]>
Commit | Line | Data |
---|---|---|
1 | import base64 | |
2 | import calendar | |
3 | import copy | |
4 | import datetime | |
5 | import hashlib | |
6 | import itertools | |
7 | import json | |
8 | import math | |
9 | import os.path | |
10 | import random | |
11 | import re | |
12 | import sys | |
13 | import threading | |
14 | import time | |
15 | import traceback | |
16 | ||
17 | from .common import InfoExtractor, SearchInfoExtractor | |
18 | from ..compat import functools # isort: split | |
19 | from ..compat import ( | |
20 | compat_chr, | |
21 | compat_HTTPError, | |
22 | compat_parse_qs, | |
23 | compat_str, | |
24 | compat_urllib_parse_unquote_plus, | |
25 | compat_urllib_parse_urlencode, | |
26 | compat_urllib_parse_urlparse, | |
27 | compat_urlparse, | |
28 | ) | |
29 | from ..jsinterp import JSInterpreter | |
30 | from ..utils import ( | |
31 | NO_DEFAULT, | |
32 | ExtractorError, | |
33 | bug_reports_message, | |
34 | classproperty, | |
35 | clean_html, | |
36 | datetime_from_str, | |
37 | dict_get, | |
38 | error_to_compat_str, | |
39 | float_or_none, | |
40 | format_field, | |
41 | get_first, | |
42 | int_or_none, | |
43 | is_html, | |
44 | join_nonempty, | |
45 | js_to_json, | |
46 | mimetype2ext, | |
47 | network_exceptions, | |
48 | orderedSet, | |
49 | parse_codecs, | |
50 | parse_count, | |
51 | parse_duration, | |
52 | parse_iso8601, | |
53 | parse_qs, | |
54 | qualities, | |
55 | remove_end, | |
56 | remove_start, | |
57 | smuggle_url, | |
58 | str_or_none, | |
59 | str_to_int, | |
60 | strftime_or_none, | |
61 | traverse_obj, | |
62 | try_get, | |
63 | unescapeHTML, | |
64 | unified_strdate, | |
65 | unified_timestamp, | |
66 | unsmuggle_url, | |
67 | update_url_query, | |
68 | url_or_none, | |
69 | urljoin, | |
70 | variadic, | |
71 | ) | |
72 | ||
73 | # any clients starting with _ cannot be explicity requested by the user | |
74 | INNERTUBE_CLIENTS = { | |
75 | 'web': { | |
76 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
77 | 'INNERTUBE_CONTEXT': { | |
78 | 'client': { | |
79 | 'clientName': 'WEB', | |
80 | 'clientVersion': '2.20211221.00.00', | |
81 | } | |
82 | }, | |
83 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 1 | |
84 | }, | |
85 | 'web_embedded': { | |
86 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
87 | 'INNERTUBE_CONTEXT': { | |
88 | 'client': { | |
89 | 'clientName': 'WEB_EMBEDDED_PLAYER', | |
90 | 'clientVersion': '1.20211215.00.01', | |
91 | }, | |
92 | }, | |
93 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 56 | |
94 | }, | |
95 | 'web_music': { | |
96 | 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30', | |
97 | 'INNERTUBE_HOST': 'music.youtube.com', | |
98 | 'INNERTUBE_CONTEXT': { | |
99 | 'client': { | |
100 | 'clientName': 'WEB_REMIX', | |
101 | 'clientVersion': '1.20211213.00.00', | |
102 | } | |
103 | }, | |
104 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 67, | |
105 | }, | |
106 | 'web_creator': { | |
107 | 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo', | |
108 | 'INNERTUBE_CONTEXT': { | |
109 | 'client': { | |
110 | 'clientName': 'WEB_CREATOR', | |
111 | 'clientVersion': '1.20211220.02.00', | |
112 | } | |
113 | }, | |
114 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 62, | |
115 | }, | |
116 | 'android': { | |
117 | 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w', | |
118 | 'INNERTUBE_CONTEXT': { | |
119 | 'client': { | |
120 | 'clientName': 'ANDROID', | |
121 | 'clientVersion': '16.49', | |
122 | } | |
123 | }, | |
124 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 3, | |
125 | 'REQUIRE_JS_PLAYER': False | |
126 | }, | |
127 | 'android_embedded': { | |
128 | 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw', | |
129 | 'INNERTUBE_CONTEXT': { | |
130 | 'client': { | |
131 | 'clientName': 'ANDROID_EMBEDDED_PLAYER', | |
132 | 'clientVersion': '16.49', | |
133 | }, | |
134 | }, | |
135 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 55, | |
136 | 'REQUIRE_JS_PLAYER': False | |
137 | }, | |
138 | 'android_music': { | |
139 | 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI', | |
140 | 'INNERTUBE_CONTEXT': { | |
141 | 'client': { | |
142 | 'clientName': 'ANDROID_MUSIC', | |
143 | 'clientVersion': '4.57', | |
144 | } | |
145 | }, | |
146 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 21, | |
147 | 'REQUIRE_JS_PLAYER': False | |
148 | }, | |
149 | 'android_creator': { | |
150 | 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8', | |
151 | 'INNERTUBE_CONTEXT': { | |
152 | 'client': { | |
153 | 'clientName': 'ANDROID_CREATOR', | |
154 | 'clientVersion': '21.47', | |
155 | }, | |
156 | }, | |
157 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 14, | |
158 | 'REQUIRE_JS_PLAYER': False | |
159 | }, | |
160 | # iOS clients have HLS live streams. Setting device model to get 60fps formats. | |
161 | # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558 | |
162 | 'ios': { | |
163 | 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc', | |
164 | 'INNERTUBE_CONTEXT': { | |
165 | 'client': { | |
166 | 'clientName': 'IOS', | |
167 | 'clientVersion': '16.46', | |
168 | 'deviceModel': 'iPhone14,3', | |
169 | } | |
170 | }, | |
171 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 5, | |
172 | 'REQUIRE_JS_PLAYER': False | |
173 | }, | |
174 | 'ios_embedded': { | |
175 | 'INNERTUBE_CONTEXT': { | |
176 | 'client': { | |
177 | 'clientName': 'IOS_MESSAGES_EXTENSION', | |
178 | 'clientVersion': '16.46', | |
179 | 'deviceModel': 'iPhone14,3', | |
180 | }, | |
181 | }, | |
182 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 66, | |
183 | 'REQUIRE_JS_PLAYER': False | |
184 | }, | |
185 | 'ios_music': { | |
186 | 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s', | |
187 | 'INNERTUBE_CONTEXT': { | |
188 | 'client': { | |
189 | 'clientName': 'IOS_MUSIC', | |
190 | 'clientVersion': '4.57', | |
191 | }, | |
192 | }, | |
193 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 26, | |
194 | 'REQUIRE_JS_PLAYER': False | |
195 | }, | |
196 | 'ios_creator': { | |
197 | 'INNERTUBE_CONTEXT': { | |
198 | 'client': { | |
199 | 'clientName': 'IOS_CREATOR', | |
200 | 'clientVersion': '21.47', | |
201 | }, | |
202 | }, | |
203 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 15, | |
204 | 'REQUIRE_JS_PLAYER': False | |
205 | }, | |
206 | # mweb has 'ultralow' formats | |
207 | # See: https://github.com/yt-dlp/yt-dlp/pull/557 | |
208 | 'mweb': { | |
209 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
210 | 'INNERTUBE_CONTEXT': { | |
211 | 'client': { | |
212 | 'clientName': 'MWEB', | |
213 | 'clientVersion': '2.20211221.01.00', | |
214 | } | |
215 | }, | |
216 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 2 | |
217 | }, | |
218 | # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option) | |
219 | # See: https://github.com/zerodytrash/YouTube-Internal-Clients | |
220 | 'tv_embedded': { | |
221 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
222 | 'INNERTUBE_CONTEXT': { | |
223 | 'client': { | |
224 | 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER', | |
225 | 'clientVersion': '2.0', | |
226 | }, | |
227 | }, | |
228 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 85 | |
229 | }, | |
230 | } | |
231 | ||
232 | ||
233 | def _split_innertube_client(client_name): | |
234 | variant, *base = client_name.rsplit('.', 1) | |
235 | if base: | |
236 | return variant, base[0], variant | |
237 | base, *variant = client_name.split('_', 1) | |
238 | return client_name, base, variant[0] if variant else None | |
239 | ||
240 | ||
241 | def build_innertube_clients(): | |
242 | THIRD_PARTY = { | |
243 | 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL | |
244 | } | |
245 | BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb') | |
246 | priority = qualities(BASE_CLIENTS[::-1]) | |
247 | ||
248 | for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()): | |
249 | ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8') | |
250 | ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com') | |
251 | ytcfg.setdefault('REQUIRE_JS_PLAYER', True) | |
252 | ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en') | |
253 | ||
254 | _, base_client, variant = _split_innertube_client(client) | |
255 | ytcfg['priority'] = 10 * priority(base_client) | |
256 | ||
257 | if not variant: | |
258 | INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg) | |
259 | embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED' | |
260 | embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY | |
261 | embedscreen['priority'] -= 3 | |
262 | elif variant == 'embedded': | |
263 | ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY | |
264 | ytcfg['priority'] -= 2 | |
265 | else: | |
266 | ytcfg['priority'] -= 3 | |
267 | ||
268 | ||
269 | build_innertube_clients() | |
270 | ||
271 | ||
272 | class YoutubeBaseInfoExtractor(InfoExtractor): | |
273 | """Provide base functions for Youtube extractors""" | |
274 | ||
275 | _RESERVED_NAMES = ( | |
276 | r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|' | |
277 | r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|' | |
278 | r'browse|oembed|get_video_info|iframe_api|s/player|' | |
279 | r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout') | |
280 | ||
281 | _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)' | |
282 | ||
283 | # _NETRC_MACHINE = 'youtube' | |
284 | ||
285 | # If True it will raise an error if no login info is provided | |
286 | _LOGIN_REQUIRED = False | |
287 | ||
288 | _INVIDIOUS_SITES = ( | |
289 | # invidious-redirect websites | |
290 | r'(?:www\.)?redirect\.invidious\.io', | |
291 | r'(?:(?:www|dev)\.)?invidio\.us', | |
292 | # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md | |
293 | r'(?:www\.)?invidious\.pussthecat\.org', | |
294 | r'(?:www\.)?invidious\.zee\.li', | |
295 | r'(?:www\.)?invidious\.ethibox\.fr', | |
296 | r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion', | |
297 | r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion', | |
298 | r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion', | |
299 | # youtube-dl invidious instances list | |
300 | r'(?:(?:www|no)\.)?invidiou\.sh', | |
301 | r'(?:(?:www|fi)\.)?invidious\.snopyta\.org', | |
302 | r'(?:www\.)?invidious\.kabi\.tk', | |
303 | r'(?:www\.)?invidious\.mastodon\.host', | |
304 | r'(?:www\.)?invidious\.zapashcanon\.fr', | |
305 | r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks', | |
306 | r'(?:www\.)?invidious\.tinfoil-hat\.net', | |
307 | r'(?:www\.)?invidious\.himiko\.cloud', | |
308 | r'(?:www\.)?invidious\.reallyancient\.tech', | |
309 | r'(?:www\.)?invidious\.tube', | |
310 | r'(?:www\.)?invidiou\.site', | |
311 | r'(?:www\.)?invidious\.site', | |
312 | r'(?:www\.)?invidious\.xyz', | |
313 | r'(?:www\.)?invidious\.nixnet\.xyz', | |
314 | r'(?:www\.)?invidious\.048596\.xyz', | |
315 | r'(?:www\.)?invidious\.drycat\.fr', | |
316 | r'(?:www\.)?inv\.skyn3t\.in', | |
317 | r'(?:www\.)?tube\.poal\.co', | |
318 | r'(?:www\.)?tube\.connect\.cafe', | |
319 | r'(?:www\.)?vid\.wxzm\.sx', | |
320 | r'(?:www\.)?vid\.mint\.lgbt', | |
321 | r'(?:www\.)?vid\.puffyan\.us', | |
322 | r'(?:www\.)?yewtu\.be', | |
323 | r'(?:www\.)?yt\.elukerio\.org', | |
324 | r'(?:www\.)?yt\.lelux\.fi', | |
325 | r'(?:www\.)?invidious\.ggc-project\.de', | |
326 | r'(?:www\.)?yt\.maisputain\.ovh', | |
327 | r'(?:www\.)?ytprivate\.com', | |
328 | r'(?:www\.)?invidious\.13ad\.de', | |
329 | r'(?:www\.)?invidious\.toot\.koeln', | |
330 | r'(?:www\.)?invidious\.fdn\.fr', | |
331 | r'(?:www\.)?watch\.nettohikari\.com', | |
332 | r'(?:www\.)?invidious\.namazso\.eu', | |
333 | r'(?:www\.)?invidious\.silkky\.cloud', | |
334 | r'(?:www\.)?invidious\.exonip\.de', | |
335 | r'(?:www\.)?invidious\.riverside\.rocks', | |
336 | r'(?:www\.)?invidious\.blamefran\.net', | |
337 | r'(?:www\.)?invidious\.moomoo\.de', | |
338 | r'(?:www\.)?ytb\.trom\.tf', | |
339 | r'(?:www\.)?yt\.cyberhost\.uk', | |
340 | r'(?:www\.)?kgg2m7yk5aybusll\.onion', | |
341 | r'(?:www\.)?qklhadlycap4cnod\.onion', | |
342 | r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion', | |
343 | r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion', | |
344 | r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion', | |
345 | r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion', | |
346 | r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p', | |
347 | r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion', | |
348 | r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion', | |
349 | r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion', | |
350 | r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion', | |
351 | r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion', | |
352 | # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances | |
353 | r'(?:www\.)?piped\.kavin\.rocks', | |
354 | r'(?:www\.)?piped\.silkky\.cloud', | |
355 | r'(?:www\.)?piped\.tokhmi\.xyz', | |
356 | r'(?:www\.)?piped\.moomoo\.me', | |
357 | r'(?:www\.)?il\.ax', | |
358 | r'(?:www\.)?piped\.syncpundit\.com', | |
359 | r'(?:www\.)?piped\.mha\.fi', | |
360 | r'(?:www\.)?piped\.mint\.lgbt', | |
361 | r'(?:www\.)?piped\.privacy\.com\.de', | |
362 | ) | |
363 | ||
364 | def _initialize_consent(self): | |
365 | cookies = self._get_cookies('https://www.youtube.com/') | |
366 | if cookies.get('__Secure-3PSID'): | |
367 | return | |
368 | consent_id = None | |
369 | consent = cookies.get('CONSENT') | |
370 | if consent: | |
371 | if 'YES' in consent.value: | |
372 | return | |
373 | consent_id = self._search_regex( | |
374 | r'PENDING\+(\d+)', consent.value, 'consent', default=None) | |
375 | if not consent_id: | |
376 | consent_id = random.randint(100, 999) | |
377 | self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id) | |
378 | ||
379 | def _initialize_pref(self): | |
380 | cookies = self._get_cookies('https://www.youtube.com/') | |
381 | pref_cookie = cookies.get('PREF') | |
382 | pref = {} | |
383 | if pref_cookie: | |
384 | try: | |
385 | pref = dict(compat_urlparse.parse_qsl(pref_cookie.value)) | |
386 | except ValueError: | |
387 | self.report_warning('Failed to parse user PREF cookie' + bug_reports_message()) | |
388 | pref.update({'hl': 'en', 'tz': 'UTC'}) | |
389 | self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref)) | |
390 | ||
391 | def _real_initialize(self): | |
392 | self._initialize_pref() | |
393 | self._initialize_consent() | |
394 | self._check_login_required() | |
395 | ||
396 | def _check_login_required(self): | |
397 | if self._LOGIN_REQUIRED and not self._cookies_passed: | |
398 | self.raise_login_required('Login details are needed to download this content', method='cookies') | |
399 | ||
400 | _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=' | |
401 | _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=' | |
402 | ||
403 | def _get_default_ytcfg(self, client='web'): | |
404 | return copy.deepcopy(INNERTUBE_CLIENTS[client]) | |
405 | ||
406 | def _get_innertube_host(self, client='web'): | |
407 | return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST'] | |
408 | ||
409 | def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'): | |
410 | # try_get but with fallback to default ytcfg client values when present | |
411 | _func = lambda y: try_get(y, getter, expected_type) | |
412 | return _func(ytcfg) or _func(self._get_default_ytcfg(default_client)) | |
413 | ||
414 | def _extract_client_name(self, ytcfg, default_client='web'): | |
415 | return self._ytcfg_get_safe( | |
416 | ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'], | |
417 | lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client) | |
418 | ||
419 | def _extract_client_version(self, ytcfg, default_client='web'): | |
420 | return self._ytcfg_get_safe( | |
421 | ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'], | |
422 | lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client) | |
423 | ||
424 | def _select_api_hostname(self, req_api_hostname, default_client=None): | |
425 | return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0] | |
426 | or req_api_hostname or self._get_innertube_host(default_client or 'web')) | |
427 | ||
428 | def _extract_api_key(self, ytcfg=None, default_client='web'): | |
429 | return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client) | |
430 | ||
431 | def _extract_context(self, ytcfg=None, default_client='web'): | |
432 | context = get_first( | |
433 | (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict) | |
434 | # Enforce language and tz for extraction | |
435 | client_context = traverse_obj(context, 'client', expected_type=dict, default={}) | |
436 | client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0}) | |
437 | return context | |
438 | ||
439 | _SAPISID = None | |
440 | ||
441 | def _generate_sapisidhash_header(self, origin='https://www.youtube.com'): | |
442 | time_now = round(time.time()) | |
443 | if self._SAPISID is None: | |
444 | yt_cookies = self._get_cookies('https://www.youtube.com') | |
445 | # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is. | |
446 | # See: https://github.com/yt-dlp/yt-dlp/issues/393 | |
447 | sapisid_cookie = dict_get( | |
448 | yt_cookies, ('__Secure-3PAPISID', 'SAPISID')) | |
449 | if sapisid_cookie and sapisid_cookie.value: | |
450 | self._SAPISID = sapisid_cookie.value | |
451 | self.write_debug('Extracted SAPISID cookie') | |
452 | # SAPISID cookie is required if not already present | |
453 | if not yt_cookies.get('SAPISID'): | |
454 | self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie') | |
455 | self._set_cookie( | |
456 | '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600) | |
457 | else: | |
458 | self._SAPISID = False | |
459 | if not self._SAPISID: | |
460 | return None | |
461 | # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323 | |
462 | sapisidhash = hashlib.sha1( | |
463 | f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest() | |
464 | return f'SAPISIDHASH {time_now}_{sapisidhash}' | |
465 | ||
466 | def _call_api(self, ep, query, video_id, fatal=True, headers=None, | |
467 | note='Downloading API JSON', errnote='Unable to download API page', | |
468 | context=None, api_key=None, api_hostname=None, default_client='web'): | |
469 | ||
470 | data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)} | |
471 | data.update(query) | |
472 | real_headers = self.generate_api_headers(default_client=default_client) | |
473 | real_headers.update({'content-type': 'application/json'}) | |
474 | if headers: | |
475 | real_headers.update(headers) | |
476 | api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0] | |
477 | or api_key or self._extract_api_key(default_client=default_client)) | |
478 | return self._download_json( | |
479 | f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}', | |
480 | video_id=video_id, fatal=fatal, note=note, errnote=errnote, | |
481 | data=json.dumps(data).encode('utf8'), headers=real_headers, | |
482 | query={'key': api_key, 'prettyPrint': 'false'}) | |
483 | ||
484 | def extract_yt_initial_data(self, item_id, webpage, fatal=True): | |
485 | return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal) | |
486 | ||
487 | @staticmethod | |
488 | def _extract_session_index(*data): | |
489 | """ | |
490 | Index of current account in account list. | |
491 | See: https://github.com/yt-dlp/yt-dlp/pull/519 | |
492 | """ | |
493 | for ytcfg in data: | |
494 | session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX'])) | |
495 | if session_index is not None: | |
496 | return session_index | |
497 | ||
498 | # Deprecated? | |
499 | def _extract_identity_token(self, ytcfg=None, webpage=None): | |
500 | if ytcfg: | |
501 | token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str) | |
502 | if token: | |
503 | return token | |
504 | if webpage: | |
505 | return self._search_regex( | |
506 | r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage, | |
507 | 'identity token', default=None, fatal=False) | |
