]> jfr.im git - yt-dlp.git/blame - yt_dlp/extractor/youtube.py
[ie/theta] Remove extractors (#8251)
[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',
bc87dac7
B
431 r'(?:www\.)?piped\.video',
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)
950 for _ in range(main_rm.retries + icd_rm.retries + 1):
109dd3b2 951 try:
952 response = self._call_api(
953 ep=ep, fatal=True, headers=headers,
be5c1ae8 954 video_id=item_id, query=query, note=note,
109dd3b2 955 context=self._extract_context(ytcfg, default_client),
956 api_key=self._extract_api_key(ytcfg, default_client),
be5c1ae8 957 api_hostname=api_hostname, default_client=default_client)
109dd3b2 958 except ExtractorError as e:
be5c1ae8 959 if not isinstance(e.cause, network_exceptions):
960 return self._error_or_warning(e, fatal=fatal)
3d2623a8 961 elif not isinstance(e.cause, HTTPError):
eb5bdbfa 962 main_rm.error = e
963 next(main_retries)
be5c1ae8 964 continue
109dd3b2 965
3d2623a8 966 first_bytes = e.cause.response.read(512)
be5c1ae8 967 if not is_html(first_bytes):
968 yt_error = try_get(
969 self._parse_json(
3d2623a8 970 self._webpage_read_content(e.cause.response, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False),
be5c1ae8 971 lambda x: x['error']['message'], str)
972 if yt_error:
973 self._report_alerts([('ERROR', yt_error)], fatal=False)
974 # Downloading page may result in intermittent 5xx HTTP error
eb5bdbfa 975 # Sometimes a 404 is also received. See: https://github.com/ytdl-org/youtube-dl/issues/28289
be5c1ae8 976 # We also want to catch all other network exceptions since errors in later pages can be troublesome
977 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
3d2623a8 978 if e.cause.status not in (403, 429):
eb5bdbfa 979 main_rm.error = e
980 next(main_retries)
be5c1ae8 981 continue
982 return self._error_or_warning(e, fatal=fatal)
983
984 try:
985 self._extract_and_report_alerts(response, only_once=True)
986 except ExtractorError as e:
eb5bdbfa 987 # YouTube's servers may return errors we want to retry on in a 200 OK response
be5c1ae8 988 # See: https://github.com/yt-dlp/yt-dlp/issues/839
989 if 'unknown error' in e.msg.lower():
eb5bdbfa 990 main_rm.error = e
991 next(main_retries)
be5c1ae8 992 continue
993 return self._error_or_warning(e, fatal=fatal)
994 # Youtube sometimes sends incomplete data
995 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
996 if not traverse_obj(response, *variadic(check_get_keys)):
eb5bdbfa 997 icd_rm.error = ExtractorError('Incomplete data received', expected=True)
998 should_retry = next(icd_retries, None)
999 if not should_retry:
1000 return None
be5c1ae8 1001 continue
1002
1003 return response
109dd3b2 1004
9297939e 1005 @staticmethod
1006 def is_music_url(url):
5b28cef7 1007 return re.match(r'(https?://)?music\.youtube\.com/', url) is not None
9297939e 1008
30a074c2 1009 def _extract_video(self, renderer):
1010 video_id = renderer.get('videoId')
4dc23a80
M
1011
1012 reel_header_renderer = traverse_obj(renderer, (
1013 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer',
1014 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer'))
1015
1016 title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText')
052e1350 1017 description = self._get_text(renderer, 'descriptionSnippet')
6141346d
M
1018
1019 duration = int_or_none(renderer.get('lengthSeconds'))
1020 if duration is None:
1021 duration = parse_duration(self._get_text(
1022 renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
1c1b2f96 1023 if duration is None:
4dc23a80 1024 # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab)
1c1b2f96 1025 duration = parse_duration(self._search_regex(
1026 r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
1027 traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str),
1028 video_id, default=None, group='duration'))
1029
f3aa3c3f 1030 channel_id = traverse_obj(
a44ca5a4 1031 renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
1032 expected_type=str, get_all=False)
4dc23a80
M
1033 if not channel_id:
1034 channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId'))
1035
7666b936 1036 channel_id = self.ucid_or_none(channel_id)
1037
f3aa3c3f 1038 overlay_style = traverse_obj(
a44ca5a4 1039 renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
1040 get_all=False, expected_type=str)
14a14335 1041 badges = self._extract_badges(traverse_obj(renderer, 'badges'))
8213ce28 1042 owner_badges = self._extract_badges(traverse_obj(renderer, 'ownerBadges'))
fd2ad7cb 1043 navigation_url = urljoin('https://www.youtube.com/', traverse_obj(
a44ca5a4 1044 renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
1045 expected_type=str)) or ''
fd2ad7cb 1046 url = f'https://www.youtube.com/watch?v={video_id}'
a44ca5a4 1047 if overlay_style == 'SHORTS' or '/shorts/' in navigation_url:
fd2ad7cb 1048 url = f'https://www.youtube.com/shorts/{video_id}'
a709d873 1049
4dc23a80
M
1050 time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo')
1051 or self._get_text(reel_header_renderer, 'timestampText') or '')
1052 scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False))
1053
867c66ff
M
1054 live_status = (
1055 'is_upcoming' if scheduled_timestamp is not None
1056 else 'was_live' if 'streamed' in time_text.lower()
1057 else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW)
1058 else None)
1059
4dc23a80
M
1060 # videoInfo is a string like '50K views • 10 years ago'.
1061 view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or ''
1062 view_count = (0 if 'no views' in view_count_text.lower()
1063 else self._get_count({'simpleText': view_count_text}))
1064 view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count'
1065
93e12ed7 1066 channel = (self._get_text(renderer, 'ownerText', 'shortBylineText')
1067 or self._get_text(reel_header_renderer, 'channelTitleText'))
1068
1069 channel_handle = traverse_obj(renderer, (
1070 'shortBylineText', 'runs', ..., 'navigationEndpoint',
1071 (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl'))),
1072 expected_type=self.handle_from_url, get_all=False)
30a074c2 1073 return {
39ed931e 1074 '_type': 'url',
30a074c2 1075 'ie_key': YoutubeIE.ie_key(),
1076 'id': video_id,
fd2ad7cb 1077 'url': url,
30a074c2 1078 'title': title,
1079 'description': description,
1080 'duration': duration,
f3aa3c3f 1081 'channel_id': channel_id,
93e12ed7 1082 'channel': channel,
4dc23a80 1083 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
93e12ed7 1084 'uploader': channel,
1085 'uploader_id': channel_handle,
1086 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
4dc23a80 1087 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
5225df50 1088 'timestamp': (self._parse_time_text(time_text)
1089 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
1090 else None),
f3aa3c3f 1091 'release_timestamp': scheduled_timestamp,
c26f9b99 1092 'availability':
1093 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
1094 else self._availability(
1095 is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None,
1096 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
1097 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
867c66ff 1098 is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None),
4dc23a80 1099 view_count_field: view_count,
14a14335 1100 'live_status': live_status,
8213ce28 1101 'channel_is_verified': True if self._has_badge(owner_badges, BadgeType.VERIFIED) else None
30a074c2 1102 }
1103
0c148415 1104
360e1ca5 1105class YoutubeIE(YoutubeBaseInfoExtractor):
96565c7e 1106 IE_DESC = 'YouTube'
cb7dfeea 1107 _VALID_URL = r"""(?x)^
c5e8d7af 1108 (
edb53e2d 1109 (?:https?://|//) # http(s):// or protocol-independent URL
bc2ca1bb 1110 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
1111 (?:www\.)?deturl\.com/www\.youtube\.com|
1112 (?:www\.)?pwnyoutube\.com|
1113 (?:www\.)?hooktube\.com|
1114 (?:www\.)?yourepeat\.com|
1115 tube\.majestyc\.net|
1116 %(invidious)s|
1117 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
c5e8d7af
PH
1118 (?:.*?\#/)? # handle anchor (#/) redirect urls
1119 (?: # the various things that can precede the ID:
dad2210c 1120 (?:(?:v|embed|e|shorts|live)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
c5e8d7af 1121 |(?: # or the v= param in all its forms
f7000f3a 1122 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 1123 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 1124 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
1125 v=
1126 )
f4b05232 1127 ))
cbaed4bb
S
1128 |(?:
1129 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
1130 vid\.plus| # or vid.plus/xxxx
1131 zwearz\.com/watch| # or zwearz.com/watch/xxxx
bc2ca1bb 1132 %(invidious)s
cbaed4bb 1133 )/
edb53e2d 1134 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 1135 )
c5e8d7af 1136 )? # all until now is optional -> you can pass the naked ID
201c1459 1137 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
c5e8d7af 1138 (?(1).+)? # if we found the ID, everything can follow
9297939e 1139 (?:\#|$)""" % {
d9190e44 1140 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
bc2ca1bb 1141 }
7c6eb424 1142 _EMBED_REGEX = [
1143 r'''(?x)
1144 (?:
0ca0f881 1145 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
7c6eb424 1146 data-video-url=|
1147 <embed[^>]+?src=|
1148 embedSWF\(?:\s*|
1149 <object[^>]+data=|
1150 new\s+SWFObject\(
1151 )
1152 (["\'])
1153 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1154 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1155 \1''',
1156 # https://wordpress.org/plugins/lazy-load-for-videos/
1157 r'''(?xs)
1158 <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1159 \s[^>]*\bclass="[^"]*\blazy-load-youtube''',
1160 ]
6368e2e6 1161 _RETURN_TYPE = 'video' # XXX: How to handle multifeed?
7c6eb424 1162
e40c758c 1163 _PLAYER_INFO_RE = (
cc2db878 1164 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1165 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$',
545cc85d 1166 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
e40c758c 1167 )
2c62dc26 1168 _formats = {
c2d3cb4c 1169 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1170 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1171 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1172 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1173 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1174 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1175 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1176 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 1177 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 1178 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1179 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1180 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1181 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1182 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1183 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 1184 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 1185 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1186 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 1187
1188
1189 # 3D videos
c2d3cb4c 1190 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1191 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1192 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1193 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 1194 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1195 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1196 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 1197
96fb5605 1198 # Apple HTTP Live Streaming
11f12195 1199 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 1200 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1201 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1202 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1203 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1204 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 1205 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1206 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
1207
1208 # DASH mp4 video
d23028a8
S
1209 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1210 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1211 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1212 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1213 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
067aa17e 1214 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
d23028a8
S
1215 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1216 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1217 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1218 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1219 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1220 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
836a086c 1221
f6f1fc92 1222 # Dash mp4 audio
d23028a8
S
1223 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1224 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1225 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1226 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1227 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1228 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1229 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
836a086c
AZ
1230
1231 # Dash webm
d23028a8
S
1232 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1233 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1234 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1235 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1236 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1237 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1238 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1239 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1240 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1241 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1242 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1243 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1244 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1245 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1246 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
4c6b4764 1247 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
d23028a8
S
1248 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1249 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1250 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1251 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1252 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1253 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
2c62dc26
PH
1254
1255 # Dash webm audio
d23028a8
S
1256 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1257 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
ce6b9a2d 1258
0857baad 1259 # Dash webm audio with opus inside
d23028a8
S
1260 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1261 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1262 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
0857baad 1263
ce6b9a2d
PH
1264 # RTMP (unnamed)
1265 '_rtmp': {'protocol': 'rtmp'},
b85eae0f
S
1266
1267 # av01 video only formats sometimes served with "unknown" codecs
9b5fa9ee
TOH
1268 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1269 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1270 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1271 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1272 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1273 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1274 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1275 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
c5e8d7af 1276 }
29f7c58a 1277 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
836a086c 1278
fd5c4aab
S
1279 _GEO_BYPASS = False
1280
78caa52a 1281 IE_NAME = 'youtube'
2eb88d95
PH
1282 _TESTS = [
1283 {
2d3d2997 1284 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
1285 'info_dict': {
1286 'id': 'BaW_jenozKc',
1287 'ext': 'mp4',
3867038a 1288 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
ff9f925b 1289 'channel': 'Philipp Hagemeister',
dd4c4492
S
1290 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1291 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
4bc3a23e 1292 'upload_date': '20121002',
ff9f925b 1293 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
4bc3a23e 1294 'categories': ['Science & Technology'],
3867038a 1295 'tags': ['youtube-dl'],
556dbe7f 1296 'duration': 10,
dbdaaa23 1297 'view_count': int,
3e7c1224 1298 'like_count': int,
ff9f925b 1299 'availability': 'public',
1300 'playable_in_embed': True,
1301 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1302 'live_status': 'not_live',
1303 'age_limit': 0,
7c80519c 1304 'start_time': 1,
297a564b 1305 'end_time': 9,
12a1b225 1306 'comment_count': int,
7666b936 1307 'channel_follower_count': int,
1308 'uploader': 'Philipp Hagemeister',
1309 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
1310 'uploader_id': '@PhilippHagemeister',
5caf30db 1311 'heatmap': 'count:100',
2eb88d95 1312 }
0e853ca4 1313 },
fccd3771 1314 {
4bc3a23e
PH
1315 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1316 'note': 'Embed-only video (#1746)',
1317 'info_dict': {
1318 'id': 'yZIXLfi8CZQ',
1319 'ext': 'mp4',
1320 'upload_date': '20120608',
1321 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1322 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
94bfcd23 1323 'age_limit': 18,
545cc85d 1324 },
1325 'skip': 'Private video',
fccd3771 1326 },
11b56058 1327 {
8bdd16b4 1328 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
11b56058
PM
1329 'note': 'Use the first video ID in the URL',
1330 'info_dict': {
1331 'id': 'BaW_jenozKc',
1332 'ext': 'mp4',
3867038a 1333 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
976ae3ea 1334 'channel': 'Philipp Hagemeister',
1335 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1336 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
11b56058 1337 'upload_date': '20121002',
976ae3ea 1338 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
11b56058 1339 'categories': ['Science & Technology'],
3867038a 1340 'tags': ['youtube-dl'],
556dbe7f 1341 'duration': 10,
dbdaaa23 1342 'view_count': int,
11b56058 1343 'like_count': int,
976ae3ea 1344 'availability': 'public',
1345 'playable_in_embed': True,
1346 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1347 'live_status': 'not_live',
1348 'age_limit': 0,
12a1b225 1349 'comment_count': int,
7666b936 1350 'channel_follower_count': int,
1351 'uploader': 'Philipp Hagemeister',
1352 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
1353 'uploader_id': '@PhilippHagemeister',
14a14335 1354 'heatmap': 'count:100',
34a7de29
S
1355 },
1356 'params': {
1357 'skip_download': True,
1358 },
11b56058 1359 },
dd27fd17 1360 {
2d3d2997 1361 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
4bc3a23e
PH
1362 'note': '256k DASH audio (format 141) via DASH manifest',
1363 'info_dict': {
1364 'id': 'a9LDPn-MO4I',
1365 'ext': 'm4a',
1366 'upload_date': '20121002',
4bc3a23e 1367 'description': '',
4bc3a23e 1368 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 1369 },
4bc3a23e
PH
1370 'params': {
1371 'youtube_include_dash_manifest': True,
1372 'format': '141',
4919603f 1373 },
de3c7fe0 1374 'skip': 'format 141 not served anymore',
dd27fd17 1375 },
8bdd16b4 1376 # DASH manifest with encrypted signature
1377 {
1378 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1379 'info_dict': {
1380 'id': 'IB3lcPjvWLA',
1381 'ext': 'm4a',
1382 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1383 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1384 'duration': 244,
8bdd16b4 1385 'upload_date': '20131011',
cc2db878 1386 'abr': 129.495,
976ae3ea 1387 'like_count': int,
1388 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1389 'playable_in_embed': True,
1390 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1391 'view_count': int,
1392 'track': 'The Spark',
1393 'live_status': 'not_live',
1394 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1395 'channel': 'Afrojack',
976ae3ea 1396 'tags': 'count:19',
1397 'availability': 'public',
1398 'categories': ['Music'],
1399 'age_limit': 0,
1400 'alt_title': 'The Spark',
7666b936 1401 'channel_follower_count': int,
1402 'uploader': 'Afrojack',
1403 'uploader_url': 'https://www.youtube.com/@Afrojack',
1404 'uploader_id': '@Afrojack',
8bdd16b4 1405 },
1406 'params': {
1407 'youtube_include_dash_manifest': True,
1408 'format': '141/bestaudio[ext=m4a]',
1409 },
1410 },
65c2fde2 1411 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
c522adb1 1412 {
65c2fde2 1413 'note': 'Embed allowed age-gate video',
2d3d2997 1414 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
c522adb1
JMF
1415 'info_dict': {
1416 'id': 'HtVdAasjOgU',
1417 'ext': 'mp4',
1418 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
ec85ded8 1419 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
556dbe7f 1420 'duration': 142,
c522adb1 1421 'upload_date': '20140605',
34952f09 1422 'age_limit': 18,
976ae3ea 1423 'categories': ['Gaming'],
1424 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1425 'availability': 'needs_auth',
1426 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1427 'like_count': int,
1428 'channel': 'The Witcher',
1429 'live_status': 'not_live',
1430 'tags': 'count:17',
1431 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1432 'playable_in_embed': True,
1433 'view_count': int,
7666b936 1434 'channel_follower_count': int,
1435 'uploader': 'The Witcher',
1436 'uploader_url': 'https://www.youtube.com/@thewitcher',
1437 'uploader_id': '@thewitcher',
14a14335 1438 'comment_count': int,
8213ce28 1439 'channel_is_verified': True,
14a14335 1440 'heatmap': 'count:100',
c522adb1
JMF
1441 },
1442 },
65c2fde2 1443 {
1444 'note': 'Age-gate video with embed allowed in public site',
1445 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1446 'info_dict': {
1447 'id': 'HsUATh_Nc2U',
1448 'ext': 'mp4',
1449 'title': 'Godzilla 2 (Official Video)',
1450 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1451 'upload_date': '20200408',
65c2fde2 1452 'age_limit': 18,
976ae3ea 1453 'availability': 'needs_auth',
1454 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
976ae3ea 1455 'channel': 'FlyingKitty',
1456 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1457 'view_count': int,
1458 'categories': ['Entertainment'],
1459 'live_status': 'not_live',
1460 'tags': ['Flyingkitty', 'godzilla 2'],
1461 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1462 'like_count': int,
1463 'duration': 177,
1464 'playable_in_embed': True,
7666b936 1465 'channel_follower_count': int,
1466 'uploader': 'FlyingKitty',
1467 'uploader_url': 'https://www.youtube.com/@FlyingKitty900',
1468 'uploader_id': '@FlyingKitty900',
5caf30db 1469 'comment_count': int,
8213ce28 1470 'channel_is_verified': True,
65c2fde2 1471 },
1472 },
1473 {
1474 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1475 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1476 'info_dict': {
1477 'id': 'Tq92D6wQ1mg',
1478 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
3619f78d 1479 'ext': 'mp4',
17322130 1480 'upload_date': '20191228',
65c2fde2 1481 'description': 'md5:17eccca93a786d51bc67646756894066',
1482 'age_limit': 18,
976ae3ea 1483 'like_count': int,
1484 'availability': 'needs_auth',
976ae3ea 1485 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1486 'view_count': int,
1487 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1488 'channel': 'Projekt Melody',
1489 'live_status': 'not_live',
1490 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1491 'playable_in_embed': True,
1492 'categories': ['Entertainment'],
1493 'duration': 106,
1494 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
12a1b225 1495 'comment_count': int,
7666b936 1496 'channel_follower_count': int,
1497 'uploader': 'Projekt Melody',
1498 'uploader_url': 'https://www.youtube.com/@ProjektMelody',
1499 'uploader_id': '@ProjektMelody',
65c2fde2 1500 },
1501 },
1502 {
1503 'note': 'Non-Agegated non-embeddable video',
1504 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1505 'info_dict': {
1506 'id': 'MeJVWBSsPAY',
1507 'ext': 'mp4',
1508 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
65c2fde2 1509 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1510 'upload_date': '20130730',
976ae3ea 1511 'track': 'Such mich find mich',
1512 'age_limit': 0,
1513 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1514 'like_count': int,
1515 'playable_in_embed': False,
1516 'creator': 'OOMPH!',
1517 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1518 'view_count': int,
1519 'alt_title': 'Such mich find mich',
1520 'duration': 210,
1521 'channel': 'Herr Lurik',
1522 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1523 'categories': ['Music'],
1524 'availability': 'public',
976ae3ea 1525 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1526 'live_status': 'not_live',
1527 'artist': 'OOMPH!',
7666b936 1528 'channel_follower_count': int,
1529 'uploader': 'Herr Lurik',
1530 'uploader_url': 'https://www.youtube.com/@HerrLurik',
1531 'uploader_id': '@HerrLurik',
65c2fde2 1532 },
1533 },
1534 {
1535 'note': 'Non-bypassable age-gated video',
1536 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1537 'only_matching': True,
1538 },
8bdd16b4 1539 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1540 # YouTube Red ad is not captured for creator
1541 {
1542 'url': '__2ABJjxzNo',
1543 'info_dict': {
1544 'id': '__2ABJjxzNo',
1545 'ext': 'mp4',
1546 'duration': 266,
1547 'upload_date': '20100430',
545cc85d 1548 'creator': 'deadmau5',
1549 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
8bdd16b4 1550 'title': 'Deadmau5 - Some Chords (HD)',
545cc85d 1551 'alt_title': 'Some Chords',
976ae3ea 1552 'availability': 'public',
1553 'tags': 'count:14',
1554 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1555 'view_count': int,
1556 'live_status': 'not_live',
1557 'channel': 'deadmau5',
1558 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1559 'like_count': int,
1560 'track': 'Some Chords',
1561 'artist': 'deadmau5',
1562 'playable_in_embed': True,
1563 'age_limit': 0,
1564 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1565 'categories': ['Music'],
1566 'album': 'Some Chords',
7666b936 1567 'channel_follower_count': int,
1568 'uploader': 'deadmau5',
1569 'uploader_url': 'https://www.youtube.com/@deadmau5',
1570 'uploader_id': '@deadmau5',
8bdd16b4 1571 },
1572 'expected_warnings': [
1573 'DASH manifest missing',
1574 ]
1575 },
067aa17e 1576 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
e52a40ab
PH
1577 {
1578 'url': 'lqQg6PlCWgI',
1579 'info_dict': {
1580 'id': 'lqQg6PlCWgI',
1581 'ext': 'mp4',
556dbe7f 1582 'duration': 6085,
90227264 1583 'upload_date': '20150827',
12a1b225 1584 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
cbe2bd91 1585 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
976ae3ea 1586 'like_count': int,
1587 'release_timestamp': 1343767800,
1588 'playable_in_embed': True,
1589 'categories': ['Sports'],
1590 'release_date': '20120731',
1591 'channel': 'Olympics',
1592 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1593 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1594 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1595 'age_limit': 0,
1596 'availability': 'public',
1597 'live_status': 'was_live',
1598 'view_count': int,
1599 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
7666b936 1600 'channel_follower_count': int,
1601 'uploader': 'Olympics',
1602 'uploader_url': 'https://www.youtube.com/@Olympics',
1603 'uploader_id': '@Olympics',
8213ce28 1604 'channel_is_verified': True,
cbe2bd91
PH
1605 },
1606 'params': {
1607 'skip_download': 'requires avconv',
e52a40ab 1608 }
cbe2bd91 1609 },
6271f1ca
PH
1610 # Non-square pixels
1611 {
1612 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1613 'info_dict': {
1614 'id': '_b-2C3KPAM0',
1615 'ext': 'mp4',
1616 'stretched_ratio': 16 / 9.,
556dbe7f 1617 'duration': 85,
6271f1ca 1618 'upload_date': '20110310',
6271f1ca 1619 '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 1620 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
976ae3ea 1621 'playable_in_embed': True,
1622 'channel': '孫ᄋᄅ',
1623 'age_limit': 0,
1624 'tags': 'count:11',
1625 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1626 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1627 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1628 'view_count': int,
1629 'categories': ['People & Blogs'],
1630 'like_count': int,
1631 'live_status': 'not_live',
1632 'availability': 'unlisted',
12a1b225 1633 'comment_count': int,
7666b936 1634 'channel_follower_count': int,
1635 'uploader': '孫ᄋᄅ',
1636 'uploader_url': 'https://www.youtube.com/@AllenMeow',
1637 'uploader_id': '@AllenMeow',
6271f1ca 1638 },
06b491eb
S
1639 },
1640 # url_encoded_fmt_stream_map is empty string
1641 {
1642 'url': 'qEJwOuvDf7I',
1643 'info_dict': {
1644 'id': 'qEJwOuvDf7I',
f57b7835 1645 'ext': 'webm',
06b491eb
S
1646 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1647 'description': '',
1648 'upload_date': '20150404',
06b491eb
S
1649 },
1650 'params': {
1651 'skip_download': 'requires avconv',
e323cf3f
S
1652 },
1653 'skip': 'This live event has ended.',
06b491eb 1654 },
067aa17e 1655 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
da77d856
S
1656 {
1657 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1658 'info_dict': {
1659 'id': 'FIl7x6_3R5Y',
eb6793ba 1660 'ext': 'webm',
da77d856
S
1661 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1662 'description': 'md5:116377fd2963b81ec4ce64b542173306',
556dbe7f 1663 'duration': 220,
da77d856 1664 'upload_date': '20150625',
eb6793ba 1665 'formats': 'mincount:31',
da77d856 1666 },
eb6793ba 1667 'skip': 'not actual anymore',
2ee8f5d8 1668 },
8a1a26ce
YCH
1669 # DASH manifest with segment_list
1670 {
1671 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1672 'md5': '8ce563a1d667b599d21064e982ab9e31',
1673 'info_dict': {
1674 'id': 'CsmdDsKjzN8',
1675 'ext': 'mp4',
17ee98e1 1676 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce 1677 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
8a1a26ce
YCH
1678 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1679 },
1680 'params': {
1681 'youtube_include_dash_manifest': True,
1682 'format': '135', # bestvideo
be49068d
S
1683 },
1684 'skip': 'This live event has ended.',
2ee8f5d8 1685 },
cf7e015f 1686 {
6368e2e6 1687 # Multifeed videos (multiple cameras), URL can be of any Camera
7666b936 1688 # TODO: fix multifeed titles
6368e2e6 1689 'url': 'https://www.youtube.com/watch?v=zaPI8MvL8pg',
cf7e015f 1690 'info_dict': {
6368e2e6 1691 'id': 'zaPI8MvL8pg',
1692 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04',
1693 'description': 'md5:563ccbc698b39298481ca3c571169519',
cf7e015f
S
1694 },
1695 'playlist': [{
1696 'info_dict': {
6368e2e6 1697 'id': 'j5yGuxZ8lLU',
cf7e015f 1698 'ext': 'mp4',
6368e2e6 1699 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Chris)',
6368e2e6 1700 'description': 'md5:563ccbc698b39298481ca3c571169519',
6368e2e6 1701 'duration': 10120,
1702 'channel_follower_count': int,
1703 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1704 'availability': 'public',
1705 'playable_in_embed': True,
1706 'upload_date': '20131105',
6368e2e6 1707 'categories': ['Gaming'],
1708 'live_status': 'was_live',
1709 'tags': 'count:24',
1710 'release_timestamp': 1383701910,
1711 'thumbnail': 'https://i.ytimg.com/vi/j5yGuxZ8lLU/maxresdefault.jpg',
1712 'comment_count': int,
1713 'age_limit': 0,
1714 'like_count': int,
1715 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1716 'channel': 'WiiLikeToPlay',
1717 'view_count': int,
1718 'release_date': '20131106',
7666b936 1719 'uploader': 'WiiLikeToPlay',
1720 'uploader_id': '@WLTP',
1721 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1722 },
1723 }, {
1724 'info_dict': {
6368e2e6 1725 'id': 'zaPI8MvL8pg',
cf7e015f 1726 'ext': 'mp4',
6368e2e6 1727 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Tyson)',
6368e2e6 1728 'availability': 'public',
1729 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1730 'channel': 'WiiLikeToPlay',
6368e2e6 1731 'channel_follower_count': int,
1732 'description': 'md5:563ccbc698b39298481ca3c571169519',
1733 'duration': 10108,
1734 'age_limit': 0,
1735 'like_count': int,
1736 'tags': 'count:24',
1737 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
6368e2e6 1738 'release_timestamp': 1383701915,
1739 'comment_count': int,
1740 'upload_date': '20131105',
1741 'thumbnail': 'https://i.ytimg.com/vi/zaPI8MvL8pg/maxresdefault.jpg',
1742 'release_date': '20131106',
1743 'playable_in_embed': True,
1744 'live_status': 'was_live',
1745 'categories': ['Gaming'],
1746 'view_count': int,
7666b936 1747 'uploader': 'WiiLikeToPlay',
1748 'uploader_id': '@WLTP',
1749 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1750 },
1751 }, {
1752 'info_dict': {
6368e2e6 1753 'id': 'R7r3vfO7Hao',
cf7e015f 1754 'ext': 'mp4',
6368e2e6 1755 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Spencer)',
1756 'thumbnail': 'https://i.ytimg.com/vi/R7r3vfO7Hao/maxresdefault.jpg',
1757 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1758 'like_count': int,
1759 'availability': 'public',
1760 'playable_in_embed': True,
1761 'upload_date': '20131105',
1762 'description': 'md5:563ccbc698b39298481ca3c571169519',
6368e2e6 1763 'channel_follower_count': int,
1764 'tags': 'count:24',
1765 'release_date': '20131106',
6368e2e6 1766 'comment_count': int,
1767 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1768 'channel': 'WiiLikeToPlay',
1769 'categories': ['Gaming'],
1770 'release_timestamp': 1383701914,
1771 'live_status': 'was_live',
1772 'age_limit': 0,
1773 'duration': 10128,
1774 'view_count': int,
7666b936 1775 'uploader': 'WiiLikeToPlay',
1776 'uploader_id': '@WLTP',
1777 'uploader_url': 'https://www.youtube.com/@WLTP',
cf7e015f
S
1778 },
1779 }],
6368e2e6 1780 'params': {'skip_download': True},
cbaed4bb 1781 },
f9f49d87 1782 {
067aa17e 1783 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
f9f49d87
S
1784 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1785 'info_dict': {
1786 'id': 'gVfLd0zydlo',
1787 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1788 },
1789 'playlist_count': 2,
be49068d 1790 'skip': 'Not multifeed anymore',
f9f49d87 1791 },
cbaed4bb 1792 {
2d3d2997 1793 'url': 'https://vid.plus/FlRa-iH7PGw',
cbaed4bb 1794 'only_matching': True,
0e49d9a6 1795 },
6d4fc66b 1796 {
2d3d2997 1797 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
6d4fc66b
S
1798 'only_matching': True,
1799 },
0e49d9a6 1800 {
067aa17e 1801 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
a8776b10 1802 # Also tests cut-off URL expansion in video description (see
067aa17e
S
1803 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1804 # https://github.com/ytdl-org/youtube-dl/issues/8164)
0e49d9a6
LL
1805 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1806 'info_dict': {
1807 'id': 'lsguqyKfVQg',
1808 'ext': 'mp4',
1809 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
11f9be09 1810 'alt_title': 'Dark Walk',
0e49d9a6 1811 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
556dbe7f 1812 'duration': 133,
0e49d9a6 1813 'upload_date': '20151119',
11f9be09 1814 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1815 'track': 'Dark Walk',
1816 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
92bc97d3 1817 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
976ae3ea 1818 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1819 'categories': ['Film & Animation'],
1820 'view_count': int,
1821 'live_status': 'not_live',
1822 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1823 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1824 'tags': 'count:13',
1825 'availability': 'public',
1826 'channel': 'IronSoulElf',
1827 'playable_in_embed': True,
1828 'like_count': int,
1829 'age_limit': 0,
6c73052c 1830 'channel_follower_count': int
0e49d9a6
LL
1831 },
1832 'params': {
1833 'skip_download': True,
1834 },
1835 },
61f92af1 1836 {
067aa17e 1837 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
61f92af1
S
1838 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1839 'only_matching': True,
1840 },
313dfc45
LL
1841 {
1842 # Video with yt:stretch=17:0
1843 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1844 'info_dict': {
1845 'id': 'Q39EVAstoRM',
1846 'ext': 'mp4',
1847 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1848 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1849 'upload_date': '20151107',
313dfc45
LL
1850 },
1851 'params': {
1852 'skip_download': True,
1853 },
be49068d 1854 'skip': 'This video does not exist.',
313dfc45 1855 },
201c1459 1856 {
1857 # Video with incomplete 'yt:stretch=16:'
1858 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1859 'only_matching': True,
1860 },
7caf9830
S
1861 {
1862 # Video licensed under Creative Commons
1863 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1864 'info_dict': {
1865 'id': 'M4gD1WSo5mA',
1866 'ext': 'mp4',
1867 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1868 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
556dbe7f 1869 'duration': 721,
17322130 1870 'upload_date': '20150128',
7caf9830 1871 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1872 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1873 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1874 'like_count': int,
1875 'age_limit': 0,
1876 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1877 'channel': 'The Berkman Klein Center for Internet & Society',
1878 'availability': 'public',
1879 'view_count': int,
1880 'categories': ['Education'],
1881 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1882 'live_status': 'not_live',
1883 'playable_in_embed': True,
d5d1df8a 1884 'channel_follower_count': int,
1885 'chapters': list,
7666b936 1886 'uploader': 'The Berkman Klein Center for Internet & Society',
1887 'uploader_id': '@BKCHarvard',
1888 'uploader_url': 'https://www.youtube.com/@BKCHarvard',
7caf9830
S
1889 },
1890 'params': {
1891 'skip_download': True,
1892 },
1893 },
fd050249 1894 {
fd050249
S
1895 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1896 'info_dict': {
1897 'id': 'eQcmzGIKrzg',
1898 'ext': 'mp4',
1899 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
545cc85d 1900 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
556dbe7f 1901 'duration': 4060,
17322130 1902 'upload_date': '20151120',
fd050249 1903 'license': 'Creative Commons Attribution license (reuse allowed)',
976ae3ea 1904 'playable_in_embed': True,
1905 'tags': 'count:12',
1906 'like_count': int,
1907 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1908 'age_limit': 0,
1909 'availability': 'public',
1910 'categories': ['News & Politics'],
1911 'channel': 'Bernie Sanders',
1912 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1913 'view_count': int,
1914 'live_status': 'not_live',
1915 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
12a1b225 1916 'comment_count': int,
d5d1df8a 1917 'channel_follower_count': int,
1918 'chapters': list,
7666b936 1919 'uploader': 'Bernie Sanders',
1920 'uploader_url': 'https://www.youtube.com/@BernieSanders',
1921 'uploader_id': '@BernieSanders',
8213ce28 1922 'channel_is_verified': True,
14a14335 1923 'heatmap': 'count:100',
fd050249
S
1924 },
1925 'params': {
1926 'skip_download': True,
1927 },
1928 },
040ac686
S
1929 {
1930 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
1931 'only_matching': True,
7f29cf54
S
1932 },
1933 {
067aa17e 1934 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
7f29cf54
S
1935 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1936 'only_matching': True,
6496ccb4
S
1937 },
1938 {
1939 # Rental video preview
1940 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1941 'info_dict': {
1942 'id': 'uGpuVWrhIzE',
1943 'ext': 'mp4',
1944 'title': 'Piku - Trailer',
1945 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1946 'upload_date': '20150811',
6496ccb4
S
1947 'license': 'Standard YouTube License',
1948 },
1949 'params': {
1950 'skip_download': True,
1951 },
eb6793ba 1952 'skip': 'This video is not available.',
022a5d66 1953 },
12afdc2a
S
1954 {
1955 # YouTube Red video with episode data
1956 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1957 'info_dict': {
1958 'id': 'iqKdEhx-dD4',
1959 'ext': 'mp4',
1960 'title': 'Isolation - Mind Field (Ep 1)',
545cc85d 1961 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
556dbe7f 1962 'duration': 2085,
12afdc2a 1963 'upload_date': '20170118',
12afdc2a
S
1964 'series': 'Mind Field',
1965 'season_number': 1,
1966 'episode_number': 1,
976ae3ea 1967 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1968 'tags': 'count:12',
1969 'view_count': int,
1970 'availability': 'public',
1971 'age_limit': 0,
1972 'channel': 'Vsauce',
1973 'episode': 'Episode 1',
1974 'categories': ['Entertainment'],
1975 'season': 'Season 1',
1976 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1977 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1978 'like_count': int,
1979 'playable_in_embed': True,
1980 'live_status': 'not_live',
7666b936 1981 'channel_follower_count': int,
1982 'uploader': 'Vsauce',
1983 'uploader_url': 'https://www.youtube.com/@Vsauce',
1984 'uploader_id': '@Vsauce',
14a14335 1985 'comment_count': int,
8213ce28 1986 'channel_is_verified': True,
12afdc2a
S
1987 },
1988 'params': {
1989 'skip_download': True,
1990 },
1991 'expected_warnings': [
1992 'Skipping DASH manifest',
1993 ],
1994 },
c7121fa7
S
1995 {
1996 # The following content has been identified by the YouTube community
1997 # as inappropriate or offensive to some audiences.
