]>
Commit | Line | Data |
---|---|---|
1 | import base64 | |
2 | import calendar | |
3 | import collections | |
4 | import copy | |
5 | import datetime as dt | |
6 | import enum | |
7 | import hashlib | |
8 | import itertools | |
9 | import json | |
10 | import math | |
11 | import os.path | |
12 | import random | |
13 | import re | |
14 | import shlex | |
15 | import sys | |
16 | import threading | |
17 | import time | |
18 | import traceback | |
19 | import urllib.parse | |
20 | ||
21 | from .common import InfoExtractor, SearchInfoExtractor | |
22 | from .openload import PhantomJSwrapper | |
23 | from ..compat import functools | |
24 | from ..jsinterp import JSInterpreter | |
25 | from ..networking.exceptions import HTTPError, network_exceptions | |
26 | from ..utils import ( | |
27 | NO_DEFAULT, | |
28 | ExtractorError, | |
29 | LazyList, | |
30 | UserNotLive, | |
31 | bug_reports_message, | |
32 | classproperty, | |
33 | clean_html, | |
34 | datetime_from_str, | |
35 | dict_get, | |
36 | filesize_from_tbr, | |
37 | filter_dict, | |
38 | float_or_none, | |
39 | format_field, | |
40 | get_first, | |
41 | int_or_none, | |
42 | is_html, | |
43 | join_nonempty, | |
44 | js_to_json, | |
45 | mimetype2ext, | |
46 | orderedSet, | |
47 | parse_codecs, | |
48 | parse_count, | |
49 | parse_duration, | |
50 | parse_iso8601, | |
51 | parse_qs, | |
52 | qualities, | |
53 | remove_start, | |
54 | smuggle_url, | |
55 | str_or_none, | |
56 | str_to_int, | |
57 | strftime_or_none, | |
58 | traverse_obj, | |
59 | try_call, | |
60 | try_get, | |
61 | unescapeHTML, | |
62 | unified_strdate, | |
63 | unified_timestamp, | |
64 | unsmuggle_url, | |
65 | update_url_query, | |
66 | url_or_none, | |
67 | urljoin, | |
68 | variadic, | |
69 | ) | |
70 | ||
71 | STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client' | |
72 | # any clients starting with _ cannot be explicitly requested by the user | |
73 | INNERTUBE_CLIENTS = { | |
74 | 'web': { | |
75 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
76 | 'INNERTUBE_CONTEXT': { | |
77 | 'client': { | |
78 | 'clientName': 'WEB', | |
79 | 'clientVersion': '2.20220801.00.00', | |
80 | } | |
81 | }, | |
82 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 1 | |
83 | }, | |
84 | 'web_embedded': { | |
85 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
86 | 'INNERTUBE_CONTEXT': { | |
87 | 'client': { | |
88 | 'clientName': 'WEB_EMBEDDED_PLAYER', | |
89 | 'clientVersion': '1.20220731.00.00', | |
90 | }, | |
91 | }, | |
92 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 56 | |
93 | }, | |
94 | 'web_music': { | |
95 | 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30', | |
96 | 'INNERTUBE_HOST': 'music.youtube.com', | |
97 | 'INNERTUBE_CONTEXT': { | |
98 | 'client': { | |
99 | 'clientName': 'WEB_REMIX', | |
100 | 'clientVersion': '1.20220727.01.00', | |
101 | } | |
102 | }, | |
103 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 67, | |
104 | }, | |
105 | 'web_creator': { | |
106 | 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo', | |
107 | 'INNERTUBE_CONTEXT': { | |
108 | 'client': { | |
109 | 'clientName': 'WEB_CREATOR', | |
110 | 'clientVersion': '1.20220726.00.00', | |
111 | } | |
112 | }, | |
113 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 62, | |
114 | }, | |
115 | 'android': { | |
116 | 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w', | |
117 | 'INNERTUBE_CONTEXT': { | |
118 | 'client': { | |
119 | 'clientName': 'ANDROID', | |
120 | 'clientVersion': '19.09.37', | |
121 | 'androidSdkVersion': 30, | |
122 | 'userAgent': 'com.google.android.youtube/19.09.37 (Linux; U; Android 11) gzip' | |
123 | } | |
124 | }, | |
125 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 3, | |
126 | 'REQUIRE_JS_PLAYER': False | |
127 | }, | |
128 | 'android_embedded': { | |
129 | 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw', | |
130 | 'INNERTUBE_CONTEXT': { | |
131 | 'client': { | |
132 | 'clientName': 'ANDROID_EMBEDDED_PLAYER', | |
133 | 'clientVersion': '19.09.37', | |
134 | 'androidSdkVersion': 30, | |
135 | 'userAgent': 'com.google.android.youtube/19.09.37 (Linux; U; Android 11) gzip' | |
136 | }, | |
137 | }, | |
138 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 55, | |
139 | 'REQUIRE_JS_PLAYER': False | |
140 | }, | |
141 | 'android_music': { | |
142 | 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI', | |
143 | 'INNERTUBE_CONTEXT': { | |
144 | 'client': { | |
145 | 'clientName': 'ANDROID_MUSIC', | |
146 | 'clientVersion': '6.42.52', | |
147 | 'androidSdkVersion': 30, | |
148 | 'userAgent': 'com.google.android.apps.youtube.music/6.42.52 (Linux; U; Android 11) gzip' | |
149 | } | |
150 | }, | |
151 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 21, | |
152 | 'REQUIRE_JS_PLAYER': False | |
153 | }, | |
154 | 'android_creator': { | |
155 | 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8', | |
156 | 'INNERTUBE_CONTEXT': { | |
157 | 'client': { | |
158 | 'clientName': 'ANDROID_CREATOR', | |
159 | 'clientVersion': '22.30.100', | |
160 | 'androidSdkVersion': 30, | |
161 | 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip' | |
162 | }, | |
163 | }, | |
164 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 14, | |
165 | 'REQUIRE_JS_PLAYER': False | |
166 | }, | |
167 | # iOS clients have HLS live streams. Setting device model to get 60fps formats. | |
168 | # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558 | |
169 | 'ios': { | |
170 | 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc', | |
171 | 'INNERTUBE_CONTEXT': { | |
172 | 'client': { | |
173 | 'clientName': 'IOS', | |
174 | 'clientVersion': '19.09.3', | |
175 | 'deviceModel': 'iPhone14,3', | |
176 | 'userAgent': 'com.google.ios.youtube/19.09.3 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)' | |
177 | } | |
178 | }, | |
179 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 5, | |
180 | 'REQUIRE_JS_PLAYER': False | |
181 | }, | |
182 | 'ios_embedded': { | |
183 | 'INNERTUBE_CONTEXT': { | |
184 | 'client': { | |
185 | 'clientName': 'IOS_MESSAGES_EXTENSION', | |
186 | 'clientVersion': '19.09.3', | |
187 | 'deviceModel': 'iPhone14,3', | |
188 | 'userAgent': 'com.google.ios.youtube/19.09.3 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)' | |
189 | }, | |
190 | }, | |
191 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 66, | |
192 | 'REQUIRE_JS_PLAYER': False | |
193 | }, | |
194 | 'ios_music': { | |
195 | 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s', | |
196 | 'INNERTUBE_CONTEXT': { | |
197 | 'client': { | |
198 | 'clientName': 'IOS_MUSIC', | |
199 | 'clientVersion': '6.33.3', | |
200 | 'deviceModel': 'iPhone14,3', | |
201 | 'userAgent': 'com.google.ios.youtubemusic/6.33.3 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)' | |
202 | }, | |
203 | }, | |
204 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 26, | |
205 | 'REQUIRE_JS_PLAYER': False | |
206 | }, | |
207 | 'ios_creator': { | |
208 | 'INNERTUBE_CONTEXT': { | |
209 | 'client': { | |
210 | 'clientName': 'IOS_CREATOR', | |
211 | 'clientVersion': '22.33.101', | |
212 | 'deviceModel': 'iPhone14,3', | |
213 | 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)' | |
214 | }, | |
215 | }, | |
216 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 15, | |
217 | 'REQUIRE_JS_PLAYER': False | |
218 | }, | |
219 | # mweb has 'ultralow' formats | |
220 | # See: https://github.com/yt-dlp/yt-dlp/pull/557 | |
221 | 'mweb': { | |
222 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
223 | 'INNERTUBE_CONTEXT': { | |
224 | 'client': { | |
225 | 'clientName': 'MWEB', | |
226 | 'clientVersion': '2.20220801.00.00', | |
227 | } | |
228 | }, | |
229 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 2 | |
230 | }, | |
231 | # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option) | |
232 | # See: https://github.com/zerodytrash/YouTube-Internal-Clients | |
233 | 'tv_embedded': { | |
234 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
235 | 'INNERTUBE_CONTEXT': { | |
236 | 'client': { | |
237 | 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER', | |
238 | 'clientVersion': '2.0', | |
239 | }, | |
240 | }, | |
241 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 85 | |
242 | }, | |
243 | # This client has pre-merged video+audio 720p/1080p streams | |
244 | 'mediaconnect': { | |
245 | 'INNERTUBE_CONTEXT': { | |
246 | 'client': { | |
247 | 'clientName': 'MEDIA_CONNECT_FRONTEND', | |
248 | 'clientVersion': '0.1', | |
249 | }, | |
250 | }, | |
251 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 95 | |
252 | }, | |
253 | } | |
254 | ||
255 | ||
256 | def _split_innertube_client(client_name): | |
257 | variant, *base = client_name.rsplit('.', 1) | |
258 | if base: | |
259 | return variant, base[0], variant | |
260 | base, *variant = client_name.split('_', 1) | |
261 | return client_name, base, variant[0] if variant else None | |
262 | ||
263 | ||
264 | def short_client_name(client_name): | |
265 | main, *parts = _split_innertube_client(client_name)[0].replace('embedscreen', 'e_s').split('_') | |
266 | return join_nonempty(main[:4], ''.join(x[0] for x in parts)).upper() | |
267 | ||
268 | ||
269 | def build_innertube_clients(): | |
270 | THIRD_PARTY = { | |
271 | 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL | |
272 | } | |
273 | BASE_CLIENTS = ('ios', 'android', 'web', 'tv', 'mweb') | |
274 | priority = qualities(BASE_CLIENTS[::-1]) | |
275 | ||
276 | for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()): | |
277 | ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8') | |
278 | ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com') | |
279 | ytcfg.setdefault('REQUIRE_JS_PLAYER', True) | |
280 | ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en') | |
281 | ||
282 | _, base_client, variant = _split_innertube_client(client) | |
283 | ytcfg['priority'] = 10 * priority(base_client) | |
284 | ||
285 | if not variant: | |
286 | INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg) | |
287 | embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED' | |
288 | embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY | |
289 | embedscreen['priority'] -= 3 | |
290 | elif variant == 'embedded': | |
291 | ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY | |
292 | ytcfg['priority'] -= 2 | |
293 | else: | |
294 | ytcfg['priority'] -= 3 | |
295 | ||
296 | ||
297 | build_innertube_clients() | |
298 | ||
299 | ||
300 | class BadgeType(enum.Enum): | |
301 | AVAILABILITY_UNLISTED = enum.auto() | |
302 | AVAILABILITY_PRIVATE = enum.auto() | |
303 | AVAILABILITY_PUBLIC = enum.auto() | |
304 | AVAILABILITY_PREMIUM = enum.auto() | |
305 | AVAILABILITY_SUBSCRIPTION = enum.auto() | |
306 | LIVE_NOW = enum.auto() | |
307 | VERIFIED = enum.auto() | |
308 | ||
309 | ||
310 | class YoutubeBaseInfoExtractor(InfoExtractor): | |
311 | """Provide base functions for Youtube extractors""" | |
312 | ||
313 | _RESERVED_NAMES = ( | |
314 | r'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|' | |
315 | r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|' | |
316 | r'browse|oembed|get_video_info|iframe_api|s/player|source|' | |
317 | r'storefront|oops|index|account|t/terms|about|upload|signin|logout') | |
318 | ||
319 | _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)' | |
320 | ||
321 | # _NETRC_MACHINE = 'youtube' | |
322 | ||
323 | # If True it will raise an error if no login info is provided | |
324 | _LOGIN_REQUIRED = False | |
325 | ||
326 | _INVIDIOUS_SITES = ( | |
327 | # invidious-redirect websites | |
328 | r'(?:www\.)?redirect\.invidious\.io', | |
329 | r'(?:(?:www|dev)\.)?invidio\.us', | |
330 | # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md | |
331 | r'(?:www\.)?invidious\.pussthecat\.org', | |
332 | r'(?:www\.)?invidious\.zee\.li', | |
333 | r'(?:www\.)?invidious\.ethibox\.fr', | |
334 | r'(?:www\.)?iv\.ggtyler\.dev', | |
335 | r'(?:www\.)?inv\.vern\.i2p', | |
336 | r'(?:www\.)?am74vkcrjp2d5v36lcdqgsj2m6x36tbrkhsruoegwfcizzabnfgf5zyd\.onion', | |
337 | r'(?:www\.)?inv\.riverside\.rocks', | |
338 | r'(?:www\.)?invidious\.silur\.me', | |
339 | r'(?:www\.)?inv\.bp\.projectsegfau\.lt', | |
340 | r'(?:www\.)?invidious\.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid\.onion', | |
341 | r'(?:www\.)?invidious\.slipfox\.xyz', | |
342 | r'(?:www\.)?invidious\.esmail5pdn24shtvieloeedh7ehz3nrwcdivnfhfcedl7gf4kwddhkqd\.onion', | |
343 | r'(?:www\.)?inv\.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad\.onion', | |
344 | r'(?:www\.)?invidious\.tiekoetter\.com', | |
345 | r'(?:www\.)?iv\.odysfvr23q5wgt7i456o5t3trw2cw5dgn56vbjfbq2m7xsc5vqbqpcyd\.onion', | |
346 | r'(?:www\.)?invidious\.nerdvpn\.de', | |
347 | r'(?:www\.)?invidious\.weblibre\.org', | |
348 | r'(?:www\.)?inv\.odyssey346\.dev', | |
349 | r'(?:www\.)?invidious\.dhusch\.de', | |
350 | r'(?:www\.)?iv\.melmac\.space', | |
351 | r'(?:www\.)?watch\.thekitty\.zone', | |
352 | r'(?:www\.)?invidious\.privacydev\.net', | |
353 | r'(?:www\.)?ng27owmagn5amdm7l5s3rsqxwscl5ynppnis5dqcasogkyxcfqn7psid\.onion', | |
354 | r'(?:www\.)?invidious\.drivet\.xyz', | |
355 | r'(?:www\.)?vid\.priv\.au', | |
356 | r'(?:www\.)?euxxcnhsynwmfidvhjf6uzptsmh4dipkmgdmcmxxuo7tunp3ad2jrwyd\.onion', | |
357 | r'(?:www\.)?inv\.vern\.cc', | |
358 | r'(?:www\.)?invidious\.esmailelbob\.xyz', | |
359 | r'(?:www\.)?invidious\.sethforprivacy\.com', | |
360 | r'(?:www\.)?yt\.oelrichsgarcia\.de', | |
361 | r'(?:www\.)?yt\.artemislena\.eu', | |
362 | r'(?:www\.)?invidious\.flokinet\.to', | |
363 | r'(?:www\.)?invidious\.baczek\.me', | |
364 | r'(?:www\.)?y\.com\.sb', | |
365 | r'(?:www\.)?invidious\.epicsite\.xyz', | |
366 | r'(?:www\.)?invidious\.lidarshield\.cloud', | |
367 | r'(?:www\.)?yt\.funami\.tech', | |
368 | r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion', | |
369 | r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion', | |
370 | r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion', | |
371 | # youtube-dl invidious instances list | |
372 | r'(?:(?:www|no)\.)?invidiou\.sh', | |
373 | r'(?:(?:www|fi)\.)?invidious\.snopyta\.org', | |
374 | r'(?:www\.)?invidious\.kabi\.tk', | |
375 | r'(?:www\.)?invidious\.mastodon\.host', | |
376 | r'(?:www\.)?invidious\.zapashcanon\.fr', | |
377 | r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks', | |
378 | r'(?:www\.)?invidious\.tinfoil-hat\.net', | |
379 | r'(?:www\.)?invidious\.himiko\.cloud', | |
380 | r'(?:www\.)?invidious\.reallyancient\.tech', | |
381 | r'(?:www\.)?invidious\.tube', | |
382 | r'(?:www\.)?invidiou\.site', | |
383 | r'(?:www\.)?invidious\.site', | |
384 | r'(?:www\.)?invidious\.xyz', | |
385 | r'(?:www\.)?invidious\.nixnet\.xyz', | |
386 | r'(?:www\.)?invidious\.048596\.xyz', | |
387 | r'(?:www\.)?invidious\.drycat\.fr', | |
388 | r'(?:www\.)?inv\.skyn3t\.in', | |
389 | r'(?:www\.)?tube\.poal\.co', | |
390 | r'(?:www\.)?tube\.connect\.cafe', | |
391 | r'(?:www\.)?vid\.wxzm\.sx', | |
392 | r'(?:www\.)?vid\.mint\.lgbt', | |
393 | r'(?:www\.)?vid\.puffyan\.us', | |
394 | r'(?:www\.)?yewtu\.be', | |
395 | r'(?:www\.)?yt\.elukerio\.org', | |
396 | r'(?:www\.)?yt\.lelux\.fi', | |
397 | r'(?:www\.)?invidious\.ggc-project\.de', | |
398 | r'(?:www\.)?yt\.maisputain\.ovh', | |
399 | r'(?:www\.)?ytprivate\.com', | |
400 | r'(?:www\.)?invidious\.13ad\.de', | |
401 | r'(?:www\.)?invidious\.toot\.koeln', | |
402 | r'(?:www\.)?invidious\.fdn\.fr', | |
403 | r'(?:www\.)?watch\.nettohikari\.com', | |
404 | r'(?:www\.)?invidious\.namazso\.eu', | |
405 | r'(?:www\.)?invidious\.silkky\.cloud', | |
406 | r'(?:www\.)?invidious\.exonip\.de', | |
407 | r'(?:www\.)?invidious\.riverside\.rocks', | |
408 | r'(?:www\.)?invidious\.blamefran\.net', | |
409 | r'(?:www\.)?invidious\.moomoo\.de', | |
410 | r'(?:www\.)?ytb\.trom\.tf', | |
411 | r'(?:www\.)?yt\.cyberhost\.uk', | |
412 | r'(?:www\.)?kgg2m7yk5aybusll\.onion', | |
413 | r'(?:www\.)?qklhadlycap4cnod\.onion', | |
414 | r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion', | |
415 | r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion', | |
416 | r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion', | |
417 | r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion', | |
418 | r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p', | |
419 | r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion', | |
420 | r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion', | |
421 | r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion', | |
422 | r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion', | |
423 | r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion', | |
424 | # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances | |
425 | r'(?:www\.)?piped\.kavin\.rocks', | |
426 | r'(?:www\.)?piped\.tokhmi\.xyz', | |
427 | r'(?:www\.)?piped\.syncpundit\.io', | |
428 | r'(?:www\.)?piped\.mha\.fi', | |
429 | r'(?:www\.)?watch\.whatever\.social', | |
430 | r'(?:www\.)?piped\.garudalinux\.org', | |
431 | r'(?:www\.)?piped\.rivo\.lol', | |
432 | r'(?:www\.)?piped-libre\.kavin\.rocks', | |
433 | r'(?:www\.)?yt\.jae\.fi', | |
434 | r'(?:www\.)?piped\.mint\.lgbt', | |
435 | r'(?:www\.)?il\.ax', | |
436 | r'(?:www\.)?piped\.esmailelbob\.xyz', | |
437 | r'(?:www\.)?piped\.projectsegfau\.lt', | |
438 | r'(?:www\.)?piped\.privacydev\.net', | |
439 | r'(?:www\.)?piped\.palveluntarjoaja\.eu', | |
440 | r'(?:www\.)?piped\.smnz\.de', | |
441 | r'(?:www\.)?piped\.adminforge\.de', | |
442 | r'(?:www\.)?watch\.whatevertinfoil\.de', | |
443 | r'(?:www\.)?piped\.qdi\.fi', | |
444 | r'(?:(?:www|cf)\.)?piped\.video', | |
445 | r'(?:www\.)?piped\.aeong\.one', | |
446 | r'(?:www\.)?piped\.moomoo\.me', | |
447 | r'(?:www\.)?piped\.chauvet\.pro', | |
448 | r'(?:www\.)?watch\.leptons\.xyz', | |
449 | r'(?:www\.)?pd\.vern\.cc', | |
450 | r'(?:www\.)?piped\.hostux\.net', | |
451 | r'(?:www\.)?piped\.lunar\.icu', | |
452 | # Hyperpipe instances from https://hyperpipe.codeberg.page/ | |
453 | r'(?:www\.)?hyperpipe\.surge\.sh', | |
454 | r'(?:www\.)?hyperpipe\.esmailelbob\.xyz', | |
455 | r'(?:www\.)?listen\.whatever\.social', | |
456 | r'(?:www\.)?music\.adminforge\.de', | |
457 | ) | |
458 | ||
459 | # extracted from account/account_menu ep | |
460 | # XXX: These are the supported YouTube UI and API languages, | |
461 | # which is slightly different from languages supported for translation in YouTube studio | |
462 | _SUPPORTED_LANG_CODES = [ | |
463 | 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es', | |
464 | 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv', | |
465 | 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi', | |
466 | 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw', | |
467 | 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml', | |
468 | 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko' | |
469 | ] | |
470 | ||
471 | _IGNORED_WARNINGS = {'Unavailable videos will be hidden during playback'} | |
472 | ||
473 | _YT_HANDLE_RE = r'@[\w.-]{3,30}' # https://support.google.com/youtube/answer/11585688?hl=en | |
474 | _YT_CHANNEL_UCID_RE = r'UC[\w-]{22}' | |
475 | ||
476 | def ucid_or_none(self, ucid): | |
477 | return self._search_regex(rf'^({self._YT_CHANNEL_UCID_RE})$', ucid, 'UC-id', default=None) | |
478 | ||
479 | def handle_or_none(self, handle): | |
480 | return self._search_regex(rf'^({self._YT_HANDLE_RE})$', handle, '@-handle', default=None) | |
481 | ||
482 | def handle_from_url(self, url): | |
483 | return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_HANDLE_RE})', | |
484 | url, 'channel handle', default=None) | |
485 | ||
486 | def ucid_from_url(self, url): | |
487 | return self._search_regex(rf'^(?:https?://(?:www\.)?youtube\.com)?/({self._YT_CHANNEL_UCID_RE})', | |
488 | url, 'channel id', default=None) | |
489 | ||
490 | @functools.cached_property | |
491 | def _preferred_lang(self): | |
492 | """ | |
493 | Returns a language code supported by YouTube for the user preferred language. | |
494 | Returns None if no preferred language set. | |
495 | """ | |
496 | preferred_lang = self._configuration_arg('lang', ie_key='Youtube', casesense=True, default=[''])[0] | |
497 | if not preferred_lang: | |
498 | return | |
499 | if preferred_lang not in self._SUPPORTED_LANG_CODES: | |
500 | raise ExtractorError( | |
501 | f'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.', | |
502 | expected=True) | |
503 | elif preferred_lang != 'en': | |
504 | self.report_warning( | |
505 | f'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.') | |
506 | return preferred_lang | |
507 | ||
508 | def _initialize_consent(self): | |
509 | cookies = self._get_cookies('https://www.youtube.com/') | |
510 | if cookies.get('__Secure-3PSID'): | |
511 | return | |
512 | socs = cookies.get('SOCS') | |
513 | if socs and not socs.value.startswith('CAA'): # not consented | |
514 | return | |
515 | self._set_cookie('.youtube.com', 'SOCS', 'CAI', secure=True) # accept all (required for mixes) | |
516 | ||
517 | def _initialize_pref(self): | |
518 | cookies = self._get_cookies('https://www.youtube.com/') | |
519 | pref_cookie = cookies.get('PREF') | |
520 | pref = {} | |
521 | if pref_cookie: | |
522 | try: | |
523 | pref = dict(urllib.parse.parse_qsl(pref_cookie.value)) | |
524 | except ValueError: | |
525 | self.report_warning('Failed to parse user PREF cookie' + bug_reports_message()) | |
526 | pref.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'}) | |
527 | self._set_cookie('.youtube.com', name='PREF', value=urllib.parse.urlencode(pref)) | |
528 | ||
529 | def _real_initialize(self): | |
530 | self._initialize_pref() | |
531 | self._initialize_consent() | |
532 | self._check_login_required() | |
533 | ||
534 | def _check_login_required(self): | |
535 | if self._LOGIN_REQUIRED and not self._cookies_passed: | |
536 | self.raise_login_required('Login details are needed to download this content', method='cookies') | |
537 | ||
538 | _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=' | |
539 | _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=' | |
540 | ||
541 | def _get_default_ytcfg(self, client='web'): | |
542 | return copy.deepcopy(INNERTUBE_CLIENTS[client]) | |
543 | ||
544 | def _get_innertube_host(self, client='web'): | |
545 | return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST'] | |
546 | ||
547 | def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'): | |
548 | # try_get but with fallback to default ytcfg client values when present | |
549 | _func = lambda y: try_get(y, getter, expected_type) | |
550 | return _func(ytcfg) or _func(self._get_default_ytcfg(default_client)) | |
551 | ||
552 | def _extract_client_name(self, ytcfg, default_client='web'): | |
553 | return self._ytcfg_get_safe( | |
554 | ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'], | |
555 | lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client) | |
556 | ||
557 | def _extract_client_version(self, ytcfg, default_client='web'): | |
558 | return self._ytcfg_get_safe( | |
559 | ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'], | |
560 | lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client) | |
561 | ||
562 | def _select_api_hostname(self, req_api_hostname, default_client=None): | |
563 | return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0] | |
564 | or req_api_hostname or self._get_innertube_host(default_client or 'web')) | |
565 | ||
566 | def _extract_api_key(self, ytcfg=None, default_client='web'): | |
567 | return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client) | |
568 | ||
569 | def _extract_context(self, ytcfg=None, default_client='web'): | |
570 | context = get_first( | |
571 | (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict) | |
572 | # Enforce language and tz for extraction | |
573 | client_context = traverse_obj(context, 'client', expected_type=dict, default={}) | |
574 | client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0}) | |
575 | return context | |
576 | ||
577 | _SAPISID = None | |
578 | ||
579 | def _generate_sapisidhash_header(self, origin='https://www.youtube.com'): | |
580 | time_now = round(time.time()) | |
581 | if self._SAPISID is None: | |
582 | yt_cookies = self._get_cookies('https://www.youtube.com') | |
583 | # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is. | |
584 | # See: https://github.com/yt-dlp/yt-dlp/issues/393 | |
585 | sapisid_cookie = dict_get( | |
586 | yt_cookies, ('__Secure-3PAPISID', 'SAPISID')) | |
587 | if sapisid_cookie and sapisid_cookie.value: | |
588 | self._SAPISID = sapisid_cookie.value | |
589 | self.write_debug('Extracted SAPISID cookie') | |
590 | # SAPISID cookie is required if not already present | |
591 | if not yt_cookies.get('SAPISID'): | |
592 | self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie') | |
593 | self._set_cookie( | |
594 | '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600) | |
595 | else: | |
596 | self._SAPISID = False | |
597 | if not self._SAPISID: | |
598 | return None | |
599 | # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323 | |
600 | sapisidhash = hashlib.sha1( | |
601 | f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest() | |
602 | return f'SAPISIDHASH {time_now}_{sapisidhash}' | |
603 | ||
604 | def _call_api(self, ep, query, video_id, fatal=True, headers=None, | |
605 | note='Downloading API JSON', errnote='Unable to download API page', | |
606 | context=None, api_key=None, api_hostname=None, default_client='web'): | |
607 | ||
608 | data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)} | |
609 | data.update(query) | |
610 | real_headers = self.generate_api_headers(default_client=default_client) | |
611 | real_headers.update({'content-type': 'application/json'}) | |
612 | if headers: | |
613 | real_headers.update(headers) | |
614 | api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0] | |
615 | or api_key or self._extract_api_key(default_client=default_client)) | |
616 | return self._download_json( | |
617 | f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}', | |
618 | video_id=video_id, fatal=fatal, note=note, errnote=errnote, | |
619 | data=json.dumps(data).encode('utf8'), headers=real_headers, | |
620 | query={'key': api_key, 'prettyPrint': 'false'}) | |
621 | ||
622 | def extract_yt_initial_data(self, item_id, webpage, fatal=True): | |
623 | return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal) | |
624 | ||
625 | @staticmethod | |
626 | def _extract_session_index(*data): | |
627 | """ | |
628 | Index of current account in account list. | |
629 | See: https://github.com/yt-dlp/yt-dlp/pull/519 | |
630 | """ | |
631 | for ytcfg in data: | |
632 | session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX'])) | |
633 | if session_index is not None: | |
634 | return session_index | |
635 | ||
636 | # Deprecated? | |
637 | def _extract_identity_token(self, ytcfg=None, webpage=None): | |
638 | if ytcfg: | |
639 | token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str) | |
640 | if token: | |
641 | return token | |
642 | if webpage: | |
643 | return self._search_regex( | |
644 | r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage, | |
645 | 'identity token', default=None, fatal=False) | |
646 | ||
647 | @staticmethod | |
648 | def _extract_account_syncid(*args): | |
649 | """ | |
650 | Extract syncId required to download private playlists of secondary channels | |
651 | @params response and/or ytcfg | |
652 | """ | |
653 | for data in args: | |
654 | # ytcfg includes channel_syncid if on secondary channel | |
655 | delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], str) | |
656 | if delegated_sid: | |
657 | return delegated_sid | |
658 | sync_ids = (try_get( | |
659 | data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'], | |
660 | lambda x: x['DATASYNC_ID']), str) or '').split('||') | |
661 | if len(sync_ids) >= 2 and sync_ids[1]: | |
662 | # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel | |
663 | # and just "user_syncid||" for primary channel. We only want the channel_syncid | |
664 | return sync_ids[0] | |
665 | ||
666 | @staticmethod | |
667 | def _extract_visitor_data(*args): | |
668 | """ | |
669 | Extracts visitorData from an API response or ytcfg | |
670 | Appears to be used to track session state | |
671 | """ | |
672 | return get_first( | |
673 | args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))], | |
674 | expected_type=str) | |
675 | ||
676 | @functools.cached_property | |
677 | def is_authenticated(self): | |
678 | return bool(self._generate_sapisidhash_header()) | |
679 | ||
680 | def extract_ytcfg(self, video_id, webpage): | |
681 | if not webpage: | |
682 | return {} | |
683 | return self._parse_json( | |
684 | self._search_regex( | |
685 | r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg', | |
686 | default='{}'), video_id, fatal=False) or {} | |
687 | ||
688 | def generate_api_headers( | |
689 | self, *, ytcfg=None, account_syncid=None, session_index=None, | |
690 | visitor_data=None, identity_token=None, api_hostname=None, default_client='web'): | |
691 | ||
692 | origin = 'https://' + (self._select_api_hostname(api_hostname, default_client)) | |
693 | headers = { | |
694 | 'X-YouTube-Client-Name': str( | |
695 | self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)), | |
696 | 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client), | |
697 | 'Origin': origin, | |
698 | 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg), | |
699 | 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg), | |
700 | 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg), | |
701 | 'User-Agent': self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['userAgent'], default_client=default_client) | |
702 | } | |
703 | if session_index is None: | |
704 | session_index = self._extract_session_index(ytcfg) | |
705 | if account_syncid or session_index is not None: | |
706 | headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0 | |
707 | ||
708 | auth = self._generate_sapisidhash_header(origin) | |
709 | if auth is not None: | |
710 | headers['Authorization'] = auth | |
711 | headers['X-Origin'] = origin | |
712 | return filter_dict(headers) | |
713 | ||
714 | def _download_ytcfg(self, client, video_id): | |
715 | url = { | |
716 | 'web': 'https://www.youtube.com', | |
717 | 'web_music': 'https://music.youtube.com', | |
718 | 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1' | |
719 | }.get(client) | |
720 | if not url: | |
721 | return {} | |
722 | webpage = self._download_webpage( | |
723 | url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config') | |
724 | return self.extract_ytcfg(video_id, webpage) or {} | |
725 | ||
726 | @staticmethod | |
727 | def _build_api_continuation_query(continuation, ctp=None): | |
728 | query = { | |
729 | 'continuation': continuation | |
730 | } | |
731 | # TODO: Inconsistency with clickTrackingParams. | |
732 | # Currently we have a fixed ctp contained within context (from ytcfg) | |
733 | # and a ctp in root query for continuation. | |
734 | if ctp: | |
735 | query['clickTracking'] = {'clickTrackingParams': ctp} | |
736 | return query | |
737 | ||
738 | @classmethod | |
739 | def _extract_next_continuation_data(cls, renderer): | |
740 | next_continuation = try_get( | |
741 | renderer, (lambda x: x['continuations'][0]['nextContinuationData'], | |
742 | lambda x: x['continuation']['reloadContinuationData']), dict) | |
743 | if not next_continuation: | |
744 | return | |
745 | continuation = next_continuation.get('continuation') | |
746 | if not continuation: | |
747 | return | |
748 | ctp = next_continuation.get('clickTrackingParams') | |
749 | return cls._build_api_continuation_query(continuation, ctp) | |
750 | ||
751 | @classmethod | |
752 | def _extract_continuation_ep_data(cls, continuation_ep: dict): | |
753 | if isinstance(continuation_ep, dict): | |
754 | continuation = try_get( | |
755 | continuation_ep, lambda x: x['continuationCommand']['token'], str) | |
756 | if not continuation: | |
757 | return | |
758 | ctp = continuation_ep.get('clickTrackingParams') | |
759 | return cls._build_api_continuation_query(continuation, ctp) | |
760 | ||
761 | @classmethod | |
762 | def _extract_continuation(cls, renderer): | |
763 | next_continuation = cls._extract_next_continuation_data(renderer) | |
764 | if next_continuation: | |
765 | return next_continuation | |
766 | ||
767 | return traverse_obj(renderer, ( | |
768 | ('contents', 'items', 'rows'), ..., 'continuationItemRenderer', | |
769 | ('continuationEndpoint', ('button', 'buttonRenderer', 'command')) | |
770 | ), get_all=False, expected_type=cls._extract_continuation_ep_data) | |
771 | ||
772 | @classmethod | |
773 | def _extract_alerts(cls, data): | |
774 | for alert_dict in try_get(data, lambda x: x['alerts'], list) or []: | |
775 | if not isinstance(alert_dict, dict): | |
776 | continue | |
777 | for alert in alert_dict.values(): | |
778 | alert_type = alert.get('type') | |
779 | if not alert_type: | |
780 | continue | |
781 | message = cls._get_text(alert, 'text') | |
782 | if message: | |
783 | yield alert_type, message | |
784 | ||
785 | def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False): | |
786 | errors, warnings = [], [] | |
787 | for alert_type, alert_message in alerts: | |
788 | if alert_type.lower() == 'error' and fatal: | |
789 | errors.append([alert_type, alert_message]) | |
790 | elif alert_message not in self._IGNORED_WARNINGS: | |
791 | warnings.append([alert_type, alert_message]) | |
792 | ||
793 | for alert_type, alert_message in (warnings + errors[:-1]): | |
794 | self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once) | |
795 | if errors: | |
796 | raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected) | |
797 | ||
798 | def _extract_and_report_alerts(self, data, *args, **kwargs): | |
799 | return self._report_alerts(self._extract_alerts(data), *args, **kwargs) | |
800 | ||
801 | def _extract_badges(self, badge_list: list): | |
802 | """ | |
803 | Extract known BadgeType's from a list of badge renderers. | |
804 | @returns [{'type': BadgeType}] | |
805 | """ | |
806 | icon_type_map = { | |
807 | 'PRIVACY_UNLISTED': BadgeType.AVAILABILITY_UNLISTED, | |
808 | 'PRIVACY_PRIVATE': BadgeType.AVAILABILITY_PRIVATE, | |
809 | 'PRIVACY_PUBLIC': BadgeType.AVAILABILITY_PUBLIC, | |
810 | 'CHECK_CIRCLE_THICK': BadgeType.VERIFIED, | |
811 | 'OFFICIAL_ARTIST_BADGE': BadgeType.VERIFIED, | |
812 | 'CHECK': BadgeType.VERIFIED, | |
813 | } | |
814 | ||
815 | badge_style_map = { | |
816 | 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType.AVAILABILITY_SUBSCRIPTION, | |
817 | 'BADGE_STYLE_TYPE_PREMIUM': BadgeType.AVAILABILITY_PREMIUM, | |
818 | 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType.LIVE_NOW, | |
819 | 'BADGE_STYLE_TYPE_VERIFIED': BadgeType.VERIFIED, | |
820 | 'BADGE_STYLE_TYPE_VERIFIED_ARTIST': BadgeType.VERIFIED, | |
821 | } | |
822 | ||
823 | label_map = { | |
824 | 'unlisted': BadgeType.AVAILABILITY_UNLISTED, | |
825 | 'private': BadgeType.AVAILABILITY_PRIVATE, | |
826 | 'members only': BadgeType.AVAILABILITY_SUBSCRIPTION, | |
827 | 'live': BadgeType.LIVE_NOW, | |
828 | 'premium': BadgeType.AVAILABILITY_PREMIUM, | |
829 | 'verified': BadgeType.VERIFIED, | |
830 | 'official artist channel': BadgeType.VERIFIED, | |
831 | } | |
832 | ||
833 | badges = [] | |
834 | for badge in traverse_obj(badge_list, (..., lambda key, _: re.search(r'[bB]adgeRenderer$', key))): | |
835 | badge_type = ( | |
836 | icon_type_map.get(traverse_obj(badge, ('icon', 'iconType'), expected_type=str)) | |
837 | or badge_style_map.get(traverse_obj(badge, 'style')) | |
838 | ) | |
839 | if badge_type: | |
840 | badges.append({'type': badge_type}) | |
841 | continue | |
842 | ||
843 | # fallback, won't work in some languages | |
844 | label = traverse_obj( | |
845 | badge, 'label', ('accessibilityData', 'label'), 'tooltip', 'iconTooltip', get_all=False, expected_type=str, default='') | |
846 | for match, label_badge_type in label_map.items(): | |
847 | if match in label.lower(): | |
848 | badges.append({'type': label_badge_type}) | |
849 | break | |
850 | ||
851 | return badges | |
852 | ||
853 | @staticmethod | |
854 | def _has_badge(badges, badge_type): | |
855 | return bool(traverse_obj(badges, lambda _, v: v['type'] == badge_type)) | |
856 | ||
857 | @staticmethod | |
858 | def _get_text(data, *path_list, max_runs=None): | |
859 | for path in path_list or [None]: | |
860 | if path is None: | |
861 | obj = [data] | |
862 | else: | |
863 | obj = traverse_obj(data, path, default=[]) | |
864 | if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)): | |
865 | obj = [obj] | |
866 | for item in obj: | |
867 | text = try_get(item, lambda x: x['simpleText'], str) | |
868 | if text: | |
869 | return text | |
870 | runs = try_get(item, lambda x: x['runs'], list) or [] | |
871 | if not runs and isinstance(item, list): | |
872 | runs = item | |
873 | ||
874 | runs = runs[:min(len(runs), max_runs or len(runs))] | |
875 | text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str)) | |
876 | if text: | |
877 | return text | |
878 | ||
879 | def _get_count(self, data, *path_list): | |
880 | count_text = self._get_text(data, *path_list) or '' | |
881 | count = parse_count(count_text) | |
882 | if count is None: | |
883 | count = str_to_int( | |
884 | self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None)) | |
885 | return count | |
886 | ||
887 | @staticmethod | |
888 | def _extract_thumbnails(data, *path_list): | |
889 | """ | |
890 | Extract thumbnails from thumbnails dict | |
891 | @param path_list: path list to level that contains 'thumbnails' key | |
892 | """ | |
893 | thumbnails = [] | |
894 | for path in path_list or [()]: | |
895 | for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...)): | |
896 | thumbnail_url = url_or_none(thumbnail.get('url')) | |
897 | if not thumbnail_url: | |
898 | continue | |
899 | # Sometimes youtube gives a wrong thumbnail URL. See: | |
900 | # https://github.com/yt-dlp/yt-dlp/issues/233 | |
901 | # https://github.com/ytdl-org/youtube-dl/issues/28023 | |
902 | if 'maxresdefault' in thumbnail_url: | |
903 | thumbnail_url = thumbnail_url.split('?')[0] | |
904 | thumbnails.append({ | |
905 | 'url': thumbnail_url, | |
906 | 'height': int_or_none(thumbnail.get('height')), | |
907 | 'width': int_or_none(thumbnail.get('width')), | |
908 | }) | |
909 | return thumbnails | |
910 | ||
911 | @staticmethod | |
912 | def extract_relative_time(relative_time_text): | |
913 | """ | |
914 | Extracts a relative time from string and converts to dt object | |
915 | e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today', '8 yr ago' | |
916 | """ | |
917 | ||
918 | # XXX: this could be moved to a general function in utils/_utils.py | |
919 | # The relative time text strings are roughly the same as what | |
920 | # Javascript's Intl.RelativeTimeFormat function generates. | |
921 | # See: https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Intl/RelativeTimeFormat | |
922 | mobj = re.search( | |
923 | r'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>sec(?:ond)?|s|min(?:ute)?|h(?:our|r)?|d(?:ay)?|w(?:eek|k)?|mo(?:nth)?|y(?:ear|r)?)s?\s*ago', | |
924 | relative_time_text) | |
925 | if mobj: | |
926 | start = mobj.group('start') | |
927 | if start: | |
928 | return datetime_from_str(start) | |
929 | try: | |
930 | return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit'))) | |
931 | except ValueError: | |
932 | return None | |
933 | ||
934 | def _parse_time_text(self, text): | |
935 | if not text: | |
936 | return | |
937 | dt_ = self.extract_relative_time(text) | |
938 | timestamp = None | |
939 | if isinstance(dt_, dt.datetime): | |
940 | timestamp = calendar.timegm(dt_.timetuple()) | |
941 | ||
942 | if timestamp is None: | |
943 | timestamp = ( | |
944 | unified_timestamp(text) or unified_timestamp( | |
945 | self._search_regex( | |
946 | (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'), | |
947 | text.lower(), 'time text', default=None))) | |
948 | ||
949 | if text and timestamp is None and self._preferred_lang in (None, 'en'): | |
950 | self.report_warning( | |
951 | f'Cannot parse localized time text "{text}"', only_once=True) | |
952 | return timestamp | |
953 | ||
954 | def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None, | |
955 | ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None, | |
956 | default_client='web'): | |
957 | raise_for_incomplete = bool(self._configuration_arg('raise_incomplete_data', ie_key=YoutubeIE)) | |
958 | # Incomplete Data should be a warning by default when retries are exhausted, while other errors should be fatal. | |
959 | icd_retries = iter(self.RetryManager(fatal=raise_for_incomplete)) | |
960 | icd_rm = next(icd_retries) | |
961 | main_retries = iter(self.RetryManager()) | |
962 | main_rm = next(main_retries) | |
963 | # Manual retry loop for multiple RetryManagers | |
