'id': 'zaPI8MvL8pg',
cf7e015f 1729 'ext': 'mp4',
6368e2e6 1730 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Tyson)',
6368e2e6 1731 'availability': 'public',
1732 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1733 'channel': 'WiiLikeToPlay',
6368e2e6 1734 'channel_follower_count': int,
1735 'description': 'md5:563ccbc698b39298481ca3c571169519',
1736 'duration': 10108,
1737 'age_limit': 0,
1738 'like_count': int,
1739 'tags': 'count:24',
1740 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
6368e2e6 1741 'release_timestamp': 1383701915,
1742 'comment_count': int,
1743 'upload_date': '20131105',
1744 'thumbnail': 'https://i.ytimg.com/vi/zaPI8MvL8pg/maxresdefault.jpg',
1745 'release_date': '20131106',
1746 'playable_in_embed': True,
1747 'live_status': 'was_live',
1748 'categories': ['Gaming'],
1749 'view_count': int,
7666b936 1750 'uploader': 'WiiLikeToPlay',
1751 'uploader_id': '@WLTP',
1752 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1753 },
1754 }, {
1755 'info_dict': {
6368e2e6 1756 'id': 'R7r3vfO7Hao',
cf7e015f 1757 'ext': 'mp4',
6368e2e6 1758 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Spencer)',
1759 'thumbnail': 'https://i.ytimg.com/vi/R7r3vfO7Hao/maxresdefault.jpg',
1760 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1761 'like_count': int,
1762 'availability': 'public',
1763 'playable_in_embed': True,
1764 'upload_date': '20131105',
1765 'description': 'md5:563ccbc698b39298481ca3c571169519',
6368e2e6 1766 'channel_follower_count': int,
1767 'tags': 'count:24',
1768 'release_date': '20131106',
6368e2e6 1769 'comment_count': int,
1770 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1771 'channel': 'WiiLikeToPlay',
1772 'categories': ['Gaming'],
1773 'release_timestamp': 1383701914,
1774 'live_status': 'was_live',
1775 'age_limit': 0,
1776 'duration': 10128,
1777 'view_count': int,
7666b936 1778 'uploader': 'WiiLikeToPlay',
1779 'uploader_id': '@WLTP',
1780 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1781 },
1782 }],
6368e2e6 1783 'params': {'skip_download': True},
cbaed4bb 1784 },
f9f49d87 1785 {
067aa17e 1786 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1787 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1788 'info_dict': {
1789 'id': 'gVfLd0zydlo',
1790 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1791 },
1792 'playlist_count': 2,
be49068d 1793 'skip': 'Not multifeed anymore',
f9f49d87 1794 },
cbaed4bb 1795 {
2d3d2997 1796 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1797 'only_matching': True,
0e49d9a6 1798 },
6d4fc66b 1799 {
2d3d2997 1800 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1801 'only_matching': True,
1802 },
0e49d9a6 1803 {
067aa17e 1804 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1805 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1806 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1807 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1808 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1809 'info_dict': {
1810 'id': 'lsguqyKfVQg',
1811 'ext': 'mp4',
1812 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1813 'alt_title': 'Dark Walk',
0e49d9a6 1814 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1815 'duration': 133,
0e49d9a6 1816 'upload_date': '20151119',
11f9be09 1817 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1818 'track': 'Dark Walk',
1819 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1820 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1821 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1822 'categories': ['Film & Animation'],
1823 'view_count': int,
1824 'live_status': 'not_live',
1825 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1826 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1827 'tags': 'count:13',
1828 'availability': 'public',
1829 'channel': 'IronSoulElf',
1830 'playable_in_embed': True,
1831 'like_count': int,
1832 'age_limit': 0,
6c73052c 1833 'channel_follower_count': int
0e49d9a6
LL
1834 },
1835 'params': {
1836 'skip_download': True,
1837 },
1838 },
61f92af1 1839 {
067aa17e 1840 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1841 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1842 'only_matching': True,
1843 },
313dfc45
LL
1844 {
1845 # Video with yt:stretch=17:0
1846 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1847 'info_dict': {
1848 'id': 'Q39EVAstoRM',
1849 'ext': 'mp4',
1850 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1851 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1852 'upload_date': '20151107',
313dfc45
LL
1853 },
1854 'params': {
1855 'skip_download': True,
1856 },
be49068d 1857 'skip': 'This video does not exist.',
313dfc45 1858 },
201c1459 1859 {
1860 # Video with incomplete 'yt:stretch=16:'
1861 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1862 'only_matching': True,
1863 },
7caf9830
S
1864 {
1865 # Video licensed under Creative Commons
1866 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1867 'info_dict': {
1868 'id': 'M4gD1WSo5mA',
1869 'ext': 'mp4',
1870 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1871 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1872 'duration': 721,
17322130 1873 'upload_date': '20150128',
7caf9830 1874 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1875 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1876 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1877 'like_count': int,
1878 'age_limit': 0,
1879 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1880 'channel': 'The Berkman Klein Center for Internet & Society',
1881 'availability': 'public',
1882 'view_count': int,
1883 'categories': ['Education'],
1884 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1885 'live_status': 'not_live',
1886 'playable_in_embed': True,
d5d1df8a 1887 'channel_follower_count': int,
1888 'chapters': list,
7666b936 1889 'uploader': 'The Berkman Klein Center for Internet & Society',
1890 'uploader_id': '@BKCHarvard',
1891 'uploader_url': 'https://www.youtube.com/@BKCHarvard',
7caf9830
S
1892 },
1893 'params': {
1894 'skip_download': True,
1895 },
1896 },
fd050249 1897 {
fd050249
S
1898 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1899 'info_dict': {
1900 'id': 'eQcmzGIKrzg',
1901 'ext': 'mp4',
1902 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1903 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1904 'duration': 4060,
17322130 1905 'upload_date': '20151120',
fd050249 1906 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1907 'playable_in_embed': True,
1908 'tags': 'count:12',
1909 'like_count': int,
1910 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1911 'age_limit': 0,
1912 'availability': 'public',
1913 'categories': ['News & Politics'],
1914 'channel': 'Bernie Sanders',
1915 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1916 'view_count': int,
1917 'live_status': 'not_live',
1918 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1919 'comment_count': int,
d5d1df8a 1920 'channel_follower_count': int,
1921 'chapters': list,
7666b936 1922 'uploader': 'Bernie Sanders',
1923 'uploader_url': 'https://www.youtube.com/@BernieSanders',
1924 'uploader_id': '@BernieSanders',
8213ce28 1925 'channel_is_verified': True,
14a14335 1926 'heatmap': 'count:100',
fd050249
S
1927 },
1928 'params': {
1929 'skip_download': True,
1930 },
1931 },
040ac686
S
1932 {
1933 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1934 'only_matching': True,
7f29cf54
S
1935 },
1936 {
067aa17e 1937 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1938 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1939 'only_matching': True,
6496ccb4
S
1940 },
1941 {
1942 # Rental video preview
1943 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1944 'info_dict': {
1945 'id': 'uGpuVWrhIzE',
1946 'ext': 'mp4',
1947 'title': 'Piku - Trailer',
1948 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1949 'upload_date': '20150811',
6496ccb4
S
1950 'license': 'Standard YouTube License',
1951 },
1952 'params': {
1953 'skip_download': True,
1954 },
eb6793ba 1955 'skip': 'This video is not available.',
022a5d66 1956 },
12afdc2a
S
1957 {
1958 # YouTube Red video with episode data
1959 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1960 'info_dict': {
1961 'id': 'iqKdEhx-dD4',
1962 'ext': 'mp4',
1963 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1964 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1965 'duration': 2085,
12afdc2a 1966 'upload_date': '20170118',
12afdc2a
S
1967 'series': 'Mind Field',
1968 'season_number': 1,
1969 'episode_number': 1,
976ae3ea 1970 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1971 'tags': 'count:12',
1972 'view_count': int,
1973 'availability': 'public',
1974 'age_limit': 0,
1975 'channel': 'Vsauce',
1976 'episode': 'Episode 1',
1977 'categories': ['Entertainment'],
1978 'season': 'Season 1',
1979 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1980 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1981 'like_count': int,
1982 'playable_in_embed': True,
1983 'live_status': 'not_live',
7666b936 1984 'channel_follower_count': int,
1985 'uploader': 'Vsauce',
1986 'uploader_url': 'https://www.youtube.com/@Vsauce',
1987 'uploader_id': '@Vsauce',
14a14335 1988 'comment_count': int,
8213ce28 1989 'channel_is_verified': True,
12afdc2a
S
1990 },
1991 'params': {
1992 'skip_download': True,
1993 },
1994 'expected_warnings': [
1995 'Skipping DASH manifest',
1996 ],
1997 },
c7121fa7
S
1998 {
1999 # The following content has been identified by the YouTube community
2000 # as inappropriate or offensive to some audiences.
2001 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
2002 'info_dict': {
2003 'id': '6SJNVb0GnPI',
2004 'ext': 'mp4',
2005 'title': 'Race Differences in Intelligence',
2006 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
2007 'duration': 965,
2008 'upload_date': '20140124',
c7121fa7
S
2009 },
2010 'params': {
2011 'skip_download': True,
2012 },
545cc85d 2013 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 2014 },
022a5d66
S
2015 {
2016 # itag 212
2017 'url': '1t24XAntNCY',
2018 'only_matching': True,
fd5c4aab
S
2019 },
2020 {
2021 # geo restricted to JP
2022 'url': 'sJL6WA-aGkQ',
2023 'only_matching': True,
2024 },
cd5a74a2
S
2025 {
2026 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
2027 'only_matching': True,
2028 },
bc2ca1bb 2029 {
2030 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
2031 'only_matching': True,
2032 },
2033 {
2034 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
2035 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
2036 'only_matching': True,
2037 },
825cd268
RA
2038 {
2039 # DRM protected
2040 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
2041 'only_matching': True,
4fe54c12
S
2042 },
2043 {
2044 # Video with unsupported adaptive stream type formats
2045 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
2046 'info_dict': {
2047 'id': 'Z4Vy8R84T1U',
2048 'ext': 'mp4',
2049 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
2050 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2051 'duration': 433,
2052 'upload_date': '20130923',
4fe54c12
S
2053 'formats': 'maxcount:10',
2054 },
2055 'params': {
2056 'skip_download': True,
2057 'youtube_include_dash_manifest': False,
2058 },
5429d6a9 2059 'skip': 'not actual anymore',
5caabd3c 2060 },
2061 {
822b9d9c 2062 # Youtube Music Auto-generated description
7666b936 2063 # TODO: fix metadata extraction
5caabd3c 2064 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2065 'info_dict': {
2066 'id': 'MgNrAu2pzNs',
2067 'ext': 'mp4',
2068 'title': 'Voyeur Girl',
2069 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
2070 'upload_date': '20190312',
104a7b5a
L
2071 'artists': ['Stephen'],
2072 'creators': ['Stephen'],
5caabd3c 2073 'track': 'Voyeur Girl',
2074 'album': 'it\'s too much love to know my dear',
2075 'release_date': '20190313',
976ae3ea 2076 'alt_title': 'Voyeur Girl',
2077 'view_count': int,
976ae3ea 2078 'playable_in_embed': True,
2079 'like_count': int,
2080 'categories': ['Music'],
2081 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
7666b936 2082 'channel': 'Stephen', # TODO: should be "Stephen - Topic"
2083 'uploader': 'Stephen',
976ae3ea 2084 'availability': 'public',
976ae3ea 2085 'duration': 169,
2086 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
2087 'age_limit': 0,
2088 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2089 'tags': 'count:11',
2090 'live_status': 'not_live',
6c73052c 2091 'channel_follower_count': int
5caabd3c 2092 },
2093 'params': {
2094 'skip_download': True,
2095 },
2096 },
66b48727
RA
2097 {
2098 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
2099 'only_matching': True,
2100 },
011e75e6
S
2101 {
2102 # invalid -> valid video id redirection
2103 'url': 'DJztXj2GPfl',
2104 'info_dict': {
2105 'id': 'DJztXj2GPfk',
2106 'ext': 'mp4',
2107 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
2108 'description': 'md5:bf577a41da97918e94fa9798d9228825',
2109 'upload_date': '20090125',
011e75e6
S
2110 'artist': 'Panjabi MC',
2111 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
2112 'album': 'Beware of the Boys (Mundian To Bach Ke)',
2113 },
2114 'params': {
2115 'skip_download': True,
2116 },
545cc85d 2117 'skip': 'Video unavailable',
ea74e00b
DP
2118 },
2119 {
2120 # empty description results in an empty string
2121 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
2122 'info_dict': {
2123 'id': 'x41yOUIvK2k',
2124 'ext': 'mp4',
2125 'title': 'IMG 3456',
2126 'description': '',
2127 'upload_date': '20170613',
976ae3ea 2128 'view_count': int,
2129 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
976ae3ea 2130 'like_count': int,
2131 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
2132 'tags': [],
2133 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
2134 'availability': 'public',
2135 'age_limit': 0,
2136 'categories': ['Pets & Animals'],
2137 'duration': 7,
2138 'playable_in_embed': True,
2139 'live_status': 'not_live',
7666b936 2140 'channel': 'l\'Or Vert asbl',
2141 'channel_follower_count': int,
2142 'uploader': 'l\'Or Vert asbl',
2143 'uploader_url': 'https://www.youtube.com/@ElevageOrVert',
2144 'uploader_id': '@ElevageOrVert',
ea74e00b
DP
2145 },
2146 'params': {
2147 'skip_download': True,
2148 },
2149 },
a0566bbf 2150 {
29f7c58a 2151 # with '};' inside yt initial data (see [1])
2152 # see [2] for an example with '};' inside ytInitialPlayerResponse
2153 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2154 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 2155 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2156 'info_dict': {
2157 'id': 'CHqg6qOn4no',
2158 'ext': 'mp4',
2159 'title': 'Part 77 Sort a list of simple types in c#',
2160 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2161 'upload_date': '20130831',
976ae3ea 2162 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2163 'like_count': int,
976ae3ea 2164 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2165 'live_status': 'not_live',
2166 'categories': ['Education'],
2167 'availability': 'public',
2168 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2169 'tags': 'count:12',
2170 'playable_in_embed': True,
2171 'age_limit': 0,
2172 'view_count': int,
2173 'duration': 522,
2174 'channel': 'kudvenkat',
12a1b225 2175 'comment_count': int,
d5d1df8a 2176 'channel_follower_count': int,
2177 'chapters': list,
7666b936 2178 'uploader': 'kudvenkat',
2179 'uploader_url': 'https://www.youtube.com/@Csharp-video-tutorialsBlogspot',
2180 'uploader_id': '@Csharp-video-tutorialsBlogspot',
8213ce28 2181 'channel_is_verified': True,
14a14335 2182 'heatmap': 'count:100',
a0566bbf 2183 },
2184 'params': {
2185 'skip_download': True,
2186 },
2187 },
29f7c58a 2188 {
2189 # another example of '};' in ytInitialData
2190 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2191 'only_matching': True,
2192 },
2193 {
2194 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2195 'only_matching': True,
2196 },
545cc85d 2197 {
cc2db878 2198 # https://github.com/ytdl-org/youtube-dl/pull/28094
2199 'url': 'OtqTfy26tG0',
2200 'info_dict': {
2201 'id': 'OtqTfy26tG0',
2202 'ext': 'mp4',
2203 'title': 'Burn Out',
2204 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2205 'upload_date': '20141120',
cc2db878 2206 'artist': 'The Cinematic Orchestra',
2207 'track': 'Burn Out',
2208 'album': 'Every Day',
976ae3ea 2209 'like_count': int,
2210 'live_status': 'not_live',
2211 'alt_title': 'Burn Out',
2212 'duration': 614,
2213 'age_limit': 0,
2214 'view_count': int,
2215 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2216 'creator': 'The Cinematic Orchestra',
2217 'channel': 'The Cinematic Orchestra',
2218 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2219 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2220 'availability': 'public',
2221 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2222 'categories': ['Music'],
2223 'playable_in_embed': True,
7666b936 2224 'channel_follower_count': int,
2225 'uploader': 'The Cinematic Orchestra',
2226 'comment_count': int,
cc2db878 2227 },
2228 'params': {
2229 'skip_download': True,
2230 },
545cc85d 2231 },
bc2ca1bb 2232 {
2233 # controversial video, only works with bpctr when authenticated with cookies
2234 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2235 'only_matching': True,
2236 },
a1a7907b 2237 {
2238 # controversial video, requires bpctr/contentCheckOk
2239 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2240 'info_dict': {
2241 'id': 'SZJvDhaSDnc',
2242 'ext': 'mp4',
2243 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2244 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
a1a7907b 2245 'upload_date': '20140716',
976ae3ea 2246 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2247 'duration': 170,
2248 'categories': ['News & Politics'],
976ae3ea 2249 'view_count': int,
2250 'channel': 'CBS Mornings',
2251 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2252 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2253 'age_limit': 18,
2254 'availability': 'needs_auth',
2255 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2256 'like_count': int,
2257 'live_status': 'not_live',
2258 'playable_in_embed': True,
7666b936 2259 'channel_follower_count': int,
2260 'uploader': 'CBS Mornings',
2261 'uploader_url': 'https://www.youtube.com/@CBSMornings',
2262 'uploader_id': '@CBSMornings',
14a14335 2263 'comment_count': int,
8213ce28 2264 'channel_is_verified': True,
a1a7907b 2265 }
2266 },
f7ad7160 2267 {
2268 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2269 'url': 'cBvYw8_A0vQ',
2270 'info_dict': {
2271 'id': 'cBvYw8_A0vQ',
2272 'ext': 'mp4',
2273 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2274 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2275 'upload_date': '20201120',
976ae3ea 2276 'duration': 1456,
2277 'categories': ['Travel & Events'],
2278 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2279 'view_count': int,
2280 'channel': 'Walk around Japan',
2281 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2282 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2283 'age_limit': 0,
2284 'availability': 'public',
2285 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2286 'live_status': 'not_live',
2287 'playable_in_embed': True,
7666b936 2288 'channel_follower_count': int,
2289 'uploader': 'Walk around Japan',
2290 'uploader_url': 'https://www.youtube.com/@walkaroundjapan7124',
2291 'uploader_id': '@walkaroundjapan7124',
f7ad7160 2292 },
2293 'params': {
2294 'skip_download': True,
2295 },
0fb983f6 2296 }, {
2297 # Has multiple audio streams
2298 'url': 'WaOKSUlf4TM',
2299 'only_matching': True
9297939e 2300 }, {
2301 # Requires Premium: has format 141 when requested using YTM url
2302 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2303 'only_matching': True
2304 }, {
120916da 2305 # multiple subtitles with same lang_code
2306 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2307 'only_matching': True,
109dd3b2 2308 }, {
2309 # Force use android client fallback
2310 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2311 'info_dict': {
2312 'id': 'YOelRv7fMxY',
11f9be09 2313 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2314 'ext': '3gp',
2315 'upload_date': '20210624',
2316 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
109dd3b2 2317 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2318 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2319 'duration': 596,
2320 'categories': ['Entertainment'],
976ae3ea 2321 'view_count': int,
2322 'channel': 'colinfurze',
2323 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2324 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2325 'age_limit': 0,
2326 'availability': 'public',
2327 'like_count': int,
2328 'live_status': 'not_live',
2329 'playable_in_embed': True,
d5d1df8a 2330 'channel_follower_count': int,
2331 'chapters': list,
7666b936 2332 'uploader': 'colinfurze',
2333 'uploader_url': 'https://www.youtube.com/@colinfurze',
2334 'uploader_id': '@colinfurze',
14a14335 2335 'comment_count': int,
8213ce28 2336 'channel_is_verified': True,
14a14335 2337 'heatmap': 'count:100',
109dd3b2 2338 },
2339 'params': {
2340 'format': '17', # 3gp format available on android
2341 'extractor_args': {'youtube': {'player_client': ['android']}},
2342 },
120916da 2343 },
109dd3b2 2344 {
2345 # Skip download of additional client configs (remix client config in this case)
2346 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2347 'only_matching': True,
2348 'params': {
2349 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2350 },
8fc54b12 2351 }, {
2352 # shorts
2353 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2354 'only_matching': True,
9222c381 2355 }, {
2356 'note': 'Storyboards',
2357 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2358 'info_dict': {
2359 'id': '5KLPxDtMqe8',
2360 'ext': 'mhtml',
2361 'format_id': 'sb0',
2362 'title': 'Your Brain is Plastic',
9222c381 2363 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2364 'upload_date': '20140324',
976ae3ea 2365 'like_count': int,
2366 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2367 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2368 'view_count': int,
2369 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2370 'playable_in_embed': True,
2371 'tags': 'count:12',
976ae3ea 2372 'availability': 'public',
2373 'channel': 'SciShow',
2374 'live_status': 'not_live',
2375 'duration': 248,
2376 'categories': ['Education'],
2377 'age_limit': 0,
d5d1df8a 2378 'channel_follower_count': int,
2379 'chapters': list,
7666b936 2380 'uploader': 'SciShow',
2381 'uploader_url': 'https://www.youtube.com/@SciShow',
2382 'uploader_id': '@SciShow',
14a14335 2383 'comment_count': int,
8213ce28 2384 'channel_is_verified': True,
14a14335 2385 'heatmap': 'count:100',
9222c381 2386 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2387 }, {
2388 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2389 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2390 'info_dict': {
2391 'id': '2NUZ8W2llS4',
2392 'ext': 'mp4',
2393 'title': 'The NP that test your phone performance 🙂',
2394 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
992f9a73 2395 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2396 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2397 'duration': 21,
2398 'view_count': int,
2399 'age_limit': 0,
2400 'categories': ['Gaming'],
2401 'tags': 'count:23',
2402 'playable_in_embed': True,
2403 'live_status': 'not_live',
2404 'upload_date': '20220103',
2405 'like_count': int,
2406 'availability': 'public',
2407 'channel': 'Leon Nguyen',
2408 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2409 'comment_count': int,
7666b936 2410 'channel_follower_count': int,
2411 'uploader': 'Leon Nguyen',
2412 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
2413 'uploader_id': '@LeonNguyen',
14a14335 2414 'heatmap': 'count:100',
992f9a73 2415 }
1ff88b7a 2416 }, {
2417 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2418 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2419 'info_dict': {
2420 'id': '2NUZ8W2llS4',
2421 'ext': 'mp4',
2422 'title': 'The NP that test your phone performance 🙂',
2423 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
1ff88b7a 2424 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2425 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2426 'duration': 21,
2427 'view_count': int,
2428 'age_limit': 0,
2429 'categories': ['Gaming'],
2430 'tags': 'count:23',
2431 'playable_in_embed': True,
2432 'live_status': 'not_live',
2433 'upload_date': '20220102',
2434 'like_count': int,
2435 'availability': 'public',
2436 'channel': 'Leon Nguyen',
2437 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2438 'comment_count': int,
7666b936 2439 'channel_follower_count': int,
2440 'uploader': 'Leon Nguyen',
2441 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
2442 'uploader_id': '@LeonNguyen',
14a14335 2443 'heatmap': 'count:100',
1ff88b7a 2444 },
2445 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
992f9a73 2446 }, {
2447 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2448 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2449 'info_dict': {
2450 'id': 'mzZzzBU6lrM',
2451 'ext': 'mp4',
2452 'title': 'I Met GeorgeNotFound In Real Life...',
7666b936 2453 'description': 'md5:978296ec9783a031738b684d4ebf302d',
992f9a73 2454 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2455 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2456 'duration': 955,
2457 'view_count': int,
2458 'age_limit': 0,
2459 'categories': ['Entertainment'],
2460 'tags': 'count:26',
2461 'playable_in_embed': True,
2462 'live_status': 'not_live',
2463 'release_timestamp': 1641172509,
2464 'release_date': '20220103',
2465 'upload_date': '20220103',
2466 'like_count': int,
2467 'availability': 'public',
2468 'channel': 'Quackity',
2469 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
7666b936 2470 'channel_follower_count': int,
2471 'uploader': 'Quackity',
2472 'uploader_id': '@Quackity',
2473 'uploader_url': 'https://www.youtube.com/@Quackity',
14a14335 2474 'comment_count': int,
8213ce28 2475 'channel_is_verified': True,
14a14335 2476 'heatmap': 'count:100',
992f9a73 2477 }
2478 },
2479 { # continuous livestream. Microformat upload date should be preferred.