1998 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1999 'info_dict': {
2000 'id': '6SJNVb0GnPI',
2001 'ext': 'mp4',
2002 'title': 'Race Differences in Intelligence',
2003 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
2004 'duration': 965,
2005 'upload_date': '20140124',
c7121fa7
S
2006 },
2007 'params': {
2008 'skip_download': True,
2009 },
545cc85d 2010 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
c7121fa7 2011 },
022a5d66
S
2012 {
2013 # itag 212
2014 'url': '1t24XAntNCY',
2015 'only_matching': True,
fd5c4aab
S
2016 },
2017 {
2018 # geo restricted to JP
2019 'url': 'sJL6WA-aGkQ',
2020 'only_matching': True,
2021 },
cd5a74a2
S
2022 {
2023 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
2024 'only_matching': True,
2025 },
bc2ca1bb 2026 {
2027 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
2028 'only_matching': True,
2029 },
2030 {
2031 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
2032 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
2033 'only_matching': True,
2034 },
825cd268
RA
2035 {
2036 # DRM protected
2037 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
2038 'only_matching': True,
4fe54c12
S
2039 },
2040 {
2041 # Video with unsupported adaptive stream type formats
2042 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
2043 'info_dict': {
2044 'id': 'Z4Vy8R84T1U',
2045 'ext': 'mp4',
2046 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
2047 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2048 'duration': 433,
2049 'upload_date': '20130923',
4fe54c12
S
2050 'formats': 'maxcount:10',
2051 },
2052 'params': {
2053 'skip_download': True,
2054 'youtube_include_dash_manifest': False,
2055 },
5429d6a9 2056 'skip': 'not actual anymore',
5caabd3c 2057 },
2058 {
822b9d9c 2059 # Youtube Music Auto-generated description
7666b936 2060 # TODO: fix metadata extraction
5caabd3c 2061 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2062 'info_dict': {
2063 'id': 'MgNrAu2pzNs',
2064 'ext': 'mp4',
2065 'title': 'Voyeur Girl',
2066 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
2067 'upload_date': '20190312',
5caabd3c 2068 'artist': 'Stephen',
2069 'track': 'Voyeur Girl',
2070 'album': 'it\'s too much love to know my dear',
2071 'release_date': '20190313',
2072 'release_year': 2019,
976ae3ea 2073 'alt_title': 'Voyeur Girl',
2074 'view_count': int,
976ae3ea 2075 'playable_in_embed': True,
2076 'like_count': int,
2077 'categories': ['Music'],
2078 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
7666b936 2079 'channel': 'Stephen', # TODO: should be "Stephen - Topic"
2080 'uploader': 'Stephen',
976ae3ea 2081 'availability': 'public',
2082 'creator': 'Stephen',
2083 'duration': 169,
2084 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
2085 'age_limit': 0,
2086 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2087 'tags': 'count:11',
2088 'live_status': 'not_live',
6c73052c 2089 'channel_follower_count': int
5caabd3c 2090 },
2091 'params': {
2092 'skip_download': True,
2093 },
2094 },
66b48727
RA
2095 {
2096 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
2097 'only_matching': True,
2098 },
011e75e6
S
2099 {
2100 # invalid -> valid video id redirection
2101 'url': 'DJztXj2GPfl',
2102 'info_dict': {
2103 'id': 'DJztXj2GPfk',
2104 'ext': 'mp4',
2105 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
2106 'description': 'md5:bf577a41da97918e94fa9798d9228825',
2107 'upload_date': '20090125',
011e75e6
S
2108 'artist': 'Panjabi MC',
2109 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
2110 'album': 'Beware of the Boys (Mundian To Bach Ke)',
2111 },
2112 'params': {
2113 'skip_download': True,
2114 },
545cc85d 2115 'skip': 'Video unavailable',
ea74e00b
DP
2116 },
2117 {
2118 # empty description results in an empty string
2119 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
2120 'info_dict': {
2121 'id': 'x41yOUIvK2k',
2122 'ext': 'mp4',
2123 'title': 'IMG 3456',
2124 'description': '',
2125 'upload_date': '20170613',
976ae3ea 2126 'view_count': int,
2127 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
976ae3ea 2128 'like_count': int,
2129 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
2130 'tags': [],
2131 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
2132 'availability': 'public',
2133 'age_limit': 0,
2134 'categories': ['Pets & Animals'],
2135 'duration': 7,
2136 'playable_in_embed': True,
2137 'live_status': 'not_live',
7666b936 2138 'channel': 'l\'Or Vert asbl',
2139 'channel_follower_count': int,
2140 'uploader': 'l\'Or Vert asbl',
2141 'uploader_url': 'https://www.youtube.com/@ElevageOrVert',
2142 'uploader_id': '@ElevageOrVert',
ea74e00b
DP
2143 },
2144 'params': {
2145 'skip_download': True,
2146 },
2147 },
a0566bbf 2148 {
29f7c58a 2149 # with '};' inside yt initial data (see [1])
2150 # see [2] for an example with '};' inside ytInitialPlayerResponse
2151 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2152 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
a0566bbf 2153 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2154 'info_dict': {
2155 'id': 'CHqg6qOn4no',
2156 'ext': 'mp4',
2157 'title': 'Part 77 Sort a list of simple types in c#',
2158 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2159 'upload_date': '20130831',
976ae3ea 2160 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2161 'like_count': int,
976ae3ea 2162 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2163 'live_status': 'not_live',
2164 'categories': ['Education'],
2165 'availability': 'public',
2166 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2167 'tags': 'count:12',
2168 'playable_in_embed': True,
2169 'age_limit': 0,
2170 'view_count': int,
2171 'duration': 522,
2172 'channel': 'kudvenkat',
12a1b225 2173 'comment_count': int,
d5d1df8a 2174 'channel_follower_count': int,
2175 'chapters': list,
7666b936 2176 'uploader': 'kudvenkat',
2177 'uploader_url': 'https://www.youtube.com/@Csharp-video-tutorialsBlogspot',
2178 'uploader_id': '@Csharp-video-tutorialsBlogspot',
8213ce28 2179 'channel_is_verified': True,
14a14335 2180 'heatmap': 'count:100',
a0566bbf 2181 },
2182 'params': {
2183 'skip_download': True,
2184 },
2185 },
29f7c58a 2186 {
2187 # another example of '};' in ytInitialData
2188 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2189 'only_matching': True,
2190 },
2191 {
2192 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2193 'only_matching': True,
2194 },
545cc85d 2195 {
cc2db878 2196 # https://github.com/ytdl-org/youtube-dl/pull/28094
2197 'url': 'OtqTfy26tG0',
2198 'info_dict': {
2199 'id': 'OtqTfy26tG0',
2200 'ext': 'mp4',
2201 'title': 'Burn Out',
2202 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2203 'upload_date': '20141120',
cc2db878 2204 'artist': 'The Cinematic Orchestra',
2205 'track': 'Burn Out',
2206 'album': 'Every Day',
976ae3ea 2207 'like_count': int,
2208 'live_status': 'not_live',
2209 'alt_title': 'Burn Out',
2210 'duration': 614,
2211 'age_limit': 0,
2212 'view_count': int,
2213 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2214 'creator': 'The Cinematic Orchestra',
2215 'channel': 'The Cinematic Orchestra',
2216 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2217 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2218 'availability': 'public',
2219 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2220 'categories': ['Music'],
2221 'playable_in_embed': True,
7666b936 2222 'channel_follower_count': int,
2223 'uploader': 'The Cinematic Orchestra',
2224 'comment_count': int,
cc2db878 2225 },
2226 'params': {
2227 'skip_download': True,
2228 },
545cc85d 2229 },
bc2ca1bb 2230 {
2231 # controversial video, only works with bpctr when authenticated with cookies
2232 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2233 'only_matching': True,
2234 },
a1a7907b 2235 {
2236 # controversial video, requires bpctr/contentCheckOk
2237 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2238 'info_dict': {
2239 'id': 'SZJvDhaSDnc',
2240 'ext': 'mp4',
2241 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2242 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
a1a7907b 2243 'upload_date': '20140716',
976ae3ea 2244 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2245 'duration': 170,
2246 'categories': ['News & Politics'],
976ae3ea 2247 'view_count': int,
2248 'channel': 'CBS Mornings',
2249 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2250 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2251 'age_limit': 18,
2252 'availability': 'needs_auth',
2253 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2254 'like_count': int,
2255 'live_status': 'not_live',
2256 'playable_in_embed': True,
7666b936 2257 'channel_follower_count': int,
2258 'uploader': 'CBS Mornings',
2259 'uploader_url': 'https://www.youtube.com/@CBSMornings',
2260 'uploader_id': '@CBSMornings',
14a14335 2261 'comment_count': int,
8213ce28 2262 'channel_is_verified': True,
a1a7907b 2263 }
2264 },
f7ad7160 2265 {
2266 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2267 'url': 'cBvYw8_A0vQ',
2268 'info_dict': {
2269 'id': 'cBvYw8_A0vQ',
2270 'ext': 'mp4',
2271 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2272 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2273 'upload_date': '20201120',
976ae3ea 2274 'duration': 1456,
2275 'categories': ['Travel & Events'],
2276 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2277 'view_count': int,
2278 'channel': 'Walk around Japan',
2279 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2280 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2281 'age_limit': 0,
2282 'availability': 'public',
2283 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2284 'live_status': 'not_live',
2285 'playable_in_embed': True,
7666b936 2286 'channel_follower_count': int,
2287 'uploader': 'Walk around Japan',
2288 'uploader_url': 'https://www.youtube.com/@walkaroundjapan7124',
2289 'uploader_id': '@walkaroundjapan7124',
f7ad7160 2290 },
2291 'params': {
2292 'skip_download': True,
2293 },
0fb983f6 2294 }, {
2295 # Has multiple audio streams
2296 'url': 'WaOKSUlf4TM',
2297 'only_matching': True
9297939e 2298 }, {
2299 # Requires Premium: has format 141 when requested using YTM url
2300 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2301 'only_matching': True
2302 }, {
120916da 2303 # multiple subtitles with same lang_code
2304 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2305 'only_matching': True,
109dd3b2 2306 }, {
2307 # Force use android client fallback
2308 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2309 'info_dict': {
2310 'id': 'YOelRv7fMxY',
11f9be09 2311 'title': 'DIGGING A SECRET TUNNEL Part 1',
109dd3b2 2312 'ext': '3gp',
2313 'upload_date': '20210624',
2314 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
109dd3b2 2315 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
976ae3ea 2316 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2317 'duration': 596,
2318 'categories': ['Entertainment'],
976ae3ea 2319 'view_count': int,
2320 'channel': 'colinfurze',
2321 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2322 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2323 'age_limit': 0,
2324 'availability': 'public',
2325 'like_count': int,
2326 'live_status': 'not_live',
2327 'playable_in_embed': True,
d5d1df8a 2328 'channel_follower_count': int,
2329 'chapters': list,
7666b936 2330 'uploader': 'colinfurze',
2331 'uploader_url': 'https://www.youtube.com/@colinfurze',
2332 'uploader_id': '@colinfurze',
14a14335 2333 'comment_count': int,
8213ce28 2334 'channel_is_verified': True,
14a14335 2335 'heatmap': 'count:100',
109dd3b2 2336 },
2337 'params': {
2338 'format': '17', # 3gp format available on android
2339 'extractor_args': {'youtube': {'player_client': ['android']}},
2340 },
120916da 2341 },
109dd3b2 2342 {
2343 # Skip download of additional client configs (remix client config in this case)
2344 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2345 'only_matching': True,
2346 'params': {
2347 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2348 },
8fc54b12 2349 }, {
2350 # shorts
2351 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2352 'only_matching': True,
9222c381 2353 }, {
2354 'note': 'Storyboards',
2355 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2356 'info_dict': {
2357 'id': '5KLPxDtMqe8',
2358 'ext': 'mhtml',
2359 'format_id': 'sb0',
2360 'title': 'Your Brain is Plastic',
9222c381 2361 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2362 'upload_date': '20140324',
976ae3ea 2363 'like_count': int,
2364 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2365 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2366 'view_count': int,
2367 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2368 'playable_in_embed': True,
2369 'tags': 'count:12',
976ae3ea 2370 'availability': 'public',
2371 'channel': 'SciShow',
2372 'live_status': 'not_live',
2373 'duration': 248,
2374 'categories': ['Education'],
2375 'age_limit': 0,
d5d1df8a 2376 'channel_follower_count': int,
2377 'chapters': list,
7666b936 2378 'uploader': 'SciShow',
2379 'uploader_url': 'https://www.youtube.com/@SciShow',
2380 'uploader_id': '@SciShow',
14a14335 2381 'comment_count': int,
8213ce28 2382 'channel_is_verified': True,
14a14335 2383 'heatmap': 'count:100',
9222c381 2384 }, 'params': {'format': 'mhtml', 'skip_download': True}
992f9a73 2385 }, {
2386 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2387 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2388 'info_dict': {
2389 'id': '2NUZ8W2llS4',
2390 'ext': 'mp4',
2391 'title': 'The NP that test your phone performance 🙂',
2392 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
992f9a73 2393 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2394 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2395 'duration': 21,
2396 'view_count': int,
2397 'age_limit': 0,
2398 'categories': ['Gaming'],
2399 'tags': 'count:23',
2400 'playable_in_embed': True,
2401 'live_status': 'not_live',
2402 'upload_date': '20220103',
2403 'like_count': int,
2404 'availability': 'public',
2405 'channel': 'Leon Nguyen',
2406 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
12a1b225 2407 'comment_count': int,
7666b936 2408 'channel_follower_count': int,
2409 'uploader': 'Leon Nguyen',
2410 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
2411 'uploader_id': '@LeonNguyen',
14a14335 2412 'heatmap': 'count:100',
992f9a73 2413 }
1ff88b7a 2414 }, {
2415 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2416 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2417 'info_dict': {
2418 'id': '2NUZ8W2llS4',
2419 'ext': 'mp4',
2420 'title': 'The NP that test your phone performance 🙂',
2421 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
1ff88b7a 2422 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2423 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2424 'duration': 21,
2425 'view_count': int,
2426 'age_limit': 0,
2427 'categories': ['Gaming'],
2428 'tags': 'count:23',
2429 'playable_in_embed': True,
2430 'live_status': 'not_live',
2431 'upload_date': '20220102',
2432 'like_count': int,
2433 'availability': 'public',
2434 'channel': 'Leon Nguyen',
2435 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2436 'comment_count': int,
7666b936 2437 'channel_follower_count': int,
2438 'uploader': 'Leon Nguyen',
2439 'uploader_url': 'https://www.youtube.com/@LeonNguyen',
2440 'uploader_id': '@LeonNguyen',
14a14335 2441 'heatmap': 'count:100',
1ff88b7a 2442 },
2443 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
992f9a73 2444 }, {
2445 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2446 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2447 'info_dict': {
2448 'id': 'mzZzzBU6lrM',
2449 'ext': 'mp4',
2450 'title': 'I Met GeorgeNotFound In Real Life...',
7666b936 2451 'description': 'md5:978296ec9783a031738b684d4ebf302d',
992f9a73 2452 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2453 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2454 'duration': 955,
2455 'view_count': int,
2456 'age_limit': 0,
2457 'categories': ['Entertainment'],
2458 'tags': 'count:26',
2459 'playable_in_embed': True,
2460 'live_status': 'not_live',
2461 'release_timestamp': 1641172509,
2462 'release_date': '20220103',
2463 'upload_date': '20220103',
2464 'like_count': int,
2465 'availability': 'public',
2466 'channel': 'Quackity',
2467 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
7666b936 2468 'channel_follower_count': int,
2469 'uploader': 'Quackity',
2470 'uploader_id': '@Quackity',
2471 'uploader_url': 'https://www.youtube.com/@Quackity',
14a14335 2472 'comment_count': int,
8213ce28 2473 'channel_is_verified': True,
14a14335 2474 'heatmap': 'count:100',
992f9a73 2475 }
2476 },
2477 { # continuous livestream. Microformat upload date should be preferred.