964 | # The proper RetryManager MUST be advanced after an error | |
965 | # and its result MUST be checked if the manager is non fatal | |
966 | while True: | |
967 | try: | |
968 | response = self._call_api( | |
969 | ep=ep, fatal=True, headers=headers, | |
970 | video_id=item_id, query=query, note=note, | |
971 | context=self._extract_context(ytcfg, default_client), | |
972 | api_key=self._extract_api_key(ytcfg, default_client), | |
973 | api_hostname=api_hostname, default_client=default_client) | |
974 | except ExtractorError as e: | |
975 | if not isinstance(e.cause, network_exceptions): | |
976 | return self._error_or_warning(e, fatal=fatal) | |
977 | elif not isinstance(e.cause, HTTPError): | |
978 | main_rm.error = e | |
979 | next(main_retries) | |
980 | continue | |
981 | ||
982 | first_bytes = e.cause.response.read(512) | |
983 | if not is_html(first_bytes): | |
984 | yt_error = try_get( | |
985 | self._parse_json( | |
986 | self._webpage_read_content(e.cause.response, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False), | |
987 | lambda x: x['error']['message'], str) | |
988 | if yt_error: | |
989 | self._report_alerts([('ERROR', yt_error)], fatal=False) | |
990 | # Downloading page may result in intermittent 5xx HTTP error | |
991 | # Sometimes a 404 is also received. See: https://github.com/ytdl-org/youtube-dl/issues/28289 | |
992 | # We also want to catch all other network exceptions since errors in later pages can be troublesome | |
993 | # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210 | |
994 | if e.cause.status not in (403, 429): | |
995 | main_rm.error = e | |
996 | next(main_retries) | |
997 | continue | |
998 | return self._error_or_warning(e, fatal=fatal) | |
999 | ||
1000 | try: | |
1001 | self._extract_and_report_alerts(response, only_once=True) | |
1002 | except ExtractorError as e: | |
1003 | # YouTube's servers may return errors we want to retry on in a 200 OK response | |
1004 | # See: https://github.com/yt-dlp/yt-dlp/issues/839 | |
1005 | if 'unknown error' in e.msg.lower(): | |
1006 | main_rm.error = e | |
1007 | next(main_retries) | |
1008 | continue | |
1009 | return self._error_or_warning(e, fatal=fatal) | |
1010 | # Youtube sometimes sends incomplete data | |
1011 | # See: https://github.com/ytdl-org/youtube-dl/issues/28194 | |
1012 | if not traverse_obj(response, *variadic(check_get_keys)): | |
1013 | icd_rm.error = ExtractorError('Incomplete data received', expected=True) | |
1014 | should_retry = next(icd_retries, None) | |
1015 | if not should_retry: | |
1016 | return None | |
1017 | continue | |
1018 | ||
1019 | return response | |
1020 | ||
1021 | @staticmethod | |
1022 | def is_music_url(url): | |
1023 | return re.match(r'(https?://)?music\.youtube\.com/', url) is not None | |
1024 | ||
1025 | def _extract_video(self, renderer): | |
1026 | video_id = renderer.get('videoId') | |
1027 | ||
1028 | reel_header_renderer = traverse_obj(renderer, ( | |
1029 | 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer', | |
1030 | 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer')) | |
1031 | ||
1032 | title = self._get_text(renderer, 'title', 'headline') or self._get_text(reel_header_renderer, 'reelTitleText') | |
1033 | description = self._get_text(renderer, 'descriptionSnippet') | |
1034 | ||
1035 | duration = int_or_none(renderer.get('lengthSeconds')) | |
1036 | if duration is None: | |
1037 | duration = parse_duration(self._get_text( | |
1038 | renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text'))) | |
1039 | if duration is None: | |
1040 | # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab) | |
1041 | duration = parse_duration(self._search_regex( | |
1042 | r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$', | |
1043 | traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str), | |
1044 | video_id, default=None, group='duration')) | |
1045 | ||
1046 | channel_id = traverse_obj( | |
1047 | renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), | |
1048 | expected_type=str, get_all=False) | |
1049 | if not channel_id: | |
1050 | channel_id = traverse_obj(reel_header_renderer, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId')) | |
1051 | ||
1052 | channel_id = self.ucid_or_none(channel_id) | |
1053 | ||
1054 | overlay_style = traverse_obj( | |
1055 | renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), | |
1056 | get_all=False, expected_type=str) | |
1057 | badges = self._extract_badges(traverse_obj(renderer, 'badges')) | |
1058 | owner_badges = self._extract_badges(traverse_obj(renderer, 'ownerBadges')) | |
1059 | navigation_url = urljoin('https://www.youtube.com/', traverse_obj( | |
1060 | renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'), | |
1061 | expected_type=str)) or '' | |
1062 | url = f'https://www.youtube.com/watch?v={video_id}' | |
1063 | if overlay_style == 'SHORTS' or '/shorts/' in navigation_url: | |
1064 | url = f'https://www.youtube.com/shorts/{video_id}' | |
1065 | ||
1066 | time_text = (self._get_text(renderer, 'publishedTimeText', 'videoInfo') | |
1067 | or self._get_text(reel_header_renderer, 'timestampText') or '') | |
1068 | scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False)) | |
1069 | ||
1070 | live_status = ( | |
1071 | 'is_upcoming' if scheduled_timestamp is not None | |
1072 | else 'was_live' if 'streamed' in time_text.lower() | |
1073 | else 'is_live' if overlay_style == 'LIVE' or self._has_badge(badges, BadgeType.LIVE_NOW) | |
1074 | else None) | |
1075 | ||
1076 | # videoInfo is a string like '50K views • 10 years ago'. | |
1077 | view_count_text = self._get_text(renderer, 'viewCountText', 'shortViewCountText', 'videoInfo') or '' | |
1078 | view_count = (0 if 'no views' in view_count_text.lower() | |
1079 | else self._get_count({'simpleText': view_count_text})) | |
1080 | view_count_field = 'concurrent_view_count' if live_status in ('is_live', 'is_upcoming') else 'view_count' | |
1081 | ||
1082 | channel = (self._get_text(renderer, 'ownerText', 'shortBylineText') | |
1083 | or self._get_text(reel_header_renderer, 'channelTitleText')) | |
1084 | ||
1085 | channel_handle = traverse_obj(renderer, ( | |
1086 | 'shortBylineText', 'runs', ..., 'navigationEndpoint', | |
1087 | (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl'))), | |
1088 | expected_type=self.handle_from_url, get_all=False) | |
1089 | return { | |
1090 | '_type': 'url', | |
1091 | 'ie_key': YoutubeIE.ie_key(), | |
1092 | 'id': video_id, | |
1093 | 'url': url, | |
1094 | 'title': title, | |
1095 | 'description': description, | |
1096 | 'duration': duration, | |
1097 | 'channel_id': channel_id, | |
1098 | 'channel': channel, | |
1099 | 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None, | |
1100 | 'uploader': channel, | |
1101 | 'uploader_id': channel_handle, | |
1102 | 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None), | |
1103 | 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'), | |
1104 | 'timestamp': (self._parse_time_text(time_text) | |
1105 | if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE) | |
1106 | else None), | |
1107 | 'release_timestamp': scheduled_timestamp, | |
1108 | 'availability': | |
1109 | 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC) | |
1110 | else self._availability( | |
1111 | is_private=self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) or None, | |
1112 | needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None, | |
1113 | needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None, | |
1114 | is_unlisted=self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) or None), | |
1115 | view_count_field: view_count, | |
1116 | 'live_status': live_status, | |
1117 | 'channel_is_verified': True if self._has_badge(owner_badges, BadgeType.VERIFIED) else None | |
1118 | } | |
1119 | ||
1120 | ||
1121 | class YoutubeIE(YoutubeBaseInfoExtractor): | |
1122 | IE_DESC = 'YouTube' | |
1123 | _VALID_URL = r"""(?x)^ | |
1124 | ( | |
1125 | (?:https?://|//) # http(s):// or protocol-independent URL | |
1126 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com| | |
1127 | (?:www\.)?deturl\.com/www\.youtube\.com| | |
1128 | (?:www\.)?pwnyoutube\.com| | |
1129 | (?:www\.)?hooktube\.com| | |
1130 | (?:www\.)?yourepeat\.com| | |
1131 | tube\.majestyc\.net| | |
1132 | %(invidious)s| | |
1133 | youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains | |
1134 | (?:.*?\#/)? # handle anchor (#/) redirect urls | |
1135 | (?: # the various things that can precede the ID: | |
1136 | (?:(?:v|embed|e|shorts|live)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/ | |
1137 | |(?: # or the v= param in all its forms | |
1138 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) | |
1139 | (?:\?|\#!?) # the params delimiter ? or # or #! | |
1140 | (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY) | |
1141 | v= | |
1142 | ) | |
1143 | )) | |
1144 | |(?: | |
1145 | youtu\.be| # just youtu.be/xxxx | |
1146 | vid\.plus| # or vid.plus/xxxx | |
1147 | zwearz\.com/watch| # or zwearz.com/watch/xxxx | |
1148 | %(invidious)s | |
1149 | )/ | |
1150 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= | |
1151 | ) | |
1152 | )? # all until now is optional -> you can pass the naked ID | |
1153 | (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID | |
1154 | (?(1).+)? # if we found the ID, everything can follow | |
1155 | (?:\#|$)""" % { | |
1156 | 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), | |
1157 | } | |
1158 | _EMBED_REGEX = [ | |
1159 | r'''(?x) | |
1160 | (?: | |
1161 | <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=| | |
1162 | data-video-url=| | |
1163 | <embed[^>]+?src=| | |
1164 | embedSWF\(?:\s*| | |
1165 | <object[^>]+data=| | |
1166 | new\s+SWFObject\( | |
1167 | ) | |
1168 | (["\']) | |
1169 | (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ | |
1170 | (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?) | |
1171 | \1''', | |
1172 | # https://wordpress.org/plugins/lazy-load-for-videos/ | |
1173 | r'''(?xs) | |
1174 | <a\s[^>]*\bhref="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})" | |
1175 | \s[^>]*\bclass="[^"]*\blazy-load-youtube''', | |
1176 | ] | |
1177 | _RETURN_TYPE = 'video' # XXX: How to handle multifeed? | |
1178 | ||
1179 | _PLAYER_INFO_RE = ( | |
1180 | r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player', | |
1181 | r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$', | |
1182 | r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$', | |
1183 | ) | |
1184 | _formats = { # NB: Used in YoutubeWebArchiveIE and GoogleDriveIE | |
1185 | '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
1186 | '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
1187 | '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
1188 | '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}, | |
1189 | '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}, | |
1190 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
1191 | '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
1192 | '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
1193 | # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well | |
1194 | '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
1195 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
1196 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
1197 | '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
1198 | '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
1199 | '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
1200 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
1201 | '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
1202 | '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
1203 | ||
1204 | ||
1205 | # 3D videos | |
1206 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
1207 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
1208 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
1209 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
1210 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}, | |
1211 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
1212 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
1213 | ||
1214 | # Apple HTTP Live Streaming | |
1215 | '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, | |
1216 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, | |
1217 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
1218 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
1219 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
1220 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
1221 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, | |
1222 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}, | |
1223 | ||
1224 | # DASH mp4 video | |
1225 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1226 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1227 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1228 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1229 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1230 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559) | |
1231 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1232 | '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1233 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1234 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
1235 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
1236 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
1237 | ||
1238 | # Dash mp4 audio | |
1239 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}, | |
1240 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}, | |
1241 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}, | |
1242 | '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
1243 | '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
1244 | '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}, | |
1245 | '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}, | |
1246 | ||
1247 | # Dash webm | |
1248 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1249 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1250 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1251 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1252 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1253 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1254 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}, | |
1255 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1256 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1257 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1258 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1259 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1260 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1261 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1262 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1263 | # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug) | |
1264 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1265 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
1266 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
1267 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
1268 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1269 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
1270 | ||
1271 | # Dash webm audio | |
1272 | '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}, | |
1273 | '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}, | |
1274 | ||
1275 | # Dash webm audio with opus inside | |
1276 | '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}, | |
1277 | '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}, | |
1278 | '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}, | |
1279 | ||
1280 | # RTMP (unnamed) | |
1281 | '_rtmp': {'protocol': 'rtmp'}, | |
1282 | ||
1283 | # av01 video only formats sometimes served with "unknown" codecs | |
1284 | '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}, | |
1285 | '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}, | |
1286 | '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'}, | |
1287 | '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'}, | |
1288 | '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'}, | |
1289 | '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'}, | |
1290 | '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}, | |
1291 | '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}, | |
1292 | } | |
1293 | _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt') | |
1294 | ||
1295 | _GEO_BYPASS = False | |
1296 | ||
1297 | IE_NAME = 'youtube' | |
1298 | _TESTS = [ | |
1299 | { | |
1300 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9', | |
1301 | 'info_dict': { | |
1302 | 'id': 'BaW_jenozKc', | |
1303 | 'ext': 'mp4', | |
1304 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
1305 | 'channel': 'Philipp Hagemeister', | |
1306 | 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', | |
1307 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', | |
1308 | 'upload_date': '20121002', | |
1309 | 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22', | |
1310 | 'categories': ['Science & Technology'], | |
1311 | 'tags': ['youtube-dl'], | |
1312 | 'duration': 10, | |
1313 | 'view_count': int, | |
1314 | 'like_count': int, | |
1315 | 'availability': 'public', | |
1316 | 'playable_in_embed': True, | |
1317 | 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg', | |
1318 | 'live_status': 'not_live', | |
1319 | 'age_limit': 0, | |
1320 | 'start_time': 1, | |
1321 | 'end_time': 9, | |
1322 | 'comment_count': int, | |
1323 | 'channel_follower_count': int, | |
1324 | 'uploader': 'Philipp Hagemeister', | |
1325 | 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister', | |
1326 | 'uploader_id': '@PhilippHagemeister', | |
1327 | 'heatmap': 'count:100', | |
1328 | } | |
1329 | }, | |
1330 | { | |
1331 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', | |
1332 | 'note': 'Embed-only video (#1746)', | |
1333 | 'info_dict': { | |
1334 | 'id': 'yZIXLfi8CZQ', | |
1335 | 'ext': 'mp4', | |
1336 | 'upload_date': '20120608', | |
1337 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
1338 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
1339 | 'age_limit': 18, | |
1340 | }, | |
1341 | 'skip': 'Private video', | |
1342 | }, | |
1343 | { | |
1344 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ', | |
1345 | 'note': 'Use the first video ID in the URL', | |
1346 | 'info_dict': { | |
1347 | 'id': 'BaW_jenozKc', | |
1348 | 'ext': 'mp4', | |
1349 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
1350 | 'channel': 'Philipp Hagemeister', | |
1351 | 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', | |
1352 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', | |
1353 | 'upload_date': '20121002', | |
1354 | 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22', | |
1355 | 'categories': ['Science & Technology'], | |
1356 | 'tags': ['youtube-dl'], | |
1357 | 'duration': 10, | |
1358 | 'view_count': int, | |
1359 | 'like_count': int, | |
1360 | 'availability': 'public', | |
1361 | 'playable_in_embed': True, | |
1362 | 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg', | |
1363 | 'live_status': 'not_live', | |
1364 | 'age_limit': 0, | |
1365 | 'comment_count': int, | |
1366 | 'channel_follower_count': int, | |
1367 | 'uploader': 'Philipp Hagemeister', | |
1368 | 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister', | |
1369 | 'uploader_id': '@PhilippHagemeister', | |
1370 | 'heatmap': 'count:100', | |
1371 | }, | |
1372 | 'params': { | |
1373 | 'skip_download': True, | |
1374 | }, | |
1375 | }, | |
1376 | { | |
1377 | 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I', | |
1378 | 'note': '256k DASH audio (format 141) via DASH manifest', | |
1379 | 'info_dict': { | |
1380 | 'id': 'a9LDPn-MO4I', | |
1381 | 'ext': 'm4a', | |
1382 | 'upload_date': '20121002', | |
1383 | 'description': '', | |
1384 | 'title': 'UHDTV TEST 8K VIDEO.mp4' | |
1385 | }, | |
1386 | 'params': { | |
1387 | 'youtube_include_dash_manifest': True, | |
1388 | 'format': '141', | |
1389 | }, | |
1390 | 'skip': 'format 141 not served anymore', | |
1391 | }, | |
1392 | # DASH manifest with encrypted signature | |
1393 | { | |
1394 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', | |
1395 | 'info_dict': { | |
1396 | 'id': 'IB3lcPjvWLA', | |
1397 | 'ext': 'm4a', | |
1398 | 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson', | |
1399 | 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf', | |
1400 | 'duration': 244, | |
1401 | 'upload_date': '20131011', | |
1402 | 'abr': 129.495, | |
1403 | 'like_count': int, | |
1404 | 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg', | |
1405 | 'playable_in_embed': True, | |
1406 | 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg', | |
1407 | 'view_count': int, | |
1408 | 'track': 'The Spark', | |
1409 | 'live_status': 'not_live', | |
1410 | 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp', | |
1411 | 'channel': 'Afrojack', | |
1412 | 'tags': 'count:19', | |
1413 | 'availability': 'public', | |
1414 | 'categories': ['Music'], | |
1415 | 'age_limit': 0, | |
1416 | 'alt_title': 'The Spark', | |
1417 | 'channel_follower_count': int, | |
1418 | 'uploader': 'Afrojack', | |
1419 | 'uploader_url': 'https://www.youtube.com/@Afrojack', | |
1420 | 'uploader_id': '@Afrojack', | |
1421 | }, | |
1422 | 'params': { | |
1423 | 'youtube_include_dash_manifest': True, | |
1424 | 'format': '141/bestaudio[ext=m4a]', | |
1425 | }, | |
1426 | }, | |
1427 | # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000 | |
1428 | { | |
1429 | 'note': 'Embed allowed age-gate video', | |
1430 | 'url': 'https://youtube.com/watch?v=HtVdAasjOgU', | |
1431 | 'info_dict': { | |
1432 | 'id': 'HtVdAasjOgU', | |
1433 | 'ext': 'mp4', | |
1434 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
1435 | 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', | |
1436 | 'duration': 142, | |
1437 | 'upload_date': '20140605', | |
1438 | 'age_limit': 18, | |
1439 | 'categories': ['Gaming'], | |
1440 | 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp', | |
1441 | 'availability': 'needs_auth', | |
1442 | 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg', | |
1443 | 'like_count': int, | |
1444 | 'channel': 'The Witcher', | |
1445 | 'live_status': 'not_live', | |
1446 | 'tags': 'count:17', | |
1447 | 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg', | |
1448 | 'playable_in_embed': True, | |
1449 | 'view_count': int, | |
1450 | 'channel_follower_count': int, | |
1451 | 'uploader': 'The Witcher', | |
1452 | 'uploader_url': 'https://www.youtube.com/@thewitcher', | |
1453 | 'uploader_id': '@thewitcher', | |
1454 | 'comment_count': int, | |
1455 | 'channel_is_verified': True, | |
1456 | 'heatmap': 'count:100', | |
1457 | }, | |
1458 | }, | |
1459 | { | |
1460 | 'note': 'Age-gate video with embed allowed in public site', | |
1461 | 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U', | |
1462 | 'info_dict': { | |
1463 | 'id': 'HsUATh_Nc2U', | |
1464 | 'ext': 'mp4', | |
1465 | 'title': 'Godzilla 2 (Official Video)', | |
1466 | 'description': 'md5:bf77e03fcae5529475e500129b05668a', | |
1467 | 'upload_date': '20200408', | |
1468 | 'age_limit': 18, | |
1469 | 'availability': 'needs_auth', | |
1470 | 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg', | |
1471 | 'channel': 'FlyingKitty', | |
1472 | 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg', | |
1473 | 'view_count': int, | |
1474 | 'categories': ['Entertainment'], | |
1475 | 'live_status': 'not_live', | |
1476 | 'tags': ['Flyingkitty', 'godzilla 2'], | |
1477 | 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg', | |
1478 | 'like_count': int, | |
1479 | 'duration': 177, | |
1480 | 'playable_in_embed': True, | |
1481 | 'channel_follower_count': int, | |
1482 | 'uploader': 'FlyingKitty', | |
1483 | 'uploader_url': 'https://www.youtube.com/@FlyingKitty900', | |
1484 | 'uploader_id': '@FlyingKitty900', | |
1485 | 'comment_count': int, | |
1486 | 'channel_is_verified': True, | |
1487 | }, | |
1488 | }, | |
1489 | { | |
1490 | 'note': 'Age-gate video embedable only with clientScreen=EMBED', | |
1491 | 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg', | |
1492 | 'info_dict': { | |
1493 | 'id': 'Tq92D6wQ1mg', | |
1494 | 'title': '[MMD] Adios - EVERGLOW [+Motion DL]', | |
1495 | 'ext': 'mp4', | |
1496 | 'upload_date': '20191228', | |
1497 | 'description': 'md5:17eccca93a786d51bc67646756894066', | |
1498 | 'age_limit': 18, | |
1499 | 'like_count': int, | |
1500 | 'availability': 'needs_auth', | |
1501 | 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ', | |
1502 | 'view_count': int, | |
1503 | 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp', | |
1504 | 'channel': 'Projekt Melody', | |
1505 | 'live_status': 'not_live', | |
1506 | 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'], | |
1507 | 'playable_in_embed': True, | |
1508 | 'categories': ['Entertainment'], | |
1509 | 'duration': 106, | |
1510 | 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ', | |
1511 | 'comment_count': int, | |
1512 | 'channel_follower_count': int, | |
1513 | 'uploader': 'Projekt Melody', | |
1514 | 'uploader_url': 'https://www.youtube.com/@ProjektMelody', | |
1515 | 'uploader_id': '@ProjektMelody', | |
1516 | }, | |
1517 | }, | |
1518 | { | |
1519 | 'note': 'Non-Agegated non-embeddable video', | |
1520 | 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY', | |
1521 | 'info_dict': { | |
1522 | 'id': 'MeJVWBSsPAY', | |
1523 | 'ext': 'mp4', | |
1524 | 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)', | |
1525 | 'description': 'Fan Video. Music & Lyrics by OOMPH!.', | |
1526 | 'upload_date': '20130730', | |
1527 | 'track': 'Such mich find mich', | |
1528 | 'age_limit': 0, | |
1529 | 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'], | |
1530 | 'like_count': int, | |
1531 | 'playable_in_embed': False, | |
1532 | 'creator': 'OOMPH!', | |
1533 | 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg', | |
1534 | 'view_count': int, | |
1535 | 'alt_title': 'Such mich find mich', | |
1536 | 'duration': 210, | |
1537 | 'channel': 'Herr Lurik', | |
1538 | 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA', | |
1539 | 'categories': ['Music'], | |
1540 | 'availability': 'public', | |
1541 | 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA', | |
1542 | 'live_status': 'not_live', | |
1543 | 'artist': 'OOMPH!', | |
1544 | 'channel_follower_count': int, | |
1545 | 'uploader': 'Herr Lurik', | |
1546 | 'uploader_url': 'https://www.youtube.com/@HerrLurik', | |
1547 | 'uploader_id': '@HerrLurik', | |
1548 | }, | |
1549 | }, | |
1550 | { | |
1551 | 'note': 'Non-bypassable age-gated video', | |
1552 | 'url': 'https://youtube.com/watch?v=Cr381pDsSsA', | |
1553 | 'only_matching': True, | |
1554 | }, | |
1555 | # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421) | |
1556 | # YouTube Red ad is not captured for creator | |
1557 | { | |
1558 | 'url': '__2ABJjxzNo', | |
1559 | 'info_dict': { | |
1560 | 'id': '__2ABJjxzNo', | |
1561 | 'ext': 'mp4', | |
1562 | 'duration': 266, | |
1563 | 'upload_date': '20100430', | |
1564 | 'creator': 'deadmau5', | |
1565 | 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336', | |
1566 | 'title': 'Deadmau5 - Some Chords (HD)', | |
1567 | 'alt_title': 'Some Chords', | |
1568 | 'availability': 'public', | |
1569 | 'tags': 'count:14', | |
1570 | 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ', | |
1571 | 'view_count': int, | |
1572 | 'live_status': 'not_live', | |
1573 | 'channel': 'deadmau5', | |
1574 | 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp', | |
1575 | 'like_count': int, | |
1576 | 'track': 'Some Chords', | |
1577 | 'artist': 'deadmau5', | |
1578 | 'playable_in_embed': True, | |
1579 | 'age_limit': 0, | |
1580 | 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ', | |
1581 | 'categories': ['Music'], | |
1582 | 'album': 'Some Chords', | |
1583 | 'channel_follower_count': int, | |
1584 | 'uploader': 'deadmau5', | |
1585 | 'uploader_url': 'https://www.youtube.com/@deadmau5', | |
1586 | 'uploader_id': '@deadmau5', | |
1587 | }, | |
1588 | 'expected_warnings': [ | |
1589 | 'DASH manifest missing', | |
1590 | ] | |
1591 | }, | |
1592 | # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431) | |
1593 | { | |
1594 | 'url': 'lqQg6PlCWgI', | |
1595 | 'info_dict': { | |
1596 | 'id': 'lqQg6PlCWgI', | |
1597 | 'ext': 'mp4', | |
1598 | 'duration': 6085, | |
1599 | 'upload_date': '20150827', | |
1600 | 'description': 'md5:04bbbf3ccceb6795947572ca36f45904', | |
1601 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', | |
1602 | 'like_count': int, | |
1603 | 'release_timestamp': 1343767800, | |
1604 | 'playable_in_embed': True, | |
1605 | 'categories': ['Sports'], | |
1606 | 'release_date': '20120731', | |
1607 | 'channel': 'Olympics', | |
1608 | 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'], | |
1609 | 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q', | |
1610 | 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg', | |
1611 | 'age_limit': 0, | |
1612 | 'availability': 'public', | |
1613 | 'live_status': 'was_live', | |
1614 | 'view_count': int, | |
1615 | 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q', | |
1616 | 'channel_follower_count': int, | |
1617 | 'uploader': 'Olympics', | |
1618 | 'uploader_url': 'https://www.youtube.com/@Olympics', | |
1619 | 'uploader_id': '@Olympics', | |
1620 | 'channel_is_verified': True, | |
1621 | }, | |
1622 | 'params': { | |
1623 | 'skip_download': 'requires avconv', | |
1624 | } | |
1625 | }, | |
1626 | # Non-square pixels | |
1627 | { | |
1628 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
1629 | 'info_dict': { | |
1630 | 'id': '_b-2C3KPAM0', | |
1631 | 'ext': 'mp4', | |
1632 | 'stretched_ratio': 16 / 9., | |
1633 | 'duration': 85, | |
1634 | 'upload_date': '20110310', | |
1635 | 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯', | |
1636 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', | |
1637 | 'playable_in_embed': True, | |
1638 | 'channel': '孫ᄋᄅ', | |
1639 | 'age_limit': 0, | |
1640 | 'tags': 'count:11', | |
1641 | 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw', | |
1642 | 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw', | |
1643 | 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg', | |
1644 | 'view_count': int, | |
1645 | 'categories': ['People & Blogs'], | |
1646 | 'like_count': int, | |
1647 | 'live_status': 'not_live', | |
1648 | 'availability': 'unlisted', | |
1649 | 'comment_count': int, | |
1650 | 'channel_follower_count': int, | |
1651 | 'uploader': '孫ᄋᄅ', | |
1652 | 'uploader_url': 'https://www.youtube.com/@AllenMeow', | |
1653 | 'uploader_id': '@AllenMeow', | |
1654 | }, | |
1655 | }, | |
1656 | # url_encoded_fmt_stream_map is empty string | |
1657 | { | |
1658 | 'url': 'qEJwOuvDf7I', | |
1659 | 'info_dict': { | |
1660 | 'id': 'qEJwOuvDf7I', | |
1661 | 'ext': 'webm', | |
1662 | 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', | |
1663 | 'description': '', | |
1664 | 'upload_date': '20150404', | |
1665 | }, | |
1666 | 'params': { | |
1667 | 'skip_download': 'requires avconv', | |
1668 | }, | |
1669 | 'skip': 'This live event has ended.', | |
1670 | }, | |
1671 | # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097) | |
1672 | { | |
1673 | 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y', | |
1674 | 'info_dict': { | |
1675 | 'id': 'FIl7x6_3R5Y', | |
1676 | 'ext': 'webm', | |
1677 | 'title': 'md5:7b81415841e02ecd4313668cde88737a', | |
1678 | 'description': 'md5:116377fd2963b81ec4ce64b542173306', | |
1679 | 'duration': 220, | |
1680 | 'upload_date': '20150625', | |
1681 | 'formats': 'mincount:31', | |
1682 | }, | |
1683 | 'skip': 'not actual anymore', | |
1684 | }, | |
1685 | # DASH manifest with segment_list | |
1686 | { | |
1687 | 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8', | |
1688 | 'md5': '8ce563a1d667b599d21064e982ab9e31', | |
1689 | 'info_dict': { | |
1690 | 'id': 'CsmdDsKjzN8', | |
1691 | 'ext': 'mp4', | |
1692 | 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510 | |
1693 | 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', | |
1694 | 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', | |
1695 | }, | |
1696 | 'params': { | |
1697 | 'youtube_include_dash_manifest': True, | |
1698 | 'format': '135', # bestvideo | |
1699 | }, | |
1700 | 'skip': 'This live event has ended.', | |
1701 | }, | |
1702 | { | |
1703 | # Multifeed videos (multiple cameras), URL can be of any Camera | |
1704 | # TODO: fix multifeed titles | |
1705 | 'url': 'https://www.youtube.com/watch?v=zaPI8MvL8pg', | |
1706 | 'info_dict': { | |
1707 | 'id': 'zaPI8MvL8pg', | |
1708 | 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04', | |
1709 | 'description': 'md5:563ccbc698b39298481ca3c571169519', | |
1710 | }, | |
1711 | 'playlist': [{ | |
1712 | 'info_dict': { | |
1713 | 'id': 'j5yGuxZ8lLU', | |
1714 | 'ext': 'mp4', | |
1715 | 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Chris)', | |
1716 | 'description': 'md5:563ccbc698b39298481ca3c571169519', | |
1717 | 'duration': 10120, | |
1718 | 'channel_follower_count': int, | |
1719 | 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg', | |
1720 | 'availability': 'public', | |
1721 | 'playable_in_embed': True, | |
1722 | 'upload_date': '20131105', | |
1723 | 'categories': ['Gaming'], | |
1724 | 'live_status': 'was_live', | |
1725 | 'tags': 'count:24', | |
1726 | 'release_timestamp': 1383701910, | |
1727 | 'thumbnail': 'https://i.ytimg.com/vi/j5yGuxZ8lLU/maxresdefault.jpg', | |
1728 | 'comment_count': int, | |
1729 | 'age_limit': 0, | |
1730 | 'like_count': int, | |
1731 | 'channel_id': 'UCN2XePorRokPB9TEgRZpddg', | |
1732 | 'channel': 'WiiLikeToPlay', | |
1733 | 'view_count': int, | |
1734 | 'release_date': '20131106', | |
1735 | 'uploader': 'WiiLikeToPlay', | |
1736 | 'uploader_id': '@WLTP', | |
1737 | 'uploader_url': 'https://www.youtube.com/@WLTP', | |
1738 | }, | |
1739 | }, { | |
1740 | 'info_dict': { | |
1741 | 'id': 'zaPI8MvL8pg', | |
1742 | 'ext': 'mp4', | |
1743 | 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Tyson)', | |
1744 | 'availability': 'public', | |
1745 | 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg', | |
1746 | 'channel': 'WiiLikeToPlay', | |
1747 | 'channel_follower_count': int, | |
1748 | 'description': 'md5:563ccbc698b39298481ca3c571169519', | |
1749 | 'duration': 10108, | |
1750 | 'age_limit': 0, | |
1751 | 'like_count': int, | |
1752 | 'tags': 'count:24', | |
1753 | 'channel_id': 'UCN2XePorRokPB9TEgRZpddg', | |
1754 | 'release_timestamp': 1383701915, | |
1755 | 'comment_count': int, | |
1756 | 'upload_date': '20131105', | |
1757 | 'thumbnail': 'https://i.ytimg.com/vi/zaPI8MvL8pg/maxresdefault.jpg', | |
1758 | 'release_date': '20131106', | |
1759 | 'playable_in_embed': True, | |
1760 | 'live_status': 'was_live', | |
1761 | 'categories': ['Gaming'], | |
1762 | 'view_count': int, | |
1763 | 'uploader': 'WiiLikeToPlay', | |
1764 | 'uploader_id': '@WLTP', | |
1765 | 'uploader_url': 'https://www.youtube.com/@WLTP', | |
1766 | }, | |
1767 | }, { | |
1768 | 'info_dict': { | |
1769 | 'id': 'R7r3vfO7Hao', | |
1770 | 'ext': 'mp4', | |
1771 | 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Spencer)', | |
1772 | 'thumbnail': 'https://i.ytimg.com/vi/R7r3vfO7Hao/maxresdefault.jpg', | |
1773 | 'channel_id': 'UCN2XePorRokPB9TEgRZpddg', | |
1774 | 'like_count': int, | |
1775 | 'availability': 'public', | |
1776 | 'playable_in_embed': True, | |
1777 | 'upload_date': '20131105', | |
1778 | 'description': 'md5:563ccbc698b39298481ca3c571169519', | |
1779 | 'channel_follower_count': int, | |
1780 | 'tags': 'count:24', | |
1781 | 'release_date': '20131106', | |
1782 | 'comment_count': int, | |
1783 | 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg', | |
1784 | 'channel': 'WiiLikeToPlay', | |
1785 | 'categories': ['Gaming'], | |
1786 | 'release_timestamp': 1383701914, | |
1787 | 'live_status': 'was_live', | |
1788 | 'age_limit': 0, | |
1789 | 'duration': 10128, | |
1790 | 'view_count': int, | |
1791 | 'uploader': 'WiiLikeToPlay', | |
1792 | 'uploader_id': '@WLTP', | |
1793 | 'uploader_url': 'https://www.youtube.com/@WLTP', | |
1794 | }, | |
1795 | }], | |
1796 | 'params': {'skip_download': True}, | |
1797 | }, | |
1798 | { | |
1799 | # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536) | |
1800 | 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo', | |
1801 | 'info_dict': { | |
1802 | 'id': 'gVfLd0zydlo', | |
1803 | 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30', | |
1804 | }, | |
1805 | 'playlist_count': 2, | |
1806 | 'skip': 'Not multifeed anymore', | |
1807 | }, | |
1808 | { | |
1809 | 'url': 'https://vid.plus/FlRa-iH7PGw', | |
1810 | 'only_matching': True, | |
1811 | }, | |
1812 | { | |
1813 | 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html', | |
1814 | 'only_matching': True, | |
1815 | }, | |
1816 | { | |
1817 | # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468) | |
1818 | # Also tests cut-off URL expansion in video description (see | |
1819 | # https://github.com/ytdl-org/youtube-dl/issues/1892, | |
1820 | # https://github.com/ytdl-org/youtube-dl/issues/8164) | |
1821 | 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg', | |
1822 | 'info_dict': { | |
1823 | 'id': 'lsguqyKfVQg', | |
1824 | 'ext': 'mp4', | |
1825 | 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21', | |
1826 | 'alt_title': 'Dark Walk', | |
1827 | 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a', | |
1828 | 'duration': 133, | |
1829 | 'upload_date': '20151119', | |
1830 | 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan', | |
1831 | 'track': 'Dark Walk', | |
1832 | 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan', | |
1833 | 'album': 'Position Music - Production Music Vol. 143 - Dark Walk', | |
1834 | 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp', | |
1835 | 'categories': ['Film & Animation'], | |
1836 | 'view_count': int, | |
1837 | 'live_status': 'not_live', | |
1838 | 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ', | |
1839 | 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ', | |
1840 | 'tags': 'count:13', | |
1841 | 'availability': 'public', | |
1842 | 'channel': 'IronSoulElf', | |
1843 | 'playable_in_embed': True, | |
1844 | 'like_count': int, | |
1845 | 'age_limit': 0, | |
1846 | 'channel_follower_count': int | |
1847 | }, | |
1848 | 'params': { | |
1849 | 'skip_download': True, | |
1850 | }, | |
1851 | }, | |
1852 | { | |
1853 | # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468) | |
1854 | 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8', | |
1855 | 'only_matching': True, | |
1856 | }, | |
1857 | { | |
1858 | # Video with yt:stretch=17:0 | |
1859 | 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM', | |
1860 | 'info_dict': { | |
1861 | 'id': 'Q39EVAstoRM', | |
1862 | 'ext': 'mp4', | |
1863 | 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4', | |
1864 | 'description': 'md5:ee18a25c350637c8faff806845bddee9', | |
1865 | 'upload_date': '20151107', | |
1866 | }, | |
1867 | 'params': { | |
1868 | 'skip_download': True, | |
1869 | }, | |
1870 | 'skip': 'This video does not exist.', | |
1871 | }, | |
1872 | { | |
1873 | # Video with incomplete 'yt:stretch=16:' | |
1874 | 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI', | |
1875 | 'only_matching': True, | |
1876 | }, | |
1877 | { | |
1878 | # Video licensed under Creative Commons | |
1879 | 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA', | |
1880 | 'info_dict': { | |
1881 | 'id': 'M4gD1WSo5mA', | |
1882 | 'ext': 'mp4', | |
1883 | 'title': 'md5:e41008789470fc2533a3252216f1c1d1', | |
1884 | 'description': 'md5:a677553cf0840649b731a3024aeff4cc', | |
1885 | 'duration': 721, | |
1886 | 'upload_date': '20150128', | |
1887 | 'license': 'Creative Commons Attribution license (reuse allowed)', | |
1888 | 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA', | |
1889 | 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA', | |
1890 | 'like_count': int, | |
1891 | 'age_limit': 0, | |
1892 | 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'], | |
1893 | 'channel': 'The Berkman Klein Center for Internet & Society', | |
1894 | 'availability': 'public', | |
1895 | 'view_count': int, | |
1896 | 'categories': ['Education'], | |
1897 | 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp', | |
1898 | 'live_status': 'not_live', | |
1899 | 'playable_in_embed': True, | |
1900 | 'channel_follower_count': int, | |
1901 | 'chapters': list, | |
1902 | 'uploader': 'The Berkman Klein Center for Internet & Society', | |
1903 | 'uploader_id': '@BKCHarvard', | |
1904 | 'uploader_url': 'https://www.youtube.com/@BKCHarvard', | |
1905 | }, | |
1906 | 'params': { | |
1907 | 'skip_download': True, | |
1908 | }, | |
1909 | }, | |
1910 | { | |