2480 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2481 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2482 'info_dict': {
2483 'id': 'kgx4WGK0oNU',
2484 '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}',
2485 'ext': 'mp4',
2486 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2487 'availability': 'public',
2488 'age_limit': 0,
2489 'release_timestamp': 1637975704,
2490 'upload_date': '20210619',
2491 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2492 'live_status': 'is_live',
2493 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
992f9a73 2494 'channel': 'Abao in Tokyo',
2495 'channel_follower_count': int,
2496 'release_date': '20211127',
2497 'tags': 'count:39',
2498 'categories': ['People & Blogs'],
2499 'like_count': int,
992f9a73 2500 'view_count': int,
2501 'playable_in_embed': True,
2502 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
867c66ff 2503 'concurrent_view_count': int,
7666b936 2504 'uploader': 'Abao in Tokyo',
2505 'uploader_url': 'https://www.youtube.com/@abaointokyo',
2506 'uploader_id': '@abaointokyo',
992f9a73 2507 },
2508 'params': {'skip_download': True}
ee27297f 2509 }, {
2510 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2511 'info_dict': {
2512 'id': 'tjjjtzRLHvA',
2513 'ext': 'mp4',
2514 'title': 'ハッシュタグ無し };if window.ytcsi',
2515 'upload_date': '20220323',
2516 'like_count': int,
2517 'availability': 'unlisted',
7666b936 2518 'channel': 'Lesmiscore',
2519 'thumbnail': r're:^https?://.*\.jpg',
ee27297f 2520 'age_limit': 0,
ee27297f 2521 'categories': ['Music'],
6e634cbe 2522 'view_count': int,
2523 'description': '',
ee27297f 2524 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2525 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2526 'live_status': 'not_live',
2527 'playable_in_embed': True,
2528 'channel_follower_count': int,
2529 'duration': 6,
2530 'tags': [],
7666b936 2531 'uploader_id': '@lesmiscore',
2532 'uploader': 'Lesmiscore',
2533 'uploader_url': 'https://www.youtube.com/@lesmiscore',
6e634cbe 2534 }
c26f9b99 2535 }, {
2536 # Prefer primary title+description language metadata by default
2537 # Do not prefer translated description if primary is empty
2538 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2539 'info_dict': {
2540 'id': 'el3E4MbxRqQ',
2541 'ext': 'mp4',
2542 'title': 'dlp test video 2 - primary sv no desc',
2543 'description': '',
2544 'channel': 'cole-dlp-test-acc',
2545 'tags': [],
2546 'view_count': int,
2547 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2548 'like_count': int,
2549 'playable_in_embed': True,
2550 'availability': 'unlisted',
7666b936 2551 'thumbnail': r're:^https?://.*\.jpg',
c26f9b99 2552 'age_limit': 0,
2553 'duration': 5,
c26f9b99 2554 'live_status': 'not_live',
2555 'upload_date': '20220908',
2556 'categories': ['People & Blogs'],
c26f9b99 2557 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
7666b936 2558 'uploader_url': 'https://www.youtube.com/@coletdjnz',
2559 'uploader_id': '@coletdjnz',
2560 'uploader': 'cole-dlp-test-acc',
c26f9b99 2561 },
2562 'params': {'skip_download': True}
2563 }, {
2564 # Extractor argument: prefer translated title+description
2565 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2566 'info_dict': {
2567 'id': 'gHKT4uU8Zng',
2568 'ext': 'mp4',
2569 'channel': 'cole-dlp-test-acc',
2570 'tags': [],
2571 'duration': 5,
2572 'live_status': 'not_live',
2573 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2574 'upload_date': '20220728',
c26f9b99 2575 'view_count': int,
2576 'categories': ['People & Blogs'],
7666b936 2577 'thumbnail': r're:^https?://.*\.jpg',
c26f9b99 2578 'title': 'dlp test video title translated (fr)',
2579 'availability': 'public',
c26f9b99 2580 'age_limit': 0,
2581 'description': 'dlp test video description translated (fr)',
2582 'playable_in_embed': True,
2583 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
7666b936 2584 'uploader_url': 'https://www.youtube.com/@coletdjnz',
2585 'uploader_id': '@coletdjnz',
2586 'uploader': 'cole-dlp-test-acc',
c26f9b99 2587 },
2588 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2589 'expected_warnings': [r'Preferring "fr" translated fields'],
a4166234 2590 }, {
2591 'note': '6 channel audio',
2592 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2593 'only_matching': True,
a4894d3e 2594 }, {
2595 'note': 'Multiple HLS formats with same itag',
2596 'url': 'https://www.youtube.com/watch?v=kX3nB4PpJko',
2597 'info_dict': {
2598 'id': 'kX3nB4PpJko',
2599 'ext': 'mp4',
2600 'categories': ['Entertainment'],
2601 'description': 'md5:e8031ff6e426cdb6a77670c9b81f6fa6',
a4894d3e 2602 'live_status': 'not_live',
2603 'duration': 937,
2604 'channel_follower_count': int,
2605 'thumbnail': 'https://i.ytimg.com/vi_webp/kX3nB4PpJko/maxresdefault.webp',
2606 'title': 'Last To Take Hand Off Jet, Keeps It!',
2607 'channel': 'MrBeast',
2608 'playable_in_embed': True,
2609 'view_count': int,
2610 'upload_date': '20221112',
a4894d3e 2611 'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA',
2612 'age_limit': 0,
2613 'availability': 'public',
2614 'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA',
2615 'like_count': int,
2616 'tags': [],
7666b936 2617 'uploader': 'MrBeast',
2618 'uploader_url': 'https://www.youtube.com/@MrBeast',
2619 'uploader_id': '@MrBeast',
14a14335 2620 'comment_count': int,
8213ce28 2621 'channel_is_verified': True,
14a14335 2622 'heatmap': 'count:100',
a4894d3e 2623 },
2624 'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
9bb85699 2625 }, {
2626 'note': 'Audio formats with Dynamic Range Compression',
2627 'url': 'https://www.youtube.com/watch?v=Tq92D6wQ1mg',
2628 'info_dict': {
2629 'id': 'Tq92D6wQ1mg',
7666b936 2630 'ext': 'webm',
9bb85699 2631 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
2632 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2633 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2634 'channel_follower_count': int,
2635 'description': 'md5:17eccca93a786d51bc67646756894066',
2636 'upload_date': '20191228',
9bb85699 2637 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
2638 'playable_in_embed': True,
2639 'like_count': int,
2640 'categories': ['Entertainment'],
2641 'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
2642 'age_limit': 18,
2643 'channel': 'Projekt Melody',
9bb85699 2644 'view_count': int,
2645 'availability': 'needs_auth',
2646 'comment_count': int,
2647 'live_status': 'not_live',
9bb85699 2648 'duration': 106,
7666b936 2649 'uploader': 'Projekt Melody',
2650 'uploader_id': '@ProjektMelody',
2651 'uploader_url': 'https://www.youtube.com/@ProjektMelody',
9bb85699 2652 },
2653 'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
dad2210c 2654 },
2655 {
2656 'url': 'https://www.youtube.com/live/qVv6vCqciTM',
2657 'info_dict': {
2658 'id': 'qVv6vCqciTM',
2659 'ext': 'mp4',
2660 'age_limit': 0,
dad2210c 2661 'comment_count': int,
2662 'chapters': 'count:13',
2663 'upload_date': '20221223',
2664 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
2665 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
dad2210c 2666 'like_count': int,
2667 'release_date': '20221223',
2668 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
2669 '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】',
2670 'view_count': int,
2671 'playable_in_embed': True,
2672 'duration': 4438,
2673 'availability': 'public',
2674 'channel_follower_count': int,
2675 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2676 'categories': ['Entertainment'],
2677 'live_status': 'was_live',
2678 'release_timestamp': 1671793345,
2679 'channel': 'さなちゃんねる',
2680 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
2681 'uploader': 'さなちゃんねる',
7666b936 2682 'uploader_url': 'https://www.youtube.com/@sana_natori',
2683 'uploader_id': '@sana_natori',
8213ce28 2684 'channel_is_verified': True,
14a14335 2685 'heatmap': 'count:100',
7666b936 2686 },
2687 },
2688 {
2689 # Fallbacks when webpage and web client is unavailable
2690 'url': 'https://www.youtube.com/watch?v=wSSmNUl9Snw',
2691 'info_dict': {
2692 'id': 'wSSmNUl9Snw',
2693 'ext': 'mp4',
2694 # 'categories': ['Science & Technology'],
2695 'view_count': int,
2696 'chapters': 'count:2',
2697 'channel': 'Scott Manley',
2698 'like_count': int,
2699 'age_limit': 0,
2700 # 'availability': 'public',
2701 'channel_follower_count': int,
2702 'live_status': 'not_live',
2703 'upload_date': '20170831',
2704 'duration': 682,
2705 'tags': 'count:8',
2706 'uploader_url': 'https://www.youtube.com/@scottmanley',
2707 'description': 'md5:f4bed7b200404b72a394c2f97b782c02',
2708 'uploader': 'Scott Manley',
2709 'uploader_id': '@scottmanley',
2710 'title': 'The Computer Hack That Saved Apollo 14',
2711 'channel_id': 'UCxzC4EngIsMrPmbm6Nxvb-A',
2712 'thumbnail': r're:^https?://.*\.webp',
2713 'channel_url': 'https://www.youtube.com/channel/UCxzC4EngIsMrPmbm6Nxvb-A',
2714 'playable_in_embed': True,
14a14335 2715 'comment_count': int,
8213ce28 2716 'channel_is_verified': True,
14a14335 2717 'heatmap': 'count:100',
7666b936 2718 },
2719 'params': {
2720 'extractor_args': {'youtube': {'player_client': ['android'], 'player_skip': ['webpage']}},
dad2210c 2721 },
2722 },
2eb88d95
PH
2723 ]
2724
f2e8dbcc 2725 _WEBPAGE_TESTS = [
2726 # YouTube <object> embed
2727 {
2728 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2729 'md5': '873c81d308b979f0e23ee7e620b312a3',
2730 'info_dict': {
2731 'id': 'msN87y-iEx0',
2732 'ext': 'mp4',
2733 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2734 'upload_date': '20080526',
2735 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
f2e8dbcc 2736 'age_limit': 0,
2737 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2738 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2739 'playable_in_embed': True,
2740 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2741 'like_count': int,
2742 'comment_count': int,
2743 'channel': 'Christopher Sykes',
2744 'live_status': 'not_live',
2745 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2746 'availability': 'public',
2747 'duration': 195,
2748 'view_count': int,
2749 'categories': ['Science & Technology'],
2750 'channel_follower_count': int,
7666b936 2751 'uploader': 'Christopher Sykes',
2752 'uploader_url': 'https://www.youtube.com/@ChristopherSykesDocumentaries',
2753 'uploader_id': '@ChristopherSykesDocumentaries',
14a14335 2754 'heatmap': 'count:100',
f2e8dbcc 2755 },
2756 'params': {
2757 'skip_download': True,
2758 }
2759 },
2760 ]
2761
201c1459 2762 @classmethod
2763 def suitable(cls, url):
4dfbf869 2764 from ..utils import parse_qs
2765
201c1459 2766 qs = parse_qs(url)
2767 if qs.get('list', [None])[0]:
2768 return False
86e5f3ed 2769 return super().suitable(url)
201c1459 2770
e0df6211 2771 def __init__(self, *args, **kwargs):
86e5f3ed 2772 super().__init__(*args, **kwargs)
545cc85d 2773 self._code_cache = {}
83799698 2774 self._player_cache = {}
e0df6211 2775
4d37720a 2776 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
adbc4ec4 2777 lock = threading.Lock()
185bf310 2778 start_time = time.time()
adbc4ec4
THD
2779 formats = [f for f in formats if f.get('is_from_start')]
2780
185bf310 2781 def refetch_manifest(format_id, delay):
2782 nonlocal formats, start_time, is_live
2783 if time.time() <= start_time + delay:
adbc4ec4
THD
2784 return
2785
2786 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
6839ae1f 2787 video_details = traverse_obj(prs, (..., 'videoDetails'), expected_type=dict)
adbc4ec4
THD
2788 microformats = traverse_obj(
2789 prs, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 2790 expected_type=dict)
4d37720a
L
2791 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2792 is_live = live_status == 'is_live'
185bf310 2793 start_time = time.time()
adbc4ec4 2794
185bf310 2795 def mpd_feed(format_id, delay):
adbc4ec4
THD
2796 """
2797 @returns (manifest_url, manifest_stream_number, is_live) or None
2798 """
253ac4ba 2799 for retry in self.RetryManager(fatal=False):
2800 with lock:
2801 refetch_manifest(format_id, delay)
2802
2803 f = next((f for f in formats if f['format_id'] == format_id), None)
2804 if not f:
2805 if not is_live:
2806 retry.error = f'{video_id}: Video is no longer live'
2807 else:
2808 retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
2809 continue
2810 return f['manifest_url'], f['manifest_stream_number'], is_live
2811 return None
adbc4ec4
THD
2812
2813 for f in formats:
4d37720a
L
2814 f['is_live'] = is_live
2815 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2816 live_start_time, mpd_feed, not is_live and f.copy())
2817 if is_live:
2818 f['fragments'] = gen
2819 f['protocol'] = 'http_dash_segments_generator'
2820 else:
2821 f['fragments'] = LazyList(gen({}))
2822 del f['is_from_start']
adbc4ec4 2823
4d37720a 2824 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
adbc4ec4
THD
2825 FETCH_SPAN, MAX_DURATION = 5, 432000
2826
2827 mpd_url, stream_number, is_live = None, None, True
2828
2829 begin_index = 0
2830 download_start_time = ctx.get('start') or time.time()
2831
2832 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2833 if lack_early_segments:
2834 self.report_warning(bug_reports_message(
2835 'Starting download from the last 120 hours of the live stream since '
2836 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2837 lack_early_segments = True
2838
2839 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2840 fragments, fragment_base_url = None, None
2841
a539f065 2842 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2843 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2844 # Obtain from MPD's maximum seq value
2845 old_mpd_url = mpd_url
185bf310 2846 last_error = ctx.pop('last_error', None)
3d2623a8 2847 expire_fast = immediate or last_error and isinstance(last_error, HTTPError) and last_error.status == 403
185bf310 2848 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2849 or (mpd_url, stream_number, False))
2850 if not refresh_sequence:
2851 if expire_fast and not is_live:
2852 return False, last_seq
2853 elif old_mpd_url == mpd_url:
2854 return True, last_seq
4d37720a
L
2855 if manifestless_orig_fmt:
2856 fmt_info = manifestless_orig_fmt
2857 else:
2858 try:
2859 fmts, _ = self._extract_mpd_formats_and_subtitles(
2860 mpd_url, None, note=False, errnote=False, fatal=False)
2861 except ExtractorError:
2862 fmts = None
2863 if not fmts:
2864 no_fragment_score += 2
2865 return False, last_seq
2866 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
adbc4ec4
THD
2867 fragments = fmt_info['fragments']
2868 fragment_base_url = fmt_info['fragment_base_url']
2869 assert fragment_base_url
2870
2871 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2872 return True, _last_seq
2873
4d37720a 2874 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
adbc4ec4
THD
2875 while is_live:
2876 fetch_time = time.time()
2877 if no_fragment_score > 30:
2878 return
2879 if last_segment_url:
2880 # Obtain from "X-Head-Seqnum" header value from each segment
2881 try:
2882 urlh = self._request_webpage(
2883 last_segment_url, None, note=False, errnote=False, fatal=False)
2884 except ExtractorError:
2885 urlh = None
2886 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2887 if last_seq is None:
a539f065 2888 no_fragment_score += 2
adbc4ec4
THD
2889 last_segment_url = None
2890 continue
2891 else:
a539f065
LNO
2892 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2893 no_fragment_score += 2
185bf310 2894 if not should_continue:
adbc4ec4
THD
2895 continue
2896
2897 if known_idx > last_seq:
2898 last_segment_url = None
2899 continue
2900
2901 last_seq += 1
2902
2903 if begin_index < 0 and known_idx < 0:
2904 # skip from the start when it's negative value
2905 known_idx = last_seq + begin_index
2906 if lack_early_segments:
2907 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2908 try:
2909 for idx in range(known_idx, last_seq):
2910 # do not update sequence here or you'll get skipped some part of it
a539f065 2911 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2912 if not should_continue:
adbc4ec4
THD
2913 known_idx = idx - 1
2914 raise ExtractorError('breaking out of outer loop')
2915 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2916 yield {
2917 'url': last_segment_url,
36195c44 2918 'fragment_count': last_seq,
adbc4ec4
THD
2919 }
2920 if known_idx == last_seq:
2921 no_fragment_score += 5
2922 else:
2923 no_fragment_score = 0
2924 known_idx = last_seq
2925 except ExtractorError:
2926 continue
2927
4d37720a
L
2928 if manifestless_orig_fmt:
2929 # Stop at the first iteration if running for post-live manifestless;
2930 # fragment count no longer increase since it starts
2931 break
2932
adbc4ec4
THD
2933 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2934
b6de707d 2935 def _extract_player_url(self, *ytcfgs, webpage=None):
2936 player_url = traverse_obj(
2937 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2938 get_all=False, expected_type=str)
11f9be09 2939 if not player_url:
b6de707d 2940 return
60f393e4 2941 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2942
b6de707d 2943 def _download_player_url(self, video_id, fatal=False):
2944 res = self._download_webpage(
2945 'https://www.youtube.com/iframe_api',
2946 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2947 if res:
2948 player_version = self._search_regex(
2949 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2950 if player_version:
2951 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2952
60064c53
PH
2953 def _signature_cache_id(self, example_sig):
2954 """ Return a string representation of a signature """
14f25df2 2955 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2956
e40c758c
S
2957 @classmethod
2958 def _extract_player_info(cls, player_url):
2959 for player_re in cls._PLAYER_INFO_RE:
2960 id_m = re.search(player_re, player_url)
2961 if id_m:
2962 break
2963 else:
c081b35c 2964 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2965 return id_m.group('id')
e40c758c 2966
404f611f 2967 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2968 player_id = self._extract_player_info(player_url)
2969 if player_id not in self._code_cache:
1276a43a 2970 code = self._download_webpage(
109dd3b2 2971 player_url, video_id, fatal=fatal,
2972 note='Downloading player ' + player_id,
2973 errnote='Download of %s failed' % player_url)
1276a43a 2974 if code:
2975 self._code_cache[player_id] = code
404f611f 2976 return self._code_cache.get(player_id)
109dd3b2 2977
e40c758c 2978 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2979 player_id = self._extract_player_info(player_url)
e0df6211 2980
c4417ddb 2981 # Read from filesystem cache
86e5f3ed 2982 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2983 assert os.path.basename(func_id) == func_id
a0e07d31 2984
ae61d108 2985 self.write_debug(f'Extracting signature function {func_id}')
580ce007 2986 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 2987
580ce007 2988 if not cache_spec:
2989 code = self._load_player(video_id, player_url)
404f611f 2990 if code:
109dd3b2 2991 res = self._parse_sig_js(code)
ac668111 2992 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 2993 cache_spec = [ord(c) for c in res(test_string)]
9809740b 2994 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 2995
2996 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2997
60064c53 2998 def _print_sig_code(self, func, example_sig):
404f611f 2999 if not self.get_param('youtube_print_sig_code'):
3000 return
3001
edf3e38e
PH
3002 def gen_sig_code(idxs):
3003 def _genslice(start, end, step):
78caa52a 3004 starts = '' if start == 0 else str(start)
8bcc8756 3005 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 3006 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 3007 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
3008
3009 step = None
7af808a5
PH
3010 # Quelch pyflakes warnings - start will be set when step is set
3011 start = '(Never used)'
edf3e38e
PH
3012 for i, prev in zip(idxs[1:], idxs[:-1]):
3013 if step is not None:
3014 if i - prev == step:
3015 continue
3016 yield _genslice(start, prev, step)
3017 step = None
3018 continue
3019 if i - prev in [-1, 1]:
3020 step = i - prev
3021 start = prev
3022 continue
3023 else:
78caa52a 3024 yield 's[%d]' % prev
edf3e38e 3025 if step is None:
78caa52a 3026 yield 's[%d]' % i
edf3e38e
PH
3027 else:
3028 yield _genslice(start, i, step)
3029
ac668111 3030 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 3031 cache_res = func(test_string)
edf3e38e 3032 cache_spec = [ord(c) for c in cache_res]
78caa52a 3033 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 3034 signature_id_tuple = '(%s)' % (
14f25df2 3035 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 3036 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 3037 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 3038 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 3039
e0df6211
PH
3040 def _parse_sig_js(self, jscode):
3041 funcname = self._search_regex(
abefc03f
S
3042 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3043 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
3044 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
3045 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
4823ec9f 3046 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 3047 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f 3048 # Obsolete patterns
4823ec9f 3049 r'("|\')signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 3050 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
3051 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3052 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3053 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f 3054 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 3055 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
3056
3057 jsi = JSInterpreter(jscode)
3058 initial_function = jsi.extract_function(funcname)
e0df6211
PH
3059 return lambda s: initial_function([s])
3060
580ce007 3061 def _cached(self, func, *cache_id):
3062 def inner(*args, **kwargs):
3063 if cache_id not in self._player_cache:
3064 try:
3065 self._player_cache[cache_id] = func(*args, **kwargs)
3066 except ExtractorError as e:
3067 self._player_cache[cache_id] = e
3068 except Exception as e:
3069 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
3070
3071 ret = self._player_cache[cache_id]
3072 if isinstance(ret, Exception):
3073 raise ret
3074 return ret
3075 return inner
3076
545cc85d 3077 def _decrypt_signature(self, s, video_id, player_url):
257a2501 3078 """Turn the encrypted s field into a working signature"""
580ce007 3079 extract_sig = self._cached(
3080 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
3081 func = extract_sig(video_id, player_url, s)
3082 self._print_sig_code(func, s)
3083 return func(s)
404f611f 3084
3085 def _decrypt_nsig(self, s, video_id, player_url):
3086 """Turn the encrypted n field into a working signature"""
3087 if player_url is None:
3088 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 3089 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 3090
b505e851 3091 try:
3092 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
3093 except ExtractorError as e:
3094 raise ExtractorError('Unable to extract nsig function code', cause=e)
580ce007 3095 if self.get_param('youtube_print_sig_code'):
3096 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 3097
25836db6 3098 try:
3099 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
3100 ret = extract_nsig(jsi, func_code)(s)
3101 except JSInterpreter.Exception as e:
3102 try:
992dc6b4 3103 jsi = PhantomJSwrapper(self, timeout=5000)
25836db6 3104 except ExtractorError:
3105 raise e
3106 self.report_warning(
3107 f'Native nsig extraction failed: Trying with PhantomJS\n'
3108 f' n = {s} ; player = {player_url}', video_id)
0468a3b3 3109 self.write_debug(e, only_once=True)
25836db6 3110
3111 args, func_body = func_code
3112 ret = jsi.execute(
3113 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
3114 video_id=video_id, note='Executing signature code').strip()
580ce007 3115
3116 self.write_debug(f'Decrypted nsig {s} => {ret}')
3117 return ret
3118
90a1df30 3119 def _extract_n_function_name(self, jscode):
3120 funcname, idx = self._search_regex(
3121 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
3122 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
3123 if not idx:
3124 return funcname
3125
3126 return json.loads(js_to_json(self._search_regex(
337734d4 3127 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])\s*[,;]', jscode,
90a1df30 3128 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
3129
580ce007 3130 def _extract_n_function_code(self, video_id, player_url):
404f611f 3131 player_id = self._extract_player_info(player_url)
05deb747 3132 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
580ce007 3133 jscode = func_code or self._load_player(video_id, player_url)
3134 jsi = JSInterpreter(jscode)
404f611f 3135
3136 if func_code:
580ce007 3137 return jsi, player_id, func_code
404f611f 3138
b505e851 3139 func_name = self._extract_n_function_name(jscode)
3140
3141 # For redundancy
3142 func_code = self._search_regex(
3143 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
3144 # NB: The end of the regex is intentionally kept strict
3145 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
3146 jscode, 'nsig function', group=('var', 'code'), default=None)
3147 if func_code:
3148 func_code = ([func_code[0]], func_code[1])
3149 else:
3150 self.write_debug('Extracting nsig function with jsinterp')
3151 func_code = jsi.extract_function_code(func_name)
3152
580ce007 3153 self.cache.store('youtube-nsig', player_id, func_code)
3154 return jsi, player_id, func_code
3155
3156 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 3157 func = jsi.extract_function_from_code(*func_code)
f6ca640b 3158
580ce007 3159 def extract_nsig(s):
25836db6 3160 try:
3161 ret = func([s])
3162 except JSInterpreter.Exception:
3163 raise
3164 except Exception as e:
3165 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
3166
f6ca640b 3167 if ret.startswith('enhanced_except_'):
25836db6 3168 raise JSInterpreter.Exception('Signature function returned an exception')
f6ca640b 3169 return ret
580ce007 3170
3171 return extract_nsig
e0df6211 3172
109dd3b2 3173 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
3174 """
3175 Extract signatureTimestamp (sts)
3176 Required to tell API what sig/player version is in use.
3177 """
3178 sts = None
3179 if isinstance(ytcfg, dict):
3180 sts = int_or_none(ytcfg.get('STS'))
3181
3182 if not sts:
3183 # Attempt to extract from player
3184 if player_url is None:
3185 error_msg = 'Cannot extract signature timestamp without player_url.'