2478 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2479 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2480 'info_dict': {
2481 'id': 'kgx4WGK0oNU',
2482 '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}',
2483 'ext': 'mp4',
2484 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2485 'availability': 'public',
2486 'age_limit': 0,
2487 'release_timestamp': 1637975704,
2488 'upload_date': '20210619',
2489 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2490 'live_status': 'is_live',
2491 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
992f9a73 2492 'channel': 'Abao in Tokyo',
2493 'channel_follower_count': int,
2494 'release_date': '20211127',
2495 'tags': 'count:39',
2496 'categories': ['People & Blogs'],
2497 'like_count': int,
992f9a73 2498 'view_count': int,
2499 'playable_in_embed': True,
2500 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
867c66ff 2501 'concurrent_view_count': int,
7666b936 2502 'uploader': 'Abao in Tokyo',
2503 'uploader_url': 'https://www.youtube.com/@abaointokyo',
2504 'uploader_id': '@abaointokyo',
992f9a73 2505 },
2506 'params': {'skip_download': True}
ee27297f 2507 }, {
2508 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2509 'info_dict': {
2510 'id': 'tjjjtzRLHvA',
2511 'ext': 'mp4',
2512 'title': 'ハッシュタグ無し };if window.ytcsi',
2513 'upload_date': '20220323',
2514 'like_count': int,
2515 'availability': 'unlisted',
7666b936 2516 'channel': 'Lesmiscore',
2517 'thumbnail': r're:^https?://.*\.jpg',
ee27297f 2518 'age_limit': 0,
ee27297f 2519 'categories': ['Music'],
6e634cbe 2520 'view_count': int,
2521 'description': '',
ee27297f 2522 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2523 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2524 'live_status': 'not_live',
2525 'playable_in_embed': True,
2526 'channel_follower_count': int,
2527 'duration': 6,
2528 'tags': [],
7666b936 2529 'uploader_id': '@lesmiscore',
2530 'uploader': 'Lesmiscore',
2531 'uploader_url': 'https://www.youtube.com/@lesmiscore',
6e634cbe 2532 }
c26f9b99 2533 }, {
2534 # Prefer primary title+description language metadata by default
2535 # Do not prefer translated description if primary is empty
2536 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2537 'info_dict': {
2538 'id': 'el3E4MbxRqQ',
2539 'ext': 'mp4',
2540 'title': 'dlp test video 2 - primary sv no desc',
2541 'description': '',
2542 'channel': 'cole-dlp-test-acc',
2543 'tags': [],
2544 'view_count': int,
2545 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2546 'like_count': int,
2547 'playable_in_embed': True,
2548 'availability': 'unlisted',
7666b936 2549 'thumbnail': r're:^https?://.*\.jpg',
c26f9b99 2550 'age_limit': 0,
2551 'duration': 5,
c26f9b99 2552 'live_status': 'not_live',
2553 'upload_date': '20220908',
2554 'categories': ['People & Blogs'],
c26f9b99 2555 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
7666b936 2556 'uploader_url': 'https://www.youtube.com/@coletdjnz',
2557 'uploader_id': '@coletdjnz',
2558 'uploader': 'cole-dlp-test-acc',
c26f9b99 2559 },
2560 'params': {'skip_download': True}
2561 }, {
2562 # Extractor argument: prefer translated title+description
2563 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2564 'info_dict': {
2565 'id': 'gHKT4uU8Zng',
2566 'ext': 'mp4',
2567 'channel': 'cole-dlp-test-acc',
2568 'tags': [],
2569 'duration': 5,
2570 'live_status': 'not_live',
2571 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2572 'upload_date': '20220728',
c26f9b99 2573 'view_count': int,
2574 'categories': ['People & Blogs'],
7666b936 2575 'thumbnail': r're:^https?://.*\.jpg',
c26f9b99 2576 'title': 'dlp test video title translated (fr)',
2577 'availability': 'public',
c26f9b99 2578 'age_limit': 0,
2579 'description': 'dlp test video description translated (fr)',
2580 'playable_in_embed': True,
2581 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
7666b936 2582 'uploader_url': 'https://www.youtube.com/@coletdjnz',
2583 'uploader_id': '@coletdjnz',
2584 'uploader': 'cole-dlp-test-acc',
c26f9b99 2585 },
2586 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2587 'expected_warnings': [r'Preferring "fr" translated fields'],
a4166234 2588 }, {
2589 'note': '6 channel audio',
2590 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2591 'only_matching': True,
a4894d3e 2592 }, {
2593 'note': 'Multiple HLS formats with same itag',
2594 'url': 'https://www.youtube.com/watch?v=kX3nB4PpJko',
2595 'info_dict': {
2596 'id': 'kX3nB4PpJko',
2597 'ext': 'mp4',
2598 'categories': ['Entertainment'],
2599 'description': 'md5:e8031ff6e426cdb6a77670c9b81f6fa6',
a4894d3e 2600 'live_status': 'not_live',
2601 'duration': 937,
2602 'channel_follower_count': int,
2603 'thumbnail': 'https://i.ytimg.com/vi_webp/kX3nB4PpJko/maxresdefault.webp',
2604 'title': 'Last To Take Hand Off Jet, Keeps It!',
2605 'channel': 'MrBeast',
2606 'playable_in_embed': True,
2607 'view_count': int,
2608 'upload_date': '20221112',
a4894d3e 2609 'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA',
2610 'age_limit': 0,
2611 'availability': 'public',
2612 'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA',
2613 'like_count': int,
2614 'tags': [],
7666b936 2615 'uploader': 'MrBeast',
2616 'uploader_url': 'https://www.youtube.com/@MrBeast',
2617 'uploader_id': '@MrBeast',
14a14335 2618 'comment_count': int,
8213ce28 2619 'channel_is_verified': True,
14a14335 2620 'heatmap': 'count:100',
a4894d3e 2621 },
2622 'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
9bb85699 2623 }, {
2624 'note': 'Audio formats with Dynamic Range Compression',
2625 'url': 'https://www.youtube.com/watch?v=Tq92D6wQ1mg',
2626 'info_dict': {
2627 'id': 'Tq92D6wQ1mg',
7666b936 2628 'ext': 'webm',
9bb85699 2629 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
2630 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2631 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2632 'channel_follower_count': int,
2633 'description': 'md5:17eccca93a786d51bc67646756894066',
2634 'upload_date': '20191228',
9bb85699 2635 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
2636 'playable_in_embed': True,
2637 'like_count': int,
2638 'categories': ['Entertainment'],
2639 'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
2640 'age_limit': 18,
2641 'channel': 'Projekt Melody',
9bb85699 2642 'view_count': int,
2643 'availability': 'needs_auth',
2644 'comment_count': int,
2645 'live_status': 'not_live',
9bb85699 2646 'duration': 106,
7666b936 2647 'uploader': 'Projekt Melody',
2648 'uploader_id': '@ProjektMelody',
2649 'uploader_url': 'https://www.youtube.com/@ProjektMelody',
9bb85699 2650 },
2651 'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
dad2210c 2652 },
2653 {
2654 'url': 'https://www.youtube.com/live/qVv6vCqciTM',
2655 'info_dict': {
2656 'id': 'qVv6vCqciTM',
2657 'ext': 'mp4',
2658 'age_limit': 0,
dad2210c 2659 'comment_count': int,
2660 'chapters': 'count:13',
2661 'upload_date': '20221223',
2662 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
2663 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
dad2210c 2664 'like_count': int,
2665 'release_date': '20221223',
2666 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
2667 '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】',
2668 'view_count': int,
2669 'playable_in_embed': True,
2670 'duration': 4438,
2671 'availability': 'public',
2672 'channel_follower_count': int,
2673 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2674 'categories': ['Entertainment'],
2675 'live_status': 'was_live',
2676 'release_timestamp': 1671793345,
2677 'channel': 'さなちゃんねる',
2678 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
2679 'uploader': 'さなちゃんねる',
7666b936 2680 'uploader_url': 'https://www.youtube.com/@sana_natori',
2681 'uploader_id': '@sana_natori',
8213ce28 2682 'channel_is_verified': True,
14a14335 2683 'heatmap': 'count:100',
7666b936 2684 },
2685 },
2686 {
2687 # Fallbacks when webpage and web client is unavailable
2688 'url': 'https://www.youtube.com/watch?v=wSSmNUl9Snw',
2689 'info_dict': {
2690 'id': 'wSSmNUl9Snw',
2691 'ext': 'mp4',
2692 # 'categories': ['Science & Technology'],
2693 'view_count': int,
2694 'chapters': 'count:2',
2695 'channel': 'Scott Manley',
2696 'like_count': int,
2697 'age_limit': 0,
2698 # 'availability': 'public',
2699 'channel_follower_count': int,
2700 'live_status': 'not_live',
2701 'upload_date': '20170831',
2702 'duration': 682,
2703 'tags': 'count:8',
2704 'uploader_url': 'https://www.youtube.com/@scottmanley',
2705 'description': 'md5:f4bed7b200404b72a394c2f97b782c02',
2706 'uploader': 'Scott Manley',
2707 'uploader_id': '@scottmanley',
2708 'title': 'The Computer Hack That Saved Apollo 14',
2709 'channel_id': 'UCxzC4EngIsMrPmbm6Nxvb-A',
2710 'thumbnail': r're:^https?://.*\.webp',
2711 'channel_url': 'https://www.youtube.com/channel/UCxzC4EngIsMrPmbm6Nxvb-A',
2712 'playable_in_embed': True,
14a14335 2713 'comment_count': int,
8213ce28 2714 'channel_is_verified': True,
14a14335 2715 'heatmap': 'count:100',
7666b936 2716 },
2717 'params': {
2718 'extractor_args': {'youtube': {'player_client': ['android'], 'player_skip': ['webpage']}},
dad2210c 2719 },
2720 },
2eb88d95
PH
2721 ]
2722
f2e8dbcc 2723 _WEBPAGE_TESTS = [
2724 # YouTube <object> embed
2725 {
2726 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2727 'md5': '873c81d308b979f0e23ee7e620b312a3',
2728 'info_dict': {
2729 'id': 'msN87y-iEx0',
2730 'ext': 'mp4',
2731 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2732 'upload_date': '20080526',
2733 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
f2e8dbcc 2734 'age_limit': 0,
2735 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2736 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2737 'playable_in_embed': True,
2738 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2739 'like_count': int,
2740 'comment_count': int,
2741 'channel': 'Christopher Sykes',
2742 'live_status': 'not_live',
2743 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2744 'availability': 'public',
2745 'duration': 195,
2746 'view_count': int,
2747 'categories': ['Science & Technology'],
2748 'channel_follower_count': int,
7666b936 2749 'uploader': 'Christopher Sykes',
2750 'uploader_url': 'https://www.youtube.com/@ChristopherSykesDocumentaries',
2751 'uploader_id': '@ChristopherSykesDocumentaries',
14a14335 2752 'heatmap': 'count:100',
f2e8dbcc 2753 },
2754 'params': {
2755 'skip_download': True,
2756 }
2757 },
2758 ]
2759
201c1459 2760 @classmethod
2761 def suitable(cls, url):
4dfbf869 2762 from ..utils import parse_qs
2763
201c1459 2764 qs = parse_qs(url)
2765 if qs.get('list', [None])[0]:
2766 return False
86e5f3ed 2767 return super().suitable(url)
201c1459 2768
e0df6211 2769 def __init__(self, *args, **kwargs):
86e5f3ed 2770 super().__init__(*args, **kwargs)
545cc85d 2771 self._code_cache = {}
83799698 2772 self._player_cache = {}
e0df6211 2773
4d37720a 2774 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
adbc4ec4 2775 lock = threading.Lock()
185bf310 2776 start_time = time.time()
adbc4ec4
THD
2777 formats = [f for f in formats if f.get('is_from_start')]
2778
185bf310 2779 def refetch_manifest(format_id, delay):
2780 nonlocal formats, start_time, is_live
2781 if time.time() <= start_time + delay:
adbc4ec4
THD
2782 return
2783
2784 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
6839ae1f 2785 video_details = traverse_obj(prs, (..., 'videoDetails'), expected_type=dict)
adbc4ec4
THD
2786 microformats = traverse_obj(
2787 prs, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 2788 expected_type=dict)
4d37720a
L
2789 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2790 is_live = live_status == 'is_live'
185bf310 2791 start_time = time.time()
adbc4ec4 2792
185bf310 2793 def mpd_feed(format_id, delay):
adbc4ec4
THD
2794 """
2795 @returns (manifest_url, manifest_stream_number, is_live) or None
2796 """
253ac4ba 2797 for retry in self.RetryManager(fatal=False):
2798 with lock:
2799 refetch_manifest(format_id, delay)
2800
2801 f = next((f for f in formats if f['format_id'] == format_id), None)
2802 if not f:
2803 if not is_live:
2804 retry.error = f'{video_id}: Video is no longer live'
2805 else:
2806 retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
2807 continue
2808 return f['manifest_url'], f['manifest_stream_number'], is_live
2809 return None
adbc4ec4
THD
2810
2811 for f in formats:
4d37720a
L
2812 f['is_live'] = is_live
2813 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2814 live_start_time, mpd_feed, not is_live and f.copy())
2815 if is_live:
2816 f['fragments'] = gen
2817 f['protocol'] = 'http_dash_segments_generator'
2818 else:
2819 f['fragments'] = LazyList(gen({}))
2820 del f['is_from_start']
adbc4ec4 2821
4d37720a 2822 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
adbc4ec4
THD
2823 FETCH_SPAN, MAX_DURATION = 5, 432000
2824
2825 mpd_url, stream_number, is_live = None, None, True
2826
2827 begin_index = 0
2828 download_start_time = ctx.get('start') or time.time()
2829
2830 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2831 if lack_early_segments:
2832 self.report_warning(bug_reports_message(
2833 'Starting download from the last 120 hours of the live stream since '
2834 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2835 lack_early_segments = True
2836
2837 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2838 fragments, fragment_base_url = None, None
2839
a539f065 2840 def _extract_sequence_from_mpd(refresh_sequence, immediate):
adbc4ec4
THD
2841 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2842 # Obtain from MPD's maximum seq value
2843 old_mpd_url = mpd_url
185bf310 2844 last_error = ctx.pop('last_error', None)
3d2623a8 2845 expire_fast = immediate or last_error and isinstance(last_error, HTTPError) and last_error.status == 403
185bf310 2846 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2847 or (mpd_url, stream_number, False))
2848 if not refresh_sequence:
2849 if expire_fast and not is_live:
2850 return False, last_seq
2851 elif old_mpd_url == mpd_url:
2852 return True, last_seq
4d37720a
L
2853 if manifestless_orig_fmt:
2854 fmt_info = manifestless_orig_fmt
2855 else:
2856 try:
2857 fmts, _ = self._extract_mpd_formats_and_subtitles(
2858 mpd_url, None, note=False, errnote=False, fatal=False)
2859 except ExtractorError:
2860 fmts = None
2861 if not fmts:
2862 no_fragment_score += 2
2863 return False, last_seq
2864 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
adbc4ec4
THD
2865 fragments = fmt_info['fragments']
2866 fragment_base_url = fmt_info['fragment_base_url']
2867 assert fragment_base_url
2868
2869 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2870 return True, _last_seq
2871
4d37720a 2872 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
adbc4ec4
THD
2873 while is_live:
2874 fetch_time = time.time()
2875 if no_fragment_score > 30:
2876 return
2877 if last_segment_url:
2878 # Obtain from "X-Head-Seqnum" header value from each segment
2879 try:
2880 urlh = self._request_webpage(
2881 last_segment_url, None, note=False, errnote=False, fatal=False)
2882 except ExtractorError:
2883 urlh = None
2884 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2885 if last_seq is None:
a539f065 2886 no_fragment_score += 2
adbc4ec4
THD
2887 last_segment_url = None
2888 continue
2889 else:
a539f065
LNO
2890 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2891 no_fragment_score += 2
185bf310 2892 if not should_continue:
adbc4ec4
THD
2893 continue
2894
2895 if known_idx > last_seq:
2896 last_segment_url = None
2897 continue
2898
2899 last_seq += 1
2900
2901 if begin_index < 0 and known_idx < 0:
2902 # skip from the start when it's negative value
2903 known_idx = last_seq + begin_index
2904 if lack_early_segments:
2905 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2906 try:
2907 for idx in range(known_idx, last_seq):
2908 # do not update sequence here or you'll get skipped some part of it
a539f065 2909 should_continue, _ = _extract_sequence_from_mpd(False, False)
185bf310 2910 if not should_continue:
adbc4ec4
THD
2911 known_idx = idx - 1
2912 raise ExtractorError('breaking out of outer loop')
2913 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2914 yield {
2915 'url': last_segment_url,
36195c44 2916 'fragment_count': last_seq,
adbc4ec4
THD
2917 }
2918 if known_idx == last_seq:
2919 no_fragment_score += 5
2920 else:
2921 no_fragment_score = 0
2922 known_idx = last_seq
2923 except ExtractorError:
2924 continue
2925
4d37720a
L
2926 if manifestless_orig_fmt:
2927 # Stop at the first iteration if running for post-live manifestless;
2928 # fragment count no longer increase since it starts
2929 break
2930
adbc4ec4
THD
2931 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2932
b6de707d 2933 def _extract_player_url(self, *ytcfgs, webpage=None):
2934 player_url = traverse_obj(
2935 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
14f25df2 2936 get_all=False, expected_type=str)
11f9be09 2937 if not player_url:
b6de707d 2938 return
60f393e4 2939 return urljoin('https://www.youtube.com', player_url)
109dd3b2 2940
b6de707d 2941 def _download_player_url(self, video_id, fatal=False):
2942 res = self._download_webpage(
2943 'https://www.youtube.com/iframe_api',
2944 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2945 if res:
2946 player_version = self._search_regex(
2947 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2948 if player_version:
2949 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2950
60064c53
PH
2951 def _signature_cache_id(self, example_sig):
2952 """ Return a string representation of a signature """
14f25df2 2953 return '.'.join(str(len(part)) for part in example_sig.split('.'))
60064c53 2954
e40c758c
S
2955 @classmethod
2956 def _extract_player_info(cls, player_url):
2957 for player_re in cls._PLAYER_INFO_RE:
2958 id_m = re.search(player_re, player_url)
2959 if id_m:
2960 break
2961 else:
c081b35c 2962 raise ExtractorError('Cannot identify player %r' % player_url)
545cc85d 2963 return id_m.group('id')
e40c758c 2964
404f611f 2965 def _load_player(self, video_id, player_url, fatal=True):
109dd3b2 2966 player_id = self._extract_player_info(player_url)
2967 if player_id not in self._code_cache:
1276a43a 2968 code = self._download_webpage(
109dd3b2 2969 player_url, video_id, fatal=fatal,
2970 note='Downloading player ' + player_id,
2971 errnote='Download of %s failed' % player_url)
1276a43a 2972 if code:
2973 self._code_cache[player_id] = code
404f611f 2974 return self._code_cache.get(player_id)
109dd3b2 2975
e40c758c 2976 def _extract_signature_function(self, video_id, player_url, example_sig):
545cc85d 2977 player_id = self._extract_player_info(player_url)
e0df6211 2978
c4417ddb 2979 # Read from filesystem cache
86e5f3ed 2980 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
c4417ddb 2981 assert os.path.basename(func_id) == func_id
a0e07d31 2982
ae61d108 2983 self.write_debug(f'Extracting signature function {func_id}')
580ce007 2984 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
83799698 2985
580ce007 2986 if not cache_spec:
2987 code = self._load_player(video_id, player_url)
404f611f 2988 if code:
109dd3b2 2989 res = self._parse_sig_js(code)
ac668111 2990 test_string = ''.join(map(chr, range(len(example_sig))))
580ce007 2991 cache_spec = [ord(c) for c in res(test_string)]
9809740b 2992 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
580ce007 2993
2994 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 2995
60064c53 2996 def _print_sig_code(self, func, example_sig):
404f611f 2997 if not self.get_param('youtube_print_sig_code'):
2998 return
2999
edf3e38e
PH
3000 def gen_sig_code(idxs):
3001 def _genslice(start, end, step):
78caa52a 3002 starts = '' if start == 0 else str(start)
8bcc8756 3003 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 3004 steps = '' if step == 1 else (':%d' % step)
86e5f3ed 3005 return f's[{starts}{ends}{steps}]'
edf3e38e
PH
3006
3007 step = None
7af808a5
PH
3008 # Quelch pyflakes warnings - start will be set when step is set
3009 start = '(Never used)'
edf3e38e
PH
3010 for i, prev in zip(idxs[1:], idxs[:-1]):
3011 if step is not None:
3012 if i - prev == step:
3013 continue
3014 yield _genslice(start, prev, step)
3015 step = None
3016 continue
3017 if i - prev in [-1, 1]:
3018 step = i - prev
3019 start = prev
3020 continue
3021 else:
78caa52a 3022 yield 's[%d]' % prev
edf3e38e 3023 if step is None:
78caa52a 3024 yield 's[%d]' % i
edf3e38e
PH
3025 else:
3026 yield _genslice(start, i, step)
3027
ac668111 3028 test_string = ''.join(map(chr, range(len(example_sig))))
c705320f 3029 cache_res = func(test_string)
edf3e38e 3030 cache_spec = [ord(c) for c in cache_res]
78caa52a 3031 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53 3032 signature_id_tuple = '(%s)' % (
14f25df2 3033 ', '.join(str(len(p)) for p in example_sig.split('.')))
69ea8ca4 3034 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 3035 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 3036 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 3037
e0df6211
PH
3038 def _parse_sig_js(self, jscode):
3039 funcname = self._search_regex(
abefc03f
S
3040 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3041 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
3042 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
3043 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
4823ec9f 3044 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 3045 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
abefc03f 3046 # Obsolete patterns
4823ec9f 3047 r'("|\')signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
9a47fa35 3048 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f
S
3049 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3050 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
3051 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
abefc03f 3052 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
3c90cc8b 3053 jscode, 'Initial JS player signature function name', group='sig')
2b25cb5d
PH
3054
3055 jsi = JSInterpreter(jscode)
3056 initial_function = jsi.extract_function(funcname)
e0df6211
PH
3057 return lambda s: initial_function([s])
3058
580ce007 3059 def _cached(self, func, *cache_id):
3060 def inner(*args, **kwargs):
3061 if cache_id not in self._player_cache:
3062 try:
3063 self._player_cache[cache_id] = func(*args, **kwargs)
3064 except ExtractorError as e:
3065 self._player_cache[cache_id] = e
3066 except Exception as e:
3067 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
3068
3069 ret = self._player_cache[cache_id]
3070 if isinstance(ret, Exception):
3071 raise ret
3072 return ret
3073 return inner
3074
545cc85d 3075 def _decrypt_signature(self, s, video_id, player_url):
257a2501 3076 """Turn the encrypted s field into a working signature"""
580ce007 3077 extract_sig = self._cached(
3078 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
3079 func = extract_sig(video_id, player_url, s)
3080 self._print_sig_code(func, s)
3081 return func(s)
404f611f 3082
3083 def _decrypt_nsig(self, s, video_id, player_url):
3084 """Turn the encrypted n field into a working signature"""
3085 if player_url is None:
3086 raise ExtractorError('Cannot decrypt nsig without player_url')
60f393e4 3087 player_url = urljoin('https://www.youtube.com', player_url)
404f611f 3088
b505e851 3089 try:
3090 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
3091 except ExtractorError as e:
3092 raise ExtractorError('Unable to extract nsig function code', cause=e)
580ce007 3093 if self.get_param('youtube_print_sig_code'):
3094 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
404f611f 3095
25836db6 3096 try:
3097 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
3098 ret = extract_nsig(jsi, func_code)(s)
3099 except JSInterpreter.Exception as e:
3100 try:
992dc6b4 3101 jsi = PhantomJSwrapper(self, timeout=5000)
25836db6 3102 except ExtractorError:
3103 raise e
3104 self.report_warning(
3105 f'Native nsig extraction failed: Trying with PhantomJS\n'
3106 f' n = {s} ; player = {player_url}', video_id)
0468a3b3 3107 self.write_debug(e, only_once=True)
25836db6 3108
3109 args, func_body = func_code
3110 ret = jsi.execute(
3111 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
3112 video_id=video_id, note='Executing signature code').strip()
580ce007 3113
3114 self.write_debug(f'Decrypted nsig {s} => {ret}')
3115 return ret
3116
90a1df30 3117 def _extract_n_function_name(self, jscode):
3118 funcname, idx = self._search_regex(
3119 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
3120 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
3121 if not idx:
3122 return funcname
3123
3124 return json.loads(js_to_json(self._search_regex(
337734d4 3125 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])\s*[,;]', jscode,
90a1df30 3126 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
3127
580ce007 3128 def _extract_n_function_code(self, video_id, player_url):
404f611f 3129 player_id = self._extract_player_info(player_url)
05deb747 3130 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
580ce007 3131 jscode = func_code or self._load_player(video_id, player_url)
3132 jsi = JSInterpreter(jscode)
404f611f 3133
3134 if func_code:
580ce007 3135 return jsi, player_id, func_code
404f611f 3136
b505e851 3137 func_name = self._extract_n_function_name(jscode)
3138
3139 # For redundancy
3140 func_code = self._search_regex(
3141 r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s*
3142 # NB: The end of the regex is intentionally kept strict
3143 {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name,
3144 jscode, 'nsig function', group=('var', 'code'), default=None)
3145 if func_code:
3146 func_code = ([func_code[0]], func_code[1])
3147 else:
3148 self.write_debug('Extracting nsig function with jsinterp')
3149 func_code = jsi.extract_function_code(func_name)
3150
580ce007 3151 self.cache.store('youtube-nsig', player_id, func_code)
3152 return jsi, player_id, func_code
3153
3154 def _extract_n_function_from_code(self, jsi, func_code):
8f53dc44 3155 func = jsi.extract_function_from_code(*func_code)
f6ca640b 3156
580ce007 3157 def extract_nsig(s):
25836db6 3158 try:
3159 ret = func([s])
3160 except JSInterpreter.Exception:
3161 raise
3162 except Exception as e:
3163 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
3164
f6ca640b 3165 if ret.startswith('enhanced_except_'):
25836db6 3166 raise JSInterpreter.Exception('Signature function returned an exception')
f6ca640b 3167 return ret
580ce007 3168
3169 return extract_nsig
e0df6211 3170
109dd3b2 3171 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
3172 """
3173 Extract signatureTimestamp (sts)
3174 Required to tell API what sig/player version is in use.
3175 """
3176 sts = None
3177 if isinstance(ytcfg, dict):
3178 sts = int_or_none(ytcfg.get('STS'))
3179
3180 if not sts:
3181 # Attempt to extract from player
3182 if player_url is None:
3183 error_msg = 'Cannot extract signature timestamp without player_url.'
3184 if fatal:
3185 raise ExtractorError(error_msg)
3186 self.report_warning(error_msg)
3187 return
404f611f 3188 code = self._load_player(video_id, player_url, fatal=fatal)
3189 if code:
109dd3b2 3190 sts = int_or_none(self._search_regex(
3191 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
3192 'JS player signature timestamp', group='sts', fatal=fatal))
3193 return sts
3194
11f9be09 3195 def _mark_watched(self, video_id, player_responses):
06cc8f10
B
3196 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
3197 label = 'fully ' if is_full else ''
3198 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
3199 expected_type=url_or_none)
3200 if not url:
3201 self.report_warning(f'Unable to mark {label}watched')
3202 return
14f25df2 3203 parsed_url = urllib.parse.urlparse(url)
3204 qs = urllib.parse.parse_qs(parsed_url.query)
06cc8f10
B
3205
3206 # cpn generation algorithm is reverse engineered from base.js.
3207 # In fact it works even with dummy cpn.
3208 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
3209 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
3210
3211 # # more consistent results setting it to right before the end
3212 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
3213
3214 qs.update({
3215 'ver': ['2'],
3216 'cpn': [cpn],
3217 'cmt': video_length,
3218 'el': 'detailpage', # otherwise defaults to "shorts"
3219 })
3220
3221 if is_full:
3222 # these seem to mark watchtime "history" in the real world
3223 # they're required, so send in a single value
3224 qs.update({
5318156f 3225 'st': 0,
06cc8f10
B
3226 'et': video_length,
3227 })
3228
14f25df2 3229 url = urllib.parse.urlunparse(
3230 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
06cc8f10
B
3231
3232 self._download_webpage(
3233 url, video_id, f'Marking {label}watched',
3234 'Unable to mark watched', fatal=False)
d77ab8e2 3235
bfd973ec 3236 @classmethod
3237 def _extract_from_webpage(cls, url, webpage):
3238 # Invidious Instances
3239 # https://github.com/yt-dlp/yt-dlp/issues/195
3240 # https://github.com/iv-org/invidious/pull/1730
3241 mobj = re.search(
3242 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
3243 webpage)
3244 if mobj:
3245 yield cls.url_result(mobj.group('url'), cls)
3246 raise cls.StopExtraction()
3247
3248 yield from super()._extract_from_webpage(url, webpage)
66c9fa36
S
3249
3250 # lazyYT YouTube embed
bfd973ec 3251 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3252 yield cls.url_result(unescapeHTML(id_), cls, id_)
66c9fa36
S
3253
3254 # Wordpress "YouTube Video Importer" plugin
bfd973ec 3255 for m in re.findall(r'''(?x)<div[^>]+
3256 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
3257 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage):
3258 yield cls.url_result(m[-1], cls, m[-1])
66c9fa36 3259
97665381
PH
3260 @classmethod
3261 def extract_id(cls, url):
ae61d108 3262 video_id = cls.get_temp_id(url)
3263 if not video_id:
3264 raise ExtractorError(f'Invalid URL: {url}')
3265 return video_id
c5e8d7af 3266
7c365c21 3267 def _extract_chapters_from_json(self, data, duration):
3268 chapter_list = traverse_obj(
3269 data, (
3270 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3271 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3272 ), expected_type=list)
3273
22ccd542 3274 return self._extract_chapters_helper(
7c365c21 3275 chapter_list,
22ccd542 3276 start_function=lambda chapter: float_or_none(
7c365c21 3277 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
22ccd542 3278 title_function=lambda chapter: traverse_obj(
7c365c21 3279 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3280 duration=duration)
3281
3282 def _extract_chapters_from_engagement_panel(self, data, duration):
3283 content_list = traverse_obj(
8bdd16b4 3284 data,
7c365c21 3285 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
6839ae1f 3286 expected_type=list)
052e1350 3287 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3288 chapter_title = lambda chapter: self._get_text(chapter, 'title')
7c365c21 3289
1890fc63 3290 return next(filter(None, (
22ccd542 3291 self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3292 chapter_time, chapter_title, duration)
1890fc63 3293 for contents in content_list)), [])
7c365c21 3294
5caf30db
A
3295 def _extract_heatmap_from_player_overlay(self, data):
3296 content_list = traverse_obj(data, (
3297 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer', 'decoratedPlayerBarRenderer', 'playerBar',
3298 'multiMarkersPlayerBarRenderer', 'markersMap', ..., 'value', 'heatmap', 'heatmapRenderer', 'heatMarkers', {list}))
3299 return next(filter(None, (
3300 traverse_obj(contents, (..., 'heatMarkerRenderer', {
3301 'start_time': ('timeRangeStartMillis', {functools.partial(float_or_none, scale=1000)}),
3302 'end_time': {lambda x: (x['timeRangeStartMillis'] + x['markerDurationMillis']) / 1000},
3303 'value': ('heatMarkerIntensityScoreNormalized', {float_or_none}),
3304 })) for contents in content_list)), None)
3305
a1c5d2ca
M
3306 def _extract_comment(self, comment_renderer, parent=None):
3307 comment_id = comment_renderer.get('commentId')
3308 if not comment_id:
3309 return
fe93e2c4 3310
c35448b7 3311 info = {
3312 'id': comment_id,
3313 'text': self._get_text(comment_renderer, 'contentText'),
3314 'like_count': self._get_count(comment_renderer, 'voteCount'),
3315 'author_id': traverse_obj(comment_renderer, ('authorEndpoint', 'browseEndpoint', 'browseId', {self.ucid_or_none})),
3316 'author': self._get_text(comment_renderer, 'authorText'),
3317 'author_thumbnail': traverse_obj(comment_renderer, ('authorThumbnail', 'thumbnails', -1, 'url', {url_or_none})),
3318 'parent': parent or 'root',
3319 }
fe93e2c4 3320
c26f9b99 3321 # Timestamp is an estimate calculated from the current time and time_text
3322 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3323 timestamp = self._parse_time_text(time_text)
3324
c35448b7 3325 info.update({
3326 # FIXME: non-standard, but we need a way of showing that it is an estimate.
3327 '_time_text': time_text,
3328 'timestamp': timestamp,
3329 })
fe93e2c4 3330
c35448b7 3331 info['author_url'] = urljoin(
3332 'https://www.youtube.com', traverse_obj(comment_renderer, ('authorEndpoint', (
3333 ('browseEndpoint', 'canonicalBaseUrl'), ('commandMetadata', 'webCommandMetadata', 'url'))),
3334 expected_type=str, get_all=False))
a1c5d2ca 3335
c35448b7 3336 author_is_uploader = traverse_obj(comment_renderer, 'authorIsChannelOwner')
3337 if author_is_uploader is not None:
3338 info['author_is_uploader'] = author_is_uploader
3339
3340 comment_abr = traverse_obj(
89bed013 3341 comment_renderer, ('actionButtons', 'commentActionButtonsRenderer'), expected_type=dict)
c35448b7 3342 if comment_abr is not None:
3343 info['is_favorited'] = 'creatorHeart' in comment_abr
3344
14a14335 3345 badges = self._extract_badges([traverse_obj(comment_renderer, 'authorCommentBadge')])
3346 if self._has_badge(badges, BadgeType.VERIFIED):
3347 info['author_is_verified'] = True
c35448b7 3348
3349 is_pinned = traverse_obj(comment_renderer, 'pinnedCommentBadge')
3350 if is_pinned:
3351 info['is_pinned'] = True
3352
3353 return info
a1c5d2ca 3354
46383212 3355 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3356
3357 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2d6659b9 3358
3359 def extract_header(contents):
2d6659b9 3360 _continuation = None
3361 for content in contents:
46383212 3362 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
f0d785d3 3363 expected_comment_count = self._get_count(
3364 comments_header_renderer, 'countText', 'commentsCount')
fe93e2c4 3365
18f8fba7 3366 if expected_comment_count is not None:
46383212 3367 tracker['est_total'] = expected_comment_count
3368 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3369 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2d6659b9 3370
3371 sort_menu_item = try_get(
3372 comments_header_renderer,
3373 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3374 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3375
3376 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3377 if not _continuation:
3378 continue
3379
46383212 3380 sort_text = str_or_none(sort_menu_item.get('title'))
3381 if not sort_text:
2d6659b9 3382 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
46383212 3383 self.to_screen('Sorting comments by %s' % sort_text.lower())
2d6659b9 3384 break
a2160aa4 3385 return _continuation
a1c5d2ca 3386
2d6659b9 3387 def extract_thread(contents):
a1c5d2ca 3388 if not parent:
46383212 3389 tracker['current_page_thread'] = 0
a1c5d2ca 3390 for content in contents:
46383212 3391 if not parent and tracker['total_parent_comments'] >= max_parents:
3392 yield
a1c5d2ca 3393 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
46383212 3394 comment_renderer = get_first(
3395 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3396 expected_type=dict, default={})
a1c5d2ca 3397
a1c5d2ca
M
3398 comment = self._extract_comment(comment_renderer, parent)
3399 if not comment:
3400 continue
141a8dff 3401 comment_id = comment['id']
c35448b7 3402 if comment.get('is_pinned'):
141a8dff 3403 tracker['pinned_comment_ids'].add(comment_id)
7f51861b 3404 # Sometimes YouTube may break and give us infinite looping comments.
3405 # See: https://github.com/yt-dlp/yt-dlp/issues/6290
141a8dff 3406 if comment_id in tracker['seen_comment_ids']:
c35448b7 3407 if comment_id in tracker['pinned_comment_ids'] and not comment.get('is_pinned'):
141a8dff 3408 # Pinned comments may appear a second time in newest first sort
3409 # See: https://github.com/yt-dlp/yt-dlp/issues/6712
3410 continue
4dc4d847 3411 self.report_warning(
3412 'Detected YouTube comments looping. Stopping comment extraction '
3413 f'{"for this thread" if parent else ""} as we probably cannot get any more.')