1911 | 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg', | |
1912 | 'info_dict': { | |
1913 | 'id': 'eQcmzGIKrzg', | |
1914 | 'ext': 'mp4', | |
1915 | 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders', | |
1916 | 'description': 'md5:13a2503d7b5904ef4b223aa101628f39', | |
1917 | 'duration': 4060, | |
1918 | 'upload_date': '20151120', | |
1919 | 'license': 'Creative Commons Attribution license (reuse allowed)', | |
1920 | 'playable_in_embed': True, | |
1921 | 'tags': 'count:12', | |
1922 | 'like_count': int, | |
1923 | 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg', | |
1924 | 'age_limit': 0, | |
1925 | 'availability': 'public', | |
1926 | 'categories': ['News & Politics'], | |
1927 | 'channel': 'Bernie Sanders', | |
1928 | 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp', | |
1929 | 'view_count': int, | |
1930 | 'live_status': 'not_live', | |
1931 | 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg', | |
1932 | 'comment_count': int, | |
1933 | 'channel_follower_count': int, | |
1934 | 'chapters': list, | |
1935 | 'uploader': 'Bernie Sanders', | |
1936 | 'uploader_url': 'https://www.youtube.com/@BernieSanders', | |
1937 | 'uploader_id': '@BernieSanders', | |
1938 | 'channel_is_verified': True, | |
1939 | 'heatmap': 'count:100', | |
1940 | }, | |
1941 | 'params': { | |
1942 | 'skip_download': True, | |
1943 | }, | |
1944 | }, | |
1945 | { | |
1946 | 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY', | |
1947 | 'only_matching': True, | |
1948 | }, | |
1949 | { | |
1950 | # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059) | |
1951 | 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo', | |
1952 | 'only_matching': True, | |
1953 | }, | |
1954 | { | |
1955 | # Rental video preview | |
1956 | 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg', | |
1957 | 'info_dict': { | |
1958 | 'id': 'uGpuVWrhIzE', | |
1959 | 'ext': 'mp4', | |
1960 | 'title': 'Piku - Trailer', | |
1961 | 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb', | |
1962 | 'upload_date': '20150811', | |
1963 | 'license': 'Standard YouTube License', | |
1964 | }, | |
1965 | 'params': { | |
1966 | 'skip_download': True, | |
1967 | }, | |
1968 | 'skip': 'This video is not available.', | |
1969 | }, | |
1970 | { | |
1971 | # YouTube Red video with episode data | |
1972 | 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4', | |
1973 | 'info_dict': { | |
1974 | 'id': 'iqKdEhx-dD4', | |
1975 | 'ext': 'mp4', | |
1976 | 'title': 'Isolation - Mind Field (Ep 1)', | |
1977 | 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd', | |
1978 | 'duration': 2085, | |
1979 | 'upload_date': '20170118', | |
1980 | 'series': 'Mind Field', | |
1981 | 'season_number': 1, | |
1982 | 'episode_number': 1, | |
1983 | 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp', | |
1984 | 'tags': 'count:12', | |
1985 | 'view_count': int, | |
1986 | 'availability': 'public', | |
1987 | 'age_limit': 0, | |
1988 | 'channel': 'Vsauce', | |
1989 | 'episode': 'Episode 1', | |
1990 | 'categories': ['Entertainment'], | |
1991 | 'season': 'Season 1', | |
1992 | 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA', | |
1993 | 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA', | |
1994 | 'like_count': int, | |
1995 | 'playable_in_embed': True, | |
1996 | 'live_status': 'not_live', | |
1997 | 'channel_follower_count': int, | |
1998 | 'uploader': 'Vsauce', | |
1999 | 'uploader_url': 'https://www.youtube.com/@Vsauce', | |
2000 | 'uploader_id': '@Vsauce', | |
2001 | 'comment_count': int, | |
2002 | 'channel_is_verified': True, | |
2003 | }, | |
2004 | 'params': { | |
2005 | 'skip_download': True, | |
2006 | }, | |
2007 | 'expected_warnings': [ | |
2008 | 'Skipping DASH manifest', | |
2009 | ], | |
2010 | }, | |
2011 | { | |
2012 | # The following content has been identified by the YouTube community | |
2013 | # as inappropriate or offensive to some audiences. | |
2014 | 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI', | |
2015 | 'info_dict': { | |
2016 | 'id': '6SJNVb0GnPI', | |
2017 | 'ext': 'mp4', | |
2018 | 'title': 'Race Differences in Intelligence', | |
2019 | 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1', | |
2020 | 'duration': 965, | |
2021 | 'upload_date': '20140124', | |
2022 | }, | |
2023 | 'params': { | |
2024 | 'skip_download': True, | |
2025 | }, | |
2026 | 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.', | |
2027 | }, | |
2028 | { | |
2029 | # itag 212 | |
2030 | 'url': '1t24XAntNCY', | |
2031 | 'only_matching': True, | |
2032 | }, | |
2033 | { | |
2034 | # geo restricted to JP | |
2035 | 'url': 'sJL6WA-aGkQ', | |
2036 | 'only_matching': True, | |
2037 | }, | |
2038 | { | |
2039 | 'url': 'https://invidio.us/watch?v=BaW_jenozKc', | |
2040 | 'only_matching': True, | |
2041 | }, | |
2042 | { | |
2043 | 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc', | |
2044 | 'only_matching': True, | |
2045 | }, | |
2046 | { | |
2047 | # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m | |
2048 | 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA', | |
2049 | 'only_matching': True, | |
2050 | }, | |
2051 | { | |
2052 | # DRM protected | |
2053 | 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc', | |
2054 | 'only_matching': True, | |
2055 | }, | |
2056 | { | |
2057 | # Video with unsupported adaptive stream type formats | |
2058 | 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U', | |
2059 | 'info_dict': { | |
2060 | 'id': 'Z4Vy8R84T1U', | |
2061 | 'ext': 'mp4', | |
2062 | 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta', | |
2063 | 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', | |
2064 | 'duration': 433, | |
2065 | 'upload_date': '20130923', | |
2066 | 'formats': 'maxcount:10', | |
2067 | }, | |
2068 | 'params': { | |
2069 | 'skip_download': True, | |
2070 | 'youtube_include_dash_manifest': False, | |
2071 | }, | |
2072 | 'skip': 'not actual anymore', | |
2073 | }, | |
2074 | { | |
2075 | # Youtube Music Auto-generated description | |
2076 | # TODO: fix metadata extraction | |
2077 | 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs', | |
2078 | 'info_dict': { | |
2079 | 'id': 'MgNrAu2pzNs', | |
2080 | 'ext': 'mp4', | |
2081 | 'title': 'Voyeur Girl', | |
2082 | 'description': 'md5:7ae382a65843d6df2685993e90a8628f', | |
2083 | 'upload_date': '20190312', | |
2084 | 'artists': ['Stephen'], | |
2085 | 'creators': ['Stephen'], | |
2086 | 'track': 'Voyeur Girl', | |
2087 | 'album': 'it\'s too much love to know my dear', | |
2088 | 'release_date': '20190313', | |
2089 | 'alt_title': 'Voyeur Girl', | |
2090 | 'view_count': int, | |
2091 | 'playable_in_embed': True, | |
2092 | 'like_count': int, | |
2093 | 'categories': ['Music'], | |
2094 | 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA', | |
2095 | 'channel': 'Stephen', # TODO: should be "Stephen - Topic" | |
2096 | 'uploader': 'Stephen', | |
2097 | 'availability': 'public', | |
2098 | 'duration': 169, | |
2099 | 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp', | |
2100 | 'age_limit': 0, | |
2101 | 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA', | |
2102 | 'tags': 'count:11', | |
2103 | 'live_status': 'not_live', | |
2104 | 'channel_follower_count': int | |
2105 | }, | |
2106 | 'params': { | |
2107 | 'skip_download': True, | |
2108 | }, | |
2109 | }, | |
2110 | { | |
2111 | 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q', | |
2112 | 'only_matching': True, | |
2113 | }, | |
2114 | { | |
2115 | # invalid -> valid video id redirection | |
2116 | 'url': 'DJztXj2GPfl', | |
2117 | 'info_dict': { | |
2118 | 'id': 'DJztXj2GPfk', | |
2119 | 'ext': 'mp4', | |
2120 | 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)', | |
2121 | 'description': 'md5:bf577a41da97918e94fa9798d9228825', | |
2122 | 'upload_date': '20090125', | |
2123 | 'artist': 'Panjabi MC', | |
2124 | 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix', | |
2125 | 'album': 'Beware of the Boys (Mundian To Bach Ke)', | |
2126 | }, | |
2127 | 'params': { | |
2128 | 'skip_download': True, | |
2129 | }, | |
2130 | 'skip': 'Video unavailable', | |
2131 | }, | |
2132 | { | |
2133 | # empty description results in an empty string | |
2134 | 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k', | |
2135 | 'info_dict': { | |
2136 | 'id': 'x41yOUIvK2k', | |
2137 | 'ext': 'mp4', | |
2138 | 'title': 'IMG 3456', | |
2139 | 'description': '', | |
2140 | 'upload_date': '20170613', | |
2141 | 'view_count': int, | |
2142 | 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp', | |
2143 | 'like_count': int, | |
2144 | 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw', | |
2145 | 'tags': [], | |
2146 | 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw', | |
2147 | 'availability': 'public', | |
2148 | 'age_limit': 0, | |
2149 | 'categories': ['Pets & Animals'], | |
2150 | 'duration': 7, | |
2151 | 'playable_in_embed': True, | |
2152 | 'live_status': 'not_live', | |
2153 | 'channel': 'l\'Or Vert asbl', | |
2154 | 'channel_follower_count': int, | |
2155 | 'uploader': 'l\'Or Vert asbl', | |
2156 | 'uploader_url': 'https://www.youtube.com/@ElevageOrVert', | |
2157 | 'uploader_id': '@ElevageOrVert', | |
2158 | }, | |
2159 | 'params': { | |
2160 | 'skip_download': True, | |
2161 | }, | |
2162 | }, | |
2163 | { | |
2164 | # with '};' inside yt initial data (see [1]) | |
2165 | # see [2] for an example with '};' inside ytInitialPlayerResponse | |
2166 | # 1. https://github.com/ytdl-org/youtube-dl/issues/27093 | |
2167 | # 2. https://github.com/ytdl-org/youtube-dl/issues/27216 | |
2168 | 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no', | |
2169 | 'info_dict': { | |
2170 | 'id': 'CHqg6qOn4no', | |
2171 | 'ext': 'mp4', | |
2172 | 'title': 'Part 77 Sort a list of simple types in c#', | |
2173 | 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc', | |
2174 | 'upload_date': '20130831', | |
2175 | 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q', | |
2176 | 'like_count': int, | |
2177 | 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q', | |
2178 | 'live_status': 'not_live', | |
2179 | 'categories': ['Education'], | |
2180 | 'availability': 'public', | |
2181 | 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg', | |
2182 | 'tags': 'count:12', | |
2183 | 'playable_in_embed': True, | |
2184 | 'age_limit': 0, | |
2185 | 'view_count': int, | |
2186 | 'duration': 522, | |
2187 | 'channel': 'kudvenkat', | |
2188 | 'comment_count': int, | |
2189 | 'channel_follower_count': int, | |
2190 | 'chapters': list, | |
2191 | 'uploader': 'kudvenkat', | |
2192 | 'uploader_url': 'https://www.youtube.com/@Csharp-video-tutorialsBlogspot', | |
2193 | 'uploader_id': '@Csharp-video-tutorialsBlogspot', | |
2194 | 'channel_is_verified': True, | |
2195 | 'heatmap': 'count:100', | |
2196 | }, | |
2197 | 'params': { | |
2198 | 'skip_download': True, | |
2199 | }, | |
2200 | }, | |
2201 | { | |
2202 | # another example of '};' in ytInitialData | |
2203 | 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY', | |
2204 | 'only_matching': True, | |
2205 | }, | |
2206 | { | |
2207 | 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ', | |
2208 | 'only_matching': True, | |
2209 | }, | |
2210 | { | |
2211 | # https://github.com/ytdl-org/youtube-dl/pull/28094 | |
2212 | 'url': 'OtqTfy26tG0', | |
2213 | 'info_dict': { | |
2214 | 'id': 'OtqTfy26tG0', | |
2215 | 'ext': 'mp4', | |
2216 | 'title': 'Burn Out', | |
2217 | 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131', | |
2218 | 'upload_date': '20141120', | |
2219 | 'artist': 'The Cinematic Orchestra', | |
2220 | 'track': 'Burn Out', | |
2221 | 'album': 'Every Day', | |
2222 | 'like_count': int, | |
2223 | 'live_status': 'not_live', | |
2224 | 'alt_title': 'Burn Out', | |
2225 | 'duration': 614, | |
2226 | 'age_limit': 0, | |
2227 | 'view_count': int, | |
2228 | 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw', | |
2229 | 'creator': 'The Cinematic Orchestra', | |
2230 | 'channel': 'The Cinematic Orchestra', | |
2231 | 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'], | |
2232 | 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw', | |
2233 | 'availability': 'public', | |
2234 | 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg', | |
2235 | 'categories': ['Music'], | |
2236 | 'playable_in_embed': True, | |
2237 | 'channel_follower_count': int, | |
2238 | 'uploader': 'The Cinematic Orchestra', | |
2239 | 'comment_count': int, | |
2240 | }, | |
2241 | 'params': { | |
2242 | 'skip_download': True, | |
2243 | }, | |
2244 | }, | |
2245 | { | |
2246 | # controversial video, only works with bpctr when authenticated with cookies | |
2247 | 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg', | |
2248 | 'only_matching': True, | |
2249 | }, | |
2250 | { | |
2251 | # controversial video, requires bpctr/contentCheckOk | |
2252 | 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc', | |
2253 | 'info_dict': { | |
2254 | 'id': 'SZJvDhaSDnc', | |
2255 | 'ext': 'mp4', | |
2256 | 'title': 'San Diego teen commits suicide after bullying over embarrassing video', | |
2257 | 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ', | |
2258 | 'upload_date': '20140716', | |
2259 | 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7', | |
2260 | 'duration': 170, | |
2261 | 'categories': ['News & Politics'], | |
2262 | 'view_count': int, | |
2263 | 'channel': 'CBS Mornings', | |
2264 | 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'], | |
2265 | 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg', | |
2266 | 'age_limit': 18, | |
2267 | 'availability': 'needs_auth', | |
2268 | 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ', | |
2269 | 'like_count': int, | |
2270 | 'live_status': 'not_live', | |
2271 | 'playable_in_embed': True, | |
2272 | 'channel_follower_count': int, | |
2273 | 'uploader': 'CBS Mornings', | |
2274 | 'uploader_url': 'https://www.youtube.com/@CBSMornings', | |
2275 | 'uploader_id': '@CBSMornings', | |
2276 | 'comment_count': int, | |
2277 | 'channel_is_verified': True, | |
2278 | } | |
2279 | }, | |
2280 | { | |
2281 | # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685 | |
2282 | 'url': 'cBvYw8_A0vQ', | |
2283 | 'info_dict': { | |
2284 | 'id': 'cBvYw8_A0vQ', | |
2285 | 'ext': 'mp4', | |
2286 | 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き', | |
2287 | 'description': 'md5:ea770e474b7cd6722b4c95b833c03630', | |
2288 | 'upload_date': '20201120', | |
2289 | 'duration': 1456, | |
2290 | 'categories': ['Travel & Events'], | |
2291 | 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw', | |
2292 | 'view_count': int, | |
2293 | 'channel': 'Walk around Japan', | |
2294 | 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'], | |
2295 | 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp', | |
2296 | 'age_limit': 0, | |
2297 | 'availability': 'public', | |
2298 | 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw', | |
2299 | 'live_status': 'not_live', | |
2300 | 'playable_in_embed': True, | |
2301 | 'channel_follower_count': int, | |
2302 | 'uploader': 'Walk around Japan', | |
2303 | 'uploader_url': 'https://www.youtube.com/@walkaroundjapan7124', | |
2304 | 'uploader_id': '@walkaroundjapan7124', | |
2305 | }, | |
2306 | 'params': { | |
2307 | 'skip_download': True, | |
2308 | }, | |
2309 | }, { | |
2310 | # Has multiple audio streams | |
2311 | 'url': 'WaOKSUlf4TM', | |
2312 | 'only_matching': True | |
2313 | }, { | |
2314 | # Requires Premium: has format 141 when requested using YTM url | |
2315 | 'url': 'https://music.youtube.com/watch?v=XclachpHxis', | |
2316 | 'only_matching': True | |
2317 | }, { | |
2318 | # multiple subtitles with same lang_code | |
2319 | 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug', | |
2320 | 'only_matching': True, | |
2321 | }, { | |
2322 | # Force use android client fallback | |
2323 | 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY', | |
2324 | 'info_dict': { | |
2325 | 'id': 'YOelRv7fMxY', | |
2326 | 'title': 'DIGGING A SECRET TUNNEL Part 1', | |
2327 | 'ext': '3gp', | |
2328 | 'upload_date': '20210624', | |
2329 | 'channel_id': 'UCp68_FLety0O-n9QU6phsgw', | |
2330 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw', | |
2331 | 'description': 'md5:5d5991195d599b56cd0c4148907eec50', | |
2332 | 'duration': 596, | |
2333 | 'categories': ['Entertainment'], | |
2334 | 'view_count': int, | |
2335 | 'channel': 'colinfurze', | |
2336 | 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'], | |
2337 | 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg', | |
2338 | 'age_limit': 0, | |
2339 | 'availability': 'public', | |
2340 | 'like_count': int, | |
2341 | 'live_status': 'not_live', | |
2342 | 'playable_in_embed': True, | |
2343 | 'channel_follower_count': int, | |
2344 | 'chapters': list, | |
2345 | 'uploader': 'colinfurze', | |
2346 | 'uploader_url': 'https://www.youtube.com/@colinfurze', | |
2347 | 'uploader_id': '@colinfurze', | |
2348 | 'comment_count': int, | |
2349 | 'channel_is_verified': True, | |
2350 | 'heatmap': 'count:100', | |
2351 | }, | |
2352 | 'params': { | |
2353 | 'format': '17', # 3gp format available on android | |
2354 | 'extractor_args': {'youtube': {'player_client': ['android']}}, | |
2355 | }, | |
2356 | 'skip': 'android client broken', | |
2357 | }, | |
2358 | { | |
2359 | # Skip download of additional client configs (remix client config in this case) | |
2360 | 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs', | |
2361 | 'only_matching': True, | |
2362 | 'params': { | |
2363 | 'extractor_args': {'youtube': {'player_skip': ['configs']}}, | |
2364 | }, | |
2365 | }, { | |
2366 | # shorts | |
2367 | 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY', | |
2368 | 'only_matching': True, | |
2369 | }, { | |
2370 | 'note': 'Storyboards', | |
2371 | 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8', | |
2372 | 'info_dict': { | |
2373 | 'id': '5KLPxDtMqe8', | |
2374 | 'ext': 'mhtml', | |
2375 | 'format_id': 'sb0', | |
2376 | 'title': 'Your Brain is Plastic', | |
2377 | 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc', | |
2378 | 'upload_date': '20140324', | |
2379 | 'like_count': int, | |
2380 | 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow', | |
2381 | 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow', | |
2382 | 'view_count': int, | |
2383 | 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg', | |
2384 | 'playable_in_embed': True, | |
2385 | 'tags': 'count:12', | |
2386 | 'availability': 'public', | |
2387 | 'channel': 'SciShow', | |
2388 | 'live_status': 'not_live', | |
2389 | 'duration': 248, | |
2390 | 'categories': ['Education'], | |
2391 | 'age_limit': 0, | |
2392 | 'channel_follower_count': int, | |
2393 | 'chapters': list, | |
2394 | 'uploader': 'SciShow', | |
2395 | 'uploader_url': 'https://www.youtube.com/@SciShow', | |
2396 | 'uploader_id': '@SciShow', | |
2397 | 'comment_count': int, | |
2398 | 'channel_is_verified': True, | |
2399 | 'heatmap': 'count:100', | |
2400 | }, 'params': {'format': 'mhtml', 'skip_download': True} | |
2401 | }, { | |
2402 | # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939) | |
2403 | 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4', | |
2404 | 'info_dict': { | |
2405 | 'id': '2NUZ8W2llS4', | |
2406 | 'ext': 'mp4', | |
2407 | 'title': 'The NP that test your phone performance 🙂', | |
2408 | 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d', | |
2409 | 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA', | |
2410 | 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA', | |
2411 | 'duration': 21, | |
2412 | 'view_count': int, | |
2413 | 'age_limit': 0, | |
2414 | 'categories': ['Gaming'], | |
2415 | 'tags': 'count:23', | |
2416 | 'playable_in_embed': True, | |
2417 | 'live_status': 'not_live', | |
2418 | 'upload_date': '20220103', | |
2419 | 'like_count': int, | |
2420 | 'availability': 'public', | |
2421 | 'channel': 'Leon Nguyen', | |
2422 | 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp', | |
2423 | 'comment_count': int, | |
2424 | 'channel_follower_count': int, | |
2425 | 'uploader': 'Leon Nguyen', | |
2426 | 'uploader_url': 'https://www.youtube.com/@LeonNguyen', | |
2427 | 'uploader_id': '@LeonNguyen', | |
2428 | 'heatmap': 'count:100', | |
2429 | } | |
2430 | }, { | |
2431 | # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date | |
2432 | 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4', | |
2433 | 'info_dict': { | |
2434 | 'id': '2NUZ8W2llS4', | |
2435 | 'ext': 'mp4', | |
2436 | 'title': 'The NP that test your phone performance 🙂', | |
2437 | 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d', | |
2438 | 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA', | |
2439 | 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA', | |
2440 | 'duration': 21, | |
2441 | 'view_count': int, | |
2442 | 'age_limit': 0, | |
2443 | 'categories': ['Gaming'], | |
2444 | 'tags': 'count:23', | |
2445 | 'playable_in_embed': True, | |
2446 | 'live_status': 'not_live', | |
2447 | 'upload_date': '20220102', | |
2448 | 'like_count': int, | |
2449 | 'availability': 'public', | |
2450 | 'channel': 'Leon Nguyen', | |
2451 | 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp', | |
2452 | 'comment_count': int, | |
2453 | 'channel_follower_count': int, | |
2454 | 'uploader': 'Leon Nguyen', | |
2455 | 'uploader_url': 'https://www.youtube.com/@LeonNguyen', | |
2456 | 'uploader_id': '@LeonNguyen', | |
2457 | 'heatmap': 'count:100', | |
2458 | }, | |
2459 | 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']} | |
2460 | }, { | |
2461 | # date text is premiered video, ensure upload date in UTC (published 1641172509) | |
2462 | 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM', | |
2463 | 'info_dict': { | |
2464 | 'id': 'mzZzzBU6lrM', | |
2465 | 'ext': 'mp4', | |
2466 | 'title': 'I Met GeorgeNotFound In Real Life...', | |
2467 | 'description': 'md5:978296ec9783a031738b684d4ebf302d', | |
2468 | 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q', | |
2469 | 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q', | |
2470 | 'duration': 955, | |
2471 | 'view_count': int, | |
2472 | 'age_limit': 0, | |
2473 | 'categories': ['Entertainment'], | |
2474 | 'tags': 'count:26', | |
2475 | 'playable_in_embed': True, | |
2476 | 'live_status': 'not_live', | |
2477 | 'release_timestamp': 1641172509, | |
2478 | 'release_date': '20220103', | |
2479 | 'upload_date': '20220103', | |
2480 | 'like_count': int, | |
2481 | 'availability': 'public', | |
2482 | 'channel': 'Quackity', | |
2483 | 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg', | |
2484 | 'channel_follower_count': int, | |
2485 | 'uploader': 'Quackity', | |
2486 | 'uploader_id': '@Quackity', | |
2487 | 'uploader_url': 'https://www.youtube.com/@Quackity', | |
2488 | 'comment_count': int, | |
2489 | 'channel_is_verified': True, | |
2490 | 'heatmap': 'count:100', | |
2491 | } | |
2492 | }, | |
2493 | { # continuous livestream. Microformat upload date should be preferred. | |
2494 | # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27 | |
2495 | 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU', | |
2496 | 'info_dict': { | |
2497 | 'id': 'kgx4WGK0oNU', | |
2498 | '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}', | |
2499 | 'ext': 'mp4', | |
2500 | 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA', | |
2501 | 'availability': 'public', | |
2502 | 'age_limit': 0, | |
2503 | 'release_timestamp': 1637975704, | |
2504 | 'upload_date': '20210619', | |
2505 | 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA', | |
2506 | 'live_status': 'is_live', | |
2507 | 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg', | |
2508 | 'channel': 'Abao in Tokyo', | |
2509 | 'channel_follower_count': int, | |
2510 | 'release_date': '20211127', | |
2511 | 'tags': 'count:39', | |
2512 | 'categories': ['People & Blogs'], | |
2513 | 'like_count': int, | |
2514 | 'view_count': int, | |
2515 | 'playable_in_embed': True, | |
2516 | 'description': 'md5:2ef1d002cad520f65825346e2084e49d', | |
2517 | 'concurrent_view_count': int, | |
2518 | 'uploader': 'Abao in Tokyo', | |
2519 | 'uploader_url': 'https://www.youtube.com/@abaointokyo', | |
2520 | 'uploader_id': '@abaointokyo', | |
2521 | }, | |
2522 | 'params': {'skip_download': True} | |
2523 | }, { | |
2524 | 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA', | |
2525 | 'info_dict': { | |
2526 | 'id': 'tjjjtzRLHvA', | |
2527 | 'ext': 'mp4', | |
2528 | 'title': 'ハッシュタグ無し };if window.ytcsi', | |
2529 | 'upload_date': '20220323', | |
2530 | 'like_count': int, | |
2531 | 'availability': 'unlisted', | |
2532 | 'channel': 'Lesmiscore', | |
2533 | 'thumbnail': r're:^https?://.*\.jpg', | |
2534 | 'age_limit': 0, | |
2535 | 'categories': ['Music'], | |
2536 | 'view_count': int, | |
2537 | 'description': '', | |
2538 | 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A', | |
2539 | 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A', | |
2540 | 'live_status': 'not_live', | |
2541 | 'playable_in_embed': True, | |
2542 | 'channel_follower_count': int, | |
2543 | 'duration': 6, | |
2544 | 'tags': [], | |
2545 | 'uploader_id': '@lesmiscore', | |
2546 | 'uploader': 'Lesmiscore', | |
2547 | 'uploader_url': 'https://www.youtube.com/@lesmiscore', | |
2548 | } | |
2549 | }, { | |
2550 | # Prefer primary title+description language metadata by default | |
2551 | # Do not prefer translated description if primary is empty | |
2552 | 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ', | |
2553 | 'info_dict': { | |
2554 | 'id': 'el3E4MbxRqQ', | |
2555 | 'ext': 'mp4', | |
2556 | 'title': 'dlp test video 2 - primary sv no desc', | |
2557 | 'description': '', | |
2558 | 'channel': 'cole-dlp-test-acc', | |
2559 | 'tags': [], | |
2560 | 'view_count': int, | |
2561 | 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', | |
2562 | 'like_count': int, | |
2563 | 'playable_in_embed': True, | |
2564 | 'availability': 'unlisted', | |
2565 | 'thumbnail': r're:^https?://.*\.jpg', | |
2566 | 'age_limit': 0, | |
2567 | 'duration': 5, | |
2568 | 'live_status': 'not_live', | |
2569 | 'upload_date': '20220908', | |
2570 | 'categories': ['People & Blogs'], | |
2571 | 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA', | |
2572 | 'uploader_url': 'https://www.youtube.com/@coletdjnz', | |
2573 | 'uploader_id': '@coletdjnz', | |
2574 | 'uploader': 'cole-dlp-test-acc', | |
2575 | }, | |
2576 | 'params': {'skip_download': True} | |
2577 | }, { | |
2578 | # Extractor argument: prefer translated title+description | |
2579 | 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng', | |
2580 | 'info_dict': { | |
2581 | 'id': 'gHKT4uU8Zng', | |
2582 | 'ext': 'mp4', | |
2583 | 'channel': 'cole-dlp-test-acc', | |
2584 | 'tags': [], | |
2585 | 'duration': 5, | |
2586 | 'live_status': 'not_live', | |
2587 | 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA', | |
2588 | 'upload_date': '20220728', | |
2589 | 'view_count': int, | |
2590 | 'categories': ['People & Blogs'], | |
2591 | 'thumbnail': r're:^https?://.*\.jpg', | |
2592 | 'title': 'dlp test video title translated (fr)', | |
2593 | 'availability': 'public', | |
2594 | 'age_limit': 0, | |
2595 | 'description': 'dlp test video description translated (fr)', | |
2596 | 'playable_in_embed': True, | |
2597 | 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', | |
2598 | 'uploader_url': 'https://www.youtube.com/@coletdjnz', | |
2599 | 'uploader_id': '@coletdjnz', | |
2600 | 'uploader': 'cole-dlp-test-acc', | |
2601 | }, | |
2602 | 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}}, | |
2603 | 'expected_warnings': [r'Preferring "fr" translated fields'], | |
2604 | }, { | |
2605 | 'note': '6 channel audio', | |
2606 | 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo', | |
2607 | 'only_matching': True, | |
2608 | }, { | |
2609 | 'note': 'Multiple HLS formats with same itag', | |
2610 | 'url': 'https://www.youtube.com/watch?v=kX3nB4PpJko', | |
2611 | 'info_dict': { | |
2612 | 'id': 'kX3nB4PpJko', | |
2613 | 'ext': 'mp4', | |
2614 | 'categories': ['Entertainment'], | |
2615 | 'description': 'md5:e8031ff6e426cdb6a77670c9b81f6fa6', | |
2616 | 'live_status': 'not_live', | |
2617 | 'duration': 937, | |
2618 | 'channel_follower_count': int, | |
2619 | 'thumbnail': 'https://i.ytimg.com/vi_webp/kX3nB4PpJko/maxresdefault.webp', | |
2620 | 'title': 'Last To Take Hand Off Jet, Keeps It!', | |
2621 | 'channel': 'MrBeast', | |
2622 | 'playable_in_embed': True, | |
2623 | 'view_count': int, | |
2624 | 'upload_date': '20221112', | |
2625 | 'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA', | |
2626 | 'age_limit': 0, | |
2627 | 'availability': 'public', | |
2628 | 'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA', | |
2629 | 'like_count': int, | |
2630 | 'tags': [], | |
2631 | 'uploader': 'MrBeast', | |
2632 | 'uploader_url': 'https://www.youtube.com/@MrBeast', | |
2633 | 'uploader_id': '@MrBeast', | |
2634 | 'comment_count': int, | |
2635 | 'channel_is_verified': True, | |
2636 | 'heatmap': 'count:100', | |
2637 | }, | |
2638 | 'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'}, | |
2639 | }, { | |
2640 | 'note': 'Audio formats with Dynamic Range Compression', | |
2641 | 'url': 'https://www.youtube.com/watch?v=Tq92D6wQ1mg', | |
2642 | 'info_dict': { | |
2643 | 'id': 'Tq92D6wQ1mg', | |
2644 | 'ext': 'webm', | |
2645 | 'title': '[MMD] Adios - EVERGLOW [+Motion DL]', | |
2646 | 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ', | |
2647 | 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ', | |
2648 | 'channel_follower_count': int, | |
2649 | 'description': 'md5:17eccca93a786d51bc67646756894066', | |
2650 | 'upload_date': '20191228', | |
2651 | 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'], | |
2652 | 'playable_in_embed': True, | |
2653 | 'like_count': int, | |
2654 | 'categories': ['Entertainment'], | |
2655 | 'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg', | |
2656 | 'age_limit': 18, | |
2657 | 'channel': 'Projekt Melody', | |
2658 | 'view_count': int, | |
2659 | 'availability': 'needs_auth', | |
2660 | 'comment_count': int, | |
2661 | 'live_status': 'not_live', | |
2662 | 'duration': 106, | |
2663 | 'uploader': 'Projekt Melody', | |
2664 | 'uploader_id': '@ProjektMelody', | |
2665 | 'uploader_url': 'https://www.youtube.com/@ProjektMelody', | |
2666 | }, | |
2667 | 'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'}, | |
2668 | }, | |
2669 | { | |
2670 | 'url': 'https://www.youtube.com/live/qVv6vCqciTM', | |
2671 | 'info_dict': { | |
2672 | 'id': 'qVv6vCqciTM', | |
2673 | 'ext': 'mp4', | |
2674 | 'age_limit': 0, | |
2675 | 'comment_count': int, | |
2676 | 'chapters': 'count:13', | |
2677 | 'upload_date': '20221223', | |
2678 | 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg', | |
2679 | 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA', | |
2680 | 'like_count': int, | |
2681 | 'release_date': '20221223', | |
2682 | 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'], | |
2683 | '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】', | |
2684 | 'view_count': int, | |
2685 | 'playable_in_embed': True, | |
2686 | 'duration': 4438, | |
2687 | 'availability': 'public', | |
2688 | 'channel_follower_count': int, | |
2689 | 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA', | |
2690 | 'categories': ['Entertainment'], | |
2691 | 'live_status': 'was_live', | |
2692 | 'release_timestamp': 1671793345, | |
2693 | 'channel': 'さなちゃんねる', | |
2694 | 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d', | |
2695 | 'uploader': 'さなちゃんねる', | |
2696 | 'uploader_url': 'https://www.youtube.com/@sana_natori', | |
2697 | 'uploader_id': '@sana_natori', | |
2698 | 'channel_is_verified': True, | |
2699 | 'heatmap': 'count:100', | |
2700 | }, | |
2701 | }, | |
2702 | { | |
2703 | # Fallbacks when webpage and web client is unavailable | |
2704 | 'url': 'https://www.youtube.com/watch?v=wSSmNUl9Snw', | |
2705 | 'info_dict': { | |
2706 | 'id': 'wSSmNUl9Snw', | |
2707 | 'ext': 'mp4', | |
2708 | # 'categories': ['Science & Technology'], | |
2709 | 'view_count': int, | |
2710 | 'chapters': 'count:2', | |
2711 | 'channel': 'Scott Manley', | |
2712 | 'like_count': int, | |
2713 | 'age_limit': 0, | |
2714 | # 'availability': 'public', | |
2715 | 'channel_follower_count': int, | |
2716 | 'live_status': 'not_live', | |
2717 | 'upload_date': '20170831', | |
2718 | 'duration': 682, | |
2719 | 'tags': 'count:8', | |
2720 | 'uploader_url': 'https://www.youtube.com/@scottmanley', | |
2721 | 'description': 'md5:f4bed7b200404b72a394c2f97b782c02', | |
2722 | 'uploader': 'Scott Manley', | |
2723 | 'uploader_id': '@scottmanley', | |
2724 | 'title': 'The Computer Hack That Saved Apollo 14', | |
2725 | 'channel_id': 'UCxzC4EngIsMrPmbm6Nxvb-A', | |
2726 | 'thumbnail': r're:^https?://.*\.webp', | |
2727 | 'channel_url': 'https://www.youtube.com/channel/UCxzC4EngIsMrPmbm6Nxvb-A', | |
2728 | 'playable_in_embed': True, | |
2729 | 'comment_count': int, | |
2730 | 'channel_is_verified': True, | |
2731 | 'heatmap': 'count:100', | |
2732 | }, | |
2733 | 'params': { | |
2734 | 'extractor_args': {'youtube': {'player_client': ['ios'], 'player_skip': ['webpage']}}, | |
2735 | }, | |
2736 | }, | |
2737 | ] | |
2738 | ||
2739 | _WEBPAGE_TESTS = [ | |
2740 | # YouTube <object> embed | |
2741 | { | |
2742 | 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/', | |
2743 | 'md5': '873c81d308b979f0e23ee7e620b312a3', | |
2744 | 'info_dict': { | |
2745 | 'id': 'msN87y-iEx0', | |
2746 | 'ext': 'mp4', | |
2747 | 'title': 'Feynman: Mirrors FUN TO IMAGINE 6', | |
2748 | 'upload_date': '20080526', | |
2749 | 'description': 'md5:873c81d308b979f0e23ee7e620b312a3', | |
2750 | 'age_limit': 0, | |
2751 | 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'], | |
2752 | 'channel_id': 'UCCeo--lls1vna5YJABWAcVA', | |
2753 | 'playable_in_embed': True, | |
2754 | 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg', | |
2755 | 'like_count': int, | |
2756 | 'comment_count': int, | |
2757 | 'channel': 'Christopher Sykes', | |
2758 | 'live_status': 'not_live', | |
2759 | 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA', | |
2760 | 'availability': 'public', | |
2761 | 'duration': 195, | |
2762 | 'view_count': int, | |
2763 | 'categories': ['Science & Technology'], | |
2764 | 'channel_follower_count': int, | |
2765 | 'uploader': 'Christopher Sykes', | |
2766 | 'uploader_url': 'https://www.youtube.com/@ChristopherSykesDocumentaries', | |
2767 | 'uploader_id': '@ChristopherSykesDocumentaries', | |
2768 | 'heatmap': 'count:100', | |
2769 | }, | |
2770 | 'params': { | |
2771 | 'skip_download': True, | |
2772 | } | |
2773 | }, | |
2774 | ] | |
2775 | ||
2776 | @classmethod | |
2777 | def suitable(cls, url): | |
2778 | from ..utils import parse_qs | |
2779 | ||
2780 | qs = parse_qs(url) | |
2781 | if qs.get('list', [None])[0]: | |
2782 | return False | |
2783 | return super().suitable(url) | |
2784 | ||
2785 | def __init__(self, *args, **kwargs): | |
2786 | super().__init__(*args, **kwargs) | |
2787 | self._code_cache = {} | |
2788 | self._player_cache = {} | |
2789 | ||
2790 | def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live): | |
2791 | lock = threading.Lock() | |
2792 | start_time = time.time() | |
2793 | formats = [f for f in formats if f.get('is_from_start')] | |
2794 | ||
2795 | def refetch_manifest(format_id, delay): | |
2796 | nonlocal formats, start_time, is_live | |
2797 | if time.time() <= start_time + delay: | |
2798 | return | |
2799 | ||
2800 | _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url) | |
2801 | video_details = traverse_obj(prs, (..., 'videoDetails'), expected_type=dict) | |
2802 | microformats = traverse_obj( | |
2803 | prs, (..., 'microformat', 'playerMicroformatRenderer'), | |
2804 | expected_type=dict) | |
2805 | _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url) | |
2806 | is_live = live_status == 'is_live' | |
2807 | start_time = time.time() | |
2808 | ||
2809 | def mpd_feed(format_id, delay): | |
2810 | """ | |
2811 | @returns (manifest_url, manifest_stream_number, is_live) or None | |
2812 | """ | |
2813 | for retry in self.RetryManager(fatal=False): | |
2814 | with lock: | |
2815 | refetch_manifest(format_id, delay) | |
2816 | ||
2817 | f = next((f for f in formats if f['format_id'] == format_id), None) | |
2818 | if not f: | |
2819 | if not is_live: | |
2820 | retry.error = f'{video_id}: Video is no longer live' | |
2821 | else: | |
2822 | retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}' | |
2823 | continue | |
2824 | return f['manifest_url'], f['manifest_stream_number'], is_live | |
2825 | return None | |
2826 | ||
2827 | for f in formats: | |
2828 | f['is_live'] = is_live | |
2829 | gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'], | |
2830 | live_start_time, mpd_feed, not is_live and f.copy()) | |
2831 | if is_live: | |
2832 | f['fragments'] = gen | |
2833 | f['protocol'] = 'http_dash_segments_generator' | |
2834 | else: | |
2835 | f['fragments'] = LazyList(gen({})) | |
2836 | del f['is_from_start'] | |
2837 | ||
2838 | def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx): | |
2839 | FETCH_SPAN, MAX_DURATION = 5, 432000 | |
2840 | ||
2841 | mpd_url, stream_number, is_live = None, None, True | |
2842 | ||
2843 | begin_index = 0 | |
2844 | download_start_time = ctx.get('start') or time.time() | |
2845 | ||
2846 | lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION | |
2847 | if lack_early_segments: | |
2848 | self.report_warning(bug_reports_message( | |
2849 | 'Starting download from the last 120 hours of the live stream since ' | |
2850 | 'YouTube does not have data before that. If you think this is wrong,'), only_once=True) | |
2851 | lack_early_segments = True | |
2852 | ||
2853 | known_idx, no_fragment_score, last_segment_url = begin_index, 0, None | |
2854 | fragments, fragment_base_url = None, None | |
2855 | ||
2856 | def _extract_sequence_from_mpd(refresh_sequence, immediate): | |
2857 | nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url | |
2858 | # Obtain from MPD's maximum seq value | |
2859 | old_mpd_url = mpd_url | |
2860 | last_error = ctx.pop('last_error', None) | |
2861 | expire_fast = immediate or last_error and isinstance(last_error, HTTPError) and last_error.status == 403 | |
2862 | mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000) | |
2863 | or (mpd_url, stream_number, False)) | |
2864 | if not refresh_sequence: | |
2865 | if expire_fast and not is_live: | |
2866 | return False, last_seq | |
2867 | elif old_mpd_url == mpd_url: | |
2868 | return True, last_seq | |
2869 | if manifestless_orig_fmt: | |
2870 | fmt_info = manifestless_orig_fmt | |
2871 | else: | |
2872 | try: | |
2873 | fmts, _ = self._extract_mpd_formats_and_subtitles( | |
2874 | mpd_url, None, note=False, errnote=False, fatal=False) | |
2875 | except ExtractorError: | |
2876 | fmts = None | |
2877 | if not fmts: | |
2878 | no_fragment_score += 2 | |
2879 | return False, last_seq | |
2880 | fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number) | |
2881 | fragments = fmt_info['fragments'] | |
2882 | fragment_base_url = fmt_info['fragment_base_url'] | |
2883 | assert fragment_base_url | |
2884 | ||
2885 | _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1)) | |
2886 | return True, _last_seq | |
2887 | ||
2888 | self.write_debug(f'[{video_id}] Generating fragments for format {format_id}') | |
2889 | while is_live: | |
2890 | fetch_time = time.time() | |
2891 | if no_fragment_score > 30: | |
2892 | return | |
2893 | if last_segment_url: | |
2894 | # Obtain from "X-Head-Seqnum" header value from each segment | |
2895 | try: | |
2896 | urlh = self._request_webpage( | |
2897 | last_segment_url, None, note=False, errnote=False, fatal=False) | |
2898 | except ExtractorError: | |
2899 | urlh = None | |
2900 | last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum'])) | |
2901 | if last_seq is None: | |
2902 | no_fragment_score += 2 | |
2903 | last_segment_url = None | |
2904 | continue | |
2905 | else: | |
2906 | should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15) | |
2907 | no_fragment_score += 2 | |
2908 | if not should_continue: | |
2909 | continue | |
2910 | ||
2911 | if known_idx > last_seq: | |
2912 | last_segment_url = None | |
2913 | continue | |
2914 | ||
2915 | last_seq += 1 | |
2916 | ||
2917 | if begin_index < 0 and known_idx < 0: | |
2918 | # skip from the start when it's negative value | |
2919 | known_idx = last_seq + begin_index | |
2920 | if lack_early_segments: | |
2921 | known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration'])) | |
2922 | try: | |
2923 | for idx in range(known_idx, last_seq): | |
2924 | # do not update sequence here or you'll get skipped some part of it | |
2925 | should_continue, _ = _extract_sequence_from_mpd(False, False) | |
2926 | if not should_continue: | |
2927 | known_idx = idx - 1 | |
2928 | raise ExtractorError('breaking out of outer loop') | |