508 | ||
509 | @staticmethod | |
510 | def _extract_account_syncid(*args): | |
511 | """ | |
512 | Extract syncId required to download private playlists of secondary channels | |
513 | @params response and/or ytcfg | |
514 | """ | |
515 | for data in args: | |
516 | # ytcfg includes channel_syncid if on secondary channel | |
517 | delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str) | |
518 | if delegated_sid: | |
519 | return delegated_sid | |
520 | sync_ids = (try_get( | |
521 | data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'], | |
522 | lambda x: x['DATASYNC_ID']), compat_str) or '').split('||') | |
523 | if len(sync_ids) >= 2 and sync_ids[1]: | |
524 | # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel | |
525 | # and just "user_syncid||" for primary channel. We only want the channel_syncid | |
526 | return sync_ids[0] | |
527 | ||
528 | @staticmethod | |
529 | def _extract_visitor_data(*args): | |
530 | """ | |
531 | Extracts visitorData from an API response or ytcfg | |
532 | Appears to be used to track session state | |
533 | """ | |
534 | return get_first( | |
535 | args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))], | |
536 | expected_type=str) | |
537 | ||
538 | @functools.cached_property | |
539 | def is_authenticated(self): | |
540 | return bool(self._generate_sapisidhash_header()) | |
541 | ||
542 | def extract_ytcfg(self, video_id, webpage): | |
543 | if not webpage: | |
544 | return {} | |
545 | return self._parse_json( | |
546 | self._search_regex( | |
547 | r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg', | |
548 | default='{}'), video_id, fatal=False) or {} | |
549 | ||
550 | def generate_api_headers( | |
551 | self, *, ytcfg=None, account_syncid=None, session_index=None, | |
552 | visitor_data=None, identity_token=None, api_hostname=None, default_client='web'): | |
553 | ||
554 | origin = 'https://' + (self._select_api_hostname(api_hostname, default_client)) | |
555 | headers = { | |
556 | 'X-YouTube-Client-Name': compat_str( | |
557 | self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)), | |
558 | 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client), | |
559 | 'Origin': origin, | |
560 | 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg), | |
561 | 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg), | |
562 | 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg) | |
563 | } | |
564 | if session_index is None: | |
565 | session_index = self._extract_session_index(ytcfg) | |
566 | if account_syncid or session_index is not None: | |
567 | headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0 | |
568 | ||
569 | auth = self._generate_sapisidhash_header(origin) | |
570 | if auth is not None: | |
571 | headers['Authorization'] = auth | |
572 | headers['X-Origin'] = origin | |
573 | return {h: v for h, v in headers.items() if v is not None} | |
574 | ||
575 | def _download_ytcfg(self, client, video_id): | |
576 | url = { | |
577 | 'web': 'https://www.youtube.com', | |
578 | 'web_music': 'https://music.youtube.com', | |
579 | 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1' | |
580 | }.get(client) | |
581 | if not url: | |
582 | return {} | |
583 | webpage = self._download_webpage( | |
584 | url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config') | |
585 | return self.extract_ytcfg(video_id, webpage) or {} | |
586 | ||
587 | @staticmethod | |
588 | def _build_api_continuation_query(continuation, ctp=None): | |
589 | query = { | |
590 | 'continuation': continuation | |
591 | } | |
592 | # TODO: Inconsistency with clickTrackingParams. | |
593 | # Currently we have a fixed ctp contained within context (from ytcfg) | |
594 | # and a ctp in root query for continuation. | |
595 | if ctp: | |
596 | query['clickTracking'] = {'clickTrackingParams': ctp} | |
597 | return query | |
598 | ||
599 | @classmethod | |
600 | def _extract_next_continuation_data(cls, renderer): | |
601 | next_continuation = try_get( | |
602 | renderer, (lambda x: x['continuations'][0]['nextContinuationData'], | |
603 | lambda x: x['continuation']['reloadContinuationData']), dict) | |
604 | if not next_continuation: | |
605 | return | |
606 | continuation = next_continuation.get('continuation') | |
607 | if not continuation: | |
608 | return | |
609 | ctp = next_continuation.get('clickTrackingParams') | |
610 | return cls._build_api_continuation_query(continuation, ctp) | |
611 | ||
612 | @classmethod | |
613 | def _extract_continuation_ep_data(cls, continuation_ep: dict): | |
614 | if isinstance(continuation_ep, dict): | |
615 | continuation = try_get( | |
616 | continuation_ep, lambda x: x['continuationCommand']['token'], compat_str) | |
617 | if not continuation: | |
618 | return | |
619 | ctp = continuation_ep.get('clickTrackingParams') | |
620 | return cls._build_api_continuation_query(continuation, ctp) | |
621 | ||
622 | @classmethod | |
623 | def _extract_continuation(cls, renderer): | |
624 | next_continuation = cls._extract_next_continuation_data(renderer) | |
625 | if next_continuation: | |
626 | return next_continuation | |
627 | ||
628 | contents = [] | |
629 | for key in ('contents', 'items'): | |
630 | contents.extend(try_get(renderer, lambda x: x[key], list) or []) | |
631 | ||
632 | for content in contents: | |
633 | if not isinstance(content, dict): | |
634 | continue | |
635 | continuation_ep = try_get( | |
636 | content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'], | |
637 | lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']), | |
638 | dict) | |
639 | continuation = cls._extract_continuation_ep_data(continuation_ep) | |
640 | if continuation: | |
641 | return continuation | |
642 | ||
643 | @classmethod | |
644 | def _extract_alerts(cls, data): | |
645 | for alert_dict in try_get(data, lambda x: x['alerts'], list) or []: | |
646 | if not isinstance(alert_dict, dict): | |
647 | continue | |
648 | for alert in alert_dict.values(): | |
649 | alert_type = alert.get('type') | |
650 | if not alert_type: | |
651 | continue | |
652 | message = cls._get_text(alert, 'text') | |
653 | if message: | |
654 | yield alert_type, message | |
655 | ||
656 | def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False): | |
657 | errors = [] | |
658 | warnings = [] | |
659 | for alert_type, alert_message in alerts: | |
660 | if alert_type.lower() == 'error' and fatal: | |
661 | errors.append([alert_type, alert_message]) | |
662 | else: | |
663 | warnings.append([alert_type, alert_message]) | |
664 | ||
665 | for alert_type, alert_message in (warnings + errors[:-1]): | |
666 | self.report_warning(f'YouTube said: {alert_type} - {alert_message}', only_once=only_once) | |
667 | if errors: | |
668 | raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected) | |
669 | ||
670 | def _extract_and_report_alerts(self, data, *args, **kwargs): | |
671 | return self._report_alerts(self._extract_alerts(data), *args, **kwargs) | |
672 | ||
673 | def _extract_badges(self, renderer: dict): | |
674 | badges = set() | |
675 | for badge in try_get(renderer, lambda x: x['badges'], list) or []: | |
676 | label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str) | |
677 | if label: | |
678 | badges.add(label.lower()) | |
679 | return badges | |
680 | ||
681 | @staticmethod | |
682 | def _get_text(data, *path_list, max_runs=None): | |
683 | for path in path_list or [None]: | |
684 | if path is None: | |
685 | obj = [data] | |
686 | else: | |
687 | obj = traverse_obj(data, path, default=[]) | |
688 | if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)): | |
689 | obj = [obj] | |
690 | for item in obj: | |
691 | text = try_get(item, lambda x: x['simpleText'], compat_str) | |
692 | if text: | |
693 | return text | |
694 | runs = try_get(item, lambda x: x['runs'], list) or [] | |
695 | if not runs and isinstance(item, list): | |
696 | runs = item | |
697 | ||
698 | runs = runs[:min(len(runs), max_runs or len(runs))] | |
699 | text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[])) | |
700 | if text: | |
701 | return text | |
702 | ||
703 | def _get_count(self, data, *path_list): | |
704 | count_text = self._get_text(data, *path_list) or '' | |
705 | count = parse_count(count_text) | |
706 | if count is None: | |
707 | count = str_to_int( | |
708 | self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None)) | |
709 | return count | |
710 | ||
711 | @staticmethod | |
712 | def _extract_thumbnails(data, *path_list): | |
713 | """ | |
714 | Extract thumbnails from thumbnails dict | |
715 | @param path_list: path list to level that contains 'thumbnails' key | |
716 | """ | |
717 | thumbnails = [] | |
718 | for path in path_list or [()]: | |
719 | for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]): | |
720 | thumbnail_url = url_or_none(thumbnail.get('url')) | |
721 | if not thumbnail_url: | |
722 | continue | |
723 | # Sometimes youtube gives a wrong thumbnail URL. See: | |
724 | # https://github.com/yt-dlp/yt-dlp/issues/233 | |
725 | # https://github.com/ytdl-org/youtube-dl/issues/28023 | |
726 | if 'maxresdefault' in thumbnail_url: | |
727 | thumbnail_url = thumbnail_url.split('?')[0] | |
728 | thumbnails.append({ | |
729 | 'url': thumbnail_url, | |
730 | 'height': int_or_none(thumbnail.get('height')), | |
731 | 'width': int_or_none(thumbnail.get('width')), | |
732 | }) | |
733 | return thumbnails | |
734 | ||
735 | @staticmethod | |
736 | def extract_relative_time(relative_time_text): | |
737 | """ | |
738 | Extracts a relative time from string and converts to dt object | |
739 | e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today' | |
740 | """ | |
741 | mobj = re.search(r'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>microsecond|second|minute|hour|day|week|month|year)s?\s*ago', relative_time_text) | |
742 | if mobj: | |
743 | start = mobj.group('start') | |
744 | if start: | |
745 | return datetime_from_str(start) | |
746 | try: | |
747 | return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit'))) | |
748 | except ValueError: | |
749 | return None | |
750 | ||
751 | def _extract_time_text(self, renderer, *path_list): | |
752 | """@returns (timestamp, time_text)""" | |
753 | text = self._get_text(renderer, *path_list) or '' | |
754 | dt = self.extract_relative_time(text) | |
755 | timestamp = None | |
756 | if isinstance(dt, datetime.datetime): | |
757 | timestamp = calendar.timegm(dt.timetuple()) | |
758 | ||
759 | if timestamp is None: | |
760 | timestamp = ( | |
761 | unified_timestamp(text) or unified_timestamp( | |
762 | self._search_regex( | |
763 | (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'), | |
764 | text.lower(), 'time text', default=None))) | |
765 | ||
766 | if text and timestamp is None: | |
767 | self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True) | |
768 | return timestamp, text | |
769 | ||
770 | def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None, | |
771 | ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None, | |
772 | default_client='web'): | |
773 | response = None | |
774 | last_error = None | |
775 | count = -1 | |
776 | retries = self.get_param('extractor_retries', 3) | |
777 | if check_get_keys is None: | |
778 | check_get_keys = [] | |
779 | while count < retries: | |
780 | count += 1 | |
781 | if last_error: | |
782 | self.report_warning('%s. Retrying ...' % remove_end(last_error, '.')) | |
783 | try: | |
784 | response = self._call_api( | |
785 | ep=ep, fatal=True, headers=headers, | |
786 | video_id=item_id, query=query, | |
787 | context=self._extract_context(ytcfg, default_client), | |
788 | api_key=self._extract_api_key(ytcfg, default_client), | |
789 | api_hostname=api_hostname, default_client=default_client, | |
790 | note='%s%s' % (note, ' (retry #%d)' % count if count else '')) | |
791 | except ExtractorError as e: | |
792 | if isinstance(e.cause, network_exceptions): | |
793 | if isinstance(e.cause, compat_HTTPError): | |
794 | first_bytes = e.cause.read(512) | |
795 | if not is_html(first_bytes): | |
796 | yt_error = try_get( | |
797 | self._parse_json( | |
798 | self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False), | |
799 | lambda x: x['error']['message'], compat_str) | |
800 | if yt_error: | |
801 | self._report_alerts([('ERROR', yt_error)], fatal=False) | |
802 | # Downloading page may result in intermittent 5xx HTTP error | |
803 | # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289 | |
804 | # We also want to catch all other network exceptions since errors in later pages can be troublesome | |
805 | # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210 | |
806 | if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429): | |
807 | last_error = error_to_compat_str(e.cause or e.msg) | |
808 | if count < retries: | |
809 | continue | |
810 | if fatal: | |
811 | raise | |
812 | else: | |
813 | self.report_warning(error_to_compat_str(e)) | |
814 | return | |
815 | ||
816 | else: | |
817 | try: | |
818 | self._extract_and_report_alerts(response, only_once=True) | |
819 | except ExtractorError as e: | |
820 | # YouTube servers may return errors we want to retry on in a 200 OK response | |
821 | # See: https://github.com/yt-dlp/yt-dlp/issues/839 | |
822 | if 'unknown error' in e.msg.lower(): | |
823 | last_error = e.msg | |
824 | continue | |
825 | if fatal: | |
826 | raise | |
827 | self.report_warning(error_to_compat_str(e)) | |
828 | return | |
829 | if not check_get_keys or dict_get(response, check_get_keys): | |
830 | break | |
831 | # Youtube sometimes sends incomplete data | |
832 | # See: https://github.com/ytdl-org/youtube-dl/issues/28194 | |
833 | last_error = 'Incomplete data received' | |
834 | if count >= retries: | |
835 | if fatal: | |
836 | raise ExtractorError(last_error) | |
837 | else: | |
838 | self.report_warning(last_error) | |
839 | return | |
840 | return response | |
841 | ||
842 | @staticmethod | |
843 | def is_music_url(url): | |
844 | return re.match(r'https?://music\.youtube\.com/', url) is not None | |
845 | ||
846 | def _extract_video(self, renderer): | |
847 | video_id = renderer.get('videoId') | |
848 | title = self._get_text(renderer, 'title') | |
849 | description = self._get_text(renderer, 'descriptionSnippet') | |
850 | duration = parse_duration(self._get_text( | |
851 | renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text'))) | |
852 | if duration is None: | |
853 | duration = parse_duration(self._search_regex( | |
854 | r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$', | |
855 | traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str), | |
856 | video_id, default=None, group='duration')) | |
857 | ||
858 | view_count = self._get_count(renderer, 'viewCountText') | |
859 | ||
860 | uploader = self._get_text(renderer, 'ownerText', 'shortBylineText') | |
861 | channel_id = traverse_obj( | |
862 | renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), | |
863 | expected_type=str, get_all=False) | |
864 | timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText') | |
865 | scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False)) | |
866 | overlay_style = traverse_obj( | |
867 | renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), | |
868 | get_all=False, expected_type=str) | |
869 | badges = self._extract_badges(renderer) | |
870 | thumbnails = self._extract_thumbnails(renderer, 'thumbnail') | |
871 | navigation_url = urljoin('https://www.youtube.com/', traverse_obj( | |
872 | renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'), | |
873 | expected_type=str)) or '' | |
874 | url = f'https://www.youtube.com/watch?v={video_id}' | |
875 | if overlay_style == 'SHORTS' or '/shorts/' in navigation_url: | |
876 | url = f'https://www.youtube.com/shorts/{video_id}' | |
877 | ||
878 | return { | |
879 | '_type': 'url', | |
880 | 'ie_key': YoutubeIE.ie_key(), | |
881 | 'id': video_id, | |
882 | 'url': url, | |
883 | 'title': title, | |
884 | 'description': description, | |
885 | 'duration': duration, | |
886 | 'view_count': view_count, | |
887 | 'uploader': uploader, | |
888 | 'channel_id': channel_id, | |
889 | 'thumbnails': thumbnails, | |
890 | 'upload_date': (strftime_or_none(timestamp, '%Y%m%d') | |
891 | if self._configuration_arg('approximate_date', ie_key='youtubetab') | |
892 | else None), | |
893 | 'live_status': ('is_upcoming' if scheduled_timestamp is not None | |
894 | else 'was_live' if 'streamed' in time_text.lower() | |
895 | else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges | |
896 | else None), | |
897 | 'release_timestamp': scheduled_timestamp, | |
898 | 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges) | |
899 | } | |
900 | ||
901 | ||
902 | class YoutubeIE(YoutubeBaseInfoExtractor): | |
903 | IE_DESC = 'YouTube' | |
904 | _VALID_URL = r"""(?x)^ | |
905 | ( | |
906 | (?:https?://|//) # http(s):// or protocol-independent URL | |
907 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com| | |
908 | (?:www\.)?deturl\.com/www\.youtube\.com| | |
909 | (?:www\.)?pwnyoutube\.com| | |
910 | (?:www\.)?hooktube\.com| | |
911 | (?:www\.)?yourepeat\.com| | |
912 | tube\.majestyc\.net| | |
913 | %(invidious)s| | |
914 | youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains | |
915 | (?:.*?\#/)? # handle anchor (#/) redirect urls | |
916 | (?: # the various things that can precede the ID: | |
917 | (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/ | |
918 | |(?: # or the v= param in all its forms | |
919 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) | |
920 | (?:\?|\#!?) # the params delimiter ? or # or #! | |
921 | (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY) | |
922 | v= | |
923 | ) | |
924 | )) | |
925 | |(?: | |
926 | youtu\.be| # just youtu.be/xxxx | |
927 | vid\.plus| # or vid.plus/xxxx | |
928 | zwearz\.com/watch| # or zwearz.com/watch/xxxx | |
929 | %(invidious)s | |
930 | )/ | |
931 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= | |
932 | ) | |
933 | )? # all until now is optional -> you can pass the naked ID | |
934 | (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID | |
935 | (?(1).+)? # if we found the ID, everything can follow | |
936 | (?:\#|$)""" % { | |
937 | 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), | |
938 | } | |
939 | _PLAYER_INFO_RE = ( | |
940 | r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player', | |
941 | 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$', | |
942 | r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$', | |
943 | ) | |
944 | _formats = { | |
945 | '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
946 | '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
947 | '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
948 | '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}, | |
949 | '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}, | |
950 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
951 | '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
952 | '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
953 | # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well | |
954 | '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
955 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
956 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
957 | '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
958 | '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
959 | '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
960 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
961 | '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
962 | '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
963 | ||
964 | ||
965 | # 3D videos | |
966 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
967 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
968 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
969 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
970 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}, | |