7f51861b 3414 yield
3415 else:
3416 tracker['seen_comment_ids'].add(comment['id'])
46383212 3417
3418 tracker['running_total'] += 1
3419 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
a1c5d2ca 3420 yield comment
46383212 3421
a1c5d2ca
M
3422 # Attempt to get the replies
3423 comment_replies_renderer = try_get(
3424 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3425
3426 if comment_replies_renderer:
46383212 3427 tracker['current_page_thread'] += 1
a1c5d2ca 3428 comment_entries_iter = self._comment_entries(
99e9e001 3429 comment_replies_renderer, ytcfg, video_id,
46383212 3430 parent=comment.get('id'), tracker=tracker)
86e5f3ed 3431 yield from itertools.islice(comment_entries_iter, min(
3432 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
a1c5d2ca 3433
46383212 3434 # Keeps track of counts across recursive calls
3435 if not tracker:
3436 tracker = dict(
3437 running_total=0,
18f8fba7 3438 est_total=None,
46383212 3439 current_page_thread=0,
3440 total_parent_comments=0,
7f51861b 3441 total_reply_comments=0,
141a8dff 3442 seen_comment_ids=set(),
3443 pinned_comment_ids=set()
3444 )
46383212 3445
3446 # TODO: Deprecated
2d6659b9 3447 # YouTube comments have a max depth of 2
46383212 3448 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3449 if max_depth:
da4db748 3450 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3451 'Set max replies in the max-comments extractor argument instead')
2d6659b9 3452 if max_depth == 1 and parent:
3453 return
a1c5d2ca 3454
46383212 3455 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3456 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2d6659b9 3457
46383212 3458 continuation = self._extract_continuation(root_continuation_data)
aae16f6e 3459
46383212 3460 response = None
6e634cbe 3461 is_forced_continuation = False
2d6659b9 3462 is_first_continuation = parent is None
6e634cbe 3463 if is_first_continuation and not continuation:
3464 # Sometimes you can get comments by generating the continuation yourself,
3465 # even if YouTube initially reports them being disabled - e.g. stories comments.
3466 # Note: if the comment section is actually disabled, YouTube may return a response with
3467 # required check_get_keys missing. So we will disable that check initially in this case.
3468 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3469 is_forced_continuation = True
a1c5d2ca 3470
18f8fba7 3471 continuation_items_path = (
3472 'onResponseReceivedEndpoints', ..., ('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems')
a1c5d2ca
M
3473 for page_num in itertools.count(0):
3474 if not continuation:
3475 break
46383212 3476 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
18f8fba7 3477 comment_prog_str = f"({tracker['running_total']}/~{tracker['est_total']})"
2d6659b9 3478 if page_num == 0:
3479 if is_first_continuation:
3480 note_prefix = 'Downloading comment section API JSON'
a1c5d2ca 3481 else:
2d6659b9 3482 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
46383212 3483 tracker['current_page_thread'], comment_prog_str)
2d6659b9 3484 else:
3485 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3486 ' ' if parent else '', ' replies' if parent else '',
3487 page_num, comment_prog_str)
18f8fba7 3488
3489 # Do a deep check for incomplete data as sometimes YouTube may return no comments for a continuation
3490 # Ignore check if YouTube says the comment count is 0.
3491 check_get_keys = None
3492 if not is_forced_continuation and not (tracker['est_total'] == 0 and tracker['running_total'] == 0):
3493 check_get_keys = [[*continuation_items_path, ..., (
3494 'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentRenderer'))]]
e72e48c5
M
3495 try:
3496 response = self._extract_response(
3497 item_id=None, query=continuation,
3498 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
18f8fba7 3499 check_get_keys=check_get_keys)
e72e48c5
M
3500 except ExtractorError as e:
3501 # Ignore incomplete data error for replies if retries didn't work.
3502 # This is to allow any other parent comments and comment threads to be downloaded.
3503 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
4dc4d847 3504 if 'incomplete data' in str(e).lower() and parent:
3505 if self.get_param('ignoreerrors') in (True, 'only_download'):
3506 self.report_warning(
3507 'Received incomplete data for a comment reply thread and retrying did not help. '
3508 'Ignoring to let other comments be downloaded. Pass --no-ignore-errors to not ignore.')
3509 return
3510 else:
3511 raise ExtractorError(
3512 'Incomplete data received for comment reply thread. '
3513 'Pass --ignore-errors to ignore and allow rest of comments to download.',
3514 expected=True)
3515 raise
6e634cbe 3516 is_forced_continuation = False
2d6659b9 3517 continuation = None
18f8fba7 3518 for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]):
46383212 3519 if is_first_continuation:
3520 continuation = extract_header(continuation_items)
3521 is_first_continuation = False
2d6659b9 3522 if continuation:
a1c5d2ca 3523 break
46383212 3524 continue
a1c5d2ca 3525
46383212 3526 for entry in extract_thread(continuation_items):
3527 if not entry:
3528 return
3529 yield entry
3530 continuation = self._extract_continuation({'contents': continuation_items})
3531 if continuation:
2d6659b9 3532 break
a1c5d2ca 3533
6e634cbe 3534 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3535 if message and not parent and tracker['running_total'] == 0:
3536 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
0cf643b2 3537 raise self.CommentsDisabled
6e634cbe 3538
3539 @staticmethod
3540 def _generate_comment_continuation(video_id):
3541 """
3542 Generates initial comment section continuation token from given video id
3543 """
3544 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3545 return base64.b64encode(token.encode()).decode()
3546
a2160aa4 3547 def _get_comments(self, ytcfg, video_id, contents, webpage):
a1c5d2ca 3548 """Entry for comment extraction"""
2d6659b9 3549 def _real_comment_extract(contents):
aae16f6e 3550 renderer = next((
3551 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3552 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3553 yield from self._comment_entries(renderer, ytcfg, video_id)
99e9e001 3554
a2160aa4 3555 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
a2160aa4 3556 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
a1c5d2ca 3557
109dd3b2 3558 @staticmethod
99e9e001 3559 def _get_checkok_params():
3560 return {'contentCheckOk': True, 'racyCheckOk': True}
3561
3562 @classmethod
3563 def _generate_player_context(cls, sts=None):
109dd3b2 3564 context = {
3565 'html5Preference': 'HTML5_PREF_WANTS',
3566 }
3567 if sts is not None:
3568 context['signatureTimestamp'] = sts
3569 return {
3570 'playbackContext': {
3571 'contentPlaybackContext': context
a1a7907b 3572 },
99e9e001 3573 **cls._get_checkok_params()
109dd3b2 3574 }
3575
e7e94f2a
D
3576 @staticmethod
3577 def _is_agegated(player_response):
3578 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
9275f62c 3579 return True
e7e94f2a 3580
6839ae1f 3581 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')))
e7e94f2a
D
3582 AGE_GATE_REASONS = (
3583 'confirm your age', 'age-restricted', 'inappropriate', # reason
3584 'age_verification_required', 'age_check_required', # status
3585 )
3586 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3587
3588 @staticmethod
3589 def _is_unplayable(player_response):
3590 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
9275f62c 3591
50ac0e54 3592 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
109dd3b2 3593
11f9be09 3594 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3595 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
b6de707d 3596 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
11f9be09 3597 headers = self.generate_api_headers(
99e9e001 3598 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
9297939e 3599
6e634cbe 3600 yt_query = {
3601 'videoId': video_id,
6e634cbe 3602 }
90db9a3c 3603 if _split_innertube_client(client)[0] == 'android':
ba06d77a 3604 yt_query['params'] = 'CgIQBg=='
3605
546b2c28 3606 pp_arg = self._configuration_arg('player_params', [None], casesense=True)[0]
ba06d77a 3607 if pp_arg:
3608 yt_query['params'] = pp_arg
50ac0e54 3609
11f9be09 3610 yt_query.update(self._generate_player_context(sts))
3611 return self._extract_response(
3612 item_id=video_id, ep='player', query=yt_query,
379e44ed 3613 ytcfg=player_ytcfg, headers=headers, fatal=True,
000c15a4 3614 default_client=client,
11f9be09 3615 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3616 ) or None
3617
11f9be09 3618 def _get_requested_clients(self, url, smuggled_data):
b4c055ba 3619 requested_clients = []
1e75d97d 3620 default = ['ios', 'android', 'web']
000c15a4 3621 allowed_clients = sorted(
86e5f3ed 3622 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
000c15a4 3623 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
b4c055ba 3624 for client in self._configuration_arg('player_client'):
3625 if client in allowed_clients:
3626 requested_clients.append(client)
d0d012d4 3627 elif client == 'default':
3628 requested_clients.extend(default)
b4c055ba 3629 elif client == 'all':
3630 requested_clients.extend(allowed_clients)
3631 else:
3632 self.report_warning(f'Skipping unsupported client {client}')
11f9be09 3633 if not requested_clients:
d0d012d4 3634 requested_clients = default
cf7e015f 3635
11f9be09 3636 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3637 requested_clients.extend(
e7e94f2a 3638 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
dbdaaa23 3639
11f9be09 3640 return orderedSet(requested_clients)
cf7e015f 3641
50ac0e54 3642 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
11f9be09 3643 initial_pr = None
3644 if webpage:
b7c47b74 3645 initial_pr = self._search_json(
3646 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
6b09401b 3647
ae729626 3648 all_clients = set(clients)
c0bc527b 3649 clients = clients[::-1]
b6de707d 3650 prs = []
e7e94f2a 3651
ae729626 3652 def append_client(*client_names):
e7870111 3653 """ Append the first client name that exists but not already used """
ae729626 3654 for client_name in client_names:
e7870111
D
3655 actual_client = _split_innertube_client(client_name)[0]
3656 if actual_client in INNERTUBE_CLIENTS:
3657 if actual_client not in all_clients:
ae729626 3658 clients.append(client_name)
e7870111
D
3659 all_clients.add(actual_client)
3660 return
e7e94f2a 3661
379e44ed 3662 # Android player_response does not have microFormats which are needed for
3663 # extraction of some data. So we return the initial_pr with formats
3664 # stripped out even if not requested by the user
3665 # See: https://github.com/yt-dlp/yt-dlp/issues/501
379e44ed 3666 if initial_pr:
3667 pr = dict(initial_pr)
3668 pr['streamingData'] = None
b6de707d 3669 prs.append(pr)
379e44ed 3670
3671 last_error = None
b6de707d 3672 tried_iframe_fallback = False
3673 player_url = None
c0bc527b 3674 while clients:
e7870111 3675 client, base_client, variant = _split_innertube_client(clients.pop())
11f9be09 3676 player_ytcfg = master_ytcfg if client == 'web' else {}
a25bca9f 3677 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3678 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
c0bc527b 3679
b6de707d 3680 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3681 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3682 if 'js' in self._configuration_arg('player_skip'):
3683 require_js_player = False
3684 player_url = None
3685
3686 if not player_url and not tried_iframe_fallback and require_js_player:
3687 player_url = self._download_player_url(video_id)
3688 tried_iframe_fallback = True
3689
379e44ed 3690 try:
3691 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
50ac0e54 3692 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
379e44ed 3693 except ExtractorError as e:
3694 if last_error:
3695 self.report_warning(last_error)
3696 last_error = e
3697 continue
3698
11f9be09 3699 if pr:
a3e96421 3700 # YouTube may return a different video player response than expected.
3701 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3702 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3703 if pr_video_id and pr_video_id != video_id:
3704 self.report_warning(
c7dcf0b3 3705 f'Skipping player response from {client} client (got player response for video "{pr_video_id}" instead of "{video_id}")' + bug_reports_message())
a3e96421 3706 else:
c795c39f
L
3707 # Save client name for introspection later
3708 name = short_client_name(client)
3709 sd = traverse_obj(pr, ('streamingData', {dict})) or {}
3710 sd[STREAMING_DATA_CLIENT_NAME] = name
3711 for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})):
3712 f[STREAMING_DATA_CLIENT_NAME] = name
a3e96421 3713 prs.append(pr)
c0bc527b 3714
e7e94f2a 3715 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
e7870111
D
3716 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3717 append_client(f'{base_client}_creator')
e7e94f2a 3718 elif self._is_agegated(pr):
e7870111
D
3719 if variant == 'tv_embedded':
3720 append_client(f'{base_client}_embedded')
3721 elif not variant:
3722 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
c0bc527b 3723
379e44ed 3724 if last_error:
b6de707d 3725 if not len(prs):
379e44ed 3726 raise last_error
3727 self.report_warning(last_error)
b6de707d 3728 return prs, player_url
11f9be09 3729
4d37720a
L
3730 def _needs_live_processing(self, live_status, duration):
3731 if (live_status == 'is_live' and self.get_param('live_from_start')
d949c10c 3732 or live_status == 'post_live' and (duration or 0) > 2 * 3600):
4d37720a
L
3733 return live_status
3734
3735 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
e389d172 3736 CHUNK_SIZE = 10 << 20
a4894d3e 3737 itags, stream_ids = collections.defaultdict(set), []
b25cac65 3738 itag_qualities, res_qualities = {}, {0: None}
d3fc8074 3739 q = qualities([
2a9c6dcd 3740 # Normally tiny is the smallest video-only formats. But
3741 # audio-only formats with unknown quality may get tagged as tiny
3742 'tiny',
3743 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
d3fc8074 3744 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3745 ])
6839ae1f 3746 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
58786a10 3747 format_types = self._configuration_arg('formats')
3748 all_formats = 'duplicate' in format_types
3749 if self._configuration_arg('include_duplicate_formats'):
3750 all_formats = True
3751 self._downloader.deprecated_feature('[youtube] include_duplicate_formats extractor argument is deprecated. '
3752 'Use formats=duplicate extractor argument instead')
9297939e 3753
e389d172 3754 def build_fragments(f):
3755 return LazyList({
3756 'url': update_url_query(f['url'], {
3757 'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, f["filesize"])}'
3758 })
3759 } for range_start in range(0, f['filesize'], CHUNK_SIZE))
3760
545cc85d 3761 for fmt in streaming_formats:
727029c5 3762 if fmt.get('targetDurationSec'):
545cc85d 3763 continue
321bf820 3764
cc2db878 3765 itag = str_or_none(fmt.get('itag'))
9297939e 3766 audio_track = fmt.get('audioTrack') or {}
9bb85699 3767 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
86cb9221 3768 if not all_formats:
3769 if stream_id in stream_ids:
3770 continue
9297939e 3771
cc2db878 3772 quality = fmt.get('quality')
2a9c6dcd 3773 height = int_or_none(fmt.get('height'))
d3fc8074 3774 if quality == 'tiny' or not quality:
3775 quality = fmt.get('audioQuality', '').lower() or quality
2a9c6dcd 3776 # The 3gp format (17) in android client has a quality of "small",
3777 # but is actually worse than other formats
3778 if itag == '17':
3779 quality = 'tiny'
3780 if quality:
3781 if itag:
3782 itag_qualities[itag] = quality
3783 if height:
3784 res_qualities[height] = quality
cc2db878 3785 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3786 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3787 # number of fragment that would subsequently requested with (`&sq=N`)
3788 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3789 continue
3790
545cc85d 3791 fmt_url = fmt.get('url')
3792 if not fmt_url:
14f25df2 3793 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
545cc85d 3794 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3795 encrypted_sig = try_get(sc, lambda x: x['s'][0])
52023f12 3796 if not all((sc, fmt_url, player_url, encrypted_sig)):
545cc85d 3797 continue
52023f12 3798 try:
3799 fmt_url += '&%s=%s' % (
3800 traverse_obj(sc, ('sp', -1)) or 'signature',
3801 self._decrypt_signature(encrypted_sig, video_id, player_url)
3802 )
3803 except ExtractorError as e:
580ce007 3804 self.report_warning('Signature extraction failed: Some formats may be missing',
3805 video_id=video_id, only_once=True)
52023f12 3806 self.write_debug(e, only_once=True)
201e9eaa 3807 continue
545cc85d 3808
404f611f 3809 query = parse_qs(fmt_url)
3810 throttled = False
b2916526 3811 if query.get('n'):
404f611f 3812 try:
580ce007 3813 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
404f611f 3814 fmt_url = update_url_query(fmt_url, {
580ce007 3815 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3816 })
404f611f 3817 except ExtractorError as e:
25836db6 3818 phantomjs_hint = ''
3819 if isinstance(e, JSInterpreter.Exception):
d81ba7d4 3820 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3821 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
17ffed18 3822 if player_url:
3823 self.report_warning(
3824 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3825 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3826 self.write_debug(e, only_once=True)
3827 else:
3828 self.report_warning(
3829 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3830 video_id=video_id, only_once=True)
404f611f 3831 throttled = True
3832
0ad92dfb 3833 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
ab6df717 3834 language_preference = (
3835 10 if audio_track.get('audioIsDefault') and 10
3836 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3837 else -1)
0ad92dfb 3838 # Some formats may have much smaller duration than others (possibly damaged during encoding)
62b58c09 3839 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
a1b2d843 3840 # Make sure to avoid false positives with small duration differences.
62b58c09 3841 # E.g. __2ABJjxzNo, ySuUZEjARPY
a1b2d843 3842 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
08d30158 3843 if is_damaged:
0f06bcd7 3844 self.report_warning(
3845 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
c795c39f
L
3846
3847 client_name = fmt.get(STREAMING_DATA_CLIENT_NAME)
51a07b0d 3848 name = fmt.get('qualityLabel') or quality.replace('audio_quality_', '') or ''
97afb093 3849 fps = int_or_none(fmt.get('fps')) or 0
545cc85d 3850 dct = {
3851 'asr': int_or_none(fmt.get('audioSampleRate')),
3852 'filesize': int_or_none(fmt.get('contentLength')),
9bb85699 3853 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
34921b43 3854 'format_note': join_nonempty(
392389b7 3855 join_nonempty(audio_track.get('displayName'),
3856 language_preference > 0 and ' (default)', delim=''),
51a07b0d 3857 name, fmt.get('isDrc') and 'DRC',
a4166234 3858 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3859 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
c795c39f 3860 throttled and 'THROTTLED', is_damaged and 'DAMAGED',
86cb9221 3861 (self.get_param('verbose') or all_formats) and client_name,
c795c39f 3862 delim=', '),
91e5e839 3863 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
51a07b0d 3864 'source_preference': ((-10 if throttled else -5 if itag == '22' else -1)
3865 + (100 if 'Premium' in name else 0)),
97afb093 3866 'fps': fps if fps > 1 else None, # For some formats, fps is wrongly returned as 1
a4166234 3867 'audio_channels': fmt.get('audioChannels'),
2a9c6dcd 3868 'height': height,
9bb85699 3869 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
727029c5 3870 'has_drm': bool(fmt.get('drmFamilies')),
cc2db878 3871 'tbr': tbr,
545cc85d 3872 'url': fmt_url,
2a9c6dcd 3873 'width': int_or_none(fmt.get('width')),
ab6df717 3874 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
08e29b9f 3875 'desc' if language_preference < -1 else '') or None,
ab6df717 3876 'language_preference': language_preference,
a405b38f 3877 # Strictly de-prioritize damaged and 3gp formats
3878 'preference': -10 if is_damaged else -2 if itag == '17' else None,
545cc85d 3879 }
60bdb7bd 3880 mime_mobj = re.match(
3881 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3882 if mime_mobj:
3883 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3884 dct.update(parse_codecs(mime_mobj.group(2)))
86cb9221 3885 if itag:
3886 itags[itag].add(('https', dct.get('language')))
3887 stream_ids.append(stream_id)
c9abebb8 3888 single_stream = 'none' in (dct.get('acodec'), dct.get('vcodec'))
3889 if single_stream and dct.get('ext'):
3890 dct['container'] = dct['ext'] + '_dash'
86cb9221 3891
58786a10 3892 if (all_formats or 'dashy' in format_types) and dct['filesize']:
86cb9221 3893 yield {
3894 **dct,
3895 'format_id': f'{dct["format_id"]}-dashy' if all_formats else dct['format_id'],
5038f6d7 3896 'protocol': 'http_dash_segments',
e389d172 3897 'fragments': build_fragments(dct),
86cb9221 3898 }
58786a10 3899 if all_formats or 'dashy' not in format_types:
3900 dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE}
3901 yield dct
545cc85d 3902
4d37720a 3903 needs_live_processing = self._needs_live_processing(live_status, duration)
58786a10 3904 skip_bad_formats = 'incomplete' not in format_types
3905 if self._configuration_arg('include_incomplete_formats'):
3906 skip_bad_formats = False
3907 self._downloader.deprecated_feature('[youtube] include_incomplete_formats extractor argument is deprecated. '
3908 'Use formats=incomplete extractor argument instead')
4d37720a
L
3909
3910 skip_manifests = set(self._configuration_arg('skip'))
3911 if (not self.get_param('youtube_include_hls_manifest', True)
3912 or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway
3913 or needs_live_processing and skip_bad_formats):
3914 skip_manifests.add('hls')
3915
0f06bcd7 3916 if not self.get_param('youtube_include_dash_manifest', True):
4d37720a
L
3917 skip_manifests.add('dash')
3918 if self._configuration_arg('include_live_dash'):
3919 self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. '
58786a10 3920 'Use formats=incomplete extractor argument instead')
4d37720a
L
3921 elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live':
3922 skip_manifests.add('dash')
5d3a0e79 3923
c795c39f 3924 def process_manifest_format(f, proto, client_name, itag):
a4894d3e 3925 key = (proto, f.get('language'))
86cb9221 3926 if not all_formats and key in itags[itag]:
a4894d3e 3927 return False
3928 itags[itag].add(key)
3929
86cb9221 3930 if itag and all_formats:
3931 f['format_id'] = f'{itag}-{proto}'
3932 elif any(p != proto for p, _ in itags[itag]):
a4894d3e 3933 f['format_id'] = f'{itag}-{proto}'
3934 elif itag:
a0bb6ce5 3935 f['format_id'] = itag
a0bb6ce5 3936
94ed638a 3937 if f.get('source_preference') is None:
3938 f['source_preference'] = -1
3939
1e75d97d 3940 if itag in ('616', '235'):
3941 f['format_note'] = join_nonempty(f.get('format_note'), 'Premium', delim=' ')
94ed638a 3942 f['source_preference'] += 100
1e75d97d 3943
b25cac65 3944 f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1))
5c6d2ef9 3945 if f['quality'] == -1 and f.get('height'):
3946 f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))])
ad54c913 3947 if self.get_param('verbose') or all_formats:
c795c39f 3948 f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ')
97afb093 3949 if f.get('fps') and f['fps'] <= 1:
3950 del f['fps']
94ed638a 3951
3952 if proto == 'hls' and f.get('has_drm'):
3953 f['has_drm'] = 'maybe'
3954 f['source_preference'] -= 5
a0bb6ce5 3955 return True
2a9c6dcd 3956
c646d76f 3957 subtitles = {}
11f9be09 3958 for sd in streaming_data:
c795c39f
L
3959 client_name = sd.get(STREAMING_DATA_CLIENT_NAME)
3960
4d37720a 3961 hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl')
9297939e 3962 if hls_manifest_url:
4d37720a
L
3963 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3964 hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
c646d76f 3965 subtitles = self._merge_subtitles(subs, subtitles)
3966 for f in fmts:
c795c39f 3967 if process_manifest_format(f, 'hls', client_name, self._search_regex(
a0bb6ce5 3968 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3969 yield f
545cc85d 3970
4d37720a 3971 dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl')
5d3a0e79 3972 if dash_manifest_url:
c646d76f 3973 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3974 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3975 for f in formats:
c795c39f 3976 if process_manifest_format(f, 'dash', client_name, f['format_id']):
a0bb6ce5 3977 f['filesize'] = int_or_none(self._search_regex(
3978 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
4d37720a 3979 if needs_live_processing:
adbc4ec4
THD
3980 f['is_from_start'] = True
3981
a0bb6ce5 3982 yield f
c646d76f 3983 yield subtitles
11f9be09 3984
720c3099 3985 def _extract_storyboard(self, player_responses, duration):
3986 spec = get_first(
3987 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
596379e2 3988 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3989 if not base_url:
720c3099 3990 return
720c3099 3991 L = len(spec) - 1
3992 for i, args in enumerate(spec):
3993 args = args.split('#')
3994 counts = list(map(int_or_none, args[:5]))
3995 if len(args) != 8 or not all(counts):
3996 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3997 continue
3998 width, height, frame_count, cols, rows = counts
3999 N, sigh = args[6:]
4000
4001 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
4002 fragment_count = frame_count / (cols * rows)
4003 fragment_duration = duration / fragment_count
4004 yield {
4005 'format_id': f'sb{i}',
4006 'format_note': 'storyboard',
4007 'ext': 'mhtml',
4008 'protocol': 'mhtml',
4009 'acodec': 'none',
4010 'vcodec': 'none',
4011 'url': url,
4012 'width': width,
4013 'height': height,
45e8a04e 4014 'fps': frame_count / duration,
4015 'rows': rows,
4016 'columns': cols,
720c3099 4017 'fragments': [{
b3edc806 4018 'url': url.replace('$M', str(j)),
720c3099 4019 'duration': min(fragment_duration, duration - (j * fragment_duration)),
4020 } for j in range(math.ceil(fragment_count))],
4021 }
4022
adbc4ec4 4023 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
b6de707d 4024 webpage = None
4025 if 'webpage' not in self._configuration_arg('player_skip'):
50ac0e54 4026 query = {'bpctr': '9999999999', 'has_verified': '1'}
546b2c28 4027 pp = self._configuration_arg('player_params', [None], casesense=True)[0]
ba06d77a 4028 if pp:
4029 query['pp'] = pp
b6de707d 4030 webpage = self._download_webpage(
50ac0e54 4031 webpage_url, video_id, fatal=False, query=query)
11f9be09 4032
4033 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
11f9be09 4034
b6de707d 4035 player_responses, player_url = self._extract_player_responses(
11f9be09 4036 self._get_requested_clients(url, smuggled_data),
50ac0e54 4037 video_id, webpage, master_ytcfg, smuggled_data)
11f9be09 4038
adbc4ec4
THD
4039 return webpage, master_ytcfg, player_responses, player_url
4040
a1b2d843 4041 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
adbc4ec4
THD
4042 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
4043 is_live = get_first(video_details, 'isLive')
4044 if is_live is None:
4045 is_live = get_first(live_broadcast_details, 'isLiveNow')
4d37720a
L
4046 live_content = get_first(video_details, 'isLiveContent')
4047 is_upcoming = get_first(video_details, 'isUpcoming')
4d37720a
L
4048 post_live = get_first(video_details, 'isPostLiveDvr')
4049 live_status = ('post_live' if post_live
4050 else 'is_live' if is_live
4051 else 'is_upcoming' if is_upcoming
6678a4f0 4052 else 'was_live' if live_content
4053 else 'not_live' if False in (is_live, live_content)
4054 else None)
6839ae1f 4055 streaming_data = traverse_obj(player_responses, (..., 'streamingData'))
4d37720a 4056 *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration)
94ed638a 4057 if all(f.get('has_drm') for f in formats):
4058 # If there are no formats that definitely don't have DRM, all have DRM
4059 for f in formats:
4060 f['has_drm'] = True
adbc4ec4 4061
4d37720a 4062 return live_broadcast_details, live_status, streaming_data, formats, subtitles
adbc4ec4
THD
4063
4064 def _real_extract(self, url):
4065 url, smuggled_data = unsmuggle_url(url, {})
4066 video_id = self._match_id(url)
4067
4068 base_url = self.http_scheme() + '//www.youtube.com/'
4069 webpage_url = base_url + 'watch?v=' + video_id
4070
4071 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
4072
11f9be09 4073 playability_statuses = traverse_obj(
6839ae1f 4074 player_responses, (..., 'playabilityStatus'), expected_type=dict)
11f9be09 4075
4076 trailer_video_id = get_first(
4077 playability_statuses,
4078 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
4079 expected_type=str)
4080 if trailer_video_id:
4081 return self.url_result(
4082 trailer_video_id, self.ie_key(), trailer_video_id)
4083
4084 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
4085 if webpage else (lambda x: None))
4086
6839ae1f 4087 video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict)
11f9be09 4088 microformats = traverse_obj(
4089 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
6839ae1f 4090 expected_type=dict)
c26f9b99 4091
4092 translated_title = self._get_text(microformats, (..., 'title'))
4093 video_title = (self._preferred_lang and translated_title
4094 or get_first(video_details, 'title') # primary
4095 or translated_title
4096 or search_meta(['og:title', 'twitter:title', 'title']))
4097 translated_description = self._get_text(microformats, (..., 'description'))
4098 original_description = get_first(video_details, 'shortDescription')
4099 video_description = (
4100 self._preferred_lang and translated_description
4101 # If original description is blank, it will be an empty string.
4102 # Do not prefer translated description in this case.