2929 | last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx) | |
2930 | yield { | |
2931 | 'url': last_segment_url, | |
2932 | 'fragment_count': last_seq, | |
2933 | } | |
2934 | if known_idx == last_seq: | |
2935 | no_fragment_score += 5 | |
2936 | else: | |
2937 | no_fragment_score = 0 | |
2938 | known_idx = last_seq | |
2939 | except ExtractorError: | |
2940 | continue | |
2941 | ||
2942 | if manifestless_orig_fmt: | |
2943 | # Stop at the first iteration if running for post-live manifestless; | |
2944 | # fragment count no longer increase since it starts | |
2945 | break | |
2946 | ||
2947 | time.sleep(max(0, FETCH_SPAN + fetch_time - time.time())) | |
2948 | ||
2949 | def _extract_player_url(self, *ytcfgs, webpage=None): | |
2950 | player_url = traverse_obj( | |
2951 | ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'), | |
2952 | get_all=False, expected_type=str) | |
2953 | if not player_url: | |
2954 | return | |
2955 | return urljoin('https://www.youtube.com', player_url) | |
2956 | ||
2957 | def _download_player_url(self, video_id, fatal=False): | |
2958 | res = self._download_webpage( | |
2959 | 'https://www.youtube.com/iframe_api', | |
2960 | note='Downloading iframe API JS', video_id=video_id, fatal=fatal) | |
2961 | if res: | |
2962 | player_version = self._search_regex( | |
2963 | r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal) | |
2964 | if player_version: | |
2965 | return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js' | |
2966 | ||
2967 | def _signature_cache_id(self, example_sig): | |
2968 | """ Return a string representation of a signature """ | |
2969 | return '.'.join(str(len(part)) for part in example_sig.split('.')) | |
2970 | ||
2971 | @classmethod | |
2972 | def _extract_player_info(cls, player_url): | |
2973 | for player_re in cls._PLAYER_INFO_RE: | |
2974 | id_m = re.search(player_re, player_url) | |
2975 | if id_m: | |
2976 | break | |
2977 | else: | |
2978 | raise ExtractorError('Cannot identify player %r' % player_url) | |
2979 | return id_m.group('id') | |
2980 | ||
2981 | def _load_player(self, video_id, player_url, fatal=True): | |
2982 | player_id = self._extract_player_info(player_url) | |
2983 | if player_id not in self._code_cache: | |
2984 | code = self._download_webpage( | |
2985 | player_url, video_id, fatal=fatal, | |
2986 | note='Downloading player ' + player_id, | |
2987 | errnote='Download of %s failed' % player_url) | |
2988 | if code: | |
2989 | self._code_cache[player_id] = code | |
2990 | return self._code_cache.get(player_id) | |
2991 | ||
2992 | def _extract_signature_function(self, video_id, player_url, example_sig): | |
2993 | player_id = self._extract_player_info(player_url) | |
2994 | ||
2995 | # Read from filesystem cache | |
2996 | func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}' | |
2997 | assert os.path.basename(func_id) == func_id | |
2998 | ||
2999 | self.write_debug(f'Extracting signature function {func_id}') | |
3000 | cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None | |
3001 | ||
3002 | if not cache_spec: | |
3003 | code = self._load_player(video_id, player_url) | |
3004 | if code: | |
3005 | res = self._parse_sig_js(code) | |
3006 | test_string = ''.join(map(chr, range(len(example_sig)))) | |
3007 | cache_spec = [ord(c) for c in res(test_string)] | |
3008 | self.cache.store('youtube-sigfuncs', func_id, cache_spec) | |
3009 | ||
3010 | return lambda s: ''.join(s[i] for i in cache_spec) | |
3011 | ||
3012 | def _print_sig_code(self, func, example_sig): | |
3013 | if not self.get_param('youtube_print_sig_code'): | |
3014 | return | |
3015 | ||
3016 | def gen_sig_code(idxs): | |
3017 | def _genslice(start, end, step): | |
3018 | starts = '' if start == 0 else str(start) | |
3019 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' | |
3020 | steps = '' if step == 1 else (':%d' % step) | |
3021 | return f's[{starts}{ends}{steps}]' | |
3022 | ||
3023 | step = None | |
3024 | # Quelch pyflakes warnings - start will be set when step is set | |
3025 | start = '(Never used)' | |
3026 | for i, prev in zip(idxs[1:], idxs[:-1]): | |
3027 | if step is not None: | |
3028 | if i - prev == step: | |
3029 | continue | |
3030 | yield _genslice(start, prev, step) | |
3031 | step = None | |
3032 | continue | |
3033 | if i - prev in [-1, 1]: | |
3034 | step = i - prev | |
3035 | start = prev | |
3036 | continue | |
3037 | else: | |
3038 | yield 's[%d]' % prev | |
3039 | if step is None: | |
3040 | yield 's[%d]' % i | |
3041 | else: | |
3042 | yield _genslice(start, i, step) | |
3043 | ||
3044 | test_string = ''.join(map(chr, range(len(example_sig)))) | |
3045 | cache_res = func(test_string) | |
3046 | cache_spec = [ord(c) for c in cache_res] | |
3047 | expr_code = ' + '.join(gen_sig_code(cache_spec)) | |
3048 | signature_id_tuple = '(%s)' % ( | |
3049 | ', '.join(str(len(p)) for p in example_sig.split('.'))) | |
3050 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' | |
3051 | ' return %s\n') % (signature_id_tuple, expr_code) | |
3052 | self.to_screen('Extracted signature function:\n' + code) | |
3053 | ||
3054 | def _parse_sig_js(self, jscode): | |
3055 | funcname = self._search_regex( | |
3056 | (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
3057 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
3058 | r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)', | |
3059 | r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)', | |
3060 | 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}\(a,\d+\))?', | |
3061 | r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', | |
3062 | # Obsolete patterns | |
3063 | r'("|\')signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
3064 | r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(', | |
3065 | r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
3066 | r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
3067 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
3068 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('), | |
3069 | jscode, 'Initial JS player signature function name', group='sig') | |
3070 | ||
3071 | jsi = JSInterpreter(jscode) | |
3072 | initial_function = jsi.extract_function(funcname) | |
3073 | return lambda s: initial_function([s]) | |
3074 | ||
3075 | def _cached(self, func, *cache_id): | |
3076 | def inner(*args, **kwargs): | |
3077 | if cache_id not in self._player_cache: | |
3078 | try: | |
3079 | self._player_cache[cache_id] = func(*args, **kwargs) | |
3080 | except ExtractorError as e: | |
3081 | self._player_cache[cache_id] = e | |
3082 | except Exception as e: | |
3083 | self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e) | |
3084 | ||
3085 | ret = self._player_cache[cache_id] | |
3086 | if isinstance(ret, Exception): | |
3087 | raise ret | |
3088 | return ret | |
3089 | return inner | |
3090 | ||
3091 | def _decrypt_signature(self, s, video_id, player_url): | |
3092 | """Turn the encrypted s field into a working signature""" | |
3093 | extract_sig = self._cached( | |
3094 | self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s)) | |
3095 | func = extract_sig(video_id, player_url, s) | |
3096 | self._print_sig_code(func, s) | |
3097 | return func(s) | |
3098 | ||
3099 | def _decrypt_nsig(self, s, video_id, player_url): | |
3100 | """Turn the encrypted n field into a working signature""" | |
3101 | if player_url is None: | |
3102 | raise ExtractorError('Cannot decrypt nsig without player_url') | |
3103 | player_url = urljoin('https://www.youtube.com', player_url) | |
3104 | ||
3105 | try: | |
3106 | jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url) | |
3107 | except ExtractorError as e: | |
3108 | raise ExtractorError('Unable to extract nsig function code', cause=e) | |
3109 | if self.get_param('youtube_print_sig_code'): | |
3110 | self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n') | |
3111 | ||
3112 | try: | |
3113 | extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url) | |
3114 | ret = extract_nsig(jsi, func_code)(s) | |
3115 | except JSInterpreter.Exception as e: | |
3116 | try: | |
3117 | jsi = PhantomJSwrapper(self, timeout=5000) | |
3118 | except ExtractorError: | |
3119 | raise e | |
3120 | self.report_warning( | |
3121 | f'Native nsig extraction failed: Trying with PhantomJS\n' | |
3122 | f' n = {s} ; player = {player_url}', video_id) | |
3123 | self.write_debug(e, only_once=True) | |
3124 | ||
3125 | args, func_body = func_code | |
3126 | ret = jsi.execute( | |
3127 | f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));', | |
3128 | video_id=video_id, note='Executing signature code').strip() | |
3129 | ||
3130 | self.write_debug(f'Decrypted nsig {s} => {ret}') | |
3131 | return ret | |
3132 | ||
3133 | def _extract_n_function_name(self, jscode): | |
3134 | funcname, idx = self._search_regex( | |
3135 | r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)', | |
3136 | jscode, 'Initial JS player n function name', group=('nfunc', 'idx')) | |
3137 | if not idx: | |
3138 | return funcname | |
3139 | ||
3140 | return json.loads(js_to_json(self._search_regex( | |
3141 | rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])\s*[,;]', jscode, | |
3142 | f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)] | |
3143 | ||
3144 | def _extract_n_function_code(self, video_id, player_url): | |
3145 | player_id = self._extract_player_info(player_url) | |
3146 | func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1') | |
3147 | jscode = func_code or self._load_player(video_id, player_url) | |
3148 | jsi = JSInterpreter(jscode) | |
3149 | ||
3150 | if func_code: | |
3151 | return jsi, player_id, func_code | |
3152 | ||
3153 | func_name = self._extract_n_function_name(jscode) | |
3154 | ||
3155 | # For redundancy | |
3156 | func_code = self._search_regex( | |
3157 | r'''(?xs)%s\s*=\s*function\s*\((?P<var>[\w$]+)\)\s* | |
3158 | # NB: The end of the regex is intentionally kept strict | |
3159 | {(?P<code>.+?}\s*return\ [\w$]+.join\(""\))};''' % func_name, | |
3160 | jscode, 'nsig function', group=('var', 'code'), default=None) | |
3161 | if func_code: | |
3162 | func_code = ([func_code[0]], func_code[1]) | |
3163 | else: | |
3164 | self.write_debug('Extracting nsig function with jsinterp') | |
3165 | func_code = jsi.extract_function_code(func_name) | |
3166 | ||
3167 | self.cache.store('youtube-nsig', player_id, func_code) | |
3168 | return jsi, player_id, func_code | |
3169 | ||
3170 | def _extract_n_function_from_code(self, jsi, func_code): | |
3171 | func = jsi.extract_function_from_code(*func_code) | |
3172 | ||
3173 | def extract_nsig(s): | |
3174 | try: | |
3175 | ret = func([s]) | |
3176 | except JSInterpreter.Exception: | |
3177 | raise | |
3178 | except Exception as e: | |
3179 | raise JSInterpreter.Exception(traceback.format_exc(), cause=e) | |
3180 | ||
3181 | if ret.startswith('enhanced_except_'): | |
3182 | raise JSInterpreter.Exception('Signature function returned an exception') | |
3183 | return ret | |
3184 | ||
3185 | return extract_nsig | |
3186 | ||
3187 | def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False): | |
3188 | """ | |
3189 | Extract signatureTimestamp (sts) | |
3190 | Required to tell API what sig/player version is in use. | |
3191 | """ | |
3192 | sts = None | |
3193 | if isinstance(ytcfg, dict): | |
3194 | sts = int_or_none(ytcfg.get('STS')) | |
3195 | ||
3196 | if not sts: | |
3197 | # Attempt to extract from player | |
3198 | if player_url is None: | |
3199 | error_msg = 'Cannot extract signature timestamp without player_url.' | |
3200 | if fatal: | |
3201 | raise ExtractorError(error_msg) | |
3202 | self.report_warning(error_msg) | |
3203 | return | |
3204 | code = self._load_player(video_id, player_url, fatal=fatal) | |
3205 | if code: | |
3206 | sts = int_or_none(self._search_regex( | |
3207 | r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code, | |
3208 | 'JS player signature timestamp', group='sts', fatal=fatal)) | |
3209 | return sts | |
3210 | ||
3211 | def _mark_watched(self, video_id, player_responses): | |
3212 | for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')): | |
3213 | label = 'fully ' if is_full else '' | |
3214 | url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'), | |
3215 | expected_type=url_or_none) | |
3216 | if not url: | |
3217 | self.report_warning(f'Unable to mark {label}watched') | |
3218 | return | |
3219 | parsed_url = urllib.parse.urlparse(url) | |
3220 | qs = urllib.parse.parse_qs(parsed_url.query) | |
3221 | ||
3222 | # cpn generation algorithm is reverse engineered from base.js. | |
3223 | # In fact it works even with dummy cpn. | |
3224 | CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_' | |
3225 | cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)) | |
3226 | ||
3227 | # # more consistent results setting it to right before the end | |
3228 | video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)] | |
3229 | ||
3230 | qs.update({ | |
3231 | 'ver': ['2'], | |
3232 | 'cpn': [cpn], | |
3233 | 'cmt': video_length, | |
3234 | 'el': 'detailpage', # otherwise defaults to "shorts" | |
3235 | }) | |
3236 | ||
3237 | if is_full: | |
3238 | # these seem to mark watchtime "history" in the real world | |
3239 | # they're required, so send in a single value | |
3240 | qs.update({ | |
3241 | 'st': 0, | |
3242 | 'et': video_length, | |
3243 | }) | |
3244 | ||
3245 | url = urllib.parse.urlunparse( | |
3246 | parsed_url._replace(query=urllib.parse.urlencode(qs, True))) | |
3247 | ||
3248 | self._download_webpage( | |
3249 | url, video_id, f'Marking {label}watched', | |
3250 | 'Unable to mark watched', fatal=False) | |
3251 | ||
3252 | @classmethod | |
3253 | def _extract_from_webpage(cls, url, webpage): | |
3254 | # Invidious Instances | |
3255 | # https://github.com/yt-dlp/yt-dlp/issues/195 | |
3256 | # https://github.com/iv-org/invidious/pull/1730 | |
3257 | mobj = re.search( | |
3258 | r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"', | |
3259 | webpage) | |
3260 | if mobj: | |
3261 | yield cls.url_result(mobj.group('url'), cls) | |
3262 | raise cls.StopExtraction() | |
3263 | ||
3264 | yield from super()._extract_from_webpage(url, webpage) | |
3265 | ||
3266 | # lazyYT YouTube embed | |
3267 | for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage): | |
3268 | yield cls.url_result(unescapeHTML(id_), cls, id_) | |
3269 | ||
3270 | # Wordpress "YouTube Video Importer" plugin | |
3271 | for m in re.findall(r'''(?x)<div[^>]+ | |
3272 | class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+ | |
3273 | data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage): | |
3274 | yield cls.url_result(m[-1], cls, m[-1]) | |
3275 | ||
3276 | @classmethod | |
3277 | def extract_id(cls, url): | |
3278 | video_id = cls.get_temp_id(url) | |
3279 | if not video_id: | |
3280 | raise ExtractorError(f'Invalid URL: {url}') | |
3281 | return video_id | |
3282 | ||
3283 | def _extract_chapters_from_json(self, data, duration): | |
3284 | chapter_list = traverse_obj( | |
3285 | data, ( | |
3286 | 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer', | |
3287 | 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters' | |
3288 | ), expected_type=list) | |
3289 | ||
3290 | return self._extract_chapters_helper( | |
3291 | chapter_list, | |
3292 | start_function=lambda chapter: float_or_none( | |
3293 | traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000), | |
3294 | title_function=lambda chapter: traverse_obj( | |
3295 | chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str), | |
3296 | duration=duration) | |
3297 | ||
3298 | def _extract_chapters_from_engagement_panel(self, data, duration): | |
3299 | content_list = traverse_obj( | |
3300 | data, | |
3301 | ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'), | |
3302 | expected_type=list) | |
3303 | chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription')) | |
3304 | chapter_title = lambda chapter: self._get_text(chapter, 'title') | |
3305 | ||
3306 | return next(filter(None, ( | |
3307 | self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')), | |
3308 | chapter_time, chapter_title, duration) | |
3309 | for contents in content_list)), []) | |
3310 | ||
3311 | def _extract_heatmap(self, data): | |
3312 | return traverse_obj(data, ( | |
3313 | 'frameworkUpdates', 'entityBatchUpdate', 'mutations', | |
3314 | lambda _, v: v['payload']['macroMarkersListEntity']['markersList']['markerType'] == 'MARKER_TYPE_HEATMAP', | |
3315 | 'payload', 'macroMarkersListEntity', 'markersList', 'markers', ..., { | |
3316 | 'start_time': ('startMillis', {functools.partial(float_or_none, scale=1000)}), | |
3317 | 'end_time': {lambda x: (int(x['startMillis']) + int(x['durationMillis'])) / 1000}, | |
3318 | 'value': ('intensityScoreNormalized', {float_or_none}), | |
3319 | })) or None | |
3320 | ||
3321 | def _extract_comment(self, entities, parent=None): | |
3322 | comment_entity_payload = get_first(entities, ('payload', 'commentEntityPayload', {dict})) | |
3323 | if not (comment_id := traverse_obj(comment_entity_payload, ('properties', 'commentId', {str}))): | |
3324 | return | |
3325 | ||
3326 | toolbar_entity_payload = get_first(entities, ('payload', 'engagementToolbarStateEntityPayload', {dict})) | |
3327 | time_text = traverse_obj(comment_entity_payload, ('properties', 'publishedTime', {str})) or '' | |
3328 | ||
3329 | return { | |
3330 | 'id': comment_id, | |
3331 | 'parent': parent or 'root', | |
3332 | **traverse_obj(comment_entity_payload, { | |
3333 | 'text': ('properties', 'content', 'content', {str}), | |
3334 | 'like_count': ('toolbar', 'likeCountA11y', {parse_count}), | |
3335 | 'author_id': ('author', 'channelId', {self.ucid_or_none}), | |
3336 | 'author': ('author', 'displayName', {str}), | |
3337 | 'author_thumbnail': ('author', 'avatarThumbnailUrl', {url_or_none}), | |
3338 | 'author_is_uploader': ('author', 'isCreator', {bool}), | |
3339 | 'author_is_verified': ('author', 'isVerified', {bool}), | |
3340 | 'author_url': ('author', 'channelCommand', 'innertubeCommand', ( | |
3341 | ('browseEndpoint', 'canonicalBaseUrl'), ('commandMetadata', 'webCommandMetadata', 'url') | |
3342 | ), {lambda x: urljoin('https://www.youtube.com', x)}), | |
3343 | }, get_all=False), | |
3344 | 'is_favorited': (None if toolbar_entity_payload is None else | |
3345 | toolbar_entity_payload.get('heartState') == 'TOOLBAR_HEART_STATE_HEARTED'), | |
3346 | '_time_text': time_text, # FIXME: non-standard, but we need a way of showing that it is an estimate. | |
3347 | 'timestamp': self._parse_time_text(time_text), | |
3348 | } | |
3349 | ||
3350 | def _extract_comment_old(self, comment_renderer, parent=None): | |
3351 | comment_id = comment_renderer.get('commentId') | |
3352 | if not comment_id: | |
3353 | return | |
3354 | ||
3355 | info = { | |
3356 | 'id': comment_id, | |
3357 | 'text': self._get_text(comment_renderer, 'contentText'), | |
3358 | 'like_count': self._get_count(comment_renderer, 'voteCount'), | |
3359 | 'author_id': traverse_obj(comment_renderer, ('authorEndpoint', 'browseEndpoint', 'browseId', {self.ucid_or_none})), | |
3360 | 'author': self._get_text(comment_renderer, 'authorText'), | |
3361 | 'author_thumbnail': traverse_obj(comment_renderer, ('authorThumbnail', 'thumbnails', -1, 'url', {url_or_none})), | |
3362 | 'parent': parent or 'root', | |
3363 | } | |
3364 | ||
3365 | # Timestamp is an estimate calculated from the current time and time_text | |
3366 | time_text = self._get_text(comment_renderer, 'publishedTimeText') or '' | |
3367 | timestamp = self._parse_time_text(time_text) | |
3368 | ||
3369 | info.update({ | |
3370 | # FIXME: non-standard, but we need a way of showing that it is an estimate. | |
3371 | '_time_text': time_text, | |
3372 | 'timestamp': timestamp, | |
3373 | }) | |
3374 | ||
3375 | info['author_url'] = urljoin( | |
3376 | 'https://www.youtube.com', traverse_obj(comment_renderer, ('authorEndpoint', ( | |
3377 | ('browseEndpoint', 'canonicalBaseUrl'), ('commandMetadata', 'webCommandMetadata', 'url'))), | |
3378 | expected_type=str, get_all=False)) | |
3379 | ||
3380 | author_is_uploader = traverse_obj(comment_renderer, 'authorIsChannelOwner') | |
3381 | if author_is_uploader is not None: | |
3382 | info['author_is_uploader'] = author_is_uploader | |
3383 | ||
3384 | comment_abr = traverse_obj( | |
3385 | comment_renderer, ('actionButtons', 'commentActionButtonsRenderer'), expected_type=dict) | |
3386 | if comment_abr is not None: | |
3387 | info['is_favorited'] = 'creatorHeart' in comment_abr | |
3388 | ||
3389 | badges = self._extract_badges([traverse_obj(comment_renderer, 'authorCommentBadge')]) | |
3390 | if self._has_badge(badges, BadgeType.VERIFIED): | |
3391 | info['author_is_verified'] = True | |
3392 | ||
3393 | is_pinned = traverse_obj(comment_renderer, 'pinnedCommentBadge') | |
3394 | if is_pinned: | |
3395 | info['is_pinned'] = True | |
3396 | ||
3397 | return info | |
3398 | ||
3399 | def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None): | |
3400 | ||
3401 | get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0] | |
3402 | ||
3403 | def extract_header(contents): | |
3404 | _continuation = None | |
3405 | for content in contents: | |
3406 | comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer') | |
3407 | expected_comment_count = self._get_count( | |
3408 | comments_header_renderer, 'countText', 'commentsCount') | |
3409 | ||
3410 | if expected_comment_count is not None: | |
3411 | tracker['est_total'] = expected_comment_count | |
3412 | self.to_screen(f'Downloading ~{expected_comment_count} comments') | |
3413 | comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top | |
3414 | ||
3415 | sort_menu_item = try_get( | |
3416 | comments_header_renderer, | |
3417 | lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {} | |
3418 | sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {} | |
3419 | ||
3420 | _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item) | |
3421 | if not _continuation: | |
3422 | continue | |
3423 | ||
3424 | sort_text = str_or_none(sort_menu_item.get('title')) | |
3425 | if not sort_text: | |
3426 | sort_text = 'top comments' if comment_sort_index == 0 else 'newest first' | |
3427 | self.to_screen('Sorting comments by %s' % sort_text.lower()) | |
3428 | break | |
3429 | return _continuation | |
3430 | ||
3431 | def extract_thread(contents, entity_payloads): | |
3432 | if not parent: | |
3433 | tracker['current_page_thread'] = 0 | |
3434 | for content in contents: | |
3435 | if not parent and tracker['total_parent_comments'] >= max_parents: | |
3436 | yield | |
3437 | comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer']) | |
3438 | ||
3439 | # old comment format | |
3440 | if not entity_payloads: | |
3441 | comment_renderer = get_first( | |
3442 | (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]], | |
3443 | expected_type=dict, default={}) | |
3444 | ||
3445 | comment = self._extract_comment_old(comment_renderer, parent) | |
3446 | ||
3447 | # new comment format | |
3448 | else: | |
3449 | view_model = ( | |
3450 | traverse_obj(comment_thread_renderer, ('commentViewModel', 'commentViewModel', {dict})) | |
3451 | or traverse_obj(content, ('commentViewModel', {dict}))) | |
3452 | comment_keys = traverse_obj(view_model, (('commentKey', 'toolbarStateKey'), {str})) | |
3453 | if not comment_keys: | |
3454 | continue | |
3455 | entities = traverse_obj(entity_payloads, lambda _, v: v['entityKey'] in comment_keys) | |
3456 | comment = self._extract_comment(entities, parent) | |
3457 | if comment: | |
3458 | comment['is_pinned'] = traverse_obj(view_model, ('pinnedText', {str})) is not None | |
3459 | ||
3460 | if not comment: | |
3461 | continue | |
3462 | comment_id = comment['id'] | |
3463 | ||
3464 | if comment.get('is_pinned'): | |
3465 | tracker['pinned_comment_ids'].add(comment_id) | |
3466 | # Sometimes YouTube may break and give us infinite looping comments. | |
3467 | # See: https://github.com/yt-dlp/yt-dlp/issues/6290 | |
3468 | if comment_id in tracker['seen_comment_ids']: | |
3469 | if comment_id in tracker['pinned_comment_ids'] and not comment.get('is_pinned'): | |
3470 | # Pinned comments may appear a second time in newest first sort | |
3471 | # See: https://github.com/yt-dlp/yt-dlp/issues/6712 | |
3472 | continue | |
3473 | self.report_warning( | |
3474 | 'Detected YouTube comments looping. Stopping comment extraction ' | |
3475 | f'{"for this thread" if parent else ""} as we probably cannot get any more.') | |
3476 | yield | |
3477 | else: | |
3478 | tracker['seen_comment_ids'].add(comment['id']) | |
3479 | ||
3480 | tracker['running_total'] += 1 | |
3481 | tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1 | |
3482 | yield comment | |
3483 | ||
3484 | # Attempt to get the replies | |
3485 | comment_replies_renderer = try_get( | |
3486 | comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict) | |
3487 | ||
3488 | if comment_replies_renderer: | |
3489 | tracker['current_page_thread'] += 1 | |
3490 | comment_entries_iter = self._comment_entries( | |
3491 | comment_replies_renderer, ytcfg, video_id, | |
3492 | parent=comment.get('id'), tracker=tracker) | |
3493 | yield from itertools.islice(comment_entries_iter, min( | |
3494 | max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))) | |
3495 | ||
3496 | # Keeps track of counts across recursive calls | |
3497 | if not tracker: | |
3498 | tracker = dict( | |
3499 | running_total=0, | |
3500 | est_total=None, | |
3501 | current_page_thread=0, | |
3502 | total_parent_comments=0, | |
3503 | total_reply_comments=0, | |
3504 | seen_comment_ids=set(), | |
3505 | pinned_comment_ids=set() | |
3506 | ) | |
3507 | ||
3508 | # TODO: Deprecated | |
3509 | # YouTube comments have a max depth of 2 | |
3510 | max_depth = int_or_none(get_single_config_arg('max_comment_depth')) | |
3511 | if max_depth: | |
3512 | self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. ' | |
3513 | 'Set max replies in the max-comments extractor argument instead') | |
3514 | if max_depth == 1 and parent: | |
3515 | return | |
3516 | ||
3517 | max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map( | |
3518 | lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4) | |
3519 | ||
3520 | continuation = self._extract_continuation(root_continuation_data) | |
3521 | ||
3522 | response = None | |
3523 | is_forced_continuation = False | |
3524 | is_first_continuation = parent is None | |
3525 | if is_first_continuation and not continuation: | |
3526 | # Sometimes you can get comments by generating the continuation yourself, | |
3527 | # even if YouTube initially reports them being disabled - e.g. stories comments. | |
3528 | # Note: if the comment section is actually disabled, YouTube may return a response with | |
3529 | # required check_get_keys missing. So we will disable that check initially in this case. | |
3530 | continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id)) | |
3531 | is_forced_continuation = True | |
3532 | ||
3533 | continuation_items_path = ( | |
3534 | 'onResponseReceivedEndpoints', ..., ('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems') | |
3535 | for page_num in itertools.count(0): | |
3536 | if not continuation: | |
3537 | break | |
3538 | headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)) | |
3539 | comment_prog_str = f"({tracker['running_total']}/~{tracker['est_total']})" | |
3540 | if page_num == 0: | |
3541 | if is_first_continuation: | |
3542 | note_prefix = 'Downloading comment section API JSON' | |
3543 | else: | |
3544 | note_prefix = ' Downloading comment API JSON reply thread %d %s' % ( | |
3545 | tracker['current_page_thread'], comment_prog_str) | |
3546 | else: | |
3547 | note_prefix = '%sDownloading comment%s API JSON page %d %s' % ( | |
3548 | ' ' if parent else '', ' replies' if parent else '', | |
3549 | page_num, comment_prog_str) | |
3550 | ||
3551 | # Do a deep check for incomplete data as sometimes YouTube may return no comments for a continuation | |
3552 | # Ignore check if YouTube says the comment count is 0. | |
3553 | check_get_keys = None | |
3554 | if not is_forced_continuation and not (tracker['est_total'] == 0 and tracker['running_total'] == 0): | |
3555 | check_get_keys = [[*continuation_items_path, ..., ( | |
3556 | 'commentsHeaderRenderer' if is_first_continuation else ('commentThreadRenderer', 'commentViewModel', 'commentRenderer'))]] | |
3557 | try: | |
3558 | response = self._extract_response( | |
3559 | item_id=None, query=continuation, | |
3560 | ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix, | |
3561 | check_get_keys=check_get_keys) | |
3562 | except ExtractorError as e: | |
3563 | # Ignore incomplete data error for replies if retries didn't work. | |
3564 | # This is to allow any other parent comments and comment threads to be downloaded. | |
3565 | # See: https://github.com/yt-dlp/yt-dlp/issues/4669 | |
3566 | if 'incomplete data' in str(e).lower() and parent: | |
3567 | if self.get_param('ignoreerrors') in (True, 'only_download'): | |
3568 | self.report_warning( | |
3569 | 'Received incomplete data for a comment reply thread and retrying did not help. ' | |
3570 | 'Ignoring to let other comments be downloaded. Pass --no-ignore-errors to not ignore.') | |
3571 | return | |
3572 | else: | |
3573 | raise ExtractorError( | |
3574 | 'Incomplete data received for comment reply thread. ' | |
3575 | 'Pass --ignore-errors to ignore and allow rest of comments to download.', | |
3576 | expected=True) | |
3577 | raise | |
3578 | is_forced_continuation = False | |
3579 | continuation = None | |
3580 | mutations = traverse_obj(response, ('frameworkUpdates', 'entityBatchUpdate', 'mutations', ..., {dict})) | |
3581 | for continuation_items in traverse_obj(response, continuation_items_path, expected_type=list, default=[]): | |
3582 | if is_first_continuation: | |
3583 | continuation = extract_header(continuation_items) | |
3584 | is_first_continuation = False | |
3585 | if continuation: | |
3586 | break | |
3587 | continue | |
3588 | ||
3589 | for entry in extract_thread(continuation_items, mutations): | |
3590 | if not entry: | |
3591 | return | |
3592 | yield entry | |
3593 | continuation = self._extract_continuation({'contents': continuation_items}) | |
3594 | if continuation: | |
3595 | break | |
3596 | ||
3597 | message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1) | |
3598 | if message and not parent and tracker['running_total'] == 0: | |
3599 | self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True) | |
3600 | raise self.CommentsDisabled | |
3601 | ||
3602 | @staticmethod | |
3603 | def _generate_comment_continuation(video_id): | |
3604 | """ | |
3605 | Generates initial comment section continuation token from given video id | |
3606 | """ | |
3607 | token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section' | |
3608 | return base64.b64encode(token.encode()).decode() | |
3609 | ||
3610 | def _get_comments(self, ytcfg, video_id, contents, webpage): | |
3611 | """Entry for comment extraction""" | |
3612 | def _real_comment_extract(contents): | |
3613 | renderer = next(( | |
3614 | item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={}) | |
3615 | if item.get('sectionIdentifier') == 'comment-item-section'), None) | |
3616 | yield from self._comment_entries(renderer, ytcfg, video_id) | |
3617 | ||
3618 | max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0]) | |
3619 | return itertools.islice(_real_comment_extract(contents), 0, max_comments) | |
3620 | ||
3621 | @staticmethod | |
3622 | def _get_checkok_params(): | |
3623 | return {'contentCheckOk': True, 'racyCheckOk': True} | |
3624 | ||
3625 | @classmethod | |
3626 | def _generate_player_context(cls, sts=None): | |
3627 | context = { | |
3628 | 'html5Preference': 'HTML5_PREF_WANTS', | |
3629 | } | |
3630 | if sts is not None: | |
3631 | context['signatureTimestamp'] = sts | |
3632 | return { | |
3633 | 'playbackContext': { | |
3634 | 'contentPlaybackContext': context | |
3635 | }, | |
3636 | **cls._get_checkok_params() | |
3637 | } | |
3638 | ||
3639 | @staticmethod | |
3640 | def _is_agegated(player_response): | |
3641 | if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')): | |
3642 | return True | |
3643 | ||
3644 | reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason'))) | |
3645 | AGE_GATE_REASONS = ( | |
3646 | 'confirm your age', 'age-restricted', 'inappropriate', # reason | |
3647 | 'age_verification_required', 'age_check_required', # status | |
3648 | ) | |
3649 | return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons) | |
3650 | ||
3651 | @staticmethod | |
3652 | def _is_unplayable(player_response): | |
3653 | return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE' | |
3654 | ||
3655 | def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data): | |
3656 | ||
3657 | session_index = self._extract_session_index(player_ytcfg, master_ytcfg) | |
3658 | syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr) | |
3659 | sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None | |
3660 | headers = self.generate_api_headers( | |
3661 | ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client) | |
3662 | ||
3663 | yt_query = { | |
3664 | 'videoId': video_id, | |
3665 | } | |
3666 | ||
3667 | pp_arg = self._configuration_arg('player_params', [None], casesense=True)[0] | |
3668 | if pp_arg: | |
3669 | yt_query['params'] = pp_arg | |
3670 | ||
3671 | yt_query.update(self._generate_player_context(sts)) | |
3672 | return self._extract_response( | |
3673 | item_id=video_id, ep='player', query=yt_query, | |
3674 | ytcfg=player_ytcfg, headers=headers, fatal=True, | |
3675 | default_client=client, | |
3676 | note='Downloading %s player API JSON' % client.replace('_', ' ').strip() | |
3677 | ) or None | |
3678 | ||
3679 | def _get_requested_clients(self, url, smuggled_data): | |
3680 | requested_clients = [] | |
3681 | android_clients = [] | |
3682 | default = ['ios', 'web'] | |
3683 | allowed_clients = sorted( | |
3684 | (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'), | |
3685 | key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True) | |
3686 | for client in self._configuration_arg('player_client'): | |
3687 | if client == 'default': | |
3688 | requested_clients.extend(default) | |
3689 | elif client == 'all': | |
3690 | requested_clients.extend(allowed_clients) | |
3691 | elif client not in allowed_clients: | |
3692 | self.report_warning(f'Skipping unsupported client {client}') | |
3693 | elif client.startswith('android'): | |
3694 | android_clients.append(client) | |
3695 | else: | |
3696 | requested_clients.append(client) | |
3697 | # Force deprioritization of broken Android clients for format de-duplication | |
3698 | requested_clients.extend(android_clients) | |
3699 | if not requested_clients: | |
3700 | requested_clients = default | |
3701 | ||
3702 | if smuggled_data.get('is_music_url') or self.is_music_url(url): | |
3703 | requested_clients.extend( | |
3704 | f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS) | |
3705 | ||
3706 | return orderedSet(requested_clients) | |
3707 | ||
3708 | def _invalid_player_response(self, pr, video_id): | |
3709 | # YouTube may return a different video player response than expected. | |
3710 | # See: https://github.com/TeamNewPipe/NewPipe/issues/8713 | |
3711 | if (pr_id := traverse_obj(pr, ('videoDetails', 'videoId'))) != video_id: | |
3712 | return pr_id | |
3713 | ||
3714 | def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data): | |
3715 | initial_pr = None | |
3716 | if webpage: | |
3717 | initial_pr = self._search_json( | |
3718 | self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False) | |
3719 | ||
3720 | prs = [] | |
3721 | if initial_pr and not self._invalid_player_response(initial_pr, video_id): | |
3722 | # Android player_response does not have microFormats which are needed for | |
3723 | # extraction of some data. So we return the initial_pr with formats | |
3724 | # stripped out even if not requested by the user | |
3725 | # See: https://github.com/yt-dlp/yt-dlp/issues/501 | |
3726 | prs.append({**initial_pr, 'streamingData': None}) | |
3727 | ||
3728 | all_clients = set(clients) | |
3729 | clients = clients[::-1] | |
3730 | ||
3731 | def append_client(*client_names): | |
3732 | """ Append the first client name that exists but not already used """ | |
3733 | for client_name in client_names: | |
3734 | actual_client = _split_innertube_client(client_name)[0] | |
3735 | if actual_client in INNERTUBE_CLIENTS: | |
3736 | if actual_client not in all_clients: | |
3737 | clients.append(client_name) | |
3738 | all_clients.add(actual_client) | |
3739 | return | |
3740 | ||
3741 | tried_iframe_fallback = False | |
3742 | player_url = None | |
3743 | skipped_clients = {} | |
3744 | while clients: | |
3745 | client, base_client, variant = _split_innertube_client(clients.pop()) | |
3746 | player_ytcfg = master_ytcfg if client == 'web' else {} | |
3747 | if 'configs' not in self._configuration_arg('player_skip') and client != 'web': | |
3748 | player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg | |
3749 | ||
3750 | player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage) | |
3751 | require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER') | |
3752 | if 'js' in self._configuration_arg('player_skip'): | |
3753 | require_js_player = False | |
3754 | player_url = None | |
3755 | ||
3756 | if not player_url and not tried_iframe_fallback and require_js_player: | |
3757 | player_url = self._download_player_url(video_id) | |
3758 | tried_iframe_fallback = True | |
3759 | ||
3760 | try: | |
3761 | pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response( | |
3762 | client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data) | |
3763 | except ExtractorError as e: | |
3764 | self.report_warning(e) | |
3765 | continue | |
3766 | ||
3767 | if pr_id := self._invalid_player_response(pr, video_id): | |
3768 | skipped_clients[client] = pr_id | |
3769 | elif pr: | |
3770 | # Save client name for introspection later | |
3771 | name = short_client_name(client) | |
3772 | sd = traverse_obj(pr, ('streamingData', {dict})) or {} | |
3773 | sd[STREAMING_DATA_CLIENT_NAME] = name | |
3774 | for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})): | |
3775 | f[STREAMING_DATA_CLIENT_NAME] = name | |
3776 | prs.append(pr) | |
3777 | ||
3778 | # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in | |
3779 | if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated: | |
3780 | append_client(f'{base_client}_creator') | |
3781 | elif self._is_agegated(pr): | |
3782 | if variant == 'tv_embedded': | |
3783 | append_client(f'{base_client}_embedded') | |
3784 | elif not variant: | |
3785 | append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded') | |
3786 | ||
3787 | if skipped_clients: | |
3788 | self.report_warning( | |
3789 | f'Skipping player responses from {"/".join(skipped_clients)} clients ' | |
3790 | f'(got player responses for video "{"/".join(set(skipped_clients.values()))}" instead of "{video_id}")') | |
3791 | if not prs: | |
3792 | raise ExtractorError( | |
3793 | 'All player responses are invalid. Your IP is likely being blocked by Youtube', expected=True) | |
3794 | elif not prs: | |
3795 | raise ExtractorError('Failed to extract any player response') | |
3796 | return prs, player_url | |
3797 | ||
3798 | def _needs_live_processing(self, live_status, duration): | |
3799 | if (live_status == 'is_live' and self.get_param('live_from_start') | |
3800 | or live_status == 'post_live' and (duration or 0) > 2 * 3600): | |
3801 | return live_status | |
3802 | ||
3803 | def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration): | |
3804 | CHUNK_SIZE = 10 << 20 | |
3805 | itags, stream_ids = collections.defaultdict(set), [] | |
3806 | itag_qualities, res_qualities = {}, {0: None} | |
3807 | q = qualities([ | |
3808 | # Normally tiny is the smallest video-only formats. But | |
3809 | # audio-only formats with unknown quality may get tagged as tiny | |
3810 | 'tiny', | |
3811 | 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats | |
3812 | 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres' | |
3813 | ]) | |
3814 | streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...)) | |
3815 | format_types = self._configuration_arg('formats') | |
3816 | all_formats = 'duplicate' in format_types | |
3817 | if self._configuration_arg('include_duplicate_formats'): | |
3818 | all_formats = True | |
3819 | self._downloader.deprecated_feature('[youtube] include_duplicate_formats extractor argument is deprecated. ' | |
3820 | 'Use formats=duplicate extractor argument instead') | |
3821 | ||
3822 | def build_fragments(f): | |
3823 | return LazyList({ | |
3824 | 'url': update_url_query(f['url'], { | |