971 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
972 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
973 | ||
974 | # Apple HTTP Live Streaming | |
975 | '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, | |
976 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, | |
977 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
978 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
979 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
980 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
981 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, | |
982 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}, | |
983 | ||
984 | # DASH mp4 video | |
985 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
986 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
987 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
988 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
989 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
990 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559) | |
991 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
992 | '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
993 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
994 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
995 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
996 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
997 | ||
998 | # Dash mp4 audio | |
999 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}, | |
1000 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}, | |
1001 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}, | |
1002 | '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
1003 | '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
1004 | '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}, | |
1005 | '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}, | |
1006 | ||
1007 | # Dash webm | |
1008 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1009 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1010 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1011 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1012 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1013 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1014 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}, | |
1015 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1016 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1017 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1018 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1019 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1020 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1021 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1022 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1023 | # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug) | |
1024 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1025 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
1026 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
1027 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
1028 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1029 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
1030 | ||
1031 | # Dash webm audio | |
1032 | '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}, | |
1033 | '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}, | |
1034 | ||
1035 | # Dash webm audio with opus inside | |
1036 | '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}, | |
1037 | '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}, | |
1038 | '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}, | |
1039 | ||
1040 | # RTMP (unnamed) | |
1041 | '_rtmp': {'protocol': 'rtmp'}, | |
1042 | ||
1043 | # av01 video only formats sometimes served with "unknown" codecs | |
1044 | '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}, | |
1045 | '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}, | |
1046 | '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'}, | |
1047 | '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'}, | |
1048 | '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'}, | |
1049 | '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'}, | |
1050 | '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}, | |
1051 | '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}, | |
1052 | } | |
1053 | _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt') | |
1054 | ||
1055 | _GEO_BYPASS = False | |
1056 | ||
1057 | IE_NAME = 'youtube' | |
1058 | _TESTS = [ | |
1059 | { | |
1060 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9', | |
1061 | 'info_dict': { | |
1062 | 'id': 'BaW_jenozKc', | |
1063 | 'ext': 'mp4', | |
1064 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
1065 | 'uploader': 'Philipp Hagemeister', | |
1066 | 'uploader_id': 'phihag', | |
1067 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', | |
1068 | 'channel': 'Philipp Hagemeister', | |
1069 | 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', | |
1070 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', | |
1071 | 'upload_date': '20121002', | |
1072 | 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22', | |
1073 | 'categories': ['Science & Technology'], | |
1074 | 'tags': ['youtube-dl'], | |
1075 | 'duration': 10, | |
1076 | 'view_count': int, | |
1077 | 'like_count': int, | |
1078 | 'availability': 'public', | |
1079 | 'playable_in_embed': True, | |
1080 | 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg', | |
1081 | 'live_status': 'not_live', | |
1082 | 'age_limit': 0, | |
1083 | 'start_time': 1, | |
1084 | 'end_time': 9, | |
1085 | 'channel_follower_count': int | |
1086 | } | |
1087 | }, | |
1088 | { | |
1089 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', | |
1090 | 'note': 'Embed-only video (#1746)', | |
1091 | 'info_dict': { | |
1092 | 'id': 'yZIXLfi8CZQ', | |
1093 | 'ext': 'mp4', | |
1094 | 'upload_date': '20120608', | |
1095 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
1096 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
1097 | 'uploader': 'SET India', | |
1098 | 'uploader_id': 'setindia', | |
1099 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia', | |
1100 | 'age_limit': 18, | |
1101 | }, | |
1102 | 'skip': 'Private video', | |
1103 | }, | |
1104 | { | |
1105 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ', | |
1106 | 'note': 'Use the first video ID in the URL', | |
1107 | 'info_dict': { | |
1108 | 'id': 'BaW_jenozKc', | |
1109 | 'ext': 'mp4', | |
1110 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
1111 | 'uploader': 'Philipp Hagemeister', | |
1112 | 'uploader_id': 'phihag', | |
1113 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', | |
1114 | 'channel': 'Philipp Hagemeister', | |
1115 | 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', | |
1116 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', | |
1117 | 'upload_date': '20121002', | |
1118 | 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22', | |
1119 | 'categories': ['Science & Technology'], | |
1120 | 'tags': ['youtube-dl'], | |
1121 | 'duration': 10, | |
1122 | 'view_count': int, | |
1123 | 'like_count': int, | |
1124 | 'availability': 'public', | |
1125 | 'playable_in_embed': True, | |
1126 | 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg', | |
1127 | 'live_status': 'not_live', | |
1128 | 'age_limit': 0, | |
1129 | 'channel_follower_count': int | |
1130 | }, | |
1131 | 'params': { | |
1132 | 'skip_download': True, | |
1133 | }, | |
1134 | }, | |
1135 | { | |
1136 | 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I', | |
1137 | 'note': '256k DASH audio (format 141) via DASH manifest', | |
1138 | 'info_dict': { | |
1139 | 'id': 'a9LDPn-MO4I', | |
1140 | 'ext': 'm4a', | |
1141 | 'upload_date': '20121002', | |
1142 | 'uploader_id': '8KVIDEO', | |
1143 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO', | |
1144 | 'description': '', | |
1145 | 'uploader': '8KVIDEO', | |
1146 | 'title': 'UHDTV TEST 8K VIDEO.mp4' | |
1147 | }, | |
1148 | 'params': { | |
1149 | 'youtube_include_dash_manifest': True, | |
1150 | 'format': '141', | |
1151 | }, | |
1152 | 'skip': 'format 141 not served anymore', | |
1153 | }, | |
1154 | # DASH manifest with encrypted signature | |
1155 | { | |
1156 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', | |
1157 | 'info_dict': { | |
1158 | 'id': 'IB3lcPjvWLA', | |
1159 | 'ext': 'm4a', | |
1160 | 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson', | |
1161 | 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf', | |
1162 | 'duration': 244, | |
1163 | 'uploader': 'AfrojackVEVO', | |
1164 | 'uploader_id': 'AfrojackVEVO', | |
1165 | 'upload_date': '20131011', | |
1166 | 'abr': 129.495, | |
1167 | 'like_count': int, | |
1168 | 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg', | |
1169 | 'playable_in_embed': True, | |
1170 | 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg', | |
1171 | 'view_count': int, | |
1172 | 'track': 'The Spark', | |
1173 | 'live_status': 'not_live', | |
1174 | 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp', | |
1175 | 'channel': 'Afrojack', | |
1176 | 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO', | |
1177 | 'tags': 'count:19', | |
1178 | 'availability': 'public', | |
1179 | 'categories': ['Music'], | |
1180 | 'age_limit': 0, | |
1181 | 'alt_title': 'The Spark', | |
1182 | 'channel_follower_count': int | |
1183 | }, | |
1184 | 'params': { | |
1185 | 'youtube_include_dash_manifest': True, | |
1186 | 'format': '141/bestaudio[ext=m4a]', | |
1187 | }, | |
1188 | }, | |
1189 | # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000 | |
1190 | { | |
1191 | 'note': 'Embed allowed age-gate video', | |
1192 | 'url': 'https://youtube.com/watch?v=HtVdAasjOgU', | |
1193 | 'info_dict': { | |
1194 | 'id': 'HtVdAasjOgU', | |
1195 | 'ext': 'mp4', | |
1196 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
1197 | 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', | |
1198 | 'duration': 142, | |
1199 | 'uploader': 'The Witcher', | |
1200 | 'uploader_id': 'WitcherGame', | |
1201 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame', | |
1202 | 'upload_date': '20140605', | |
1203 | 'age_limit': 18, | |
1204 | 'categories': ['Gaming'], | |
1205 | 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp', | |
1206 | 'availability': 'needs_auth', | |
1207 | 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg', | |
1208 | 'like_count': int, | |
1209 | 'channel': 'The Witcher', | |
1210 | 'live_status': 'not_live', | |
1211 | 'tags': 'count:17', | |
1212 | 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg', | |
1213 | 'playable_in_embed': True, | |
1214 | 'view_count': int, | |
1215 | 'channel_follower_count': int | |
1216 | }, | |
1217 | }, | |
1218 | { | |
1219 | 'note': 'Age-gate video with embed allowed in public site', | |
1220 | 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U', | |
1221 | 'info_dict': { | |
1222 | 'id': 'HsUATh_Nc2U', | |
1223 | 'ext': 'mp4', | |
1224 | 'title': 'Godzilla 2 (Official Video)', | |
1225 | 'description': 'md5:bf77e03fcae5529475e500129b05668a', | |
1226 | 'upload_date': '20200408', | |
1227 | 'uploader_id': 'FlyingKitty900', | |
1228 | 'uploader': 'FlyingKitty', | |
1229 | 'age_limit': 18, | |
1230 | 'availability': 'needs_auth', | |
1231 | 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg', | |
1232 | 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900', | |
1233 | 'channel': 'FlyingKitty', | |
1234 | 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg', | |
1235 | 'view_count': int, | |
1236 | 'categories': ['Entertainment'], | |
1237 | 'live_status': 'not_live', | |
1238 | 'tags': ['Flyingkitty', 'godzilla 2'], | |
1239 | 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg', | |
1240 | 'like_count': int, | |
1241 | 'duration': 177, | |
1242 | 'playable_in_embed': True, | |
1243 | 'channel_follower_count': int | |
1244 | }, | |
1245 | }, | |
1246 | { | |
1247 | 'note': 'Age-gate video embedable only with clientScreen=EMBED', | |
1248 | 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg', | |
1249 | 'info_dict': { | |
1250 | 'id': 'Tq92D6wQ1mg', | |
1251 | 'title': '[MMD] Adios - EVERGLOW [+Motion DL]', | |
1252 | 'ext': 'mp4', | |
1253 | 'upload_date': '20191228', | |
1254 | 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ', | |
1255 | 'uploader': 'Projekt Melody', | |
1256 | 'description': 'md5:17eccca93a786d51bc67646756894066', | |
1257 | 'age_limit': 18, | |
1258 | 'like_count': int, | |
1259 | 'availability': 'needs_auth', | |
1260 | 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ', | |
1261 | 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ', | |
1262 | 'view_count': int, | |
1263 | 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp', | |
1264 | 'channel': 'Projekt Melody', | |
1265 | 'live_status': 'not_live', | |
1266 | 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'], | |
1267 | 'playable_in_embed': True, | |
1268 | 'categories': ['Entertainment'], | |
1269 | 'duration': 106, | |
1270 | 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ', | |
1271 | 'channel_follower_count': int | |
1272 | }, | |
1273 | }, | |
1274 | { | |
1275 | 'note': 'Non-Agegated non-embeddable video', | |
1276 | 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY', | |
1277 | 'info_dict': { | |
1278 | 'id': 'MeJVWBSsPAY', | |
1279 | 'ext': 'mp4', | |
1280 | 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)', | |
1281 | 'uploader': 'Herr Lurik', | |
1282 | 'uploader_id': 'st3in234', | |
1283 | 'description': 'Fan Video. Music & Lyrics by OOMPH!.', | |
1284 | 'upload_date': '20130730', | |
1285 | 'track': 'Such mich find mich', | |
1286 | 'age_limit': 0, | |
1287 | 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'], | |
1288 | 'like_count': int, | |
1289 | 'playable_in_embed': False, | |
1290 | 'creator': 'OOMPH!', | |
1291 | 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg', | |
1292 | 'view_count': int, | |
1293 | 'alt_title': 'Such mich find mich', | |
1294 | 'duration': 210, | |
1295 | 'channel': 'Herr Lurik', | |
1296 | 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA', | |
1297 | 'categories': ['Music'], | |
1298 | 'availability': 'public', | |
1299 | 'uploader_url': 'http://www.youtube.com/user/st3in234', | |
1300 | 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA', | |
1301 | 'live_status': 'not_live', | |
1302 | 'artist': 'OOMPH!', | |
1303 | 'channel_follower_count': int | |
1304 | }, | |
1305 | }, | |
1306 | { | |
1307 | 'note': 'Non-bypassable age-gated video', | |
1308 | 'url': 'https://youtube.com/watch?v=Cr381pDsSsA', | |
1309 | 'only_matching': True, | |
1310 | }, | |
1311 | # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421) | |
1312 | # YouTube Red ad is not captured for creator | |
1313 | { | |
1314 | 'url': '__2ABJjxzNo', | |
1315 | 'info_dict': { | |
1316 | 'id': '__2ABJjxzNo', | |
1317 | 'ext': 'mp4', | |
1318 | 'duration': 266, | |
1319 | 'upload_date': '20100430', | |
1320 | 'uploader_id': 'deadmau5', | |
1321 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5', | |
1322 | 'creator': 'deadmau5', | |
1323 | 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336', | |
1324 | 'uploader': 'deadmau5', | |
1325 | 'title': 'Deadmau5 - Some Chords (HD)', | |
1326 | 'alt_title': 'Some Chords', | |
1327 | 'availability': 'public', | |
1328 | 'tags': 'count:14', | |
1329 | 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ', | |
1330 | 'view_count': int, | |
1331 | 'live_status': 'not_live', | |
1332 | 'channel': 'deadmau5', | |
1333 | 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp', | |
1334 | 'like_count': int, | |
1335 | 'track': 'Some Chords', | |
1336 | 'artist': 'deadmau5', | |
1337 | 'playable_in_embed': True, | |
1338 | 'age_limit': 0, | |
1339 | 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ', | |
1340 | 'categories': ['Music'], | |
1341 | 'album': 'Some Chords', | |
1342 | 'channel_follower_count': int | |
1343 | }, | |
1344 | 'expected_warnings': [ | |
1345 | 'DASH manifest missing', | |
1346 | ] | |
1347 | }, | |
1348 | # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431) | |
1349 | { | |
1350 | 'url': 'lqQg6PlCWgI', | |
1351 | 'info_dict': { | |
1352 | 'id': 'lqQg6PlCWgI', | |
1353 | 'ext': 'mp4', | |
1354 | 'duration': 6085, | |
1355 | 'upload_date': '20150827', | |
1356 | 'uploader_id': 'olympic', | |
1357 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic', | |
1358 | 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', | |
1359 | 'uploader': 'Olympics', | |
1360 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', | |
1361 | 'like_count': int, | |
1362 | 'release_timestamp': 1343767800, | |
1363 | 'playable_in_embed': True, | |
1364 | 'categories': ['Sports'], | |
1365 | 'release_date': '20120731', | |
1366 | 'channel': 'Olympics', | |
1367 | 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'], | |
1368 | 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q', | |
1369 | 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg', | |
1370 | 'age_limit': 0, | |
1371 | 'availability': 'public', | |
1372 | 'live_status': 'was_live', | |
1373 | 'view_count': int, | |
1374 | 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q', | |
1375 | 'channel_follower_count': int | |
1376 | }, | |
1377 | 'params': { | |
1378 | 'skip_download': 'requires avconv', | |
1379 | } | |
1380 | }, | |
1381 | # Non-square pixels | |
1382 | { | |
1383 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
1384 | 'info_dict': { | |
1385 | 'id': '_b-2C3KPAM0', | |
1386 | 'ext': 'mp4', | |
1387 | 'stretched_ratio': 16 / 9., | |
1388 | 'duration': 85, | |
1389 | 'upload_date': '20110310', | |
1390 | 'uploader_id': 'AllenMeow', | |
1391 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow', | |
1392 | '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', | |
1393 | 'uploader': '孫ᄋᄅ', | |
1394 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', | |
1395 | 'playable_in_embed': True, | |
1396 | 'channel': '孫ᄋᄅ', | |
1397 | 'age_limit': 0, | |
1398 | 'tags': 'count:11', | |
1399 | 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw', | |
1400 | 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw', | |
1401 | 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg', | |
1402 | 'view_count': int, | |
1403 | 'categories': ['People & Blogs'], | |
1404 | 'like_count': int, | |
1405 | 'live_status': 'not_live', | |
1406 | 'availability': 'unlisted', | |
1407 | 'channel_follower_count': int | |
1408 | }, | |
1409 | }, | |
1410 | # url_encoded_fmt_stream_map is empty string | |
1411 | { | |
1412 | 'url': 'qEJwOuvDf7I', | |
1413 | 'info_dict': { | |
1414 | 'id': 'qEJwOuvDf7I', | |
1415 | 'ext': 'webm', | |
1416 | 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', | |
1417 | 'description': '', | |
1418 | 'upload_date': '20150404', | |
1419 | 'uploader_id': 'spbelect', | |
1420 | 'uploader': 'Наблюдатели Петербурга', | |
1421 | }, | |
1422 | 'params': { | |
1423 | 'skip_download': 'requires avconv', | |
1424 | }, | |
1425 | 'skip': 'This live event has ended.', | |
1426 | }, | |
1427 | # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097) | |
1428 | { | |
1429 | 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y', | |
1430 | 'info_dict': { | |
1431 | 'id': 'FIl7x6_3R5Y', | |
1432 | 'ext': 'webm', | |
1433 | 'title': 'md5:7b81415841e02ecd4313668cde88737a', | |
1434 | 'description': 'md5:116377fd2963b81ec4ce64b542173306', | |
1435 | 'duration': 220, | |
1436 | 'upload_date': '20150625', | |
1437 | 'uploader_id': 'dorappi2000', | |
1438 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000', | |
1439 | 'uploader': 'dorappi2000', | |
1440 | 'formats': 'mincount:31', | |
1441 | }, | |
1442 | 'skip': 'not actual anymore', | |
1443 | }, | |
1444 | # DASH manifest with segment_list | |
1445 | { | |
1446 | 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8', | |
1447 | 'md5': '8ce563a1d667b599d21064e982ab9e31', | |