4103 or original_description if original_description is not None else translated_description)
11f9be09 4104
d89257f3 4105 multifeed_metadata_list = get_first(
4106 player_responses,
4107 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
4108 expected_type=str)
4109 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
4110 if self.get_param('noplaylist'):
11f9be09 4111 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
d89257f3 4112 else:
4113 entries = []
4114 feed_ids = []
4115 for feed in multifeed_metadata_list.split(','):
4116 # Unquote should take place before split on comma (,) since textual
4117 # fields may contain comma as well (see
4118 # https://github.com/ytdl-org/youtube-dl/issues/8536)
14f25df2 4119 feed_data = urllib.parse.parse_qs(
ac668111 4120 urllib.parse.unquote_plus(feed))
d89257f3 4121
4122 def feed_entry(name):
4123 return try_get(
14f25df2 4124 feed_data, lambda x: x[name][0], str)
d89257f3 4125
4126 feed_id = feed_entry('id')
4127 if not feed_id:
4128 continue
4129 feed_title = feed_entry('title')
4130 title = video_title
4131 if feed_title:
4132 title += ' (%s)' % feed_title
4133 entries.append({
4134 '_type': 'url_transparent',
4135 'ie_key': 'Youtube',
4136 'url': smuggle_url(
4137 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
4138 {'force_singlefeed': True}),
4139 'title': title,
4140 })
4141 feed_ids.append(feed_id)
4142 self.to_screen(
4143 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
4144 % (', '.join(feed_ids), video_id))
4145 return self.playlist_result(
4146 entries, video_id, video_title, video_description)
11f9be09 4147
9da6612b 4148 duration = (int_or_none(get_first(video_details, 'lengthSeconds'))
4149 or int_or_none(get_first(microformats, 'lengthSeconds'))
4150 or parse_duration(search_meta('duration')) or None)
a1b2d843 4151
4d37720a
L
4152 live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \
4153 self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration)
4154 if live_status == 'post_live':
4155 self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode')
bf1317d2 4156
545cc85d 4157 if not formats:
11f9be09 4158 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
88acdbc2 4159 self.report_drm(video_id)
11f9be09 4160 pemr = get_first(
4161 playability_statuses,
4162 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
4163 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
4164 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
545cc85d 4165 if subreason:
545cc85d 4166 if subreason == 'The uploader has not made this video available in your country.':
11f9be09 4167 countries = get_first(microformats, 'availableCountries')
545cc85d 4168 if not countries:
4169 regions_allowed = search_meta('regionsAllowed')
4170 countries = regions_allowed.split(',') if regions_allowed else None
b7da73eb 4171 self.raise_geo_restricted(subreason, countries, metadata_available=True)
11f9be09 4172 reason += f'. {subreason}'
545cc85d 4173 if reason:
b7da73eb 4174 self.raise_no_formats(reason, expected=True)
bf1317d2 4175
11f9be09 4176 keywords = get_first(video_details, 'keywords', expected_type=list) or []
545cc85d 4177 if not keywords and webpage:
4178 keywords = [
4179 unescapeHTML(m.group('content'))
4180 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
4181 for keyword in keywords:
4182 if keyword.startswith('yt:stretch='):
201c1459 4183 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
4184 if mobj:
4185 # NB: float is intentional for forcing float division
4186 w, h = (float(v) for v in mobj.groups())
4187 if w > 0 and h > 0:
4188 ratio = w / h
4189 for f in formats:
4190 if f.get('vcodec') != 'none':
4191 f['stretched_ratio'] = ratio
4192 break
a709d873 4193 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
ff2751ac 4194 thumbnail_url = search_meta(['og:image', 'twitter:image'])
4195 if thumbnail_url:
4196 thumbnails.append({
4197 'url': thumbnail_url,
ff2751ac 4198 })
fccf5021 4199 original_thumbnails = thumbnails.copy()
4200
0ba692ac 4201 # The best resolution thumbnails sometimes does not appear in the webpage
bfec31be 4202 # See: https://github.com/yt-dlp/yt-dlp/issues/340
cca80fe6 4203 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
e820fbaa 4204 thumbnail_names = [
962ffcf8 4205 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
bfec31be 4206 # in resolution, these are not the custom thumbnail. So de-prioritize them
4207 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4208 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
cca80fe6 4209 ]
cca80fe6 4210 n_thumbnail_names = len(thumbnail_names)
0ba692ac 4211 thumbnails.extend({
4212 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4213 video_id=video_id, name=name, ext=ext,
4d37720a 4214 webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''),
cca80fe6 4215 } for name in thumbnail_names for ext in ('webp', 'jpg'))
0ba692ac 4216 for thumb in thumbnails:
cca80fe6 4217 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
0ba692ac 4218 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
ff2751ac 4219 self._remove_duplicate_formats(thumbnails)
fccf5021 4220 self._downloader._sort_thumbnails(original_thumbnails)
545cc85d 4221
7ea65411 4222 category = get_first(microformats, 'category') or search_meta('genre')
7666b936 4223 channel_id = self.ucid_or_none(str_or_none(
7ea65411 4224 get_first(video_details, 'channelId')
4225 or get_first(microformats, 'externalChannelId')
7666b936 4226 or search_meta('channelId')))
7ea65411 4227 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
4228
adbc4ec4
THD
4229 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
4230 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
4231 if not duration and live_end_time and live_start_time:
4232 duration = live_end_time - live_start_time
4233
4d37720a
L
4234 needs_live_processing = self._needs_live_processing(live_status, duration)
4235
4236 def is_bad_format(fmt):
4237 if needs_live_processing and not fmt.get('is_from_start'):
4238 return True
4239 elif (live_status == 'is_live' and needs_live_processing != 'is_live'
4240 and fmt.get('protocol') == 'http_dash_segments'):
4241 return True
4242
4243 for fmt in filter(is_bad_format, formats):
4244 fmt['preference'] = (fmt.get('preference') or -1) - 10
d949c10c 4245 fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 2 hours)', delim=' ')
4d37720a
L
4246
4247 if needs_live_processing:
4248 self._prepare_live_from_start_formats(
4249 formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live')
7ea65411 4250
720c3099 4251 formats.extend(self._extract_storyboard(player_responses, duration))
4252
7666b936 4253 channel_handle = self.handle_from_url(owner_profile_url)
4254
545cc85d 4255 info = {
4256 'id': video_id,
39ca3b5c 4257 'title': video_title,
545cc85d 4258 'formats': formats,
4259 'thumbnails': thumbnails,
fccf5021 4260 # The best thumbnail that we are sure exists. Prevents unnecessary
4261 # URL checking if user don't care about getting the best possible thumbnail
4262 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
545cc85d 4263 'description': video_description,
545cc85d 4264 'channel_id': channel_id,
7666b936 4265 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None),
545cc85d 4266 'duration': duration,
4267 'view_count': int_or_none(
11f9be09 4268 get_first((video_details, microformats), (..., 'viewCount'))
545cc85d 4269 or search_meta('interactionCount')),
11f9be09 4270 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
545cc85d 4271 'age_limit': 18 if (
11f9be09 4272 get_first(microformats, 'isFamilySafe') is False
545cc85d 4273 or search_meta('isFamilyFriendly') == 'false'
4274 or search_meta('og:restrictions:age') == '18+') else 0,
4275 'webpage_url': webpage_url,
4276 'categories': [category] if category else None,
4277 'tags': keywords,
11f9be09 4278 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
4d37720a 4279 'live_status': live_status,
adbc4ec4 4280 'release_timestamp': live_start_time,
9f14daf2 4281 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4282 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
545cc85d 4283 }
b477fc13 4284
c646d76f 4285 subtitles = {}
3944e7af 4286 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
545cc85d 4287 if pctr:
ecdc9049 4288 def get_lang_code(track):
4289 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
4290 or track.get('languageCode'))
4291
4292 # Converted into dicts to remove duplicates
4293 captions = {
4294 get_lang_code(sub): sub
6839ae1f 4295 for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
ecdc9049 4296 translation_languages = {
4297 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
6839ae1f 4298 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
ecdc9049 4299
774d79cc 4300 def process_language(container, base_url, lang_code, sub_name, query):
120916da 4301 lang_subs = container.setdefault(lang_code, [])
545cc85d 4302 for fmt in self._SUBTITLE_FORMATS:
4303 query.update({
4304 'fmt': fmt,
4305 })
4306 lang_subs.append({
4307 'ext': fmt,
60f393e4 4308 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
774d79cc 4309 'name': sub_name,
545cc85d 4310 })
7e72694b 4311
07b47084 4312 # NB: Constructing the full subtitle dictionary is slow
4313 get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
4314 self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
ecdc9049 4315 for lang_code, caption_track in captions.items():
4316 base_url = caption_track.get('baseUrl')
1235d333 4317 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
545cc85d 4318 if not base_url:
4319 continue
ecdc9049 4320 lang_name = self._get_text(caption_track, 'name', max_runs=1)
545cc85d 4321 if caption_track.get('kind') != 'asr':
545cc85d 4322 if not lang_code:
4323 continue
4324 process_language(
ecdc9049 4325 subtitles, base_url, lang_code, lang_name, {})
4326 if not caption_track.get('isTranslatable'):
4327 continue
3944e7af 4328 for trans_code, trans_name in translation_languages.items():
4329 if not trans_code:
545cc85d 4330 continue
1235d333 4331 orig_trans_code = trans_code
71eb82d1 4332 if caption_track.get('kind') != 'asr' and trans_code != 'und':
07b47084 4333 if not get_translated_subs:
18e49408 4334 continue
ecdc9049 4335 trans_code += f'-{lang_code}'
a70635b8 4336 trans_name += format_field(lang_name, None, ' from %s')
1235d333 4337 if lang_code == f'a-{orig_trans_code}':
ff9b0e07 4338 # Set audio language based on original subtitles
4339 for f in formats:
4340 if f.get('acodec') != 'none' and not f.get('language'):
4341 f['language'] = orig_trans_code
4342 # Add an "-orig" label to the original language so that it can be distinguished.
4343 # The subs are returned without "-orig" as well for compatibility
0c8d9e5f 4344 process_language(
d49669ac 4345 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
4346 # Setting tlang=lang returns damaged subtitles.
d49669ac 4347 process_language(automatic_captions, base_url, trans_code, trans_name,
1235d333 4348 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
c646d76f 4349
4350 info['automatic_captions'] = automatic_captions
4351 info['subtitles'] = subtitles
7e72694b 4352
14f25df2 4353 parsed_url = urllib.parse.urlparse(url)
545cc85d 4354 for component in [parsed_url.fragment, parsed_url.query]:
14f25df2 4355 query = urllib.parse.parse_qs(component)
545cc85d 4356 for k, v in query.items():
4357 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
4358 d_k += '_time'
4359 if d_k not in info and k in s_ks:
4360 info[d_k] = parse_duration(query[k][0])
822b9d9c
RA
4361
4362 # Youtube Music Auto-generated description
71dc18fa
BT
4363 if (video_description or '').strip().endswith('\nAuto-generated by YouTube.'):
4364 # XXX: Causes catastrophic backtracking if description has "·"
4365 # E.g. https://www.youtube.com/watch?v=DoPaAxMQoiI
4366 # Simulating atomic groups: (?P<a>[^xy]+)x => (?=(?P<a>[^xy]+))(?P=a)x
4367 # reduces it, but does not fully fix it. https://regex101.com/r/8Ssf2h/2
1890fc63 4368 mobj = re.search(
4369 r'''(?xs)
71dc18fa
BT
4370 (?=(?P<track>[^\n·]+))(?P=track)·
4371 (?=(?P<artist>[^\n]+))(?P=artist)\n+
4372 (?=(?P<album>[^\n]+))(?P=album)\n
1890fc63 4373 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4374 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
71dc18fa
BT
4375 (.+?\nArtist\s*:\s*
4376 (?=(?P<clean_artist>[^\n]+))(?P=clean_artist)\n
4377 )?.+\nAuto-generated\ by\ YouTube\.\s*$
1890fc63 4378 ''', video_description)
822b9d9c 4379 if mobj:
822b9d9c
RA
4380 release_year = mobj.group('release_year')
4381 release_date = mobj.group('release_date')
4382 if release_date:
4383 release_date = release_date.replace('-', '')
4384 if not release_year:
545cc85d 4385 release_year = release_date[:4]
4386 info.update({
4387 'album': mobj.group('album'.strip()),
4388 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
4389 'track': mobj.group('track').strip(),
4390 'release_date': release_date,
cc2db878 4391 'release_year': int_or_none(release_year),
545cc85d 4392 })
7e72694b 4393
545cc85d 4394 initial_data = None
4395 if webpage:
56ba69e4 4396 initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
607510b9 4397 if not traverse_obj(initial_data, 'contents'):
4398 self.report_warning('Incomplete data received in embedded initial data; re-fetching using API.')
4399 initial_data = None
545cc85d 4400 if not initial_data:
99e9e001 4401 query = {'videoId': video_id}
4402 query.update(self._get_checkok_params())
109dd3b2 4403 initial_data = self._extract_response(
4404 item_id=video_id, ep='next', fatal=False,
607510b9 4405 ytcfg=master_ytcfg, query=query, check_get_keys='contents',
99e9e001 4406 headers=self.generate_api_headers(ytcfg=master_ytcfg),
109dd3b2 4407 note='Downloading initial data API JSON')
545cc85d 4408
0df111a3 4409 info['comment_count'] = traverse_obj(initial_data, (
4410 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
071670cb 4411 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount'
0df111a3 4412 ), (
4413 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
071670cb
ND
4414 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo'
4415 ), expected_type=self._get_count, get_all=False)
0df111a3 4416
19a03940 4417 try: # This will error if there is no livechat
c60ee3a2 4418 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
19a03940 4419 except (KeyError, IndexError, TypeError):
4420 pass
4421 else:
ecdc9049 4422 info.setdefault('subtitles', {})['live_chat'] = [{
4ce05f57 4423 # url is needed to set cookies
4424 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
c60ee3a2 4425 'video_id': video_id,
4426 'ext': 'json',
4d37720a
L
4427 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming')
4428 else 'youtube_live_chat_replay'),
c60ee3a2 4429 }]
545cc85d 4430
4431 if initial_data:
7c365c21 4432 info['chapters'] = (
4433 self._extract_chapters_from_json(initial_data, duration)
4434 or self._extract_chapters_from_engagement_panel(initial_data, duration)
0fe51254 4435 or self._extract_chapters_from_description(video_description, duration)
7c365c21 4436 or None)
545cc85d 4437
5caf30db
A
4438 info['heatmap'] = self._extract_heatmap_from_player_overlay(initial_data)
4439
17322130 4440 contents = traverse_obj(
4441 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4442 expected_type=list, default=[])
4443
4444 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
4445 if vpir:
4446 stl = vpir.get('superTitleLink')
4447 if stl:
4448 stl = self._get_text(stl)
4449 if try_get(
4450 vpir,
4451 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4452 info['location'] = stl
4453 else:
affc4fef 4454 mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl)
17322130 4455 if mobj:
545cc85d 4456 info.update({
17322130 4457 'series': mobj.group(1),
4458 'season_number': int(mobj.group(2)),
4459 'episode_number': int(mobj.group(3)),
545cc85d 4460 })
17322130 4461 for tlb in (try_get(
4462 vpir,
4463 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
4464 list) or []):
3ffb2f5b 4465 tbrs = variadic(
4466 traverse_obj(
6839ae1f
SS
4467 tlb, ('toggleButtonRenderer', ...),
4468 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
3ffb2f5b 4469 for tbr in tbrs:
4470 for getter, regex in [(
4471 lambda x: x['defaultText']['accessibility']['accessibilityData'],
4472 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4473 lambda x: x['accessibility'],
4474 lambda x: x['accessibilityData']['accessibilityData'],
4475 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4476 label = (try_get(tbr, getter, dict) or {}).get('label')
4477 if label:
4478 mobj = re.match(regex, label)
4479 if mobj:
4480 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
4481 break
17322130 4482 sbr_tooltip = try_get(
4483 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
4484 if sbr_tooltip:
4485 like_count, dislike_count = sbr_tooltip.split(' / ')
4486 info.update({
4487 'like_count': str_to_int(like_count),
4488 'dislike_count': str_to_int(dislike_count),
4489 })
867c66ff
M
4490 vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer'))
4491 if vcr:
4492 vc = self._get_count(vcr, 'viewCount')
4493 # Upcoming premieres with waiting count are treated as live here
4494 if vcr.get('isLive'):
4495 info['concurrent_view_count'] = vc
4496 elif info.get('view_count') is None:
4497 info['view_count'] = vc
4498
17322130 4499 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
4500 if vsir:
4501 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
4502 info.update({
4503 'channel': self._get_text(vor, 'title'),
4504 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
4505
7666b936 4506 if not channel_handle:
4507 channel_handle = self.handle_from_url(
4508 traverse_obj(vor, (
4509 ('navigationEndpoint', ('title', 'runs', ..., 'navigationEndpoint')),
4510 (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl')),
4511 {str}), get_all=False))
4512
17322130 4513 rows = try_get(
4514 vsir,
4515 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4516 list) or []
4517 multiple_songs = False
4518 for row in rows:
4519 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
4520 multiple_songs = True
4521 break
4522 for row in rows:
4523 mrr = row.get('metadataRowRenderer') or {}
4524 mrr_title = mrr.get('title')
4525 if not mrr_title:
4526 continue
4527 mrr_title = self._get_text(mrr, 'title')
4528 mrr_contents_text = self._get_text(mrr, ('contents', 0))
4529 if mrr_title == 'License':
4530 info['license'] = mrr_contents_text
4531 elif not multiple_songs:
4532 if mrr_title == 'Album':
4533 info['album'] = mrr_contents_text
4534 elif mrr_title == 'Artist':
4535 info['artist'] = mrr_contents_text
4536 elif mrr_title == 'Song':
4537 info['track'] = mrr_contents_text
8213ce28 4538 owner_badges = self._extract_badges(traverse_obj(vsir, ('owner', 'videoOwnerRenderer', 'badges')))
4539 if self._has_badge(owner_badges, BadgeType.VERIFIED):
4540 info['channel_is_verified'] = True
545cc85d 4541
7666b936 4542 info.update({
4543 'uploader': info.get('channel'),
4544 'uploader_id': channel_handle,
4545 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
4546 })
17322130 4547 # The upload date for scheduled, live and past live streams / premieres in microformats
4548 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
992f9a73 4549 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
17322130 4550 upload_date = (
4551 unified_strdate(get_first(microformats, 'uploadDate'))
4552 or unified_strdate(search_meta('uploadDate')))
1ff88b7a 4553 if not upload_date or (
4d37720a 4554 live_status in ('not_live', None)
1ff88b7a 4555 and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', [])
4556 ):
c26f9b99 4557 upload_date = strftime_or_none(
ad54c913 4558 self._parse_time_text(self._get_text(vpir, 'dateText'))) or upload_date
17322130 4559 info['upload_date'] = upload_date
992f9a73 4560
545cc85d 4561 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
4562 v = info.get(s_k)
4563 if v:
4564 info[d_k] = v
b84071c0 4565
14a14335 4566 badges = self._extract_badges(traverse_obj(vpir, 'badges'))
c26f9b99 4567
4568 is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
4569 or get_first(video_details, 'isPrivate', expected_type=bool))
4570
4571 info['availability'] = (
4572 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
4573 else self._availability(
4574 is_private=is_private,
4575 needs_premium=(
4576 self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM)
4577 or False if initial_data and is_private is not None else None),
4578 needs_subscription=(
4579 self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION)
4580 or False if initial_data and is_private is not None else None),
4581 needs_auth=info['age_limit'] >= 18,
4582 is_unlisted=None if is_private is None else (
4583 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
4584 or get_first(microformats, 'isUnlisted', expected_type=bool))))
c224251a 4585
a2160aa4 4586 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
4ea3be0a 4587
11f9be09 4588 self.mark_watched(video_id, player_responses)
d77ab8e2 4589
545cc85d 4590 return info
c5e8d7af 4591
a61fd4cf 4592
a6213a49 4593class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
182bda88 4594 @staticmethod
4595 def passthrough_smuggled_data(func):
bd7e919a 4596 def _smuggle(info, smuggled_data):
4597 if info.get('_type') not in ('url', 'url_transparent'):
4598 return info
4599 if smuggled_data.get('is_music_url'):
4600 parsed_url = urllib.parse.urlparse(info['url'])
4601 if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'):
4602 smuggled_data.pop('is_music_url')
4603 info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com'))
4604 if smuggled_data:
4605 info['url'] = smuggle_url(info['url'], smuggled_data)
4606 return info
182bda88 4607
4608 @functools.wraps(func)
4609 def wrapper(self, url):
4610 url, smuggled_data = unsmuggle_url(url, {})
4611 if self.is_music_url(url):
4612 smuggled_data['is_music_url'] = True
4613 info_dict = func(self, url, smuggled_data)
bd7e919a 4614 if smuggled_data:
4615 _smuggle(info_dict, smuggled_data)
4616 if info_dict.get('entries'):
a8c754cc 4617 info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries'])
182bda88 4618 return info_dict
4619 return wrapper
4620
8bdd16b4 4621 @staticmethod
cd7c66cf 4622 def _extract_basic_item_renderer(item):
4623 # Modified from _extract_grid_item_renderer
201c1459 4624 known_basic_renderers = (
a17526e4 4625 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
cd7c66cf 4626 )
4627 for key, renderer in item.items():
201c1459 4628 if not isinstance(renderer, dict):
cd7c66cf 4629 continue
201c1459 4630 elif key in known_basic_renderers:
4631 return renderer
4632 elif key.startswith('grid') and key.endswith('Renderer'):
4633 return renderer
8bdd16b4 4634
c7335551 4635 def _extract_channel_renderer(self, renderer):
7666b936 4636 channel_id = self.ucid_or_none(renderer['channelId'])
c7335551 4637 title = self._get_text(renderer, 'title')
7666b936 4638 channel_url = format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None)
7666b936 4639 channel_handle = self.handle_from_url(
4640 traverse_obj(renderer, (
4641 'navigationEndpoint', (('commandMetadata', 'webCommandMetadata', 'url'),
4642 ('browseEndpoint', 'canonicalBaseUrl')),
4643 {str}), get_all=False))
14a14335 4644 if not channel_handle:
4645 # As of 2023-06-01, YouTube sets subscriberCountText to the handle in search
4646 channel_handle = self.handle_or_none(self._get_text(renderer, 'subscriberCountText'))
c7335551
M
4647 return {
4648 '_type': 'url',
4649 'url': channel_url,
4650 'id': channel_id,
4651 'ie_key': YoutubeTabIE.ie_key(),
4652 'channel': title,
7666b936 4653 'uploader': title,
c7335551
M
4654 'channel_id': channel_id,
4655 'channel_url': channel_url,
4656 'title': title,
7666b936 4657 'uploader_id': channel_handle,
4658 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
14a14335 4659 # See above. YouTube sets videoCountText to the subscriber text in search channel renderers.
4660 # However, in feed/channels this is set correctly to the subscriber count
4661 'channel_follower_count': traverse_obj(
4662 renderer, 'subscriberCountText', 'videoCountText', expected_type=self._get_count),
c7335551 4663 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'),
14a14335 4664 'playlist_count': (
4665 # videoCountText may be the subscriber count
4666 self._get_count(renderer, 'videoCountText')
4667 if self._get_count(renderer, 'subscriberCountText') is not None else None),
c7335551 4668 'description': self._get_text(renderer, 'descriptionSnippet'),
8213ce28 4669 'channel_is_verified': True if self._has_badge(
4670 self._extract_badges(traverse_obj(renderer, 'ownerBadges')), BadgeType.VERIFIED) else None,
c7335551
M
4671 }
4672
8bdd16b4 4673 def _grid_entries(self, grid_renderer):
4674 for item in grid_renderer['items']:
4675 if not isinstance(item, dict):
39b62db1 4676 continue
cd7c66cf 4677 renderer = self._extract_basic_item_renderer(item)
8bdd16b4 4678 if not isinstance(renderer, dict):
4679 continue
052e1350 4680 title = self._get_text(renderer, 'title')
fe93e2c4 4681
8bdd16b4 4682 # playlist
4683 playlist_id = renderer.get('playlistId')
4684 if playlist_id:
4685 yield self.url_result(
4686 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4687 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4688 video_title=title)
201c1459 4689 continue
8bdd16b4 4690 # video
4691 video_id = renderer.get('videoId')
4692 if video_id:
4693 yield self._extract_video(renderer)
201c1459 4694 continue
8bdd16b4 4695 # channel
4696 channel_id = renderer.get('channelId')
4697 if channel_id:
c7335551 4698 yield self._extract_channel_renderer(renderer)
201c1459 4699 continue
4700 # generic endpoint URL support
4701 ep_url = urljoin('https://www.youtube.com/', try_get(
4702 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4703 str))
201c1459 4704 if ep_url:
4705 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
4706 if ie.suitable(ep_url):
4707 yield self.url_result(
4708 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
4709 break
8bdd16b4 4710
16aa9ea4 4711 def _music_reponsive_list_entry(self, renderer):
4712 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
4713 if video_id:
69a40e4a 4714 title = traverse_obj(renderer, (
4715 'flexColumns', 0, 'musicResponsiveListItemFlexColumnRenderer',
4716 'text', 'runs', 0, 'text'))
16aa9ea4 4717 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
69a40e4a 4718 ie=YoutubeIE.ie_key(), video_id=video_id, title=title)
16aa9ea4 4719 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4720 if playlist_id:
4721 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4722 if video_id:
4723 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4724 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4725 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
4726 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4727 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4728 if browse_id:
4729 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
4730 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
4731
3d3dddc9 4732 def _shelf_entries_from_content(self, shelf_renderer):
4733 content = shelf_renderer.get('content')
4734 if not isinstance(content, dict):
8bdd16b4 4735 return
cd7c66cf 4736 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3d3dddc9 4737 if renderer:
4738 # TODO: add support for nested playlists so each shelf is processed
4739 # as separate playlist
4740 # TODO: this includes only first N items
86e5f3ed 4741 yield from self._grid_entries(renderer)
3d3dddc9 4742 renderer = content.get('horizontalListRenderer')
4743 if renderer:
4744 # TODO
4745 pass
8bdd16b4 4746
29f7c58a 4747 def _shelf_entries(self, shelf_renderer, skip_channels=False):
8bdd16b4 4748 ep = try_get(
4749 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 4750 str)
8bdd16b4 4751 shelf_url = urljoin('https://www.youtube.com', ep)
3d3dddc9 4752 if shelf_url:
29f7c58a 4753 # Skipping links to another channels, note that checking for
4754 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4755 # will not work
4756 if skip_channels and '/channels?' in shelf_url:
4757 return
052e1350 4758 title = self._get_text(shelf_renderer, 'title')
3d3dddc9 4759 yield self.url_result(shelf_url, video_title=title)
4760 # Shelf may not contain shelf URL, fallback to extraction from content
86e5f3ed 4761 yield from self._shelf_entries_from_content(shelf_renderer)
c5e8d7af 4762
8bdd16b4 4763 def _playlist_entries(self, video_list_renderer):
4764 for content in video_list_renderer['contents']:
4765 if not isinstance(content, dict):
4766 continue
4767 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
4768 if not isinstance(renderer, dict):
4769 continue
4770 video_id = renderer.get('videoId')
4771 if not video_id:
4772 continue
4773 yield self._extract_video(renderer)
07aeced6 4774
3462ffa8 4775 def _rich_entries(self, rich_grid_renderer):
80eb0bd9 4776 renderer = traverse_obj(
447afb9e 4777 rich_grid_renderer,
4778 ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer')), get_all=False) or {}
3462ffa8 4779 video_id = renderer.get('videoId')
447afb9e 4780 if video_id:
4781 yield self._extract_video(renderer)
4782 return
4783 playlist_id = renderer.get('playlistId')
4784 if playlist_id:
4785 yield self.url_result(
4786 f'https://www.youtube.com/playlist?list={playlist_id}',
4787 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4788 video_title=self._get_text(renderer, 'title'))
3462ffa8 4789 return
3462ffa8 4790
8bdd16b4 4791 def _video_entry(self, video_renderer):
4792 video_id = video_renderer.get('videoId')
4793 if video_id:
4794 return self._extract_video(video_renderer)
dacb3a86 4795
ad210f4f 4796 def _hashtag_tile_entry(self, hashtag_tile_renderer):
4797 url = urljoin('https://youtube.com', traverse_obj(
4798 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4799 if url:
4800 return self.url_result(
4801 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
4802
8bdd16b4 4803 def _post_thread_entries(self, post_thread_renderer):
4804 post_renderer = try_get(
4805 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
4806 if not post_renderer:
4807 return
4808 # video attachment
4809 video_renderer = try_get(
895b0931 4810 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
4811 video_id = video_renderer.get('videoId')
4812 if video_id:
4813 entry = self._extract_video(video_renderer)
8bdd16b4 4814 if entry:
4815 yield entry
895b0931 4816 # playlist attachment
4817 playlist_id = try_get(
14f25df2 4818 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str)
895b0931 4819 if playlist_id:
4820 yield self.url_result(
e28f1c0a 4821 'https://www.youtube.com/playlist?list=%s' % playlist_id,
4822 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 4823 # inline video links
4824 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
4825 for run in runs:
4826 if not isinstance(run, dict):
4827 continue
4828 ep_url = try_get(
14f25df2 4829 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str)
8bdd16b4 4830 if not ep_url:
4831 continue
4832 if not YoutubeIE.suitable(ep_url):
4833 continue
4834 ep_video_id = YoutubeIE._match_id(ep_url)
4835 if video_id == ep_video_id:
4836 continue
895b0931 4837 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
dacb3a86 4838
8bdd16b4 4839 def _post_thread_continuation_entries(self, post_thread_continuation):
4840 contents = post_thread_continuation.get('contents')
4841 if not isinstance(contents, list):
4842 return
4843 for content in contents:
4844 renderer = content.get('backstagePostThreadRenderer')
6b0b0a28 4845 if isinstance(renderer, dict):
4846 yield from self._post_thread_entries(renderer)
8bdd16b4 4847 continue
6b0b0a28 4848 renderer = content.get('videoRenderer')
4849 if isinstance(renderer, dict):
4850 yield self._video_entry(renderer)
07aeced6 4851
39ed931e 4852 r''' # unused
4853 def _rich_grid_entries(self, contents):
4854 for content in contents:
4855 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4856 if video_renderer:
4857 entry = self._video_entry(video_renderer)
4858 if entry:
4859 yield entry
4860 '''
52efa4b3 4861
0a5095fe 4862 def _report_history_entries(self, renderer):
4863 for url in traverse_obj(renderer, (
7a32c70d 4864 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4865 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
0a5095fe 4866 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4867 yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE)
4868
a6213a49 4869 def _extract_entries(self, parent_renderer, continuation_list):
4870 # continuation_list is modified in-place with continuation_list = [continuation_token]
4871 continuation_list[:] = [None]
4872 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
4873 for content in contents:
4874 if not isinstance(content, dict):
4875 continue
16aa9ea4 4876 is_renderer = traverse_obj(
4877 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4878 expected_type=dict)
a6213a49 4879 if not is_renderer:
0a5095fe 4880 if content.get('richItemRenderer'):
4881 for entry in self._rich_entries(content['richItemRenderer']):
a6213a49 4882 yield entry
4883 continuation_list[0] = self._extract_continuation(parent_renderer)
0a5095fe 4884 elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4885 table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4886 yield from self._report_history_entries(table)
4887 continuation_list[0] = self._extract_continuation(table)
a6213a49 4888 continue
0a5095fe 4889
a6213a49 4890 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
4891 for isr_content in isr_contents:
4892 if not isinstance(isr_content, dict):
8bdd16b4 4893 continue
69184e41 4894
a6213a49 4895 known_renderers = {
4896 'playlistVideoListRenderer': self._playlist_entries,
4897 'gridRenderer': self._grid_entries,
a17526e4 4898 'reelShelfRenderer': self._grid_entries,
4899 'shelfRenderer': self._shelf_entries,
16aa9ea4 4900 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
a6213a49 4901 'backstagePostThreadRenderer': self._post_thread_entries,
4902 'videoRenderer': lambda x: [self._video_entry(x)],
a61fd4cf 4903 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4904 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
fcbc9ed7 4905 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)],
4906 'richGridRenderer': lambda x: self._extract_entries(x, continuation_list),
a6213a49 4907 }
4908 for key, renderer in isr_content.items():
4909 if key not in known_renderers:
4910 continue
4911 for entry in known_renderers[key](renderer):
4912 if entry:
4913 yield entry
4914 continuation_list[0] = self._extract_continuation(renderer)
4915 break
70d5c17b 4916
4917 if not continuation_list[0]:
a6213a49 4918 continuation_list[0] = self._extract_continuation(is_renderer)
3462ffa8 4919
a6213a49 4920 if not continuation_list[0]:
4921 continuation_list[0] = self._extract_continuation(parent_renderer)
4922
4923 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4924 continuation_list = [None]
4925 extract_entries = lambda x: self._extract_entries(x, continuation_list)
29f7c58a 4926 tab_content = try_get(tab, lambda x: x['content'], dict)
4927 if not tab_content:
4928 return
3462ffa8 4929 parent_renderer = (
29f7c58a 4930 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4931 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
86e5f3ed 4932 yield from extract_entries(parent_renderer)
3462ffa8 4933 continuation = continuation_list[0]
1ba6fe9d 4934 seen_continuations = set()
8bdd16b4 4935 for page_num in itertools.count(1):
4936 if not continuation:
4937 break
1ba6fe9d 4938 continuation_token = continuation.get('continuation')
4939 if continuation_token is not None and continuation_token in seen_continuations:
4940 self.write_debug('Detected YouTube feed looping - assuming end of feed.')