3186 if fatal:
3187 raise ExtractorError(error_msg)
3188 self.report_warning(error_msg)
3189 return
404f611f 3190 code = self._load_player(video_id, player_url, fatal=fatal)
3191 if code:
109dd3b2 3192 sts = int_or_none(self._search_regex(
3193 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
3194 'JS player signature timestamp', group='sts', fatal=fatal))
3195 return sts
3196
11f9be09 3197 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
3198 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
3199 label = 'fully ' if is_full else ''
3200 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
3201 expected_type=url_or_none)
3202 if not url:
3203 self.report_warning(f'Unable to mark {label}watched')
3204 return
14f25df2 3205 parsed_url = urllib.parse.urlparse(url)
3206 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
3207
3208 # cpn generation algorithm is reverse engineered from base.js.
3209 # In fact it works even with dummy cpn.
3210 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
3211 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
3212
3213 # # more consistent results setting it to right before the end
3214 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
3215
3216 qs.update({
3217 'ver': ['2'],
3218 'cpn': [cpn],
3219 'cmt': video_length,
3220 'el': 'detailpage', # otherwise defaults to "shorts"
3221 })
3222
3223 if is_full:
3224 # these seem to mark watchtime "history" in the real world
3225 # they're required, so send in a single value
3226 qs.update({
5318156f 3227 'st': 0,
06cc8f10
B
3228 'et': video_length,
3229 })
3230
14f25df2 3231 url = urllib.parse.urlunparse(
3232 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
3233
3234 self._download_webpage(
3235 url, video_id, f'Marking {label}watched',
3236 'Unable to mark watched', fatal=False)
d77ab8e2 3237
bfd973ec 3238 @classmethod
3239 def _extract_from_webpage(cls, url, webpage):
3240 # Invidious Instances
3241 # https://github.com/yt-dlp/yt-dlp/issues/195
3242 # https://github.com/iv-org/invidious/pull/1730
3243 mobj = re.search(
3244 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
3245 webpage)
3246 if mobj:
3247 yield cls.url_result(mobj.group('url'), cls)
3248 raise cls.StopExtraction()
3249
3250 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
3251
3252 # lazyYT YouTube embed
bfd973ec 3253 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3254 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
3255
3256 # Wordpress "YouTube Video Importer" plugin
bfd973ec 3257 for m in re.findall(r'''(?x)<div[^>]+
3258 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
3259 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
3260 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 3261
97665381
PH
3262 @classmethod
3263 def extract_id(cls, url):
ae61d108 3264 video_id = cls.get_temp_id(url)
3265 if not video_id:
3266 raise ExtractorError(f'Invalid URL: {url}')
3267 return video_id
c5e8d7af 3268
7c365c21 3269 def _extract_chapters_from_json(self, data, duration):
3270 chapter_list = traverse_obj(
3271 data, (
3272 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3273 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3274 ), expected_type=list)
3275
22ccd542 3276 return self._extract_chapters_helper(
7c365c21 3277 chapter_list,
22ccd542 3278 start_function=lambda chapter: float_or_none(
7c365c21 3279 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
22ccd542 3280 title_function=lambda chapter: traverse_obj(
7c365c21 3281 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3282 duration=duration)
3283
3284 def _extract_chapters_from_engagement_panel(self, data, duration):
3285 content_list = traverse_obj(
8bdd16b4 3286 data,
7c365c21 3287 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
6839ae1f 3288 expected_type=list)
052e1350 3289 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3290 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 3291
1890fc63 3292 return next(filter(None, (
22ccd542 3293 self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3294 chapter_time, chapter_title, duration)
1890fc63 3295 for contents in content_list)), [])
7c365c21 3296
03e85ea9 3297 def _extract_heatmap(self, data):
3298 return traverse_obj(data, (
3299 'frameworkUpdates', 'entityBatchUpdate', 'mutations',
3300 lambda _, v: v['payload']['macroMarkersListEntity']['markersList']['markerType'] == 'MARKER_TYPE_HEATMAP',
3301 'payload', 'macroMarkersListEntity', 'markersList', 'markers', ..., {
3302 'start_time': ('startMillis', {functools.partial(float_or_none, scale=1000)}),
3303 'end_time': {lambda x: (int(x['startMillis']) + int(x['durationMillis'])) / 1000},
3304 'value': ('intensityScoreNormalized', {float_or_none}),
3305 })) or None
5caf30db 3306
a1c5d2ca
M
3307 def _extract_comment(self, comment_renderer, parent=None):
3308 comment_id = comment_renderer.get('commentId')
3309 if not comment_id:
3310 return
fe93e2c4 3311
c35448b7 3312 info = {
3313 'id': comment_id,
3314 'text': self._get_text(comment_renderer, 'contentText'),
3315 'like_count': self._get_count(comment_renderer, 'voteCount'),
3316 'author_id': traverse_obj(comment_renderer, ('authorEndpoint', 'browseEndpoint', 'browseId', {self.ucid_or_none})),
3317 'author': self._get_text(comment_renderer, 'authorText'),
3318 'author_thumbnail': traverse_obj(comment_renderer, ('authorThumbnail', 'thumbnails', -1, 'url', {url_or_none})),
3319 'parent': parent or 'root',
3320 }
fe93e2c4 3321
c26f9b99 3322 # Timestamp is an estimate calculated from the current time and time_text
3323 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3324 timestamp = self._parse_time_text(time_text)
3325
c35448b7 3326 info.update({
3327 # FIXME: non-standard, but we need a way of showing that it is an estimate.
3328 '_time_text': time_text,
3329 'timestamp': timestamp,
3330 })
fe93e2c4 3331
c35448b7 3332 info['author_url'] = urljoin(
3333 'https://www.youtube.com', traverse_obj(comment_renderer, ('authorEndpoint', (
3334 ('browseEndpoint', 'canonicalBaseUrl'), ('commandMetadata', 'webCommandMetadata', 'url'))),
3335 expected_type=str, get_all=False))
a1c5d2ca 3336
c35448b7 3337 author_is_uploader = traverse_obj(comment_renderer, 'authorIsChannelOwner')
3338 if author_is_uploader is not None:
3339 info['author_is_uploader'] = author_is_uploader
3340
3341 comment_abr = traverse_obj(
89bed013 3342 comment_renderer, ('actionButtons', 'commentActionButtonsRenderer'), expected_type=dict)
c35448b7 3343 if comment_abr is not None:
3344 info['is_favorited'] = 'creatorHeart' in comment_abr
3345
14a14335 3346 badges = self._extract_badges([traverse_obj(comment_renderer, 'authorCommentBadge')])
3347 if self._has_badge(badges, BadgeType.VERIFIED):
3348 info['author_is_verified'] = True
c35448b7 3349
3350 is_pinned = traverse_obj(comment_renderer, 'pinnedCommentBadge')
3351 if is_pinned:
3352 info['is_pinned'] = True
3353
3354 return info
a1c5d2ca 3355
46383212 3356 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3357
3358 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 3359
3360 def extract_header(contents):
2d6659b9 3361 _continuation = None
3362 for content in contents:
46383212 3363 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 3364 expected_comment_count = self._get_count(
3365 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 3366
18f8fba7 3367 if expected_comment_count is not None:
46383212 3368 tracker['est_total'] = expected_comment_count
3369 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3370 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 3371
3372 sort_menu_item = try_get(
3373 comments_header_renderer,
3374 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3375 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3376
3377 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3378 if not _continuation:
3379 continue
3380
46383212 3381 sort_text = str_or_none(sort_menu_item.get('title'))
3382 if not sort_text:
2d6659b9 3383 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 3384 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 3385 break
a2160aa4 3386 return _continuation
a1c5d2ca 3387
2d6659b9 3388 def extract_thread(contents):
a1c5d2ca 3389 if not parent:
46383212 3390 tracker['current_page_thread'] = 0
a1c5d2ca 3391 for content in contents:
46383212 3392 if not parent and tracker['total_parent_comments'] >= max_parents:
3393 yield
a1c5d2ca 3394 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 3395 comment_renderer = get_first(
3396 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3397 expected_type=dict, default={})
a1c5d2ca 3398
a1c5d2ca
M
3399 comment = self._extract_comment(comment_renderer, parent)
3400 if not comment:
3401 continue
141a8dff 3402 comment_id = comment['id']
c35448b7 3403 if comment.get('is_pinned'):
141a8dff 3404 tracker['pinned_comment_ids'].add(comment_id)
7f51861b 3405 # Sometimes YouTube may break and give us infinite looping comments.
3406 # See: https://github.com/yt-dlp/yt-dlp/issues/6290
141a8dff 3407 if comment_id in tracker['seen_comment_ids']:
c35448b7 3408 if comment_id in tracker['pinned_comment_ids'] and not comment.get('is_pinned'):
141a8dff 3409 # Pinned comments may appear a second time in newest first sort
3410 # See: https://github.com/yt-dlp/yt-dlp/issues/6712
3411 continue
4dc4d847 3412 self.report_warning(
3413 'Detected YouTube comments looping. Stopping comment extraction '
3414 f'{"for this thread" if parent else ""} as we probably cannot get any more.')
7f51861b 3415 yield
3416 else:
3417 tracker['seen_comment_ids'].add(comment['id'])
46383212 3418
3419 tracker['running_total'] += 1
3420 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 3421 yield comment
46383212 3422
a1c5d2ca
M
3423 # Attempt to get the replies
3424 comment_replies_renderer = try_get(
3425 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3426
3427 if comment_replies_renderer:
46383212 3428 tracker['current_page_thread'] += 1
a1c5d2ca 3429 comment_entries_iter = self._comment_entries(
99e9e001 3430 comment_replies_renderer, ytcfg, video_id,
46383212 3431 parent=comment.get('id'), tracker=tracker)
86e5f3ed 3432 yield from itertools.islice(comment_entries_iter, min(
3433 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 3434
46383212 3435 # Keeps track of counts across recursive calls
3436 if not tracker:
3437 tracker = dict(
3438 running_total=0,
18f8fba7 3439 est_total=None,
46383212 3440 current_page_thread=0,
3441 total_parent_comments=0,
7f51861b 3442 total_reply_comments=0,
141a8dff 3443 seen_comment_ids=set(),
3444 pinned_comment_ids=set()
3445 )
46383212 3446
3447 # TODO: Deprecated
2d6659b9 3448 # YouTube comments have a max depth of 2
46383212 3449 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3450 if max_depth:
da4db748 3451 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3452 'Set max replies in the max-comments extractor argument instead')
2d6659b9 3453 if max_depth == 1 and parent:
3454 return
a1c5d2ca 3455
46383212 3456 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3457 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 3458
46383212 3459 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 3460
46383212 3461 response = None
6e634cbe 3462 is_forced_continuation = False
2d6659b9 3463 is_first_continuation = parent is None
6e634cbe 3464 if is_first_continuation and not continuation:
3465 # Sometimes you can get comments by generating the continuation yourself,
3466 # even if YouTube initially reports them being disabled - e.g. stories comments.
3467 # Note: if the comment section is actually disabled, YouTube may return a response with
3468 # required check_get_keys missing. So we will disable that check initially in this case.
3469 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3470 is_forced_continuation = True
a1c5d2ca 3471
18f8fba7 3472 continuation_items_path = (
3473 'onResponseReceivedEndpoints', ..., ('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems')
a1c5d2ca
M
3474 for page_num in itertools.count(0):
3475 if not continuation:
3476 break
46383212 3477 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
18f8fba7 3478 comment_prog_str = f"({tracker['running_total']}/~{tracker['est_total']})"
2d6659b9 3479 if page_num == 0:
3480 if is_first_continuation:
3481 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 3482 else:
2d6659b9 3483 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 3484 tracker['current_page_thread'], comment_prog_str)
2d6659b9 3485 else:
3486 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3487 ' ' if parent else '', ' replies' if parent else '',
3488 page_num, comment_prog_str)
18f8fba7 3489
3490 # Do a deep check for incomplete data as sometimes YouTube may return no comments for a continuation
3491 # Ignore check if YouTube says the comment count is 0.
3492 check_get_keys = None
3493 if not is_forced_continuation and not (tracker['est_total'] == 0 and tracker['running_total'] == 0):
3494 check_get_keys = [[*continuation_items_path, ..., (
3495 'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentRenderer'))]]
e72e48c5
M
3496 try:
3497 response = self._extract_response(
3498 item_id=None, query=continuation,
3499 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
18f8fba7 3500 check_get_keys=check_get_keys)
e72e48c5
M
3501 except ExtractorError as e:
3502 # Ignore incomplete data error for replies if retries didn't work.
3503 # This is to allow any other parent comments and comment threads to be downloaded.
3504 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
4dc4d847 3505 if 'incomplete data' in str(e).lower() and parent:
3506 if self.get_param('ignoreerrors') in (True, 'only_download'):
3507 self.report_warning(
3508 'Received incomplete data for a comment reply thread and retrying did not help. '
3509 'Ignoring to let other comments be downloaded. Pass --no-ignore-errors to not ignore.')
3510 return
3511 else:
3512 raise ExtractorError(
3513 'Incomplete data received for comment reply thread. '
3514 'Pass --ignore-errors to ignore and allow rest of comments to download.',
3515 expected=True)
3516 raise
6e634cbe 3517 is_forced_continuation = False
2d6659b9 3518 continuation = None
18f8fba7 3519 for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]):
46383212 3520 if is_first_continuation:
3521 continuation = extract_header(continuation_items)
3522 is_first_continuation = False
2d6659b9 3523 if continuation:
a1c5d2ca 3524 break
46383212 3525 continue
a1c5d2ca 3526
46383212 3527 for entry in extract_thread(continuation_items):
3528 if not entry:
3529 return
3530 yield entry
3531 continuation = self._extract_continuation({'contents': continuation_items})
3532 if continuation:
2d6659b9 3533 break
a1c5d2ca 3534
6e634cbe 3535 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3536 if message and not parent and tracker['running_total'] == 0:
3537 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
0cf643b2 3538 raise self.CommentsDisabled
6e634cbe 3539
3540 @staticmethod
3541 def _generate_comment_continuation(video_id):
3542 """
3543 Generates initial comment section continuation token from given video id
3544 """
3545 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3546 return base64.b64encode(token.encode()).decode()
3547
a2160aa4 3548 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3549 """Entry for comment extraction"""
2d6659b9 3550 def _real_comment_extract(contents):
aae16f6e 3551 renderer = next((
3552 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3553 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3554 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3555
a2160aa4 3556 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3557 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3558
109dd3b2 3559 @staticmethod
99e9e001 3560 def _get_checkok_params():
3561 return {'contentCheckOk': True, 'racyCheckOk': True}
3562
3563 @classmethod
3564 def _generate_player_context(cls, sts=None):
109dd3b2 3565 context = {
3566 'html5Preference': 'HTML5_PREF_WANTS',
3567 }
3568 if sts is not None:
3569 context['signatureTimestamp'] = sts
3570 return {
3571 'playbackContext': {
3572 'contentPlaybackContext': context
a1a7907b 3573 },
99e9e001 3574 **cls._get_checkok_params()
109dd3b2 3575 }
3576
e7e94f2a
D
3577 @staticmethod
3578 def _is_agegated(player_response):
3579 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3580 return True
e7e94f2a 3581
6839ae1f 3582 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')))
e7e94f2a
D
3583 AGE_GATE_REASONS = (
3584 'confirm your age', 'age-restricted', 'inappropriate', # reason
3585 'age_verification_required', 'age_check_required', # status
3586 )
3587 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3588
3589 @staticmethod
3590 def _is_unplayable(player_response):
3591 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3592
50ac0e54 3593 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3594
11f9be09 3595 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3596 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3597 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3598 headers = self.generate_api_headers(
99e9e001 3599 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3600
6e634cbe 3601 yt_query = {
3602 'videoId': video_id,
6e634cbe 3603 }
90db9a3c 3604 if _split_innertube_client(client)[0] == 'android':
ba06d77a 3605 yt_query['params'] = 'CgIQBg=='
3606
546b2c28 3607 pp_arg = self._configuration_arg('player_params', [None], casesense=True)[0]
ba06d77a 3608 if pp_arg:
3609 yt_query['params'] = pp_arg
50ac0e54 3610
11f9be09 3611 yt_query.update(self._generate_player_context(sts))
3612 return self._extract_response(
3613 item_id=video_id, ep='player', query=yt_query,
379e44ed 3614 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3615 default_client=client,
11f9be09 3616 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3617 ) or None
3618
11f9be09 3619 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3620 requested_clients = []
fd8fcf8f 3621 default = ['ios', 'android', 'web']
000c15a4 3622 allowed_clients = sorted(
86e5f3ed 3623 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3624 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3625 for client in self._configuration_arg('player_client'):
3626 if client in allowed_clients:
3627 requested_clients.append(client)
d0d012d4 3628 elif client == 'default':
3629 requested_clients.extend(default)
b4c055ba 3630 elif client == 'all':
3631 requested_clients.extend(allowed_clients)
3632 else:
3633 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3634 if not requested_clients:
d0d012d4 3635 requested_clients = default
cf7e015f 3636
11f9be09 3637 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3638 requested_clients.extend(
e7e94f2a 3639 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3640
11f9be09 3641 return orderedSet(requested_clients)
cf7e015f 3642
50ac0e54 3643 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3644 initial_pr = None
3645 if webpage:
b7c47b74 3646 initial_pr = self._search_json(
3647 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3648
ae729626 3649 all_clients = set(clients)
c0bc527b 3650 clients = clients[::-1]
b6de707d 3651 prs = []
e7e94f2a 3652
ae729626 3653 def append_client(*client_names):
e7870111 3654 """ Append the first client name that exists but not already used """
ae729626 3655 for client_name in client_names:
e7870111
D
3656 actual_client = _split_innertube_client(client_name)[0]
3657 if actual_client in INNERTUBE_CLIENTS:
3658 if actual_client not in all_clients:
ae729626 3659 clients.append(client_name)
e7870111
D
3660 all_clients.add(actual_client)
3661 return
e7e94f2a 3662
379e44ed 3663 # Android player_response does not have microFormats which are needed for
3664 # extraction of some data. So we return the initial_pr with formats
3665 # stripped out even if not requested by the user
3666 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3667 if initial_pr:
3668 pr = dict(initial_pr)
3669 pr['streamingData'] = None
b6de707d 3670 prs.append(pr)
379e44ed 3671
3672 last_error = None
b6de707d 3673 tried_iframe_fallback = False
3674 player_url = None
c0bc527b 3675 while clients:
e7870111 3676 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3677 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3678 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3679 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3680
b6de707d 3681 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3682 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3683 if 'js' in self._configuration_arg('player_skip'):
3684 require_js_player = False
3685 player_url = None
3686
3687 if not player_url and not tried_iframe_fallback and require_js_player:
3688 player_url = self._download_player_url(video_id)
3689 tried_iframe_fallback = True
3690
379e44ed 3691 try:
3692 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3693 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3694 except ExtractorError as e:
3695 if last_error:
3696 self.report_warning(last_error)
3697 last_error = e
3698 continue
3699
11f9be09 3700 if pr:
a3e96421 3701 # YouTube may return a different video player response than expected.
3702 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3703 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3704 if pr_video_id and pr_video_id != video_id:
3705 self.report_warning(
c7dcf0b3 3706 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3707 else:
c795c39f
L
3708 # Save client name for introspection later
3709 name = short_client_name(client)
3710 sd = traverse_obj(pr, ('streamingData', {dict})) or {}
3711 sd[STREAMING_DATA_CLIENT_NAME] = name
3712 for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})):
3713 f[STREAMING_DATA_CLIENT_NAME] = name
a3e96421 3714 prs.append(pr)
c0bc527b 3715
e7e94f2a 3716 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3717 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3718 append_client(f'{base_client}_creator')
e7e94f2a 3719 elif self._is_agegated(pr):
e7870111
D
3720 if variant == 'tv_embedded':
3721 append_client(f'{base_client}_embedded')
3722 elif not variant:
3723 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3724
379e44ed 3725 if last_error:
b6de707d 3726 if not len(prs):
379e44ed 3727 raise last_error
3728 self.report_warning(last_error)
b6de707d 3729 return prs, player_url
11f9be09 3730
4d37720a
L
3731 def _needs_live_processing(self, live_status, duration):
3732 if (live_status == 'is_live' and self.get_param('live_from_start')
d949c10c 3733 or live_status == 'post_live' and (duration or 0) > 2 * 3600):
4d37720a
L
3734 return live_status
3735
3736 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
e389d172 3737 CHUNK_SIZE = 10 << 20
a4894d3e 3738 itags, stream_ids = collections.defaultdict(set), []
b25cac65 3739 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3740 q = qualities([
2a9c6dcd 3741 # Normally tiny is the smallest video-only formats. But
3742 # audio-only formats with unknown quality may get tagged as tiny
3743 'tiny',
3744 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3745 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3746 ])
6839ae1f 3747 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
58786a10 3748 format_types = self._configuration_arg('formats')
3749 all_formats = 'duplicate' in format_types
3750 if self._configuration_arg('include_duplicate_formats'):
3751 all_formats = True
3752 self._downloader.deprecated_feature('[youtube] include_duplicate_formats extractor argument is deprecated. '
3753 'Use formats=duplicate extractor argument instead')
9297939e 3754
e389d172 3755 def build_fragments(f):
3756 return LazyList({
3757 'url': update_url_query(f['url'], {
3758 'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, f["filesize"])}'
3759 })
3760 } for range_start in range(0, f['filesize'], CHUNK_SIZE))
3761
545cc85d 3762 for fmt in streaming_formats:
727029c5 3763 if fmt.get('targetDurationSec'):
545cc85d 3764 continue
321bf820 3765
cc2db878 3766 itag = str_or_none(fmt.get('itag'))
9297939e 3767 audio_track = fmt.get('audioTrack') or {}
9bb85699 3768 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
86cb9221 3769 if not all_formats:
3770 if stream_id in stream_ids:
3771 continue
9297939e 3772
cc2db878 3773 quality = fmt.get('quality')
2a9c6dcd 3774 height = int_or_none(fmt.get('height'))
d3fc8074 3775 if quality == 'tiny' or not quality:
3776 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3777 # The 3gp format (17) in android client has a quality of "small",
3778 # but is actually worse than other formats
3779 if itag == '17':
3780 quality = 'tiny'
3781 if quality:
3782 if itag:
3783 itag_qualities[itag] = quality
3784 if height:
3785 res_qualities[height] = quality
cc2db878 3786 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3787 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3788 # number of fragment that would subsequently requested with (`&sq=N`)
3789 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3790 continue
3791
545cc85d 3792 fmt_url = fmt.get('url')
3793 if not fmt_url:
14f25df2 3794 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3795 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3796 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3797 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3798 continue
52023f12 3799 try:
3800 fmt_url += '&%s=%s' % (
3801 traverse_obj(sc, ('sp', -1)) or 'signature',
3802 self._decrypt_signature(encrypted_sig, video_id, player_url)
3803 )
3804 except ExtractorError as e:
580ce007 3805 self.report_warning('Signature extraction failed: Some formats may be missing',
3806 video_id=video_id, only_once=True)
52023f12 3807 self.write_debug(e, only_once=True)
201e9eaa 3808 continue
545cc85d 3809
404f611f 3810 query = parse_qs(fmt_url)
3811 throttled = False
b2916526 3812 if query.get('n'):
404f611f 3813 try:
580ce007 3814 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3815 fmt_url = update_url_query(fmt_url, {
580ce007 3816 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3817 })
404f611f 3818 except ExtractorError as e:
25836db6 3819 phantomjs_hint = ''
3820 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3821 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3822 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
17ffed18 3823 if player_url:
3824 self.report_warning(
3825 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3826 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3827 self.write_debug(e, only_once=True)
3828 else:
3829 self.report_warning(
3830 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3831 video_id=video_id, only_once=True)
404f611f 3832 throttled = True
3833
0ad92dfb 3834 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3835 language_preference = (
3836 10 if audio_track.get('audioIsDefault') and 10
3837 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3838 else -1)
0ad92dfb 3839 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3840 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3841 # Make sure to avoid false positives with small duration differences.