1448 | 'info_dict': { | |
1449 | 'id': 'CsmdDsKjzN8', | |
1450 | 'ext': 'mp4', | |
1451 | 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510 | |
1452 | 'uploader': 'Airtek', | |
1453 | 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', | |
1454 | 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ', | |
1455 | 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', | |
1456 | }, | |
1457 | 'params': { | |
1458 | 'youtube_include_dash_manifest': True, | |
1459 | 'format': '135', # bestvideo | |
1460 | }, | |
1461 | 'skip': 'This live event has ended.', | |
1462 | }, | |
1463 | { | |
1464 | # Multifeed videos (multiple cameras), URL is for Main Camera | |
1465 | 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg', | |
1466 | 'info_dict': { | |
1467 | 'id': 'jvGDaLqkpTg', | |
1468 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever', | |
1469 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1470 | }, | |
1471 | 'playlist': [{ | |
1472 | 'info_dict': { | |
1473 | 'id': 'jvGDaLqkpTg', | |
1474 | 'ext': 'mp4', | |
1475 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)', | |
1476 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1477 | 'duration': 10643, | |
1478 | 'upload_date': '20161111', | |
1479 | 'uploader': 'Team PGP', | |
1480 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1481 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
1482 | }, | |
1483 | }, { | |
1484 | 'info_dict': { | |
1485 | 'id': '3AKt1R1aDnw', | |
1486 | 'ext': 'mp4', | |
1487 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)', | |
1488 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1489 | 'duration': 10991, | |
1490 | 'upload_date': '20161111', | |
1491 | 'uploader': 'Team PGP', | |
1492 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1493 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
1494 | }, | |
1495 | }, { | |
1496 | 'info_dict': { | |
1497 | 'id': 'RtAMM00gpVc', | |
1498 | 'ext': 'mp4', | |
1499 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)', | |
1500 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1501 | 'duration': 10995, | |
1502 | 'upload_date': '20161111', | |
1503 | 'uploader': 'Team PGP', | |
1504 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1505 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
1506 | }, | |
1507 | }, { | |
1508 | 'info_dict': { | |
1509 | 'id': '6N2fdlP3C5U', | |
1510 | 'ext': 'mp4', | |
1511 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)', | |
1512 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1513 | 'duration': 10990, | |
1514 | 'upload_date': '20161111', | |
1515 | 'uploader': 'Team PGP', | |
1516 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1517 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
1518 | }, | |
1519 | }], | |
1520 | 'params': { | |
1521 | 'skip_download': True, | |
1522 | }, | |
1523 | 'skip': 'Not multifeed anymore', | |
1524 | }, | |
1525 | { | |
1526 | # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536) | |
1527 | 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo', | |
1528 | 'info_dict': { | |
1529 | 'id': 'gVfLd0zydlo', | |
1530 | 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30', | |
1531 | }, | |
1532 | 'playlist_count': 2, | |
1533 | 'skip': 'Not multifeed anymore', | |
1534 | }, | |
1535 | { | |
1536 | 'url': 'https://vid.plus/FlRa-iH7PGw', | |
1537 | 'only_matching': True, | |
1538 | }, | |
1539 | { | |
1540 | 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html', | |
1541 | 'only_matching': True, | |
1542 | }, | |
1543 | { | |
1544 | # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468) | |
1545 | # Also tests cut-off URL expansion in video description (see | |
1546 | # https://github.com/ytdl-org/youtube-dl/issues/1892, | |
1547 | # https://github.com/ytdl-org/youtube-dl/issues/8164) | |
1548 | 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg', | |
1549 | 'info_dict': { | |
1550 | 'id': 'lsguqyKfVQg', | |
1551 | 'ext': 'mp4', | |
1552 | 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21', | |
1553 | 'alt_title': 'Dark Walk', | |
1554 | 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a', | |
1555 | 'duration': 133, | |
1556 | 'upload_date': '20151119', | |
1557 | 'uploader_id': 'IronSoulElf', | |
1558 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf', | |
1559 | 'uploader': 'IronSoulElf', | |
1560 | 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan', | |
1561 | 'track': 'Dark Walk', | |
1562 | 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan', | |
1563 | 'album': 'Position Music - Production Music Vol. 143 - Dark Walk', | |
1564 | 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp', | |
1565 | 'categories': ['Film & Animation'], | |
1566 | 'view_count': int, | |
1567 | 'live_status': 'not_live', | |
1568 | 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ', | |
1569 | 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ', | |
1570 | 'tags': 'count:13', | |
1571 | 'availability': 'public', | |
1572 | 'channel': 'IronSoulElf', | |
1573 | 'playable_in_embed': True, | |
1574 | 'like_count': int, | |
1575 | 'age_limit': 0, | |
1576 | 'channel_follower_count': int | |
1577 | }, | |
1578 | 'params': { | |
1579 | 'skip_download': True, | |
1580 | }, | |
1581 | }, | |
1582 | { | |
1583 | # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468) | |
1584 | 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8', | |
1585 | 'only_matching': True, | |
1586 | }, | |
1587 | { | |
1588 | # Video with yt:stretch=17:0 | |
1589 | 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM', | |
1590 | 'info_dict': { | |
1591 | 'id': 'Q39EVAstoRM', | |
1592 | 'ext': 'mp4', | |
1593 | 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4', | |
1594 | 'description': 'md5:ee18a25c350637c8faff806845bddee9', | |
1595 | 'upload_date': '20151107', | |
1596 | 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA', | |
1597 | 'uploader': 'CH GAMER DROID', | |
1598 | }, | |
1599 | 'params': { | |
1600 | 'skip_download': True, | |
1601 | }, | |
1602 | 'skip': 'This video does not exist.', | |
1603 | }, | |
1604 | { | |
1605 | # Video with incomplete 'yt:stretch=16:' | |
1606 | 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI', | |
1607 | 'only_matching': True, | |
1608 | }, | |
1609 | { | |
1610 | # Video licensed under Creative Commons | |
1611 | 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA', | |
1612 | 'info_dict': { | |
1613 | 'id': 'M4gD1WSo5mA', | |
1614 | 'ext': 'mp4', | |
1615 | 'title': 'md5:e41008789470fc2533a3252216f1c1d1', | |
1616 | 'description': 'md5:a677553cf0840649b731a3024aeff4cc', | |
1617 | 'duration': 721, | |
1618 | 'upload_date': '20150128', | |
1619 | 'uploader_id': 'BerkmanCenter', | |
1620 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter', | |
1621 | 'uploader': 'The Berkman Klein Center for Internet & Society', | |
1622 | 'license': 'Creative Commons Attribution license (reuse allowed)', | |
1623 | 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA', | |
1624 | 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA', | |
1625 | 'like_count': int, | |
1626 | 'age_limit': 0, | |
1627 | 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'], | |
1628 | 'channel': 'The Berkman Klein Center for Internet & Society', | |
1629 | 'availability': 'public', | |
1630 | 'view_count': int, | |
1631 | 'categories': ['Education'], | |
1632 | 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp', | |
1633 | 'live_status': 'not_live', | |
1634 | 'playable_in_embed': True, | |
1635 | 'channel_follower_count': int | |
1636 | }, | |
1637 | 'params': { | |
1638 | 'skip_download': True, | |
1639 | }, | |
1640 | }, | |
1641 | { | |
1642 | # Channel-like uploader_url | |
1643 | 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg', | |
1644 | 'info_dict': { | |
1645 | 'id': 'eQcmzGIKrzg', | |
1646 | 'ext': 'mp4', | |
1647 | 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders', | |
1648 | 'description': 'md5:13a2503d7b5904ef4b223aa101628f39', | |
1649 | 'duration': 4060, | |
1650 | 'upload_date': '20151120', | |
1651 | 'uploader': 'Bernie Sanders', | |
1652 | 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg', | |
1653 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg', | |
1654 | 'license': 'Creative Commons Attribution license (reuse allowed)', | |
1655 | 'playable_in_embed': True, | |
1656 | 'tags': 'count:12', | |
1657 | 'like_count': int, | |
1658 | 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg', | |
1659 | 'age_limit': 0, | |
1660 | 'availability': 'public', | |
1661 | 'categories': ['News & Politics'], | |
1662 | 'channel': 'Bernie Sanders', | |
1663 | 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp', | |
1664 | 'view_count': int, | |
1665 | 'live_status': 'not_live', | |
1666 | 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg', | |
1667 | 'channel_follower_count': int | |
1668 | }, | |
1669 | 'params': { | |
1670 | 'skip_download': True, | |
1671 | }, | |
1672 | }, | |
1673 | { | |
1674 | 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY', | |
1675 | 'only_matching': True, | |
1676 | }, | |
1677 | { | |
1678 | # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059) | |
1679 | 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo', | |
1680 | 'only_matching': True, | |
1681 | }, | |
1682 | { | |
1683 | # Rental video preview | |
1684 | 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg', | |
1685 | 'info_dict': { | |
1686 | 'id': 'uGpuVWrhIzE', | |
1687 | 'ext': 'mp4', | |
1688 | 'title': 'Piku - Trailer', | |
1689 | 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb', | |
1690 | 'upload_date': '20150811', | |
1691 | 'uploader': 'FlixMatrix', | |
1692 | 'uploader_id': 'FlixMatrixKaravan', | |
1693 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan', | |
1694 | 'license': 'Standard YouTube License', | |
1695 | }, | |
1696 | 'params': { | |
1697 | 'skip_download': True, | |
1698 | }, | |
1699 | 'skip': 'This video is not available.', | |
1700 | }, | |
1701 | { | |
1702 | # YouTube Red video with episode data | |
1703 | 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4', | |
1704 | 'info_dict': { | |
1705 | 'id': 'iqKdEhx-dD4', | |
1706 | 'ext': 'mp4', | |
1707 | 'title': 'Isolation - Mind Field (Ep 1)', | |
1708 | 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd', | |
1709 | 'duration': 2085, | |
1710 | 'upload_date': '20170118', | |
1711 | 'uploader': 'Vsauce', | |
1712 | 'uploader_id': 'Vsauce', | |
1713 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce', | |
1714 | 'series': 'Mind Field', | |
1715 | 'season_number': 1, | |
1716 | 'episode_number': 1, | |
1717 | 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp', | |
1718 | 'tags': 'count:12', | |
1719 | 'view_count': int, | |
1720 | 'availability': 'public', | |
1721 | 'age_limit': 0, | |
1722 | 'channel': 'Vsauce', | |
1723 | 'episode': 'Episode 1', | |
1724 | 'categories': ['Entertainment'], | |
1725 | 'season': 'Season 1', | |
1726 | 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA', | |
1727 | 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA', | |
1728 | 'like_count': int, | |
1729 | 'playable_in_embed': True, | |
1730 | 'live_status': 'not_live', | |
1731 | 'channel_follower_count': int | |
1732 | }, | |
1733 | 'params': { | |
1734 | 'skip_download': True, | |
1735 | }, | |
1736 | 'expected_warnings': [ | |
1737 | 'Skipping DASH manifest', | |
1738 | ], | |
1739 | }, | |
1740 | { | |
1741 | # The following content has been identified by the YouTube community | |
1742 | # as inappropriate or offensive to some audiences. | |
1743 | 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI', | |
1744 | 'info_dict': { | |
1745 | 'id': '6SJNVb0GnPI', | |
1746 | 'ext': 'mp4', | |
1747 | 'title': 'Race Differences in Intelligence', | |
1748 | 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1', | |
1749 | 'duration': 965, | |
1750 | 'upload_date': '20140124', | |
1751 | 'uploader': 'New Century Foundation', | |
1752 | 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg', | |
1753 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg', | |
1754 | }, | |
1755 | 'params': { | |
1756 | 'skip_download': True, | |
1757 | }, | |
1758 | 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.', | |
1759 | }, | |
1760 | { | |
1761 | # itag 212 | |
1762 | 'url': '1t24XAntNCY', | |
1763 | 'only_matching': True, | |
1764 | }, | |
1765 | { | |
1766 | # geo restricted to JP | |
1767 | 'url': 'sJL6WA-aGkQ', | |
1768 | 'only_matching': True, | |
1769 | }, | |
1770 | { | |
1771 | 'url': 'https://invidio.us/watch?v=BaW_jenozKc', | |
1772 | 'only_matching': True, | |
1773 | }, | |
1774 | { | |
1775 | 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc', | |
1776 | 'only_matching': True, | |
1777 | }, | |
1778 | { | |
1779 | # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m | |
1780 | 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA', | |
1781 | 'only_matching': True, | |
1782 | }, | |
1783 | { | |
1784 | # DRM protected | |
1785 | 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc', | |
1786 | 'only_matching': True, | |
1787 | }, | |
1788 | { | |
1789 | # Video with unsupported adaptive stream type formats | |
1790 | 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U', | |
1791 | 'info_dict': { | |
1792 | 'id': 'Z4Vy8R84T1U', | |
1793 | 'ext': 'mp4', | |
1794 | 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta', | |
1795 | 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', | |
1796 | 'duration': 433, | |
1797 | 'upload_date': '20130923', | |
1798 | 'uploader': 'Amelia Putri Harwita', | |
1799 | 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q', | |
1800 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q', | |
1801 | 'formats': 'maxcount:10', | |
1802 | }, | |
1803 | 'params': { | |
1804 | 'skip_download': True, | |
1805 | 'youtube_include_dash_manifest': False, | |
1806 | }, | |
1807 | 'skip': 'not actual anymore', | |
1808 | }, | |
1809 | { | |
1810 | # Youtube Music Auto-generated description | |
1811 | 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs', | |
1812 | 'info_dict': { | |
1813 | 'id': 'MgNrAu2pzNs', | |
1814 | 'ext': 'mp4', | |
1815 | 'title': 'Voyeur Girl', | |
1816 | 'description': 'md5:7ae382a65843d6df2685993e90a8628f', | |
1817 | 'upload_date': '20190312', | |
1818 | 'uploader': 'Stephen - Topic', | |
1819 | 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA', | |
1820 | 'artist': 'Stephen', | |
1821 | 'track': 'Voyeur Girl', | |
1822 | 'album': 'it\'s too much love to know my dear', | |
1823 | 'release_date': '20190313', | |
1824 | 'release_year': 2019, | |
1825 | 'alt_title': 'Voyeur Girl', | |
1826 | 'view_count': int, | |
1827 | 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA', | |
1828 | 'playable_in_embed': True, | |
1829 | 'like_count': int, | |
1830 | 'categories': ['Music'], | |
1831 | 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA', | |
1832 | 'channel': 'Stephen', | |
1833 | 'availability': 'public', | |
1834 | 'creator': 'Stephen', | |
1835 | 'duration': 169, | |
1836 | 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp', | |
1837 | 'age_limit': 0, | |
1838 | 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA', | |
1839 | 'tags': 'count:11', | |
1840 | 'live_status': 'not_live', | |
1841 | 'channel_follower_count': int | |
1842 | }, | |
1843 | 'params': { | |
1844 | 'skip_download': True, | |
1845 | }, | |
1846 | }, | |
1847 | { | |
1848 | 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q', | |
1849 | 'only_matching': True, | |
1850 | }, | |
1851 | { | |
1852 | # invalid -> valid video id redirection | |
1853 | 'url': 'DJztXj2GPfl', | |
1854 | 'info_dict': { | |
1855 | 'id': 'DJztXj2GPfk', | |
1856 | 'ext': 'mp4', | |
1857 | 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)', | |
1858 | 'description': 'md5:bf577a41da97918e94fa9798d9228825', | |
1859 | 'upload_date': '20090125', | |
1860 | 'uploader': 'Prochorowka', | |
1861 | 'uploader_id': 'Prochorowka', | |
1862 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka', | |
1863 | 'artist': 'Panjabi MC', | |
1864 | 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix', | |
1865 | 'album': 'Beware of the Boys (Mundian To Bach Ke)', | |
1866 | }, | |
1867 | 'params': { | |
1868 | 'skip_download': True, | |
1869 | }, | |
1870 | 'skip': 'Video unavailable', | |
1871 | }, | |
1872 | { | |
1873 | # empty description results in an empty string | |
1874 | 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k', | |
1875 | 'info_dict': { | |
1876 | 'id': 'x41yOUIvK2k', | |
1877 | 'ext': 'mp4', | |
1878 | 'title': 'IMG 3456', | |
1879 | 'description': '', | |
1880 | 'upload_date': '20170613', | |
1881 | 'uploader_id': 'ElevageOrVert', | |
1882 | 'uploader': 'ElevageOrVert', | |
1883 | 'view_count': int, | |
1884 | 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp', | |
1885 | 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert', | |
1886 | 'like_count': int, | |
1887 | 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw', | |
1888 | 'tags': [], | |
1889 | 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw', | |
1890 | 'availability': 'public', | |
1891 | 'age_limit': 0, | |
1892 | 'categories': ['Pets & Animals'], | |
1893 | 'duration': 7, | |
1894 | 'playable_in_embed': True, | |
1895 | 'live_status': 'not_live', | |
1896 | 'channel': 'ElevageOrVert', | |
1897 | 'channel_follower_count': int | |
1898 | }, | |
1899 | 'params': { | |
1900 | 'skip_download': True, | |
1901 | }, | |
1902 | }, | |
1903 | { | |
1904 | # with '};' inside yt initial data (see [1]) | |
1905 | # see [2] for an example with '};' inside ytInitialPlayerResponse | |
1906 | # 1. https://github.com/ytdl-org/youtube-dl/issues/27093 | |
1907 | # 2. https://github.com/ytdl-org/youtube-dl/issues/27216 | |
1908 | 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no', | |
1909 | 'info_dict': { | |
1910 | 'id': 'CHqg6qOn4no', | |
1911 | 'ext': 'mp4', | |
1912 | 'title': 'Part 77 Sort a list of simple types in c#', | |
1913 | 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc', | |
1914 | 'upload_date': '20130831', | |
1915 | 'uploader_id': 'kudvenkat', | |
1916 | 'uploader': 'kudvenkat', | |
1917 | 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q', | |
1918 | 'like_count': int, | |
1919 | 'uploader_url': 'http://www.youtube.com/user/kudvenkat', | |
1920 | 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q', | |
1921 | 'live_status': 'not_live', | |
1922 | 'categories': ['Education'], | |
1923 | 'availability': 'public', | |
1924 | 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg', | |
1925 | 'tags': 'count:12', | |
1926 | 'playable_in_embed': True, | |
1927 | 'age_limit': 0, | |
1928 | 'view_count': int, | |
1929 | 'duration': 522, | |
1930 | 'channel': 'kudvenkat', | |
1931 | 'channel_follower_count': int | |
1932 | }, | |
1933 | 'params': { | |
1934 | 'skip_download': True, | |
1935 | }, | |
1936 | }, | |
1937 | { | |
1938 | # another example of '};' in ytInitialData | |
1939 | 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY', | |
1940 | 'only_matching': True, | |
1941 | }, | |
1942 | { | |
1943 | 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ', | |
1944 | 'only_matching': True, | |
1945 | }, | |
1946 | { | |
1947 | # https://github.com/ytdl-org/youtube-dl/pull/28094 | |
1948 | 'url': 'OtqTfy26tG0', | |
1949 | 'info_dict': { | |
1950 | 'id': 'OtqTfy26tG0', | |
1951 | 'ext': 'mp4', | |
1952 | 'title': 'Burn Out', | |
1953 | 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131', | |
1954 | 'upload_date': '20141120', | |
1955 | 'uploader': 'The Cinematic Orchestra - Topic', | |
1956 | 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw', | |
1957 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw', | |
1958 | 'artist': 'The Cinematic Orchestra', | |
1959 | 'track': 'Burn Out', | |
1960 | 'album': 'Every Day', | |
1961 | 'like_count': int, | |