3825 | 'range': f'{range_start}-{min(range_start + CHUNK_SIZE - 1, f["filesize"])}' | |
3826 | }) | |
3827 | } for range_start in range(0, f['filesize'], CHUNK_SIZE)) | |
3828 | ||
3829 | for fmt in streaming_formats: | |
3830 | if fmt.get('targetDurationSec'): | |
3831 | continue | |
3832 | ||
3833 | itag = str_or_none(fmt.get('itag')) | |
3834 | audio_track = fmt.get('audioTrack') or {} | |
3835 | stream_id = (itag, audio_track.get('id'), fmt.get('isDrc')) | |
3836 | if not all_formats: | |
3837 | if stream_id in stream_ids: | |
3838 | continue | |
3839 | ||
3840 | quality = fmt.get('quality') | |
3841 | height = int_or_none(fmt.get('height')) | |
3842 | if quality == 'tiny' or not quality: | |
3843 | quality = fmt.get('audioQuality', '').lower() or quality | |
3844 | # The 3gp format (17) in android client has a quality of "small", | |
3845 | # but is actually worse than other formats | |
3846 | if itag == '17': | |
3847 | quality = 'tiny' | |
3848 | if quality: | |
3849 | if itag: | |
3850 | itag_qualities[itag] = quality | |
3851 | if height: | |
3852 | res_qualities[height] = quality | |
3853 | # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment | |
3854 | # (adding `&sq=0` to the URL) and parsing emsg box to determine the | |
3855 | # number of fragment that would subsequently requested with (`&sq=N`) | |
3856 | if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF': | |
3857 | continue | |
3858 | ||
3859 | fmt_url = fmt.get('url') | |
3860 | if not fmt_url: | |
3861 | sc = urllib.parse.parse_qs(fmt.get('signatureCipher')) | |
3862 | fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0])) | |
3863 | encrypted_sig = try_get(sc, lambda x: x['s'][0]) | |
3864 | if not all((sc, fmt_url, player_url, encrypted_sig)): | |
3865 | continue | |
3866 | try: | |
3867 | fmt_url += '&%s=%s' % ( | |
3868 | traverse_obj(sc, ('sp', -1)) or 'signature', | |
3869 | self._decrypt_signature(encrypted_sig, video_id, player_url) | |
3870 | ) | |
3871 | except ExtractorError as e: | |
3872 | self.report_warning('Signature extraction failed: Some formats may be missing', | |
3873 | video_id=video_id, only_once=True) | |
3874 | self.write_debug(e, only_once=True) | |
3875 | continue | |
3876 | ||
3877 | query = parse_qs(fmt_url) | |
3878 | throttled = False | |
3879 | if query.get('n'): | |
3880 | try: | |
3881 | decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0]) | |
3882 | fmt_url = update_url_query(fmt_url, { | |
3883 | 'n': decrypt_nsig(query['n'][0], video_id, player_url) | |
3884 | }) | |
3885 | except ExtractorError as e: | |
3886 | phantomjs_hint = '' | |
3887 | if isinstance(e, JSInterpreter.Exception): | |
3888 | phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} ' | |
3889 | f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n') | |
3890 | if player_url: | |
3891 | self.report_warning( | |
3892 | f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}' | |
3893 | f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True) | |
3894 | self.write_debug(e, only_once=True) | |
3895 | else: | |
3896 | self.report_warning( | |
3897 | 'Cannot decrypt nsig without player_url: You may experience throttling for some formats', | |
3898 | video_id=video_id, only_once=True) | |
3899 | throttled = True | |
3900 | ||
3901 | tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) | |
3902 | language_preference = ( | |
3903 | 10 if audio_track.get('audioIsDefault') and 10 | |
3904 | else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10 | |
3905 | else -1) | |
3906 | format_duration = traverse_obj(fmt, ('approxDurationMs', {lambda x: float_or_none(x, 1000)})) | |
3907 | # Some formats may have much smaller duration than others (possibly damaged during encoding) | |
3908 | # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823 | |
3909 | # Make sure to avoid false positives with small duration differences. | |
3910 | # E.g. __2ABJjxzNo, ySuUZEjARPY | |
3911 | is_damaged = try_call(lambda: format_duration < duration // 2) | |
3912 | if is_damaged: | |
3913 | self.report_warning( | |
3914 | f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True) | |
3915 | ||
3916 | client_name = fmt.get(STREAMING_DATA_CLIENT_NAME) | |
3917 | # Android client formats are broken due to integrity check enforcement | |
3918 | # Ref: https://github.com/yt-dlp/yt-dlp/issues/9554 | |
3919 | is_broken = client_name and client_name.startswith(short_client_name('android')) | |
3920 | if is_broken: | |
3921 | self.report_warning( | |
3922 | f'{video_id}: Android client formats are broken and may yield HTTP Error 403. ' | |
3923 | 'They will be deprioritized', only_once=True) | |
3924 | ||
3925 | name = fmt.get('qualityLabel') or quality.replace('audio_quality_', '') or '' | |
3926 | fps = int_or_none(fmt.get('fps')) or 0 | |
3927 | dct = { | |
3928 | 'asr': int_or_none(fmt.get('audioSampleRate')), | |
3929 | 'filesize': int_or_none(fmt.get('contentLength')), | |
3930 | 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}', | |
3931 | 'format_note': join_nonempty( | |
3932 | join_nonempty(audio_track.get('displayName'), | |
3933 | language_preference > 0 and ' (default)', delim=''), | |
3934 | name, fmt.get('isDrc') and 'DRC', | |
3935 | try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()), | |
3936 | try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()), | |
3937 | throttled and 'THROTTLED', is_damaged and 'DAMAGED', is_broken and 'BROKEN', | |
3938 | (self.get_param('verbose') or all_formats) and client_name, | |
3939 | delim=', '), | |
3940 | # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372 | |
3941 | 'source_preference': ((-10 if throttled else -5 if itag == '22' else -1) | |
3942 | + (100 if 'Premium' in name else 0)), | |
3943 | 'fps': fps if fps > 1 else None, # For some formats, fps is wrongly returned as 1 | |
3944 | 'audio_channels': fmt.get('audioChannels'), | |
3945 | 'height': height, | |
3946 | 'quality': q(quality) - bool(fmt.get('isDrc')) / 2, | |
3947 | 'has_drm': bool(fmt.get('drmFamilies')), | |
3948 | 'tbr': tbr, | |
3949 | 'filesize_approx': filesize_from_tbr(tbr, format_duration), | |
3950 | 'url': fmt_url, | |
3951 | 'width': int_or_none(fmt.get('width')), | |
3952 | 'language': join_nonempty(audio_track.get('id', '').split('.')[0], | |
3953 | 'desc' if language_preference < -1 else '') or None, | |
3954 | 'language_preference': language_preference, | |
3955 | # Strictly de-prioritize broken, damaged and 3gp formats | |
3956 | 'preference': -20 if is_broken else -10 if is_damaged else -2 if itag == '17' else None, | |
3957 | } | |
3958 | mime_mobj = re.match( | |
3959 | r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '') | |
3960 | if mime_mobj: | |
3961 | dct['ext'] = mimetype2ext(mime_mobj.group(1)) | |
3962 | dct.update(parse_codecs(mime_mobj.group(2))) | |
3963 | if itag: | |
3964 | itags[itag].add(('https', dct.get('language'))) | |
3965 | stream_ids.append(stream_id) | |
3966 | single_stream = 'none' in (dct.get('acodec'), dct.get('vcodec')) | |
3967 | if single_stream and dct.get('ext'): | |
3968 | dct['container'] = dct['ext'] + '_dash' | |
3969 | ||
3970 | if (all_formats or 'dashy' in format_types) and dct['filesize']: | |
3971 | yield { | |
3972 | **dct, | |
3973 | 'format_id': f'{dct["format_id"]}-dashy' if all_formats else dct['format_id'], | |
3974 | 'protocol': 'http_dash_segments', | |
3975 | 'fragments': build_fragments(dct), | |
3976 | } | |
3977 | if all_formats or 'dashy' not in format_types: | |
3978 | dct['downloader_options'] = {'http_chunk_size': CHUNK_SIZE} | |
3979 | yield dct | |
3980 | ||
3981 | needs_live_processing = self._needs_live_processing(live_status, duration) | |
3982 | skip_bad_formats = 'incomplete' not in format_types | |
3983 | if self._configuration_arg('include_incomplete_formats'): | |
3984 | skip_bad_formats = False | |
3985 | self._downloader.deprecated_feature('[youtube] include_incomplete_formats extractor argument is deprecated. ' | |
3986 | 'Use formats=incomplete extractor argument instead') | |
3987 | ||
3988 | skip_manifests = set(self._configuration_arg('skip')) | |
3989 | if (not self.get_param('youtube_include_hls_manifest', True) | |
3990 | or needs_live_processing == 'is_live' # These will be filtered out by YoutubeDL anyway | |
3991 | or needs_live_processing and skip_bad_formats): | |
3992 | skip_manifests.add('hls') | |
3993 | ||
3994 | if not self.get_param('youtube_include_dash_manifest', True): | |
3995 | skip_manifests.add('dash') | |
3996 | if self._configuration_arg('include_live_dash'): | |
3997 | self._downloader.deprecated_feature('[youtube] include_live_dash extractor argument is deprecated. ' | |
3998 | 'Use formats=incomplete extractor argument instead') | |
3999 | elif skip_bad_formats and live_status == 'is_live' and needs_live_processing != 'is_live': | |
4000 | skip_manifests.add('dash') | |
4001 | ||
4002 | def process_manifest_format(f, proto, client_name, itag): | |
4003 | key = (proto, f.get('language')) | |
4004 | if not all_formats and key in itags[itag]: | |
4005 | return False | |
4006 | itags[itag].add(key) | |
4007 | ||
4008 | if itag and all_formats: | |
4009 | f['format_id'] = f'{itag}-{proto}' | |
4010 | elif any(p != proto for p, _ in itags[itag]): | |
4011 | f['format_id'] = f'{itag}-{proto}' | |
4012 | elif itag: | |
4013 | f['format_id'] = itag | |
4014 | ||
4015 | if f.get('source_preference') is None: | |
4016 | f['source_preference'] = -1 | |
4017 | ||
4018 | if itag in ('616', '235'): | |
4019 | f['format_note'] = join_nonempty(f.get('format_note'), 'Premium', delim=' ') | |
4020 | f['source_preference'] += 100 | |
4021 | ||
4022 | f['quality'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id'].split('-')[0]), -1)) | |
4023 | if f['quality'] == -1 and f.get('height'): | |
4024 | f['quality'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height']))]) | |
4025 | if self.get_param('verbose') or all_formats: | |
4026 | f['format_note'] = join_nonempty(f.get('format_note'), client_name, delim=', ') | |
4027 | if f.get('fps') and f['fps'] <= 1: | |
4028 | del f['fps'] | |
4029 | ||
4030 | if proto == 'hls' and f.get('has_drm'): | |
4031 | f['has_drm'] = 'maybe' | |
4032 | f['source_preference'] -= 5 | |
4033 | return True | |
4034 | ||
4035 | subtitles = {} | |
4036 | for sd in streaming_data: | |
4037 | client_name = sd.get(STREAMING_DATA_CLIENT_NAME) | |
4038 | ||
4039 | hls_manifest_url = 'hls' not in skip_manifests and sd.get('hlsManifestUrl') | |
4040 | if hls_manifest_url: | |
4041 | fmts, subs = self._extract_m3u8_formats_and_subtitles( | |
4042 | hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live') | |
4043 | subtitles = self._merge_subtitles(subs, subtitles) | |
4044 | for f in fmts: | |
4045 | if process_manifest_format(f, 'hls', client_name, self._search_regex( | |
4046 | r'/itag/(\d+)', f['url'], 'itag', default=None)): | |
4047 | yield f | |
4048 | ||
4049 | dash_manifest_url = 'dash' not in skip_manifests and sd.get('dashManifestUrl') | |
4050 | if dash_manifest_url: | |
4051 | formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False) | |
4052 | subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH | |
4053 | for f in formats: | |
4054 | if process_manifest_format(f, 'dash', client_name, f['format_id']): | |
4055 | f['filesize'] = int_or_none(self._search_regex( | |
4056 | r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None)) | |
4057 | if needs_live_processing: | |
4058 | f['is_from_start'] = True | |
4059 | ||
4060 | yield f | |
4061 | yield subtitles | |
4062 | ||
4063 | def _extract_storyboard(self, player_responses, duration): | |
4064 | spec = get_first( | |
4065 | player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1] | |
4066 | base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None)) | |
4067 | if not base_url: | |
4068 | return | |
4069 | L = len(spec) - 1 | |
4070 | for i, args in enumerate(spec): | |
4071 | args = args.split('#') | |
4072 | counts = list(map(int_or_none, args[:5])) | |
4073 | if len(args) != 8 or not all(counts): | |
4074 | self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}') | |
4075 | continue | |
4076 | width, height, frame_count, cols, rows = counts | |
4077 | N, sigh = args[6:] | |
4078 | ||
4079 | url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}' | |
4080 | fragment_count = frame_count / (cols * rows) | |
4081 | fragment_duration = duration / fragment_count | |
4082 | yield { | |
4083 | 'format_id': f'sb{i}', | |
4084 | 'format_note': 'storyboard', | |
4085 | 'ext': 'mhtml', | |
4086 | 'protocol': 'mhtml', | |
4087 | 'acodec': 'none', | |
4088 | 'vcodec': 'none', | |
4089 | 'url': url, | |
4090 | 'width': width, | |
4091 | 'height': height, | |
4092 | 'fps': frame_count / duration, | |
4093 | 'rows': rows, | |
4094 | 'columns': cols, | |
4095 | 'fragments': [{ | |
4096 | 'url': url.replace('$M', str(j)), | |
4097 | 'duration': min(fragment_duration, duration - (j * fragment_duration)), | |
4098 | } for j in range(math.ceil(fragment_count))], | |
4099 | } | |
4100 | ||
4101 | def _download_player_responses(self, url, smuggled_data, video_id, webpage_url): | |
4102 | webpage = None | |
4103 | if 'webpage' not in self._configuration_arg('player_skip'): | |
4104 | query = {'bpctr': '9999999999', 'has_verified': '1'} | |
4105 | pp = self._configuration_arg('player_params', [None], casesense=True)[0] | |
4106 | if pp: | |
4107 | query['pp'] = pp | |
4108 | webpage = self._download_webpage( | |
4109 | webpage_url, video_id, fatal=False, query=query) | |
4110 | ||
4111 | master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg() | |
4112 | ||
4113 | player_responses, player_url = self._extract_player_responses( | |
4114 | self._get_requested_clients(url, smuggled_data), | |
4115 | video_id, webpage, master_ytcfg, smuggled_data) | |
4116 | ||
4117 | return webpage, master_ytcfg, player_responses, player_url | |
4118 | ||
4119 | def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None): | |
4120 | live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails')) | |
4121 | is_live = get_first(video_details, 'isLive') | |
4122 | if is_live is None: | |
4123 | is_live = get_first(live_broadcast_details, 'isLiveNow') | |
4124 | live_content = get_first(video_details, 'isLiveContent') | |
4125 | is_upcoming = get_first(video_details, 'isUpcoming') | |
4126 | post_live = get_first(video_details, 'isPostLiveDvr') | |
4127 | live_status = ('post_live' if post_live | |
4128 | else 'is_live' if is_live | |
4129 | else 'is_upcoming' if is_upcoming | |
4130 | else 'was_live' if live_content | |
4131 | else 'not_live' if False in (is_live, live_content) | |
4132 | else None) | |
4133 | streaming_data = traverse_obj(player_responses, (..., 'streamingData')) | |
4134 | *formats, subtitles = self._extract_formats_and_subtitles(streaming_data, video_id, player_url, live_status, duration) | |
4135 | if all(f.get('has_drm') for f in formats): | |
4136 | # If there are no formats that definitely don't have DRM, all have DRM | |
4137 | for f in formats: | |
4138 | f['has_drm'] = True | |
4139 | ||
4140 | return live_broadcast_details, live_status, streaming_data, formats, subtitles | |
4141 | ||
4142 | def _real_extract(self, url): | |
4143 | url, smuggled_data = unsmuggle_url(url, {}) | |
4144 | video_id = self._match_id(url) | |
4145 | ||
4146 | base_url = self.http_scheme() + '//www.youtube.com/' | |
4147 | webpage_url = base_url + 'watch?v=' + video_id | |
4148 | ||
4149 | webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url) | |
4150 | ||
4151 | playability_statuses = traverse_obj( | |
4152 | player_responses, (..., 'playabilityStatus'), expected_type=dict) | |
4153 | ||
4154 | trailer_video_id = get_first( | |
4155 | playability_statuses, | |
4156 | ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'), | |
4157 | expected_type=str) | |
4158 | if trailer_video_id: | |
4159 | return self.url_result( | |
4160 | trailer_video_id, self.ie_key(), trailer_video_id) | |
4161 | ||
4162 | search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None)) | |
4163 | if webpage else (lambda x: None)) | |
4164 | ||
4165 | video_details = traverse_obj(player_responses, (..., 'videoDetails'), expected_type=dict) | |
4166 | microformats = traverse_obj( | |
4167 | player_responses, (..., 'microformat', 'playerMicroformatRenderer'), | |
4168 | expected_type=dict) | |
4169 | ||
4170 | translated_title = self._get_text(microformats, (..., 'title')) | |
4171 | video_title = (self._preferred_lang and translated_title | |
4172 | or get_first(video_details, 'title') # primary | |
4173 | or translated_title | |
4174 | or search_meta(['og:title', 'twitter:title', 'title'])) | |
4175 | translated_description = self._get_text(microformats, (..., 'description')) | |
4176 | original_description = get_first(video_details, 'shortDescription') | |
4177 | video_description = ( | |
4178 | self._preferred_lang and translated_description | |
4179 | # If original description is blank, it will be an empty string. | |
4180 | # Do not prefer translated description in this case. | |
4181 | or original_description if original_description is not None else translated_description) | |
4182 | ||
4183 | multifeed_metadata_list = get_first( | |
4184 | player_responses, | |
4185 | ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'), | |
4186 | expected_type=str) | |
4187 | if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'): | |
4188 | if self.get_param('noplaylist'): | |
4189 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
4190 | else: | |
4191 | entries = [] | |
4192 | feed_ids = [] | |
4193 | for feed in multifeed_metadata_list.split(','): | |
4194 | # Unquote should take place before split on comma (,) since textual | |
4195 | # fields may contain comma as well (see | |
4196 | # https://github.com/ytdl-org/youtube-dl/issues/8536) | |
4197 | feed_data = urllib.parse.parse_qs( | |
4198 | urllib.parse.unquote_plus(feed)) | |
4199 | ||
4200 | def feed_entry(name): | |
4201 | return try_get( | |
4202 | feed_data, lambda x: x[name][0], str) | |
4203 | ||
4204 | feed_id = feed_entry('id') | |
4205 | if not feed_id: | |
4206 | continue | |
4207 | feed_title = feed_entry('title') | |
4208 | title = video_title | |
4209 | if feed_title: | |
4210 | title += ' (%s)' % feed_title | |
4211 | entries.append({ | |
4212 | '_type': 'url_transparent', | |
4213 | 'ie_key': 'Youtube', | |
4214 | 'url': smuggle_url( | |
4215 | '%swatch?v=%s' % (base_url, feed_data['id'][0]), | |
4216 | {'force_singlefeed': True}), | |
4217 | 'title': title, | |
4218 | }) | |
4219 | feed_ids.append(feed_id) | |
4220 | self.to_screen( | |
4221 | 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' | |
4222 | % (', '.join(feed_ids), video_id)) | |
4223 | return self.playlist_result( | |
4224 | entries, video_id, video_title, video_description) | |
4225 | ||
4226 | duration = (int_or_none(get_first(video_details, 'lengthSeconds')) | |
4227 | or int_or_none(get_first(microformats, 'lengthSeconds')) | |
4228 | or parse_duration(search_meta('duration')) or None) | |
4229 | ||
4230 | live_broadcast_details, live_status, streaming_data, formats, automatic_captions = \ | |
4231 | self._list_formats(video_id, microformats, video_details, player_responses, player_url, duration) | |
4232 | if live_status == 'post_live': | |
4233 | self.write_debug(f'{video_id}: Video is in Post-Live Manifestless mode') | |
4234 | ||
4235 | if not formats: | |
4236 | if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')): | |
4237 | self.report_drm(video_id) | |
4238 | pemr = get_first( | |
4239 | playability_statuses, | |
4240 | ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {} | |
4241 | reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason') | |
4242 | subreason = clean_html(self._get_text(pemr, 'subreason') or '') | |
4243 | if subreason: | |
4244 | if subreason == 'The uploader has not made this video available in your country.': | |
4245 | countries = get_first(microformats, 'availableCountries') | |
4246 | if not countries: | |
4247 | regions_allowed = search_meta('regionsAllowed') | |
4248 | countries = regions_allowed.split(',') if regions_allowed else None | |
4249 | self.raise_geo_restricted(subreason, countries, metadata_available=True) | |
4250 | reason += f'. {subreason}' | |
4251 | if reason: | |
4252 | self.raise_no_formats(reason, expected=True) | |
4253 | ||
4254 | keywords = get_first(video_details, 'keywords', expected_type=list) or [] | |
4255 | if not keywords and webpage: | |
4256 | keywords = [ | |
4257 | unescapeHTML(m.group('content')) | |
4258 | for m in re.finditer(self._meta_regex('og:video:tag'), webpage)] | |
4259 | for keyword in keywords: | |
4260 | if keyword.startswith('yt:stretch='): | |
4261 | mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword) | |
4262 | if mobj: | |
4263 | # NB: float is intentional for forcing float division | |
4264 | w, h = (float(v) for v in mobj.groups()) | |
4265 | if w > 0 and h > 0: | |
4266 | ratio = w / h | |
4267 | for f in formats: | |
4268 | if f.get('vcodec') != 'none': | |
4269 | f['stretched_ratio'] = ratio | |
4270 | break | |
4271 | thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail')) | |
4272 | thumbnail_url = search_meta(['og:image', 'twitter:image']) | |
4273 | if thumbnail_url: | |
4274 | thumbnails.append({ | |
4275 | 'url': thumbnail_url, | |
4276 | }) | |
4277 | original_thumbnails = thumbnails.copy() | |
4278 | ||
4279 | # The best resolution thumbnails sometimes does not appear in the webpage | |
4280 | # See: https://github.com/yt-dlp/yt-dlp/issues/340 | |
4281 | # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029> | |
4282 | thumbnail_names = [ | |
4283 | # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants | |
4284 | # in resolution, these are not the custom thumbnail. So de-prioritize them | |
4285 | 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default', | |
4286 | 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3' | |
4287 | ] | |
4288 | n_thumbnail_names = len(thumbnail_names) | |
4289 | thumbnails.extend({ | |
4290 | 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format( | |
4291 | video_id=video_id, name=name, ext=ext, | |
4292 | webp='_webp' if ext == 'webp' else '', live='_live' if live_status == 'is_live' else ''), | |
4293 | } for name in thumbnail_names for ext in ('webp', 'jpg')) | |
4294 | for thumb in thumbnails: | |
4295 | i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names) | |
4296 | thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i) | |
4297 | self._remove_duplicate_formats(thumbnails) | |
4298 | self._downloader._sort_thumbnails(original_thumbnails) | |
4299 | ||
4300 | category = get_first(microformats, 'category') or search_meta('genre') | |
4301 | channel_id = self.ucid_or_none(str_or_none( | |
4302 | get_first(video_details, 'channelId') | |
4303 | or get_first(microformats, 'externalChannelId') | |
4304 | or search_meta('channelId'))) | |
4305 | owner_profile_url = get_first(microformats, 'ownerProfileUrl') | |
4306 | ||
4307 | live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp')) | |
4308 | live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp')) | |
4309 | if not duration and live_end_time and live_start_time: | |
4310 | duration = live_end_time - live_start_time | |
4311 | ||
4312 | needs_live_processing = self._needs_live_processing(live_status, duration) | |
4313 | ||
4314 | def is_bad_format(fmt): | |
4315 | if needs_live_processing and not fmt.get('is_from_start'): | |
4316 | return True | |
4317 | elif (live_status == 'is_live' and needs_live_processing != 'is_live' | |
4318 | and fmt.get('protocol') == 'http_dash_segments'): | |
4319 | return True | |
4320 | ||
4321 | for fmt in filter(is_bad_format, formats): | |
4322 | fmt['preference'] = (fmt.get('preference') or -1) - 10 | |
4323 | fmt['format_note'] = join_nonempty(fmt.get('format_note'), '(Last 2 hours)', delim=' ') | |
4324 | ||
4325 | if needs_live_processing: | |
4326 | self._prepare_live_from_start_formats( | |
4327 | formats, video_id, live_start_time, url, webpage_url, smuggled_data, live_status == 'is_live') | |
4328 | ||
4329 | formats.extend(self._extract_storyboard(player_responses, duration)) | |
4330 | ||
4331 | channel_handle = self.handle_from_url(owner_profile_url) | |
4332 | ||
4333 | info = { | |
4334 | 'id': video_id, | |
4335 | 'title': video_title, | |
4336 | 'formats': formats, | |
4337 | 'thumbnails': thumbnails, | |
4338 | # The best thumbnail that we are sure exists. Prevents unnecessary | |
4339 | # URL checking if user don't care about getting the best possible thumbnail | |
4340 | 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')), | |
4341 | 'description': video_description, | |
4342 | 'channel_id': channel_id, | |
4343 | 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None), | |
4344 | 'duration': duration, | |
4345 | 'view_count': int_or_none( | |
4346 | get_first((video_details, microformats), (..., 'viewCount')) | |
4347 | or search_meta('interactionCount')), | |
4348 | 'average_rating': float_or_none(get_first(video_details, 'averageRating')), | |
4349 | 'age_limit': 18 if ( | |
4350 | get_first(microformats, 'isFamilySafe') is False | |
4351 | or search_meta('isFamilyFriendly') == 'false' | |
4352 | or search_meta('og:restrictions:age') == '18+') else 0, | |
4353 | 'webpage_url': webpage_url, | |
4354 | 'categories': [category] if category else None, | |
4355 | 'tags': keywords, | |
4356 | 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'), | |
4357 | 'live_status': live_status, | |
4358 | 'release_timestamp': live_start_time, | |
4359 | '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats | |
4360 | 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto') | |
4361 | } | |
4362 | ||
4363 | subtitles = {} | |
4364 | pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict) | |
4365 | if pctr: | |
4366 | def get_lang_code(track): | |
4367 | return (remove_start(track.get('vssId') or '', '.').replace('.', '-') | |
4368 | or track.get('languageCode')) | |
4369 | ||
4370 | # Converted into dicts to remove duplicates | |
4371 | captions = { | |
4372 | get_lang_code(sub): sub | |
4373 | for sub in traverse_obj(pctr, (..., 'captionTracks', ...))} | |
4374 | translation_languages = { | |
4375 | lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1) | |
4376 | for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))} | |
4377 | ||
4378 | def process_language(container, base_url, lang_code, sub_name, query): | |
4379 | lang_subs = container.setdefault(lang_code, []) | |
4380 | for fmt in self._SUBTITLE_FORMATS: | |
4381 | query.update({ | |
4382 | 'fmt': fmt, | |
4383 | }) | |
4384 | lang_subs.append({ | |
4385 | 'ext': fmt, | |
4386 | 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)), | |
4387 | 'name': sub_name, | |
4388 | }) | |
4389 | ||
4390 | # NB: Constructing the full subtitle dictionary is slow | |
4391 | get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and ( | |
4392 | self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles')) | |
4393 | for lang_code, caption_track in captions.items(): | |
4394 | base_url = caption_track.get('baseUrl') | |
4395 | orig_lang = parse_qs(base_url).get('lang', [None])[-1] | |
4396 | if not base_url: | |
4397 | continue | |
4398 | lang_name = self._get_text(caption_track, 'name', max_runs=1) | |
4399 | if caption_track.get('kind') != 'asr': | |
4400 | if not lang_code: | |
4401 | continue | |
4402 | process_language( | |
4403 | subtitles, base_url, lang_code, lang_name, {}) | |
4404 | if not caption_track.get('isTranslatable'): | |
4405 | continue | |
4406 | for trans_code, trans_name in translation_languages.items(): | |
4407 | if not trans_code: | |
4408 | continue | |
4409 | orig_trans_code = trans_code | |
4410 | if caption_track.get('kind') != 'asr' and trans_code != 'und': | |
4411 | if not get_translated_subs: | |
4412 | continue | |
4413 | trans_code += f'-{lang_code}' | |
4414 | trans_name += format_field(lang_name, None, ' from %s') | |
4415 | if lang_code == f'a-{orig_trans_code}': | |
4416 | # Set audio language based on original subtitles | |
4417 | for f in formats: | |
4418 | if f.get('acodec') != 'none' and not f.get('language'): | |
4419 | f['language'] = orig_trans_code | |
4420 | # Add an "-orig" label to the original language so that it can be distinguished. | |
4421 | # The subs are returned without "-orig" as well for compatibility | |
4422 | process_language( | |
4423 | automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {}) | |
4424 | # Setting tlang=lang returns damaged subtitles. | |
4425 | process_language(automatic_captions, base_url, trans_code, trans_name, | |
4426 | {} if orig_lang == orig_trans_code else {'tlang': trans_code}) | |
4427 | ||
4428 | info['automatic_captions'] = automatic_captions | |
4429 | info['subtitles'] = subtitles | |
4430 | ||
4431 | parsed_url = urllib.parse.urlparse(url) | |
4432 | for component in [parsed_url.fragment, parsed_url.query]: | |
4433 | query = urllib.parse.parse_qs(component) | |
4434 | for k, v in query.items(): | |
4435 | for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]: | |
4436 | d_k += '_time' | |
4437 | if d_k not in info and k in s_ks: | |
4438 | info[d_k] = parse_duration(query[k][0]) | |
4439 | ||
4440 | # Youtube Music Auto-generated description | |
4441 | if (video_description or '').strip().endswith('\nAuto-generated by YouTube.'): | |
4442 | # XXX: Causes catastrophic backtracking if description has "·" | |
4443 | # E.g. https://www.youtube.com/watch?v=DoPaAxMQoiI | |
4444 | # Simulating atomic groups: (?P<a>[^xy]+)x => (?=(?P<a>[^xy]+))(?P=a)x | |
4445 | # reduces it, but does not fully fix it. https://regex101.com/r/8Ssf2h/2 | |
4446 | mobj = re.search( | |
4447 | r'''(?xs) | |
4448 | (?=(?P<track>[^\n·]+))(?P=track)· | |
4449 | (?=(?P<artist>[^\n]+))(?P=artist)\n+ | |
4450 | (?=(?P<album>[^\n]+))(?P=album)\n | |
4451 | (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))? | |
4452 | (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))? | |
4453 | (.+?\nArtist\s*:\s* | |
4454 | (?=(?P<clean_artist>[^\n]+))(?P=clean_artist)\n | |
4455 | )?.+\nAuto-generated\ by\ YouTube\.\s*$ | |
4456 | ''', video_description) | |
4457 | if mobj: | |
4458 | release_year = mobj.group('release_year') | |
4459 | release_date = mobj.group('release_date') | |
4460 | if release_date: | |
4461 | release_date = release_date.replace('-', '') | |
4462 | if not release_year: | |
4463 | release_year = release_date[:4] | |
4464 | info.update({ | |
4465 | 'album': mobj.group('album'.strip()), | |
4466 | 'artists': ([a] if (a := mobj.group('clean_artist')) | |
4467 | else [a.strip() for a in mobj.group('artist').split('·')]), | |
4468 | 'track': mobj.group('track').strip(), | |
4469 | 'release_date': release_date, | |
4470 | 'release_year': int_or_none(release_year), | |
4471 | }) | |
4472 | ||
4473 | initial_data = None | |
4474 | if webpage: | |
4475 | initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False) | |
4476 | if not traverse_obj(initial_data, 'contents'): | |
4477 | self.report_warning('Incomplete data received in embedded initial data; re-fetching using API.') | |
4478 | initial_data = None | |
4479 | if not initial_data: | |
4480 | query = {'videoId': video_id} | |
4481 | query.update(self._get_checkok_params()) | |
4482 | initial_data = self._extract_response( | |
4483 | item_id=video_id, ep='next', fatal=False, | |
4484 | ytcfg=master_ytcfg, query=query, check_get_keys='contents', | |
4485 | headers=self.generate_api_headers(ytcfg=master_ytcfg), | |
4486 | note='Downloading initial data API JSON') | |
4487 | ||
4488 | info['comment_count'] = traverse_obj(initial_data, ( | |
4489 | 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer', | |
4490 | 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount' | |
4491 | ), ( | |
4492 | 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section', | |
4493 | 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo' | |
4494 | ), expected_type=self._get_count, get_all=False) | |
4495 | ||
4496 | try: # This will error if there is no livechat | |
4497 | initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation'] | |
4498 | except (KeyError, IndexError, TypeError): | |
4499 | pass | |
4500 | else: | |
4501 | info.setdefault('subtitles', {})['live_chat'] = [{ | |
4502 | # url is needed to set cookies | |
4503 | 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1', | |
4504 | 'video_id': video_id, | |
4505 | 'ext': 'json', | |
4506 | 'protocol': ('youtube_live_chat' if live_status in ('is_live', 'is_upcoming') | |
4507 | else 'youtube_live_chat_replay'), | |
4508 | }] | |
4509 | ||
4510 | if initial_data: | |
4511 | info['chapters'] = ( | |
4512 | self._extract_chapters_from_json(initial_data, duration) | |
4513 | or self._extract_chapters_from_engagement_panel(initial_data, duration) | |
4514 | or self._extract_chapters_from_description(video_description, duration) | |
4515 | or None) | |
4516 | ||
4517 | info['heatmap'] = self._extract_heatmap(initial_data) | |
4518 | ||
4519 | contents = traverse_obj( | |
4520 | initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'), | |
4521 | expected_type=list, default=[]) | |
4522 | ||
4523 | vpir = get_first(contents, 'videoPrimaryInfoRenderer') | |
4524 | if vpir: | |
4525 | stl = vpir.get('superTitleLink') | |
4526 | if stl: | |
4527 | stl = self._get_text(stl) | |
4528 | if try_get( | |
4529 | vpir, | |
4530 | lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN': | |
4531 | info['location'] = stl | |
4532 | else: | |
4533 | mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl) | |
4534 | if mobj: | |
4535 | info.update({ | |
4536 | 'series': mobj.group(1), | |
4537 | 'season_number': int(mobj.group(2)), | |
4538 | 'episode_number': int(mobj.group(3)), | |
4539 | }) | |
4540 | for tlb in (try_get( | |
4541 | vpir, | |
4542 | lambda x: x['videoActions']['menuRenderer']['topLevelButtons'], | |
4543 | list) or []): | |
4544 | tbrs = variadic( | |
4545 | traverse_obj( | |
4546 | tlb, ('toggleButtonRenderer', ...), | |
4547 | ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer'))) | |
4548 | for tbr in tbrs: | |
4549 | for getter, regex in [( | |
4550 | lambda x: x['defaultText']['accessibility']['accessibilityData'], | |
4551 | r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([ | |
4552 | lambda x: x['accessibility'], | |
4553 | lambda x: x['accessibilityData']['accessibilityData'], | |
4554 | ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]: | |
4555 | label = (try_get(tbr, getter, dict) or {}).get('label') | |
4556 | if label: | |
4557 | mobj = re.match(regex, label) | |
4558 | if mobj: | |
4559 | info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count')) | |
4560 | break | |
4561 | ||
4562 | info['like_count'] = traverse_obj(vpir, ( | |
4563 | 'videoActions', 'menuRenderer', 'topLevelButtons', ..., | |
4564 | 'segmentedLikeDislikeButtonViewModel', 'likeButtonViewModel', 'likeButtonViewModel', | |
4565 | 'toggleButtonViewModel', 'toggleButtonViewModel', 'defaultButtonViewModel', | |
4566 | 'buttonViewModel', 'accessibilityText', {parse_count}), get_all=False) | |
4567 | ||
4568 | vcr = traverse_obj(vpir, ('viewCount', 'videoViewCountRenderer')) | |
4569 | if vcr: | |
4570 | vc = self._get_count(vcr, 'viewCount') | |
4571 | # Upcoming premieres with waiting count are treated as live here | |
4572 | if vcr.get('isLive'): | |
4573 | info['concurrent_view_count'] = vc | |
4574 | elif info.get('view_count') is None: | |
4575 | info['view_count'] = vc | |
4576 | ||
4577 | vsir = get_first(contents, 'videoSecondaryInfoRenderer') | |
4578 | if vsir: | |
4579 | vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer')) | |
4580 | info.update({ | |
4581 | 'channel': self._get_text(vor, 'title'), | |
4582 | 'channel_follower_count': self._get_count(vor, 'subscriberCountText')}) | |
4583 | ||
4584 | if not channel_handle: | |
4585 | channel_handle = self.handle_from_url( | |
4586 | traverse_obj(vor, ( | |
4587 | ('navigationEndpoint', ('title', 'runs', ..., 'navigationEndpoint')), | |
4588 | (('commandMetadata', 'webCommandMetadata', 'url'), ('browseEndpoint', 'canonicalBaseUrl')), | |
4589 | {str}), get_all=False)) | |
4590 | ||
4591 | rows = try_get( | |
4592 | vsir, | |
4593 | lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'], | |
4594 | list) or [] | |
4595 | multiple_songs = False | |
4596 | for row in rows: | |
4597 | if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True: | |
4598 | multiple_songs = True | |
4599 | break | |
4600 | for row in rows: | |
4601 | mrr = row.get('metadataRowRenderer') or {} | |
4602 | mrr_title = mrr.get('title') | |
4603 | if not mrr_title: | |
4604 | continue | |
4605 | mrr_title = self._get_text(mrr, 'title') | |
4606 | mrr_contents_text = self._get_text(mrr, ('contents', 0)) | |
4607 | if mrr_title == 'License': | |
4608 | info['license'] = mrr_contents_text | |
4609 | elif not multiple_songs: | |
4610 | if mrr_title == 'Album': | |
4611 | info['album'] = mrr_contents_text | |
4612 | elif mrr_title == 'Artist': | |
4613 | info['artists'] = [mrr_contents_text] if mrr_contents_text else None | |
4614 | elif mrr_title == 'Song': | |
4615 | info['track'] = mrr_contents_text | |
4616 | owner_badges = self._extract_badges(traverse_obj(vsir, ('owner', 'videoOwnerRenderer', 'badges'))) | |
4617 | if self._has_badge(owner_badges, BadgeType.VERIFIED): | |
4618 | info['channel_is_verified'] = True | |
4619 | ||
4620 | info.update({ | |
4621 | 'uploader': info.get('channel'), | |
4622 | 'uploader_id': channel_handle, | |
4623 | 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None), | |
4624 | }) | |
4625 | # The upload date for scheduled, live and past live streams / premieres in microformats | |
4626 | # may be different from the stream date. Although not in UTC, we will prefer it in this case. | |
4627 | # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139 | |
4628 | upload_date = ( | |
4629 | unified_strdate(get_first(microformats, 'uploadDate')) | |
4630 | or unified_strdate(search_meta('uploadDate'))) | |
4631 | if not upload_date or ( | |
4632 | live_status in ('not_live', None) | |
4633 | and 'no-youtube-prefer-utc-upload-date' not in self.get_param('compat_opts', []) | |
4634 | ): | |
4635 | upload_date = strftime_or_none( | |
4636 | self._parse_time_text(self._get_text(vpir, 'dateText'))) or upload_date | |
4637 | info['upload_date'] = upload_date | |
4638 | ||
4639 | if upload_date and live_status not in ('is_live', 'post_live', 'is_upcoming'): | |
4640 | # Newly uploaded videos' HLS formats are potentially problematic and need to be checked | |
4641 | upload_datetime = datetime_from_str(upload_date).replace(tzinfo=dt.timezone.utc) | |
4642 | if upload_datetime >= datetime_from_str('today-2days'): | |
4643 | for fmt in info['formats']: | |
4644 | if fmt.get('protocol') == 'm3u8_native': | |
4645 | fmt['__needs_testing'] = True | |
4646 | ||
4647 | for s_k, d_k in [('artists', 'creators'), ('track', 'alt_title')]: | |
4648 | v = info.get(s_k) | |
4649 | if v: | |
4650 | info[d_k] = v | |
4651 | ||
4652 | badges = self._extract_badges(traverse_obj(vpir, 'badges')) | |
4653 | ||
4654 | is_private = (self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) | |
4655 | or get_first(video_details, 'isPrivate', expected_type=bool)) | |
4656 | ||
4657 | info['availability'] = ( | |
4658 | 'public' if self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC) | |
4659 | else self._availability( | |
4660 | is_private=is_private, | |
4661 | needs_premium=( | |
4662 | self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) | |
4663 | or False if initial_data and is_private is not None else None), | |
4664 | needs_subscription=( | |
4665 | self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) | |
4666 | or False if initial_data and is_private is not None else None), | |
4667 | needs_auth=info['age_limit'] >= 18, | |
4668 | is_unlisted=None if is_private is None else ( | |
4669 | self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) | |
4670 | or get_first(microformats, 'isUnlisted', expected_type=bool)))) | |
4671 | ||
4672 | info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage) | |
4673 | ||
4674 | self.mark_watched(video_id, player_responses) | |
4675 | ||
4676 | return info | |
4677 | ||
4678 | ||
4679 | class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor): | |
4680 | @staticmethod | |
4681 | def passthrough_smuggled_data(func): | |
4682 | def _smuggle(info, smuggled_data): | |
4683 | if info.get('_type') not in ('url', 'url_transparent'): | |
4684 | return info | |
4685 | if smuggled_data.get('is_music_url'): | |
4686 | parsed_url = urllib.parse.urlparse(info['url']) | |