62b58c09 3842 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3843 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3844 if is_damaged:
0f06bcd7 3845 self.report_warning(
3846 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
c795c39f
L
3847
3848 client_name = fmt.get(STREAMING_DATA_CLIENT_NAME)
51a07b0d 3849 name = fmt.get('qualityLabel') or quality.replace('audio_quality_', '') or ''
97afb093 3850 fps = int_or_none(fmt.get('fps')) or 0
545cc85d 3851 dct = {
3852 'asr': int_or_none(fmt.get('audioSampleRate')),
3853 'filesize': int_or_none(fmt.get('contentLength')),
9bb85699 3854 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
34921b43 3855 'format_note': join_nonempty(
392389b7 3856 join_nonempty(audio_track.get('displayName'),
3857 language_preference > 0 and ' (default)', delim=''),
51a07b0d 3858 name, fmt.get('isDrc') and 'DRC',
a4166234 3859 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3860 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
c795c39f 3861 throttled and 'THROTTLED', is_damaged and 'DAMAGED',
86cb9221 3862 (self.get_param('verbose') or all_formats) and client_name,
c795c39f 3863 delim=', '),
91e5e839 3864 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
51a07b0d 3865 'source_preference': ((-10 if throttled else -5 if itag == '22' else -1)
3866 + (100 if 'Premium' in name else 0)),
97afb093 3867 'fps': fps if fps > 1 else None, # For some formats, fps is wrongly returned as 1
a4166234 3868 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3869 'height': height,
9bb85699 3870 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
727029c5 3871 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3872 'tbr': tbr,
545cc85d 3873 'url': fmt_url,
2a9c6dcd 3874 'width': int_or_none(fmt.get('width')),
ab6df717 3875 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
08e29b9f 3876 'desc' if language_preference < -1 else '') or None,
ab6df717 3877 'language_preference': language_preference,
a405b38f 3878 # Strictly de-prioritize damaged and 3gp formats
3879 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3880 }
60bdb7bd 3881 mime_mobj = re.match(
3882 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3883 if mime_mobj:
3884 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3885 dct.update(parse_codecs(mime_mobj.group(2)))
86cb9221 3886 if itag:
3887 itags[itag].add(('https', dct.get('language')))
3888 stream_ids.append(stream_id)
c9abebb8 3889 single_stream = 'none' in (dct.get('acodec'), dct.get('vcodec'))
3890 if single_stream and dct.get('ext'):
3891 dct['container'] = dct['ext'] + '_dash'
86cb9221 3892
58786a10 3893 if (all_formats or 'dashy' in format_types) and dct['filesize']:
86cb9221 3894 yield {
3895 **dct,
3896 'format_id': f'{dct["format_id"]}-dashy' if all_formats else dct['format_id'],
5038f6d7 3897 'protocol': 'http_dash_segments',
e389d172 3898 'fragments': build_fragments(dct),
86cb9221 3899 }
58786a10 3900 if all_formats or 'dashy' not in format_types:
3901 dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE}
3902 yield dct
545cc85d 3903
4d37720a 3904 needs_live_processing = self._needs_live_processing(live_status, duration)
58786a10 3905 skip_bad_formats = 'incomplete' not in format_types
3906 if self._configuration_arg('include_incomplete_formats'):
3907 skip_bad_formats = False
3908 self._downloader.deprecated_feature('[youtube] include_incomplete_formats extractor argument is deprecated. '
3909 'Use formats=incomplete extractor argument instead')
4d37720a
L
3910
3911 skip_manifests = set(self._configuration_arg('skip'))
3912 if (not self.get_param('youtube_include_hls_manifest', True)
3913 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3914 or needs_live_processing and skip_bad_formats):
3915 skip_manifests.add('hls')
3916
0f06bcd7 3917 if not self.get_param('youtube_include_dash_manifest', True):
4d37720a
L
3918 skip_manifests.add('dash')
3919 if self._configuration_arg('include_live_dash'):
3920 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
58786a10 3921 'Use formats=incomplete extractor argument instead')
4d37720a
L
3922 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3923 skip_manifests.add('dash')
5d3a0e79 3924
c795c39f 3925 def process_manifest_format(f, proto, client_name, itag):
a4894d3e 3926 key = (proto, f.get('language'))
86cb9221 3927 if not all_formats and key in itags[itag]:
a4894d3e 3928 return False
3929 itags[itag].add(key)
3930
86cb9221 3931 if itag and all_formats:
3932 f['format_id'] = f'{itag}-{proto}'
3933 elif any(p != proto for p, _ in itags[itag]):
a4894d3e 3934 f['format_id'] = f'{itag}-{proto}'
3935 elif itag:
a0bb6ce5 3936 f['format_id'] = itag
a0bb6ce5 3937
94ed638a 3938 if f.get('source_preference') is None:
3939 f['source_preference'] = -1
3940
1e75d97d 3941 if itag in ('616', '235'):
3942 f['format_note'] = join_nonempty(f.get('format_note'), 'Premium', delim=' ')
94ed638a 3943 f['source_preference'] += 100
1e75d97d 3944
b25cac65 3945 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3946 if f['quality'] == -1 and f.get('height'):
3947 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
ad54c913 3948 if self.get_param('verbose') or all_formats:
c795c39f 3949 f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ')
97afb093 3950 if f.get('fps') and f['fps'] <= 1:
3951 del f['fps']
94ed638a 3952
3953 if proto == 'hls' and f.get('has_drm'):
3954 f['has_drm'] = 'maybe'
3955 f['source_preference'] -= 5
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'}
546b2c28 4028 pp = self._configuration_arg('player_params', [None], casesense=True)[0]
ba06d77a 4029 if pp:
4030 query['pp'] = pp
b6de707d 4031 webpage = self._download_webpage(
50ac0e54 4032 webpage_url, video_id, fatal=False, query=query)
11f9be09 4033
4034 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 4035
b6de707d 4036 player_responses, player_url = self._extract_player_responses(
11f9be09 4037 self._get_requested_clients(url, smuggled_data),
50ac0e54 4038 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 4039
adbc4ec4
THD
4040 return webpage, master_ytcfg, player_responses, player_url
4041
a1b2d843 4042 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
4043 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
4044 is_live = get_first(video_details, 'isLive')
4045 if is_live is None:
4046 is_live = get_first(live_broadcast_details, 'isLiveNow')
4d37720a
L
4047 live_content = get_first(video_details, 'isLiveContent')
4048 is_upcoming = get_first(video_details, 'isUpcoming')
4d37720a
L
4049 post_live = get_first(video_details, 'isPostLiveDvr')
4050 live_status = ('post_live' if post_live
4051 else 'is_live' if is_live
4052 else 'is_upcoming' if is_upcoming
6678a4f0 4053 else 'was_live' if live_content
4054 else 'not_live' if False in (is_live, live_content)
4055 else None)
6839ae1f 4056 streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
4d37720a 4057 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
94ed638a 4058 if all(f.get('has_drm') for f in formats):
4059 # If there are no formats that definitely don't have DRM, all have DRM
4060 for f in formats:
4061 f['has_drm'] = True
adbc4ec4 4062
4d37720a 4063 return live_broadcast_details, live_status, streaming_data, formats, subtitles
adbc4ec4
THD
4064
4065 def _real_extract(self, url):
4066 url, smuggled_data = unsmuggle_url(url, {})
4067 video_id = self._match_id(url)
4068
4069 base_url = self.http_scheme() + '//www.youtube.com/'
4070 webpage_url = base_url + 'watch?v=' + video_id
4071
4072 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
4073
11f9be09 4074 playability_statuses = traverse_obj(
6839ae1f 4075 player_responses, (..., 'playabilityStatus'), expected_type=dict)
11f9be09 4076
4077 trailer_video_id = get_first(
4078 playability_statuses,
4079 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
4080 expected_type=str)
4081 if trailer_video_id:
4082 return self.url_result(
4083 trailer_video_id, self.ie_key(), trailer_video_id)
4084
4085 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
4086 if webpage else (lambda x: None))
4087
6839ae1f 4088 video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict)
11f9be09 4089 microformats = traverse_obj(
4090 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 4091 expected_type=dict)
c26f9b99 4092
4093 translated_title = self._get_text(microformats, (..., 'title'))
4094 video_title = (self._preferred_lang and translated_title
4095 or get_first(video_details, 'title') # primary
4096 or translated_title
4097 or search_meta(['og:title', 'twitter:title', 'title']))
4098 translated_description = self._get_text(microformats, (..., 'description'))
4099 original_description = get_first(video_details, 'shortDescription')
4100 video_description = (
4101 self._preferred_lang and translated_description
4102 # If original description is blank, it will be an empty string.
4103 # Do not prefer translated description in this case.
4104 or original_description if original_description is not None else translated_description)
11f9be09 4105
d89257f3 4106 multifeed_metadata_list = get_first(
4107 player_responses,
4108 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
4109 expected_type=str)
4110 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
4111 if self.get_param('noplaylist'):
11f9be09 4112 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 4113 else:
4114 entries = []
4115 feed_ids = []
4116 for feed in multifeed_metadata_list.split(','):
4117 # Unquote should take place before split on comma (,) since textual
4118 # fields may contain comma as well (see
4119 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 4120 feed_data = urllib.parse.parse_qs(
ac668111 4121 urllib.parse.unquote_plus(feed))
d89257f3 4122
4123 def feed_entry(name):
4124 return try_get(
14f25df2 4125 feed_data, lambda x: x[name][0], str)
d89257f3 4126
4127 feed_id = feed_entry('id')
4128 if not feed_id:
4129 continue
4130 feed_title = feed_entry('title')
4131 title = video_title
4132 if feed_title:
4133 title += ' (%s)' % feed_title
4134 entries.append({
4135 '_type': 'url_transparent',
4136 'ie_key': 'Youtube',
4137 'url': smuggle_url(
4138 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
4139 {'force_singlefeed': True}),
4140 'title': title,
4141 })
4142 feed_ids.append(feed_id)
4143 self.to_screen(
4144 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
4145 % (', '.join(feed_ids), video_id))
4146 return self.playlist_result(
4147 entries, video_id, video_title, video_description)
11f9be09 4148
9da6612b 4149 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
4150 or int_or_none(get_first(microformats, 'lengthSeconds'))
4151 or parse_duration(search_meta('duration')) or None)
a1b2d843 4152
4d37720a
L
4153 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
4154 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
4155 if live_status == 'post_live':
4156 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
bf1317d2 4157
545cc85d 4158 if not formats:
11f9be09 4159 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 4160 self.report_drm(video_id)
11f9be09 4161 pemr = get_first(
4162 playability_statuses,
4163 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
4164 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
4165 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 4166 if subreason:
545cc85d 4167 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 4168 countries = get_first(microformats, 'availableCountries')
545cc85d 4169 if not countries:
4170 regions_allowed = search_meta('regionsAllowed')
4171 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 4172 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 4173 reason += f'. {subreason}'
545cc85d 4174 if reason:
b7da73eb 4175 self.raise_no_formats(reason, expected=True)
bf1317d2 4176
11f9be09 4177 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 4178 if not keywords and webpage:
4179 keywords = [
4180 unescapeHTML(m.group('content'))
4181 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
4182 for keyword in keywords:
4183 if keyword.startswith('yt:stretch='):
201c1459 4184 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
4185 if mobj:
4186 # NB: float is intentional for forcing float division
4187 w, h = (float(v) for v in mobj.groups())
4188 if w > 0 and h > 0:
4189 ratio = w / h
4190 for f in formats:
4191 if f.get('vcodec') != 'none':
4192 f['stretched_ratio'] = ratio
4193 break
a709d873 4194 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 4195 thumbnail_url = search_meta(['og:image', 'twitter:image'])
4196 if thumbnail_url:
4197 thumbnails.append({
4198 'url': thumbnail_url,
ff2751ac 4199 })
fccf5021 4200 original_thumbnails = thumbnails.copy()
4201
0ba692ac 4202 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 4203 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 4204 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 4205 thumbnail_names = [
962ffcf8 4206 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 4207 # in resolution, these are not the custom thumbnail. So de-prioritize them
4208 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4209 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 4210 ]
cca80fe6 4211 n_thumbnail_names = len(thumbnail_names)
0ba692ac 4212 thumbnails.extend({
4213 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4214 video_id=video_id, name=name, ext=ext,
4d37720a 4215 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
cca80fe6 4216 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 4217 for thumb in thumbnails:
cca80fe6 4218 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 4219 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 4220 self._remove_duplicate_formats(thumbnails)
fccf5021 4221 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 4222
7ea65411 4223 category = get_first(microformats, 'category') or search_meta('genre')
7666b936 4224 channel_id = self.ucid_or_none(str_or_none(
7ea65411 4225 get_first(video_details, 'channelId')
4226 or get_first(microformats, 'externalChannelId')
7666b936 4227 or search_meta('channelId')))
7ea65411 4228 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4229
adbc4ec4
THD
4230 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4231 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4232 if not duration and live_end_time and live_start_time:
4233 duration = live_end_time - live_start_time
4234
4d37720a
L
4235 needs_live_processing = self._needs_live_processing(live_status, duration)
4236
4237 def is_bad_format(fmt):
4238 if needs_live_processing and not fmt.get('is_from_start'):
4239 return True
4240 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4241 and fmt.get('protocol') == 'http_dash_segments'):
4242 return True
4243
4244 for fmt in filter(is_bad_format, formats):
4245 fmt['preference'] = (fmt.get('preference') or -1) - 10
d949c10c 4246 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 2 hours)', delim=' ')
4d37720a
L
4247
4248 if needs_live_processing:
4249 self._prepare_live_from_start_formats(
4250 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
7ea65411 4251
720c3099 4252 formats.extend(self._extract_storyboard(player_responses, duration))
4253
7666b936 4254 channel_handle = self.handle_from_url(owner_profile_url)
4255
545cc85d 4256 info = {
4257 'id': video_id,
39ca3b5c 4258 'title': video_title,
545cc85d 4259 'formats': formats,
4260 'thumbnails': thumbnails,
fccf5021 4261 # The best thumbnail that we are sure exists. Prevents unnecessary
4262 # URL checking if user don't care about getting the best possible thumbnail
4263 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 4264 'description': video_description,
545cc85d 4265 'channel_id': channel_id,
7666b936 4266 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None),
545cc85d 4267 'duration': duration,
4268 'view_count': int_or_none(
11f9be09 4269 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 4270 or search_meta('interactionCount')),
11f9be09 4271 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 4272 'age_limit': 18 if (
11f9be09 4273 get_first(microformats, 'isFamilySafe') is False
545cc85d 4274 or search_meta('isFamilyFriendly') == 'false'
4275 or search_meta('og:restrictions:age') == '18+') else 0,
4276 'webpage_url': webpage_url,
4277 'categories': [category] if category else None,
4278 'tags': keywords,
11f9be09 4279 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4d37720a 4280 'live_status': live_status,
adbc4ec4 4281 'release_timestamp': live_start_time,
9f14daf2 4282 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4283 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
545cc85d 4284 }
b477fc13 4285
c646d76f 4286 subtitles = {}
3944e7af 4287 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 4288 if pctr:
ecdc9049 4289 def get_lang_code(track):
4290 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4291 or track.get('languageCode'))
4292
4293 # Converted into dicts to remove duplicates
4294 captions = {
4295 get_lang_code(sub): sub
6839ae1f 4296 for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
ecdc9049 4297 translation_languages = {
4298 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
6839ae1f 4299 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
ecdc9049 4300
774d79cc 4301 def process_language(container, base_url, lang_code, sub_name, query):
120916da 4302 lang_subs = container.setdefault(lang_code, [])
545cc85d 4303 for fmt in self._SUBTITLE_FORMATS:
4304 query.update({
4305 'fmt': fmt,
4306 })
4307 lang_subs.append({
4308 'ext': fmt,
60f393e4 4309 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 4310 'name': sub_name,
545cc85d 4311 })
7e72694b 4312
07b47084 4313 # NB: Constructing the full subtitle dictionary is slow
4314 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4315 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 4316 for lang_code, caption_track in captions.items():
4317 base_url = caption_track.get('baseUrl')
1235d333 4318 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 4319 if not base_url:
4320 continue
ecdc9049 4321 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 4322 if caption_track.get('kind') != 'asr':
545cc85d 4323 if not lang_code:
4324 continue
4325 process_language(
ecdc9049 4326 subtitles, base_url, lang_code, lang_name, {})
4327 if not caption_track.get('isTranslatable'):
4328 continue
3944e7af 4329 for trans_code, trans_name in translation_languages.items():
4330 if not trans_code:
545cc85d 4331 continue
1235d333 4332 orig_trans_code = trans_code
71eb82d1 4333 if caption_track.get('kind') != 'asr' and trans_code != 'und':
07b47084 4334 if not get_translated_subs:
18e49408 4335 continue
ecdc9049 4336 trans_code += f'-{lang_code}'
a70635b8 4337 trans_name += format_field(lang_name, None, ' from %s')
1235d333 4338 if lang_code == f'a-{orig_trans_code}':
ff9b0e07 4339 # Set audio language based on original subtitles
4340 for f in formats:
4341 if f.get('acodec') != 'none' and not f.get('language'):
4342 f['language'] = orig_trans_code
4343 # Add an "-orig" label to the original language so that it can be distinguished.
4344 # The subs are returned without "-orig" as well for compatibility
0c8d9e5f 4345 process_language(
d49669ac 4346 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4347 # Setting tlang=lang returns damaged subtitles.
d49669ac 4348 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 4349 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 4350
4351 info['automatic_captions'] = automatic_captions
4352 info['subtitles'] = subtitles
7e72694b 4353
14f25df2 4354 parsed_url = urllib.parse.urlparse(url)
545cc85d 4355 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 4356 query = urllib.parse.parse_qs(component)
545cc85d 4357 for k, v in query.items():
4358 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4359 d_k += '_time'
4360 if d_k not in info and k in s_ks:
4361 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
4362
4363 # Youtube Music Auto-generated description
71dc18fa
BT
4364 if (video_description or '').strip().endswith('\nAuto-generated by YouTube.'):
4365 # XXX: Causes catastrophic backtracking if description has "·"
4366 # E.g. https://www.youtube.com/watch?v=DoPaAxMQoiI
4367 # Simulating atomic groups: (?P<a>[^xy]+)x => (?=(?P<a>[^xy]+))(?P=a)x
4368 # reduces it, but does not fully fix it. https://regex101.com/r/8Ssf2h/2
1890fc63 4369 mobj = re.search(
4370 r'''(?xs)
71dc18fa
BT
4371 (?=(?P<track>[^\n·]+))(?P=track)·
4372 (?=(?P<artist>[^\n]+))(?P=artist)\n+
4373 (?=(?P<album>[^\n]+))(?P=album)\n
1890fc63 4374 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4375 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
71dc18fa
BT
4376 (.+?\nArtist\s*:\s*
4377 (?=(?P<clean_artist>[^\n]+))(?P=clean_artist)\n
4378 )?.+\nAuto-generated\ by\ YouTube\.\s*$
1890fc63 4379 ''', video_description)
822b9d9c 4380 if mobj:
822b9d9c
RA
4381 release_year = mobj.group('release_year')
4382 release_date = mobj.group('release_date')
4383 if release_date:
4384 release_date = release_date.replace('-', '')
4385 if not release_year:
545cc85d 4386 release_year = release_date[:4]
4387 info.update({
4388 'album': mobj.group('album'.strip()),
104a7b5a
L
4389 'artists': ([a] if (a := mobj.group('clean_artist'))
4390 else [a.strip() for a in mobj.group('artist').split('·')]),
545cc85d 4391 'track': mobj.group('track').strip(),
4392 'release_date': release_date,
cc2db878 4393 'release_year': int_or_none(release_year),
545cc85d 4394 })
7e72694b 4395
545cc85d 4396 initial_data = None
4397 if webpage:
56ba69e4 4398 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
607510b9 4399 if not traverse_obj(initial_data, 'contents'):
4400 self.report_warning('Incomplete data received in embedded initial data; re-fetching using API.')