1962 | 'live_status': 'not_live', | |
1963 | 'alt_title': 'Burn Out', | |
1964 | 'duration': 614, | |
1965 | 'age_limit': 0, | |
1966 | 'view_count': int, | |
1967 | 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw', | |
1968 | 'creator': 'The Cinematic Orchestra', | |
1969 | 'channel': 'The Cinematic Orchestra', | |
1970 | 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'], | |
1971 | 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw', | |
1972 | 'availability': 'public', | |
1973 | 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg', | |
1974 | 'categories': ['Music'], | |
1975 | 'playable_in_embed': True, | |
1976 | 'channel_follower_count': int | |
1977 | }, | |
1978 | 'params': { | |
1979 | 'skip_download': True, | |
1980 | }, | |
1981 | }, | |
1982 | { | |
1983 | # controversial video, only works with bpctr when authenticated with cookies | |
1984 | 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg', | |
1985 | 'only_matching': True, | |
1986 | }, | |
1987 | { | |
1988 | # controversial video, requires bpctr/contentCheckOk | |
1989 | 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc', | |
1990 | 'info_dict': { | |
1991 | 'id': 'SZJvDhaSDnc', | |
1992 | 'ext': 'mp4', | |
1993 | 'title': 'San Diego teen commits suicide after bullying over embarrassing video', | |
1994 | 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ', | |
1995 | 'uploader': 'CBS Mornings', | |
1996 | 'uploader_id': 'CBSThisMorning', | |
1997 | 'upload_date': '20140716', | |
1998 | 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7', | |
1999 | 'duration': 170, | |
2000 | 'categories': ['News & Politics'], | |
2001 | 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning', | |
2002 | 'view_count': int, | |
2003 | 'channel': 'CBS Mornings', | |
2004 | 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'], | |
2005 | 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg', | |
2006 | 'age_limit': 18, | |
2007 | 'availability': 'needs_auth', | |
2008 | 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ', | |
2009 | 'like_count': int, | |
2010 | 'live_status': 'not_live', | |
2011 | 'playable_in_embed': True, | |
2012 | 'channel_follower_count': int | |
2013 | } | |
2014 | }, | |
2015 | { | |
2016 | # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685 | |
2017 | 'url': 'cBvYw8_A0vQ', | |
2018 | 'info_dict': { | |
2019 | 'id': 'cBvYw8_A0vQ', | |
2020 | 'ext': 'mp4', | |
2021 | 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き', | |
2022 | 'description': 'md5:ea770e474b7cd6722b4c95b833c03630', | |
2023 | 'upload_date': '20201120', | |
2024 | 'uploader': 'Walk around Japan', | |
2025 | 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw', | |
2026 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw', | |
2027 | 'duration': 1456, | |
2028 | 'categories': ['Travel & Events'], | |
2029 | 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw', | |
2030 | 'view_count': int, | |
2031 | 'channel': 'Walk around Japan', | |
2032 | 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'], | |
2033 | 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp', | |
2034 | 'age_limit': 0, | |
2035 | 'availability': 'public', | |
2036 | 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw', | |
2037 | 'live_status': 'not_live', | |
2038 | 'playable_in_embed': True, | |
2039 | 'channel_follower_count': int | |
2040 | }, | |
2041 | 'params': { | |
2042 | 'skip_download': True, | |
2043 | }, | |
2044 | }, { | |
2045 | # Has multiple audio streams | |
2046 | 'url': 'WaOKSUlf4TM', | |
2047 | 'only_matching': True | |
2048 | }, { | |
2049 | # Requires Premium: has format 141 when requested using YTM url | |
2050 | 'url': 'https://music.youtube.com/watch?v=XclachpHxis', | |
2051 | 'only_matching': True | |
2052 | }, { | |
2053 | # multiple subtitles with same lang_code | |
2054 | 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug', | |
2055 | 'only_matching': True, | |
2056 | }, { | |
2057 | # Force use android client fallback | |
2058 | 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY', | |
2059 | 'info_dict': { | |
2060 | 'id': 'YOelRv7fMxY', | |
2061 | 'title': 'DIGGING A SECRET TUNNEL Part 1', | |
2062 | 'ext': '3gp', | |
2063 | 'upload_date': '20210624', | |
2064 | 'channel_id': 'UCp68_FLety0O-n9QU6phsgw', | |
2065 | 'uploader': 'colinfurze', | |
2066 | 'uploader_id': 'colinfurze', | |
2067 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw', | |
2068 | 'description': 'md5:5d5991195d599b56cd0c4148907eec50', | |
2069 | 'duration': 596, | |
2070 | 'categories': ['Entertainment'], | |
2071 | 'uploader_url': 'http://www.youtube.com/user/colinfurze', | |
2072 | 'view_count': int, | |
2073 | 'channel': 'colinfurze', | |
2074 | 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'], | |
2075 | 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg', | |
2076 | 'age_limit': 0, | |
2077 | 'availability': 'public', | |
2078 | 'like_count': int, | |
2079 | 'live_status': 'not_live', | |
2080 | 'playable_in_embed': True, | |
2081 | 'channel_follower_count': int | |
2082 | }, | |
2083 | 'params': { | |
2084 | 'format': '17', # 3gp format available on android | |
2085 | 'extractor_args': {'youtube': {'player_client': ['android']}}, | |
2086 | }, | |
2087 | }, | |
2088 | { | |
2089 | # Skip download of additional client configs (remix client config in this case) | |
2090 | 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs', | |
2091 | 'only_matching': True, | |
2092 | 'params': { | |
2093 | 'extractor_args': {'youtube': {'player_skip': ['configs']}}, | |
2094 | }, | |
2095 | }, { | |
2096 | # shorts | |
2097 | 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY', | |
2098 | 'only_matching': True, | |
2099 | }, { | |
2100 | 'note': 'Storyboards', | |
2101 | 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8', | |
2102 | 'info_dict': { | |
2103 | 'id': '5KLPxDtMqe8', | |
2104 | 'ext': 'mhtml', | |
2105 | 'format_id': 'sb0', | |
2106 | 'title': 'Your Brain is Plastic', | |
2107 | 'uploader_id': 'scishow', | |
2108 | 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc', | |
2109 | 'upload_date': '20140324', | |
2110 | 'uploader': 'SciShow', | |
2111 | 'like_count': int, | |
2112 | 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow', | |
2113 | 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow', | |
2114 | 'view_count': int, | |
2115 | 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg', | |
2116 | 'playable_in_embed': True, | |
2117 | 'tags': 'count:12', | |
2118 | 'uploader_url': 'http://www.youtube.com/user/scishow', | |
2119 | 'availability': 'public', | |
2120 | 'channel': 'SciShow', | |
2121 | 'live_status': 'not_live', | |
2122 | 'duration': 248, | |
2123 | 'categories': ['Education'], | |
2124 | 'age_limit': 0, | |
2125 | 'channel_follower_count': int | |
2126 | }, 'params': {'format': 'mhtml', 'skip_download': True} | |
2127 | }, { | |
2128 | # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939) | |
2129 | 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4', | |
2130 | 'info_dict': { | |
2131 | 'id': '2NUZ8W2llS4', | |
2132 | 'ext': 'mp4', | |
2133 | 'title': 'The NP that test your phone performance 🙂', | |
2134 | 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d', | |
2135 | 'uploader': 'Leon Nguyen', | |
2136 | 'uploader_id': 'VNSXIII', | |
2137 | 'uploader_url': 'http://www.youtube.com/user/VNSXIII', | |
2138 | 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA', | |
2139 | 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA', | |
2140 | 'duration': 21, | |
2141 | 'view_count': int, | |
2142 | 'age_limit': 0, | |
2143 | 'categories': ['Gaming'], | |
2144 | 'tags': 'count:23', | |
2145 | 'playable_in_embed': True, | |
2146 | 'live_status': 'not_live', | |
2147 | 'upload_date': '20220103', | |
2148 | 'like_count': int, | |
2149 | 'availability': 'public', | |
2150 | 'channel': 'Leon Nguyen', | |
2151 | 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp', | |
2152 | 'channel_follower_count': int | |
2153 | } | |
2154 | }, { | |
2155 | # date text is premiered video, ensure upload date in UTC (published 1641172509) | |
2156 | 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM', | |
2157 | 'info_dict': { | |
2158 | 'id': 'mzZzzBU6lrM', | |
2159 | 'ext': 'mp4', | |
2160 | 'title': 'I Met GeorgeNotFound In Real Life...', | |
2161 | 'description': 'md5:cca98a355c7184e750f711f3a1b22c84', | |
2162 | 'uploader': 'Quackity', | |
2163 | 'uploader_id': 'QuackityHQ', | |
2164 | 'uploader_url': 'http://www.youtube.com/user/QuackityHQ', | |
2165 | 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q', | |
2166 | 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q', | |
2167 | 'duration': 955, | |
2168 | 'view_count': int, | |
2169 | 'age_limit': 0, | |
2170 | 'categories': ['Entertainment'], | |
2171 | 'tags': 'count:26', | |
2172 | 'playable_in_embed': True, | |
2173 | 'live_status': 'not_live', | |
2174 | 'release_timestamp': 1641172509, | |
2175 | 'release_date': '20220103', | |
2176 | 'upload_date': '20220103', | |
2177 | 'like_count': int, | |
2178 | 'availability': 'public', | |
2179 | 'channel': 'Quackity', | |
2180 | 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg', | |
2181 | 'channel_follower_count': int | |
2182 | } | |
2183 | }, | |
2184 | { # continuous livestream. Microformat upload date should be preferred. | |
2185 | # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27 | |
2186 | 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU', | |
2187 | 'info_dict': { | |
2188 | 'id': 'kgx4WGK0oNU', | |
2189 | '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}', | |
2190 | 'ext': 'mp4', | |
2191 | 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA', | |
2192 | 'availability': 'public', | |
2193 | 'age_limit': 0, | |
2194 | 'release_timestamp': 1637975704, | |
2195 | 'upload_date': '20210619', | |
2196 | 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA', | |
2197 | 'live_status': 'is_live', | |
2198 | 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg', | |
2199 | 'uploader': '阿鲍Abao', | |
2200 | 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA', | |
2201 | 'channel': 'Abao in Tokyo', | |
2202 | 'channel_follower_count': int, | |
2203 | 'release_date': '20211127', | |
2204 | 'tags': 'count:39', | |
2205 | 'categories': ['People & Blogs'], | |
2206 | 'like_count': int, | |
2207 | 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA', | |
2208 | 'view_count': int, | |
2209 | 'playable_in_embed': True, | |
2210 | 'description': 'md5:2ef1d002cad520f65825346e2084e49d', | |
2211 | }, | |
2212 | 'params': {'skip_download': True} | |
2213 | }, { | |
2214 | # Story. Requires specific player params to work. | |
2215 | # Note: stories get removed after some period of time | |
2216 | 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI', | |
2217 | 'info_dict': { | |
2218 | 'id': 'vv8qTUWmulI', | |
2219 | 'ext': 'mp4', | |
2220 | 'availability': 'unlisted', | |
2221 | 'view_count': int, | |
2222 | 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA', | |
2223 | 'upload_date': '20220526', | |
2224 | 'categories': ['Education'], | |
2225 | 'title': 'Story', | |
2226 | 'channel': 'IT\'S HISTORY', | |
2227 | 'description': '', | |
2228 | 'uploader_id': 'BlastfromthePast', | |
2229 | 'duration': 12, | |
2230 | 'uploader': 'IT\'S HISTORY', | |
2231 | 'playable_in_embed': True, | |
2232 | 'age_limit': 0, | |
2233 | 'live_status': 'not_live', | |
2234 | 'tags': [], | |
2235 | 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp', | |
2236 | 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast', | |
2237 | 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA', | |
2238 | } | |
2239 | }, { | |
2240 | 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA', | |
2241 | 'info_dict': { | |
2242 | 'id': 'tjjjtzRLHvA', | |
2243 | 'ext': 'mp4', | |
2244 | 'title': 'ハッシュタグ無し };if window.ytcsi', | |
2245 | 'upload_date': '20220323', | |
2246 | 'like_count': int, | |
2247 | 'availability': 'unlisted', | |
2248 | 'channel': 'nao20010128nao', | |
2249 | 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp', | |
2250 | 'age_limit': 0, | |
2251 | 'uploader': 'nao20010128nao', | |
2252 | 'uploader_id': 'nao20010128nao', | |
2253 | 'categories': ['Music'], | |
2254 | 'view_count': int, | |
2255 | 'description': '', | |
2256 | 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A', | |
2257 | 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A', | |
2258 | 'live_status': 'not_live', | |
2259 | 'playable_in_embed': True, | |
2260 | 'channel_follower_count': int, | |
2261 | 'duration': 6, | |
2262 | 'tags': [], | |
2263 | 'uploader_url': 'http://www.youtube.com/user/nao20010128nao', | |
2264 | } | |
2265 | } | |
2266 | ] | |
2267 | ||
2268 | @classmethod | |
2269 | def suitable(cls, url): | |
2270 | from ..utils import parse_qs | |
2271 | ||
2272 | qs = parse_qs(url) | |
2273 | if qs.get('list', [None])[0]: | |
2274 | return False | |
2275 | return super().suitable(url) | |
2276 | ||
2277 | def __init__(self, *args, **kwargs): | |
2278 | super().__init__(*args, **kwargs) | |
2279 | self._code_cache = {} | |
2280 | self._player_cache = {} | |
2281 | ||
2282 | def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data): | |
2283 | lock = threading.Lock() | |
2284 | ||
2285 | is_live = True | |
2286 | start_time = time.time() | |
2287 | formats = [f for f in formats if f.get('is_from_start')] | |
2288 | ||
2289 | def refetch_manifest(format_id, delay): | |
2290 | nonlocal formats, start_time, is_live | |
2291 | if time.time() <= start_time + delay: | |
2292 | return | |
2293 | ||
2294 | _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url) | |
2295 | video_details = traverse_obj( | |
2296 | prs, (..., 'videoDetails'), expected_type=dict, default=[]) | |
2297 | microformats = traverse_obj( | |
2298 | prs, (..., 'microformat', 'playerMicroformatRenderer'), | |
2299 | expected_type=dict, default=[]) | |
2300 | _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url) | |
2301 | start_time = time.time() | |
2302 | ||
2303 | def mpd_feed(format_id, delay): | |
2304 | """ | |
2305 | @returns (manifest_url, manifest_stream_number, is_live) or None | |
2306 | """ | |
2307 | with lock: | |
2308 | refetch_manifest(format_id, delay) | |
2309 | ||
2310 | f = next((f for f in formats if f['format_id'] == format_id), None) | |
2311 | if not f: | |
2312 | if not is_live: | |
2313 | self.to_screen(f'{video_id}: Video is no longer live') | |
2314 | else: | |
2315 | self.report_warning( | |
2316 | f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}') | |
2317 | return None | |
2318 | return f['manifest_url'], f['manifest_stream_number'], is_live | |
2319 | ||
2320 | for f in formats: | |
2321 | f['is_live'] = True | |
2322 | f['protocol'] = 'http_dash_segments_generator' | |
2323 | f['fragments'] = functools.partial( | |
2324 | self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed) | |
2325 | ||
2326 | def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx): | |
2327 | FETCH_SPAN, MAX_DURATION = 5, 432000 | |
2328 | ||
2329 | mpd_url, stream_number, is_live = None, None, True | |
2330 | ||
2331 | begin_index = 0 | |
2332 | download_start_time = ctx.get('start') or time.time() | |
2333 | ||
2334 | lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION | |
2335 | if lack_early_segments: | |
2336 | self.report_warning(bug_reports_message( | |
2337 | 'Starting download from the last 120 hours of the live stream since ' | |
2338 | 'YouTube does not have data before that. If you think this is wrong,'), only_once=True) | |
2339 | lack_early_segments = True | |
2340 | ||
2341 | known_idx, no_fragment_score, last_segment_url = begin_index, 0, None | |
2342 | fragments, fragment_base_url = None, None | |
2343 | ||
2344 | def _extract_sequence_from_mpd(refresh_sequence, immediate): | |
2345 | nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url | |
2346 | # Obtain from MPD's maximum seq value | |
2347 | old_mpd_url = mpd_url | |
2348 | last_error = ctx.pop('last_error', None) | |
2349 | expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403 | |
2350 | mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000) | |
2351 | or (mpd_url, stream_number, False)) | |
2352 | if not refresh_sequence: | |
2353 | if expire_fast and not is_live: | |
2354 | return False, last_seq | |
2355 | elif old_mpd_url == mpd_url: | |
2356 | return True, last_seq | |
2357 | try: | |
2358 | fmts, _ = self._extract_mpd_formats_and_subtitles( | |
2359 | mpd_url, None, note=False, errnote=False, fatal=False) | |
2360 | except ExtractorError: | |
2361 | fmts = None | |
2362 | if not fmts: | |
2363 | no_fragment_score += 2 | |
2364 | return False, last_seq | |
2365 | fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number) | |
2366 | fragments = fmt_info['fragments'] | |
2367 | fragment_base_url = fmt_info['fragment_base_url'] | |
2368 | assert fragment_base_url | |
2369 | ||
2370 | _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1)) | |
2371 | return True, _last_seq | |
2372 | ||
2373 | while is_live: | |
2374 | fetch_time = time.time() | |
2375 | if no_fragment_score > 30: | |
2376 | return | |
2377 | if last_segment_url: | |
2378 | # Obtain from "X-Head-Seqnum" header value from each segment | |
2379 | try: | |
2380 | urlh = self._request_webpage( | |
2381 | last_segment_url, None, note=False, errnote=False, fatal=False) | |
2382 | except ExtractorError: | |
2383 | urlh = None | |
2384 | last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum'])) | |
2385 | if last_seq is None: | |
2386 | no_fragment_score += 2 | |
2387 | last_segment_url = None | |
2388 | continue | |
2389 | else: | |
2390 | should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15) | |
2391 | no_fragment_score += 2 | |
2392 | if not should_continue: | |
2393 | continue | |
2394 | ||
2395 | if known_idx > last_seq: | |
2396 | last_segment_url = None | |
2397 | continue | |
2398 | ||
2399 | last_seq += 1 | |
2400 | ||
2401 | if begin_index < 0 and known_idx < 0: | |
2402 | # skip from the start when it's negative value | |
2403 | known_idx = last_seq + begin_index | |
2404 | if lack_early_segments: | |
2405 | known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration'])) | |
2406 | try: | |
2407 | for idx in range(known_idx, last_seq): | |
2408 | # do not update sequence here or you'll get skipped some part of it | |
2409 | should_continue, _ = _extract_sequence_from_mpd(False, False) | |
2410 | if not should_continue: | |
2411 | known_idx = idx - 1 | |
2412 | raise ExtractorError('breaking out of outer loop') | |
2413 | last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx) | |
2414 | yield { | |
2415 | 'url': last_segment_url, | |
2416 | 'fragment_count': last_seq, | |
2417 | } | |
2418 | if known_idx == last_seq: | |
2419 | no_fragment_score += 5 | |
2420 | else: | |
2421 | no_fragment_score = 0 | |
2422 | known_idx = last_seq | |
2423 | except ExtractorError: | |
2424 | continue | |
2425 | ||
2426 | time.sleep(max(0, FETCH_SPAN + fetch_time - time.time())) | |
2427 | ||
2428 | def _extract_player_url(self, *ytcfgs, webpage=None): | |
2429 | player_url = traverse_obj( | |
2430 | ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'), | |
2431 | get_all=False, expected_type=compat_str) | |
2432 | if not player_url: | |
2433 | return | |
2434 | return urljoin('https://www.youtube.com', player_url) | |
2435 | ||
2436 | def _download_player_url(self, video_id, fatal=False): | |
2437 | res = self._download_webpage( | |
2438 | 'https://www.youtube.com/iframe_api', | |
2439 | note='Downloading iframe API JS', video_id=video_id, fatal=fatal) | |
2440 | if res: | |
2441 | player_version = self._search_regex( | |
2442 | r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal) | |
2443 | if player_version: | |
2444 | return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js' | |
2445 | ||
2446 | def _signature_cache_id(self, example_sig): | |