4687 | if parsed_url.netloc in ('www.youtube.com', 'music.youtube.com'): | |
4688 | smuggled_data.pop('is_music_url') | |
4689 | info['url'] = urllib.parse.urlunparse(parsed_url._replace(netloc='music.youtube.com')) | |
4690 | if smuggled_data: | |
4691 | info['url'] = smuggle_url(info['url'], smuggled_data) | |
4692 | return info | |
4693 | ||
4694 | @functools.wraps(func) | |
4695 | def wrapper(self, url): | |
4696 | url, smuggled_data = unsmuggle_url(url, {}) | |
4697 | if self.is_music_url(url): | |
4698 | smuggled_data['is_music_url'] = True | |
4699 | info_dict = func(self, url, smuggled_data) | |
4700 | if smuggled_data: | |
4701 | _smuggle(info_dict, smuggled_data) | |
4702 | if info_dict.get('entries'): | |
4703 | info_dict['entries'] = (_smuggle(i, smuggled_data.copy()) for i in info_dict['entries']) | |
4704 | return info_dict | |
4705 | return wrapper | |
4706 | ||
4707 | @staticmethod | |
4708 | def _extract_basic_item_renderer(item): | |
4709 | # Modified from _extract_grid_item_renderer | |
4710 | known_basic_renderers = ( | |
4711 | 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer' | |
4712 | ) | |
4713 | for key, renderer in item.items(): | |
4714 | if not isinstance(renderer, dict): | |
4715 | continue | |
4716 | elif key in known_basic_renderers: | |
4717 | return renderer | |
4718 | elif key.startswith('grid') and key.endswith('Renderer'): | |
4719 | return renderer | |
4720 | ||
4721 | def _extract_channel_renderer(self, renderer): | |
4722 | channel_id = self.ucid_or_none(renderer['channelId']) | |
4723 | title = self._get_text(renderer, 'title') | |
4724 | channel_url = format_field(channel_id, None, 'https://www.youtube.com/channel/%s', default=None) | |
4725 | channel_handle = self.handle_from_url( | |
4726 | traverse_obj(renderer, ( | |
4727 | 'navigationEndpoint', (('commandMetadata', 'webCommandMetadata', 'url'), | |
4728 | ('browseEndpoint', 'canonicalBaseUrl')), | |
4729 | {str}), get_all=False)) | |
4730 | if not channel_handle: | |
4731 | # As of 2023-06-01, YouTube sets subscriberCountText to the handle in search | |
4732 | channel_handle = self.handle_or_none(self._get_text(renderer, 'subscriberCountText')) | |
4733 | return { | |
4734 | '_type': 'url', | |
4735 | 'url': channel_url, | |
4736 | 'id': channel_id, | |
4737 | 'ie_key': YoutubeTabIE.ie_key(), | |
4738 | 'channel': title, | |
4739 | 'uploader': title, | |
4740 | 'channel_id': channel_id, | |
4741 | 'channel_url': channel_url, | |
4742 | 'title': title, | |
4743 | 'uploader_id': channel_handle, | |
4744 | 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None), | |
4745 | # See above. YouTube sets videoCountText to the subscriber text in search channel renderers. | |
4746 | # However, in feed/channels this is set correctly to the subscriber count | |
4747 | 'channel_follower_count': traverse_obj( | |
4748 | renderer, 'subscriberCountText', 'videoCountText', expected_type=self._get_count), | |
4749 | 'thumbnails': self._extract_thumbnails(renderer, 'thumbnail'), | |
4750 | 'playlist_count': ( | |
4751 | # videoCountText may be the subscriber count | |
4752 | self._get_count(renderer, 'videoCountText') | |
4753 | if self._get_count(renderer, 'subscriberCountText') is not None else None), | |
4754 | 'description': self._get_text(renderer, 'descriptionSnippet'), | |
4755 | 'channel_is_verified': True if self._has_badge( | |
4756 | self._extract_badges(traverse_obj(renderer, 'ownerBadges')), BadgeType.VERIFIED) else None, | |
4757 | } | |
4758 | ||
4759 | def _grid_entries(self, grid_renderer): | |
4760 | for item in grid_renderer['items']: | |
4761 | if not isinstance(item, dict): | |
4762 | continue | |
4763 | renderer = self._extract_basic_item_renderer(item) | |
4764 | if not isinstance(renderer, dict): | |
4765 | continue | |
4766 | title = self._get_text(renderer, 'title') | |
4767 | ||
4768 | # playlist | |
4769 | playlist_id = renderer.get('playlistId') | |
4770 | if playlist_id: | |
4771 | yield self.url_result( | |
4772 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, | |
4773 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id, | |
4774 | video_title=title) | |
4775 | continue | |
4776 | # video | |
4777 | video_id = renderer.get('videoId') | |
4778 | if video_id: | |
4779 | yield self._extract_video(renderer) | |
4780 | continue | |
4781 | # channel | |
4782 | channel_id = renderer.get('channelId') | |
4783 | if channel_id: | |
4784 | yield self._extract_channel_renderer(renderer) | |
4785 | continue | |
4786 | # generic endpoint URL support | |
4787 | ep_url = urljoin('https://www.youtube.com/', try_get( | |
4788 | renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'], | |
4789 | str)) | |
4790 | if ep_url: | |
4791 | for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE): | |
4792 | if ie.suitable(ep_url): | |
4793 | yield self.url_result( | |
4794 | ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title) | |
4795 | break | |
4796 | ||
4797 | def _music_reponsive_list_entry(self, renderer): | |
4798 | video_id = traverse_obj(renderer, ('playlistItemData', 'videoId')) | |
4799 | if video_id: | |
4800 | title = traverse_obj(renderer, ( | |
4801 | 'flexColumns', 0, 'musicResponsiveListItemFlexColumnRenderer', | |
4802 | 'text', 'runs', 0, 'text')) | |
4803 | return self.url_result(f'https://music.youtube.com/watch?v={video_id}', | |
4804 | ie=YoutubeIE.ie_key(), video_id=video_id, title=title) | |
4805 | playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId')) | |
4806 | if playlist_id: | |
4807 | video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId')) | |
4808 | if video_id: | |
4809 | return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}', | |
4810 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
4811 | return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}', | |
4812 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
4813 | browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId')) | |
4814 | if browse_id: | |
4815 | return self.url_result(f'https://music.youtube.com/browse/{browse_id}', | |
4816 | ie=YoutubeTabIE.ie_key(), video_id=browse_id) | |
4817 | ||
4818 | def _shelf_entries_from_content(self, shelf_renderer): | |
4819 | content = shelf_renderer.get('content') | |
4820 | if not isinstance(content, dict): | |
4821 | return | |
4822 | renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer') | |
4823 | if renderer: | |
4824 | # TODO: add support for nested playlists so each shelf is processed | |
4825 | # as separate playlist | |
4826 | # TODO: this includes only first N items | |
4827 | yield from self._grid_entries(renderer) | |
4828 | renderer = content.get('horizontalListRenderer') | |
4829 | if renderer: | |
4830 | # TODO | |
4831 | pass | |
4832 | ||
4833 | def _shelf_entries(self, shelf_renderer, skip_channels=False): | |
4834 | ep = try_get( | |
4835 | shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], | |
4836 | str) | |
4837 | shelf_url = urljoin('https://www.youtube.com', ep) | |
4838 | if shelf_url: | |
4839 | # Skipping links to another channels, note that checking for | |
4840 | # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL | |
4841 | # will not work | |
4842 | if skip_channels and '/channels?' in shelf_url: | |
4843 | return | |
4844 | title = self._get_text(shelf_renderer, 'title') | |
4845 | yield self.url_result(shelf_url, video_title=title) | |
4846 | # Shelf may not contain shelf URL, fallback to extraction from content | |
4847 | yield from self._shelf_entries_from_content(shelf_renderer) | |
4848 | ||
4849 | def _playlist_entries(self, video_list_renderer): | |
4850 | for content in video_list_renderer['contents']: | |
4851 | if not isinstance(content, dict): | |
4852 | continue | |
4853 | renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer') | |
4854 | if not isinstance(renderer, dict): | |
4855 | continue | |
4856 | video_id = renderer.get('videoId') | |
4857 | if not video_id: | |
4858 | continue | |
4859 | yield self._extract_video(renderer) | |
4860 | ||
4861 | def _rich_entries(self, rich_grid_renderer): | |
4862 | renderer = traverse_obj( | |
4863 | rich_grid_renderer, | |
4864 | ('content', ('videoRenderer', 'reelItemRenderer', 'playlistRenderer')), get_all=False) or {} | |
4865 | video_id = renderer.get('videoId') | |
4866 | if video_id: | |
4867 | yield self._extract_video(renderer) | |
4868 | return | |
4869 | playlist_id = renderer.get('playlistId') | |
4870 | if playlist_id: | |
4871 | yield self.url_result( | |
4872 | f'https://www.youtube.com/playlist?list={playlist_id}', | |
4873 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id, | |
4874 | video_title=self._get_text(renderer, 'title')) | |
4875 | return | |
4876 | ||
4877 | def _video_entry(self, video_renderer): | |
4878 | video_id = video_renderer.get('videoId') | |
4879 | if video_id: | |
4880 | return self._extract_video(video_renderer) | |
4881 | ||
4882 | def _hashtag_tile_entry(self, hashtag_tile_renderer): | |
4883 | url = urljoin('https://youtube.com', traverse_obj( | |
4884 | hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url'))) | |
4885 | if url: | |
4886 | return self.url_result( | |
4887 | url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag')) | |
4888 | ||
4889 | def _post_thread_entries(self, post_thread_renderer): | |
4890 | post_renderer = try_get( | |
4891 | post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict) | |
4892 | if not post_renderer: | |
4893 | return | |
4894 | # video attachment | |
4895 | video_renderer = try_get( | |
4896 | post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {} | |
4897 | video_id = video_renderer.get('videoId') | |
4898 | if video_id: | |
4899 | entry = self._extract_video(video_renderer) | |
4900 | if entry: | |
4901 | yield entry | |
4902 | # playlist attachment | |
4903 | playlist_id = try_get( | |
4904 | post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], str) | |
4905 | if playlist_id: | |
4906 | yield self.url_result( | |
4907 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, | |
4908 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
4909 | # inline video links | |
4910 | runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or [] | |
4911 | for run in runs: | |
4912 | if not isinstance(run, dict): | |
4913 | continue | |
4914 | ep_url = try_get( | |
4915 | run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], str) | |
4916 | if not ep_url: | |
4917 | continue | |
4918 | if not YoutubeIE.suitable(ep_url): | |
4919 | continue | |
4920 | ep_video_id = YoutubeIE._match_id(ep_url) | |
4921 | if video_id == ep_video_id: | |
4922 | continue | |
4923 | yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id) | |
4924 | ||
4925 | def _post_thread_continuation_entries(self, post_thread_continuation): | |
4926 | contents = post_thread_continuation.get('contents') | |
4927 | if not isinstance(contents, list): | |
4928 | return | |
4929 | for content in contents: | |
4930 | renderer = content.get('backstagePostThreadRenderer') | |
4931 | if isinstance(renderer, dict): | |
4932 | yield from self._post_thread_entries(renderer) | |
4933 | continue | |
4934 | renderer = content.get('videoRenderer') | |
4935 | if isinstance(renderer, dict): | |
4936 | yield self._video_entry(renderer) | |
4937 | ||
4938 | r''' # unused | |
4939 | def _rich_grid_entries(self, contents): | |
4940 | for content in contents: | |
4941 | video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict) | |
4942 | if video_renderer: | |
4943 | entry = self._video_entry(video_renderer) | |
4944 | if entry: | |
4945 | yield entry | |
4946 | ''' | |
4947 | ||
4948 | def _report_history_entries(self, renderer): | |
4949 | for url in traverse_obj(renderer, ( | |
4950 | 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ..., | |
4951 | 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ..., | |
4952 | 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')): | |
4953 | yield self.url_result(urljoin('https://www.youtube.com', url), YoutubeIE) | |
4954 | ||
4955 | def _extract_entries(self, parent_renderer, continuation_list): | |
4956 | # continuation_list is modified in-place with continuation_list = [continuation_token] | |
4957 | continuation_list[:] = [None] | |
4958 | contents = try_get(parent_renderer, lambda x: x['contents'], list) or [] | |
4959 | for content in contents: | |
4960 | if not isinstance(content, dict): | |
4961 | continue | |
4962 | is_renderer = traverse_obj( | |
4963 | content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation', | |
4964 | expected_type=dict) | |
4965 | if not is_renderer: | |
4966 | if content.get('richItemRenderer'): | |
4967 | for entry in self._rich_entries(content['richItemRenderer']): | |
4968 | yield entry | |
4969 | continuation_list[0] = self._extract_continuation(parent_renderer) | |
4970 | elif content.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory | |
4971 | table = traverse_obj(content, ('reportHistorySectionRenderer', 'table', 'tableRenderer')) | |
4972 | yield from self._report_history_entries(table) | |
4973 | continuation_list[0] = self._extract_continuation(table) | |
4974 | continue | |
4975 | ||
4976 | isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or [] | |
4977 | for isr_content in isr_contents: | |
4978 | if not isinstance(isr_content, dict): | |
4979 | continue | |
4980 | ||
4981 | known_renderers = { | |
4982 | 'playlistVideoListRenderer': self._playlist_entries, | |
4983 | 'gridRenderer': self._grid_entries, | |
4984 | 'reelShelfRenderer': self._grid_entries, | |
4985 | 'shelfRenderer': self._shelf_entries, | |
4986 | 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)], | |
4987 | 'backstagePostThreadRenderer': self._post_thread_entries, | |
4988 | 'videoRenderer': lambda x: [self._video_entry(x)], | |
4989 | 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}), | |
4990 | 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}), | |
4991 | 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)], | |
4992 | 'richGridRenderer': lambda x: self._extract_entries(x, continuation_list), | |
4993 | } | |
4994 | for key, renderer in isr_content.items(): | |
4995 | if key not in known_renderers: | |
4996 | continue | |
4997 | for entry in known_renderers[key](renderer): | |
4998 | if entry: | |
4999 | yield entry | |
5000 | continuation_list[0] = self._extract_continuation(renderer) | |
5001 | break | |
5002 | ||
5003 | if not continuation_list[0]: | |
5004 | continuation_list[0] = self._extract_continuation(is_renderer) | |
5005 | ||
5006 | if not continuation_list[0]: | |
5007 | continuation_list[0] = self._extract_continuation(parent_renderer) | |
5008 | ||
5009 | def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data): | |
5010 | continuation_list = [None] | |
5011 | extract_entries = lambda x: self._extract_entries(x, continuation_list) | |
5012 | tab_content = try_get(tab, lambda x: x['content'], dict) | |
5013 | if not tab_content: | |
5014 | return | |
5015 | parent_renderer = ( | |
5016 | try_get(tab_content, lambda x: x['sectionListRenderer'], dict) | |
5017 | or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {}) | |
5018 | yield from extract_entries(parent_renderer) | |
5019 | continuation = continuation_list[0] | |
5020 | seen_continuations = set() | |
5021 | for page_num in itertools.count(1): | |
5022 | if not continuation: | |
5023 | break | |
5024 | continuation_token = continuation.get('continuation') | |
5025 | if continuation_token is not None and continuation_token in seen_continuations: | |
5026 | self.write_debug('Detected YouTube feed looping - assuming end of feed.') | |
5027 | break | |
5028 | seen_continuations.add(continuation_token) | |
5029 | headers = self.generate_api_headers( | |
5030 | ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data) | |
5031 | response = self._extract_response( | |
5032 | item_id=f'{item_id} page {page_num}', | |
5033 | query=continuation, headers=headers, ytcfg=ytcfg, | |
5034 | check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints')) | |
5035 | ||
5036 | if not response: | |
5037 | break | |
5038 | # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases | |
5039 | # See: https://github.com/ytdl-org/youtube-dl/issues/28702 | |
5040 | visitor_data = self._extract_visitor_data(response) or visitor_data | |
5041 | ||
5042 | known_renderers = { | |
5043 | 'videoRenderer': (self._grid_entries, 'items'), # for membership tab | |
5044 | 'gridPlaylistRenderer': (self._grid_entries, 'items'), | |
5045 | 'gridVideoRenderer': (self._grid_entries, 'items'), | |
5046 | 'gridChannelRenderer': (self._grid_entries, 'items'), | |
5047 | 'playlistVideoRenderer': (self._playlist_entries, 'contents'), | |
5048 | 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds | |
5049 | 'richItemRenderer': (extract_entries, 'contents'), # for hashtag | |
5050 | 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents'), | |
5051 | 'reportHistoryTableRowRenderer': (self._report_history_entries, 'rows'), | |
5052 | 'playlistVideoListContinuation': (self._playlist_entries, None), | |
5053 | 'gridContinuation': (self._grid_entries, None), | |
5054 | 'itemSectionContinuation': (self._post_thread_continuation_entries, None), | |
5055 | 'sectionListContinuation': (extract_entries, None), # for feeds | |
5056 | } | |
5057 | ||
5058 | continuation_items = traverse_obj(response, ( | |
5059 | ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ..., | |
5060 | 'appendContinuationItemsAction', 'continuationItems' | |
5061 | ), 'continuationContents', get_all=False) | |
5062 | continuation_item = traverse_obj(continuation_items, 0, None, expected_type=dict, default={}) | |
5063 | ||
5064 | video_items_renderer = None | |
5065 | for key in continuation_item.keys(): | |
5066 | if key not in known_renderers: | |
5067 | continue | |
5068 | func, parent_key = known_renderers[key] | |
5069 | video_items_renderer = {parent_key: continuation_items} if parent_key else continuation_items | |
5070 | continuation_list = [None] | |
5071 | yield from func(video_items_renderer) | |
5072 | continuation = continuation_list[0] or self._extract_continuation(video_items_renderer) | |
5073 | ||
5074 | if not video_items_renderer: | |
5075 | break | |
5076 | ||
5077 | @staticmethod | |
5078 | def _extract_selected_tab(tabs, fatal=True): | |
5079 | for tab_renderer in tabs: | |
5080 | if tab_renderer.get('selected'): | |
5081 | return tab_renderer | |
5082 | if fatal: | |
5083 | raise ExtractorError('Unable to find selected tab') | |
5084 | ||
5085 | @staticmethod | |
5086 | def _extract_tab_renderers(response): | |
5087 | return traverse_obj( | |
5088 | response, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type=dict) | |
5089 | ||
5090 | def _extract_from_tabs(self, item_id, ytcfg, data, tabs): | |
5091 | metadata = self._extract_metadata_from_tabs(item_id, data) | |
5092 | ||
5093 | selected_tab = self._extract_selected_tab(tabs) | |
5094 | metadata['title'] += format_field(selected_tab, 'title', ' - %s') | |
5095 | metadata['title'] += format_field(selected_tab, 'expandedText', ' - %s') | |
5096 | ||
5097 | return self.playlist_result( | |
5098 | self._entries( | |
5099 | selected_tab, metadata['id'], ytcfg, | |
5100 | self._extract_account_syncid(ytcfg, data), | |
5101 | self._extract_visitor_data(data, ytcfg)), | |
5102 | **metadata) | |
5103 | ||
5104 | def _extract_metadata_from_tabs(self, item_id, data): | |
5105 | info = {'id': item_id} | |
5106 | ||
5107 | metadata_renderer = traverse_obj(data, ('metadata', 'channelMetadataRenderer'), expected_type=dict) | |
5108 | if metadata_renderer: | |
5109 | channel_id = traverse_obj(metadata_renderer, ('externalId', {self.ucid_or_none}), | |
5110 | ('channelUrl', {self.ucid_from_url})) | |
5111 | info.update({ | |
5112 | 'channel': metadata_renderer.get('title'), | |
5113 | 'channel_id': channel_id, | |
5114 | }) | |
5115 | if info['channel_id']: | |
5116 | info['id'] = info['channel_id'] | |
5117 | else: | |
5118 | metadata_renderer = traverse_obj(data, ('metadata', 'playlistMetadataRenderer'), expected_type=dict) | |
5119 | ||
5120 | # We can get the uncropped banner/avatar by replacing the crop params with '=s0' | |
5121 | # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714 | |
5122 | def _get_uncropped(url): | |
5123 | return url_or_none((url or '').split('=')[0] + '=s0') | |
5124 | ||
5125 | avatar_thumbnails = self._extract_thumbnails(metadata_renderer, 'avatar') | |
5126 | if avatar_thumbnails: | |
5127 | uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url']) | |
5128 | if uncropped_avatar: | |
5129 | avatar_thumbnails.append({ | |
5130 | 'url': uncropped_avatar, | |
5131 | 'id': 'avatar_uncropped', | |
5132 | 'preference': 1 | |
5133 | }) | |
5134 | ||
5135 | channel_banners = self._extract_thumbnails( | |
5136 | data, ('header', ..., ('banner', 'mobileBanner', 'tvBanner'))) | |
5137 | for banner in channel_banners: | |
5138 | banner['preference'] = -10 | |
5139 | ||
5140 | if channel_banners: | |
5141 | uncropped_banner = _get_uncropped(channel_banners[0]['url']) | |
5142 | if uncropped_banner: | |
5143 | channel_banners.append({ | |
5144 | 'url': uncropped_banner, | |
5145 | 'id': 'banner_uncropped', | |
5146 | 'preference': -5 | |
5147 | }) | |
5148 | ||
5149 | # Deprecated - remove primary_sidebar_renderer when layout discontinued | |
5150 | primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') | |
5151 | playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer'), expected_type=dict) | |
5152 | ||
5153 | primary_thumbnails = self._extract_thumbnails( | |
5154 | primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail')) | |
5155 | playlist_thumbnails = self._extract_thumbnails( | |
5156 | playlist_header_renderer, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail')) | |
5157 | ||
5158 | info.update({ | |
5159 | 'title': (traverse_obj(metadata_renderer, 'title') | |
5160 | or self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) | |
5161 | or info['id']), | |
5162 | 'availability': self._extract_availability(data), | |
5163 | 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')), | |
5164 | 'description': try_get(metadata_renderer, lambda x: x.get('description', '')), | |
5165 | 'tags': (traverse_obj(data, ('microformat', 'microformatDataRenderer', 'tags', ..., {str})) | |
5166 | or traverse_obj(metadata_renderer, ('keywords', {lambda x: x and shlex.split(x)}, ...))), | |
5167 | 'thumbnails': (primary_thumbnails or playlist_thumbnails) + avatar_thumbnails + channel_banners, | |
5168 | }) | |
5169 | ||
5170 | channel_handle = ( | |
5171 | traverse_obj(metadata_renderer, (('vanityChannelUrl', ('ownerUrls', ...)), {self.handle_from_url}), get_all=False) | |
5172 | or traverse_obj(data, ('header', ..., 'channelHandleText', {self.handle_or_none}), get_all=False)) | |
5173 | ||
5174 | if channel_handle: | |
5175 | info.update({ | |
5176 | 'uploader_id': channel_handle, | |
5177 | 'uploader_url': format_field(channel_handle, None, 'https://www.youtube.com/%s', default=None), | |
5178 | }) | |
5179 | ||
5180 | channel_badges = self._extract_badges(traverse_obj(data, ('header', ..., 'badges'), get_all=False)) | |
5181 | if self._has_badge(channel_badges, BadgeType.VERIFIED): | |
5182 | info['channel_is_verified'] = True | |
5183 | # Playlist stats is a text runs array containing [video count, view count, last updated]. | |
5184 | # last updated or (view count and last updated) may be missing. | |
5185 | playlist_stats = get_first( | |
5186 | (primary_sidebar_renderer, playlist_header_renderer), (('stats', 'briefStats', 'numVideosText'), )) | |
5187 | ||
5188 | last_updated_unix = self._parse_time_text( | |
5189 | self._get_text(playlist_stats, 2) # deprecated, remove when old layout discontinued | |
5190 | or self._get_text(playlist_header_renderer, ('byline', 1, 'playlistBylineRenderer', 'text'))) | |
5191 | info['modified_date'] = strftime_or_none(last_updated_unix) | |
5192 | ||
5193 | info['view_count'] = self._get_count(playlist_stats, 1) | |
5194 | if info['view_count'] is None: # 0 is allowed | |
5195 | info['view_count'] = self._get_count(playlist_header_renderer, 'viewCountText') | |
5196 | if info['view_count'] is None: | |
5197 | info['view_count'] = self._get_count(data, ( | |
5198 | 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer', | |
5199 | 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText')) | |
5200 | ||
5201 | info['playlist_count'] = self._get_count(playlist_stats, 0) | |
5202 | if info['playlist_count'] is None: # 0 is allowed | |
5203 | info['playlist_count'] = self._get_count(playlist_header_renderer, ('byline', 0, 'playlistBylineRenderer', 'text')) | |
5204 | ||
5205 | if not info.get('channel_id'): | |
5206 | owner = traverse_obj(playlist_header_renderer, 'ownerText') | |
5207 | if not owner: # Deprecated | |
5208 | owner = traverse_obj( | |
5209 | self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer'), | |
5210 | ('videoOwner', 'videoOwnerRenderer', 'title')) | |
5211 | owner_text = self._get_text(owner) | |
5212 | browse_ep = traverse_obj(owner, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {} | |
5213 | info.update({ | |
5214 | 'channel': self._search_regex(r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text), | |
5215 | 'channel_id': self.ucid_or_none(browse_ep.get('browseId')), | |
5216 | 'uploader_id': self.handle_from_url(urljoin('https://www.youtube.com', browse_ep.get('canonicalBaseUrl'))) | |
5217 | }) | |
5218 | ||
5219 | info.update({ | |
5220 | 'uploader': info['channel'], | |
5221 | 'channel_url': format_field(info.get('channel_id'), None, 'https://www.youtube.com/channel/%s', default=None), | |
5222 | 'uploader_url': format_field(info.get('uploader_id'), None, 'https://www.youtube.com/%s', default=None), | |
5223 | }) | |
5224 | ||
5225 | return info | |
5226 | ||
5227 | def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg): | |
5228 | first_id = last_id = response = None | |
5229 | for page_num in itertools.count(1): | |
5230 | videos = list(self._playlist_entries(playlist)) | |
5231 | if not videos: | |
5232 | return | |
5233 | start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1 | |
5234 | if start >= len(videos): | |
5235 | return | |
5236 | yield from videos[start:] | |
5237 | first_id = first_id or videos[0]['id'] | |
5238 | last_id = videos[-1]['id'] | |
5239 | watch_endpoint = try_get( | |
5240 | playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint']) | |
5241 | headers = self.generate_api_headers( | |
5242 | ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data), | |
5243 | visitor_data=self._extract_visitor_data(response, data, ytcfg)) | |
5244 | query = { | |
5245 | 'playlistId': playlist_id, | |
5246 | 'videoId': watch_endpoint.get('videoId') or last_id, | |
5247 | 'index': watch_endpoint.get('index') or len(videos), | |
5248 | 'params': watch_endpoint.get('params') or 'OAE%3D' | |
5249 | } | |
5250 | response = self._extract_response( | |
5251 | item_id='%s page %d' % (playlist_id, page_num), | |
5252 | query=query, ep='next', headers=headers, ytcfg=ytcfg, | |
5253 | check_get_keys='contents' | |
5254 | ) | |
5255 | playlist = try_get( | |
5256 | response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict) | |
5257 | ||
5258 | def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg): | |
5259 | title = playlist.get('title') or try_get( | |
5260 | data, lambda x: x['titleText']['simpleText'], str) | |
5261 | playlist_id = playlist.get('playlistId') or item_id | |
5262 | ||
5263 | # Delegating everything except mix playlists to regular tab-based playlist URL | |
5264 | playlist_url = urljoin(url, try_get( | |
5265 | playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], | |
5266 | str)) | |
5267 | ||
5268 | # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1] | |
5269 | # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg | |
5270 | is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id) | |
5271 | ||
5272 | if playlist_url and playlist_url != url and not is_known_unviewable: | |
5273 | return self.url_result( | |
5274 | playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id, | |
5275 | video_title=title) | |
5276 | ||
5277 | return self.playlist_result( | |
5278 | self._extract_inline_playlist(playlist, playlist_id, data, ytcfg), | |
5279 | playlist_id=playlist_id, playlist_title=title) | |
5280 | ||
5281 | def _extract_availability(self, data): | |
5282 | """ | |
5283 | Gets the availability of a given playlist/tab. | |
5284 | Note: Unless YouTube tells us explicitly, we do not assume it is public | |
5285 | @param data: response | |
5286 | """ | |
5287 | sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {} | |
5288 | playlist_header_renderer = traverse_obj(data, ('header', 'playlistHeaderRenderer')) or {} | |
5289 | player_header_privacy = playlist_header_renderer.get('privacy') | |
5290 | ||
5291 | badges = self._extract_badges(traverse_obj(sidebar_renderer, 'badges')) | |
5292 | ||
5293 | # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge | |
5294 | privacy_setting_icon = get_first( | |
5295 | (playlist_header_renderer, sidebar_renderer), | |
5296 | ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries', | |
5297 | lambda _, v: v['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'), | |
5298 | expected_type=str) | |
5299 | ||
5300 | microformats_is_unlisted = traverse_obj( | |
5301 | data, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type=bool) | |
5302 | ||
5303 | return ( | |
5304 | 'public' if ( | |
5305 | self._has_badge(badges, BadgeType.AVAILABILITY_PUBLIC) | |
5306 | or player_header_privacy == 'PUBLIC' | |
5307 | or privacy_setting_icon == 'PRIVACY_PUBLIC') | |
5308 | else self._availability( | |
5309 | is_private=( | |
5310 | self._has_badge(badges, BadgeType.AVAILABILITY_PRIVATE) | |
5311 | or player_header_privacy == 'PRIVATE' if player_header_privacy is not None | |
5312 | else privacy_setting_icon == 'PRIVACY_PRIVATE' if privacy_setting_icon is not None else None), | |
5313 | is_unlisted=( | |
5314 | self._has_badge(badges, BadgeType.AVAILABILITY_UNLISTED) | |
5315 | or player_header_privacy == 'UNLISTED' if player_header_privacy is not None | |
5316 | else privacy_setting_icon == 'PRIVACY_UNLISTED' if privacy_setting_icon is not None | |
5317 | else microformats_is_unlisted if microformats_is_unlisted is not None else None), | |
5318 | needs_subscription=self._has_badge(badges, BadgeType.AVAILABILITY_SUBSCRIPTION) or None, | |
5319 | needs_premium=self._has_badge(badges, BadgeType.AVAILABILITY_PREMIUM) or None, | |
5320 | needs_auth=False)) | |
5321 | ||
5322 | @staticmethod | |
5323 | def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict): | |
5324 | sidebar_renderer = try_get( | |
5325 | data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or [] | |
5326 | for item in sidebar_renderer: | |
5327 | renderer = try_get(item, lambda x: x[info_renderer], expected_type) | |
5328 | if renderer: | |
5329 | return renderer | |
5330 | ||
5331 | def _reload_with_unavailable_videos(self, item_id, data, ytcfg): | |
5332 | """ | |
5333 | Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.) | |
5334 | """ | |
5335 | is_playlist = bool(traverse_obj( | |
5336 | data, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer'))) | |
5337 | if not is_playlist: | |
5338 | return | |
5339 | headers = self.generate_api_headers( | |
5340 | ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data), | |
5341 | visitor_data=self._extract_visitor_data(data, ytcfg)) | |
5342 | query = { | |
5343 | 'params': 'wgYCCAA=', | |
5344 | 'browseId': f'VL{item_id}' | |
5345 | } | |
5346 | return self._extract_response( | |
5347 | item_id=item_id, headers=headers, query=query, | |
5348 | check_get_keys='contents', fatal=False, ytcfg=ytcfg, | |
5349 | note='Redownloading playlist API JSON with unavailable videos') | |
5350 | ||
5351 | @functools.cached_property | |
5352 | def skip_webpage(self): | |
5353 | return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) | |
5354 | ||
5355 | def _extract_webpage(self, url, item_id, fatal=True): | |
5356 | webpage, data = None, None | |
5357 | for retry in self.RetryManager(fatal=fatal): | |
5358 | try: | |
5359 | webpage = self._download_webpage(url, item_id, note='Downloading webpage') | |
5360 | data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {} | |
5361 | except ExtractorError as e: | |
5362 | if isinstance(e.cause, network_exceptions): | |
5363 | if not isinstance(e.cause, HTTPError) or e.cause.status not in (403, 429): | |
5364 | retry.error = e | |
5365 | continue | |
5366 | self._error_or_warning(e, fatal=fatal) | |
5367 | break | |
5368 | ||
5369 | try: | |
5370 | self._extract_and_report_alerts(data) | |
5371 | except ExtractorError as e: | |
5372 | self._error_or_warning(e, fatal=fatal) | |
5373 | break | |
5374 | ||
5375 | # Sometimes youtube returns a webpage with incomplete ytInitialData | |
5376 | # See: https://github.com/yt-dlp/yt-dlp/issues/116 | |
5377 | if not traverse_obj(data, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'): | |
5378 | retry.error = ExtractorError('Incomplete yt initial data received') | |
5379 | data = None | |
5380 | continue | |
5381 | ||
5382 | return webpage, data | |
5383 | ||
5384 | def _report_playlist_authcheck(self, ytcfg, fatal=True): | |
5385 | """Use if failed to extract ytcfg (and data) from initial webpage""" | |
5386 | if not ytcfg and self.is_authenticated: | |
5387 | msg = 'Playlists that require authentication may not extract correctly without a successful webpage download' | |
5388 | if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal: | |
5389 | raise ExtractorError( | |
5390 | f'{msg}. If you are not downloading private content, or ' | |
5391 | 'your cookies are only for the first account and channel,' | |
5392 | ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check', | |
5393 | expected=True) | |
5394 | self.report_warning(msg, only_once=True) | |
5395 | ||
5396 | def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'): | |
5397 | data = None | |
5398 | if not self.skip_webpage: | |
5399 | webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal) | |
5400 | ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage) | |
5401 | # Reject webpage data if redirected to home page without explicitly requesting | |
5402 | selected_tab = self._extract_selected_tab(self._extract_tab_renderers(data), fatal=False) or {} | |
5403 | if (url != 'https://www.youtube.com/feed/recommended' | |
5404 | and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page | |
5405 | and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])): | |
5406 | msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page' | |
5407 | if fatal: | |
5408 | raise ExtractorError(msg, expected=True) | |
5409 | self.report_warning(msg, only_once=True) | |
5410 | if not data: | |
5411 | self._report_playlist_authcheck(ytcfg, fatal=fatal) | |
5412 | data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client) | |
5413 | return data, ytcfg | |
5414 | ||
5415 | def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'): | |
5416 | headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client) | |
5417 | resolve_response = self._extract_response( | |
5418 | item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal, | |
5419 | ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client) | |
5420 | endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'} | |
5421 | for ep_key, ep in endpoints.items(): | |
5422 | params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict) | |
5423 | if params: | |
5424 | return self._extract_response( | |
5425 | item_id=item_id, query=params, ep=ep, headers=headers, | |
5426 | ytcfg=ytcfg, fatal=fatal, default_client=default_client, | |
5427 | check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')) | |
5428 | err_note = 'Failed to resolve url (does the playlist exist?)' | |
5429 | if fatal: | |
5430 | raise ExtractorError(err_note, expected=True) | |
5431 | self.report_warning(err_note, item_id) | |
5432 | ||
5433 | _SEARCH_PARAMS = None | |
5434 | ||
5435 | def _search_results(self, query, params=NO_DEFAULT, default_client='web'): | |
5436 | data = {'query': query} | |
5437 | if params is NO_DEFAULT: | |
5438 | params = self._SEARCH_PARAMS | |
5439 | if params: | |
5440 | data['params'] = params | |
5441 | ||
5442 | content_keys = ( | |
5443 | ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'), | |
5444 | ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'), | |
5445 | # ytmusic search | |
5446 | ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'), | |
5447 | ('continuationContents', ), | |
5448 | ) | |
5449 | display_id = f'query "{query}"' | |
5450 | check_get_keys = tuple({keys[0] for keys in content_keys}) | |
5451 | ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {} | |
5452 | self._report_playlist_authcheck(ytcfg, fatal=False) | |
5453 | ||
5454 | continuation_list = [None] | |
5455 | search = None | |
5456 | for page_num in itertools.count(1): | |
5457 | data.update(continuation_list[0] or {}) | |
5458 | headers = self.generate_api_headers( | |
5459 | ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client) | |
5460 | search = self._extract_response( | |
5461 | item_id=f'{display_id} page {page_num}', ep='search', query=data, | |
5462 | default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers) | |
5463 | slr_contents = traverse_obj(search, *content_keys) | |
5464 | yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list) | |
5465 | if not continuation_list[0]: | |
5466 | break | |
5467 | ||
5468 | ||
5469 | class YoutubeTabIE(YoutubeTabBaseInfoExtractor): | |
5470 | IE_DESC = 'YouTube Tabs' | |
5471 | _VALID_URL = r'''(?x: | |
5472 | https?:// | |
5473 | (?!consent\.)(?:\w+\.)? | |
5474 | (?: | |
5475 | youtube(?:kids)?\.com| | |
5476 | %(invidious)s | |
5477 | )/ | |
5478 | (?: | |
5479 | (?P<channel_type>channel|c|user|browse)/| | |
5480 | (?P<not_channel> | |
5481 | feed/|hashtag/| | |
5482 | (?:playlist|watch)\?.*?\blist= | |
5483 | )| | |
5484 | (?!(?:%(reserved_names)s)\b) # Direct URLs | |
5485 | ) | |
5486 | (?P<id>[^/?\#&]+) | |
5487 | )''' % { | |
5488 | 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES, | |
5489 | 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), | |
5490 | } | |
5491 | IE_NAME = 'youtube:tab' | |
5492 | ||
5493 | _TESTS = [{ | |
5494 | 'note': 'playlists, multipage', | |
5495 | 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid', | |
5496 | 'playlist_mincount': 94, | |
5497 | 'info_dict': { | |
5498 | 'id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
5499 | 'title': 'Igor Kleiner Ph.D. - Playlists', | |
5500 | 'description': 'md5:15d7dd9e333cb987907fcb0d604b233a', | |
5501 | 'uploader': 'Igor Kleiner Ph.D.', | |
5502 | 'uploader_id': '@IgorDataScience', | |
5503 | 'uploader_url': 'https://www.youtube.com/@IgorDataScience', | |
5504 | 'channel': 'Igor Kleiner Ph.D.', | |
5505 | 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
5506 | 'tags': ['критическое мышление', 'наука просто', 'математика', 'анализ данных'], | |
5507 | 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', | |
5508 | 'channel_follower_count': int | |
5509 | }, | |
5510 | }, { | |
5511 | 'note': 'playlists, multipage, different order', | |
5512 | 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', | |
5513 | 'playlist_mincount': 94, | |
5514 | 'info_dict': { | |
5515 | 'id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
5516 | 'title': 'Igor Kleiner Ph.D. - Playlists', | |
5517 | 'description': 'md5:15d7dd9e333cb987907fcb0d604b233a', | |
5518 | 'uploader': 'Igor Kleiner Ph.D.', | |
5519 | 'uploader_id': '@IgorDataScience', | |
5520 | 'uploader_url': 'https://www.youtube.com/@IgorDataScience', | |
5521 | 'tags': ['критическое мышление', 'наука просто', 'математика', 'анализ данных'], | |
5522 | 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
5523 | 'channel': 'Igor Kleiner Ph.D.', | |
5524 | 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', | |
5525 | 'channel_follower_count': int | |
5526 | }, | |
5527 | }, { | |
5528 | 'note': 'playlists, series', | |
5529 | 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3', | |
5530 | 'playlist_mincount': 5, | |
5531 | 'info_dict': { | |
5532 | 'id': 'UCYO_jab_esuFRV4b17AJtAw', | |
5533 | 'title': '3Blue1Brown - Playlists', | |
5534 | 'description': 'md5:4d1da95432004b7ba840ebc895b6b4c9', | |
5535 | 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', | |
5536 | 'channel': '3Blue1Brown', | |
5537 | 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
5538 | 'uploader_id': '@3blue1brown', | |
5539 | 'uploader_url': 'https://www.youtube.com/@3blue1brown', | |
5540 | 'uploader': '3Blue1Brown', | |
5541 | 'tags': ['Mathematics'], | |