4401 initial_data = None
545cc85d 4402 if not initial_data:
99e9e001 4403 query = {'videoId': video_id}
4404 query.update(self._get_checkok_params())
109dd3b2 4405 initial_data = self._extract_response(
4406 item_id=video_id, ep='next', fatal=False,
607510b9 4407 ytcfg=master_ytcfg, query=query, check_get_keys='contents',
99e9e001 4408 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 4409 note='Downloading initial data API JSON')
545cc85d 4410
0df111a3 4411 info['comment_count'] = traverse_obj(initial_data, (
4412 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
071670cb 4413 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount'
0df111a3 4414 ), (
4415 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
071670cb
ND
4416 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo'
4417 ), expected_type=self._get_count, get_all=False)
0df111a3 4418
19a03940 4419 try: # This will error if there is no livechat
c60ee3a2 4420 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 4421 except (KeyError, IndexError, TypeError):
4422 pass
4423 else:
ecdc9049 4424 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 4425 # url is needed to set cookies
4426 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 4427 'video_id': video_id,
4428 'ext': 'json',
4d37720a
L
4429 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4430 else 'youtube_live_chat_replay'),
c60ee3a2 4431 }]
545cc85d 4432
4433 if initial_data:
7c365c21 4434 info['chapters'] = (
4435 self._extract_chapters_from_json(initial_data, duration)
4436 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 4437 or self._extract_chapters_from_description(video_description, duration)
7c365c21 4438 or None)
545cc85d 4439
03e85ea9 4440 info['heatmap'] = self._extract_heatmap(initial_data)
5caf30db 4441
17322130 4442 contents = traverse_obj(
4443 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4444 expected_type=list, default=[])
4445
4446 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4447 if vpir:
4448 stl = vpir.get('superTitleLink')
4449 if stl:
4450 stl = self._get_text(stl)
4451 if try_get(
4452 vpir,
4453 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4454 info['location'] = stl
4455 else:
affc4fef 4456 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 4457 if mobj:
545cc85d 4458 info.update({
17322130 4459 'series': mobj.group(1),
4460 'season_number': int(mobj.group(2)),
4461 'episode_number': int(mobj.group(3)),
545cc85d 4462 })
17322130 4463 for tlb in (try_get(
4464 vpir,
4465 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4466 list) or []):
3ffb2f5b 4467 tbrs = variadic(
4468 traverse_obj(
6839ae1f
SS
4469 tlb, ('toggleButtonRenderer', ...),
4470 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
3ffb2f5b 4471 for tbr in tbrs:
4472 for getter, regex in [(
4473 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4474 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4475 lambda x: x['accessibility'],
4476 lambda x: x['accessibilityData']['accessibilityData'],
4477 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4478 label = (try_get(tbr, getter, dict) or {}).get('label')
4479 if label:
4480 mobj = re.match(regex, label)
4481 if mobj:
4482 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4483 break
6b5d93b0
PG
4484
4485 info['like_count'] = traverse_obj(vpir, (
4486 'videoActions', 'menuRenderer', 'topLevelButtons', ...,
4487 'segmentedLikeDislikeButtonViewModel', 'likeButtonViewModel', 'likeButtonViewModel',
4488 'toggleButtonViewModel', 'toggleButtonViewModel', 'defaultButtonViewModel',
4489 'buttonViewModel', 'accessibilityText', {parse_count}), get_all=False)
4490
867c66ff
M
4491 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4492 if vcr:
4493 vc = self._get_count(vcr, 'viewCount')
4494 # Upcoming premieres with waiting count are treated as live here
4495 if vcr.get('isLive'):
4496 info['concurrent_view_count'] = vc
4497 elif info.get('view_count') is None:
4498 info['view_count'] = vc
4499
17322130 4500 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4501 if vsir:
4502 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4503 info.update({
4504 'channel': self._get_text(vor, 'title'),
4505 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4506
7666b936 4507 if not channel_handle:
4508 channel_handle = self.handle_from_url(
4509 traverse_obj(vor, (
4510 ('navigationEndpoint', ('title', 'runs', ..., 'navigationEndpoint')),
4511 (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl')),
4512 {str}), get_all=False))
4513
17322130 4514 rows = try_get(
4515 vsir,
4516 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4517 list) or []
4518 multiple_songs = False
4519 for row in rows:
4520 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4521 multiple_songs = True
4522 break
4523 for row in rows:
4524 mrr = row.get('metadataRowRenderer') or {}
4525 mrr_title = mrr.get('title')
4526 if not mrr_title:
4527 continue
4528 mrr_title = self._get_text(mrr, 'title')
4529 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4530 if mrr_title == 'License':
4531 info['license'] = mrr_contents_text
4532 elif not multiple_songs:
4533 if mrr_title == 'Album':
4534 info['album'] = mrr_contents_text
4535 elif mrr_title == 'Artist':
104a7b5a 4536 info['artists'] = [mrr_contents_text] if mrr_contents_text else None
17322130 4537 elif mrr_title == 'Song':
4538 info['track'] = mrr_contents_text
8213ce28 4539 owner_badges = self._extract_badges(traverse_obj(vsir, ('owner', 'videoOwnerRenderer', 'badges')))
4540 if self._has_badge(owner_badges, BadgeType.VERIFIED):
4541 info['channel_is_verified'] = True
545cc85d 4542
7666b936 4543 info.update({
4544 'uploader': info.get('channel'),
4545 'uploader_id': channel_handle,
4546 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
4547 })
17322130 4548 # The upload date for scheduled, live and past live streams / premieres in microformats
4549 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 4550 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 4551 upload_date = (
4552 unified_strdate(get_first(microformats, 'uploadDate'))
4553 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 4554 if not upload_date or (
4d37720a 4555 live_status in ('not_live', None)
1ff88b7a 4556 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4557 ):
c26f9b99 4558 upload_date = strftime_or_none(
ad54c913 4559 self._parse_time_text(self._get_text(vpir, 'dateText'))) or upload_date
17322130 4560 info['upload_date'] = upload_date
992f9a73 4561
ef79d20d 4562 if upload_date and live_status not in ('is_live', 'post_live', 'is_upcoming'):
4563 # Newly uploaded videos' HLS formats are potentially problematic and need to be checked
4564 upload_datetime = datetime_from_str(upload_date).replace(tzinfo=datetime.timezone.utc)
bb5a54e6 4565 if upload_datetime >= datetime_from_str('today-2days'):
ef79d20d 4566 for fmt in info['formats']:
4567 if fmt.get('protocol') == 'm3u8_native':
4568 fmt['__needs_testing'] = True
4569
104a7b5a 4570 for s_k, d_k in [('artists', 'creators'), ('track', 'alt_title')]:
545cc85d 4571 v = info.get(s_k)
4572 if v:
4573 info[d_k] = v
b84071c0 4574
14a14335 4575 badges = self._extract_badges(traverse_obj(vpir, 'badges'))
c26f9b99 4576
4577 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4578 or get_first(video_details, 'isPrivate', expected_type=bool))
4579
4580 info['availability'] = (
4581 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4582 else self._availability(
4583 is_private=is_private,
4584 needs_premium=(
4585 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4586 or False if initial_data and is_private is not None else None),
4587 needs_subscription=(
4588 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4589 or False if initial_data and is_private is not None else None),
4590 needs_auth=info['age_limit'] >= 18,
4591 is_unlisted=None if is_private is None else (
4592 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4593 or get_first(microformats, 'isUnlisted', expected_type=bool))))
c224251a 4594
a2160aa4 4595 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 4596
11f9be09 4597 self.mark_watched(video_id, player_responses)
d77ab8e2 4598
545cc85d 4599 return info
c5e8d7af 4600
a61fd4cf 4601
a6213a49 4602class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
182bda88 4603 @staticmethod
4604 def passthrough_smuggled_data(func):
bd7e919a 4605 def _smuggle(info, smuggled_data):
4606 if info.get('_type') not in ('url', 'url_transparent'):
4607 return info
4608 if smuggled_data.get('is_music_url'):
4609 parsed_url = urllib.parse.urlparse(info['url'])
4610 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4611 smuggled_data.pop('is_music_url')
4612 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4613 if smuggled_data:
4614 info['url'] = smuggle_url(info['url'], smuggled_data)
4615 return info
182bda88 4616
4617 @functools.wraps(func)
4618 def wrapper(self, url):
4619 url, smuggled_data = unsmuggle_url(url, {})
4620 if self.is_music_url(url):
4621 smuggled_data['is_music_url'] = True
4622 info_dict = func(self, url, smuggled_data)
bd7e919a 4623 if smuggled_data:
4624 _smuggle(info_dict, smuggled_data)
4625 if info_dict.get('entries'):
a8c754cc 4626 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
182bda88 4627 return info_dict
4628 return wrapper
4629
8bdd16b4 4630 @staticmethod
cd7c66cf 4631 def _extract_basic_item_renderer(item):
4632 # Modified from _extract_grid_item_renderer
201c1459 4633 known_basic_renderers = (
a17526e4 4634 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4635 )
4636 for key, renderer in item.items():
201c1459 4637 if not isinstance(renderer, dict):
cd7c66cf 4638 continue
201c1459 4639 elif key in known_basic_renderers:
4640 return renderer
4641 elif key.startswith('grid') and key.endswith('Renderer'):
4642 return renderer
8bdd16b4 4643
c7335551 4644 def _extract_channel_renderer(self, renderer):
7666b936 4645 channel_id = self.ucid_or_none(renderer['channelId'])
c7335551 4646 title = self._get_text(renderer, 'title')
7666b936 4647 channel_url = format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None)
7666b936 4648 channel_handle = self.handle_from_url(
4649 traverse_obj(renderer, (
4650 'navigationEndpoint', (('commandMetadata', 'webCommandMetadata', 'url'),
4651 ('browseEndpoint', 'canonicalBaseUrl')),
4652 {str}), get_all=False))
14a14335 4653 if not channel_handle:
4654 # As of 2023-06-01, YouTube sets subscriberCountText to the handle in search
4655 channel_handle = self.handle_or_none(self._get_text(renderer, 'subscriberCountText'))
c7335551
M
4656 return {
4657 '_type': 'url',
4658 'url': channel_url,
4659 'id': channel_id,
4660 'ie_key': YoutubeTabIE.ie_key(),
4661 'channel': title,
7666b936 4662 'uploader': title,
c7335551
M
4663 'channel_id': channel_id,
4664 'channel_url': channel_url,
4665 'title': title,
7666b936 4666 'uploader_id': channel_handle,
4667 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
14a14335 4668 # See above. YouTube sets videoCountText to the subscriber text in search channel renderers.
4669 # However, in feed/channels this is set correctly to the subscriber count
4670 'channel_follower_count': traverse_obj(
4671 renderer, 'subscriberCountText', 'videoCountText', expected_type=self._get_count),
c7335551 4672 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
14a14335 4673 'playlist_count': (
4674 # videoCountText may be the subscriber count
4675 self._get_count(renderer, 'videoCountText')
4676 if self._get_count(renderer, 'subscriberCountText') is not None else None),
c7335551 4677 'description': self._get_text(renderer, 'descriptionSnippet'),
8213ce28 4678 'channel_is_verified': True if self._has_badge(
4679 self._extract_badges(traverse_obj(renderer, 'ownerBadges')), BadgeType.VERIFIED) else None,
c7335551
M
4680 }
4681
8bdd16b4 4682 def _grid_entries(self, grid_renderer):
4683 for item in grid_renderer['items']:
4684 if not isinstance(item, dict):
39b62db1 4685 continue
cd7c66cf 4686 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4687 if not isinstance(renderer, dict):
4688 continue
052e1350 4689 title = self._get_text(renderer, 'title')
fe93e2c4 4690
8bdd16b4 4691 # playlist
4692 playlist_id = renderer.get('playlistId')
4693 if playlist_id:
4694 yield self.url_result(
4695 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4696 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4697 video_title=title)
201c1459 4698 continue
8bdd16b4 4699 # video
4700 video_id = renderer.get('videoId')
4701 if video_id:
4702 yield self._extract_video(renderer)
201c1459 4703 continue
8bdd16b4 4704 # channel
4705 channel_id = renderer.get('channelId')
4706 if channel_id:
c7335551 4707 yield self._extract_channel_renderer(renderer)
201c1459 4708 continue
4709 # generic endpoint URL support
4710 ep_url = urljoin('https://www.youtube.com/', try_get(
4711 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4712 str))
201c1459 4713 if ep_url:
4714 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4715 if ie.suitable(ep_url):
4716 yield self.url_result(
4717 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4718 break
8bdd16b4 4719
16aa9ea4 4720 def _music_reponsive_list_entry(self, renderer):
4721 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4722 if video_id:
69a40e4a 4723 title = traverse_obj(renderer, (
4724 'flexColumns', 0, 'musicResponsiveListItemFlexColumnRenderer',
4725 'text', 'runs', 0, 'text'))
16aa9ea4 4726 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
69a40e4a 4727 ie=YoutubeIE.ie_key(), video_id=video_id, title=title)
16aa9ea4 4728 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4729 if playlist_id:
4730 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4731 if video_id:
4732 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4733 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4734 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4735 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4736 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4737 if browse_id:
4738 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4739 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4740
3d3dddc9 4741 def _shelf_entries_from_content(self, shelf_renderer):
4742 content = shelf_renderer.get('content')
4743 if not isinstance(content, dict):
8bdd16b4 4744 return
cd7c66cf 4745 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4746 if renderer:
4747 # TODO: add support for nested playlists so each shelf is processed
4748 # as separate playlist
4749 # TODO: this includes only first N items
86e5f3ed 4750 yield from self._grid_entries(renderer)
3d3dddc9 4751 renderer = content.get('horizontalListRenderer')
4752 if renderer:
4753 # TODO
4754 pass
8bdd16b4 4755
29f7c58a 4756 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4757 ep = try_get(
4758 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4759 str)
8bdd16b4 4760 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4761 if shelf_url:
29f7c58a 4762 # Skipping links to another channels, note that checking for
4763 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4764 # will not work
4765 if skip_channels and '/channels?' in shelf_url:
4766 return
052e1350 4767 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4768 yield self.url_result(shelf_url, video_title=title)
4769 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4770 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4771
8bdd16b4 4772 def _playlist_entries(self, video_list_renderer):
4773 for content in video_list_renderer['contents']:
4774 if not isinstance(content, dict):
4775 continue
4776 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4777 if not isinstance(renderer, dict):
4778 continue
4779 video_id = renderer.get('videoId')
4780 if not video_id:
4781 continue
4782 yield self._extract_video(renderer)
07aeced6 4783
3462ffa8 4784 def _rich_entries(self, rich_grid_renderer):
80eb0bd9 4785 renderer = traverse_obj(
447afb9e 4786 rich_grid_renderer,
4787 ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer')), get_all=False) or {}
3462ffa8 4788 video_id = renderer.get('videoId')
447afb9e 4789 if video_id:
4790 yield self._extract_video(renderer)
4791 return
4792 playlist_id = renderer.get('playlistId')
4793 if playlist_id:
4794 yield self.url_result(
4795 f'https://www.youtube.com/playlist?list={playlist_id}',
4796 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4797 video_title=self._get_text(renderer, 'title'))
3462ffa8 4798 return
3462ffa8 4799
8bdd16b4 4800 def _video_entry(self, video_renderer):
4801 video_id = video_renderer.get('videoId')
4802 if video_id:
4803 return self._extract_video(video_renderer)
dacb3a86 4804
ad210f4f 4805 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4806 url = urljoin('https://youtube.com', traverse_obj(
4807 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4808 if url:
4809 return self.url_result(
4810 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4811
8bdd16b4 4812 def _post_thread_entries(self, post_thread_renderer):
4813 post_renderer = try_get(
4814 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4815 if not post_renderer:
4816 return
4817 # video attachment
4818 video_renderer = try_get(
895b0931 4819 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4820 video_id = video_renderer.get('videoId')
4821 if video_id:
4822 entry = self._extract_video(video_renderer)
8bdd16b4 4823 if entry:
4824 yield entry
895b0931 4825 # playlist attachment
4826 playlist_id = try_get(
14f25df2 4827 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4828 if playlist_id:
4829 yield self.url_result(
e28f1c0a 4830 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4831 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4832 # inline video links
4833 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4834 for run in runs:
4835 if not isinstance(run, dict):
4836 continue
4837 ep_url = try_get(
14f25df2 4838 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4839 if not ep_url:
4840 continue
4841 if not YoutubeIE.suitable(ep_url):
4842 continue
4843 ep_video_id = YoutubeIE._match_id(ep_url)
4844 if video_id == ep_video_id:
4845 continue
895b0931 4846 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4847
8bdd16b4 4848 def _post_thread_continuation_entries(self, post_thread_continuation):
4849 contents = post_thread_continuation.get('contents')
4850 if not isinstance(contents, list):
4851 return
4852 for content in contents:
4853 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4854 if isinstance(renderer, dict):
4855 yield from self._post_thread_entries(renderer)
8bdd16b4 4856 continue
6b0b0a28 4857 renderer = content.get('videoRenderer')
4858 if isinstance(renderer, dict):
4859 yield self._video_entry(renderer)
07aeced6 4860
39ed931e 4861 r''' # unused
4862 def _rich_grid_entries(self, contents):
4863 for content in contents:
4864 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4865 if video_renderer:
4866 entry = self._video_entry(video_renderer)
4867 if entry:
4868 yield entry
4869 '''
52efa4b3 4870
0a5095fe 4871 def _report_history_entries(self, renderer):
4872 for url in traverse_obj(renderer, (
7a32c70d 4873 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4874 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
0a5095fe 4875 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4876 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4877
a6213a49 4878 def _extract_entries(self, parent_renderer, continuation_list):
4879 # continuation_list is modified in-place with continuation_list = [continuation_token]
4880 continuation_list[:] = [None]
4881 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4882 for content in contents:
4883 if not isinstance(content, dict):
4884 continue
16aa9ea4 4885 is_renderer = traverse_obj(
4886 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4887 expected_type=dict)
a6213a49 4888 if not is_renderer:
0a5095fe 4889 if content.get('richItemRenderer'):
4890 for entry in self._rich_entries(content['richItemRenderer']):
a6213a49 4891 yield entry
4892 continuation_list[0] = self._extract_continuation(parent_renderer)
0a5095fe 4893 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4894 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4895 yield from self._report_history_entries(table)
4896 continuation_list[0] = self._extract_continuation(table)
a6213a49 4897 continue
0a5095fe 4898
a6213a49 4899 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4900 for isr_content in isr_contents:
4901 if not isinstance(isr_content, dict):
8bdd16b4 4902 continue
69184e41 4903
a6213a49 4904 known_renderers = {
4905 'playlistVideoListRenderer': self._playlist_entries,
4906 'gridRenderer': self._grid_entries,
a17526e4 4907 'reelShelfRenderer': self._grid_entries,
4908 'shelfRenderer': self._shelf_entries,
16aa9ea4 4909 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4910 'backstagePostThreadRenderer': self._post_thread_entries,
4911 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4912 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4913 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
fcbc9ed7 4914 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)],
4915 'richGridRenderer': lambda x: self._extract_entries(x, continuation_list),
a6213a49 4916 }
4917 for key, renderer in isr_content.items():
4918 if key not in known_renderers:
4919 continue
4920 for entry in known_renderers[key](renderer):
4921 if entry:
4922 yield entry
4923 continuation_list[0] = self._extract_continuation(renderer)
4924 break
70d5c17b 4925
4926 if not continuation_list[0]:
a6213a49 4927 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4928
a6213a49 4929 if not continuation_list[0]:
4930 continuation_list[0] = self._extract_continuation(parent_renderer)
4931
4932 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4933 continuation_list = [None]
4934 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4935 tab_content = try_get(tab, lambda x: x['content'], dict)
4936 if not tab_content:
4937 return
3462ffa8 4938 parent_renderer = (
29f7c58a 4939 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4940 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4941 yield from extract_entries(parent_renderer)
3462ffa8 4942 continuation = continuation_list[0]
1ba6fe9d 4943 seen_continuations = set()
8bdd16b4 4944 for page_num in itertools.count(1):
4945 if not continuation:
4946 break
1ba6fe9d 4947 continuation_token = continuation.get('continuation')
4948 if continuation_token is not None and continuation_token in seen_continuations:
4949 self.write_debug('Detected YouTube feed looping - assuming end of feed.')
4950 break
4951 seen_continuations.add(continuation_token)
99e9e001 4952 headers = self.generate_api_headers(
4953 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4954 response = self._extract_response(
86e5f3ed 4955 item_id=f'{item_id} page {page_num}',
fe93e2c4 4956 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4957 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4958
4959 if not response:
8bdd16b4 4960 break
ac56cf38 4961 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4962 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4963 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4964
a1b535bd 4965 known_renderers = {
e4b98809 4966 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4967 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4968 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4969 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4970 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4971 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4972 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
0a5095fe 4973 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4974 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
1fb53b94 4975 'playlistVideoListContinuation': (self._playlist_entries, None),
4976 'gridContinuation': (self._grid_entries, None),
4977 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4978 'sectionListContinuation': (extract_entries, None), # for feeds
a1b535bd 4979 }
1fb53b94 4980
4981 continuation_items = traverse_obj(response, (
4982 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4983 'appendContinuationItemsAction', 'continuationItems'
4984 ), 'continuationContents', get_all=False)
4985 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4986
a1b535bd 4987 video_items_renderer = None
1fb53b94 4988 for key in continuation_item.keys():
a1b535bd 4989 if key not in known_renderers:
8bdd16b4 4990 continue
1fb53b94 4991 func, parent_key = known_renderers[key]
4992 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
9ba5705a 4993 continuation_list = [None]
1fb53b94 4994 yield from func(video_items_renderer)
9ba5705a 4995 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
1fb53b94 4996
4997 if not video_items_renderer:
a1b535bd 4998 break
9558dcec 4999
8bdd16b4 5000 @staticmethod
7c219ea6 5001 def _extract_selected_tab(tabs, fatal=True):
86973308
M
5002 for tab_renderer in tabs:
5003 if tab_renderer.get('selected'):
5004 return tab_renderer
5005 if fatal:
5006 raise ExtractorError('Unable to find selected tab')
5007
5008 @staticmethod
5009 def _extract_tab_renderers(response):
5010 return traverse_obj(
5011 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
b82f815f 5012
ac56cf38 5013 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
bd7e919a 5014 metadata = self._extract_metadata_from_tabs(item_id, data)
b60419c5 5015
8bdd16b4 5016 selected_tab = self._extract_selected_tab(tabs)
bd7e919a 5017 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
5018 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
5019
5020 return self.playlist_result(
5021 self._entries(
5022 selected_tab, metadata['id'], ytcfg,
5023 self._extract_account_syncid(ytcfg, data),
5024 self._extract_visitor_data(data, ytcfg)),
5025 **metadata)
39ed931e 5026
bd7e919a 5027 def _extract_metadata_from_tabs(self, item_id, data):
5028 info = {'id': item_id}
5029
5030 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
6141346d 5031 if metadata_renderer:
7666b936 5032 channel_id = traverse_obj(metadata_renderer, ('externalId', {self.ucid_or_none}),
4823ec9f 5033 ('channelUrl', {self.ucid_from_url}))
bd7e919a 5034 info.update({
7666b936 5035 'channel': metadata_renderer.get('title'),
5036 'channel_id': channel_id,
bd7e919a 5037 })
7666b936 5038 if info['channel_id']:
5039 info['id'] = info['channel_id']
bd7e919a 5040 else:
5041 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
b60419c5 5042
301d07fc 5043 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
5044 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
5045 def _get_uncropped(url):
5046 return url_or_none((url or '').split('=')[0] + '=s0')
5047
6141346d 5048 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
301d07fc 5049 if avatar_thumbnails:
5050 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
5051 if uncropped_avatar:
5052 avatar_thumbnails.append({
5053 'url': uncropped_avatar,
5054 'id': 'avatar_uncropped',
5055 'preference': 1
5056 })
5057
5058 channel_banners = self._extract_thumbnails(
bd7e919a 5059 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
301d07fc 5060 for banner in channel_banners:
5061 banner['preference'] = -10
5062
5063 if channel_banners:
5064 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
5065 if uncropped_banner:
5066 channel_banners.append({
5067 'url': uncropped_banner,
5068 'id': 'banner_uncropped',
5069 'preference': -5
5070 })
5071
bd7e919a 5072 # Deprecated - remove primary_sidebar_renderer when layout discontinued
5073 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
5074 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
5075
301d07fc 5076 primary_thumbnails = self._extract_thumbnails(
a17526e4 5077 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
6141346d
M
5078 playlist_thumbnails = self._extract_thumbnails(
5079 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
5080
bd7e919a 5081 info.update({
5082 'title': (traverse_obj(metadata_renderer, 'title')
5083 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
5084 or info['id']),
5085 'availability': self._extract_availability(data),
5086 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
5087 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
5088 'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
5089 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
5090 })
f0d785d3 5091
7666b936 5092 channel_handle = (
5093 traverse_obj(metadata_renderer, (('vanityChannelUrl', ('ownerUrls', ...)), {self.handle_from_url}), get_all=False)
5094 or traverse_obj(data, ('header', ..., 'channelHandleText', {self.handle_or_none}), get_all=False))
5095
5096 if channel_handle:
5097 info.update({
5098 'uploader_id': channel_handle,
5099 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
5100 })
8213ce28 5101
5102 channel_badges = self._extract_badges(traverse_obj(data, ('header', ..., 'badges'), get_all=False))
5103 if self._has_badge(channel_badges, BadgeType.VERIFIED):
5104 info['channel_is_verified'] = True
6141346d
M
5105 # Playlist stats is a text runs array containing [video count, view count, last updated].
5106 # last updated or (view count and last updated) may be missing.