2447 | """ Return a string representation of a signature """ | |
2448 | return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) | |
2449 | ||
2450 | @classmethod | |
2451 | def _extract_player_info(cls, player_url): | |
2452 | for player_re in cls._PLAYER_INFO_RE: | |
2453 | id_m = re.search(player_re, player_url) | |
2454 | if id_m: | |
2455 | break | |
2456 | else: | |
2457 | raise ExtractorError('Cannot identify player %r' % player_url) | |
2458 | return id_m.group('id') | |
2459 | ||
2460 | def _load_player(self, video_id, player_url, fatal=True): | |
2461 | player_id = self._extract_player_info(player_url) | |
2462 | if player_id not in self._code_cache: | |
2463 | code = self._download_webpage( | |
2464 | player_url, video_id, fatal=fatal, | |
2465 | note='Downloading player ' + player_id, | |
2466 | errnote='Download of %s failed' % player_url) | |
2467 | if code: | |
2468 | self._code_cache[player_id] = code | |
2469 | return self._code_cache.get(player_id) | |
2470 | ||
2471 | def _extract_signature_function(self, video_id, player_url, example_sig): | |
2472 | player_id = self._extract_player_info(player_url) | |
2473 | ||
2474 | # Read from filesystem cache | |
2475 | func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}' | |
2476 | assert os.path.basename(func_id) == func_id | |
2477 | ||
2478 | cache_spec = self.cache.load('youtube-sigfuncs', func_id) | |
2479 | if cache_spec is not None: | |
2480 | return lambda s: ''.join(s[i] for i in cache_spec) | |
2481 | ||
2482 | code = self._load_player(video_id, player_url) | |
2483 | if code: | |
2484 | res = self._parse_sig_js(code) | |
2485 | ||
2486 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) | |
2487 | cache_res = res(test_string) | |
2488 | cache_spec = [ord(c) for c in cache_res] | |
2489 | ||
2490 | self.cache.store('youtube-sigfuncs', func_id, cache_spec) | |
2491 | return res | |
2492 | ||
2493 | def _print_sig_code(self, func, example_sig): | |
2494 | if not self.get_param('youtube_print_sig_code'): | |
2495 | return | |
2496 | ||
2497 | def gen_sig_code(idxs): | |
2498 | def _genslice(start, end, step): | |
2499 | starts = '' if start == 0 else str(start) | |
2500 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' | |
2501 | steps = '' if step == 1 else (':%d' % step) | |
2502 | return f's[{starts}{ends}{steps}]' | |
2503 | ||
2504 | step = None | |
2505 | # Quelch pyflakes warnings - start will be set when step is set | |
2506 | start = '(Never used)' | |
2507 | for i, prev in zip(idxs[1:], idxs[:-1]): | |
2508 | if step is not None: | |
2509 | if i - prev == step: | |
2510 | continue | |
2511 | yield _genslice(start, prev, step) | |
2512 | step = None | |
2513 | continue | |
2514 | if i - prev in [-1, 1]: | |
2515 | step = i - prev | |
2516 | start = prev | |
2517 | continue | |
2518 | else: | |
2519 | yield 's[%d]' % prev | |
2520 | if step is None: | |
2521 | yield 's[%d]' % i | |
2522 | else: | |
2523 | yield _genslice(start, i, step) | |
2524 | ||
2525 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) | |
2526 | cache_res = func(test_string) | |
2527 | cache_spec = [ord(c) for c in cache_res] | |
2528 | expr_code = ' + '.join(gen_sig_code(cache_spec)) | |
2529 | signature_id_tuple = '(%s)' % ( | |
2530 | ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) | |
2531 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' | |
2532 | ' return %s\n') % (signature_id_tuple, expr_code) | |
2533 | self.to_screen('Extracted signature function:\n' + code) | |
2534 | ||
2535 | def _parse_sig_js(self, jscode): | |
2536 | funcname = self._search_regex( | |
2537 | (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2538 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2539 | r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)', | |
2540 | r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)', | |
2541 | 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}\(a,\d+\)', | |
2542 | 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\(\s*""\s*\)', | |
2543 | r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', | |
2544 | # Obsolete patterns | |
2545 | r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2546 | r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(', | |
2547 | r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2548 | r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2549 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2550 | r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2551 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2552 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('), | |
2553 | jscode, 'Initial JS player signature function name', group='sig') | |
2554 | ||
2555 | jsi = JSInterpreter(jscode) | |
2556 | initial_function = jsi.extract_function(funcname) | |
2557 | return lambda s: initial_function([s]) | |
2558 | ||
2559 | def _decrypt_signature(self, s, video_id, player_url): | |
2560 | """Turn the encrypted s field into a working signature""" | |
2561 | try: | |
2562 | player_id = (player_url, self._signature_cache_id(s)) | |
2563 | if player_id not in self._player_cache: | |
2564 | func = self._extract_signature_function(video_id, player_url, s) | |
2565 | self._player_cache[player_id] = func | |
2566 | func = self._player_cache[player_id] | |
2567 | self._print_sig_code(func, s) | |
2568 | return func(s) | |
2569 | except Exception as e: | |
2570 | raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id) | |
2571 | ||
2572 | def _decrypt_nsig(self, s, video_id, player_url): | |
2573 | """Turn the encrypted n field into a working signature""" | |
2574 | if player_url is None: | |
2575 | raise ExtractorError('Cannot decrypt nsig without player_url') | |
2576 | player_url = urljoin('https://www.youtube.com', player_url) | |
2577 | ||
2578 | sig_id = ('nsig_value', s) | |
2579 | if sig_id in self._player_cache: | |
2580 | return self._player_cache[sig_id] | |
2581 | ||
2582 | try: | |
2583 | player_id = ('nsig', player_url) | |
2584 | if player_id not in self._player_cache: | |
2585 | self._player_cache[player_id] = self._extract_n_function(video_id, player_url) | |
2586 | func = self._player_cache[player_id] | |
2587 | self._player_cache[sig_id] = func(s) | |
2588 | self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}') | |
2589 | return self._player_cache[sig_id] | |
2590 | except Exception as e: | |
2591 | raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id) | |
2592 | ||
2593 | def _extract_n_function_name(self, jscode): | |
2594 | nfunc, idx = self._search_regex( | |
2595 | r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)', | |
2596 | jscode, 'Initial JS player n function name', group=('nfunc', 'idx')) | |
2597 | if not idx: | |
2598 | return nfunc | |
2599 | return json.loads(js_to_json(self._search_regex( | |
2600 | rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode, | |
2601 | f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)] | |
2602 | ||
2603 | def _extract_n_function(self, video_id, player_url): | |
2604 | player_id = self._extract_player_info(player_url) | |
2605 | func_code = self.cache.load('youtube-nsig', player_id) | |
2606 | ||
2607 | if func_code: | |
2608 | jsi = JSInterpreter(func_code) | |
2609 | else: | |
2610 | jscode = self._load_player(video_id, player_url) | |
2611 | funcname = self._extract_n_function_name(jscode) | |
2612 | jsi = JSInterpreter(jscode) | |
2613 | func_code = jsi.extract_function_code(funcname) | |
2614 | self.cache.store('youtube-nsig', player_id, func_code) | |
2615 | ||
2616 | if self.get_param('youtube_print_sig_code'): | |
2617 | self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n') | |
2618 | ||
2619 | return lambda s: jsi.extract_function_from_code(*func_code)([s]) | |
2620 | ||
2621 | def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False): | |
2622 | """ | |
2623 | Extract signatureTimestamp (sts) | |
2624 | Required to tell API what sig/player version is in use. | |
2625 | """ | |
2626 | sts = None | |
2627 | if isinstance(ytcfg, dict): | |
2628 | sts = int_or_none(ytcfg.get('STS')) | |
2629 | ||
2630 | if not sts: | |
2631 | # Attempt to extract from player | |
2632 | if player_url is None: | |
2633 | error_msg = 'Cannot extract signature timestamp without player_url.' | |
2634 | if fatal: | |
2635 | raise ExtractorError(error_msg) | |
2636 | self.report_warning(error_msg) | |
2637 | return | |
2638 | code = self._load_player(video_id, player_url, fatal=fatal) | |
2639 | if code: | |
2640 | sts = int_or_none(self._search_regex( | |
2641 | r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code, | |
2642 | 'JS player signature timestamp', group='sts', fatal=fatal)) | |
2643 | return sts | |
2644 | ||
2645 | def _mark_watched(self, video_id, player_responses): | |
2646 | playback_url = get_first( | |
2647 | player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'), | |
2648 | expected_type=url_or_none) | |
2649 | if not playback_url: | |
2650 | self.report_warning('Unable to mark watched') | |
2651 | return | |
2652 | parsed_playback_url = compat_urlparse.urlparse(playback_url) | |
2653 | qs = compat_urlparse.parse_qs(parsed_playback_url.query) | |
2654 | ||
2655 | # cpn generation algorithm is reverse engineered from base.js. | |
2656 | # In fact it works even with dummy cpn. | |
2657 | CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_' | |
2658 | cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)) | |
2659 | ||
2660 | qs.update({ | |
2661 | 'ver': ['2'], | |
2662 | 'cpn': [cpn], | |
2663 | }) | |
2664 | playback_url = compat_urlparse.urlunparse( | |
2665 | parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True))) | |
2666 | ||
2667 | self._download_webpage( | |
2668 | playback_url, video_id, 'Marking watched', | |
2669 | 'Unable to mark watched', fatal=False) | |
2670 | ||
2671 | @staticmethod | |
2672 | def _extract_urls(webpage): | |
2673 | # Embedded YouTube player | |
2674 | entries = [ | |
2675 | unescapeHTML(mobj.group('url')) | |
2676 | for mobj in re.finditer(r'''(?x) | |
2677 | (?: | |
2678 | <iframe[^>]+?src=| | |
2679 | data-video-url=| | |
2680 | <embed[^>]+?src=| | |
2681 | embedSWF\(?:\s*| | |
2682 | <object[^>]+data=| | |
2683 | new\s+SWFObject\( | |
2684 | ) | |
2685 | (["\']) | |
2686 | (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ | |
2687 | (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?) | |
2688 | \1''', webpage)] | |
2689 | ||
2690 | # lazyYT YouTube embed | |
2691 | entries.extend(list(map( | |
2692 | unescapeHTML, | |
2693 | re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)))) | |
2694 | ||
2695 | # Wordpress "YouTube Video Importer" plugin | |
2696 | matches = re.findall(r'''(?x)<div[^>]+ | |
2697 | class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+ | |
2698 | data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage) | |
2699 | entries.extend(m[-1] for m in matches) | |
2700 | ||
2701 | return entries | |
2702 | ||
2703 | @staticmethod | |
2704 | def _extract_url(webpage): | |
2705 | urls = YoutubeIE._extract_urls(webpage) | |
2706 | return urls[0] if urls else None | |
2707 | ||
2708 | @classmethod | |
2709 | def extract_id(cls, url): | |
2710 | mobj = re.match(cls._VALID_URL, url, re.VERBOSE) | |
2711 | if mobj is None: | |
2712 | raise ExtractorError('Invalid URL: %s' % url) | |
2713 | return mobj.group('id') | |
2714 | ||
2715 | def _extract_chapters_from_json(self, data, duration): | |
2716 | chapter_list = traverse_obj( | |
2717 | data, ( | |
2718 | 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer', | |
2719 | 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters' | |
2720 | ), expected_type=list) | |
2721 | ||
2722 | return self._extract_chapters( | |
2723 | chapter_list, | |
2724 | chapter_time=lambda chapter: float_or_none( | |
2725 | traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000), | |
2726 | chapter_title=lambda chapter: traverse_obj( | |
2727 | chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str), | |
2728 | duration=duration) | |
2729 | ||
2730 | def _extract_chapters_from_engagement_panel(self, data, duration): | |
2731 | content_list = traverse_obj( | |
2732 | data, | |
2733 | ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'), | |
2734 | expected_type=list, default=[]) | |
2735 | chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription')) | |
2736 | chapter_title = lambda chapter: self._get_text(chapter, 'title') | |
2737 | ||
2738 | return next(filter(None, ( | |
2739 | self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')), | |
2740 | chapter_time, chapter_title, duration) | |
2741 | for contents in content_list)), []) | |
2742 | ||
2743 | def _extract_chapters_from_description(self, description, duration): | |
2744 | return self._extract_chapters( | |
2745 | re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''), | |
2746 | chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1], | |
2747 | duration=duration, strict=False) | |
2748 | ||
2749 | def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True): | |
2750 | if not duration: | |
2751 | return | |
2752 | chapter_list = [{ | |
2753 | 'start_time': chapter_time(chapter), | |
2754 | 'title': chapter_title(chapter), | |
2755 | } for chapter in chapter_list or []] | |
2756 | if not strict: | |
2757 | chapter_list.sort(key=lambda c: c['start_time'] or 0) | |
2758 | ||
2759 | chapters = [{'start_time': 0, 'title': '<Untitled>'}] | |
2760 | for idx, chapter in enumerate(chapter_list): | |
2761 | if chapter['start_time'] is None or not chapter['title']: | |
2762 | self.report_warning(f'Incomplete chapter {idx}') | |
2763 | elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration: | |
2764 | chapters[-1]['end_time'] = chapter['start_time'] | |
2765 | chapters.append(chapter) | |
2766 | else: | |
2767 | self.report_warning(f'Invalid start time for chapter "{chapter["title"]}"') | |
2768 | chapters[-1]['end_time'] = duration | |
2769 | return chapters if len(chapters) > 1 and chapters[1]['start_time'] else chapters[1:] | |
2770 | ||
2771 | def _extract_comment(self, comment_renderer, parent=None): | |
2772 | comment_id = comment_renderer.get('commentId') | |
2773 | if not comment_id: | |
2774 | return | |
2775 | ||
2776 | text = self._get_text(comment_renderer, 'contentText') | |
2777 | ||
2778 | # note: timestamp is an estimate calculated from the current time and time_text | |
2779 | timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText') | |
2780 | author = self._get_text(comment_renderer, 'authorText') | |
2781 | author_id = try_get(comment_renderer, | |
2782 | lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str) | |
2783 | ||
2784 | votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'], | |
2785 | lambda x: x['likeCount']), compat_str)) or 0 | |
2786 | author_thumbnail = try_get(comment_renderer, | |
2787 | lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str) | |
2788 | ||
2789 | author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool) | |
2790 | is_favorited = 'creatorHeart' in (try_get( | |
2791 | comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {}) | |
2792 | return { | |
2793 | 'id': comment_id, | |
2794 | 'text': text, | |
2795 | 'timestamp': timestamp, | |
2796 | 'time_text': time_text, | |
2797 | 'like_count': votes, | |
2798 | 'is_favorited': is_favorited, | |
2799 | 'author': author, | |
2800 | 'author_id': author_id, | |
2801 | 'author_thumbnail': author_thumbnail, | |
2802 | 'author_is_uploader': author_is_uploader, | |
2803 | 'parent': parent or 'root' | |
2804 | } | |
2805 | ||
2806 | def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None): | |
2807 | ||
2808 | get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0] | |
2809 | ||
2810 | def extract_header(contents): | |
2811 | _continuation = None | |
2812 | for content in contents: | |
2813 | comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer') | |
2814 | expected_comment_count = self._get_count( | |
2815 | comments_header_renderer, 'countText', 'commentsCount') | |
2816 | ||
2817 | if expected_comment_count: | |
2818 | tracker['est_total'] = expected_comment_count | |
2819 | self.to_screen(f'Downloading ~{expected_comment_count} comments') | |
2820 | comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top | |
2821 | ||
2822 | sort_menu_item = try_get( | |
2823 | comments_header_renderer, | |
2824 | lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {} | |
2825 | sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {} | |
2826 | ||
2827 | _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item) | |
2828 | if not _continuation: | |
2829 | continue | |
2830 | ||
2831 | sort_text = str_or_none(sort_menu_item.get('title')) | |
2832 | if not sort_text: | |
2833 | sort_text = 'top comments' if comment_sort_index == 0 else 'newest first' | |
2834 | self.to_screen('Sorting comments by %s' % sort_text.lower()) | |
2835 | break | |
2836 | return _continuation | |
2837 | ||
2838 | def extract_thread(contents): | |
2839 | if not parent: | |
2840 | tracker['current_page_thread'] = 0 | |
2841 | for content in contents: | |
2842 | if not parent and tracker['total_parent_comments'] >= max_parents: | |
2843 | yield | |
2844 | comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer']) | |
2845 | comment_renderer = get_first( | |
2846 | (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]], | |
2847 | expected_type=dict, default={}) | |
2848 | ||
2849 | comment = self._extract_comment(comment_renderer, parent) | |
2850 | if not comment: | |
2851 | continue | |
2852 | ||
2853 | tracker['running_total'] += 1 | |
2854 | tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1 | |
2855 | yield comment | |
2856 | ||
2857 | # Attempt to get the replies | |
2858 | comment_replies_renderer = try_get( | |
2859 | comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict) | |
2860 | ||
2861 | if comment_replies_renderer: | |
2862 | tracker['current_page_thread'] += 1 | |
2863 | comment_entries_iter = self._comment_entries( | |
2864 | comment_replies_renderer, ytcfg, video_id, | |
2865 | parent=comment.get('id'), tracker=tracker) | |
2866 | yield from itertools.islice(comment_entries_iter, min( | |
2867 | max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))) | |
2868 | ||
2869 | # Keeps track of counts across recursive calls | |
2870 | if not tracker: | |
2871 | tracker = dict( | |
2872 | running_total=0, | |
2873 | est_total=0, | |
2874 | current_page_thread=0, | |
2875 | total_parent_comments=0, | |
2876 | total_reply_comments=0) | |
2877 | ||
2878 | # TODO: Deprecated | |
2879 | # YouTube comments have a max depth of 2 | |
2880 | max_depth = int_or_none(get_single_config_arg('max_comment_depth')) | |
2881 | if max_depth: | |
2882 | self._downloader.deprecation_warning( | |
2883 | '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.') | |
2884 | if max_depth == 1 and parent: | |
2885 | return | |
2886 | ||
2887 | max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map( | |
2888 | lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4) | |
2889 | ||
2890 | continuation = self._extract_continuation(root_continuation_data) | |
2891 | ||
2892 | response = None | |
2893 | is_forced_continuation = False | |
2894 | is_first_continuation = parent is None | |
2895 | if is_first_continuation and not continuation: | |
2896 | # Sometimes you can get comments by generating the continuation yourself, | |
2897 | # even if YouTube initially reports them being disabled - e.g. stories comments. | |
2898 | # Note: if the comment section is actually disabled, YouTube may return a response with | |
2899 | # required check_get_keys missing. So we will disable that check initially in this case. | |
2900 | continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id)) | |
2901 | is_forced_continuation = True | |
2902 | ||
2903 | for page_num in itertools.count(0): | |
2904 | if not continuation: | |