4941 break
4942 seen_continuations.add(continuation_token)
99e9e001 4943 headers = self.generate_api_headers(
4944 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
79360d99 4945 response = self._extract_response(
86e5f3ed 4946 item_id=f'{item_id} page {page_num}',
fe93e2c4 4947 query=continuation, headers=headers, ytcfg=ytcfg,
79360d99 4948 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
a5c56234
M
4949
4950 if not response:
8bdd16b4 4951 break
ac56cf38 4952 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4953 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4954 visitor_data = self._extract_visitor_data(response) or visitor_data
ebf1b291 4955
a1b535bd 4956 known_renderers = {
e4b98809 4957 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
a1b535bd 4958 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4959 'gridVideoRenderer': (self._grid_entries, 'items'),
d61fc646 4960 'gridChannelRenderer': (self._grid_entries, 'items'),
a1b535bd 4961 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
cd7c66cf 4962 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
9ba5705a 4963 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
0a5095fe 4964 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'),
4965 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'),
1fb53b94 4966 'playlistVideoListContinuation': (self._playlist_entries, None),
4967 'gridContinuation': (self._grid_entries, None),
4968 'itemSectionContinuation': (self._post_thread_continuation_entries, None),
4969 'sectionListContinuation': (extract_entries, None), # for feeds
a1b535bd 4970 }
1fb53b94 4971
4972 continuation_items = traverse_obj(response, (
4973 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4974 'appendContinuationItemsAction', 'continuationItems'
4975 ), 'continuationContents', get_all=False)
4976 continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={})
4977
a1b535bd 4978 video_items_renderer = None
1fb53b94 4979 for key in continuation_item.keys():
a1b535bd 4980 if key not in known_renderers:
8bdd16b4 4981 continue
1fb53b94 4982 func, parent_key = known_renderers[key]
4983 video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items
9ba5705a 4984 continuation_list = [None]
1fb53b94 4985 yield from func(video_items_renderer)
9ba5705a 4986 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
1fb53b94 4987
4988 if not video_items_renderer:
a1b535bd 4989 break
9558dcec 4990
8bdd16b4 4991 @staticmethod
7c219ea6 4992 def _extract_selected_tab(tabs, fatal=True):
86973308
M
4993 for tab_renderer in tabs:
4994 if tab_renderer.get('selected'):
4995 return tab_renderer
4996 if fatal:
4997 raise ExtractorError('Unable to find selected tab')
4998
4999 @staticmethod
5000 def _extract_tab_renderers(response):
5001 return traverse_obj(
5002 response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict)
b82f815f 5003
ac56cf38 5004 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
bd7e919a 5005 metadata = self._extract_metadata_from_tabs(item_id, data)
b60419c5 5006
8bdd16b4 5007 selected_tab = self._extract_selected_tab(tabs)
bd7e919a 5008 metadata['title'] += format_field(selected_tab, 'title', ' - %s')
5009 metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s')
5010
5011 return self.playlist_result(
5012 self._entries(
5013 selected_tab, metadata['id'], ytcfg,
5014 self._extract_account_syncid(ytcfg, data),
5015 self._extract_visitor_data(data, ytcfg)),
5016 **metadata)
39ed931e 5017
bd7e919a 5018 def _extract_metadata_from_tabs(self, item_id, data):
5019 info = {'id': item_id}
5020
5021 metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict)
6141346d 5022 if metadata_renderer:
7666b936 5023 channel_id = traverse_obj(metadata_renderer, ('externalId', {self.ucid_or_none}),
4823ec9f 5024 ('channelUrl', {self.ucid_from_url}))
bd7e919a 5025 info.update({
7666b936 5026 'channel': metadata_renderer.get('title'),
5027 'channel_id': channel_id,
bd7e919a 5028 })
7666b936 5029 if info['channel_id']:
5030 info['id'] = info['channel_id']
bd7e919a 5031 else:
5032 metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict)
b60419c5 5033
301d07fc 5034 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
5035 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
5036 def _get_uncropped(url):
5037 return url_or_none((url or '').split('=')[0] + '=s0')
5038
6141346d 5039 avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar')
301d07fc 5040 if avatar_thumbnails:
5041 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
5042 if uncropped_avatar:
5043 avatar_thumbnails.append({
5044 'url': uncropped_avatar,
5045 'id': 'avatar_uncropped',
5046 'preference': 1
5047 })
5048
5049 channel_banners = self._extract_thumbnails(
bd7e919a 5050 data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
301d07fc 5051 for banner in channel_banners:
5052 banner['preference'] = -10
5053
5054 if channel_banners:
5055 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
5056 if uncropped_banner:
5057 channel_banners.append({
5058 'url': uncropped_banner,
5059 'id': 'banner_uncropped',
5060 'preference': -5
5061 })
5062
bd7e919a 5063 # Deprecated - remove primary_sidebar_renderer when layout discontinued
5064 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
5065 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict)
5066
301d07fc 5067 primary_thumbnails = self._extract_thumbnails(
a17526e4 5068 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
6141346d
M
5069 playlist_thumbnails = self._extract_thumbnails(
5070 playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
5071
bd7e919a 5072 info.update({
5073 'title': (traverse_obj(metadata_renderer, 'title')
5074 or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag'))
5075 or info['id']),
5076 'availability': self._extract_availability(data),
5077 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
5078 'description': try_get(metadata_renderer, lambda x: x.get('description', '')),
5079 'tags': try_get(metadata_renderer or {}, lambda x: x.get('keywords', '').split()),
5080 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners,
5081 })
f0d785d3 5082
7666b936 5083 channel_handle = (
5084 traverse_obj(metadata_renderer, (('vanityChannelUrl', ('ownerUrls', ...)), {self.handle_from_url}), get_all=False)
5085 or traverse_obj(data, ('header', ..., 'channelHandleText', {self.handle_or_none}), get_all=False))
5086
5087 if channel_handle:
5088 info.update({
5089 'uploader_id': channel_handle,
5090 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None),
5091 })
8213ce28 5092
5093 channel_badges = self._extract_badges(traverse_obj(data, ('header', ..., 'badges'), get_all=False))
5094 if self._has_badge(channel_badges, BadgeType.VERIFIED):
5095 info['channel_is_verified'] = True
6141346d
M
5096 # Playlist stats is a text runs array containing [video count, view count, last updated].
5097 # last updated or (view count and last updated) may be missing.
5098 playlist_stats = get_first(
bd7e919a 5099 (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), ))
5100
6141346d
M
5101 last_updated_unix = self._parse_time_text(
5102 self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued
5103 or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text')))
ad54c913 5104 info['modified_date'] = strftime_or_none(last_updated_unix)
6141346d 5105
bd7e919a 5106 info['view_count'] = self._get_count(playlist_stats, 1)
5107 if info['view_count'] is None: # 0 is allowed
5108 info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText')
31e18355 5109 if info['view_count'] is None:
5110 info['view_count'] = self._get_count(data, (
5111 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer',
5112 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText'))
bd7e919a 5113
5114 info['playlist_count'] = self._get_count(playlist_stats, 0)
5115 if info['playlist_count'] is None: # 0 is allowed
5116 info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text'))
5117
7666b936 5118 if not info.get('channel_id'):
6141346d 5119 owner = traverse_obj(playlist_header_renderer, 'ownerText')
bd7e919a 5120 if not owner: # Deprecated
6141346d
M
5121 owner = traverse_obj(
5122 self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'),
5123 ('videoOwner', 'videoOwnerRenderer', 'title'))
5124 owner_text = self._get_text(owner)
5125 browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
bd7e919a 5126 info.update({
7666b936 5127 'channel': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text),
5128 'channel_id': self.ucid_or_none(browse_ep.get('browseId')),
5129 'uploader_id': self.handle_from_url(urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl')))
bd7e919a 5130 })
6141346d 5131
bd7e919a 5132 info.update({
7666b936 5133 'uploader': info['channel'],
5134 'channel_url': format_field(info.get('channel_id'), None, 'https://www.youtube.com/channel/%s', default=None),
5135 'uploader_url': format_field(info.get('uploader_id'), None, 'https://www.youtube.com/%s', default=None),
bd7e919a 5136 })
7666b936 5137
bd7e919a 5138 return info
73c4ac2c 5139
6e634cbe 5140 def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg):
ac56cf38 5141 first_id = last_id = response = None
2be71994 5142 for page_num in itertools.count(1):
cd7c66cf 5143 videos = list(self._playlist_entries(playlist))
5144 if not videos:
5145 return
2be71994 5146 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
5147 if start >= len(videos):
5148 return
24146491 5149 yield from videos[start:]
2be71994 5150 first_id = first_id or videos[0]['id']
5151 last_id = videos[-1]['id']
79360d99 5152 watch_endpoint = try_get(
5153 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
ac56cf38 5154 headers = self.generate_api_headers(
5155 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
5156 visitor_data=self._extract_visitor_data(response, data, ytcfg))
79360d99 5157 query = {
5158 'playlistId': playlist_id,
5159 'videoId': watch_endpoint.get('videoId') or last_id,
5160 'index': watch_endpoint.get('index') or len(videos),
5161 'params': watch_endpoint.get('params') or 'OAE%3D'
5162 }
5163 response = self._extract_response(
5164 item_id='%s page %d' % (playlist_id, page_num),
fe93e2c4 5165 query=query, ep='next', headers=headers, ytcfg=ytcfg,
79360d99 5166 check_get_keys='contents'
5167 )
cd7c66cf 5168 playlist = try_get(
79360d99 5169 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
cd7c66cf 5170
ac56cf38 5171 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
8bdd16b4 5172 title = playlist.get('title') or try_get(
14f25df2 5173 data, lambda x: x['titleText']['simpleText'], str)
8bdd16b4 5174 playlist_id = playlist.get('playlistId') or item_id
cd7c66cf 5175
5176 # Delegating everything except mix playlists to regular tab-based playlist URL
29f7c58a 5177 playlist_url = urljoin(url, try_get(
5178 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
14f25df2 5179 str))
6e634cbe 5180
5181 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
5182 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
5183 is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id)
5184
5185 if playlist_url and playlist_url != url and not is_known_unviewable:
29f7c58a 5186 return self.url_result(
5187 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
5188 video_title=title)
cd7c66cf 5189
8bdd16b4 5190 return self.playlist_result(
6e634cbe 5191 self._extract_inline_playlist(playlist, playlist_id, data, ytcfg),
cd7c66cf 5192 playlist_id=playlist_id, playlist_title=title)
c5e8d7af 5193
47193e02 5194 def _extract_availability(self, data):
5195 """
5196 Gets the availability of a given playlist/tab.
5197 Note: Unless YouTube tells us explicitly, we do not assume it is public
5198 @param data: response
5199 """
6141346d
M
5200 sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
5201 playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {}
5202 player_header_privacy = playlist_header_renderer.get('privacy')
c26f9b99 5203
14a14335 5204 badges = self._extract_badges(traverse_obj(sidebar_renderer, 'badges'))
47193e02 5205
5206 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
6141346d
M
5207 privacy_setting_icon = get_first(
5208 (playlist_header_renderer, sidebar_renderer),
5209 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
5210 lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
5211 expected_type=str)
5212
5213 microformats_is_unlisted = traverse_obj(
5214 data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool)
47193e02 5215
c26f9b99 5216 return (
5217 'public' if (
5218 self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC)
5219 or player_header_privacy == 'PUBLIC'
5220 or privacy_setting_icon == 'PRIVACY_PUBLIC')
5221 else self._availability(
5222 is_private=(
5223 self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE)
5224 or player_header_privacy == 'PRIVATE' if player_header_privacy is not None
5225 else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None),
5226 is_unlisted=(
5227 self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED)
5228 or player_header_privacy == 'UNLISTED' if player_header_privacy is not None
6141346d
M
5229 else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None
5230 else microformats_is_unlisted if microformats_is_unlisted is not None else None),
c26f9b99 5231 needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None,
5232 needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None,
5233 needs_auth=False))
47193e02 5234
5235 @staticmethod
5236 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
5237 sidebar_renderer = try_get(
5238 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
5239 for item in sidebar_renderer:
5240 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
5241 if renderer:
5242 return renderer
5243
ac56cf38 5244 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
358de58c 5245 """
6141346d 5246 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
358de58c 5247 """
6141346d
M
5248 is_playlist = bool(traverse_obj(
5249 data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5250 if not is_playlist:
47193e02 5251 return
11f9be09 5252 headers = self.generate_api_headers(
99e9e001 5253 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
ac56cf38 5254 visitor_data=self._extract_visitor_data(data, ytcfg))
47193e02 5255 query = {
6141346d
M
5256 'params': 'wgYCCAA=',
5257 'browseId': f'VL{item_id}'
47193e02 5258 }
5259 return self._extract_response(
5260 item_id=item_id, headers=headers, query=query,
fe93e2c4 5261 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
6141346d 5262 note='Redownloading playlist API JSON with unavailable videos')
358de58c 5263
2762dbb1 5264 @functools.cached_property
a25bca9f 5265 def skip_webpage(self):
5266 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
5267
ac56cf38 5268 def _extract_webpage(self, url, item_id, fatal=True):
be5c1ae8 5269 webpage, data = None, None
5270 for retry in self.RetryManager(fatal=fatal):
ac56cf38 5271 try:
be5c1ae8 5272 webpage = self._download_webpage(url, item_id, note='Downloading webpage')
ac56cf38 5273 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
5274 except ExtractorError as e:
5275 if isinstance(e.cause, network_exceptions):
3d2623a8 5276 if not isinstance(e.cause, HTTPError) or e.cause.status not in (403, 429):
be5c1ae8 5277 retry.error = e
5278 continue
5279 self._error_or_warning(e, fatal=fatal)
14fdfea9 5280 break
ac56cf38 5281
be5c1ae8 5282 try:
5283 self._extract_and_report_alerts(data)
5284 except ExtractorError as e:
5285 self._error_or_warning(e, fatal=fatal)
5286 break
ac56cf38 5287
be5c1ae8 5288 # Sometimes youtube returns a webpage with incomplete ytInitialData
5289 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5290 if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5291 retry.error = ExtractorError('Incomplete yt initial data received')
5292 continue
ac56cf38 5293
cd7c66cf 5294 return webpage, data
5295
a25bca9f 5296 def _report_playlist_authcheck(self, ytcfg, fatal=True):
5297 """Use if failed to extract ytcfg (and data) from initial webpage"""
5298 if not ytcfg and self.is_authenticated:
5299 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
5300 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
5301 raise ExtractorError(
5302 f'{msg}. If you are not downloading private content, or '
5303 'your cookies are only for the first account and channel,'
5304 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5305 expected=True)
5306 self.report_warning(msg, only_once=True)
5307
ac56cf38 5308 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
5309 data = None
a25bca9f 5310 if not self.skip_webpage:
ac56cf38 5311 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
5312 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
1108613f 5313 # Reject webpage data if redirected to home page without explicitly requesting
86973308 5314 selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {}
1108613f 5315 if (url != 'https://www.youtube.com/feed/recommended'
5316 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5317 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
5318 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5319 if fatal:
5320 raise ExtractorError(msg, expected=True)
5321 self.report_warning(msg, only_once=True)
ac56cf38 5322 if not data:
a25bca9f 5323 self._report_playlist_authcheck(ytcfg, fatal=fatal)
ac56cf38 5324 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
5325 return data, ytcfg
5326
5327 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
5328 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
5329 resolve_response = self._extract_response(
5330 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
5331 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
5332 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5333 for ep_key, ep in endpoints.items():
5334 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
5335 if params:
5336 return self._extract_response(
5337 item_id=item_id, query=params, ep=ep, headers=headers,
5338 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
7c219ea6 5339 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
ac56cf38 5340 err_note = 'Failed to resolve url (does the playlist exist?)'
5341 if fatal:
5342 raise ExtractorError(err_note, expected=True)
5343 self.report_warning(err_note, item_id)
5344
a6213a49 5345 _SEARCH_PARAMS = None
5346
af5c1c55 5347 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
a6213a49 5348 data = {'query': query}
5349 if params is NO_DEFAULT:
5350 params = self._SEARCH_PARAMS
5351 if params:
5352 data['params'] = params
16aa9ea4 5353
5354 content_keys = (
5355 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5356 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5357 # ytmusic search
5358 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5359 ('continuationContents', ),
5360 )
a25bca9f 5361 display_id = f'query "{query}"'
86e5f3ed 5362 check_get_keys = tuple({keys[0] for keys in content_keys})
a25bca9f 5363 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
5364 self._report_playlist_authcheck(ytcfg, fatal=False)
16aa9ea4 5365
a61fd4cf 5366 continuation_list = [None]
a25bca9f 5367 search = None
a6213a49 5368 for page_num in itertools.count(1):
a61fd4cf 5369 data.update(continuation_list[0] or {})
a25bca9f 5370 headers = self.generate_api_headers(
5371 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
a6213a49 5372 search = self._extract_response(
a25bca9f 5373 item_id=f'{display_id} page {page_num}', ep='search', query=data,
5374 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
16aa9ea4 5375 slr_contents = traverse_obj(search, *content_keys)
5376 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
a61fd4cf 5377 if not continuation_list[0]:
a6213a49 5378 break
5379
5380
5381class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
5382 IE_DESC = 'YouTube Tabs'
5383 _VALID_URL = r'''(?x:
5384 https?://
b032ff0f 5385 (?!consent\.)(?:\w+\.)?
a6213a49 5386 (?:
5387 youtube(?:kids)?\.com|
5388 %(invidious)s
5389 )/
5390 (?:
5391 (?P<channel_type>channel|c|user|browse)/|
5392 (?P<not_channel>
5393 feed/|hashtag/|
5394 (?:playlist|watch)\?.*?\blist=
5395 )|
5396 (?!(?:%(reserved_names)s)\b) # Direct URLs
5397 )
5398 (?P<id>[^/?\#&]+)
5399 )''' % {
5400 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
5401 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5402 }
5403 IE_NAME = 'youtube:tab'
5404
5405 _TESTS = [{
5406 'note': 'playlists, multipage',
5407 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5408 'playlist_mincount': 94,
5409 'info_dict': {
5410 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5411 'title': 'Igor Kleiner - Playlists',
a6213a49 5412 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5413 'uploader': 'Igor Kleiner',
7666b936 5414 'uploader_id': '@IgorDataScience',
5415 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
976ae3ea 5416 'channel': 'Igor Kleiner',
5417 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5418 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5419 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5420 'channel_follower_count': int
a6213a49 5421 },
5422 }, {
5423 'note': 'playlists, multipage, different order',
5424 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5425 'playlist_mincount': 94,
5426 'info_dict': {
5427 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
976ae3ea 5428 'title': 'Igor Kleiner - Playlists',
a6213a49 5429 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
976ae3ea 5430 'uploader': 'Igor Kleiner',
7666b936 5431 'uploader_id': '@IgorDataScience',
5432 'uploader_url': 'https://www.youtube.com/@IgorDataScience',
976ae3ea 5433 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5434 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5435 'channel': 'Igor Kleiner',
5436 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
6c73052c 5437 'channel_follower_count': int
a6213a49 5438 },
5439 }, {
5440 'note': 'playlists, series',
5441 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5442 'playlist_mincount': 5,
5443 'info_dict': {
5444 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5445 'title': '3Blue1Brown - Playlists',
5446 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
976ae3ea 5447 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5448 'channel': '3Blue1Brown',
5449 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
7666b936 5450 'uploader_id': '@3blue1brown',
5451 'uploader_url': 'https://www.youtube.com/@3blue1brown',
5452 'uploader': '3Blue1Brown',
976ae3ea 5453 'tags': ['Mathematics'],
14a14335 5454 'channel_follower_count': int,
8213ce28 5455 'channel_is_verified': True,
a6213a49 5456 },
5457 }, {
5458 'note': 'playlists, singlepage',
5459 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5460 'playlist_mincount': 4,
5461 'info_dict': {
5462 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5463 'title': 'ThirstForScience - Playlists',
5464 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5465 'uploader': 'ThirstForScience',
7666b936 5466 'uploader_url': 'https://www.youtube.com/@ThirstForScience',
5467 'uploader_id': '@ThirstForScience',
976ae3ea 5468 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
7666b936 5469 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
976ae3ea 5470 'tags': 'count:13',
5471 'channel': 'ThirstForScience',
6c73052c 5472 'channel_follower_count': int
a6213a49 5473 }
5474 }, {
5475 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5476 'only_matching': True,
5477 }, {
5478 'note': 'basic, single video playlist',
5479 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5480 'info_dict': {
a6213a49 5481 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5482 'title': 'youtube-dl public playlist',
976ae3ea 5483 'description': '',
5484 'tags': [],
5485 'view_count': int,
5486 'modified_date': '20201130',
5487 'channel': 'Sergey M.',
5488 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
976ae3ea 5489 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5490 'availability': 'public',
7666b936 5491 'uploader': 'Sergey M.',
5492 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
5493 'uploader_id': '@sergeym.6173',
a6213a49 5494 },
5495 'playlist_count': 1,
5496 }, {
5497 'note': 'empty playlist',
5498 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5499 'info_dict': {
a6213a49 5500 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5501 'title': 'youtube-dl empty playlist',
976ae3ea 5502 'tags': [],
5503 'channel': 'Sergey M.',
5504 'description': '',
5505 'modified_date': '20160902',
5506 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5507 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
c26f9b99 5508 'availability': 'public',
7666b936 5509 'uploader_url': 'https://www.youtube.com/@sergeym.6173',
5510 'uploader_id': '@sergeym.6173',
5511 'uploader': 'Sergey M.',
a6213a49 5512 },
5513 'playlist_count': 0,
5514 }, {
5515 'note': 'Home tab',
5516 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5517 'info_dict': {
5518 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5519 'title': 'lex will - Home',
5520 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5521 'uploader': 'lex will',
7666b936 5522 'uploader_id': '@lexwill718',
976ae3ea 5523 'channel': 'lex will',
5524 'tags': ['bible', 'history', 'prophesy'],
7666b936 5525 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5526 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5527 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5528 'channel_follower_count': int
a6213a49 5529 },
5530 'playlist_mincount': 2,
5531 }, {
5532 'note': 'Videos tab',
5533 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5534 'info_dict': {
5535 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5536 'title': 'lex will - Videos',
5537 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5538 'uploader': 'lex will',
7666b936 5539 'uploader_id': '@lexwill718',
976ae3ea 5540 'tags': ['bible', 'history', 'prophesy'],
5541 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5542 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
7666b936 5543 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5544 'channel': 'lex will',
6c73052c 5545 'channel_follower_count': int
a6213a49 5546 },
5547 'playlist_mincount': 975,
5548 }, {
5549 'note': 'Videos tab, sorted by popular',
5550 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5551 'info_dict': {
5552 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5553 'title': 'lex will - Videos',
5554 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5555 'uploader': 'lex will',
7666b936 5556 'uploader_id': '@lexwill718',
976ae3ea 5557 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
7666b936 5558 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5559 'channel': 'lex will',
5560 'tags': ['bible', 'history', 'prophesy'],
5561 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
6c73052c 5562 'channel_follower_count': int
a6213a49 5563 },
5564 'playlist_mincount': 199,
5565 }, {
5566 'note': 'Playlists tab',
5567 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5568 'info_dict': {
5569 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5570 'title': 'lex will - Playlists',
5571 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5572 'uploader': 'lex will',
7666b936 5573 'uploader_id': '@lexwill718',
5574 'uploader_url': 'https://www.youtube.com/@lexwill718',
976ae3ea 5575 'channel': 'lex will',
5576 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5577 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5578 'tags': ['bible', 'history', 'prophesy'],
6c73052c 5579 'channel_follower_count': int
a6213a49 5580 },
5581 'playlist_mincount': 17,
5582 }, {
5583 'note': 'Community tab',
5584 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5585 'info_dict': {
5586 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5587 'title': 'lex will - Community',
5588 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
976ae3ea 5589 'channel': 'lex will',
5590 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5591 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5592 'tags': ['bible', 'history', 'prophesy'],
7666b936 5593 'channel_follower_count': int,
5594 'uploader_url': 'https://www.youtube.com/@lexwill718',
5595 'uploader_id': '@lexwill718',
5596 'uploader': 'lex will',
a6213a49 5597 },
5598 'playlist_mincount': 18,
5599 }, {
5600 'note': 'Channels tab',
5601 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5602 'info_dict': {
5603 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5604 'title': 'lex will - Channels',
5605 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
976ae3ea 5606 'channel': 'lex will',
5607 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5608 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5609 'tags': ['bible', 'history', 'prophesy'],
7666b936 5610 'channel_follower_count': int,
5611 'uploader_url': 'https://www.youtube.com/@lexwill718',
5612 'uploader_id': '@lexwill718',
5613 'uploader': 'lex will',
a6213a49 5614 },
5615 'playlist_mincount': 12,
5616 }, {
5617 'note': 'Search tab',
5618 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5619 'playlist_mincount': 40,
5620 'info_dict': {
5621 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5622 'title': '3Blue1Brown - Search - linear algebra',
5623 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
976ae3ea 5624 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
976ae3ea 5625 'tags': ['Mathematics'],
5626 'channel': '3Blue1Brown',
5627 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
7666b936 5628 'channel_follower_count': int,
5629 'uploader_url': 'https://www.youtube.com/@3blue1brown',
5630 'uploader_id': '@3blue1brown',
5631 'uploader': '3Blue1Brown',
8213ce28 5632 'channel_is_verified': True,
a6213a49 5633 },
5634 }, {
5635 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5636 'only_matching': True,
5637 }, {
5638 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5639 'only_matching': True,
5640 }, {
5641 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5642 'only_matching': True,
5643 }, {
5644 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5645 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5646 'info_dict': {
5647 'title': '29C3: Not my department',
5648 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
a6213a49 5649 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
976ae3ea 5650 'tags': [],
976ae3ea 5651 'view_count': int,
5652 'modified_date': '20150605',
5653 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
7666b936 5654 'channel_url': 'https://www.youtube.com/channel/UCEPzS1rYsrkqzSLNp76nrcg',
976ae3ea 5655 'channel': 'Christiaan008',
c26f9b99 5656 'availability': 'public',
7666b936 5657 'uploader_id': '@ChRiStIaAn008',
5658 'uploader': 'Christiaan008',
5659 'uploader_url': 'https://www.youtube.com/@ChRiStIaAn008',
a6213a49 5660 },
5661 'playlist_count': 96,
5662 }, {
5663 'note': 'Large playlist',
5664 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5665 'info_dict': {
5666 'title': 'Uploads from Cauchemar',
5667 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
7666b936 5668 'channel_url': 'https://www.youtube.com/channel/UCBABnxM4Ar9ten8Mdjj1j0Q',
976ae3ea 5669 'tags': [],
5670 'modified_date': r're:\d{8}',
5671 'channel': 'Cauchemar',
976ae3ea 5672 'view_count': int,
5673 'description': '',
5674 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
c26f9b99 5675 'availability': 'public',
7666b936 5676 'uploader_id': '@Cauchemar89',
5677 'uploader': 'Cauchemar',
5678 'uploader_url': 'https://www.youtube.com/@Cauchemar89',
a6213a49 5679 },
5680 'playlist_mincount': 1123,
976ae3ea 5681 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5682 }, {
5683 'note': 'even larger playlist, 8832 videos',
5684 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5685 'only_matching': True,
5686 }, {
5687 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5688 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5689 'info_dict': {
5690 'title': 'Uploads from Interstellar Movie',
5691 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5692 'tags': [],
5693 'view_count': int,
5694 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
7666b936 5695 'channel_url': 'https://www.youtube.com/channel/UCXw-G3eDE9trcvY2sBMM_aA',
976ae3ea 5696 'channel': 'Interstellar Movie',
5697 'description': '',
5698 'modified_date': r're:\d{8}',
c26f9b99 5699 'availability': 'public',
7666b936 5700 'uploader_id': '@InterstellarMovie',
5701 'uploader': 'Interstellar Movie',
5702 'uploader_url': 'https://www.youtube.com/@InterstellarMovie',
a6213a49 5703 },
5704 'playlist_mincount': 21,
5705 }, {
5706 'note': 'Playlist with "show unavailable videos" button',
5707 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5708 'info_dict': {
5709 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5710 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
976ae3ea 5711 'view_count': int,
5712 'channel': 'Phim Siêu Nhân Nhật Bản',
5713 'tags': [],
976ae3ea 5714 'description': '',
5715 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5716 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5717 'modified_date': r're:\d{8}',
c26f9b99 5718 'availability': 'public',
7666b936 5719 'uploader_url': 'https://www.youtube.com/@phimsieunhannhatban',
5720 'uploader_id': '@phimsieunhannhatban',
5721 'uploader': 'Phim Siêu Nhân Nhật Bản',
a6213a49 5722 },
5723 'playlist_mincount': 200,
976ae3ea 5724 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5725 }, {
5726 'note': 'Playlist with unavailable videos in page 7',