5107 playlist_stats = get_first(
bd7e919a 5108 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
5109
6141346d
M
5110 last_updated_unix = self._parse_time_text(
5111 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
5112 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
ad54c913 5113 info['modified_date'] = strftime_or_none(last_updated_unix)
6141346d 5114
bd7e919a 5115 info['view_count'] = self._get_count(playlist_stats, 1)
5116 if info['view_count'] is None: # 0 is allowed
5117 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
31e18355 5118 if info['view_count'] is None:
5119 info['view_count'] = self._get_count(data, (
5120 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer',
5121 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText'))
bd7e919a 5122
5123 info['playlist_count'] = self._get_count(playlist_stats, 0)
5124 if info['playlist_count'] is None: # 0 is allowed
5125 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
5126
7666b936 5127 if not info.get('channel_id'):
6141346d 5128 owner = traverse_obj(playlist_header_renderer, 'ownerText')
bd7e919a 5129 if not owner: # Deprecated
6141346d
M
5130 owner = traverse_obj(
5131 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
5132 ('videoOwner', 'videoOwnerRenderer', 'title'))
5133 owner_text = self._get_text(owner)
5134 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
bd7e919a 5135 info.update({
7666b936 5136 'channel': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
5137 'channel_id': self.ucid_or_none(browse_ep.get('browseId')),
5138 'uploader_id': self.handle_from_url(urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl')))
bd7e919a 5139 })
6141346d 5140
bd7e919a 5141 info.update({
7666b936 5142 'uploader': info['channel'],
5143 'channel_url': format_field(info.get('channel_id'), None, 'https://www.youtube.com/channel/%s', default=None),
5144 'uploader_url': format_field(info.get('uploader_id'), None, 'https://www.youtube.com/%s', default=None),
bd7e919a 5145 })
7666b936 5146
bd7e919a 5147 return info
73c4ac2c 5148
6e634cbe 5149 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 5150 first_id = last_id = response = None
2be71994 5151 for page_num in itertools.count(1):
cd7c66cf 5152 videos = list(self._playlist_entries(playlist))
5153 if not videos:
5154 return
2be71994 5155 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
5156 if start >= len(videos):
5157 return
24146491 5158 yield from videos[start:]
2be71994 5159 first_id = first_id or videos[0]['id']
5160 last_id = videos[-1]['id']
79360d99 5161 watch_endpoint = try_get(
5162 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 5163 headers = self.generate_api_headers(
5164 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
5165 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 5166 query = {
5167 'playlistId': playlist_id,
5168 'videoId': watch_endpoint.get('videoId') or last_id,
5169 'index': watch_endpoint.get('index') or len(videos),
5170 'params': watch_endpoint.get('params') or 'OAE%3D'
5171 }
5172 response = self._extract_response(
5173 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 5174 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 5175 check_get_keys='contents'
5176 )
cd7c66cf 5177 playlist = try_get(
79360d99 5178 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 5179
ac56cf38 5180 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 5181 title = playlist.get('title') or try_get(
14f25df2 5182 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 5183 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 5184
5185 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 5186 playlist_url = urljoin(url, try_get(
5187 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 5188 str))
6e634cbe 5189
5190 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
5191 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
5192 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
5193
5194 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 5195 return self.url_result(
5196 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
5197 video_title=title)
cd7c66cf 5198
8bdd16b4 5199 return self.playlist_result(
6e634cbe 5200 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 5201 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 5202
47193e02 5203 def _extract_availability(self, data):
5204 """
5205 Gets the availability of a given playlist/tab.
5206 Note: Unless YouTube tells us explicitly, we do not assume it is public
5207 @param data: response
5208 """
6141346d
M
5209 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
5210 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
5211 player_header_privacy = playlist_header_renderer.get('privacy')
c26f9b99 5212
14a14335 5213 badges = self._extract_badges(traverse_obj(sidebar_renderer, 'badges'))
47193e02 5214
5215 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
6141346d
M
5216 privacy_setting_icon = get_first(
5217 (playlist_header_renderer, sidebar_renderer),
5218 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
5219 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
5220 expected_type=str)
5221
5222 microformats_is_unlisted = traverse_obj(
5223 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
47193e02 5224
c26f9b99 5225 return (
5226 'public' if (
5227 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
5228 or player_header_privacy == 'PUBLIC'
5229 or privacy_setting_icon == 'PRIVACY_PUBLIC')
5230 else self._availability(
5231 is_private=(
5232 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
5233 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
5234 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
5235 is_unlisted=(
5236 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
5237 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
6141346d
M
5238 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
5239 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
c26f9b99 5240 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
5241 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
5242 needs_auth=False))
47193e02 5243
5244 @staticmethod
5245 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
5246 sidebar_renderer = try_get(
5247 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
5248 for item in sidebar_renderer:
5249 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
5250 if renderer:
5251 return renderer
5252
ac56cf38 5253 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 5254 """
6141346d 5255 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
358de58c 5256 """
6141346d
M
5257 is_playlist = bool(traverse_obj(
5258 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5259 if not is_playlist:
47193e02 5260 return
11f9be09 5261 headers = self.generate_api_headers(
99e9e001 5262 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 5263 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 5264 query = {
6141346d
M
5265 'params': 'wgYCCAA=',
5266 'browseId': f'VL{item_id}'
47193e02 5267 }
5268 return self._extract_response(
5269 item_id=item_id, headers=headers, query=query,
fe93e2c4 5270 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
6141346d 5271 note='Redownloading playlist API JSON with unavailable videos')
358de58c 5272
2762dbb1 5273 @functools.cached_property
a25bca9f 5274 def skip_webpage(self):
5275 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
5276
ac56cf38 5277 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 5278 webpage, data = None, None
5279 for retry in self.RetryManager(fatal=fatal):
ac56cf38 5280 try:
be5c1ae8 5281 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 5282 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5283 except ExtractorError as e:
5284 if isinstance(e.cause, network_exceptions):
3d2623a8 5285 if not isinstance(e.cause, HTTPError) or e.cause.status not in (403, 429):
be5c1ae8 5286 retry.error = e
5287 continue
5288 self._error_or_warning(e, fatal=fatal)
14fdfea9 5289 break
ac56cf38 5290
be5c1ae8 5291 try:
5292 self._extract_and_report_alerts(data)
5293 except ExtractorError as e:
5294 self._error_or_warning(e, fatal=fatal)
5295 break
ac56cf38 5296
be5c1ae8 5297 # Sometimes youtube returns a webpage with incomplete ytInitialData
5298 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5299 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5300 retry.error = ExtractorError('Incomplete yt initial data received')
f9fb3ce8 5301 data = None
be5c1ae8 5302 continue
ac56cf38 5303
cd7c66cf 5304 return webpage, data
5305
a25bca9f 5306 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5307 """Use if failed to extract ytcfg (and data) from initial webpage"""
5308 if not ytcfg and self.is_authenticated:
5309 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5310 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5311 raise ExtractorError(
5312 f'{msg}. If you are not downloading private content, or '
5313 'your cookies are only for the first account and channel,'
5314 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5315 expected=True)
5316 self.report_warning(msg, only_once=True)
5317
ac56cf38 5318 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5319 data = None
a25bca9f 5320 if not self.skip_webpage:
ac56cf38 5321 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5322 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 5323 # Reject webpage data if redirected to home page without explicitly requesting
86973308 5324 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
1108613f 5325 if (url != 'https://www.youtube.com/feed/recommended'
5326 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5327 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5328 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5329 if fatal:
5330 raise ExtractorError(msg, expected=True)
5331 self.report_warning(msg, only_once=True)
ac56cf38 5332 if not data:
a25bca9f 5333 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 5334 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5335 return data, ytcfg
5336
5337 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5338 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5339 resolve_response = self._extract_response(
5340 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5341 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5342 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5343 for ep_key, ep in endpoints.items():
5344 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5345 if params:
5346 return self._extract_response(
5347 item_id=item_id, query=params, ep=ep, headers=headers,
5348 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 5349 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 5350 err_note = 'Failed to resolve url (does the playlist exist?)'
5351 if fatal:
5352 raise ExtractorError(err_note, expected=True)
5353 self.report_warning(err_note, item_id)
5354
a6213a49 5355 _SEARCH_PARAMS = None
5356
af5c1c55 5357 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 5358 data = {'query': query}
5359 if params is NO_DEFAULT:
5360 params = self._SEARCH_PARAMS
5361 if params:
5362 data['params'] = params
16aa9ea4 5363
5364 content_keys = (
5365 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5366 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5367 # ytmusic search
5368 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5369 ('continuationContents', ),
5370 )
a25bca9f 5371 display_id = f'query "{query}"'
86e5f3ed 5372 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 5373 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5374 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 5375
a61fd4cf 5376 continuation_list = [None]
a25bca9f 5377 search = None
a6213a49 5378 for page_num in itertools.count(1):
a61fd4cf 5379 data.update(continuation_list[0] or {})
a25bca9f 5380 headers = self.generate_api_headers(
5381 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 5382 search = self._extract_response(
a25bca9f 5383 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5384 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 5385 slr_contents = traverse_obj(search, *content_keys)
5386 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 5387 if not continuation_list[0]:
a6213a49 5388 break
5389
5390
5391class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5392 IE_DESC = 'YouTube Tabs'
5393 _VALID_URL = r'''(?x:
5394 https?://
b032ff0f 5395 (?!consent\.)(?:\w+\.)?
a6213a49 5396 (?:
5397 youtube(?:kids)?\.com|
5398 %(invidious)s
5399 )/
5400 (?:
5401 (?P<channel_type>channel|c|user|browse)/|
5402 (?P<not_channel>
5403 feed/|hashtag/|
5404 (?:playlist|watch)\?.*?\blist=
5405 )|
5406 (?!(?:%(reserved_names)s)\b) # Direct URLs
5407 )
5408 (?P<id>[^/?\#&]+)
5409 )''' % {
5410 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5411 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5412 }
5413 IE_NAME = 'youtube:tab'
5414
5415 _TESTS = [{
5416 'note': 'playlists, multipage',
5417 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5418 'playlist_mincount': 94,
5419 'info_dict': {
5420 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5421 'title': 'Igor Kleiner - Playlists',
a6213a49 5422 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5423 'uploader': 'Igor Kleiner',
7666b936 5424 'uploader_id': '@IgorDataScience',
5425 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
976ae3ea 5426 'channel': 'Igor Kleiner',
5427 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5428 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5429 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5430 'channel_follower_count': int
a6213a49 5431 },
5432 }, {
5433 'note': 'playlists, multipage, different order',
5434 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5435 'playlist_mincount': 94,
5436 'info_dict': {
5437 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5438 'title': 'Igor Kleiner - Playlists',
a6213a49 5439 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5440 'uploader': 'Igor Kleiner',
7666b936 5441 'uploader_id': '@IgorDataScience',
5442 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
976ae3ea 5443 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5444 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5445 'channel': 'Igor Kleiner',
5446 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5447 'channel_follower_count': int
a6213a49 5448 },
5449 }, {
5450 'note': 'playlists, series',
5451 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5452 'playlist_mincount': 5,
5453 'info_dict': {
5454 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5455 'title': '3Blue1Brown - Playlists',
5456 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
976ae3ea 5457 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5458 'channel': '3Blue1Brown',
5459 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
7666b936 5460 'uploader_id': '@3blue1brown',
5461 'uploader_url': 'https://www.youtube.com/@3blue1brown',
5462 'uploader': '3Blue1Brown',
976ae3ea 5463 'tags': ['Mathematics'],
14a14335 5464 'channel_follower_count': int,
8213ce28 5465 'channel_is_verified': True,
a6213a49 5466 },
5467 }, {
5468 'note': 'playlists, singlepage',
5469 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5470 'playlist_mincount': 4,
5471 'info_dict': {
5472 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5473 'title': 'ThirstForScience - Playlists',
5474 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5475 'uploader': 'ThirstForScience',
7666b936 5476 'uploader_url': 'https://www.youtube.com/@ThirstForScience',
5477 'uploader_id': '@ThirstForScience',
976ae3ea 5478 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
7666b936 5479 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 5480 'tags': 'count:13',
5481 'channel': 'ThirstForScience',
6c73052c 5482 'channel_follower_count': int
a6213a49 5483 }
5484 }, {
5485 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5486 'only_matching': True,
5487 }, {
5488 'note': 'basic, single video playlist',
5489 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5490 'info_dict': {
a6213a49 5491 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5492 'title': 'youtube-dl public playlist',
976ae3ea 5493 'description': '',
5494 'tags': [],
5495 'view_count': int,
5496 'modified_date': '20201130',
5497 'channel': 'Sergey M.',
5498 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
976ae3ea 5499 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5500 'availability': 'public',
7666b936 5501 'uploader': 'Sergey M.',
5502 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
5503 'uploader_id': '@sergeym.6173',
a6213a49 5504 },
5505 'playlist_count': 1,
5506 }, {
5507 'note': 'empty playlist',
5508 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5509 'info_dict': {
a6213a49 5510 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5511 'title': 'youtube-dl empty playlist',
976ae3ea 5512 'tags': [],
5513 'channel': 'Sergey M.',
5514 'description': '',
5515 'modified_date': '20160902',
5516 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5517 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5518 'availability': 'public',
7666b936 5519 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
5520 'uploader_id': '@sergeym.6173',
5521 'uploader': 'Sergey M.',
a6213a49 5522 },
5523 'playlist_count': 0,
5524 }, {
5525 'note': 'Home tab',
5526 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5527 'info_dict': {
5528 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5529 'title': 'lex will - Home',
5530 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5531 'uploader': 'lex will',
7666b936 5532 'uploader_id': '@lexwill718',
976ae3ea 5533 'channel': 'lex will',
5534 'tags': ['bible', 'history', 'prophesy'],
7666b936 5535 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5536 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5537 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5538 'channel_follower_count': int
a6213a49 5539 },
5540 'playlist_mincount': 2,
5541 }, {
5542 'note': 'Videos tab',
5543 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5544 'info_dict': {
5545 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5546 'title': 'lex will - Videos',
5547 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5548 'uploader': 'lex will',
7666b936 5549 'uploader_id': '@lexwill718',
976ae3ea 5550 'tags': ['bible', 'history', 'prophesy'],
5551 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5552 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
7666b936 5553 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5554 'channel': 'lex will',
6c73052c 5555 'channel_follower_count': int
a6213a49 5556 },
5557 'playlist_mincount': 975,
5558 }, {
5559 'note': 'Videos tab, sorted by popular',
5560 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5561 'info_dict': {
5562 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5563 'title': 'lex will - Videos',
5564 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5565 'uploader': 'lex will',
7666b936 5566 'uploader_id': '@lexwill718',
976ae3ea 5567 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
7666b936 5568 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5569 'channel': 'lex will',
5570 'tags': ['bible', 'history', 'prophesy'],
5571 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5572 'channel_follower_count': int
a6213a49 5573 },
5574 'playlist_mincount': 199,
5575 }, {
5576 'note': 'Playlists tab',
5577 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5578 'info_dict': {
5579 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5580 'title': 'lex will - Playlists',
5581 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5582 'uploader': 'lex will',
7666b936 5583 'uploader_id': '@lexwill718',
5584 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5585 'channel': 'lex will',
5586 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5587 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5588 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5589 'channel_follower_count': int
a6213a49 5590 },
5591 'playlist_mincount': 17,
5592 }, {
5593 'note': 'Community tab',
5594 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5595 'info_dict': {
5596 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5597 'title': 'lex will - Community',
5598 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
976ae3ea 5599 'channel': 'lex will',
5600 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5601 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5602 'tags': ['bible', 'history', 'prophesy'],
7666b936 5603 'channel_follower_count': int,
5604 'uploader_url': 'https://www.youtube.com/@lexwill718',
5605 'uploader_id': '@lexwill718',
5606 'uploader': 'lex will',
a6213a49 5607 },
5608 'playlist_mincount': 18,
5609 }, {
5610 'note': 'Channels tab',
5611 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5612 'info_dict': {
5613 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5614 'title': 'lex will - Channels',
5615 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
976ae3ea 5616 'channel': 'lex will',
5617 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5618 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5619 'tags': ['bible', 'history', 'prophesy'],
7666b936 5620 'channel_follower_count': int,
5621 'uploader_url': 'https://www.youtube.com/@lexwill718',
5622 'uploader_id': '@lexwill718',
5623 'uploader': 'lex will',
a6213a49 5624 },
5625 'playlist_mincount': 12,
5626 }, {
5627 'note': 'Search tab',
5628 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5629 'playlist_mincount': 40,
5630 'info_dict': {
5631 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5632 'title': '3Blue1Brown - Search - linear algebra',
5633 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
976ae3ea 5634 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5635 'tags': ['Mathematics'],
5636 'channel': '3Blue1Brown',
5637 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
7666b936 5638 'channel_follower_count': int,
5639 'uploader_url': 'https://www.youtube.com/@3blue1brown',
5640 'uploader_id': '@3blue1brown',
5641 'uploader': '3Blue1Brown',
8213ce28 5642 'channel_is_verified': True,
a6213a49 5643 },
5644 }, {
5645 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5646 'only_matching': True,
5647 }, {
5648 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5649 'only_matching': True,
5650 }, {
5651 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5652 'only_matching': True,
5653 }, {
5654 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5655 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5656 'info_dict': {
5657 'title': '29C3: Not my department',
5658 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
a6213a49 5659 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 5660 'tags': [],
976ae3ea 5661 'view_count': int,
5662 'modified_date': '20150605',
5663 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
7666b936 5664 'channel_url': 'https://www.youtube.com/channel/UCEPzS1rYsrkqzSLNp76nrcg',
976ae3ea 5665 'channel': 'Christiaan008',
c26f9b99 5666 'availability': 'public',
7666b936 5667 'uploader_id': '@ChRiStIaAn008',
5668 'uploader': 'Christiaan008',
5669 'uploader_url': 'https://www.youtube.com/@ChRiStIaAn008',
a6213a49 5670 },
5671 'playlist_count': 96,
5672 }, {
5673 'note': 'Large playlist',
5674 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5675 'info_dict': {
5676 'title': 'Uploads from Cauchemar',
5677 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
7666b936 5678 'channel_url': 'https://www.youtube.com/channel/UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5679 'tags': [],
5680 'modified_date': r're:\d{8}',
5681 'channel': 'Cauchemar',
976ae3ea 5682 'view_count': int,
5683 'description': '',
5684 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
c26f9b99 5685 'availability': 'public',
7666b936 5686 'uploader_id': '@Cauchemar89',
5687 'uploader': 'Cauchemar',
5688 'uploader_url': 'https://www.youtube.com/@Cauchemar89',
a6213a49 5689 },
5690 'playlist_mincount': 1123,
976ae3ea 5691 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5692 }, {
5693 'note': 'even larger playlist, 8832 videos',
5694 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5695 'only_matching': True,
5696 }, {
5697 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5698 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5699 'info_dict': {
5700 'title': 'Uploads from Interstellar Movie',
5701 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5702 'tags': [],
5703 'view_count': int,
5704 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
7666b936 5705 'channel_url': 'https://www.youtube.com/channel/UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5706 'channel': 'Interstellar Movie',
5707 'description': '',
5708 'modified_date': r're:\d{8}',
c26f9b99 5709 'availability': 'public',
7666b936 5710 'uploader_id': '@InterstellarMovie',
5711 'uploader': 'Interstellar Movie',
5712 'uploader_url': 'https://www.youtube.com/@InterstellarMovie',
a6213a49 5713 },
5714 'playlist_mincount': 21,
5715 }, {
5716 'note': 'Playlist with "show unavailable videos" button',
5717 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5718 'info_dict': {
5719 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5720 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5721 'view_count': int,
5722 'channel': 'Phim Siêu Nhân Nhật Bản',
5723 'tags': [],
976ae3ea 5724 'description': '',
5725 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5726 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5727 'modified_date': r're:\d{8}',
c26f9b99 5728 'availability': 'public',
7666b936 5729 'uploader_url': 'https://www.youtube.com/@phimsieunhannhatban',
5730 'uploader_id': '@phimsieunhannhatban',
5731 'uploader': 'Phim Siêu Nhân Nhật Bản',
a6213a49 5732 },
5733 'playlist_mincount': 200,
976ae3ea 5734 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5735 }, {
5736 'note': 'Playlist with unavailable videos in page 7',
5737 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5738 'info_dict': {
5739 'title': 'Uploads from BlankTV',
5740 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5741 'channel': 'BlankTV',
7666b936 5742 'channel_url': 'https://www.youtube.com/channel/UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5743 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5744 'view_count': int,
5745 'tags': [],
976ae3ea 5746 'modified_date': r're:\d{8}',
5747 'description': '',
c26f9b99 5748 'availability': 'public',
7666b936 5749 'uploader_id': '@blanktv',
5750 'uploader': 'BlankTV',
5751 'uploader_url': 'https://www.youtube.com/@blanktv',
a6213a49 5752 },
5753 'playlist_mincount': 1000,
976ae3ea 5754 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5755 }, {
5756 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5757 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5758 'info_dict': {
5759 'title': 'Data Analysis with Dr Mike Pound',
5760 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
a6213a49 5761 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5762 'tags': [],
5763 'view_count': int,
5764 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
7666b936 5765 'channel_url': 'https://www.youtube.com/channel/UC9-y-6csu5WGm29I7JiwpnA',
976ae3ea 5766 'channel': 'Computerphile',
c26f9b99 5767 'availability': 'public',
6141346d 5768 'modified_date': '20190712',
7666b936 5769 'uploader_id': '@Computerphile',
5770 'uploader': 'Computerphile',
5771 'uploader_url': 'https://www.youtube.com/@Computerphile',
a6213a49 5772 },
5773 'playlist_mincount': 11,
5774 }, {
5775 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5776 'only_matching': True,
5777 }, {
5778 'note': 'Playlist URL that does not actually serve a playlist',
5779 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5780 'info_dict': {
5781 'id': 'FqZTN594JQw',
5782 'ext': 'webm',
5783 'title': "Smiley's People 01 detective, Adventure Series, Action",
a6213a49 5784 'upload_date': '20150526',
5785 'license': 'Standard YouTube License',
5786 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5787 'categories': ['People & Blogs'],
5788 'tags': list,
5789 'view_count': int,
5790 'like_count': int,
a6213a49 5791 },
5792 'params': {
5793 'skip_download': True,
5794 },
5795 'skip': 'This video is not available.',
5796 'add_ie': [YoutubeIE.ie_key()],
5797 }, {
5798 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5799 'only_matching': True,
5800 }, {
5801 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5802 'only_matching': True,
5803 }, {
5804 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5805 'info_dict': {
14a14335 5806 'id': 'hGkQjiJLjWQ', # This will keep changing
a6213a49 5807 'ext': 'mp4',
976ae3ea 5808 'title': str,
a6213a49 5809 'upload_date': r're:\d{8}',
976ae3ea 5810 'description': str,
a6213a49 5811 'categories': ['News & Politics'],
5812 'tags': list,
5813 'like_count': int,
86973308 5814 'release_timestamp': int,
976ae3ea 5815 'channel': 'Sky News',
5816 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5817 'age_limit': 0,
5818 'view_count': int,
86973308 5819 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
976ae3ea 5820 'playable_in_embed': True,
86973308 5821 'release_date': r're:\d+',
976ae3ea 5822 'availability': 'public',
5823 'live_status': 'is_live',
5824 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
86973308
M
5825 'channel_follower_count': int,
5826 'concurrent_view_count': int,
7666b936 5827 'uploader_url': 'https://www.youtube.com/@SkyNews',
5828 'uploader_id': '@SkyNews',
5829 'uploader': 'Sky News',
8213ce28 5830 'channel_is_verified': True,
a6213a49 5831 },
5832 'params': {
5833 'skip_download': True,
5834 },
976ae3ea 5835 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5836 }, {
5837 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5838 'info_dict': {
5839 'id': 'a48o2S1cPoo',
5840 'ext': 'mp4',
5841 'title': 'The Young Turks - Live Main Show',
a6213a49 5842 'upload_date': '20150715',
5843 'license': 'Standard YouTube License',
5844 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5845 'categories': ['News & Politics'],
5846 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5847 'like_count': int,
a6213a49 5848 },
5849 'params': {
5850 'skip_download': True,
5851 },
5852 'only_matching': True,
5853 }, {
5854 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5855 'only_matching': True,
5856 }, {
5857 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5858 'only_matching': True,
5859 }, {
5860 'note': 'A channel that is not live. Should raise error',
5861 'url': 'https://www.youtube.com/user/numberphile/live',
5862 'only_matching': True,
5863 }, {
5864 'url': 'https://www.youtube.com/feed/trending',
5865 'only_matching': True,
5866 }, {
5867 'url': 'https://www.youtube.com/feed/library',
5868 'only_matching': True,
5869 }, {
5870 'url': 'https://www.youtube.com/feed/history',
5871 'only_matching': True,
5872 }, {
5873 'url': 'https://www.youtube.com/feed/subscriptions',
5874 'only_matching': True,
5875 }, {
5876 'url': 'https://www.youtube.com/feed/watch_later',
5877 'only_matching': True,
5878 }, {
5879 'note': 'Recommended - redirects to home page.',
5880 'url': 'https://www.youtube.com/feed/recommended',
5881 'only_matching': True,
5882 }, {
5883 'note': 'inline playlist with not always working continuations',
5884 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5885 'only_matching': True,
5886 }, {
5887 'url': 'https://www.youtube.com/course',
5888 'only_matching': True,
5889 }, {
5890 'url': 'https://www.youtube.com/zsecurity',
5891 'only_matching': True,
5892 }, {
5893 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5894 'only_matching': True,
5895 }, {
5896 'url': 'https://www.youtube.com/TheYoungTurks/live',
5897 'only_matching': True,
5898 }, {
5899 'url': 'https://www.youtube.com/hashtag/cctv9',
5900 'info_dict': {
5901 'id': 'cctv9',
5902 'title': '#cctv9',
976ae3ea 5903 'tags': [],
a6213a49 5904 },
4dc23a80 5905 'playlist_mincount': 300, # not consistent but should be over 300
a6213a49 5906 }, {
5907 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5908 'only_matching': True,
5909 }, {
5910 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5911 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5912 'only_matching': True
5913 }, {
5914 'note': '/browse/ should redirect to /channel/',
5915 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5916 'only_matching': True
5917 }, {
5918 'note': 'VLPL, should redirect to playlist?list=PL...',
5919 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5920 'info_dict': {
5921 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
a6213a49 5922 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
12a1b225 5923 'title': 'NCS : All Releases 💿',
7666b936 5924 'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
976ae3ea 5925 'modified_date': r're:\d{8}',
5926 'view_count': int,
5927 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5928 'tags': [],
5929 'channel': 'NoCopyrightSounds',
c26f9b99 5930 'availability': 'public',
7666b936 5931 'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds',
5932 'uploader': 'NoCopyrightSounds',
5933 'uploader_id': '@NoCopyrightSounds',
a6213a49 5934 },
5935 'playlist_mincount': 166,
7666b936 5936 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden', 'YouTube Music is not directly supported'],
a6213a49 5937 }, {
7666b936 5938 # TODO: fix 'unviewable' issue with this playlist when reloading with unavailable videos
a6213a49 5939 'note': 'Topic, should redirect to playlist?list=UU...',
5940 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5941 'info_dict': {
5942 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5943 'title': 'Uploads from Royalty Free Music - Topic',
976ae3ea 5944 'tags': [],
5945 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5946 'channel': 'Royalty Free Music - Topic',
5947 'view_count': int,
5948 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
976ae3ea 5949 'modified_date': r're:\d{8}',
976ae3ea 5950 'description': '',
c26f9b99 5951 'availability': 'public',
7666b936 5952 'uploader': 'Royalty Free Music - Topic',
a6213a49 5953 },
a6213a49 5954 'playlist_mincount': 101,
7666b936 5955 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5956 }, {
86973308
M
5957 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5958 # Treat as a general feed
a6213a49 5959 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5960 'info_dict': {
5961 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5962 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5963 'tags': [],
a6213a49 5964 },
a6213a49 5965 'playlist_mincount': 9,
5966 }, {
5967 'note': 'Youtube music Album',
5968 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5969 'info_dict': {
5970 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5971 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5972 'tags': [],
5973 'view_count': int,
5974 'description': '',
5975 'availability': 'unlisted',
5976 'modified_date': r're:\d{8}',
a6213a49 5977 },
5978 'playlist_count': 50,
7666b936 5979 'expected_warnings': ['YouTube Music is not directly supported'],
a6213a49 5980 }, {
5981 'note': 'unlisted single video playlist',
5982 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5983 'info_dict': {
a6213a49 5984 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5985 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5986 'availability': 'unlisted',
5987 'tags': [],
12a1b225 5988 'modified_date': '20220418',
976ae3ea 5989 'channel': 'colethedj',
5990 'view_count': int,
5991 'description': '',
976ae3ea 5992 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5993 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
7666b936 5994 'uploader_url': 'https://www.youtube.com/@colethedj1894',
5995 'uploader_id': '@colethedj1894',
5996 'uploader': 'colethedj',
a6213a49 5997 },
93e12ed7 5998 'playlist': [{
5999 'info_dict': {
6000 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
6001 'id': 'BaW_jenozKc',
6002 '_type': 'url',
6003 'ie_key': 'Youtube',
6004 'duration': 10,
6005 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
6006 'channel_url': 'https://www.youtube.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
6007 'view_count': int,
6008 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc',
6009 'channel': 'Philipp Hagemeister',
6010 'uploader_id': '@PhilippHagemeister',
6011 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
6012 'uploader': 'Philipp Hagemeister',
6013 }
6014 }],
a6213a49 6015 'playlist_count': 1,
93e12ed7 6016 'params': {'extract_flat': True},
a6213a49 6017 }, {
6018 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
6019 'url': 'https://www.youtube.com/feed/recommended',
6020 'info_dict': {
6021 'id': 'recommended',
6022 'title': 'recommended',
6c73052c 6023 'tags': [],
a6213a49 6024 },
6025 'playlist_mincount': 50,
6026 'params': {
6027 'skip_download': True,
6028 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6029 },
6030 }, {
6031 'note': 'API Fallback: /videos tab, sorted by oldest first',
6032 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
6033 'info_dict': {
6034 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
6035 'title': 'Cody\'sLab - Videos',
6036 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
976ae3ea 6037 'channel': 'Cody\'sLab',
6038 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
6039 'tags': [],
6040 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 6041 'channel_follower_count': int
a6213a49 6042 },
6043 'playlist_mincount': 650,
6044 'params': {
6045 'skip_download': True,
6046 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6047 },
86973308 6048 'skip': 'Query for sorting no longer works',
a6213a49 6049 }, {
6050 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
6051 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
6052 'info_dict': {
6053 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 6054 'title': 'Uploads from Royalty Free Music - Topic',
976ae3ea 6055 'modified_date': r're:\d{8}',
6056 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
6057 'description': '',
6058 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
6059 'tags': [],
6060 'channel': 'Royalty Free Music - Topic',
6061 'view_count': int,
c26f9b99 6062 'availability': 'public',
7666b936 6063 'uploader': 'Royalty Free Music - Topic',
a6213a49 6064 },
a6213a49 6065 'playlist_mincount': 101,
6066 'params': {
6067 'skip_download': True,
6068 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6069 },
7666b936 6070 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
7c219ea6 6071 }, {
6072 'note': 'non-standard redirect to regional channel',
6073 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
6074 'only_matching': True
61d3665d 6075 }, {
6076 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
6077 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
6078 'info_dict': {
6079 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
6080 'modified_date': '20220407',
6081 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
6082 'tags': [],
61d3665d 6083 'availability': 'unlisted',
6084 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
6085 'channel': 'pukkandan',
6086 'description': 'Test for collaborative playlist',
6087 'title': 'yt-dlp test - collaborative playlist',
12a1b225 6088 'view_count': int,
7666b936 6089 'uploader_url': 'https://www.youtube.com/@pukkandan',
6090 'uploader_id': '@pukkandan',
6091 'uploader': 'pukkandan',
61d3665d 6092 },
6093 'playlist_mincount': 2
c26f9b99 6094 }, {
6095 'note': 'translated tab name',
6096 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
6097 'info_dict': {
6098 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6099 'tags': [],
c26f9b99 6100 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
4dc23a80 6101 'description': 'test description',
c26f9b99 6102 'title': 'cole-dlp-test-acc - 再生リスト',
c26f9b99 6103 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6104 'channel': 'cole-dlp-test-acc',
7666b936 6105 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6106 'uploader_id': '@coletdjnz',
6107 'uploader': 'cole-dlp-test-acc',
c26f9b99 6108 },
6109 'playlist_mincount': 1,
6110 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
6111 'expected_warnings': ['Preferring "ja"'],
6112 }, {
6113 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
6114 'note': 'preferred lang set with playlist with translated video titles',
6115 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
6116 'info_dict': {
6117 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
6118 'tags': [],
6119 'view_count': int,
6120 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
c26f9b99 6121 'channel': 'cole-dlp-test-acc',
6122 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6123 'description': 'test',
c26f9b99 6124 'title': 'dlp test playlist',
6125 'availability': 'public',
7666b936 6126 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6127 'uploader_id': '@coletdjnz',
6128 'uploader': 'cole-dlp-test-acc',
c26f9b99 6129 },
6130 'playlist_mincount': 1,
6131 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
6132 'expected_warnings': ['Preferring "ja"'],
80eb0bd9 6133 }, {
6134 # shorts audio pivot for 2GtVksBMYFM.