2905 | break | |
2906 | headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)) | |
2907 | comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})" | |
2908 | if page_num == 0: | |
2909 | if is_first_continuation: | |
2910 | note_prefix = 'Downloading comment section API JSON' | |
2911 | else: | |
2912 | note_prefix = ' Downloading comment API JSON reply thread %d %s' % ( | |
2913 | tracker['current_page_thread'], comment_prog_str) | |
2914 | else: | |
2915 | note_prefix = '%sDownloading comment%s API JSON page %d %s' % ( | |
2916 | ' ' if parent else '', ' replies' if parent else '', | |
2917 | page_num, comment_prog_str) | |
2918 | ||
2919 | response = self._extract_response( | |
2920 | item_id=None, query=continuation, | |
2921 | ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix, | |
2922 | check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None) | |
2923 | is_forced_continuation = False | |
2924 | continuation_contents = traverse_obj( | |
2925 | response, 'onResponseReceivedEndpoints', expected_type=list, default=[]) | |
2926 | ||
2927 | continuation = None | |
2928 | for continuation_section in continuation_contents: | |
2929 | continuation_items = traverse_obj( | |
2930 | continuation_section, | |
2931 | (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'), | |
2932 | get_all=False, expected_type=list) or [] | |
2933 | if is_first_continuation: | |
2934 | continuation = extract_header(continuation_items) | |
2935 | is_first_continuation = False | |
2936 | if continuation: | |
2937 | break | |
2938 | continue | |
2939 | ||
2940 | for entry in extract_thread(continuation_items): | |
2941 | if not entry: | |
2942 | return | |
2943 | yield entry | |
2944 | continuation = self._extract_continuation({'contents': continuation_items}) | |
2945 | if continuation: | |
2946 | break | |
2947 | ||
2948 | message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1) | |
2949 | if message and not parent and tracker['running_total'] == 0: | |
2950 | self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True) | |
2951 | ||
2952 | @staticmethod | |
2953 | def _generate_comment_continuation(video_id): | |
2954 | """ | |
2955 | Generates initial comment section continuation token from given video id | |
2956 | """ | |
2957 | token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section' | |
2958 | return base64.b64encode(token.encode()).decode() | |
2959 | ||
2960 | def _get_comments(self, ytcfg, video_id, contents, webpage): | |
2961 | """Entry for comment extraction""" | |
2962 | def _real_comment_extract(contents): | |
2963 | renderer = next(( | |
2964 | item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={}) | |
2965 | if item.get('sectionIdentifier') == 'comment-item-section'), None) | |
2966 | yield from self._comment_entries(renderer, ytcfg, video_id) | |
2967 | ||
2968 | max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0]) | |
2969 | return itertools.islice(_real_comment_extract(contents), 0, max_comments) | |
2970 | ||
2971 | @staticmethod | |
2972 | def _get_checkok_params(): | |
2973 | return {'contentCheckOk': True, 'racyCheckOk': True} | |
2974 | ||
2975 | @classmethod | |
2976 | def _generate_player_context(cls, sts=None): | |
2977 | context = { | |
2978 | 'html5Preference': 'HTML5_PREF_WANTS', | |
2979 | } | |
2980 | if sts is not None: | |
2981 | context['signatureTimestamp'] = sts | |
2982 | return { | |
2983 | 'playbackContext': { | |
2984 | 'contentPlaybackContext': context | |
2985 | }, | |
2986 | **cls._get_checkok_params() | |
2987 | } | |
2988 | ||
2989 | @staticmethod | |
2990 | def _is_agegated(player_response): | |
2991 | if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')): | |
2992 | return True | |
2993 | ||
2994 | reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[]) | |
2995 | AGE_GATE_REASONS = ( | |
2996 | 'confirm your age', 'age-restricted', 'inappropriate', # reason | |
2997 | 'age_verification_required', 'age_check_required', # status | |
2998 | ) | |
2999 | return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons) | |
3000 | ||
3001 | @staticmethod | |
3002 | def _is_unplayable(player_response): | |
3003 | return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE' | |
3004 | ||
3005 | def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr): | |
3006 | ||
3007 | session_index = self._extract_session_index(player_ytcfg, master_ytcfg) | |
3008 | syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr) | |
3009 | sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None | |
3010 | headers = self.generate_api_headers( | |
3011 | ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client) | |
3012 | ||
3013 | yt_query = { | |
3014 | 'videoId': video_id, | |
3015 | 'params': '8AEB' # enable stories | |
3016 | } | |
3017 | yt_query.update(self._generate_player_context(sts)) | |
3018 | return self._extract_response( | |
3019 | item_id=video_id, ep='player', query=yt_query, | |
3020 | ytcfg=player_ytcfg, headers=headers, fatal=True, | |
3021 | default_client=client, | |
3022 | note='Downloading %s player API JSON' % client.replace('_', ' ').strip() | |
3023 | ) or None | |
3024 | ||
3025 | def _get_requested_clients(self, url, smuggled_data): | |
3026 | requested_clients = [] | |
3027 | default = ['android', 'web'] | |
3028 | allowed_clients = sorted( | |
3029 | (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'), | |
3030 | key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True) | |
3031 | for client in self._configuration_arg('player_client'): | |
3032 | if client in allowed_clients: | |
3033 | requested_clients.append(client) | |
3034 | elif client == 'default': | |
3035 | requested_clients.extend(default) | |
3036 | elif client == 'all': | |
3037 | requested_clients.extend(allowed_clients) | |
3038 | else: | |
3039 | self.report_warning(f'Skipping unsupported client {client}') | |
3040 | if not requested_clients: | |
3041 | requested_clients = default | |
3042 | ||
3043 | if smuggled_data.get('is_music_url') or self.is_music_url(url): | |
3044 | requested_clients.extend( | |
3045 | f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS) | |
3046 | ||
3047 | return orderedSet(requested_clients) | |
3048 | ||
3049 | def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg): | |
3050 | initial_pr = None | |
3051 | if webpage: | |
3052 | initial_pr = self._search_json( | |
3053 | self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False) | |
3054 | ||
3055 | all_clients = set(clients) | |
3056 | clients = clients[::-1] | |
3057 | prs = [] | |
3058 | ||
3059 | def append_client(*client_names): | |
3060 | """ Append the first client name that exists but not already used """ | |
3061 | for client_name in client_names: | |
3062 | actual_client = _split_innertube_client(client_name)[0] | |
3063 | if actual_client in INNERTUBE_CLIENTS: | |
3064 | if actual_client not in all_clients: | |
3065 | clients.append(client_name) | |
3066 | all_clients.add(actual_client) | |
3067 | return | |
3068 | ||
3069 | # Android player_response does not have microFormats which are needed for | |
3070 | # extraction of some data. So we return the initial_pr with formats | |
3071 | # stripped out even if not requested by the user | |
3072 | # See: https://github.com/yt-dlp/yt-dlp/issues/501 | |
3073 | if initial_pr: | |
3074 | pr = dict(initial_pr) | |
3075 | pr['streamingData'] = None | |
3076 | prs.append(pr) | |
3077 | ||
3078 | last_error = None | |
3079 | tried_iframe_fallback = False | |
3080 | player_url = None | |
3081 | while clients: | |
3082 | client, base_client, variant = _split_innertube_client(clients.pop()) | |
3083 | player_ytcfg = master_ytcfg if client == 'web' else {} | |
3084 | if 'configs' not in self._configuration_arg('player_skip') and client != 'web': | |
3085 | player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg | |
3086 | ||
3087 | player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage) | |
3088 | require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER') | |
3089 | if 'js' in self._configuration_arg('player_skip'): | |
3090 | require_js_player = False | |
3091 | player_url = None | |
3092 | ||
3093 | if not player_url and not tried_iframe_fallback and require_js_player: | |
3094 | player_url = self._download_player_url(video_id) | |
3095 | tried_iframe_fallback = True | |
3096 | ||
3097 | try: | |
3098 | pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response( | |
3099 | client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr) | |
3100 | except ExtractorError as e: | |
3101 | if last_error: | |
3102 | self.report_warning(last_error) | |
3103 | last_error = e | |
3104 | continue | |
3105 | ||
3106 | if pr: | |
3107 | prs.append(pr) | |
3108 | ||
3109 | # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in | |
3110 | if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated: | |
3111 | append_client(f'{base_client}_creator') | |
3112 | elif self._is_agegated(pr): | |
3113 | if variant == 'tv_embedded': | |
3114 | append_client(f'{base_client}_embedded') | |
3115 | elif not variant: | |
3116 | append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded') | |
3117 | ||
3118 | if last_error: | |
3119 | if not len(prs): | |
3120 | raise last_error | |
3121 | self.report_warning(last_error) | |
3122 | return prs, player_url | |
3123 | ||
3124 | def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration): | |
3125 | itags, stream_ids = {}, [] | |
3126 | itag_qualities, res_qualities = {}, {} | |
3127 | q = qualities([ | |
3128 | # Normally tiny is the smallest video-only formats. But | |
3129 | # audio-only formats with unknown quality may get tagged as tiny | |
3130 | 'tiny', | |
3131 | 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats | |
3132 | 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres' | |
3133 | ]) | |
3134 | streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[]) | |
3135 | ||
3136 | for fmt in streaming_formats: | |
3137 | if fmt.get('targetDurationSec'): | |
3138 | continue | |
3139 | ||
3140 | itag = str_or_none(fmt.get('itag')) | |
3141 | audio_track = fmt.get('audioTrack') or {} | |
3142 | stream_id = '%s.%s' % (itag or '', audio_track.get('id', '')) | |
3143 | if stream_id in stream_ids: | |
3144 | continue | |
3145 | ||
3146 | quality = fmt.get('quality') | |
3147 | height = int_or_none(fmt.get('height')) | |
3148 | if quality == 'tiny' or not quality: | |
3149 | quality = fmt.get('audioQuality', '').lower() or quality | |
3150 | # The 3gp format (17) in android client has a quality of "small", | |
3151 | # but is actually worse than other formats | |
3152 | if itag == '17': | |
3153 | quality = 'tiny' | |
3154 | if quality: | |
3155 | if itag: | |
3156 | itag_qualities[itag] = quality | |
3157 | if height: | |
3158 | res_qualities[height] = quality | |
3159 | # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment | |
3160 | # (adding `&sq=0` to the URL) and parsing emsg box to determine the | |
3161 | # number of fragment that would subsequently requested with (`&sq=N`) | |
3162 | if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF': | |
3163 | continue | |
3164 | ||
3165 | fmt_url = fmt.get('url') | |
3166 | if not fmt_url: | |
3167 | sc = compat_parse_qs(fmt.get('signatureCipher')) | |
3168 | fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0])) | |
3169 | encrypted_sig = try_get(sc, lambda x: x['s'][0]) | |
3170 | if not all((sc, fmt_url, player_url, encrypted_sig)): | |
3171 | continue | |
3172 | try: | |
3173 | fmt_url += '&%s=%s' % ( | |
3174 | traverse_obj(sc, ('sp', -1)) or 'signature', | |
3175 | self._decrypt_signature(encrypted_sig, video_id, player_url) | |
3176 | ) | |
3177 | except ExtractorError as e: | |
3178 | self.report_warning('Signature extraction failed: Some formats may be missing', only_once=True) | |
3179 | self.write_debug(e, only_once=True) | |
3180 | continue | |
3181 | ||
3182 | query = parse_qs(fmt_url) | |
3183 | throttled = False | |
3184 | if query.get('n'): | |
3185 | try: | |
3186 | fmt_url = update_url_query(fmt_url, { | |
3187 | 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)}) | |
3188 | except ExtractorError as e: | |
3189 | self.report_warning( | |
3190 | 'nsig extraction failed: You may experience throttling for some formats\n' | |
3191 | f'n = {query["n"][0]} ; player = {player_url}', only_once=True) | |
3192 | self.write_debug(e, only_once=True) | |
3193 | throttled = True | |
3194 | ||
3195 | if itag: | |
3196 | itags[itag] = 'https' | |
3197 | stream_ids.append(stream_id) | |
3198 | ||
3199 | tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) | |
3200 | language_preference = ( | |
3201 | 10 if audio_track.get('audioIsDefault') and 10 | |
3202 | else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10 | |
3203 | else -1) | |
3204 | # Some formats may have much smaller duration than others (possibly damaged during encoding) | |
3205 | # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823 | |
3206 | # Make sure to avoid false positives with small duration differences. | |
3207 | # Eg: __2ABJjxzNo, ySuUZEjARPY | |
3208 | is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500) | |
3209 | if is_damaged: | |
3210 | self.report_warning( | |
3211 | f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True) | |
3212 | dct = { | |
3213 | 'asr': int_or_none(fmt.get('audioSampleRate')), | |
3214 | 'filesize': int_or_none(fmt.get('contentLength')), | |
3215 | 'format_id': itag, | |
3216 | 'format_note': join_nonempty( | |
3217 | '%s%s' % (audio_track.get('displayName') or '', | |
3218 | ' (default)' if language_preference > 0 else ''), | |
3219 | fmt.get('qualityLabel') or quality.replace('audio_quality_', ''), | |
3220 | throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '), | |
3221 | # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372 | |
3222 | 'source_preference': -10 if throttled else -5 if itag == '22' else -1, | |
3223 | 'fps': int_or_none(fmt.get('fps')) or None, | |
3224 | 'height': height, | |
3225 | 'quality': q(quality), | |
3226 | 'has_drm': bool(fmt.get('drmFamilies')), | |
3227 | 'tbr': tbr, | |
3228 | 'url': fmt_url, | |
3229 | 'width': int_or_none(fmt.get('width')), | |
3230 | 'language': join_nonempty(audio_track.get('id', '').split('.')[0], | |
3231 | 'desc' if language_preference < -1 else ''), | |
3232 | 'language_preference': language_preference, | |
3233 | # Strictly de-prioritize damaged and 3gp formats | |
3234 | 'preference': -10 if is_damaged else -2 if itag == '17' else None, | |
3235 | } | |
3236 | mime_mobj = re.match( | |
3237 | r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '') | |
3238 | if mime_mobj: | |
3239 | dct['ext'] = mimetype2ext(mime_mobj.group(1)) | |
3240 | dct.update(parse_codecs(mime_mobj.group(2))) | |
3241 | no_audio = dct.get('acodec') == 'none' | |
3242 | no_video = dct.get('vcodec') == 'none' | |
3243 | if no_audio: | |
3244 | dct['vbr'] = tbr | |
3245 | if no_video: | |
3246 | dct['abr'] = tbr | |
3247 | if no_audio or no_video: | |
3248 | dct['downloader_options'] = { | |
3249 | # Youtube throttles chunks >~10M | |
3250 | 'http_chunk_size': 10485760, | |
3251 | } | |
3252 | if dct.get('ext'): | |
3253 | dct['container'] = dct['ext'] + '_dash' | |
3254 | yield dct | |
3255 | ||
3256 | live_from_start = is_live and self.get_param('live_from_start') | |
3257 | skip_manifests = self._configuration_arg('skip') | |
3258 | if not self.get_param('youtube_include_hls_manifest', True): | |
3259 | skip_manifests.append('hls') | |
3260 | if not self.get_param('youtube_include_dash_manifest', True): | |
3261 | skip_manifests.append('dash') | |
3262 | get_dash = 'dash' not in skip_manifests and ( | |
3263 | not is_live or live_from_start or self._configuration_arg('include_live_dash')) | |
3264 | get_hls = not live_from_start and 'hls' not in skip_manifests | |
3265 | ||
3266 | def process_manifest_format(f, proto, itag): | |
3267 | if itag in itags: | |
3268 | if itags[itag] == proto or f'{itag}-{proto}' in itags: | |
3269 | return False | |
3270 | itag = f'{itag}-{proto}' | |
3271 | if itag: | |
3272 | f['format_id'] = itag | |
3273 | itags[itag] = proto | |
3274 | ||
3275 | f['quality'] = next(( | |
3276 | q(qdict[val]) | |
3277 | for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities)) | |
3278 | if val in qdict), -1) | |
3279 | return True | |
3280 | ||
3281 | for sd in streaming_data: | |
3282 | hls_manifest_url = get_hls and sd.get('hlsManifestUrl') | |
3283 | if hls_manifest_url: | |
3284 | for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False): | |
3285 | if process_manifest_format(f, 'hls', self._search_regex( | |
3286 | r'/itag/(\d+)', f['url'], 'itag', default=None)): | |
3287 | yield f | |
3288 | ||
3289 | dash_manifest_url = get_dash and sd.get('dashManifestUrl') | |
3290 | if dash_manifest_url: | |
3291 | for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False): | |
3292 | if process_manifest_format(f, 'dash', f['format_id']): | |
3293 | f['filesize'] = int_or_none(self._search_regex( | |
3294 | r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None)) | |
3295 | if live_from_start: | |
3296 | f['is_from_start'] = True | |
3297 | ||
3298 | yield f | |
3299 | ||
3300 | def _extract_storyboard(self, player_responses, duration): | |
3301 | spec = get_first( | |
3302 | player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1] | |
3303 | base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None)) | |
3304 | if not base_url: | |
3305 | return | |
3306 | L = len(spec) - 1 | |
3307 | for i, args in enumerate(spec): | |
3308 | args = args.split('#') | |
3309 | counts = list(map(int_or_none, args[:5])) | |
3310 | if len(args) != 8 or not all(counts): | |
3311 | self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}') | |
3312 | continue | |
3313 | width, height, frame_count, cols, rows = counts | |
3314 | N, sigh = args[6:] | |
3315 | ||
3316 | url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}' | |
3317 | fragment_count = frame_count / (cols * rows) | |
3318 | fragment_duration = duration / fragment_count | |
3319 | yield { | |
3320 | 'format_id': f'sb{i}', | |
3321 | 'format_note': 'storyboard', | |
3322 | 'ext': 'mhtml', | |
3323 | 'protocol': 'mhtml', | |
3324 | 'acodec': 'none', | |
3325 | 'vcodec': 'none', | |
3326 | 'url': url, | |
3327 | 'width': width, | |
3328 | 'height': height, | |
3329 | 'fragments': [{ | |
3330 | 'url': url.replace('$M', str(j)), | |
3331 | 'duration': min(fragment_duration, duration - (j * fragment_duration)), | |
3332 | } for j in range(math.ceil(fragment_count))], | |
3333 | } | |
3334 | ||
3335 | def _download_player_responses(self, url, smuggled_data, video_id, webpage_url): | |
3336 | webpage = None | |
3337 | if 'webpage' not in self._configuration_arg('player_skip'): | |
3338 | webpage = self._download_webpage( | |
3339 | webpage_url + '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id, fatal=False) | |
3340 | ||
3341 | master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg() | |
3342 | ||
3343 | player_responses, player_url = self._extract_player_responses( | |
3344 | self._get_requested_clients(url, smuggled_data), | |
3345 | video_id, webpage, master_ytcfg) | |
3346 | ||
3347 | return webpage, master_ytcfg, player_responses, player_url | |
3348 | ||
3349 | def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None): | |
3350 | live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails')) | |
3351 | is_live = get_first(video_details, 'isLive') | |
3352 | if is_live is None: | |
3353 | is_live = get_first(live_broadcast_details, 'isLiveNow') | |
3354 | ||
3355 | streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[]) | |
3356 | formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration)) | |
3357 | ||
3358 | return live_broadcast_details, is_live, streaming_data, formats | |
3359 | ||
3360 | def _real_extract(self, url): | |
3361 | url, smuggled_data = unsmuggle_url(url, {}) | |