5727 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5728 'info_dict': {
5729 'title': 'Uploads from BlankTV',
5730 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5731 'channel': 'BlankTV',
7666b936 5732 'channel_url': 'https://www.youtube.com/channel/UC8l9frL61Yl5KFOl87nIm2w',
976ae3ea 5733 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5734 'view_count': int,
5735 'tags': [],
976ae3ea 5736 'modified_date': r're:\d{8}',
5737 'description': '',
c26f9b99 5738 'availability': 'public',
7666b936 5739 'uploader_id': '@blanktv',
5740 'uploader': 'BlankTV',
5741 'uploader_url': 'https://www.youtube.com/@blanktv',
a6213a49 5742 },
5743 'playlist_mincount': 1000,
976ae3ea 5744 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5745 }, {
5746 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5747 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5748 'info_dict': {
5749 'title': 'Data Analysis with Dr Mike Pound',
5750 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
a6213a49 5751 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
976ae3ea 5752 'tags': [],
5753 'view_count': int,
5754 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
7666b936 5755 'channel_url': 'https://www.youtube.com/channel/UC9-y-6csu5WGm29I7JiwpnA',
976ae3ea 5756 'channel': 'Computerphile',
c26f9b99 5757 'availability': 'public',
6141346d 5758 'modified_date': '20190712',
7666b936 5759 'uploader_id': '@Computerphile',
5760 'uploader': 'Computerphile',
5761 'uploader_url': 'https://www.youtube.com/@Computerphile',
a6213a49 5762 },
5763 'playlist_mincount': 11,
5764 }, {
5765 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5766 'only_matching': True,
5767 }, {
5768 'note': 'Playlist URL that does not actually serve a playlist',
5769 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5770 'info_dict': {
5771 'id': 'FqZTN594JQw',
5772 'ext': 'webm',
5773 'title': "Smiley's People 01 detective, Adventure Series, Action",
a6213a49 5774 'upload_date': '20150526',
5775 'license': 'Standard YouTube License',
5776 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5777 'categories': ['People & Blogs'],
5778 'tags': list,
5779 'view_count': int,
5780 'like_count': int,
a6213a49 5781 },
5782 'params': {
5783 'skip_download': True,
5784 },
5785 'skip': 'This video is not available.',
5786 'add_ie': [YoutubeIE.ie_key()],
5787 }, {
5788 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5789 'only_matching': True,
5790 }, {
5791 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5792 'only_matching': True,
5793 }, {
5794 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5795 'info_dict': {
14a14335 5796 'id': 'hGkQjiJLjWQ', # This will keep changing
a6213a49 5797 'ext': 'mp4',
976ae3ea 5798 'title': str,
a6213a49 5799 'upload_date': r're:\d{8}',
976ae3ea 5800 'description': str,
a6213a49 5801 'categories': ['News & Politics'],
5802 'tags': list,
5803 'like_count': int,
86973308 5804 'release_timestamp': int,
976ae3ea 5805 'channel': 'Sky News',
5806 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5807 'age_limit': 0,
5808 'view_count': int,
86973308 5809 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
976ae3ea 5810 'playable_in_embed': True,
86973308 5811 'release_date': r're:\d+',
976ae3ea 5812 'availability': 'public',
5813 'live_status': 'is_live',
5814 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
86973308
M
5815 'channel_follower_count': int,
5816 'concurrent_view_count': int,
7666b936 5817 'uploader_url': 'https://www.youtube.com/@SkyNews',
5818 'uploader_id': '@SkyNews',
5819 'uploader': 'Sky News',
8213ce28 5820 'channel_is_verified': True,
a6213a49 5821 },
5822 'params': {
5823 'skip_download': True,
5824 },
976ae3ea 5825 'expected_warnings': ['Ignoring subtitle tracks found in '],
a6213a49 5826 }, {
5827 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5828 'info_dict': {
5829 'id': 'a48o2S1cPoo',
5830 'ext': 'mp4',
5831 'title': 'The Young Turks - Live Main Show',
a6213a49 5832 'upload_date': '20150715',
5833 'license': 'Standard YouTube License',
5834 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5835 'categories': ['News & Politics'],
5836 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5837 'like_count': int,
a6213a49 5838 },
5839 'params': {
5840 'skip_download': True,
5841 },
5842 'only_matching': True,
5843 }, {
5844 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5845 'only_matching': True,
5846 }, {
5847 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5848 'only_matching': True,
5849 }, {
5850 'note': 'A channel that is not live. Should raise error',
5851 'url': 'https://www.youtube.com/user/numberphile/live',
5852 'only_matching': True,
5853 }, {
5854 'url': 'https://www.youtube.com/feed/trending',
5855 'only_matching': True,
5856 }, {
5857 'url': 'https://www.youtube.com/feed/library',
5858 'only_matching': True,
5859 }, {
5860 'url': 'https://www.youtube.com/feed/history',
5861 'only_matching': True,
5862 }, {
5863 'url': 'https://www.youtube.com/feed/subscriptions',
5864 'only_matching': True,
5865 }, {
5866 'url': 'https://www.youtube.com/feed/watch_later',
5867 'only_matching': True,
5868 }, {
5869 'note': 'Recommended - redirects to home page.',
5870 'url': 'https://www.youtube.com/feed/recommended',
5871 'only_matching': True,
5872 }, {
5873 'note': 'inline playlist with not always working continuations',
5874 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5875 'only_matching': True,
5876 }, {
5877 'url': 'https://www.youtube.com/course',
5878 'only_matching': True,
5879 }, {
5880 'url': 'https://www.youtube.com/zsecurity',
5881 'only_matching': True,
5882 }, {
5883 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5884 'only_matching': True,
5885 }, {
5886 'url': 'https://www.youtube.com/TheYoungTurks/live',
5887 'only_matching': True,
5888 }, {
5889 'url': 'https://www.youtube.com/hashtag/cctv9',
5890 'info_dict': {
5891 'id': 'cctv9',
5892 'title': '#cctv9',
976ae3ea 5893 'tags': [],
a6213a49 5894 },
4dc23a80 5895 'playlist_mincount': 300, # not consistent but should be over 300
a6213a49 5896 }, {
5897 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5898 'only_matching': True,
5899 }, {
5900 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5901 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5902 'only_matching': True
5903 }, {
5904 'note': '/browse/ should redirect to /channel/',
5905 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5906 'only_matching': True
5907 }, {
5908 'note': 'VLPL, should redirect to playlist?list=PL...',
5909 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5910 'info_dict': {
5911 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
a6213a49 5912 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
12a1b225 5913 'title': 'NCS : All Releases 💿',
7666b936 5914 'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
976ae3ea 5915 'modified_date': r're:\d{8}',
5916 'view_count': int,
5917 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5918 'tags': [],
5919 'channel': 'NoCopyrightSounds',
c26f9b99 5920 'availability': 'public',
7666b936 5921 'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds',
5922 'uploader': 'NoCopyrightSounds',
5923 'uploader_id': '@NoCopyrightSounds',
a6213a49 5924 },
5925 'playlist_mincount': 166,
7666b936 5926 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden', 'YouTube Music is not directly supported'],
a6213a49 5927 }, {
7666b936 5928 # TODO: fix 'unviewable' issue with this playlist when reloading with unavailable videos
a6213a49 5929 'note': 'Topic, should redirect to playlist?list=UU...',
5930 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5931 'info_dict': {
5932 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 5933 'title': 'Uploads from Royalty Free Music - Topic',
976ae3ea 5934 'tags': [],
5935 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5936 'channel': 'Royalty Free Music - Topic',
5937 'view_count': int,
5938 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
976ae3ea 5939 'modified_date': r're:\d{8}',
976ae3ea 5940 'description': '',
c26f9b99 5941 'availability': 'public',
7666b936 5942 'uploader': 'Royalty Free Music - Topic',
a6213a49 5943 },
a6213a49 5944 'playlist_mincount': 101,
7666b936 5945 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 5946 }, {
86973308
M
5947 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5948 # Treat as a general feed
a6213a49 5949 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5950 'info_dict': {
5951 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5952 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
976ae3ea 5953 'tags': [],
a6213a49 5954 },
a6213a49 5955 'playlist_mincount': 9,
5956 }, {
5957 'note': 'Youtube music Album',
5958 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5959 'info_dict': {
5960 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5961 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
976ae3ea 5962 'tags': [],
5963 'view_count': int,
5964 'description': '',
5965 'availability': 'unlisted',
5966 'modified_date': r're:\d{8}',
a6213a49 5967 },
5968 'playlist_count': 50,
7666b936 5969 'expected_warnings': ['YouTube Music is not directly supported'],
a6213a49 5970 }, {
5971 'note': 'unlisted single video playlist',
5972 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5973 'info_dict': {
a6213a49 5974 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5975 'title': 'yt-dlp unlisted playlist test',
976ae3ea 5976 'availability': 'unlisted',
5977 'tags': [],
12a1b225 5978 'modified_date': '20220418',
976ae3ea 5979 'channel': 'colethedj',
5980 'view_count': int,
5981 'description': '',
976ae3ea 5982 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5983 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
7666b936 5984 'uploader_url': 'https://www.youtube.com/@colethedj1894',
5985 'uploader_id': '@colethedj1894',
5986 'uploader': 'colethedj',
a6213a49 5987 },
93e12ed7 5988 'playlist': [{
5989 'info_dict': {
5990 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
5991 'id': 'BaW_jenozKc',
5992 '_type': 'url',
5993 'ie_key': 'Youtube',
5994 'duration': 10,
5995 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
5996 'channel_url': 'https://www.youtube.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
5997 'view_count': int,
5998 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc',
5999 'channel': 'Philipp Hagemeister',
6000 'uploader_id': '@PhilippHagemeister',
6001 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister',
6002 'uploader': 'Philipp Hagemeister',
6003 }
6004 }],
a6213a49 6005 'playlist_count': 1,
93e12ed7 6006 'params': {'extract_flat': True},
a6213a49 6007 }, {
6008 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
6009 'url': 'https://www.youtube.com/feed/recommended',
6010 'info_dict': {
6011 'id': 'recommended',
6012 'title': 'recommended',
6c73052c 6013 'tags': [],
a6213a49 6014 },
6015 'playlist_mincount': 50,
6016 'params': {
6017 'skip_download': True,
6018 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6019 },
6020 }, {
6021 'note': 'API Fallback: /videos tab, sorted by oldest first',
6022 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
6023 'info_dict': {
6024 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
6025 'title': 'Cody\'sLab - Videos',
6026 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
976ae3ea 6027 'channel': 'Cody\'sLab',
6028 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
6029 'tags': [],
6030 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
6c73052c 6031 'channel_follower_count': int
a6213a49 6032 },
6033 'playlist_mincount': 650,
6034 'params': {
6035 'skip_download': True,
6036 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6037 },
86973308 6038 'skip': 'Query for sorting no longer works',
a6213a49 6039 }, {
6040 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
6041 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
6042 'info_dict': {
6043 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
a6213a49 6044 'title': 'Uploads from Royalty Free Music - Topic',
976ae3ea 6045 'modified_date': r're:\d{8}',
6046 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
6047 'description': '',
6048 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
6049 'tags': [],
6050 'channel': 'Royalty Free Music - Topic',
6051 'view_count': int,
c26f9b99 6052 'availability': 'public',
7666b936 6053 'uploader': 'Royalty Free Music - Topic',
a6213a49 6054 },
a6213a49 6055 'playlist_mincount': 101,
6056 'params': {
6057 'skip_download': True,
6058 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
6059 },
7666b936 6060 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'],
7c219ea6 6061 }, {
6062 'note': 'non-standard redirect to regional channel',
6063 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
6064 'only_matching': True
61d3665d 6065 }, {
6066 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
6067 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
6068 'info_dict': {
6069 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
6070 'modified_date': '20220407',
6071 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
6072 'tags': [],
61d3665d 6073 'availability': 'unlisted',
6074 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
6075 'channel': 'pukkandan',
6076 'description': 'Test for collaborative playlist',
6077 'title': 'yt-dlp test - collaborative playlist',
12a1b225 6078 'view_count': int,
7666b936 6079 'uploader_url': 'https://www.youtube.com/@pukkandan',
6080 'uploader_id': '@pukkandan',
6081 'uploader': 'pukkandan',
61d3665d 6082 },
6083 'playlist_mincount': 2
c26f9b99 6084 }, {
6085 'note': 'translated tab name',
6086 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
6087 'info_dict': {
6088 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6089 'tags': [],
c26f9b99 6090 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
4dc23a80 6091 'description': 'test description',
c26f9b99 6092 'title': 'cole-dlp-test-acc - 再生リスト',
c26f9b99 6093 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6094 'channel': 'cole-dlp-test-acc',
7666b936 6095 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6096 'uploader_id': '@coletdjnz',
6097 'uploader': 'cole-dlp-test-acc',
c26f9b99 6098 },
6099 'playlist_mincount': 1,
6100 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
6101 'expected_warnings': ['Preferring "ja"'],
6102 }, {
6103 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
6104 'note': 'preferred lang set with playlist with translated video titles',
6105 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
6106 'info_dict': {
6107 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
6108 'tags': [],
6109 'view_count': int,
6110 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
c26f9b99 6111 'channel': 'cole-dlp-test-acc',
6112 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6113 'description': 'test',
c26f9b99 6114 'title': 'dlp test playlist',
6115 'availability': 'public',
7666b936 6116 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6117 'uploader_id': '@coletdjnz',
6118 'uploader': 'cole-dlp-test-acc',
c26f9b99 6119 },
6120 'playlist_mincount': 1,
6121 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}},
6122 'expected_warnings': ['Preferring "ja"'],
80eb0bd9 6123 }, {
6124 # shorts audio pivot for 2GtVksBMYFM.
6125 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
6126 'info_dict': {
6127 'id': 'sfv_audio_pivot',
6128 'title': 'sfv_audio_pivot',
6129 'tags': [],
6130 },
6131 'playlist_mincount': 50,
6132
86973308
M
6133 }, {
6134 # Channel with a real live tab (not to be mistaken with streams tab)
6135 # Do not treat like it should redirect to live stream
6136 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
6137 'info_dict': {
6138 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
6139 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
6140 'tags': [],
6141 },
6142 'playlist_mincount': 20,
6143 }, {
6144 # Tab name is not the same as tab id
6145 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
6146 'info_dict': {
6147 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6148 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
6149 'tags': [],
6150 },
6151 'playlist_mincount': 8,
6152 }, {
6153 # Home tab id is literally home. Not to get mistaken with featured
6154 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
6155 'info_dict': {
6156 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6157 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
6158 'tags': [],
6159 },
6160 'playlist_mincount': 8,
6161 }, {
6162 # Should get three playlists for videos, shorts and streams tabs
6163 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
6164 'info_dict': {
6165 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
bd7e919a 6166 'title': 'Polka Ch. 尾丸ポルカ',
6167 'channel_follower_count': int,
6168 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
6169 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
7666b936 6170 'description': 'md5:e56b74b5bb7e9c701522162e9abfb822',
bd7e919a 6171 'channel': 'Polka Ch. 尾丸ポルカ',
6172 'tags': 'count:35',
7666b936 6173 'uploader_url': 'https://www.youtube.com/@OmaruPolka',
6174 'uploader': 'Polka Ch. 尾丸ポルカ',
6175 'uploader_id': '@OmaruPolka',
86973308
M
6176 },
6177 'playlist_count': 3,
6178 }, {
6179 # Shorts tab with channel with handle
7666b936 6180 # TODO: fix channel description
86973308
M
6181 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
6182 'info_dict': {
6183 'id': 'UC0intLFzLaudFG-xAvUEO-A',
6184 'title': 'Not Just Bikes - Shorts',
6185 'tags': 'count:12',
86973308 6186 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
7666b936 6187 'description': 'md5:26bc55af26855a608a5cf89dfa595c8d',
86973308 6188 'channel_follower_count': int,
86973308 6189 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
86973308 6190 'channel': 'Not Just Bikes',
7666b936 6191 'uploader_url': 'https://www.youtube.com/@NotJustBikes',
6192 'uploader': 'Not Just Bikes',
6193 'uploader_id': '@NotJustBikes',
86973308
M
6194 },
6195 'playlist_mincount': 10,
6196 }, {
6197 # Streams tab
6198 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
6199 'info_dict': {
6200 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6201 'title': '中村悠一 - Live',
6202 'tags': 'count:7',
6203 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
6204 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
86973308 6205 'channel': '中村悠一',
86973308 6206 'channel_follower_count': int,
86973308 6207 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
7666b936 6208 'uploader_url': 'https://www.youtube.com/@Yuichi-Nakamura',
6209 'uploader_id': '@Yuichi-Nakamura',
6210 'uploader': '中村悠一',
86973308
M
6211 },
6212 'playlist_mincount': 60,
6213 }, {
6214 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
6215 # See test_youtube_lists
6216 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
6217 'only_matching': True,
6218 }, {
6219 # No uploads and no UCID given. Should fail with no uploads error
6220 # See test_youtube_lists
6221 'url': 'https://www.youtube.com/news',
6222 'only_matching': True
6223 }, {
6224 # No videos tab but has a shorts tab
6225 'url': 'https://www.youtube.com/c/TKFShorts',
6226 'info_dict': {
6227 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6228 'title': 'Shorts Break - Shorts',
7666b936 6229 'tags': 'count:48',
86973308
M
6230 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
6231 'channel': 'Shorts Break',
7666b936 6232 'description': 'md5:6de33c5e7ba686e5f3efd4e19c7ef499',
86973308 6233 'channel_follower_count': int,
86973308 6234 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
7666b936 6235 'uploader_url': 'https://www.youtube.com/@ShortsBreak_Official',
6236 'uploader': 'Shorts Break',
6237 'uploader_id': '@ShortsBreak_Official',
86973308
M
6238 },
6239 'playlist_mincount': 30,
6240 }, {
6241 # Trending Now Tab. tab id is empty
6242 'url': 'https://www.youtube.com/feed/trending',
6243 'info_dict': {
6244 'id': 'trending',
6245 'title': 'trending - Now',
6246 'tags': [],
6247 },
6248 'playlist_mincount': 30,
6249 }, {
6250 # Trending Gaming Tab. tab id is empty
6251 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
6252 'info_dict': {
6253 'id': 'trending',
6254 'title': 'trending - Gaming',
6255 'tags': [],
6256 },
6257 'playlist_mincount': 30,
4dc23a80
M
6258 }, {
6259 # Shorts url result in shorts tab
7666b936 6260 # TODO: Fix channel id extraction
4dc23a80
M
6261 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6262 'info_dict': {
6263 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6264 'title': 'cole-dlp-test-acc - Shorts',
4dc23a80 6265 'channel': 'cole-dlp-test-acc',
4dc23a80
M
6266 'description': 'test description',
6267 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6268 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6269 'tags': [],
7666b936 6270 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6271 'uploader_id': '@coletdjnz',
4dc23a80 6272 'uploader': 'cole-dlp-test-acc',
4dc23a80
M
6273 },
6274 'playlist': [{
6275 'info_dict': {
7666b936 6276 # Channel data is not currently available for short renderers (as of 2023-03-01)
4dc23a80
M
6277 '_type': 'url',
6278 'ie_key': 'Youtube',
6279 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6280 'id': 'sSM9J5YH_60',
4dc23a80 6281 'title': 'SHORT short',
4dc23a80
M
6282 'view_count': int,
6283 'thumbnails': list,
6284 }
6285 }],
6286 'params': {'extract_flat': True},
6287 }, {
6288 # Live video status should be extracted
6289 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6290 'info_dict': {
6291 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6292 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6293 'tags': []
6294 },
6295 'playlist': [{
6296 'info_dict': {
6297 '_type': 'url',
6298 'ie_key': 'Youtube',
6299 'url': 'startswith:https://www.youtube.com/watch?v=',
6300 'id': str,
6301 'title': str,
6302 'live_status': 'is_live',
6303 'channel_id': str,
6304 'channel_url': str,
6305 'concurrent_view_count': int,
6306 'channel': str,
93e12ed7 6307 'uploader': str,
6308 'uploader_url': str,
14a14335 6309 'uploader_id': str,
8213ce28 6310 'channel_is_verified': bool, # this will keep changing
4dc23a80
M
6311 }
6312 }],
c7335551 6313 'params': {'extract_flat': True, 'playlist_items': '1'},
4dc23a80 6314 'playlist_mincount': 1
c7335551
M
6315 }, {
6316 # Channel renderer metadata. Contains number of videos on the channel
6317 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6318 'info_dict': {
6319 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6320 'title': 'cole-dlp-test-acc - Channels',
c7335551
M
6321 'channel': 'cole-dlp-test-acc',
6322 'description': 'test description',
6323 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6324 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6325 'tags': [],
7666b936 6326 'uploader_url': 'https://www.youtube.com/@coletdjnz',
6327 'uploader_id': '@coletdjnz',
c7335551 6328 'uploader': 'cole-dlp-test-acc',
c7335551
M
6329 },
6330 'playlist': [{
6331 'info_dict': {
6332 '_type': 'url',
6333 'ie_key': 'YoutubeTab',
6334 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6335 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6336 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6337 'title': 'PewDiePie',
6338 'channel': 'PewDiePie',
6339 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6340 'thumbnails': list,
6341 'channel_follower_count': int,
7666b936 6342 'playlist_count': int,
6343 'uploader': 'PewDiePie',
6344 'uploader_url': 'https://www.youtube.com/@PewDiePie',
6345 'uploader_id': '@PewDiePie',
8213ce28 6346 'channel_is_verified': True,
c7335551
M
6347 }
6348 }],
6349 'params': {'extract_flat': True},
31e18355 6350 }, {
6351 'url': 'https://www.youtube.com/@3blue1brown/about',
6352 'info_dict': {
6353 'id': 'UCYO_jab_esuFRV4b17AJtAw',
6354 'tags': ['Mathematics'],
6355 'title': '3Blue1Brown - About',
31e18355 6356 'channel_follower_count': int,
6357 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
31e18355 6358 'channel': '3Blue1Brown',
31e18355 6359 'view_count': int,
6360 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6361 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
7666b936 6362 'uploader_url': 'https://www.youtube.com/@3blue1brown',
6363 'uploader_id': '@3blue1brown',
6364 'uploader': '3Blue1Brown',
8213ce28 6365 'channel_is_verified': True,
31e18355 6366 },
6367 'playlist_count': 0,
447afb9e 6368 }, {
6369 # Podcasts tab, with rich entry playlistRenderers
6370 'url': 'https://www.youtube.com/@99percentinvisiblepodcast/podcasts',
6371 'info_dict': {
6372 'id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6373 'channel_id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6374 'uploader_url': 'https://www.youtube.com/@99percentinvisiblepodcast',
6375 'description': 'md5:3a0ed38f1ad42a68ef0428c04a15695c',
6376 'title': '99 Percent Invisible - Podcasts',
6377 'uploader': '99 Percent Invisible',
6378 'channel_follower_count': int,
6379 'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw',
6380 'tags': [],
6381 'channel': '99 Percent Invisible',
6382 'uploader_id': '@99percentinvisiblepodcast',
6383 },
6384 'playlist_count': 1,
6385 }, {
6386 # Releases tab, with rich entry playlistRenderers (same as Podcasts tab)
6387 'url': 'https://www.youtube.com/@AHimitsu/releases',
6388 'info_dict': {
6389 'id': 'UCgFwu-j5-xNJml2FtTrrB3A',
6390 'channel': 'A Himitsu',
6391 'uploader_url': 'https://www.youtube.com/@AHimitsu',
6392 'title': 'A Himitsu - Releases',
6393 'uploader_id': '@AHimitsu',
6394 'uploader': 'A Himitsu',
6395 'channel_id': 'UCgFwu-j5-xNJml2FtTrrB3A',
6396 'tags': 'count:16',
6397 'description': 'I make music',
6398 'channel_url': 'https://www.youtube.com/channel/UCgFwu-j5-xNJml2FtTrrB3A',
6399 'channel_follower_count': int,
8213ce28 6400 'channel_is_verified': True,
447afb9e 6401 },
6402 'playlist_mincount': 10,
fcbc9ed7 6403 }, {
6404 # Playlist with only shorts, shown as reel renderers
6405 # FIXME: future: YouTube currently doesn't give continuation for this,
6406 # may do in future.
6407 'url': 'https://www.youtube.com/playlist?list=UUxqPAgubo4coVn9Lx1FuKcg',
6408 'info_dict': {
6409 'id': 'UUxqPAgubo4coVn9Lx1FuKcg',
6410 'channel_url': 'https://www.youtube.com/channel/UCxqPAgubo4coVn9Lx1FuKcg',
6411 'view_count': int,
6412 'uploader_id': '@BangyShorts',
6413 'description': '',
6414 'uploader_url': 'https://www.youtube.com/@BangyShorts',
6415 'channel_id': 'UCxqPAgubo4coVn9Lx1FuKcg',
6416 'channel': 'Bangy Shorts',
6417 'uploader': 'Bangy Shorts',
6418 'tags': [],
6419 'availability': 'public',
6420 'modified_date': '20230626',
6421 'title': 'Uploads from Bangy Shorts',
6422 },
6423 'playlist_mincount': 100,
6424 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
a6213a49 6425 }]
6426
6427 @classmethod
6428 def suitable(cls, url):
86e5f3ed 6429 return False if YoutubeIE.suitable(url) else super().suitable(url)
9297939e 6430
86973308
M
6431 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6432
6433 def _get_url_mobj(self, url):
6434 mobj = self._URL_RE.match(url).groupdict()
6435 mobj.update((k, '') for k, v in mobj.items() if v is None)
6436 return mobj
6437
6438 def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'):
6439 tab_name = (tab.get('title') or '').lower()
6440 tab_url = urljoin(base_url, traverse_obj(
6441 tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6442
bd7e919a 6443 tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:]
6444 or traverse_obj(tab, 'tabIdentifier', expected_type=str))
86973308 6445 if tab_id:
bd7e919a 6446 return {
6447 'TAB_ID_SPONSORSHIPS': 'membership',
6448 }.get(tab_id, tab_id), tab_name
86973308
M
6449
6450 # Fallback to tab name if we cannot get the tab id.
6451 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6452 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
bd7e919a 6453 if tab_name:
6454 self.write_debug(f'Falling back to selected tab name: {tab_name}')
86973308
M
6455 return {
6456 'home': 'featured',
6457 'live': 'streams',
6458 }.get(tab_name, tab_name), tab_name
6459
6460 def _has_tab(self, tabs, tab_id):
6461 return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs)
fe03a6cd 6462
182bda88 6463 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6464 def _real_extract(self, url, smuggled_data):
cd7c66cf 6465 item_id = self._match_id(url)
14f25df2 6466 url = urllib.parse.urlunparse(
6467 urllib.parse.urlparse(url)._replace(netloc='www.youtube.com'))
a06916d9 6468 compat_opts = self.get_param('compat_opts', [])
cd7c66cf 6469
86973308
M
6470 mobj = self._get_url_mobj(url)
6471 pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel']
bd7e919a 6472 if is_channel and smuggled_data.get('is_music_url'):
6473 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6474 return self.url_result(
6475 f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:])
6476 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6477 mdata = self._extract_tab_endpoint(
6478 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
6479 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6480 get_all=False, expected_type=str)
6481 if not murl:
6482 raise ExtractorError('Failed to resolve album to playlist')
6483 return self.url_result(murl, YoutubeTabIE)
6484 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6485 return self.url_result(
6486 f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id)
6487
6488 original_tab_id, display_id = tab[1:], f'{item_id}{tab}'
fe03a6cd 6489 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6490 url = f'{pre}/videos{post}'
5b28cef7 6491 if smuggled_data.get('is_music_url'):
6492 self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}')
cd7c66cf 6493
6494 # Handle both video/playlist URLs
201c1459 6495 qs = parse_qs(url)
bd7e919a 6496 video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')]
fe03a6cd 6497 if not video_id and mobj['not_channel'].startswith('watch'):
cd7c66cf 6498 if not playlist_id:
fe03a6cd 6499 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
bd7e919a 6500 raise ExtractorError('A video URL was given without video ID', expected=True)
fe03a6cd 6501 # Common mistake: https://www.youtube.com/watch?list=playlist_id
37e57a9f 6502 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
bd7e919a 6503 return self.url_result(
6504 f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id)
cd7c66cf 6505
86973308
M
6506 if not self._yes_playlist(playlist_id, video_id):
6507 return self.url_result(
6508 f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6509
bd7e919a 6510 data, ytcfg = self._extract_data(url, display_id)
14fdfea9 6511
7c219ea6 6512 # YouTube may provide a non-standard redirect to the regional channel
6513 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
86973308 6514 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
7c219ea6 6515 redirect_url = traverse_obj(
6516 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
6517 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
bd7e919a 6518 redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post))
86973308
M
6519 self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6520 return self.url_result(redirect_url, YoutubeTabIE)
7c219ea6 6521
bd7e919a 6522 tabs, extra_tabs = self._extract_tab_renderers(data), []
86973308 6523 if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts:
18db7548 6524 selected_tab = self._extract_selected_tab(tabs)
86973308
M
6525 selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated
6526 self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6527
6528 if not original_tab_id and selected_tab_name:
bd7e919a 6529 self.to_screen('Downloading all uploads of the channel. '
86973308
M
6530 'To download only the videos in a specific tab, pass the tab\'s URL')
6531 if self._has_tab(tabs, 'streams'):
bd7e919a 6532 extra_tabs.append(''.join((pre, '/streams', post)))
86973308 6533 if self._has_tab(tabs, 'shorts'):
bd7e919a 6534 extra_tabs.append(''.join((pre, '/shorts', post)))
86973308
M
6535 # XXX: Members-only tab should also be extracted
6536
bd7e919a 6537 if not extra_tabs and selected_tab_id != 'videos':
86973308
M
6538 # Channel does not have streams, shorts or videos tabs
6539 if item_id[:2] != 'UC':
6540 raise ExtractorError('This channel has no uploads', expected=True)
6541
6542 # Topic channels don't have /videos. Use the equivalent playlist instead
6543 pl_id = f'UU{item_id[2:]}'
6544 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
6545 try:
6546 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
6547 except ExtractorError:
6548 raise ExtractorError('This channel has no uploads', expected=True)
64f36541 6549 else:
86973308
M
6550 item_id, url = pl_id, pl_url
6551 self.to_screen(
6552 f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6553
bd7e919a 6554 elif extra_tabs and selected_tab_id != 'videos':
86973308 6555 # When there are shorts/live tabs but not videos tab
bd7e919a 6556 url, data = f'{pre}{post}', None
86973308
M
6557
6558 elif (original_tab_id or 'videos') != selected_tab_id:
6559 if original_tab_id == 'live':
6560 # Live tab should have redirected to the video
6561 # Except in the case the channel has an actual live tab
6562 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
bd7e919a 6563 raise UserNotLive(video_id=item_id)
86973308
M
6564 elif selected_tab_name:
6565 raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True)
6566
6567 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6568 url = f'{pre}{post}'
18db7548 6569
358de58c 6570 # YouTube sometimes provides a button to reload playlist with unavailable videos.