5542 | 'channel_follower_count': int, | |
5543 | 'channel_is_verified': True, | |
5544 | }, | |
5545 | }, { | |
5546 | 'note': 'playlists, singlepage', | |
5547 | 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', | |
5548 | 'playlist_mincount': 4, | |
5549 | 'info_dict': { | |
5550 | 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
5551 | 'title': 'ThirstForScience - Playlists', | |
5552 | 'description': 'md5:609399d937ea957b0f53cbffb747a14c', | |
5553 | 'uploader': 'ThirstForScience', | |
5554 | 'uploader_url': 'https://www.youtube.com/@ThirstForScience', | |
5555 | 'uploader_id': '@ThirstForScience', | |
5556 | 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
5557 | 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ', | |
5558 | 'tags': 'count:12', | |
5559 | 'channel': 'ThirstForScience', | |
5560 | 'channel_follower_count': int | |
5561 | } | |
5562 | }, { | |
5563 | 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', | |
5564 | 'only_matching': True, | |
5565 | }, { | |
5566 | 'note': 'basic, single video playlist', | |
5567 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
5568 | 'info_dict': { | |
5569 | 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
5570 | 'title': 'youtube-dl public playlist', | |
5571 | 'description': '', | |
5572 | 'tags': [], | |
5573 | 'view_count': int, | |
5574 | 'modified_date': '20201130', | |
5575 | 'channel': 'Sergey M.', | |
5576 | 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
5577 | 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
5578 | 'availability': 'public', | |
5579 | 'uploader': 'Sergey M.', | |
5580 | 'uploader_url': 'https://www.youtube.com/@sergeym.6173', | |
5581 | 'uploader_id': '@sergeym.6173', | |
5582 | }, | |
5583 | 'playlist_count': 1, | |
5584 | }, { | |
5585 | 'note': 'empty playlist', | |
5586 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', | |
5587 | 'info_dict': { | |
5588 | 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', | |
5589 | 'title': 'youtube-dl empty playlist', | |
5590 | 'tags': [], | |
5591 | 'channel': 'Sergey M.', | |
5592 | 'description': '', | |
5593 | 'modified_date': '20230921', | |
5594 | 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
5595 | 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
5596 | 'availability': 'unlisted', | |
5597 | 'uploader_url': 'https://www.youtube.com/@sergeym.6173', | |
5598 | 'uploader_id': '@sergeym.6173', | |
5599 | 'uploader': 'Sergey M.', | |
5600 | }, | |
5601 | 'playlist_count': 0, | |
5602 | }, { | |
5603 | 'note': 'Home tab', | |
5604 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured', | |
5605 | 'info_dict': { | |
5606 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
5607 | 'title': 'lex will - Home', | |
5608 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
5609 | 'uploader': 'lex will', | |
5610 | 'uploader_id': '@lexwill718', | |
5611 | 'channel': 'lex will', | |
5612 | 'tags': ['bible', 'history', 'prophesy'], | |
5613 | 'uploader_url': 'https://www.youtube.com/@lexwill718', | |
5614 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
5615 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
5616 | 'channel_follower_count': int | |
5617 | }, | |
5618 | 'playlist_mincount': 2, | |
5619 | }, { | |
5620 | 'note': 'Videos tab', | |
5621 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos', | |
5622 | 'info_dict': { | |
5623 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
5624 | 'title': 'lex will - Videos', | |
5625 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
5626 | 'uploader': 'lex will', | |
5627 | 'uploader_id': '@lexwill718', | |
5628 | 'tags': ['bible', 'history', 'prophesy'], | |
5629 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
5630 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
5631 | 'uploader_url': 'https://www.youtube.com/@lexwill718', | |
5632 | 'channel': 'lex will', | |
5633 | 'channel_follower_count': int | |
5634 | }, | |
5635 | 'playlist_mincount': 975, | |
5636 | }, { | |
5637 | 'note': 'Videos tab, sorted by popular', | |
5638 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid', | |
5639 | 'info_dict': { | |
5640 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
5641 | 'title': 'lex will - Videos', | |
5642 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
5643 | 'uploader': 'lex will', | |
5644 | 'uploader_id': '@lexwill718', | |
5645 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
5646 | 'uploader_url': 'https://www.youtube.com/@lexwill718', | |
5647 | 'channel': 'lex will', | |
5648 | 'tags': ['bible', 'history', 'prophesy'], | |
5649 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
5650 | 'channel_follower_count': int | |
5651 | }, | |
5652 | 'playlist_mincount': 199, | |
5653 | }, { | |
5654 | 'note': 'Playlists tab', | |
5655 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists', | |
5656 | 'info_dict': { | |
5657 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
5658 | 'title': 'lex will - Playlists', | |
5659 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
5660 | 'uploader': 'lex will', | |
5661 | 'uploader_id': '@lexwill718', | |
5662 | 'uploader_url': 'https://www.youtube.com/@lexwill718', | |
5663 | 'channel': 'lex will', | |
5664 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
5665 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
5666 | 'tags': ['bible', 'history', 'prophesy'], | |
5667 | 'channel_follower_count': int | |
5668 | }, | |
5669 | 'playlist_mincount': 17, | |
5670 | }, { | |
5671 | 'note': 'Community tab', | |
5672 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community', | |
5673 | 'info_dict': { | |
5674 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
5675 | 'title': 'lex will - Community', | |
5676 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
5677 | 'channel': 'lex will', | |
5678 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
5679 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
5680 | 'tags': ['bible', 'history', 'prophesy'], | |
5681 | 'channel_follower_count': int, | |
5682 | 'uploader_url': 'https://www.youtube.com/@lexwill718', | |
5683 | 'uploader_id': '@lexwill718', | |
5684 | 'uploader': 'lex will', | |
5685 | }, | |
5686 | 'playlist_mincount': 18, | |
5687 | }, { | |
5688 | 'note': 'Channels tab', | |
5689 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels', | |
5690 | 'info_dict': { | |
5691 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
5692 | 'title': 'lex will - Channels', | |
5693 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
5694 | 'channel': 'lex will', | |
5695 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
5696 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
5697 | 'tags': ['bible', 'history', 'prophesy'], | |
5698 | 'channel_follower_count': int, | |
5699 | 'uploader_url': 'https://www.youtube.com/@lexwill718', | |
5700 | 'uploader_id': '@lexwill718', | |
5701 | 'uploader': 'lex will', | |
5702 | }, | |
5703 | 'playlist_mincount': 12, | |
5704 | }, { | |
5705 | 'note': 'Search tab', | |
5706 | 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra', | |
5707 | 'playlist_mincount': 40, | |
5708 | 'info_dict': { | |
5709 | 'id': 'UCYO_jab_esuFRV4b17AJtAw', | |
5710 | 'title': '3Blue1Brown - Search - linear algebra', | |
5711 | 'description': 'md5:4d1da95432004b7ba840ebc895b6b4c9', | |
5712 | 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', | |
5713 | 'tags': ['Mathematics'], | |
5714 | 'channel': '3Blue1Brown', | |
5715 | 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
5716 | 'channel_follower_count': int, | |
5717 | 'uploader_url': 'https://www.youtube.com/@3blue1brown', | |
5718 | 'uploader_id': '@3blue1brown', | |
5719 | 'uploader': '3Blue1Brown', | |
5720 | 'channel_is_verified': True, | |
5721 | }, | |
5722 | }, { | |
5723 | 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
5724 | 'only_matching': True, | |
5725 | }, { | |
5726 | 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
5727 | 'only_matching': True, | |
5728 | }, { | |
5729 | 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
5730 | 'only_matching': True, | |
5731 | }, { | |
5732 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
5733 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
5734 | 'info_dict': { | |
5735 | 'title': '29C3: Not my department', | |
5736 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
5737 | 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268', | |
5738 | 'tags': [], | |
5739 | 'view_count': int, | |
5740 | 'modified_date': '20150605', | |
5741 | 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg', | |
5742 | 'channel_url': 'https://www.youtube.com/channel/UCEPzS1rYsrkqzSLNp76nrcg', | |
5743 | 'channel': 'Christiaan008', | |
5744 | 'availability': 'public', | |
5745 | 'uploader_id': '@ChRiStIaAn008', | |
5746 | 'uploader': 'Christiaan008', | |
5747 | 'uploader_url': 'https://www.youtube.com/@ChRiStIaAn008', | |
5748 | }, | |
5749 | 'playlist_count': 96, | |
5750 | }, { | |
5751 | 'note': 'Large playlist', | |
5752 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
5753 | 'info_dict': { | |
5754 | 'title': 'Uploads from Cauchemar', | |
5755 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', | |
5756 | 'channel_url': 'https://www.youtube.com/channel/UCBABnxM4Ar9ten8Mdjj1j0Q', | |
5757 | 'tags': [], | |
5758 | 'modified_date': r're:\d{8}', | |
5759 | 'channel': 'Cauchemar', | |
5760 | 'view_count': int, | |
5761 | 'description': '', | |
5762 | 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q', | |
5763 | 'availability': 'public', | |
5764 | 'uploader_id': '@Cauchemar89', | |
5765 | 'uploader': 'Cauchemar', | |
5766 | 'uploader_url': 'https://www.youtube.com/@Cauchemar89', | |
5767 | }, | |
5768 | 'playlist_mincount': 1123, | |
5769 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], | |
5770 | }, { | |
5771 | 'note': 'even larger playlist, 8832 videos', | |
5772 | 'url': 'http://www.youtube.com/user/NASAgovVideo/videos', | |
5773 | 'only_matching': True, | |
5774 | }, { | |
5775 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
5776 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
5777 | 'info_dict': { | |
5778 | 'title': 'Uploads from Interstellar Movie', | |
5779 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
5780 | 'tags': [], | |
5781 | 'view_count': int, | |
5782 | 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA', | |
5783 | 'channel_url': 'https://www.youtube.com/channel/UCXw-G3eDE9trcvY2sBMM_aA', | |
5784 | 'channel': 'Interstellar Movie', | |
5785 | 'description': '', | |
5786 | 'modified_date': r're:\d{8}', | |
5787 | 'availability': 'public', | |
5788 | 'uploader_id': '@InterstellarMovie', | |
5789 | 'uploader': 'Interstellar Movie', | |
5790 | 'uploader_url': 'https://www.youtube.com/@InterstellarMovie', | |
5791 | }, | |
5792 | 'playlist_mincount': 21, | |
5793 | }, { | |
5794 | 'note': 'Playlist with "show unavailable videos" button', | |
5795 | 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q', | |
5796 | 'info_dict': { | |
5797 | 'title': 'Uploads from Phim Siêu Nhân Nhật Bản', | |
5798 | 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q', | |
5799 | 'view_count': int, | |
5800 | 'channel': 'Phim Siêu Nhân Nhật Bản', | |
5801 | 'tags': [], | |
5802 | 'description': '', | |
5803 | 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q', | |
5804 | 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q', | |
5805 | 'modified_date': r're:\d{8}', | |
5806 | 'availability': 'public', | |
5807 | 'uploader_url': 'https://www.youtube.com/@phimsieunhannhatban', | |
5808 | 'uploader_id': '@phimsieunhannhatban', | |
5809 | 'uploader': 'Phim Siêu Nhân Nhật Bản', | |
5810 | }, | |
5811 | 'playlist_mincount': 200, | |
5812 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], | |
5813 | }, { | |
5814 | 'note': 'Playlist with unavailable videos in page 7', | |
5815 | 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w', | |
5816 | 'info_dict': { | |
5817 | 'title': 'Uploads from BlankTV', | |
5818 | 'id': 'UU8l9frL61Yl5KFOl87nIm2w', | |
5819 | 'channel': 'BlankTV', | |
5820 | 'channel_url': 'https://www.youtube.com/channel/UC8l9frL61Yl5KFOl87nIm2w', | |
5821 | 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w', | |
5822 | 'view_count': int, | |
5823 | 'tags': [], | |
5824 | 'modified_date': r're:\d{8}', | |
5825 | 'description': '', | |
5826 | 'availability': 'public', | |
5827 | 'uploader_id': '@blanktv', | |
5828 | 'uploader': 'BlankTV', | |
5829 | 'uploader_url': 'https://www.youtube.com/@blanktv', | |
5830 | }, | |
5831 | 'playlist_mincount': 1000, | |
5832 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], | |
5833 | }, { | |
5834 | 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844', | |
5835 | 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
5836 | 'info_dict': { | |
5837 | 'title': 'Data Analysis with Dr Mike Pound', | |
5838 | 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
5839 | 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487', | |
5840 | 'tags': [], | |
5841 | 'view_count': int, | |
5842 | 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA', | |
5843 | 'channel_url': 'https://www.youtube.com/channel/UC9-y-6csu5WGm29I7JiwpnA', | |
5844 | 'channel': 'Computerphile', | |
5845 | 'availability': 'public', | |
5846 | 'modified_date': '20190712', | |
5847 | 'uploader_id': '@Computerphile', | |
5848 | 'uploader': 'Computerphile', | |
5849 | 'uploader_url': 'https://www.youtube.com/@Computerphile', | |
5850 | }, | |
5851 | 'playlist_mincount': 11, | |
5852 | }, { | |
5853 | 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
5854 | 'only_matching': True, | |
5855 | }, { | |
5856 | 'note': 'Playlist URL that does not actually serve a playlist', | |
5857 | 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', | |
5858 | 'info_dict': { | |
5859 | 'id': 'FqZTN594JQw', | |
5860 | 'ext': 'webm', | |
5861 | 'title': "Smiley's People 01 detective, Adventure Series, Action", | |
5862 | 'upload_date': '20150526', | |
5863 | 'license': 'Standard YouTube License', | |
5864 | 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', | |
5865 | 'categories': ['People & Blogs'], | |
5866 | 'tags': list, | |
5867 | 'view_count': int, | |
5868 | 'like_count': int, | |
5869 | }, | |
5870 | 'params': { | |
5871 | 'skip_download': True, | |
5872 | }, | |
5873 | 'skip': 'This video is not available.', | |
5874 | 'add_ie': [YoutubeIE.ie_key()], | |
5875 | }, { | |
5876 | 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g', | |
5877 | 'only_matching': True, | |
5878 | }, { | |
5879 | 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', | |
5880 | 'only_matching': True, | |
5881 | }, { | |
5882 | 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live', | |
5883 | 'info_dict': { | |
5884 | 'id': 'hGkQjiJLjWQ', # This will keep changing | |
5885 | 'ext': 'mp4', | |
5886 | 'title': str, | |
5887 | 'upload_date': r're:\d{8}', | |
5888 | 'description': str, | |
5889 | 'categories': ['News & Politics'], | |
5890 | 'tags': list, | |
5891 | 'like_count': int, | |
5892 | 'release_timestamp': int, | |
5893 | 'channel': 'Sky News', | |
5894 | 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ', | |
5895 | 'age_limit': 0, | |
5896 | 'view_count': int, | |
5897 | 'thumbnail': r're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg', | |
5898 | 'playable_in_embed': True, | |
5899 | 'release_date': r're:\d+', | |
5900 | 'availability': 'public', | |
5901 | 'live_status': 'is_live', | |
5902 | 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ', | |
5903 | 'channel_follower_count': int, | |
5904 | 'concurrent_view_count': int, | |
5905 | 'uploader_url': 'https://www.youtube.com/@SkyNews', | |
5906 | 'uploader_id': '@SkyNews', | |
5907 | 'uploader': 'Sky News', | |
5908 | 'channel_is_verified': True, | |
5909 | }, | |
5910 | 'params': { | |
5911 | 'skip_download': True, | |
5912 | }, | |
5913 | 'expected_warnings': ['Ignoring subtitle tracks found in '], | |
5914 | }, { | |
5915 | 'url': 'https://www.youtube.com/user/TheYoungTurks/live', | |
5916 | 'info_dict': { | |
5917 | 'id': 'a48o2S1cPoo', | |
5918 | 'ext': 'mp4', | |
5919 | 'title': 'The Young Turks - Live Main Show', | |
5920 | 'upload_date': '20150715', | |
5921 | 'license': 'Standard YouTube License', | |
5922 | 'description': 'md5:438179573adcdff3c97ebb1ee632b891', | |
5923 | 'categories': ['News & Politics'], | |
5924 | 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], | |
5925 | 'like_count': int, | |
5926 | }, | |
5927 | 'params': { | |
5928 | 'skip_download': True, | |
5929 | }, | |
5930 | 'only_matching': True, | |
5931 | }, { | |
5932 | 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', | |
5933 | 'only_matching': True, | |
5934 | }, { | |
5935 | 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', | |
5936 | 'only_matching': True, | |
5937 | }, { | |
5938 | 'note': 'A channel that is not live. Should raise error', | |
5939 | 'url': 'https://www.youtube.com/user/numberphile/live', | |
5940 | 'only_matching': True, | |
5941 | }, { | |
5942 | 'url': 'https://www.youtube.com/feed/trending', | |
5943 | 'only_matching': True, | |
5944 | }, { | |
5945 | 'url': 'https://www.youtube.com/feed/library', | |
5946 | 'only_matching': True, | |
5947 | }, { | |
5948 | 'url': 'https://www.youtube.com/feed/history', | |
5949 | 'only_matching': True, | |
5950 | }, { | |
5951 | 'url': 'https://www.youtube.com/feed/subscriptions', | |
5952 | 'only_matching': True, | |
5953 | }, { | |
5954 | 'url': 'https://www.youtube.com/feed/watch_later', | |
5955 | 'only_matching': True, | |
5956 | }, { | |
5957 | 'note': 'Recommended - redirects to home page.', | |
5958 | 'url': 'https://www.youtube.com/feed/recommended', | |
5959 | 'only_matching': True, | |
5960 | }, { | |
5961 | 'note': 'inline playlist with not always working continuations', | |
5962 | 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C', | |
5963 | 'only_matching': True, | |
5964 | }, { | |
5965 | 'url': 'https://www.youtube.com/course', | |
5966 | 'only_matching': True, | |
5967 | }, { | |
5968 | 'url': 'https://www.youtube.com/zsecurity', | |
5969 | 'only_matching': True, | |
5970 | }, { | |
5971 | 'url': 'http://www.youtube.com/NASAgovVideo/videos', | |
5972 | 'only_matching': True, | |
5973 | }, { | |
5974 | 'url': 'https://www.youtube.com/TheYoungTurks/live', | |
5975 | 'only_matching': True, | |
5976 | }, { | |
5977 | 'url': 'https://www.youtube.com/hashtag/cctv9', | |
5978 | 'info_dict': { | |
5979 | 'id': 'cctv9', | |
5980 | 'title': 'cctv9 - All', | |
5981 | 'tags': [], | |
5982 | }, | |
5983 | 'playlist_mincount': 300, # not consistent but should be over 300 | |
5984 | }, { | |
5985 | 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU', | |
5986 | 'only_matching': True, | |
5987 | }, { | |
5988 | 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist', | |
5989 | 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', | |
5990 | 'only_matching': True | |
5991 | }, { | |
5992 | 'note': '/browse/ should redirect to /channel/', | |
5993 | 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng', | |
5994 | 'only_matching': True | |
5995 | }, { | |
5996 | 'note': 'VLPL, should redirect to playlist?list=PL...', | |
5997 | 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', | |
5998 | 'info_dict': { | |
5999 | 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', | |
6000 | 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!', | |
6001 | 'title': 'NCS : All Releases 💿', | |
6002 | 'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg', | |
6003 | 'modified_date': r're:\d{8}', | |
6004 | 'view_count': int, | |
6005 | 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg', | |
6006 | 'tags': [], | |
6007 | 'channel': 'NoCopyrightSounds', | |
6008 | 'availability': 'public', | |
6009 | 'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds', | |
6010 | 'uploader': 'NoCopyrightSounds', | |
6011 | 'uploader_id': '@NoCopyrightSounds', | |
6012 | }, | |
6013 | 'playlist_mincount': 166, | |
6014 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden', 'YouTube Music is not directly supported'], | |
6015 | }, { | |
6016 | # TODO: fix 'unviewable' issue with this playlist when reloading with unavailable videos | |
6017 | 'note': 'Topic, should redirect to playlist?list=UU...', | |
6018 | 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw', | |
6019 | 'info_dict': { | |
6020 | 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw', | |
6021 | 'title': 'Uploads from Royalty Free Music - Topic', | |
6022 | 'tags': [], | |
6023 | 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', | |
6024 | 'channel': 'Royalty Free Music - Topic', | |
6025 | 'view_count': int, | |
6026 | 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
6027 | 'modified_date': r're:\d{8}', | |
6028 | 'description': '', | |
6029 | 'availability': 'public', | |
6030 | 'uploader': 'Royalty Free Music - Topic', | |
6031 | }, | |
6032 | 'playlist_mincount': 101, | |
6033 | 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'], | |
6034 | }, { | |
6035 | # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg) | |
6036 | # Treat as a general feed | |
6037 | 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg', | |
6038 | 'info_dict': { | |
6039 | 'id': 'UCtFRv9O2AHqOZjjynzrv-xg', | |
6040 | 'title': 'UCtFRv9O2AHqOZjjynzrv-xg', | |
6041 | 'tags': [], | |
6042 | }, | |
6043 | 'playlist_mincount': 9, | |
6044 | }, { | |
6045 | 'note': 'Youtube music Album', | |
6046 | 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE', | |
6047 | 'info_dict': { | |
6048 | 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0', | |
6049 | 'title': 'Album - Royalty Free Music Library V2 (50 Songs)', | |
6050 | 'tags': [], | |
6051 | 'view_count': int, | |
6052 | 'description': '', | |
6053 | 'availability': 'unlisted', | |
6054 | 'modified_date': r're:\d{8}', | |
6055 | }, | |
6056 | 'playlist_count': 50, | |
6057 | 'expected_warnings': ['YouTube Music is not directly supported'], | |
6058 | }, { | |
6059 | 'note': 'unlisted single video playlist', | |
6060 | 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', | |
6061 | 'info_dict': { | |
6062 | 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', | |
6063 | 'title': 'yt-dlp unlisted playlist test', | |
6064 | 'availability': 'unlisted', | |
6065 | 'tags': [], | |
6066 | 'modified_date': '20220418', | |
6067 | 'channel': 'colethedj', | |
6068 | 'view_count': int, | |
6069 | 'description': '', | |
6070 | 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q', | |
6071 | 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q', | |
6072 | 'uploader_url': 'https://www.youtube.com/@colethedj1894', | |
6073 | 'uploader_id': '@colethedj1894', | |
6074 | 'uploader': 'colethedj', | |
6075 | }, | |
6076 | 'playlist': [{ | |
6077 | 'info_dict': { | |
6078 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
6079 | 'id': 'BaW_jenozKc', | |
6080 | '_type': 'url', | |
6081 | 'ie_key': 'Youtube', | |
6082 | 'duration': 10, | |
6083 | 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', | |
6084 | 'channel_url': 'https://www.youtube.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', | |
6085 | 'view_count': int, | |
6086 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc', | |
6087 | 'channel': 'Philipp Hagemeister', | |
6088 | 'uploader_id': '@PhilippHagemeister', | |
6089 | 'uploader_url': 'https://www.youtube.com/@PhilippHagemeister', | |
6090 | 'uploader': 'Philipp Hagemeister', | |
6091 | } | |
6092 | }], | |
6093 | 'playlist_count': 1, | |
6094 | 'params': {'extract_flat': True}, | |
6095 | }, { | |
6096 | 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData', | |
6097 | 'url': 'https://www.youtube.com/feed/recommended', | |
6098 | 'info_dict': { | |
6099 | 'id': 'recommended', | |
6100 | 'title': 'recommended', | |
6101 | 'tags': [], | |
6102 | }, | |
6103 | 'playlist_mincount': 50, | |
6104 | 'params': { | |
6105 | 'skip_download': True, | |
6106 | 'extractor_args': {'youtubetab': {'skip': ['webpage']}} | |
6107 | }, | |
6108 | }, { | |
6109 | 'note': 'API Fallback: /videos tab, sorted by oldest first', | |
6110 | 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid', | |
6111 | 'info_dict': { | |
6112 | 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', | |
6113 | 'title': 'Cody\'sLab - Videos', | |
6114 | 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa', | |
6115 | 'channel': 'Cody\'sLab', | |
6116 | 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', | |
6117 | 'tags': [], | |
6118 | 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw', | |
6119 | 'channel_follower_count': int | |
6120 | }, | |
6121 | 'playlist_mincount': 650, | |
6122 | 'params': { | |
6123 | 'skip_download': True, | |
6124 | 'extractor_args': {'youtubetab': {'skip': ['webpage']}} | |
6125 | }, | |
6126 | 'skip': 'Query for sorting no longer works', | |
6127 | }, { | |
6128 | 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...', | |
6129 | 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw', | |
6130 | 'info_dict': { | |
6131 | 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw', | |
6132 | 'title': 'Uploads from Royalty Free Music - Topic', | |
6133 | 'modified_date': r're:\d{8}', | |
6134 | 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', | |
6135 | 'description': '', | |
6136 | 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
6137 | 'tags': [], | |
6138 | 'channel': 'Royalty Free Music - Topic', | |
6139 | 'view_count': int, | |
6140 | 'availability': 'public', | |
6141 | 'uploader': 'Royalty Free Music - Topic', | |
6142 | }, | |
6143 | 'playlist_mincount': 101, | |
6144 | 'params': { | |
6145 | 'skip_download': True, | |
6146 | 'extractor_args': {'youtubetab': {'skip': ['webpage']}} | |
6147 | }, | |
6148 | 'expected_warnings': ['YouTube Music is not directly supported', r'[Uu]navailable videos (are|will be) hidden'], | |
6149 | }, { | |
6150 | 'note': 'non-standard redirect to regional channel', | |
6151 | 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ', | |
6152 | 'only_matching': True | |
6153 | }, { | |
6154 | 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")', | |
6155 | 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6', | |
6156 | 'info_dict': { | |
6157 | 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6', | |
6158 | 'modified_date': '20220407', | |
6159 | 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q', | |
6160 | 'tags': [], | |
6161 | 'availability': 'unlisted', | |
6162 | 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q', | |
6163 | 'channel': 'pukkandan', | |
6164 | 'description': 'Test for collaborative playlist', | |
6165 | 'title': 'yt-dlp test - collaborative playlist', | |
6166 | 'view_count': int, | |
6167 | 'uploader_url': 'https://www.youtube.com/@pukkandan', | |
6168 | 'uploader_id': '@pukkandan', | |
6169 | 'uploader': 'pukkandan', | |
6170 | }, | |
6171 | 'playlist_mincount': 2 | |
6172 | }, { | |
6173 | 'note': 'translated tab name', | |
6174 | 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists', | |
6175 | 'info_dict': { | |
6176 | 'id': 'UCiu-3thuViMebBjw_5nWYrA', | |
6177 | 'tags': [], | |
6178 | 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', | |
6179 | 'description': 'test description', | |
6180 | 'title': 'cole-dlp-test-acc - 再生リスト', | |
6181 | 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA', | |
6182 | 'channel': 'cole-dlp-test-acc', | |
6183 | 'uploader_url': 'https://www.youtube.com/@coletdjnz', | |
6184 | 'uploader_id': '@coletdjnz', | |
6185 | 'uploader': 'cole-dlp-test-acc', | |
6186 | }, | |
6187 | 'playlist_mincount': 1, | |
6188 | 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}}, | |
6189 | 'expected_warnings': ['Preferring "ja"'], | |
6190 | }, { | |
6191 | # XXX: this should really check flat playlist entries, but the test suite doesn't support that | |
6192 | 'note': 'preferred lang set with playlist with translated video titles', | |
6193 | 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0', | |
6194 | 'info_dict': { | |
6195 | 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0', | |
6196 | 'tags': [], | |
6197 | 'view_count': int, | |
6198 | 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', | |
6199 | 'channel': 'cole-dlp-test-acc', | |
6200 | 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA', | |
6201 | 'description': 'test', | |
6202 | 'title': 'dlp test playlist', | |
6203 | 'availability': 'public', | |
6204 | 'uploader_url': 'https://www.youtube.com/@coletdjnz', | |
6205 | 'uploader_id': '@coletdjnz', | |
6206 | 'uploader': 'cole-dlp-test-acc', | |
6207 | }, | |
6208 | 'playlist_mincount': 1, | |
6209 | 'params': {'extractor_args': {'youtube': {'lang': ['ja']}}}, | |
6210 | 'expected_warnings': ['Preferring "ja"'], | |
6211 | }, { | |
6212 | # shorts audio pivot for 2GtVksBMYFM. | |
6213 | 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==', | |
6214 | 'info_dict': { | |
6215 | 'id': 'sfv_audio_pivot', | |
6216 | 'title': 'sfv_audio_pivot', | |
6217 | 'tags': [], | |
6218 | }, | |
6219 | 'playlist_mincount': 50, | |
6220 | ||
6221 | }, { | |
6222 | # Channel with a real live tab (not to be mistaken with streams tab) | |
6223 | # Do not treat like it should redirect to live stream | |
6224 | 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live', | |
6225 | 'info_dict': { | |
6226 | 'id': 'UCEH7P7kyJIkS_gJf93VYbmg', | |
6227 | 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live', | |
6228 | 'tags': [], | |
6229 | }, | |
6230 | 'playlist_mincount': 20, | |
6231 | }, { | |
6232 | # Tab name is not the same as tab id | |
6233 | 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay', | |
6234 | 'info_dict': { | |
6235 | 'id': 'UCQvWX73GQygcwXOTSf_VDVg', | |
6236 | 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play', | |
6237 | 'tags': [], | |
6238 | }, | |
6239 | 'playlist_mincount': 8, | |
6240 | }, { | |
6241 | # Home tab id is literally home. Not to get mistaken with featured | |
6242 | 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home', | |
6243 | 'info_dict': { | |
6244 | 'id': 'UCQvWX73GQygcwXOTSf_VDVg', | |
6245 | 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home', | |
6246 | 'tags': [], | |
6247 | }, | |
6248 | 'playlist_mincount': 8, | |
6249 | }, { | |
6250 | # Should get three playlists for videos, shorts and streams tabs | |
6251 | 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA', | |
6252 | 'info_dict': { | |
6253 | 'id': 'UCK9V2B22uJYu3N7eR_BT9QA', | |
6254 | 'title': 'Polka Ch. 尾丸ポルカ', | |
6255 | 'channel_follower_count': int, | |
6256 | 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA', | |
6257 | 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA', | |
6258 | 'description': 'md5:49809d8bf9da539bc48ed5d1f83c33f2', | |
6259 | 'channel': 'Polka Ch. 尾丸ポルカ', | |
6260 | 'tags': 'count:35', | |
6261 | 'uploader_url': 'https://www.youtube.com/@OmaruPolka', | |
6262 | 'uploader': 'Polka Ch. 尾丸ポルカ', | |
6263 | 'uploader_id': '@OmaruPolka', | |
6264 | 'channel_is_verified': True, | |
6265 | }, | |
6266 | 'playlist_count': 3, | |
6267 | }, { | |
6268 | # Shorts tab with channel with handle | |
6269 | # TODO: fix channel description | |
6270 | 'url': 'https://www.youtube.com/@NotJustBikes/shorts', | |
6271 | 'info_dict': { | |
6272 | 'id': 'UC0intLFzLaudFG-xAvUEO-A', | |
6273 | 'title': 'Not Just Bikes - Shorts', | |
6274 | 'tags': 'count:10', | |
6275 | 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A', | |
6276 | 'description': 'md5:5e82545b3a041345927a92d0585df247', | |
6277 | 'channel_follower_count': int, | |
6278 | 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A', | |
6279 | 'channel': 'Not Just Bikes', | |
6280 | 'uploader_url': 'https://www.youtube.com/@NotJustBikes', | |
6281 | 'uploader': 'Not Just Bikes', | |
6282 | 'uploader_id': '@NotJustBikes', | |
6283 | 'channel_is_verified': True, | |
6284 | }, | |
6285 | 'playlist_mincount': 10, | |
6286 | }, { | |
6287 | # Streams tab | |
6288 | 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams', | |
6289 | 'info_dict': { | |
6290 | 'id': 'UC3eYAvjCVwNHgkaGbXX3sig', | |
6291 | 'title': '中村悠一 - Live', | |
6292 | 'tags': 'count:7', | |
6293 | 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig', | |
6294 | 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig', | |
6295 | 'channel': '中村悠一', | |
6296 | 'channel_follower_count': int, | |
6297 | 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300', | |
6298 | 'uploader_url': 'https://www.youtube.com/@Yuichi-Nakamura', | |
6299 | 'uploader_id': '@Yuichi-Nakamura', | |
6300 | 'uploader': '中村悠一', | |
6301 | }, | |
6302 | 'playlist_mincount': 60, | |
6303 | }, { | |
6304 | # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail. | |
6305 | # See test_youtube_lists | |
6306 | 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA', | |
6307 | 'only_matching': True, | |
6308 | }, { | |
6309 | # No uploads and no UCID given. Should fail with no uploads error | |
6310 | # See test_youtube_lists | |
6311 | 'url': 'https://www.youtube.com/news', | |
6312 | 'only_matching': True | |
6313 | }, { | |
6314 | # No videos tab but has a shorts tab | |
6315 | 'url': 'https://www.youtube.com/c/TKFShorts', | |
6316 | 'info_dict': { | |
6317 | 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg', | |
6318 | 'title': 'Shorts Break - Shorts', | |
6319 | 'tags': 'count:48', | |
6320 | 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg', | |
6321 | 'channel': 'Shorts Break', | |
6322 | 'description': 'md5:6de33c5e7ba686e5f3efd4e19c7ef499', | |
6323 | 'channel_follower_count': int, | |
6324 | 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg', | |
6325 | 'uploader_url': 'https://www.youtube.com/@ShortsBreak_Official', | |
6326 | 'uploader': 'Shorts Break', | |
6327 | 'uploader_id': '@ShortsBreak_Official', | |
6328 | }, | |
6329 | 'playlist_mincount': 30, | |
6330 | }, { | |
6331 | # Trending Now Tab. tab id is empty | |
6332 | 'url': 'https://www.youtube.com/feed/trending', | |
6333 | 'info_dict': { | |
6334 | 'id': 'trending', | |
6335 | 'title': 'trending - Now', | |
6336 | 'tags': [], | |
6337 | }, | |
6338 | 'playlist_mincount': 30, | |
6339 | }, { | |
6340 | # Trending Gaming Tab. tab id is empty | |
6341 | 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D', | |
6342 | 'info_dict': { | |
6343 | 'id': 'trending', | |
6344 | 'title': 'trending - Gaming', | |
6345 | 'tags': [], | |
6346 | }, | |
6347 | 'playlist_mincount': 30, | |
6348 | }, { | |
6349 | # Shorts url result in shorts tab | |
6350 | # TODO: Fix channel id extraction | |
6351 | 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts', | |
6352 | 'info_dict': { | |
6353 | 'id': 'UCiu-3thuViMebBjw_5nWYrA', | |
6354 | 'title': 'cole-dlp-test-acc - Shorts', | |
6355 | 'channel': 'cole-dlp-test-acc', | |
6356 | 'description': 'test description', | |
6357 | 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA', | |
6358 | 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', | |
6359 | 'tags': [], | |
6360 | 'uploader_url': 'https://www.youtube.com/@coletdjnz', | |
6361 | 'uploader_id': '@coletdjnz', | |
6362 | 'uploader': 'cole-dlp-test-acc', | |
6363 | }, | |
6364 | 'playlist': [{ | |
6365 | 'info_dict': { | |
6366 | # Channel data is not currently available for short renderers (as of 2023-03-01) | |
6367 | '_type': 'url', | |
6368 | 'ie_key': 'Youtube', | |
6369 | 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60', | |
6370 | 'id': 'sSM9J5YH_60', | |
6371 | 'title': 'SHORT short', | |
6372 | 'view_count': int, | |
6373 | 'thumbnails': list, | |
6374 | } | |
6375 | }], | |
6376 | 'params': {'extract_flat': True}, | |
6377 | }, { | |
6378 | # Live video status should be extracted | |
6379 | 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live', | |
6380 | 'info_dict': { | |
6381 | 'id': 'UCQvWX73GQygcwXOTSf_VDVg', | |
6382 | 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live | |
6383 | 'tags': [] | |
6384 | }, | |
6385 | 'playlist': [{ | |
6386 | 'info_dict': { | |
6387 | '_type': 'url', | |
6388 | 'ie_key': 'Youtube', | |
6389 | 'url': 'startswith:https://www.youtube.com/watch?v=', | |
6390 | 'id': str, | |
6391 | 'title': str, | |
6392 | 'live_status': 'is_live', | |
6393 | 'channel_id': str, | |
6394 | 'channel_url': str, | |
6395 | 'concurrent_view_count': int, | |
6396 | 'channel': str, | |
6397 | 'uploader': str, | |
6398 | 'uploader_url': str, | |
6399 | 'uploader_id': str, | |
6400 | 'channel_is_verified': bool, # this will keep changing | |
6401 | } | |
6402 | }], | |
6403 | 'params': {'extract_flat': True, 'playlist_items': '1'}, | |
6404 | 'playlist_mincount': 1 | |
6405 | }, { | |
6406 | # Channel renderer metadata. Contains number of videos on the channel | |
6407 | 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels', | |
6408 | 'info_dict': { | |
6409 | 'id': 'UCiu-3thuViMebBjw_5nWYrA', | |
6410 | 'title': 'cole-dlp-test-acc - Channels', | |
6411 | 'channel': 'cole-dlp-test-acc', | |
6412 | 'description': 'test description', | |
6413 | 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA', | |
6414 | 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA', | |
6415 | 'tags': [], | |
6416 | 'uploader_url': 'https://www.youtube.com/@coletdjnz', | |
6417 | 'uploader_id': '@coletdjnz', | |
6418 | 'uploader': 'cole-dlp-test-acc', | |
6419 | }, | |
6420 | 'playlist': [{ | |
6421 | 'info_dict': { | |
6422 | '_type': 'url', | |
6423 | 'ie_key': 'YoutubeTab', | |
6424 | 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw', | |
6425 | 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw', | |
6426 | 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw', | |
6427 | 'title': 'PewDiePie', | |
6428 | 'channel': 'PewDiePie', | |
6429 | 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw', | |
6430 | 'thumbnails': list, | |
6431 | 'channel_follower_count': int, | |
6432 | 'playlist_count': int, | |
6433 | 'uploader': 'PewDiePie', | |
6434 | 'uploader_url': 'https://www.youtube.com/@PewDiePie', | |
6435 | 'uploader_id': '@PewDiePie', | |
6436 | 'channel_is_verified': True, | |
6437 | } | |
6438 | }], | |
6439 | 'params': {'extract_flat': True}, | |
6440 | }, { | |
6441 | 'url': 'https://www.youtube.com/@3blue1brown/about', | |
6442 | 'info_dict': { | |
6443 | 'id': '@3blue1brown', | |
6444 | 'tags': ['Mathematics'], | |
6445 | 'title': '3Blue1Brown', | |
6446 | 'channel_follower_count': int, | |
6447 | 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
6448 | 'channel': '3Blue1Brown', | |
6449 | 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', | |
6450 | 'description': 'md5:4d1da95432004b7ba840ebc895b6b4c9', | |
6451 | 'uploader_url': 'https://www.youtube.com/@3blue1brown', | |
6452 | 'uploader_id': '@3blue1brown', | |
6453 | 'uploader': '3Blue1Brown', | |
6454 | 'channel_is_verified': True, | |
6455 | }, | |
6456 | 'playlist_count': 0, | |
6457 | }, { | |
6458 | # Podcasts tab, with rich entry playlistRenderers | |
6459 | 'url': 'https://www.youtube.com/@99percentinvisiblepodcast/podcasts', | |
6460 | 'info_dict': { | |
6461 | 'id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw', | |
6462 | 'channel_id': 'UCVMF2HD4ZgC0QHpU9Yq5Xrw', | |
6463 | 'uploader_url': 'https://www.youtube.com/@99percentinvisiblepodcast', | |
6464 | 'description': 'md5:3a0ed38f1ad42a68ef0428c04a15695c', | |
6465 | 'title': '99 Percent Invisible - Podcasts', | |
6466 | 'uploader': '99 Percent Invisible', | |
6467 | 'channel_follower_count': int, | |
6468 | 'channel_url': 'https://www.youtube.com/channel/UCVMF2HD4ZgC0QHpU9Yq5Xrw', | |
6469 | 'tags': [], | |
6470 | 'channel': '99 Percent Invisible', | |
6471 | 'uploader_id': '@99percentinvisiblepodcast', | |
6472 | }, | |
6473 | 'playlist_count': 0, | |
6474 | }, { | |
6475 | # Releases tab, with rich entry playlistRenderers (same as Podcasts tab) | |
6476 | 'url': 'https://www.youtube.com/@AHimitsu/releases', | |
6477 | 'info_dict': { | |
6478 | 'id': 'UCgFwu-j5-xNJml2FtTrrB3A', | |
6479 | 'channel': 'A Himitsu', | |
6480 | 'uploader_url': 'https://www.youtube.com/@AHimitsu', | |
6481 | 'title': 'A Himitsu - Releases', | |
6482 | 'uploader_id': '@AHimitsu', | |
6483 | 'uploader': 'A Himitsu', | |
6484 | 'channel_id': 'UCgFwu-j5-xNJml2FtTrrB3A', | |
6485 | 'tags': 'count:12', | |
6486 | 'description': 'I make music', | |
6487 | 'channel_url': 'https://www.youtube.com/channel/UCgFwu-j5-xNJml2FtTrrB3A', | |
6488 | 'channel_follower_count': int, | |
6489 | 'channel_is_verified': True, | |
6490 | }, | |
6491 | 'playlist_mincount': 10, | |
6492 | }, { | |
6493 | # Playlist with only shorts, shown as reel renderers | |
6494 | # FIXME: future: YouTube currently doesn't give continuation for this, | |
6495 | # may do in future. | |
6496 | 'url': 'https://www.youtube.com/playlist?list=UUxqPAgubo4coVn9Lx1FuKcg', | |