6135 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
6136 'info_dict': {
6137 'id': 'sfv_audio_pivot',
6138 'title': 'sfv_audio_pivot',
6139 'tags': [],
6140 },
6141 'playlist_mincount': 50,
6142
86973308
M
6143 }, {
6144 # Channel with a real live tab (not to be mistaken with streams tab)
6145 # Do not treat like it should redirect to live stream
6146 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
6147 'info_dict': {
6148 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
6149 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
6150 'tags': [],
6151 },
6152 'playlist_mincount': 20,
6153 }, {
6154 # Tab name is not the same as tab id
6155 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
6156 'info_dict': {
6157 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6158 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
6159 'tags': [],
6160 },
6161 'playlist_mincount': 8,
6162 }, {
6163 # Home tab id is literally home. Not to get mistaken with featured
6164 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
6165 'info_dict': {
6166 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6167 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
6168 'tags': [],
6169 },
6170 'playlist_mincount': 8,
6171 }, {
6172 # Should get three playlists for videos, shorts and streams tabs
6173 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
6174 'info_dict': {
6175 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
bd7e919a 6176 'title': 'Polka Ch. 尾丸ポルカ',
6177 'channel_follower_count': int,
6178 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
6179 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
7666b936 6180 'description': 'md5:e56b74b5bb7e9c701522162e9abfb822',
bd7e919a 6181 'channel': 'Polka Ch. 尾丸ポルカ',
6182 'tags': 'count:35',
7666b936 6183 'uploader_url': 'https://www.youtube.com/@OmaruPolka',
6184 'uploader': 'Polka Ch. 尾丸ポルカ',
6185 'uploader_id': '@OmaruPolka',
86973308
M
6186 },
6187 'playlist_count': 3,
6188 }, {
6189 # Shorts tab with channel with handle
7666b936 6190 # TODO: fix channel description
86973308
M
6191 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
6192 'info_dict': {
6193 'id': 'UC0intLFzLaudFG-xAvUEO-A',
6194 'title': 'Not Just Bikes - Shorts',
6195 'tags': 'count:12',
86973308 6196 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
7666b936 6197 'description': 'md5:26bc55af26855a608a5cf89dfa595c8d',
86973308 6198 'channel_follower_count': int,
86973308 6199 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
86973308 6200 'channel': 'Not Just Bikes',
7666b936 6201 'uploader_url': 'https://www.youtube.com/@NotJustBikes',
6202 'uploader': 'Not Just Bikes',
6203 'uploader_id': '@NotJustBikes',
86973308
M
6204 },
6205 'playlist_mincount': 10,
6206 }, {
6207 # Streams tab
6208 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
6209 'info_dict': {
6210 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6211 'title': '中村悠一 - Live',
6212 'tags': 'count:7',
6213 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6214 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
86973308 6215 'channel': '中村悠一',
86973308 6216 'channel_follower_count': int,
86973308 6217 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
7666b936 6218 'uploader_url': 'https://www.youtube.com/@Yuichi-Nakamura',
6219 'uploader_id': '@Yuichi-Nakamura',
6220 'uploader': '中村悠一',
86973308
M
6221 },
6222 'playlist_mincount': 60,
6223 }, {
6224 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
6225 # See test_youtube_lists
6226 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
6227 'only_matching': True,
6228 }, {
6229 # No uploads and no UCID given. Should fail with no uploads error
6230 # See test_youtube_lists
6231 'url': 'https://www.youtube.com/news',
6232 'only_matching': True
6233 }, {
6234 # No videos tab but has a shorts tab
6235 'url': 'https://www.youtube.com/c/TKFShorts',
6236 'info_dict': {
6237 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6238 'title': 'Shorts Break - Shorts',
7666b936 6239 'tags': 'count:48',
86973308
M
6240 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6241 'channel': 'Shorts Break',
7666b936 6242 'description': 'md5:6de33c5e7ba686e5f3efd4e19c7ef499',
86973308 6243 'channel_follower_count': int,
86973308 6244 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
7666b936 6245 'uploader_url': 'https://www.youtube.com/@ShortsBreak_Official',
6246 'uploader': 'Shorts Break',
6247 'uploader_id': '@ShortsBreak_Official',
86973308
M
6248 },
6249 'playlist_mincount': 30,
6250 }, {
6251 # Trending Now Tab. tab id is empty
6252 'url': 'https://www.youtube.com/feed/trending',
6253 'info_dict': {
6254 'id': 'trending',
6255 'title': 'trending - Now',
6256 'tags': [],
6257 },
6258 'playlist_mincount': 30,
6259 }, {
6260 # Trending Gaming Tab. tab id is empty
6261 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
6262 'info_dict': {
6263 'id': 'trending',
6264 'title': 'trending - Gaming',
6265 'tags': [],
6266 },
6267 'playlist_mincount': 30,
4dc23a80
M
6268 }, {
6269 # Shorts url result in shorts tab
7666b936 6270 # TODO: Fix channel id extraction
4dc23a80
M
6271 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6272 'info_dict': {
6273 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6274 'title': 'cole-dlp-test-acc - Shorts',
4dc23a80 6275 'channel': 'cole-dlp-test-acc',
4dc23a80
M
6276 'description': 'test description',
6277 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6278 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6279 'tags': [],
7666b936 6280 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6281 'uploader_id': '@coletdjnz',
4dc23a80 6282 'uploader': 'cole-dlp-test-acc',
4dc23a80
M
6283 },
6284 'playlist': [{
6285 'info_dict': {
7666b936 6286 # Channel data is not currently available for short renderers (as of 2023-03-01)
4dc23a80
M
6287 '_type': 'url',
6288 'ie_key': 'Youtube',
6289 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6290 'id': 'sSM9J5YH_60',
4dc23a80 6291 'title': 'SHORT short',
4dc23a80
M
6292 'view_count': int,
6293 'thumbnails': list,
6294 }
6295 }],
6296 'params': {'extract_flat': True},
6297 }, {
6298 # Live video status should be extracted
6299 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6300 'info_dict': {
6301 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6302 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6303 'tags': []
6304 },
6305 'playlist': [{
6306 'info_dict': {
6307 '_type': 'url',
6308 'ie_key': 'Youtube',
6309 'url': 'startswith:https://www.youtube.com/watch?v=',
6310 'id': str,
6311 'title': str,
6312 'live_status': 'is_live',
6313 'channel_id': str,
6314 'channel_url': str,
6315 'concurrent_view_count': int,
6316 'channel': str,
93e12ed7 6317 'uploader': str,
6318 'uploader_url': str,
14a14335 6319 'uploader_id': str,
8213ce28 6320 'channel_is_verified': bool, # this will keep changing
4dc23a80
M
6321 }
6322 }],
c7335551 6323 'params': {'extract_flat': True, 'playlist_items': '1'},
4dc23a80 6324 'playlist_mincount': 1
c7335551
M
6325 }, {
6326 # Channel renderer metadata. Contains number of videos on the channel
6327 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6328 'info_dict': {
6329 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6330 'title': 'cole-dlp-test-acc - Channels',
c7335551
M
6331 'channel': 'cole-dlp-test-acc',
6332 'description': 'test description',
6333 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6334 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6335 'tags': [],
7666b936 6336 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6337 'uploader_id': '@coletdjnz',
c7335551 6338 'uploader': 'cole-dlp-test-acc',
c7335551
M
6339 },
6340 'playlist': [{
6341 'info_dict': {
6342 '_type': 'url',
6343 'ie_key': 'YoutubeTab',
6344 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6345 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6346 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6347 'title': 'PewDiePie',
6348 'channel': 'PewDiePie',
6349 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6350 'thumbnails': list,
6351 'channel_follower_count': int,
7666b936 6352 'playlist_count': int,
6353 'uploader': 'PewDiePie',
6354 'uploader_url': 'https://www.youtube.com/@PewDiePie',
6355 'uploader_id': '@PewDiePie',
8213ce28 6356 'channel_is_verified': True,
c7335551
M
6357 }
6358 }],
6359 'params': {'extract_flat': True},
31e18355 6360 }, {
6361 'url': 'https://www.youtube.com/@3blue1brown/about',
6362 'info_dict': {
6363 'id': 'UCYO_jab_esuFRV4b17AJtAw',
6364 'tags': ['Mathematics'],
6365 'title': '3Blue1Brown - About',
31e18355 6366 'channel_follower_count': int,
6367 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
31e18355 6368 'channel': '3Blue1Brown',
31e18355 6369 'view_count': int,
6370 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6371 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
7666b936 6372 'uploader_url': 'https://www.youtube.com/@3blue1brown',
6373 'uploader_id': '@3blue1brown',
6374 'uploader': '3Blue1Brown',
8213ce28 6375 'channel_is_verified': True,
31e18355 6376 },
6377 'playlist_count': 0,
447afb9e 6378 }, {
6379 # Podcasts tab, with rich entry playlistRenderers
6380 'url': 'https://www.youtube.com/@99percentinvisiblepodcast/podcasts',
6381 'info_dict': {
6382 'id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6383 'channel_id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6384 'uploader_url': 'https://www.youtube.com/@99percentinvisiblepodcast',
6385 'description': 'md5:3a0ed38f1ad42a68ef0428c04a15695c',
6386 'title': '99 Percent Invisible - Podcasts',
6387 'uploader': '99 Percent Invisible',
6388 'channel_follower_count': int,
6389 'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6390 'tags': [],
6391 'channel': '99 Percent Invisible',
6392 'uploader_id': '@99percentinvisiblepodcast',
6393 },
6394 'playlist_count': 1,
6395 }, {
6396 # Releases tab, with rich entry playlistRenderers (same as Podcasts tab)
6397 'url': 'https://www.youtube.com/@AHimitsu/releases',
6398 'info_dict': {
6399 'id': 'UCgFwu-j5-xNJml2FtTrrB3A',
6400 'channel': 'A Himitsu',
6401 'uploader_url': 'https://www.youtube.com/@AHimitsu',
6402 'title': 'A Himitsu - Releases',
6403 'uploader_id': '@AHimitsu',
6404 'uploader': 'A Himitsu',
6405 'channel_id': 'UCgFwu-j5-xNJml2FtTrrB3A',
6406 'tags': 'count:16',
6407 'description': 'I make music',
6408 'channel_url': 'https://www.youtube.com/channel/UCgFwu-j5-xNJml2FtTrrB3A',
6409 'channel_follower_count': int,
8213ce28 6410 'channel_is_verified': True,
447afb9e 6411 },
6412 'playlist_mincount': 10,
fcbc9ed7 6413 }, {
6414 # Playlist with only shorts, shown as reel renderers
6415 # FIXME: future: YouTube currently doesn't give continuation for this,
6416 # may do in future.
6417 'url': 'https://www.youtube.com/playlist?list=UUxqPAgubo4coVn9Lx1FuKcg',
6418 'info_dict': {
6419 'id': 'UUxqPAgubo4coVn9Lx1FuKcg',
6420 'channel_url': 'https://www.youtube.com/channel/UCxqPAgubo4coVn9Lx1FuKcg',
6421 'view_count': int,
6422 'uploader_id': '@BangyShorts',
6423 'description': '',
6424 'uploader_url': 'https://www.youtube.com/@BangyShorts',
6425 'channel_id': 'UCxqPAgubo4coVn9Lx1FuKcg',
6426 'channel': 'Bangy Shorts',
6427 'uploader': 'Bangy Shorts',
6428 'tags': [],
6429 'availability': 'public',
6430 'modified_date': '20230626',
6431 'title': 'Uploads from Bangy Shorts',
6432 },
6433 'playlist_mincount': 100,
6434 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 6435 }]
6436
6437 @classmethod
6438 def suitable(cls, url):
86e5f3ed 6439 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 6440
86973308
M
6441 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6442
6443 def _get_url_mobj(self, url):
6444 mobj = self._URL_RE.match(url).groupdict()
6445 mobj.update((k, '') for k, v in mobj.items() if v is None)
6446 return mobj
6447
6448 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6449 tab_name = (tab.get('title') or '').lower()
6450 tab_url = urljoin(base_url, traverse_obj(
6451 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6452
bd7e919a 6453 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6454 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
86973308 6455 if tab_id:
bd7e919a 6456 return {
6457 'TAB_ID_SPONSORSHIPS': 'membership',
6458 }.get(tab_id, tab_id), tab_name
86973308
M
6459
6460 # Fallback to tab name if we cannot get the tab id.
6461 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6462 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
bd7e919a 6463 if tab_name:
6464 self.write_debug(f'Falling back to selected tab name: {tab_name}')
86973308
M
6465 return {
6466 'home': 'featured',
6467 'live': 'streams',
6468 }.get(tab_name, tab_name), tab_name
6469
6470 def _has_tab(self, tabs, tab_id):
6471 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
fe03a6cd 6472
044886c2 6473 def _empty_playlist(self, item_id, data):
6474 return self.playlist_result([], item_id, **self._extract_metadata_from_tabs(item_id, data))
6475
182bda88 6476 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6477 def _real_extract(self, url, smuggled_data):
cd7c66cf 6478 item_id = self._match_id(url)
14f25df2 6479 url = urllib.parse.urlunparse(
6480 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 6481 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 6482
86973308
M
6483 mobj = self._get_url_mobj(url)
6484 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
bd7e919a 6485 if is_channel and smuggled_data.get('is_music_url'):
6486 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6487 return self.url_result(
6488 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6489 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6490 mdata = self._extract_tab_endpoint(
6491 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6492 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6493 get_all=False, expected_type=str)
6494 if not murl:
6495 raise ExtractorError('Failed to resolve album to playlist')
6496 return self.url_result(murl, YoutubeTabIE)
6497 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6498 return self.url_result(
6499 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6500
6501 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
fe03a6cd 6502 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6503 url = f'{pre}/videos{post}'
5b28cef7 6504 if smuggled_data.get('is_music_url'):
6505 self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}')
cd7c66cf 6506
6507 # Handle both video/playlist URLs
201c1459 6508 qs = parse_qs(url)
bd7e919a 6509 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
fe03a6cd 6510 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 6511 if not playlist_id:
fe03a6cd 6512 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
bd7e919a 6513 raise ExtractorError('A video URL was given without video ID', expected=True)
fe03a6cd 6514 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 6515 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
bd7e919a 6516 return self.url_result(
6517 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
cd7c66cf 6518
86973308
M
6519 if not self._yes_playlist(playlist_id, video_id):
6520 return self.url_result(
6521 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6522
bd7e919a 6523 data, ytcfg = self._extract_data(url, display_id)
14fdfea9 6524
7c219ea6 6525 # YouTube may provide a non-standard redirect to the regional channel
6526 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
86973308 6527 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
7c219ea6 6528 redirect_url = traverse_obj(
6529 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6530 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6531 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
86973308
M
6532 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6533 return self.url_result(redirect_url, YoutubeTabIE)
7c219ea6 6534
bd7e919a 6535 tabs, extra_tabs = self._extract_tab_renderers(data), []
86973308 6536 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
18db7548 6537 selected_tab = self._extract_selected_tab(tabs)
86973308
M
6538 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6539 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6540
044886c2 6541 # /about is no longer a tab
6542 if original_tab_id == 'about':
6543 return self._empty_playlist(item_id, data)
6544
86973308 6545 if not original_tab_id and selected_tab_name:
bd7e919a 6546 self.to_screen('Downloading all uploads of the channel. '
86973308
M
6547 'To download only the videos in a specific tab, pass the tab\'s URL')
6548 if self._has_tab(tabs, 'streams'):
bd7e919a 6549 extra_tabs.append(''.join((pre, '/streams', post)))
86973308 6550 if self._has_tab(tabs, 'shorts'):
bd7e919a 6551 extra_tabs.append(''.join((pre, '/shorts', post)))
86973308
M
6552 # XXX: Members-only tab should also be extracted
6553
bd7e919a 6554 if not extra_tabs and selected_tab_id != 'videos':
86973308
M
6555 # Channel does not have streams, shorts or videos tabs
6556 if item_id[:2] != 'UC':
044886c2 6557 return self._empty_playlist(item_id, data)
86973308
M
6558
6559 # Topic channels don't have /videos. Use the equivalent playlist instead
6560 pl_id = f'UU{item_id[2:]}'
6561 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6562 try:
6563 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6564 except ExtractorError:
044886c2 6565 return self._empty_playlist(item_id, data)
64f36541 6566 else:
86973308
M
6567 item_id, url = pl_id, pl_url
6568 self.to_screen(
6569 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6570
bd7e919a 6571 elif extra_tabs and selected_tab_id != 'videos':
86973308 6572 # When there are shorts/live tabs but not videos tab
bd7e919a 6573 url, data = f'{pre}{post}', None
86973308
M
6574
6575 elif (original_tab_id or 'videos') != selected_tab_id:
6576 if original_tab_id == 'live':
6577 # Live tab should have redirected to the video
6578 # Except in the case the channel has an actual live tab
6579 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
bd7e919a 6580 raise UserNotLive(video_id=item_id)
86973308
M
6581 elif selected_tab_name:
6582 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6583
6584 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6585 url = f'{pre}{post}'
18db7548 6586
358de58c 6587 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 6588 if 'no-youtube-unavailable-videos' not in compat_opts:
bd7e919a 6589 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
c0ac49bc 6590 self._extract_and_report_alerts(data, only_once=True)
86973308 6591
bd7e919a 6592 tabs, entries = self._extract_tab_renderers(data), []
8bdd16b4 6593 if tabs:
bd7e919a 6594 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6595 entries[0].update({
86973308
M
6596 'extractor_key': YoutubeTabIE.ie_key(),
6597 'extractor': YoutubeTabIE.IE_NAME,
6598 'webpage_url': url,
6599 })
bd7e919a 6600 if self.get_param('playlist_items') == '0':
6601 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6602 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6603 entries.extend(map(self._real_extract, extra_tabs))
6604
6605 if len(entries) == 1:
6606 return entries[0]
6607 elif entries:
6608 metadata = self._extract_metadata_from_tabs(item_id, data)
6609 uploads_url = 'the Uploads (UU) playlist URL'
6610 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6611 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6612 self.to_screen(
6613 'Downloading as multiple playlists, separated by tabs. '
6614 f'To download as a single playlist instead, pass {uploads_url}')
6615 return self.playlist_result(entries, item_id, **metadata)
6616
6617 # Inline playlist
37e57a9f 6618 playlist = traverse_obj(
6619 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 6620 if playlist:
ac56cf38 6621 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 6622
37e57a9f 6623 video_id = traverse_obj(
6624 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 6625 if video_id:
bd7e919a 6626 if tab != '/live': # live tab is expected to redirect to video
37e57a9f 6627 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
86973308 6628 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6629
8bdd16b4 6630 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 6631
c5e8d7af 6632
8bdd16b4 6633class YoutubePlaylistIE(InfoExtractor):
96565c7e 6634 IE_DESC = 'YouTube playlists'
8bdd16b4 6635 _VALID_URL = r'''(?x)(?:
6636 (?:https?://)?