53ed7066 6571 if 'no-youtube-unavailable-videos' not in compat_opts:
bd7e919a 6572 data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data
c0ac49bc 6573 self._extract_and_report_alerts(data, only_once=True)
86973308 6574
bd7e919a 6575 tabs, entries = self._extract_tab_renderers(data), []
8bdd16b4 6576 if tabs:
bd7e919a 6577 entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)]
6578 entries[0].update({
86973308
M
6579 'extractor_key': YoutubeTabIE.ie_key(),
6580 'extractor': YoutubeTabIE.IE_NAME,
6581 'webpage_url': url,
6582 })
bd7e919a 6583 if self.get_param('playlist_items') == '0':
6584 entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs)
6585 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6586 entries.extend(map(self._real_extract, extra_tabs))
6587
6588 if len(entries) == 1:
6589 return entries[0]
6590 elif entries:
6591 metadata = self._extract_metadata_from_tabs(item_id, data)
6592 uploads_url = 'the Uploads (UU) playlist URL'
6593 if try_get(metadata, lambda x: x['channel_id'].startswith('UC')):
6594 uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6595 self.to_screen(
6596 'Downloading as multiple playlists, separated by tabs. '
6597 f'To download as a single playlist instead, pass {uploads_url}')
6598 return self.playlist_result(entries, item_id, **metadata)
6599
6600 # Inline playlist
37e57a9f 6601 playlist = traverse_obj(
6602 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
8bdd16b4 6603 if playlist:
ac56cf38 6604 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
cd7c66cf 6605
37e57a9f 6606 video_id = traverse_obj(
6607 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
8bdd16b4 6608 if video_id:
bd7e919a 6609 if tab != '/live': # live tab is expected to redirect to video
37e57a9f 6610 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
86973308 6611 return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id)
cd7c66cf 6612
8bdd16b4 6613 raise ExtractorError('Unable to recognize tab page')
c5e8d7af 6614
c5e8d7af 6615
8bdd16b4 6616class YoutubePlaylistIE(InfoExtractor):
96565c7e 6617 IE_DESC = 'YouTube playlists'
8bdd16b4 6618 _VALID_URL = r'''(?x)(?:
6619 (?:https?://)?
6620 (?:\w+\.)?
6621 (?:
6622 (?:
6623 youtube(?:kids)?\.com|
d9190e44 6624 %(invidious)s
8bdd16b4 6625 )
6626 /.*?\?.*?\blist=
6627 )?
6628 (?P<id>%(playlist_id)s)
d9190e44
RH
6629 )''' % {
6630 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
6631 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
6632 }
8bdd16b4 6633 IE_NAME = 'youtube:playlist'
cdc628a4 6634 _TESTS = [{
8bdd16b4 6635 'note': 'issue #673',
6636 'url': 'PLBB231211A4F62143',
cdc628a4 6637 'info_dict': {
8bdd16b4 6638 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6639 'id': 'PLBB231211A4F62143',
976ae3ea 6640 'uploader': 'Wickman',
7666b936 6641 'uploader_id': '@WickmanVT',
11f9be09 6642 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
976ae3ea 6643 'view_count': int,
7666b936 6644 'uploader_url': 'https://www.youtube.com/@WickmanVT',
976ae3ea 6645 'modified_date': r're:\d{8}',
6646 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6647 'channel': 'Wickman',
6648 'tags': [],
7666b936 6649 'channel_url': 'https://www.youtube.com/channel/UCKSpbfbl5kRQpTdL7kMc-1Q',
86973308 6650 'availability': 'public',
8bdd16b4 6651 },
6652 'playlist_mincount': 29,
6653 }, {
6654 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6655 'info_dict': {
6656 'title': 'YDL_safe_search',
6657 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6658 },
6659 'playlist_count': 2,
6660 'skip': 'This playlist is private',
9558dcec 6661 }, {
8bdd16b4 6662 'note': 'embedded',
6663 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6664 'playlist_count': 4,
9558dcec 6665 'info_dict': {
8bdd16b4 6666 'title': 'JODA15',
6667 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6668 'uploader': 'milan',
7666b936 6669 'uploader_id': '@milan5503',
976ae3ea 6670 'description': '',
6671 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6672 'tags': [],
6673 'modified_date': '20140919',
6674 'view_count': int,
6675 'channel': 'milan',
6676 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
7666b936 6677 'uploader_url': 'https://www.youtube.com/@milan5503',
c26f9b99 6678 'availability': 'public',
976ae3ea 6679 },
86973308 6680 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden'],
cdc628a4 6681 }, {
8bdd16b4 6682 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
12a1b225 6683 'playlist_mincount': 455,
8bdd16b4 6684 'info_dict': {
6685 'title': '2018 Chinese New Singles (11/6 updated)',
6686 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6687 'uploader': 'LBK',
7666b936 6688 'uploader_id': '@music_king',
11f9be09 6689 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
976ae3ea 6690 'channel': 'LBK',
6691 'view_count': int,
7666b936 6692 'channel_url': 'https://www.youtube.com/channel/UC21nz3_MesPLqtDqwdvnoxA',
976ae3ea 6693 'tags': [],
7666b936 6694 'uploader_url': 'https://www.youtube.com/@music_king',
976ae3ea 6695 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6696 'modified_date': r're:\d{8}',
c26f9b99 6697 'availability': 'public',
976ae3ea 6698 },
6699 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
daa0df9e 6700 }, {
29f7c58a 6701 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6702 'only_matching': True,
6703 }, {
6704 # music album playlist
6705 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6706 'only_matching': True,
6707 }]
6708
6709 @classmethod
6710 def suitable(cls, url):
201c1459 6711 if YoutubeTabIE.suitable(url):
6712 return False
49a57e70 6713 from ..utils import parse_qs
201c1459 6714 qs = parse_qs(url)
6715 if qs.get('v', [None])[0]:
6716 return False
86e5f3ed 6717 return super().suitable(url)
29f7c58a 6718
6719 def _real_extract(self, url):
6720 playlist_id = self._match_id(url)
46953e7e 6721 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
9297939e 6722 url = update_url_query(
6723 'https://www.youtube.com/playlist',
6724 parse_qs(url) or {'list': playlist_id})
6725 if is_music_url:
6726 url = smuggle_url(url, {'is_music_url': True})
6727 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
29f7c58a 6728
6729
6730class YoutubeYtBeIE(InfoExtractor):
c76eb41b 6731 IE_DESC = 'youtu.be'
29f7c58a 6732 _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}
6733 _TESTS = [{
8bdd16b4 6734 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6735 'info_dict': {
6736 'id': 'yeWKywCrFtk',
6737 'ext': 'mp4',
6738 'title': 'Small Scale Baler and Braiding Rugs',
6739 'uploader': 'Backus-Page House Museum',
7666b936 6740 'uploader_id': '@backuspagemuseum',
6741 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@backuspagemuseum',
8bdd16b4 6742 'upload_date': '20161008',
6743 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6744 'categories': ['Nonprofits & Activism'],
6745 'tags': list,
6746 'like_count': int,
976ae3ea 6747 'age_limit': 0,
6748 'playable_in_embed': True,
7666b936 6749 'thumbnail': r're:^https?://.*\.webp',
976ae3ea 6750 'channel': 'Backus-Page House Museum',
6751 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6752 'live_status': 'not_live',
6753 'view_count': int,
6754 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6755 'availability': 'public',
6756 'duration': 59,
12a1b225
A
6757 'comment_count': int,
6758 'channel_follower_count': int
8bdd16b4 6759 },
6760 'params': {
6761 'noplaylist': True,
6762 'skip_download': True,
6763 },
39e7107d 6764 }, {
8bdd16b4 6765 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
39e7107d 6766 'only_matching': True,
cdc628a4
PH
6767 }]
6768
8bdd16b4 6769 def _real_extract(self, url):
5ad28e7f 6770 mobj = self._match_valid_url(url)
29f7c58a 6771 video_id = mobj.group('id')
6772 playlist_id = mobj.group('playlist_id')
8bdd16b4 6773 return self.url_result(
29f7c58a 6774 update_url_query('https://www.youtube.com/watch', {
6775 'v': video_id,
6776 'list': playlist_id,
6777 'feature': 'youtu.be',
6778 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
8bdd16b4 6779
6780
b6ce9bb0 6781class YoutubeLivestreamEmbedIE(InfoExtractor):
6782 IE_DESC = 'YouTube livestream embeds'
6783 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6784 _TESTS = [{
6785 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6786 'only_matching': True,
6787 }]
6788
6789 def _real_extract(self, url):
6790 channel_id = self._match_id(url)
6791 return self.url_result(
6792 f'https://www.youtube.com/channel/{channel_id}/live',
6793 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
6794
6795
8bdd16b4 6796class YoutubeYtUserIE(InfoExtractor):
96565c7e 6797 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
b6ce9bb0 6798 IE_NAME = 'youtube:user'
8bdd16b4 6799 _VALID_URL = r'ytuser:(?P<id>.+)'
6800 _TESTS = [{
6801 'url': 'ytuser:phihag',
6802 'only_matching': True,
6803 }]
6804
6805 def _real_extract(self, url):
6806 user_id = self._match_id(url)
08270da5 6807 return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id)
9558dcec 6808
b05654f0 6809
3d3dddc9 6810class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
70d5c17b 6811 IE_NAME = 'youtube:favorites'
96565c7e 6812 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
70d5c17b 6813 _VALID_URL = r':ytfav(?:ou?rite)?s?'
6814 _LOGIN_REQUIRED = True
6815 _TESTS = [{
6816 'url': ':ytfav',
6817 'only_matching': True,
6818 }, {
6819 'url': ':ytfavorites',
6820 'only_matching': True,
6821 }]
6822
6823 def _real_extract(self, url):
6824 return self.url_result(
6825 'https://www.youtube.com/playlist?list=LL',
6826 ie=YoutubeTabIE.ie_key())
6827
6828
ca5300c7 6829class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor):
6830 IE_NAME = 'youtube:notif'
6831 IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6832 _VALID_URL = r':ytnotif(?:ication)?s?'
6833 _LOGIN_REQUIRED = True
6834 _TESTS = [{
6835 'url': ':ytnotif',
6836 'only_matching': True,
6837 }, {
6838 'url': ':ytnotifications',
6839 'only_matching': True,
6840 }]
6841
6842 def _extract_notification_menu(self, response, continuation_list):
6843 notification_list = traverse_obj(
6844 response,
6845 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6846 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6847 expected_type=list) or []
6848 continuation_list[0] = None
6849 for item in notification_list:
6850 entry = self._extract_notification_renderer(item.get('notificationRenderer'))
6851 if entry:
6852 yield entry
6853 continuation = item.get('continuationItemRenderer')
6854 if continuation:
6855 continuation_list[0] = continuation
6856
6857 def _extract_notification_renderer(self, notification):
6858 video_id = traverse_obj(
6859 notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str)
6860 url = f'https://www.youtube.com/watch?v={video_id}'
6861 channel_id = None
6862 if not video_id:
6863 browse_ep = traverse_obj(
6864 notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict)
7666b936 6865 channel_id = self.ucid_or_none(traverse_obj(browse_ep, 'browseId', expected_type=str))
ca5300c7 6866 post_id = self._search_regex(
6867 r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str),
6868 'post id', default=None)
6869 if not channel_id or not post_id:
6870 return
6871 # The direct /post url redirects to this in the browser
6872 url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6873
6874 channel = traverse_obj(
6875 notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6876 expected_type=str)
c7a7baaa 6877 notification_title = self._get_text(notification, 'shortMessage')
6878 if notification_title:
6879 notification_title = notification_title.replace('\xad', '') # remove soft hyphens
6880 # TODO: handle recommended videos
ca5300c7 6881 title = self._search_regex(
c7a7baaa 6882 rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
ca5300c7 6883 'video title', default=None)
5225df50 6884 timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText'))
6885 if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE)
6886 else None)
ca5300c7 6887 return {
6888 '_type': 'url',
6889 'url': url,
6890 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(),
6891 'video_id': video_id,
6892 'title': title,
6893 'channel_id': channel_id,
6894 'channel': channel,
7666b936 6895 'uploader': channel,
ca5300c7 6896 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'),
5225df50 6897 'timestamp': timestamp,
ca5300c7 6898 }
6899
6900 def _notification_menu_entries(self, ytcfg):
6901 continuation_list = [None]
6902 response = None
6903 for page in itertools.count(1):
6904 ctoken = traverse_obj(
6905 continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str)
6906 response = self._extract_response(
6907 item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg,
6908 ep='notification/get_notification_menu', check_get_keys='actions',
6909 headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)))
6910 yield from self._extract_notification_menu(response, continuation_list)
6911 if not continuation_list[0]:
6912 break
6913
6914 def _real_extract(self, url):
6915 display_id = 'notifications'
6916 ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {}
6917 self._report_playlist_authcheck(ytcfg)
6918 return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id)
6919
6920
a6213a49 6921class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
6922 IE_DESC = 'YouTube search'
78caa52a 6923 IE_NAME = 'youtube:search'
b05654f0 6924 _SEARCH_KEY = 'ytsearch'
a61fd4cf 6925 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
84bbc545 6926 _TESTS = [{
6927 'url': 'ytsearch5:youtube-dl test video',
6928 'playlist_count': 5,
6929 'info_dict': {
6930 'id': 'youtube-dl test video',
6931 'title': 'youtube-dl test video',
6932 }
6933 }]
b05654f0 6934
a61fd4cf 6935
5f7cb91a 6936class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
cb7fb546 6937 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 6938 _SEARCH_KEY = 'ytsearchdate'
a6213a49 6939 IE_DESC = 'YouTube search, newest videos first'
a61fd4cf 6940 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
84bbc545 6941 _TESTS = [{
6942 'url': 'ytsearchdate5:youtube-dl test video',
6943 'playlist_count': 5,
6944 'info_dict': {
6945 'id': 'youtube-dl test video',
6946 'title': 'youtube-dl test video',
6947 }
6948 }]
75dff0ee 6949
c9ae7b95 6950
a6213a49 6951class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
96565c7e 6952 IE_DESC = 'YouTube search URLs with sorting and filter support'
386e1dd9 6953 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
182bda88 6954 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
3462ffa8 6955 _TESTS = [{
6956 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6957 'playlist_mincount': 5,
6958 'info_dict': {
11f9be09 6959 'id': 'youtube-dl test video',
3462ffa8 6960 'title': 'youtube-dl test video',
6961 }
a61fd4cf 6962 }, {
6963 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6964 'playlist_mincount': 5,
6965 'info_dict': {
6966 'id': 'python',
6967 'title': 'python',
6968 }
ad210f4f 6969 }, {
6970 'url': 'https://www.youtube.com/results?search_query=%23cats',
6971 'playlist_mincount': 1,
6972 'info_dict': {
6973 'id': '#cats',
6974 'title': '#cats',
12a1b225
A
6975 # The test suite does not have support for nested playlists
6976 # 'entries': [{
6977 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6978 # 'title': '#cats',
6979 # }],
ad210f4f 6980 },
c7335551
M
6981 }, {
6982 # Channel results
6983 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
6984 'info_dict': {
6985 'id': 'kurzgesagt',
6986 'title': 'kurzgesagt',
6987 },
6988 'playlist': [{
6989 'info_dict': {
6990 '_type': 'url',
6991 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6992 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6993 'ie_key': 'YoutubeTab',
6994 'channel': 'Kurzgesagt – In a Nutshell',
6995 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
6996 'title': 'Kurzgesagt – In a Nutshell',
6997 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
14a14335 6998 # No longer available for search as it is set to the handle.
6999 # 'playlist_count': int,
c7335551 7000 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
7666b936 7001 'thumbnails': list,
7002 'uploader_id': '@kurzgesagt',
7003 'uploader_url': 'https://www.youtube.com/@kurzgesagt',
7004 'uploader': 'Kurzgesagt – In a Nutshell',
8213ce28 7005 'channel_is_verified': True,
14a14335 7006 'channel_follower_count': int,
c7335551
M
7007 }
7008 }],
7009 'params': {'extract_flat': True, 'playlist_items': '1'},
7010 'playlist_mincount': 1,
3462ffa8 7011 }, {
7012 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
7013 'only_matching': True,
7014 }]
7015
7016 def _real_extract(self, url):
4dfbf869 7017 qs = parse_qs(url)
386e1dd9 7018 query = (qs.get('search_query') or qs.get('q'))[0]
a6213a49 7019 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
3462ffa8 7020
7021
16aa9ea4 7022class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
62b58c09 7023 IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs'
16aa9ea4 7024 IE_NAME = 'youtube:music:search_url'
7025 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
7026 _TESTS = [{
7027 'url': 'https://music.youtube.com/search?q=royalty+free+music',
7028 'playlist_count': 16,
7029 'info_dict': {
7030 'id': 'royalty free music',
7031 'title': 'royalty free music',
7032 }
7033 }, {
7034 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
7035 'playlist_mincount': 30,
7036 'info_dict': {
7037 'id': 'royalty free music - songs',
7038 'title': 'royalty free music - songs',
7039 },
7040 'params': {'extract_flat': 'in_playlist'}
7041 }, {
7042 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
7043 'playlist_mincount': 30,
7044 'info_dict': {
7045 'id': 'royalty free music - community playlists',
7046 'title': 'royalty free music - community playlists',
7047 },
7048 'params': {'extract_flat': 'in_playlist'}
7049 }]
7050
7051 _SECTIONS = {
7052 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
7053 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
7054 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
7055 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
7056 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
7057 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
7058 }
7059
7060 def _real_extract(self, url):
7061 qs = parse_qs(url)
7062 query = (qs.get('search_query') or qs.get('q'))[0]
7063 params = qs.get('sp', (None,))[0]
7064 if params:
7065 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
7066 else:
ac668111 7067 section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower()
16aa9ea4 7068 params = self._SECTIONS.get(section)
7069 if not params:
7070 section = None
7071 title = join_nonempty(query, section, delim=' - ')
af5c1c55 7072 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
16aa9ea4 7073
7074
182bda88 7075class YoutubeFeedsInfoExtractor(InfoExtractor):
d7ae0639 7076 """
25f14e9f 7077 Base class for feed extractors
82d02080 7078 Subclasses must re-define the _FEED_NAME property.
d7ae0639 7079 """
b2e8bc1b 7080 _LOGIN_REQUIRED = True
82d02080 7081 _FEED_NAME = 'feeds'
a25bca9f 7082
7083 def _real_initialize(self):
7084 YoutubeBaseInfoExtractor._check_login_required(self)
d7ae0639 7085
82d02080 7086 @classproperty
d7ae0639 7087 def IE_NAME(self):
82d02080 7088 return f'youtube:{self._FEED_NAME}'
04cc9617 7089
3853309f 7090 def _real_extract(self, url):
3d3dddc9 7091 return self.url_result(
182bda88 7092 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
25f14e9f
S
7093
7094
ef2f3c7f 7095class YoutubeWatchLaterIE(InfoExtractor):
7096 IE_NAME = 'youtube:watchlater'
96565c7e 7097 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
3d3dddc9 7098 _VALID_URL = r':ytwatchlater'
bc7a9cd8 7099 _TESTS = [{
8bdd16b4 7100 'url': ':ytwatchlater',
bc7a9cd8
S
7101 'only_matching': True,
7102 }]
25f14e9f
S
7103
7104 def _real_extract(self, url):
ef2f3c7f 7105 return self.url_result(
7106 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3462ffa8 7107
7108
25f14e9f 7109class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
96565c7e 7110 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
3d3dddc9 7111 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
25f14e9f 7112 _FEED_NAME = 'recommended'
45db527f 7113 _LOGIN_REQUIRED = False
3d3dddc9 7114 _TESTS = [{
7115 'url': ':ytrec',
7116 'only_matching': True,
7117 }, {
7118 'url': ':ytrecommended',
7119 'only_matching': True,
7120 }, {
7121 'url': 'https://youtube.com',
7122 'only_matching': True,
7123 }]
1ed5b5c9 7124
1ed5b5c9 7125
25f14e9f 7126class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
96565c7e 7127 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
3d3dddc9 7128 _VALID_URL = r':ytsub(?:scription)?s?'
25f14e9f 7129 _FEED_NAME = 'subscriptions'
3d3dddc9 7130 _TESTS = [{
7131 'url': ':ytsubs',
7132 'only_matching': True,
7133 }, {
7134 'url': ':ytsubscriptions',
7135 'only_matching': True,
7136 }]
1ed5b5c9 7137
1ed5b5c9 7138
25f14e9f 7139class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
96565c7e 7140 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
a5c56234 7141 _VALID_URL = r':ythis(?:tory)?'
25f14e9f 7142 _FEED_NAME = 'history'
3d3dddc9 7143 _TESTS = [{
7144 'url': ':ythistory',
7145 'only_matching': True,
7146 }]
1ed5b5c9
JMF
7147
7148
80eb0bd9 7149class YoutubeShortsAudioPivotIE(InfoExtractor):
1dd18a88 7150 IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
80eb0bd9 7151 IE_NAME = 'youtube:shorts:pivot:audio'
1dd18a88 7152 _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
80eb0bd9 7153 _TESTS = [{
1dd18a88 7154 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
80eb0bd9 7155 'only_matching': True,
7156 }]
7157
7158 @staticmethod
7159 def _generate_audio_pivot_params(video_id):
7160 """
7161 Generates sfv_audio_pivot browse params for this video id
7162 """
7163 pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3)
7164 return urllib.parse.quote(base64.b64encode(pb_params).decode())
7165
7166 def _real_extract(self, url):
7167 video_id = self._match_id(url)
7168 return self.url_result(
7169 f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
7170 ie=YoutubeTabIE)
7171
7172
15870e90
PH
7173class YoutubeTruncatedURLIE(InfoExtractor):
7174 IE_NAME = 'youtube:truncated_url'
7175 IE_DESC = False # Do not list
975d35db 7176 _VALID_URL = r'''(?x)
b95aab84
PH
7177 (?:https?://)?
7178 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
7179 (?:watch\?(?:
c4808c60 7180 feature=[a-z_]+|
b95aab84
PH
7181 annotation_id=annotation_[^&]+|
7182 x-yt-cl=[0-9]+|
c1708b89 7183 hl=[^&]*|
287be8c6 7184 t=[0-9]+
b95aab84
PH
7185 )?
7186 |
7187 attribution_link\?a=[^&]+
7188 )
7189 $
975d35db 7190 '''
15870e90 7191
c4808c60 7192 _TESTS = [{
2d3d2997 7193 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
c4808c60 7194 'only_matching': True,
dc2fc736 7195 }, {
2d3d2997 7196 'url': 'https://www.youtube.com/watch?',
dc2fc736 7197 'only_matching': True,
b95aab84
PH
7198 }, {
7199 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
7200 'only_matching': True,
7201 }, {
7202 'url': 'https://www.youtube.com/watch?feature=foo',
7203 'only_matching': True,
c1708b89
PH
7204 }, {
7205 'url': 'https://www.youtube.com/watch?hl=en-GB',
7206 'only_matching': True,
287be8c6
PH
7207 }, {
7208 'url': 'https://www.youtube.com/watch?t=2372',
7209 'only_matching': True,
c4808c60
PH
7210 }]
7211
15870e90
PH
7212 def _real_extract(self, url):
7213 raise ExtractorError(
78caa52a
PH
7214 'Did you forget to quote the URL? Remember that & is a meta '
7215 'character in most shells, so you want to put the URL in quotes, '
3867038a 7216 'like youtube-dl '
2d3d2997 7217 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3867038a 7218 ' or simply youtube-dl BaW_jenozKc .',
15870e90 7219 expected=True)
772fd5cc
PH
7220
7221
471d0367 7222class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
3cd786db 7223 IE_NAME = 'youtube:clip'
471d0367 7224 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
7225 _TESTS = [{
7226 # FIXME: Other metadata should be extracted from the clip, not from the base video
7227 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
7228 'info_dict': {
7229 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
7230 'ext': 'mp4',
7231 'section_start': 29.0,
7232 'section_end': 39.7,
7233 'duration': 10.7,
12a1b225
A
7234 'age_limit': 0,
7235 'availability': 'public',
7236 'categories': ['Gaming'],
7237 'channel': 'Scott The Woz',
7238 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
7239 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
7240 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
7241 'like_count': int,
7242 'playable_in_embed': True,
7243 'tags': 'count:17',
7244 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
7245 'title': 'Mobile Games on Console - Scott The Woz',
7246 'upload_date': '20210920',
7247 'uploader': 'Scott The Woz',
7666b936 7248 'uploader_id': '@ScottTheWoz',
7249 'uploader_url': 'https://www.youtube.com/@ScottTheWoz',
12a1b225
A
7250 'view_count': int,
7251 'live_status': 'not_live',
7666b936 7252 'channel_follower_count': int,
7253 'chapters': 'count:20',
14a14335 7254 'comment_count': int,
7255 'heatmap': 'count:100',
471d0367 7256 }
7257 }]
3cd786db 7258
7259 def _real_extract(self, url):
471d0367 7260 clip_id = self._match_id(url)
7261 _, data = self._extract_webpage(url, clip_id)
7262
7263 video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
7264 if not video_id:
7265 raise ExtractorError('Unable to find video ID')
7266
7267 clip_data = traverse_obj(data, (
7268 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
7269 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
7270 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
7271 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False)
7272
7273 return {
7274 '_type': 'url_transparent',
7275 'url': f'https://www.youtube.com/watch?v={video_id}',
7276 'ie_key': YoutubeIE.ie_key(),
7277 'id': clip_id,
7278 'section_start': int(clip_data['startTimeMs']) / 1000,
7279 'section_end': int(clip_data['endTimeMs']) / 1000,
7280 }
3cd786db 7281
7282
b032ff0f 7283class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor):
7284 IE_NAME = 'youtube:consent'
7285 IE_DESC = False # Do not list
7286 _VALID_URL = r'https?://consent\.youtube\.com/m\?'
7287 _TESTS = [{
7288 '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',
7289 'info_dict': {
7290 'id': 'qVv6vCqciTM',
7291 'ext': 'mp4',
7292 'age_limit': 0,
7666b936 7293 'uploader_id': '@sana_natori',
b032ff0f 7294 'comment_count': int,
7295 'chapters': 'count:13',
7296 'upload_date': '20221223',
7297 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
7298 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7666b936 7299 'uploader_url': 'https://www.youtube.com/@sana_natori',
b032ff0f 7300 'like_count': int,
7301 'release_date': '20221223',
7302 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
7303 '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】',
7304 'view_count': int,
7305 'playable_in_embed': True,
7306 'duration': 4438,
7307 'availability': 'public',
7308 'channel_follower_count': int,
7309 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7310 'categories': ['Entertainment'],
7311 'live_status': 'was_live',
7312 'release_timestamp': 1671793345,
7313 'channel': 'さなちゃんねる',
7314 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
7315 'uploader': 'さなちゃんねる',
8213ce28 7316 'channel_is_verified': True,
14a14335 7317 'heatmap': 'count:100',
b032ff0f 7318 },
7319 'add_ie': ['Youtube'],
7320 'params': {'skip_download': 'Youtube'},
7321 }]
7322
7323 def _real_extract(self, url):
7324 redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1])
7325 if not redirect_url:
7326 raise ExtractorError('Invalid cookie consent redirect URL', expected=True)
7327 return self.url_result(redirect_url)
7328
7329
772fd5cc
PH
7330class YoutubeTruncatedIDIE(InfoExtractor):
7331 IE_NAME = 'youtube:truncated_id'
7332 IE_DESC = False # Do not list
b95aab84 7333 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
7334
7335 _TESTS = [{
7336 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7337 'only_matching': True,
7338 }]
7339
7340 def _real_extract(self, url):
7341 video_id = self._match_id(url)
7342 raise ExtractorError(
86e5f3ed 7343 f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',
772fd5cc 7344 expected=True)