6497 | 'info_dict': { | |
6498 | 'id': 'UUxqPAgubo4coVn9Lx1FuKcg', | |
6499 | 'channel_url': 'https://www.youtube.com/channel/UCxqPAgubo4coVn9Lx1FuKcg', | |
6500 | 'view_count': int, | |
6501 | 'uploader_id': '@BangyShorts', | |
6502 | 'description': '', | |
6503 | 'uploader_url': 'https://www.youtube.com/@BangyShorts', | |
6504 | 'channel_id': 'UCxqPAgubo4coVn9Lx1FuKcg', | |
6505 | 'channel': 'Bangy Shorts', | |
6506 | 'uploader': 'Bangy Shorts', | |
6507 | 'tags': [], | |
6508 | 'availability': 'public', | |
6509 | 'modified_date': r're:\d{8}', | |
6510 | 'title': 'Uploads from Bangy Shorts', | |
6511 | }, | |
6512 | 'playlist_mincount': 100, | |
6513 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], | |
6514 | }, { | |
6515 | 'note': 'Tags containing spaces', | |
6516 | 'url': 'https://www.youtube.com/channel/UC7_YxT-KID8kRbqZo7MyscQ', | |
6517 | 'playlist_count': 3, | |
6518 | 'info_dict': { | |
6519 | 'id': 'UC7_YxT-KID8kRbqZo7MyscQ', | |
6520 | 'channel': 'Markiplier', | |
6521 | 'channel_id': 'UC7_YxT-KID8kRbqZo7MyscQ', | |
6522 | 'title': 'Markiplier', | |
6523 | 'channel_follower_count': int, | |
6524 | 'description': 'md5:0c010910558658824402809750dc5d97', | |
6525 | 'uploader_id': '@markiplier', | |
6526 | 'uploader_url': 'https://www.youtube.com/@markiplier', | |
6527 | 'uploader': 'Markiplier', | |
6528 | 'channel_url': 'https://www.youtube.com/channel/UC7_YxT-KID8kRbqZo7MyscQ', | |
6529 | 'channel_is_verified': True, | |
6530 | 'tags': ['markiplier', 'comedy', 'gaming', 'funny videos', 'funny moments', | |
6531 | 'sketch comedy', 'laughing', 'lets play', 'challenge videos', 'hilarious', | |
6532 | 'challenges', 'sketches', 'scary games', 'funny games', 'rage games', | |
6533 | 'mark fischbach'], | |
6534 | }, | |
6535 | }] | |
6536 | ||
6537 | @classmethod | |
6538 | def suitable(cls, url): | |
6539 | return False if YoutubeIE.suitable(url) else super().suitable(url) | |
6540 | ||
6541 | _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$') | |
6542 | ||
6543 | def _get_url_mobj(self, url): | |
6544 | mobj = self._URL_RE.match(url).groupdict() | |
6545 | mobj.update((k, '') for k, v in mobj.items() if v is None) | |
6546 | return mobj | |
6547 | ||
6548 | def _extract_tab_id_and_name(self, tab, base_url='https://www.youtube.com'): | |
6549 | tab_name = (tab.get('title') or '').lower() | |
6550 | tab_url = urljoin(base_url, traverse_obj( | |
6551 | tab, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url'))) | |
6552 | ||
6553 | tab_id = (tab_url and self._get_url_mobj(tab_url)['tab'][1:] | |
6554 | or traverse_obj(tab, 'tabIdentifier', expected_type=str)) | |
6555 | if tab_id: | |
6556 | return { | |
6557 | 'TAB_ID_SPONSORSHIPS': 'membership', | |
6558 | }.get(tab_id, tab_id), tab_name | |
6559 | ||
6560 | # Fallback to tab name if we cannot get the tab id. | |
6561 | # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel | |
6562 | # Note that in the case of translated tab name this may result in an empty string, which we don't want. | |
6563 | if tab_name: | |
6564 | self.write_debug(f'Falling back to selected tab name: {tab_name}') | |
6565 | return { | |
6566 | 'home': 'featured', | |
6567 | 'live': 'streams', | |
6568 | }.get(tab_name, tab_name), tab_name | |
6569 | ||
6570 | def _has_tab(self, tabs, tab_id): | |
6571 | return any(self._extract_tab_id_and_name(tab)[0] == tab_id for tab in tabs) | |
6572 | ||
6573 | def _empty_playlist(self, item_id, data): | |
6574 | return self.playlist_result([], item_id, **self._extract_metadata_from_tabs(item_id, data)) | |
6575 | ||
6576 | @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data | |
6577 | def _real_extract(self, url, smuggled_data): | |
6578 | item_id = self._match_id(url) | |
6579 | url = urllib.parse.urlunparse( | |
6580 | urllib.parse.urlparse(url)._replace(netloc='www.youtube.com')) | |
6581 | compat_opts = self.get_param('compat_opts', []) | |
6582 | ||
6583 | mobj = self._get_url_mobj(url) | |
6584 | pre, tab, post, is_channel = mobj['pre'], mobj['tab'], mobj['post'], not mobj['not_channel'] | |
6585 | if is_channel and smuggled_data.get('is_music_url'): | |
6586 | if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist | |
6587 | return self.url_result( | |
6588 | f'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE, item_id[2:]) | |
6589 | elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist | |
6590 | mdata = self._extract_tab_endpoint( | |
6591 | f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music') | |
6592 | murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'), | |
6593 | get_all=False, expected_type=str) | |
6594 | if not murl: | |
6595 | raise ExtractorError('Failed to resolve album to playlist') | |
6596 | return self.url_result(murl, YoutubeTabIE) | |
6597 | elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/ | |
6598 | return self.url_result( | |
6599 | f'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE, item_id) | |
6600 | ||
6601 | original_tab_id, display_id = tab[1:], f'{item_id}{tab}' | |
6602 | if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts: | |
6603 | url = f'{pre}/videos{post}' | |
6604 | if smuggled_data.get('is_music_url'): | |
6605 | self.report_warning(f'YouTube Music is not directly supported. Redirecting to {url}') | |
6606 | ||
6607 | # Handle both video/playlist URLs | |
6608 | qs = parse_qs(url) | |
6609 | video_id, playlist_id = [traverse_obj(qs, (key, 0)) for key in ('v', 'list')] | |
6610 | if not video_id and mobj['not_channel'].startswith('watch'): | |
6611 | if not playlist_id: | |
6612 | # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable | |
6613 | raise ExtractorError('A video URL was given without video ID', expected=True) | |
6614 | # Common mistake: https://www.youtube.com/watch?list=playlist_id | |
6615 | self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}') | |
6616 | return self.url_result( | |
6617 | f'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE, playlist_id) | |
6618 | ||
6619 | if not self._yes_playlist(playlist_id, video_id): | |
6620 | return self.url_result( | |
6621 | f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id) | |
6622 | ||
6623 | data, ytcfg = self._extract_data(url, display_id) | |
6624 | ||
6625 | # YouTube may provide a non-standard redirect to the regional channel | |
6626 | # See: https://github.com/yt-dlp/yt-dlp/issues/2694 | |
6627 | # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects | |
6628 | redirect_url = traverse_obj( | |
6629 | data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False) | |
6630 | if redirect_url and 'no-youtube-channel-redirect' not in compat_opts: | |
6631 | redirect_url = ''.join((urljoin('https://www.youtube.com', redirect_url), tab, post)) | |
6632 | self.to_screen(f'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}') | |
6633 | return self.url_result(redirect_url, YoutubeTabIE) | |
6634 | ||
6635 | tabs, extra_tabs = self._extract_tab_renderers(data), [] | |
6636 | if is_channel and tabs and 'no-youtube-channel-redirect' not in compat_opts: | |
6637 | selected_tab = self._extract_selected_tab(tabs) | |
6638 | selected_tab_id, selected_tab_name = self._extract_tab_id_and_name(selected_tab, url) # NB: Name may be translated | |
6639 | self.write_debug(f'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}') | |
6640 | ||
6641 | # /about is no longer a tab | |
6642 | if original_tab_id == 'about': | |
6643 | return self._empty_playlist(item_id, data) | |
6644 | ||
6645 | if not original_tab_id and selected_tab_name: | |
6646 | self.to_screen('Downloading all uploads of the channel. ' | |
6647 | 'To download only the videos in a specific tab, pass the tab\'s URL') | |
6648 | if self._has_tab(tabs, 'streams'): | |
6649 | extra_tabs.append(''.join((pre, '/streams', post))) | |
6650 | if self._has_tab(tabs, 'shorts'): | |
6651 | extra_tabs.append(''.join((pre, '/shorts', post))) | |
6652 | # XXX: Members-only tab should also be extracted | |
6653 | ||
6654 | if not extra_tabs and selected_tab_id != 'videos': | |
6655 | # Channel does not have streams, shorts or videos tabs | |
6656 | if item_id[:2] != 'UC': | |
6657 | return self._empty_playlist(item_id, data) | |
6658 | ||
6659 | # Topic channels don't have /videos. Use the equivalent playlist instead | |
6660 | pl_id = f'UU{item_id[2:]}' | |
6661 | pl_url = f'https://www.youtube.com/playlist?list={pl_id}' | |
6662 | try: | |
6663 | data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True) | |
6664 | except ExtractorError: | |
6665 | return self._empty_playlist(item_id, data) | |
6666 | else: | |
6667 | item_id, url = pl_id, pl_url | |
6668 | self.to_screen( | |
6669 | f'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead') | |
6670 | ||
6671 | elif extra_tabs and selected_tab_id != 'videos': | |
6672 | # When there are shorts/live tabs but not videos tab | |
6673 | url, data = f'{pre}{post}', None | |
6674 | ||
6675 | elif (original_tab_id or 'videos') != selected_tab_id: | |
6676 | if original_tab_id == 'live': | |
6677 | # Live tab should have redirected to the video | |
6678 | # Except in the case the channel has an actual live tab | |
6679 | # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live | |
6680 | raise UserNotLive(video_id=item_id) | |
6681 | elif selected_tab_name: | |
6682 | raise ExtractorError(f'This channel does not have a {original_tab_id} tab', expected=True) | |
6683 | ||
6684 | # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg | |
6685 | url = f'{pre}{post}' | |
6686 | ||
6687 | # YouTube sometimes provides a button to reload playlist with unavailable videos. | |
6688 | if 'no-youtube-unavailable-videos' not in compat_opts: | |
6689 | data = self._reload_with_unavailable_videos(display_id, data, ytcfg) or data | |
6690 | self._extract_and_report_alerts(data, only_once=True) | |
6691 | ||
6692 | tabs, entries = self._extract_tab_renderers(data), [] | |
6693 | if tabs: | |
6694 | entries = [self._extract_from_tabs(item_id, ytcfg, data, tabs)] | |
6695 | entries[0].update({ | |
6696 | 'extractor_key': YoutubeTabIE.ie_key(), | |
6697 | 'extractor': YoutubeTabIE.IE_NAME, | |
6698 | 'webpage_url': url, | |
6699 | }) | |
6700 | if self.get_param('playlist_items') == '0': | |
6701 | entries.extend(self.url_result(u, YoutubeTabIE) for u in extra_tabs) | |
6702 | else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result` | |
6703 | entries.extend(map(self._real_extract, extra_tabs)) | |
6704 | ||
6705 | if len(entries) == 1: | |
6706 | return entries[0] | |
6707 | elif entries: | |
6708 | metadata = self._extract_metadata_from_tabs(item_id, data) | |
6709 | uploads_url = 'the Uploads (UU) playlist URL' | |
6710 | if try_get(metadata, lambda x: x['channel_id'].startswith('UC')): | |
6711 | uploads_url = f'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}' | |
6712 | self.to_screen( | |
6713 | 'Downloading as multiple playlists, separated by tabs. ' | |
6714 | f'To download as a single playlist instead, pass {uploads_url}') | |
6715 | return self.playlist_result(entries, item_id, **metadata) | |
6716 | ||
6717 | # Inline playlist | |
6718 | playlist = traverse_obj( | |
6719 | data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict) | |
6720 | if playlist: | |
6721 | return self._extract_from_playlist(item_id, url, data, playlist, ytcfg) | |
6722 | ||
6723 | video_id = traverse_obj( | |
6724 | data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id | |
6725 | if video_id: | |
6726 | if tab != '/live': # live tab is expected to redirect to video | |
6727 | self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}') | |
6728 | return self.url_result(f'https://www.youtube.com/watch?v={video_id}', YoutubeIE, video_id) | |
6729 | ||
6730 | raise ExtractorError('Unable to recognize tab page') | |
6731 | ||
6732 | ||
6733 | class YoutubePlaylistIE(InfoExtractor): | |
6734 | IE_DESC = 'YouTube playlists' | |
6735 | _VALID_URL = r'''(?x)(?: | |
6736 | (?:https?://)? | |
6737 | (?:\w+\.)? | |
6738 | (?: | |
6739 | (?: | |
6740 | youtube(?:kids)?\.com| | |
6741 | %(invidious)s | |
6742 | ) | |
6743 | /.*?\?.*?\blist= | |
6744 | )? | |
6745 | (?P<id>%(playlist_id)s) | |
6746 | )''' % { | |
6747 | 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE, | |
6748 | 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), | |
6749 | } | |
6750 | IE_NAME = 'youtube:playlist' | |
6751 | _TESTS = [{ | |
6752 | 'note': 'issue #673', | |
6753 | 'url': 'PLBB231211A4F62143', | |
6754 | 'info_dict': { | |
6755 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', | |
6756 | 'id': 'PLBB231211A4F62143', | |
6757 | 'uploader': 'Wickman', | |
6758 | 'uploader_id': '@WickmanVT', | |
6759 | 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2', | |
6760 | 'view_count': int, | |
6761 | 'uploader_url': 'https://www.youtube.com/@WickmanVT', | |
6762 | 'modified_date': r're:\d{8}', | |
6763 | 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q', | |
6764 | 'channel': 'Wickman', | |
6765 | 'tags': [], | |
6766 | 'channel_url': 'https://www.youtube.com/channel/UCKSpbfbl5kRQpTdL7kMc-1Q', | |
6767 | 'availability': 'public', | |
6768 | }, | |
6769 | 'playlist_mincount': 29, | |
6770 | }, { | |
6771 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
6772 | 'info_dict': { | |
6773 | 'title': 'YDL_safe_search', | |
6774 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
6775 | }, | |
6776 | 'playlist_count': 2, | |
6777 | 'skip': 'This playlist is private', | |
6778 | }, { | |
6779 | 'note': 'embedded', | |
6780 | 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
6781 | 'playlist_count': 4, | |
6782 | 'info_dict': { | |
6783 | 'title': 'JODA15', | |
6784 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
6785 | 'uploader': 'milan', | |
6786 | 'uploader_id': '@milan5503', | |
6787 | 'description': '', | |
6788 | 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw', | |
6789 | 'tags': [], | |
6790 | 'modified_date': '20140919', | |
6791 | 'view_count': int, | |
6792 | 'channel': 'milan', | |
6793 | 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw', | |
6794 | 'uploader_url': 'https://www.youtube.com/@milan5503', | |
6795 | 'availability': 'public', | |
6796 | }, | |
6797 | 'expected_warnings': [r'[Uu]navailable videos? (is|are|will be) hidden', 'Retrying', 'Giving up'], | |
6798 | }, { | |
6799 | 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
6800 | 'playlist_mincount': 455, | |
6801 | 'info_dict': { | |
6802 | 'title': '2018 Chinese New Singles (11/6 updated)', | |
6803 | 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
6804 | 'uploader': 'LBK', | |
6805 | 'uploader_id': '@music_king', | |
6806 | 'description': 'md5:da521864744d60a198e3a88af4db0d9d', | |
6807 | 'channel': 'LBK', | |
6808 | 'view_count': int, | |
6809 | 'channel_url': 'https://www.youtube.com/channel/UC21nz3_MesPLqtDqwdvnoxA', | |
6810 | 'tags': [], | |
6811 | 'uploader_url': 'https://www.youtube.com/@music_king', | |
6812 | 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA', | |
6813 | 'modified_date': r're:\d{8}', | |
6814 | 'availability': 'public', | |
6815 | }, | |
6816 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], | |
6817 | }, { | |
6818 | 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', | |
6819 | 'only_matching': True, | |
6820 | }, { | |
6821 | # music album playlist | |
6822 | 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', | |
6823 | 'only_matching': True, | |
6824 | }] | |
6825 | ||
6826 | @classmethod | |
6827 | def suitable(cls, url): | |
6828 | if YoutubeTabIE.suitable(url): | |
6829 | return False | |
6830 | from ..utils import parse_qs | |
6831 | qs = parse_qs(url) | |
6832 | if qs.get('v', [None])[0]: | |
6833 | return False | |
6834 | return super().suitable(url) | |
6835 | ||
6836 | def _real_extract(self, url): | |
6837 | playlist_id = self._match_id(url) | |
6838 | is_music_url = YoutubeBaseInfoExtractor.is_music_url(url) | |
6839 | url = update_url_query( | |
6840 | 'https://www.youtube.com/playlist', | |
6841 | parse_qs(url) or {'list': playlist_id}) | |
6842 | if is_music_url: | |
6843 | url = smuggle_url(url, {'is_music_url': True}) | |
6844 | return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
6845 | ||
6846 | ||
6847 | class YoutubeYtBeIE(InfoExtractor): | |
6848 | IE_DESC = 'youtu.be' | |
6849 | _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} | |
6850 | _TESTS = [{ | |
6851 | 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', | |
6852 | 'info_dict': { | |
6853 | 'id': 'yeWKywCrFtk', | |
6854 | 'ext': 'mp4', | |
6855 | 'title': 'Small Scale Baler and Braiding Rugs', | |
6856 | 'uploader': 'Backus-Page House Museum', | |
6857 | 'uploader_id': '@backuspagemuseum', | |
6858 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/@backuspagemuseum', | |
6859 | 'upload_date': '20161008', | |
6860 | 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', | |
6861 | 'categories': ['Nonprofits & Activism'], | |
6862 | 'tags': list, | |
6863 | 'like_count': int, | |
6864 | 'age_limit': 0, | |
6865 | 'playable_in_embed': True, | |
6866 | 'thumbnail': r're:^https?://.*\.webp', | |
6867 | 'channel': 'Backus-Page House Museum', | |
6868 | 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw', | |
6869 | 'live_status': 'not_live', | |
6870 | 'view_count': int, | |
6871 | 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw', | |
6872 | 'availability': 'public', | |
6873 | 'duration': 59, | |
6874 | 'comment_count': int, | |
6875 | 'channel_follower_count': int | |
6876 | }, | |
6877 | 'params': { | |
6878 | 'noplaylist': True, | |
6879 | 'skip_download': True, | |
6880 | }, | |
6881 | }, { | |
6882 | 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', | |
6883 | 'only_matching': True, | |
6884 | }] | |
6885 | ||
6886 | def _real_extract(self, url): | |
6887 | mobj = self._match_valid_url(url) | |
6888 | video_id = mobj.group('id') | |
6889 | playlist_id = mobj.group('playlist_id') | |
6890 | return self.url_result( | |
6891 | update_url_query('https://www.youtube.com/watch', { | |
6892 | 'v': video_id, | |
6893 | 'list': playlist_id, | |
6894 | 'feature': 'youtu.be', | |
6895 | }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
6896 | ||
6897 | ||
6898 | class YoutubeLivestreamEmbedIE(InfoExtractor): | |
6899 | IE_DESC = 'YouTube livestream embeds' | |
6900 | _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)' | |
6901 | _TESTS = [{ | |
6902 | 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA', | |
6903 | 'only_matching': True, | |
6904 | }] | |
6905 | ||
6906 | def _real_extract(self, url): | |
6907 | channel_id = self._match_id(url) | |
6908 | return self.url_result( | |
6909 | f'https://www.youtube.com/channel/{channel_id}/live', | |
6910 | ie=YoutubeTabIE.ie_key(), video_id=channel_id) | |
6911 | ||
6912 | ||
6913 | class YoutubeYtUserIE(InfoExtractor): | |
6914 | IE_DESC = 'YouTube user videos; "ytuser:" prefix' | |
6915 | IE_NAME = 'youtube:user' | |
6916 | _VALID_URL = r'ytuser:(?P<id>.+)' | |
6917 | _TESTS = [{ | |
6918 | 'url': 'ytuser:phihag', | |
6919 | 'only_matching': True, | |
6920 | }] | |
6921 | ||
6922 | def _real_extract(self, url): | |
6923 | user_id = self._match_id(url) | |
6924 | return self.url_result(f'https://www.youtube.com/user/{user_id}', YoutubeTabIE, user_id) | |
6925 | ||
6926 | ||
6927 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): | |
6928 | IE_NAME = 'youtube:favorites' | |
6929 | IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)' | |
6930 | _VALID_URL = r':ytfav(?:ou?rite)?s?' | |
6931 | _LOGIN_REQUIRED = True | |
6932 | _TESTS = [{ | |
6933 | 'url': ':ytfav', | |
6934 | 'only_matching': True, | |
6935 | }, { | |
6936 | 'url': ':ytfavorites', | |
6937 | 'only_matching': True, | |
6938 | }] | |
6939 | ||
6940 | def _real_extract(self, url): | |
6941 | return self.url_result( | |
6942 | 'https://www.youtube.com/playlist?list=LL', | |
6943 | ie=YoutubeTabIE.ie_key()) | |
6944 | ||
6945 | ||
6946 | class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor): | |
6947 | IE_NAME = 'youtube:notif' | |
6948 | IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)' | |
6949 | _VALID_URL = r':ytnotif(?:ication)?s?' | |
6950 | _LOGIN_REQUIRED = True | |
6951 | _TESTS = [{ | |
6952 | 'url': ':ytnotif', | |
6953 | 'only_matching': True, | |
6954 | }, { | |
6955 | 'url': ':ytnotifications', | |
6956 | 'only_matching': True, | |
6957 | }] | |
6958 | ||
6959 | def _extract_notification_menu(self, response, continuation_list): | |
6960 | notification_list = traverse_obj( | |
6961 | response, | |
6962 | ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'), | |
6963 | ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'), | |
6964 | expected_type=list) or [] | |
6965 | continuation_list[0] = None | |
6966 | for item in notification_list: | |
6967 | entry = self._extract_notification_renderer(item.get('notificationRenderer')) | |
6968 | if entry: | |
6969 | yield entry | |
6970 | continuation = item.get('continuationItemRenderer') | |
6971 | if continuation: | |
6972 | continuation_list[0] = continuation | |
6973 | ||
6974 | def _extract_notification_renderer(self, notification): | |
6975 | video_id = traverse_obj( | |
6976 | notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) | |
6977 | url = f'https://www.youtube.com/watch?v={video_id}' | |
6978 | channel_id = None | |
6979 | if not video_id: | |
6980 | browse_ep = traverse_obj( | |
6981 | notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict) | |
6982 | channel_id = self.ucid_or_none(traverse_obj(browse_ep, 'browseId', expected_type=str)) | |
6983 | post_id = self._search_regex( | |
6984 | r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str), | |
6985 | 'post id', default=None) | |
6986 | if not channel_id or not post_id: | |
6987 | return | |
6988 | # The direct /post url redirects to this in the browser | |
6989 | url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}' | |
6990 | ||
6991 | channel = traverse_obj( | |
6992 | notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'), | |
6993 | expected_type=str) | |
6994 | notification_title = self._get_text(notification, 'shortMessage') | |
6995 | if notification_title: | |
6996 | notification_title = notification_title.replace('\xad', '') # remove soft hyphens | |
6997 | # TODO: handle recommended videos | |
6998 | title = self._search_regex( | |
6999 | rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title, | |
7000 | 'video title', default=None) | |
7001 | timestamp = (self._parse_time_text(self._get_text(notification, 'sentTimeText')) | |
7002 | if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE) | |
7003 | else None) | |
7004 | return { | |
7005 | '_type': 'url', | |
7006 | 'url': url, | |
7007 | 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(), | |
7008 | 'video_id': video_id, | |
7009 | 'title': title, | |
7010 | 'channel_id': channel_id, | |
7011 | 'channel': channel, | |
7012 | 'uploader': channel, | |
7013 | 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'), | |
7014 | 'timestamp': timestamp, | |
7015 | } | |
7016 | ||
7017 | def _notification_menu_entries(self, ytcfg): | |
7018 | continuation_list = [None] | |
7019 | response = None | |
7020 | for page in itertools.count(1): | |
7021 | ctoken = traverse_obj( | |
7022 | continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str) | |
7023 | response = self._extract_response( | |
7024 | item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg, | |
7025 | ep='notification/get_notification_menu', check_get_keys='actions', | |
7026 | headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))) | |
7027 | yield from self._extract_notification_menu(response, continuation_list) | |
7028 | if not continuation_list[0]: | |
7029 | break | |
7030 | ||
7031 | def _real_extract(self, url): | |
7032 | display_id = 'notifications' | |
7033 | ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {} | |
7034 | self._report_playlist_authcheck(ytcfg) | |
7035 | return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id) | |
7036 | ||
7037 | ||
7038 | class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor): | |
7039 | IE_DESC = 'YouTube search' | |
7040 | IE_NAME = 'youtube:search' | |
7041 | _SEARCH_KEY = 'ytsearch' | |
7042 | _SEARCH_PARAMS = 'EgIQAfABAQ==' # Videos only | |
7043 | _TESTS = [{ | |
7044 | 'url': 'ytsearch5:youtube-dl test video', | |
7045 | 'playlist_count': 5, | |
7046 | 'info_dict': { | |
7047 | 'id': 'youtube-dl test video', | |
7048 | 'title': 'youtube-dl test video', | |
7049 | } | |
7050 | }, { | |
7051 | 'note': 'Suicide/self-harm search warning', | |
7052 | 'url': 'ytsearch1:i hate myself and i wanna die', | |
7053 | 'playlist_count': 1, | |
7054 | 'info_dict': { | |
7055 | 'id': 'i hate myself and i wanna die', | |
7056 | 'title': 'i hate myself and i wanna die', | |
7057 | } | |
7058 | }] | |
7059 | ||
7060 | ||
7061 | class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor): | |
7062 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' | |
7063 | _SEARCH_KEY = 'ytsearchdate' | |
7064 | IE_DESC = 'YouTube search, newest videos first' | |
7065 | _SEARCH_PARAMS = 'CAISAhAB8AEB' # Videos only, sorted by date | |
7066 | _TESTS = [{ | |
7067 | 'url': 'ytsearchdate5:youtube-dl test video', | |
7068 | 'playlist_count': 5, | |
7069 | 'info_dict': { | |
7070 | 'id': 'youtube-dl test video', | |
7071 | 'title': 'youtube-dl test video', | |
7072 | } | |
7073 | }] | |
7074 | ||
7075 | ||
7076 | class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor): | |
7077 | IE_DESC = 'YouTube search URLs with sorting and filter support' | |
7078 | IE_NAME = YoutubeSearchIE.IE_NAME + '_url' | |
7079 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)' | |
7080 | _TESTS = [{ | |
7081 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
7082 | 'playlist_mincount': 5, | |
7083 | 'info_dict': { | |
7084 | 'id': 'youtube-dl test video', | |
7085 | 'title': 'youtube-dl test video', | |
7086 | } | |
7087 | }, { | |
7088 | 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D', | |
7089 | 'playlist_mincount': 5, | |
7090 | 'info_dict': { | |
7091 | 'id': 'python', | |
7092 | 'title': 'python', | |
7093 | } | |
7094 | }, { | |
7095 | 'url': 'https://www.youtube.com/results?search_query=%23cats', | |
7096 | 'playlist_mincount': 1, | |
7097 | 'info_dict': { | |
7098 | 'id': '#cats', | |
7099 | 'title': '#cats', | |
7100 | # The test suite does not have support for nested playlists | |
7101 | # 'entries': [{ | |
7102 | # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats', | |
7103 | # 'title': '#cats', | |
7104 | # }], | |
7105 | }, | |
7106 | }, { | |
7107 | # Channel results | |
7108 | 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D', | |
7109 | 'info_dict': { | |
7110 | 'id': 'kurzgesagt', | |
7111 | 'title': 'kurzgesagt', | |
7112 | }, | |
7113 | 'playlist': [{ | |
7114 | 'info_dict': { | |
7115 | '_type': 'url', | |
7116 | 'id': 'UCsXVk37bltHxD1rDPwtNM8Q', | |
7117 | 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q', | |
7118 | 'ie_key': 'YoutubeTab', | |
7119 | 'channel': 'Kurzgesagt – In a Nutshell', | |
7120 | 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc', | |
7121 | 'title': 'Kurzgesagt – In a Nutshell', | |
7122 | 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q', | |
7123 | # No longer available for search as it is set to the handle. | |
7124 | # 'playlist_count': int, | |
7125 | 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q', | |
7126 | 'thumbnails': list, | |
7127 | 'uploader_id': '@kurzgesagt', | |
7128 | 'uploader_url': 'https://www.youtube.com/@kurzgesagt', | |
7129 | 'uploader': 'Kurzgesagt – In a Nutshell', | |
7130 | 'channel_is_verified': True, | |
7131 | 'channel_follower_count': int, | |
7132 | } | |
7133 | }], | |
7134 | 'params': {'extract_flat': True, 'playlist_items': '1'}, | |
7135 | 'playlist_mincount': 1, | |
7136 | }, { | |
7137 | 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB', | |
7138 | 'only_matching': True, | |
7139 | }] | |
7140 | ||
7141 | def _real_extract(self, url): | |
7142 | qs = parse_qs(url) | |
7143 | query = (qs.get('search_query') or qs.get('q'))[0] | |
7144 | return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query) | |
7145 | ||
7146 | ||
7147 | class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor): | |
7148 | IE_DESC = 'YouTube music search URLs with selectable sections, e.g. #songs' | |
7149 | IE_NAME = 'youtube:music:search_url' | |
7150 | _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)' | |
7151 | _TESTS = [{ | |
7152 | 'url': 'https://music.youtube.com/search?q=royalty+free+music', | |
7153 | 'playlist_count': 16, | |
7154 | 'info_dict': { | |
7155 | 'id': 'royalty free music', | |
7156 | 'title': 'royalty free music', | |
7157 | } | |
7158 | }, { | |
7159 | 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D', | |
7160 | 'playlist_mincount': 30, | |
7161 | 'info_dict': { | |
7162 | 'id': 'royalty free music - songs', | |
7163 | 'title': 'royalty free music - songs', | |
7164 | }, | |
7165 | 'params': {'extract_flat': 'in_playlist'} | |
7166 | }, { | |
7167 | 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists', | |
7168 | 'playlist_mincount': 30, | |
7169 | 'info_dict': { | |
7170 | 'id': 'royalty free music - community playlists', | |
7171 | 'title': 'royalty free music - community playlists', | |
7172 | }, | |
7173 | 'params': {'extract_flat': 'in_playlist'} | |
7174 | }] | |
7175 | ||
7176 | _SECTIONS = { | |
7177 | 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==', | |
7178 | 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==', | |
7179 | 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF', | |
7180 | 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==', | |
7181 | 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==', | |
7182 | 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==', | |
7183 | } | |
7184 | ||
7185 | def _real_extract(self, url): | |
7186 | qs = parse_qs(url) | |
7187 | query = (qs.get('search_query') or qs.get('q'))[0] | |
7188 | params = qs.get('sp', (None,))[0] | |
7189 | if params: | |
7190 | section = next((k for k, v in self._SECTIONS.items() if v == params), params) | |
7191 | else: | |
7192 | section = urllib.parse.unquote_plus((url.split('#') + [''])[1]).lower() | |
7193 | params = self._SECTIONS.get(section) | |
7194 | if not params: | |
7195 | section = None | |
7196 | title = join_nonempty(query, section, delim=' - ') | |
7197 | return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title) | |
7198 | ||
7199 | ||
7200 | class YoutubeFeedsInfoExtractor(InfoExtractor): | |
7201 | """ | |
7202 | Base class for feed extractors | |
7203 | Subclasses must re-define the _FEED_NAME property. | |
7204 | """ | |
7205 | _LOGIN_REQUIRED = True | |
7206 | _FEED_NAME = 'feeds' | |
7207 | ||
7208 | def _real_initialize(self): | |
7209 | YoutubeBaseInfoExtractor._check_login_required(self) | |
7210 | ||
7211 | @classproperty | |
7212 | def IE_NAME(self): | |
7213 | return f'youtube:{self._FEED_NAME}' | |
7214 | ||
7215 | def _real_extract(self, url): | |
7216 | return self.url_result( | |
7217 | f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key()) | |
7218 | ||
7219 | ||
7220 | class YoutubeWatchLaterIE(InfoExtractor): | |
7221 | IE_NAME = 'youtube:watchlater' | |
7222 | IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)' | |
7223 | _VALID_URL = r':ytwatchlater' | |
7224 | _TESTS = [{ | |
7225 | 'url': ':ytwatchlater', | |
7226 | 'only_matching': True, | |
7227 | }] | |
7228 | ||
7229 | def _real_extract(self, url): | |
7230 | return self.url_result( | |
7231 | 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key()) | |
7232 | ||
7233 | ||
7234 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): | |
7235 | IE_DESC = 'YouTube recommended videos; ":ytrec" keyword' | |
7236 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?' | |
7237 | _FEED_NAME = 'recommended' | |
7238 | _LOGIN_REQUIRED = False | |
7239 | _TESTS = [{ | |
7240 | 'url': ':ytrec', | |
7241 | 'only_matching': True, | |
7242 | }, { | |
7243 | 'url': ':ytrecommended', | |
7244 | 'only_matching': True, | |
7245 | }, { | |
7246 | 'url': 'https://youtube.com', | |
7247 | 'only_matching': True, | |
7248 | }] | |
7249 | ||
7250 | ||
7251 | class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): | |
7252 | IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)' | |
7253 | _VALID_URL = r':ytsub(?:scription)?s?' | |
7254 | _FEED_NAME = 'subscriptions' | |
7255 | _TESTS = [{ | |
7256 | 'url': ':ytsubs', | |
7257 | 'only_matching': True, | |
7258 | }, { | |
7259 | 'url': ':ytsubscriptions', | |
7260 | 'only_matching': True, | |
7261 | }] | |
7262 | ||
7263 | ||
7264 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): | |
7265 | IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)' | |
7266 | _VALID_URL = r':ythis(?:tory)?' | |
7267 | _FEED_NAME = 'history' | |
7268 | _TESTS = [{ | |
7269 | 'url': ':ythistory', | |
7270 | 'only_matching': True, | |
7271 | }] | |
7272 | ||
7273 | ||
7274 | class YoutubeShortsAudioPivotIE(InfoExtractor): | |
7275 | IE_DESC = 'YouTube Shorts audio pivot (Shorts using audio of a given video)' | |
7276 | IE_NAME = 'youtube:shorts:pivot:audio' | |
7277 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts' | |
7278 | _TESTS = [{ | |
7279 | 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts', | |
7280 | 'only_matching': True, | |
7281 | }] | |
7282 | ||
7283 | @staticmethod | |
7284 | def _generate_audio_pivot_params(video_id): | |
7285 | """ | |
7286 | Generates sfv_audio_pivot browse params for this video id | |
7287 | """ | |
7288 | pb_params = b'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id.encode(),) * 3) | |
7289 | return urllib.parse.quote(base64.b64encode(pb_params).decode()) | |
7290 | ||
7291 | def _real_extract(self, url): | |
7292 | video_id = self._match_id(url) | |
7293 | return self.url_result( | |
7294 | f'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}', | |
7295 | ie=YoutubeTabIE) | |
7296 | ||
7297 | ||
7298 | class YoutubeTruncatedURLIE(InfoExtractor): | |
7299 | IE_NAME = 'youtube:truncated_url' | |
7300 | IE_DESC = False # Do not list | |
7301 | _VALID_URL = r'''(?x) | |
7302 | (?:https?://)? | |
7303 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
7304 | (?:watch\?(?: | |
7305 | feature=[a-z_]+| | |
7306 | annotation_id=annotation_[^&]+| | |
7307 | x-yt-cl=[0-9]+| | |
7308 | hl=[^&]*| | |
7309 | t=[0-9]+ | |
7310 | )? | |
7311 | | | |
7312 | attribution_link\?a=[^&]+ | |
7313 | ) | |
7314 | $ | |
7315 | ''' | |
7316 | ||
7317 | _TESTS = [{ | |
7318 | 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041', | |
7319 | 'only_matching': True, | |
7320 | }, { | |
7321 | 'url': 'https://www.youtube.com/watch?', | |
7322 | 'only_matching': True, | |
7323 | }, { | |
7324 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
7325 | 'only_matching': True, | |
7326 | }, { | |
7327 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
7328 | 'only_matching': True, | |
7329 | }, { | |
7330 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
7331 | 'only_matching': True, | |
7332 | }, { | |
7333 | 'url': 'https://www.youtube.com/watch?t=2372', | |
7334 | 'only_matching': True, | |
7335 | }] | |
7336 | ||
7337 | def _real_extract(self, url): | |
7338 | raise ExtractorError( | |
7339 | 'Did you forget to quote the URL? Remember that & is a meta ' | |
7340 | 'character in most shells, so you want to put the URL in quotes, ' | |
7341 | 'like youtube-dl ' | |
7342 | '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' | |
7343 | ' or simply youtube-dl BaW_jenozKc .', | |
7344 | expected=True) | |
7345 | ||
7346 | ||
7347 | class YoutubeClipIE(YoutubeTabBaseInfoExtractor): | |
7348 | IE_NAME = 'youtube:clip' | |
7349 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)' | |
7350 | _TESTS = [{ | |
7351 | # FIXME: Other metadata should be extracted from the clip, not from the base video | |
7352 | 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ', | |
7353 | 'info_dict': { | |
7354 | 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ', | |
7355 | 'ext': 'mp4', | |
7356 | 'section_start': 29.0, | |
7357 | 'section_end': 39.7, | |
7358 | 'duration': 10.7, | |
7359 | 'age_limit': 0, | |
7360 | 'availability': 'public', | |
7361 | 'categories': ['Gaming'], | |
7362 | 'channel': 'Scott The Woz', | |
7363 | 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ', | |
7364 | 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ', | |
7365 | 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7', | |
7366 | 'like_count': int, | |
7367 | 'playable_in_embed': True, | |
7368 | 'tags': 'count:17', | |
7369 | 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp', | |
7370 | 'title': 'Mobile Games on Console - Scott The Woz', | |
7371 | 'upload_date': '20210920', | |
7372 | 'uploader': 'Scott The Woz', | |
7373 | 'uploader_id': '@ScottTheWoz', | |
7374 | 'uploader_url': 'https://www.youtube.com/@ScottTheWoz', | |
7375 | 'view_count': int, | |
7376 | 'live_status': 'not_live', | |
7377 | 'channel_follower_count': int, | |
7378 | 'chapters': 'count:20', | |
7379 | 'comment_count': int, | |
7380 | 'heatmap': 'count:100', | |
7381 | } | |
7382 | }] | |
7383 | ||
7384 | def _real_extract(self, url): | |
7385 | clip_id = self._match_id(url) | |
7386 | _, data = self._extract_webpage(url, clip_id) | |
7387 | ||
7388 | video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId')) | |
7389 | if not video_id: | |
7390 | raise ExtractorError('Unable to find video ID') | |
7391 | ||
7392 | clip_data = traverse_obj(data, ( | |
7393 | 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer', | |
7394 | 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ..., | |
7395 | 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command', | |
7396 | 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False) | |
7397 | ||
7398 | return { | |
7399 | '_type': 'url_transparent', | |
7400 | 'url': f'https://www.youtube.com/watch?v={video_id}', | |
7401 | 'ie_key': YoutubeIE.ie_key(), | |
7402 | 'id': clip_id, | |
7403 | 'section_start': int(clip_data['startTimeMs']) / 1000, | |
7404 | 'section_end': int(clip_data['endTimeMs']) / 1000, | |
7405 | } | |
7406 | ||
7407 | ||
7408 | class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor): | |
7409 | IE_NAME = 'youtube:consent' | |
7410 | IE_DESC = False # Do not list | |
7411 | _VALID_URL = r'https?://consent\.youtube\.com/m\?' | |
7412 | _TESTS = [{ | |
7413 | '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', | |
7414 | 'info_dict': { | |
7415 | 'id': 'qVv6vCqciTM', | |
7416 | 'ext': 'mp4', | |
7417 | 'age_limit': 0, | |
7418 | 'uploader_id': '@sana_natori', | |
7419 | 'comment_count': int, | |
7420 | 'chapters': 'count:13', | |
7421 | 'upload_date': '20221223', | |
7422 | 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg', | |
7423 | 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA', | |
7424 | 'uploader_url': 'https://www.youtube.com/@sana_natori', | |
7425 | 'like_count': int, | |
7426 | 'release_date': '20221223', | |
7427 | 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'], | |
7428 | '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】', | |
7429 | 'view_count': int, | |
7430 | 'playable_in_embed': True, | |
7431 | 'duration': 4438, | |
7432 | 'availability': 'public', | |
7433 | 'channel_follower_count': int, | |
7434 | 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA', | |
7435 | 'categories': ['Entertainment'], | |
7436 | 'live_status': 'was_live', | |
7437 | 'release_timestamp': 1671793345, | |
7438 | 'channel': 'さなちゃんねる', | |
7439 | 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d', | |
7440 | 'uploader': 'さなちゃんねる', | |
7441 | 'channel_is_verified': True, | |
7442 | 'heatmap': 'count:100', | |
7443 | }, | |
7444 | 'add_ie': ['Youtube'], | |
7445 | 'params': {'skip_download': 'Youtube'}, | |
7446 | }] | |
7447 | ||
7448 | def _real_extract(self, url): | |
7449 | redirect_url = url_or_none(parse_qs(url).get('continue', [None])[-1]) | |
7450 | if not redirect_url: | |
7451 | raise ExtractorError('Invalid cookie consent redirect URL', expected=True) | |
7452 | return self.url_result(redirect_url) | |
7453 | ||
7454 | ||
7455 | class YoutubeTruncatedIDIE(InfoExtractor): | |
7456 | IE_NAME = 'youtube:truncated_id' | |
7457 | IE_DESC = False # Do not list | |
7458 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' | |
7459 | ||
7460 | _TESTS = [{ | |
7461 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
7462 | 'only_matching': True, | |
7463 | }] | |
7464 | ||
7465 | def _real_extract(self, url): | |
7466 | video_id = self._match_id(url) | |
7467 | raise ExtractorError( | |
7468 | f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.', | |
7469 | expected=True) |