6637 (?:\w+\.)?
6638 (?:
6639 (?:
6640 youtube(?:kids)?\.com|
d9190e44 6641 %(invidious)s
8bdd16b4 6642 )
6643 /.*?\?.*?\blist=
6644 )?
6645 (?P<id>%(playlist_id)s)
d9190e44
RH
6646 )''' % {
6647 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6648 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6649 }
8bdd16b4 6650 IE_NAME = 'youtube:playlist'
cdc628a4 6651 _TESTS = [{
8bdd16b4 6652 'note': 'issue #673',
6653 'url': 'PLBB231211A4F62143',
cdc628a4 6654 'info_dict': {
8bdd16b4 6655 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6656 'id': 'PLBB231211A4F62143',
976ae3ea 6657 'uploader': 'Wickman',
7666b936 6658 'uploader_id': '@WickmanVT',
11f9be09 6659 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 6660 'view_count': int,
7666b936 6661 'uploader_url': 'https://www.youtube.com/@WickmanVT',
976ae3ea 6662 'modified_date': r're:\d{8}',
6663 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6664 'channel': 'Wickman',
6665 'tags': [],
7666b936 6666 'channel_url': 'https://www.youtube.com/channel/UCKSpbfbl5kRQpTdL7kMc-1Q',
86973308 6667 'availability': 'public',
8bdd16b4 6668 },
6669 'playlist_mincount': 29,
6670 }, {
6671 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6672 'info_dict': {
6673 'title': 'YDL_safe_search',
6674 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6675 },
6676 'playlist_count': 2,
6677 'skip': 'This playlist is private',
9558dcec 6678 }, {
8bdd16b4 6679 'note': 'embedded',
6680 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6681 'playlist_count': 4,
9558dcec 6682 'info_dict': {
8bdd16b4 6683 'title': 'JODA15',
6684 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6685 'uploader': 'milan',
7666b936 6686 'uploader_id': '@milan5503',
976ae3ea 6687 'description': '',
6688 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6689 'tags': [],
6690 'modified_date': '20140919',
6691 'view_count': int,
6692 'channel': 'milan',
6693 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
7666b936 6694 'uploader_url': 'https://www.youtube.com/@milan5503',
c26f9b99 6695 'availability': 'public',
976ae3ea 6696 },
b012271d 6697 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden', 'Retrying', 'Giving up'],
cdc628a4 6698 }, {
8bdd16b4 6699 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 6700 'playlist_mincount': 455,
8bdd16b4 6701 'info_dict': {
6702 'title': '2018 Chinese New Singles (11/6 updated)',
6703 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6704 'uploader': 'LBK',
7666b936 6705 'uploader_id': '@music_king',
11f9be09 6706 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 6707 'channel': 'LBK',
6708 'view_count': int,
7666b936 6709 'channel_url': 'https://www.youtube.com/channel/UC21nz3_MesPLqtDqwdvnoxA',
976ae3ea 6710 'tags': [],
7666b936 6711 'uploader_url': 'https://www.youtube.com/@music_king',
976ae3ea 6712 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6713 'modified_date': r're:\d{8}',
c26f9b99 6714 'availability': 'public',
976ae3ea 6715 },
6716 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 6717 }, {
29f7c58a 6718 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6719 'only_matching': True,
6720 }, {
6721 # music album playlist
6722 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6723 'only_matching': True,
6724 }]
6725
6726 @classmethod
6727 def suitable(cls, url):
201c1459 6728 if YoutubeTabIE.suitable(url):
6729 return False
49a57e70 6730 from ..utils import parse_qs
201c1459 6731 qs = parse_qs(url)
6732 if qs.get('v', [None])[0]:
6733 return False
86e5f3ed 6734 return super().suitable(url)
29f7c58a 6735
6736 def _real_extract(self, url):
6737 playlist_id = self._match_id(url)
46953e7e 6738 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 6739 url = update_url_query(
6740 'https://www.youtube.com/playlist',
6741 parse_qs(url) or {'list': playlist_id})
6742 if is_music_url:
6743 url = smuggle_url(url, {'is_music_url': True})
6744 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 6745
6746
6747class YoutubeYtBeIE(InfoExtractor):
c76eb41b 6748 IE_DESC = 'youtu.be'
29f7c58a 6749 _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}
6750 _TESTS = [{
8bdd16b4 6751 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6752 'info_dict': {
6753 'id': 'yeWKywCrFtk',
6754 'ext': 'mp4',
6755 'title': 'Small Scale Baler and Braiding Rugs',
6756 'uploader': 'Backus-Page House Museum',
7666b936 6757 'uploader_id': '@backuspagemuseum',
6758 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@backuspagemuseum',
8bdd16b4 6759 'upload_date': '20161008',
6760 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6761 'categories': ['Nonprofits & Activism'],
6762 'tags': list,
6763 'like_count': int,
976ae3ea 6764 'age_limit': 0,
6765 'playable_in_embed': True,
7666b936 6766 'thumbnail': r're:^https?://.*\.webp',
976ae3ea 6767 'channel': 'Backus-Page House Museum',
6768 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6769 'live_status': 'not_live',
6770 'view_count': int,
6771 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6772 'availability': 'public',
6773 'duration': 59,
12a1b225
A
6774 'comment_count': int,
6775 'channel_follower_count': int
8bdd16b4 6776 },
6777 'params': {
6778 'noplaylist': True,
6779 'skip_download': True,
6780 },
39e7107d 6781 }, {
8bdd16b4 6782 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 6783 'only_matching': True,
cdc628a4
PH
6784 }]
6785
8bdd16b4 6786 def _real_extract(self, url):
5ad28e7f 6787 mobj = self._match_valid_url(url)
29f7c58a 6788 video_id = mobj.group('id')
6789 playlist_id = mobj.group('playlist_id')
8bdd16b4 6790 return self.url_result(
29f7c58a 6791 update_url_query('https://www.youtube.com/watch', {
6792 'v': video_id,
6793 'list': playlist_id,
6794 'feature': 'youtu.be',
6795 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 6796
6797
b6ce9bb0 6798class YoutubeLivestreamEmbedIE(InfoExtractor):
6799 IE_DESC = 'YouTube livestream embeds'
6800 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6801 _TESTS = [{
6802 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6803 'only_matching': True,
6804 }]
6805
6806 def _real_extract(self, url):
6807 channel_id = self._match_id(url)
6808 return self.url_result(
6809 f'https://www.youtube.com/channel/{channel_id}/live',
6810 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6811
6812
8bdd16b4 6813class YoutubeYtUserIE(InfoExtractor):
96565c7e 6814 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 6815 IE_NAME = 'youtube:user'
8bdd16b4 6816 _VALID_URL = r'ytuser:(?P<id>.+)'
6817 _TESTS = [{
6818 'url': 'ytuser:phihag',
6819 'only_matching': True,
6820 }]
6821
6822 def _real_extract(self, url):
6823 user_id = self._match_id(url)
08270da5 6824 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
9558dcec 6825
b05654f0 6826
3d3dddc9 6827class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 6828 IE_NAME = 'youtube:favorites'
96565c7e 6829 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 6830 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6831 _LOGIN_REQUIRED = True
6832 _TESTS = [{
6833 'url': ':ytfav',
6834 'only_matching': True,
6835 }, {
6836 'url': ':ytfavorites',
6837 'only_matching': True,
6838 }]
6839
6840 def _real_extract(self, url):
6841 return self.url_result(
6842 'https://www.youtube.com/playlist?list=LL',
6843 ie=YoutubeTabIE.ie_key())
6844
6845
ca5300c7 6846class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6847 IE_NAME = 'youtube:notif'
6848 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6849 _VALID_URL = r':ytnotif(?:ication)?s?'
6850 _LOGIN_REQUIRED = True
6851 _TESTS = [{
6852 'url': ':ytnotif',
6853 'only_matching': True,
6854 }, {
6855 'url': ':ytnotifications',
6856 'only_matching': True,
6857 }]
6858
6859 def _extract_notification_menu(self, response, continuation_list):
6860 notification_list = traverse_obj(
6861 response,
6862 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6863 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6864 expected_type=list) or []
6865 continuation_list[0] = None
6866 for item in notification_list:
6867 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6868 if entry:
6869 yield entry
6870 continuation = item.get('continuationItemRenderer')
6871 if continuation:
6872 continuation_list[0] = continuation
6873
6874 def _extract_notification_renderer(self, notification):
6875 video_id = traverse_obj(
6876 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6877 url = f'https://www.youtube.com/watch?v={video_id}'
6878 channel_id = None
6879 if not video_id:
6880 browse_ep = traverse_obj(
6881 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
7666b936 6882 channel_id = self.ucid_or_none(traverse_obj(browse_ep, 'browseId', expected_type=str))
ca5300c7 6883 post_id = self._search_regex(
6884 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6885 'post id', default=None)
6886 if not channel_id or not post_id:
6887 return
6888 # The direct /post url redirects to this in the browser
6889 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6890
6891 channel = traverse_obj(
6892 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6893 expected_type=str)
c7a7baaa 6894 notification_title = self._get_text(notification, 'shortMessage')
6895 if notification_title:
6896 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6897 # TODO: handle recommended videos
ca5300c7 6898 title = self._search_regex(
c7a7baaa 6899 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 6900 'video title', default=None)
5225df50 6901 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6902 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6903 else None)
ca5300c7 6904 return {
6905 '_type': 'url',
6906 'url': url,
6907 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6908 'video_id': video_id,
6909 'title': title,
6910 'channel_id': channel_id,
6911 'channel': channel,
7666b936 6912 'uploader': channel,
ca5300c7 6913 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5225df50 6914 'timestamp': timestamp,
ca5300c7 6915 }
6916
6917 def _notification_menu_entries(self, ytcfg):
6918 continuation_list = [None]
6919 response = None
6920 for page in itertools.count(1):
6921 ctoken = traverse_obj(
6922 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6923 response = self._extract_response(
6924 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6925 ep='notification/get_notification_menu', check_get_keys='actions',
6926 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6927 yield from self._extract_notification_menu(response, continuation_list)
6928 if not continuation_list[0]:
6929 break
6930
6931 def _real_extract(self, url):
6932 display_id = 'notifications'
6933 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6934 self._report_playlist_authcheck(ytcfg)
6935 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6936
6937
a6213a49 6938class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6939 IE_DESC = 'YouTube search'
78caa52a 6940 IE_NAME = 'youtube:search'
b05654f0 6941 _SEARCH_KEY = 'ytsearch'
a61fd4cf 6942 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 6943 _TESTS = [{
6944 'url': 'ytsearch5:youtube-dl test video',
6945 'playlist_count': 5,
6946 'info_dict': {
6947 'id': 'youtube-dl test video',
6948 'title': 'youtube-dl test video',
6949 }
6950 }]
b05654f0 6951
a61fd4cf 6952
5f7cb91a 6953class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 6954 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 6955 _SEARCH_KEY = 'ytsearchdate'
a6213a49 6956 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 6957 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 6958 _TESTS = [{
6959 'url': 'ytsearchdate5:youtube-dl test video',
6960 'playlist_count': 5,
6961 'info_dict': {
6962 'id': 'youtube-dl test video',
6963 'title': 'youtube-dl test video',
6964 }
6965 }]
75dff0ee 6966
c9ae7b95 6967
a6213a49 6968class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 6969 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 6970 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 6971 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 6972 _TESTS = [{
6973 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6974 'playlist_mincount': 5,
6975 'info_dict': {
11f9be09 6976 'id': 'youtube-dl test video',
3462ffa8 6977 'title': 'youtube-dl test video',
6978 }
a61fd4cf 6979 }, {
6980 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6981 'playlist_mincount': 5,
6982 'info_dict': {
6983 'id': 'python',
6984 'title': 'python',
6985 }
ad210f4f 6986 }, {
6987 'url': 'https://www.youtube.com/results?search_query=%23cats',
6988 'playlist_mincount': 1,
6989 'info_dict': {
6990 'id': '#cats',
6991 'title': '#cats',
12a1b225
A
6992 # The test suite does not have support for nested playlists
6993 # 'entries': [{
6994 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6995 # 'title': '#cats',
6996 # }],
ad210f4f 6997 },
c7335551
M
6998 }, {
6999 # Channel results
7000 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
7001 'info_dict': {
7002 'id': 'kurzgesagt',
7003 'title': 'kurzgesagt',
7004 },
7005 'playlist': [{
7006 'info_dict': {
7007 '_type': 'url',
7008 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
7009 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
7010 'ie_key': 'YoutubeTab',
7011 'channel': 'Kurzgesagt – In a Nutshell',
7012 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
7013 'title': 'Kurzgesagt – In a Nutshell',
7014 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
14a14335 7015 # No longer available for search as it is set to the handle.
7016 # 'playlist_count': int,
c7335551 7017 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
7666b936 7018 'thumbnails': list,
7019 'uploader_id': '@kurzgesagt',
7020 'uploader_url': 'https://www.youtube.com/@kurzgesagt',
7021 'uploader': 'Kurzgesagt – In a Nutshell',
8213ce28 7022 'channel_is_verified': True,
14a14335 7023 'channel_follower_count': int,
c7335551
M
7024 }
7025 }],
7026 'params': {'extract_flat': True, 'playlist_items': '1'},
7027 'playlist_mincount': 1,
3462ffa8 7028 }, {
7029 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
7030 'only_matching': True,
7031 }]
7032
7033 def _real_extract(self, url):
4dfbf869 7034 qs = parse_qs(url)
386e1dd9 7035 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 7036 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 7037
7038
16aa9ea4 7039class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 7040 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 7041 IE_NAME = 'youtube:music:search_url'
7042 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
7043 _TESTS = [{
7044 'url': 'https://music.youtube.com/search?q=royalty+free+music',
7045 'playlist_count': 16,
7046 'info_dict': {
7047 'id': 'royalty free music',
7048 'title': 'royalty free music',
7049 }
7050 }, {
7051 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
7052 'playlist_mincount': 30,
7053 'info_dict': {
7054 'id': 'royalty free music - songs',
7055 'title': 'royalty free music - songs',
7056 },
7057 'params': {'extract_flat': 'in_playlist'}
7058 }, {
7059 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
7060 'playlist_mincount': 30,
7061 'info_dict': {
7062 'id': 'royalty free music - community playlists',
7063 'title': 'royalty free music - community playlists',
7064 },
7065 'params': {'extract_flat': 'in_playlist'}
7066 }]
7067
7068 _SECTIONS = {
7069 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
7070 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
7071 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
7072 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
7073 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
7074 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
7075 }
7076
7077 def _real_extract(self, url):
7078 qs = parse_qs(url)
7079 query = (qs.get('search_query') or qs.get('q'))[0]
7080 params = qs.get('sp', (None,))[0]
7081 if params:
7082 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
7083 else:
ac668111 7084 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 7085 params = self._SECTIONS.get(section)
7086 if not params:
7087 section = None
7088 title = join_nonempty(query, section, delim=' - ')
af5c1c55 7089 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 7090
7091
182bda88 7092class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 7093 """
25f14e9f 7094 Base class for feed extractors
82d02080 7095 Subclasses must re-define the _FEED_NAME property.
d7ae0639 7096 """
b2e8bc1b 7097 _LOGIN_REQUIRED = True
82d02080 7098 _FEED_NAME = 'feeds'
a25bca9f 7099
7100 def _real_initialize(self):
7101 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 7102
82d02080 7103 @classproperty
d7ae0639 7104 def IE_NAME(self):
82d02080 7105 return f'youtube:{self._FEED_NAME}'
04cc9617 7106
3853309f 7107 def _real_extract(self, url):
3d3dddc9 7108 return self.url_result(
182bda88 7109 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
7110
7111
ef2f3c7f 7112class YoutubeWatchLaterIE(InfoExtractor):
7113 IE_NAME = 'youtube:watchlater'
96565c7e 7114 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 7115 _VALID_URL = r':ytwatchlater'
bc7a9cd8 7116 _TESTS = [{
8bdd16b4 7117 'url': ':ytwatchlater',
bc7a9cd8
S
7118 'only_matching': True,
7119 }]
25f14e9f
S
7120
7121 def _real_extract(self, url):
ef2f3c7f 7122 return self.url_result(
7123 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 7124
7125
25f14e9f 7126class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 7127 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 7128 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 7129 _FEED_NAME = 'recommended'
45db527f 7130 _LOGIN_REQUIRED = False
3d3dddc9 7131 _TESTS = [{
7132 'url': ':ytrec',
7133 'only_matching': True,
7134 }, {
7135 'url': ':ytrecommended',
7136 'only_matching': True,
7137 }, {
7138 'url': 'https://youtube.com',
7139 'only_matching': True,
7140 }]
1ed5b5c9 7141
1ed5b5c9 7142
25f14e9f 7143class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 7144 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 7145 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 7146 _FEED_NAME = 'subscriptions'
3d3dddc9 7147 _TESTS = [{
7148 'url': ':ytsubs',
7149 'only_matching': True,
7150 }, {
7151 'url': ':ytsubscriptions',
7152 'only_matching': True,
7153 }]
1ed5b5c9 7154
1ed5b5c9 7155
25f14e9f 7156class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 7157 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 7158 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 7159 _FEED_NAME = 'history'
3d3dddc9 7160 _TESTS = [{
7161 'url': ':ythistory',
7162 'only_matching': True,
7163 }]
1ed5b5c9
JMF
7164
7165
80eb0bd9 7166class YoutubeShortsAudioPivotIE(InfoExtractor):
1dd18a88 7167 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
80eb0bd9 7168 IE_NAME = 'youtube:shorts:pivot:audio'
1dd18a88 7169 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
80eb0bd9 7170 _TESTS = [{
1dd18a88 7171 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
80eb0bd9 7172 'only_matching': True,
7173 }]
7174
7175 @staticmethod
7176 def _generate_audio_pivot_params(video_id):
7177 """
7178 Generates sfv_audio_pivot browse params for this video id
7179 """
7180 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
7181 return urllib.parse.quote(base64.b64encode(pb_params).decode())
7182
7183 def _real_extract(self, url):
7184 video_id = self._match_id(url)
7185 return self.url_result(
7186 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
7187 ie=YoutubeTabIE)
7188
7189
15870e90
PH
7190class YoutubeTruncatedURLIE(InfoExtractor):
7191 IE_NAME = 'youtube:truncated_url'
7192 IE_DESC = False # Do not list
975d35db 7193 _VALID_URL = r'''(?x)
b95aab84
PH
7194 (?:https?://)?
7195 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
7196 (?:watch\?(?:
c4808c60 7197 feature=[a-z_]+|
b95aab84
PH
7198 annotation_id=annotation_[^&]+|
7199 x-yt-cl=[0-9]+|
c1708b89 7200 hl=[^&]*|
287be8c6 7201 t=[0-9]+
b95aab84
PH
7202 )?
7203 |
7204 attribution_link\?a=[^&]+
7205 )
7206 $
975d35db 7207 '''
15870e90 7208
c4808c60 7209 _TESTS = [{
2d3d2997 7210 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 7211 'only_matching': True,
dc2fc736 7212 }, {
2d3d2997 7213 'url': 'https://www.youtube.com/watch?',
dc2fc736 7214 'only_matching': True,
b95aab84
PH
7215 }, {
7216 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
7217 'only_matching': True,
7218 }, {
7219 'url': 'https://www.youtube.com/watch?feature=foo',
7220 'only_matching': True,
c1708b89
PH
7221 }, {
7222 'url': 'https://www.youtube.com/watch?hl=en-GB',
7223 'only_matching': True,
287be8c6
PH
7224 }, {
7225 'url': 'https://www.youtube.com/watch?t=2372',
7226 'only_matching': True,
c4808c60
PH
7227 }]
7228
15870e90
PH
7229 def _real_extract(self, url):
7230 raise ExtractorError(
78caa52a
PH
7231 'Did you forget to quote the URL? Remember that & is a meta '
7232 'character in most shells, so you want to put the URL in quotes, '
3867038a 7233 'like youtube-dl '
2d3d2997 7234 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 7235 ' or simply youtube-dl BaW_jenozKc .',
15870e90 7236 expected=True)
772fd5cc
PH
7237
7238
471d0367 7239class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 7240 IE_NAME = 'youtube:clip'
471d0367 7241 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
7242 _TESTS = [{
7243 # FIXME: Other metadata should be extracted from the clip, not from the base video
7244 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
7245 'info_dict': {
7246 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
7247 'ext': 'mp4',
7248 'section_start': 29.0,
7249 'section_end': 39.7,
7250 'duration': 10.7,
12a1b225
A
7251 'age_limit': 0,
7252 'availability': 'public',
7253 'categories': ['Gaming'],
7254 'channel': 'Scott The Woz',
7255 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
7256 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
7257 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
7258 'like_count': int,
7259 'playable_in_embed': True,
7260 'tags': 'count:17',
7261 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
7262 'title': 'Mobile Games on Console - Scott The Woz',
7263 'upload_date': '20210920',
7264 'uploader': 'Scott The Woz',
7666b936 7265 'uploader_id': '@ScottTheWoz',
7266 'uploader_url': 'https://www.youtube.com/@ScottTheWoz',
12a1b225
A
7267 'view_count': int,
7268 'live_status': 'not_live',
7666b936 7269 'channel_follower_count': int,
7270 'chapters': 'count:20',
14a14335 7271 'comment_count': int,
7272 'heatmap': 'count:100',
471d0367 7273 }
7274 }]
3cd786db 7275
7276 def _real_extract(self, url):
471d0367 7277 clip_id = self._match_id(url)
7278 _, data = self._extract_webpage(url, clip_id)
7279
7280 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
7281 if not video_id:
7282 raise ExtractorError('Unable to find video ID')
7283
7284 clip_data = traverse_obj(data, (
7285 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
7286 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
7287 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
7288 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
7289
7290 return {
7291 '_type': 'url_transparent',
7292 'url': f'https://www.youtube.com/watch?v={video_id}',
7293 'ie_key': YoutubeIE.ie_key(),
7294 'id': clip_id,
7295 'section_start': int(clip_data['startTimeMs']) / 1000,
7296 'section_end': int(clip_data['endTimeMs']) / 1000,
7297 }
3cd786db 7298
7299
b032ff0f 7300class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
7301 IE_NAME = 'youtube:consent'
7302 IE_DESC = False # Do not list
7303 _VALID_URL = r'https?://consent\.youtube\.com/m\?'
7304 _TESTS = [{
7305 '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',
7306 'info_dict': {
7307 'id': 'qVv6vCqciTM',
7308 'ext': 'mp4',
7309 'age_limit': 0,
7666b936 7310 'uploader_id': '@sana_natori',
b032ff0f 7311 'comment_count': int,
7312 'chapters': 'count:13',
7313 'upload_date': '20221223',
7314 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
7315 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7666b936 7316 'uploader_url': 'https://www.youtube.com/@sana_natori',
b032ff0f 7317 'like_count': int,
7318 'release_date': '20221223',
7319 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
7320 '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】',
7321 'view_count': int,
7322 'playable_in_embed': True,
7323 'duration': 4438,
7324 'availability': 'public',
7325 'channel_follower_count': int,
7326 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7327 'categories': ['Entertainment'],
7328 'live_status': 'was_live',
7329 'release_timestamp': 1671793345,
7330 'channel': 'さなちゃんねる',
7331 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
7332 'uploader': 'さなちゃんねる',
8213ce28 7333 'channel_is_verified': True,
14a14335 7334 'heatmap': 'count:100',
b032ff0f 7335 },
7336 'add_ie': ['Youtube'],
7337 'params': {'skip_download': 'Youtube'},
7338 }]
7339
7340 def _real_extract(self, url):
7341 redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
7342 if not redirect_url:
7343 raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
7344 return self.url_result(redirect_url)
7345
7346
772fd5cc
PH
7347class YoutubeTruncatedIDIE(InfoExtractor):
7348 IE_NAME = 'youtube:truncated_id'
7349 IE_DESC = False # Do not list
b95aab84 7350 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
7351
7352 _TESTS = [{
7353 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7354 'only_matching': True,
7355 }]
7356
7357 def _real_extract(self, url):
7358 video_id = self._match_id(url)
7359 raise ExtractorError(
86e5f3ed 7360 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 7361 expected=True)