3362 | video_id = self._match_id(url) | |
3363 | ||
3364 | base_url = self.http_scheme() + '//www.youtube.com/' | |
3365 | webpage_url = base_url + 'watch?v=' + video_id | |
3366 | ||
3367 | webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url) | |
3368 | ||
3369 | playability_statuses = traverse_obj( | |
3370 | player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[]) | |
3371 | ||
3372 | trailer_video_id = get_first( | |
3373 | playability_statuses, | |
3374 | ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'), | |
3375 | expected_type=str) | |
3376 | if trailer_video_id: | |
3377 | return self.url_result( | |
3378 | trailer_video_id, self.ie_key(), trailer_video_id) | |
3379 | ||
3380 | search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None)) | |
3381 | if webpage else (lambda x: None)) | |
3382 | ||
3383 | video_details = traverse_obj( | |
3384 | player_responses, (..., 'videoDetails'), expected_type=dict, default=[]) | |
3385 | microformats = traverse_obj( | |
3386 | player_responses, (..., 'microformat', 'playerMicroformatRenderer'), | |
3387 | expected_type=dict, default=[]) | |
3388 | video_title = ( | |
3389 | get_first(video_details, 'title') | |
3390 | or self._get_text(microformats, (..., 'title')) | |
3391 | or search_meta(['og:title', 'twitter:title', 'title'])) | |
3392 | video_description = get_first(video_details, 'shortDescription') | |
3393 | ||
3394 | multifeed_metadata_list = get_first( | |
3395 | player_responses, | |
3396 | ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'), | |
3397 | expected_type=str) | |
3398 | if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'): | |
3399 | if self.get_param('noplaylist'): | |
3400 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
3401 | else: | |
3402 | entries = [] | |
3403 | feed_ids = [] | |
3404 | for feed in multifeed_metadata_list.split(','): | |
3405 | # Unquote should take place before split on comma (,) since textual | |
3406 | # fields may contain comma as well (see | |
3407 | # https://github.com/ytdl-org/youtube-dl/issues/8536) | |
3408 | feed_data = compat_parse_qs( | |
3409 | compat_urllib_parse_unquote_plus(feed)) | |
3410 | ||
3411 | def feed_entry(name): | |
3412 | return try_get( | |
3413 | feed_data, lambda x: x[name][0], compat_str) | |
3414 | ||
3415 | feed_id = feed_entry('id') | |
3416 | if not feed_id: | |
3417 | continue | |
3418 | feed_title = feed_entry('title') | |
3419 | title = video_title | |
3420 | if feed_title: | |
3421 | title += ' (%s)' % feed_title | |
3422 | entries.append({ | |
3423 | '_type': 'url_transparent', | |
3424 | 'ie_key': 'Youtube', | |
3425 | 'url': smuggle_url( | |
3426 | '%swatch?v=%s' % (base_url, feed_data['id'][0]), | |
3427 | {'force_singlefeed': True}), | |
3428 | 'title': title, | |
3429 | }) | |
3430 | feed_ids.append(feed_id) | |
3431 | self.to_screen( | |
3432 | 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' | |
3433 | % (', '.join(feed_ids), video_id)) | |
3434 | return self.playlist_result( | |
3435 | entries, video_id, video_title, video_description) | |
3436 | ||
3437 | duration = int_or_none( | |
3438 | get_first(video_details, 'lengthSeconds') | |
3439 | or get_first(microformats, 'lengthSeconds') | |
3440 | or parse_duration(search_meta('duration'))) or None | |
3441 | ||
3442 | if get_first(video_details, 'isPostLiveDvr'): | |
3443 | self.write_debug('Video is in Post-Live Manifestless mode') | |
3444 | if duration or 0 > 4 * 3600: | |
3445 | self.report_warning( | |
3446 | 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. ' | |
3447 | 'This is a known issue and patches are welcome') | |
3448 | ||
3449 | live_broadcast_details, is_live, streaming_data, formats = self._list_formats( | |
3450 | video_id, microformats, video_details, player_responses, player_url, duration) | |
3451 | ||
3452 | if not formats: | |
3453 | if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')): | |
3454 | self.report_drm(video_id) | |
3455 | pemr = get_first( | |
3456 | playability_statuses, | |
3457 | ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {} | |
3458 | reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason') | |
3459 | subreason = clean_html(self._get_text(pemr, 'subreason') or '') | |
3460 | if subreason: | |
3461 | if subreason == 'The uploader has not made this video available in your country.': | |
3462 | countries = get_first(microformats, 'availableCountries') | |
3463 | if not countries: | |
3464 | regions_allowed = search_meta('regionsAllowed') | |
3465 | countries = regions_allowed.split(',') if regions_allowed else None | |
3466 | self.raise_geo_restricted(subreason, countries, metadata_available=True) | |
3467 | reason += f'. {subreason}' | |
3468 | if reason: | |
3469 | self.raise_no_formats(reason, expected=True) | |
3470 | ||
3471 | keywords = get_first(video_details, 'keywords', expected_type=list) or [] | |
3472 | if not keywords and webpage: | |
3473 | keywords = [ | |
3474 | unescapeHTML(m.group('content')) | |
3475 | for m in re.finditer(self._meta_regex('og:video:tag'), webpage)] | |
3476 | for keyword in keywords: | |
3477 | if keyword.startswith('yt:stretch='): | |
3478 | mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword) | |
3479 | if mobj: | |
3480 | # NB: float is intentional for forcing float division | |
3481 | w, h = (float(v) for v in mobj.groups()) | |
3482 | if w > 0 and h > 0: | |
3483 | ratio = w / h | |
3484 | for f in formats: | |
3485 | if f.get('vcodec') != 'none': | |
3486 | f['stretched_ratio'] = ratio | |
3487 | break | |
3488 | thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail')) | |
3489 | thumbnail_url = search_meta(['og:image', 'twitter:image']) | |
3490 | if thumbnail_url: | |
3491 | thumbnails.append({ | |
3492 | 'url': thumbnail_url, | |
3493 | }) | |
3494 | original_thumbnails = thumbnails.copy() | |
3495 | ||
3496 | # The best resolution thumbnails sometimes does not appear in the webpage | |
3497 | # See: https://github.com/yt-dlp/yt-dlp/issues/340 | |
3498 | # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029> | |
3499 | thumbnail_names = [ | |
3500 | # While the *1,*2,*3 thumbnails are just below their correspnding "*default" variants | |
3501 | # in resolution, these are not the custom thumbnail. So de-prioritize them | |
3502 | 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default', | |
3503 | 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3' | |
3504 | ] | |
3505 | n_thumbnail_names = len(thumbnail_names) | |
3506 | thumbnails.extend({ | |
3507 | 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format( | |
3508 | video_id=video_id, name=name, ext=ext, | |
3509 | webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''), | |
3510 | } for name in thumbnail_names for ext in ('webp', 'jpg')) | |
3511 | for thumb in thumbnails: | |
3512 | i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names) | |
3513 | thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i) | |
3514 | self._remove_duplicate_formats(thumbnails) | |
3515 | self._downloader._sort_thumbnails(original_thumbnails) | |
3516 | ||
3517 | category = get_first(microformats, 'category') or search_meta('genre') | |
3518 | channel_id = str_or_none( | |
3519 | get_first(video_details, 'channelId') | |
3520 | or get_first(microformats, 'externalChannelId') | |
3521 | or search_meta('channelId')) | |
3522 | owner_profile_url = get_first(microformats, 'ownerProfileUrl') | |
3523 | ||
3524 | live_content = get_first(video_details, 'isLiveContent') | |
3525 | is_upcoming = get_first(video_details, 'isUpcoming') | |
3526 | if is_live is None: | |
3527 | if is_upcoming or live_content is False: | |
3528 | is_live = False | |
3529 | if is_upcoming is None and (live_content or is_live): | |
3530 | is_upcoming = False | |
3531 | live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp')) | |
3532 | live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp')) | |
3533 | if not duration and live_end_time and live_start_time: | |
3534 | duration = live_end_time - live_start_time | |
3535 | ||
3536 | if is_live and self.get_param('live_from_start'): | |
3537 | self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data) | |
3538 | ||
3539 | formats.extend(self._extract_storyboard(player_responses, duration)) | |
3540 | ||
3541 | # Source is given priority since formats that throttle are given lower source_preference | |
3542 | # When throttling issue is fully fixed, remove this | |
3543 | self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto')) | |
3544 | ||
3545 | info = { | |
3546 | 'id': video_id, | |
3547 | 'title': video_title, | |
3548 | 'formats': formats, | |
3549 | 'thumbnails': thumbnails, | |
3550 | # The best thumbnail that we are sure exists. Prevents unnecessary | |
3551 | # URL checking if user don't care about getting the best possible thumbnail | |
3552 | 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')), | |
3553 | 'description': video_description, | |
3554 | 'uploader': get_first(video_details, 'author'), | |
3555 | 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None, | |
3556 | 'uploader_url': owner_profile_url, | |
3557 | 'channel_id': channel_id, | |
3558 | 'channel_url': format_field(channel_id, None, 'https://www.youtube.com/channel/%s'), | |
3559 | 'duration': duration, | |
3560 | 'view_count': int_or_none( | |
3561 | get_first((video_details, microformats), (..., 'viewCount')) | |
3562 | or search_meta('interactionCount')), | |
3563 | 'average_rating': float_or_none(get_first(video_details, 'averageRating')), | |
3564 | 'age_limit': 18 if ( | |
3565 | get_first(microformats, 'isFamilySafe') is False | |
3566 | or search_meta('isFamilyFriendly') == 'false' | |
3567 | or search_meta('og:restrictions:age') == '18+') else 0, | |
3568 | 'webpage_url': webpage_url, | |
3569 | 'categories': [category] if category else None, | |
3570 | 'tags': keywords, | |
3571 | 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'), | |
3572 | 'is_live': is_live, | |
3573 | 'was_live': (False if is_live or is_upcoming or live_content is False | |
3574 | else None if is_live is None or is_upcoming is None | |
3575 | else live_content), | |
3576 | 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL | |
3577 | 'release_timestamp': live_start_time, | |
3578 | } | |
3579 | ||
3580 | pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict) | |
3581 | if pctr: | |
3582 | def get_lang_code(track): | |
3583 | return (remove_start(track.get('vssId') or '', '.').replace('.', '-') | |
3584 | or track.get('languageCode')) | |
3585 | ||
3586 | # Converted into dicts to remove duplicates | |
3587 | captions = { | |
3588 | get_lang_code(sub): sub | |
3589 | for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])} | |
3590 | translation_languages = { | |
3591 | lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1) | |
3592 | for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])} | |
3593 | ||
3594 | def process_language(container, base_url, lang_code, sub_name, query): | |
3595 | lang_subs = container.setdefault(lang_code, []) | |
3596 | for fmt in self._SUBTITLE_FORMATS: | |
3597 | query.update({ | |
3598 | 'fmt': fmt, | |
3599 | }) | |
3600 | lang_subs.append({ | |
3601 | 'ext': fmt, | |
3602 | 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)), | |
3603 | 'name': sub_name, | |
3604 | }) | |
3605 | ||
3606 | subtitles, automatic_captions = {}, {} | |
3607 | for lang_code, caption_track in captions.items(): | |
3608 | base_url = caption_track.get('baseUrl') | |
3609 | orig_lang = parse_qs(base_url).get('lang', [None])[-1] | |
3610 | if not base_url: | |
3611 | continue | |
3612 | lang_name = self._get_text(caption_track, 'name', max_runs=1) | |
3613 | if caption_track.get('kind') != 'asr': | |
3614 | if not lang_code: | |
3615 | continue | |
3616 | process_language( | |
3617 | subtitles, base_url, lang_code, lang_name, {}) | |
3618 | if not caption_track.get('isTranslatable'): | |
3619 | continue | |
3620 | for trans_code, trans_name in translation_languages.items(): | |
3621 | if not trans_code: | |
3622 | continue | |
3623 | orig_trans_code = trans_code | |
3624 | if caption_track.get('kind') != 'asr': | |
3625 | if 'translated_subs' in self._configuration_arg('skip'): | |
3626 | continue | |
3627 | trans_code += f'-{lang_code}' | |
3628 | trans_name += format_field(lang_name, None, ' from %s') | |
3629 | # Add an "-orig" label to the original language so that it can be distinguished. | |
3630 | # The subs are returned without "-orig" as well for compatibility | |
3631 | if lang_code == f'a-{orig_trans_code}': | |
3632 | process_language( | |
3633 | automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {}) | |
3634 | # Setting tlang=lang returns damaged subtitles. | |
3635 | process_language(automatic_captions, base_url, trans_code, trans_name, | |
3636 | {} if orig_lang == orig_trans_code else {'tlang': trans_code}) | |
3637 | info['automatic_captions'] = automatic_captions | |
3638 | info['subtitles'] = subtitles | |
3639 | ||
3640 | parsed_url = compat_urllib_parse_urlparse(url) | |
3641 | for component in [parsed_url.fragment, parsed_url.query]: | |
3642 | query = compat_parse_qs(component) | |
3643 | for k, v in query.items(): | |
3644 | for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]: | |
3645 | d_k += '_time' | |
3646 | if d_k not in info and k in s_ks: | |
3647 | info[d_k] = parse_duration(query[k][0]) | |
3648 | ||
3649 | # Youtube Music Auto-generated description | |
3650 | if video_description: | |
3651 | mobj = re.search( | |
3652 | r'''(?xs) | |
3653 | (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+ | |
3654 | (?P<album>[^\n]+) | |
3655 | (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))? | |
3656 | (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))? | |
3657 | (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))? | |
3658 | .+\nAuto-generated\ by\ YouTube\.\s*$ | |
3659 | ''', video_description) | |
3660 | if mobj: | |
3661 | release_year = mobj.group('release_year') | |
3662 | release_date = mobj.group('release_date') | |
3663 | if release_date: | |
3664 | release_date = release_date.replace('-', '') | |
3665 | if not release_year: | |
3666 | release_year = release_date[:4] | |
3667 | info.update({ | |
3668 | 'album': mobj.group('album'.strip()), | |
3669 | 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')), | |
3670 | 'track': mobj.group('track').strip(), | |
3671 | 'release_date': release_date, | |
3672 | 'release_year': int_or_none(release_year), | |
3673 | }) | |
3674 | ||
3675 | initial_data = None | |
3676 | if webpage: | |
3677 | initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False) | |
3678 | if not initial_data: | |
3679 | query = {'videoId': video_id} | |
3680 | query.update(self._get_checkok_params()) | |
3681 | initial_data = self._extract_response( | |
3682 | item_id=video_id, ep='next', fatal=False, | |
3683 | ytcfg=master_ytcfg, query=query, | |
3684 | headers=self.generate_api_headers(ytcfg=master_ytcfg), | |
3685 | note='Downloading initial data API JSON') | |
3686 | ||
3687 | info['comment_count'] = traverse_obj(initial_data, ( | |
3688 | 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer', | |
3689 | 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText' | |
3690 | ), ( | |
3691 | 'engagementPanels', lambda _, v: v['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section', | |
3692 | 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text' | |
3693 | ), expected_type=int_or_none, get_all=False) | |
3694 | ||
3695 | try: # This will error if there is no livechat | |
3696 | initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation'] | |
3697 | except (KeyError, IndexError, TypeError): | |
3698 | pass | |
3699 | else: | |
3700 | info.setdefault('subtitles', {})['live_chat'] = [{ | |
3701 | # url is needed to set cookies | |
3702 | 'url': f'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1', | |
3703 | 'video_id': video_id, | |
3704 | 'ext': 'json', | |
3705 | 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay', | |
3706 | }] | |
3707 | ||
3708 | if initial_data: | |
3709 | info['chapters'] = ( | |
3710 | self._extract_chapters_from_json(initial_data, duration) | |
3711 | or self._extract_chapters_from_engagement_panel(initial_data, duration) | |
3712 | or self._extract_chapters_from_description(video_description, duration) | |
3713 | or None) | |
3714 | ||
3715 | contents = traverse_obj( | |
3716 | initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'), | |
3717 | expected_type=list, default=[]) | |
3718 | ||
3719 | vpir = get_first(contents, 'videoPrimaryInfoRenderer') | |
3720 | if vpir: | |
3721 | stl = vpir.get('superTitleLink') | |
3722 | if stl: | |
3723 | stl = self._get_text(stl) | |
3724 | if try_get( | |
3725 | vpir, | |
3726 | lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN': | |
3727 | info['location'] = stl | |
3728 | else: | |
3729 | mobj = re.search(r'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl) | |
3730 | if mobj: | |
3731 | info.update({ | |
3732 | 'series': mobj.group(1), | |
3733 | 'season_number': int(mobj.group(2)), | |
3734 | 'episode_number': int(mobj.group(3)), | |
3735 | }) | |
3736 | for tlb in (try_get( | |
3737 | vpir, | |
3738 | lambda x: x['videoActions']['menuRenderer']['topLevelButtons'], | |
3739 | list) or []): | |
3740 | tbr = tlb.get('toggleButtonRenderer') or {} | |
3741 | for getter, regex in [( | |
3742 | lambda x: x['defaultText']['accessibility']['accessibilityData'], | |
3743 | r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([ | |
3744 | lambda x: x['accessibility'], | |
3745 | lambda x: x['accessibilityData']['accessibilityData'], | |
3746 | ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]: | |
3747 | label = (try_get(tbr, getter, dict) or {}).get('label') | |
3748 | if label: | |
3749 | mobj = re.match(regex, label) | |
3750 | if mobj: | |
3751 | info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count')) | |
3752 | break | |
3753 | sbr_tooltip = try_get( | |
3754 | vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip']) | |
3755 | if sbr_tooltip: | |
3756 | like_count, dislike_count = sbr_tooltip.split(' / ') | |
3757 | info.update({ | |
3758 | 'like_count': str_to_int(like_count), | |
3759 | 'dislike_count': str_to_int(dislike_count), | |
3760 | }) | |
3761 | vsir = get_first(contents, 'videoSecondaryInfoRenderer') | |
3762 | if vsir: | |
3763 | vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer')) | |
3764 | info.update({ | |
3765 | 'channel': self._get_text(vor, 'title'), | |
3766 | 'channel_follower_count': self._get_count(vor, 'subscriberCountText')}) | |
3767 | ||
3768 | rows = try_get( | |
3769 | vsir, | |
3770 | lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'], | |
3771 | list) or [] | |
3772 | multiple_songs = False | |
3773 | for row in rows: | |
3774 | if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True: | |
3775 | multiple_songs = True | |
3776 | break | |
3777 | for row in rows: | |
3778 | mrr = row.get('metadataRowRenderer') or {} | |
3779 | mrr_title = mrr.get('title') | |
3780 | if not mrr_title: | |
3781 | continue | |
3782 | mrr_title = self._get_text(mrr, 'title') | |
3783 | mrr_contents_text = self._get_text(mrr, ('contents', 0)) | |
3784 | if mrr_title == 'License': | |
3785 | info['license'] = mrr_contents_text | |
3786 | elif not multiple_songs: | |
3787 | if mrr_title == 'Album': | |
3788 | info['album'] = mrr_contents_text | |
3789 | elif mrr_title == 'Artist': | |
3790 | info['artist'] = mrr_contents_text | |
3791 | elif mrr_title == 'Song': | |
3792 | info['track'] = mrr_contents_text | |
3793 | ||
3794 | fallbacks = { | |
3795 | 'channel': 'uploader', | |
3796 | 'channel_id': 'uploader_id', | |
3797 | 'channel_url': 'uploader_url', | |
3798 | } | |
3799 | ||
3800 | # The upload date for scheduled, live and past live streams / premieres in microformats | |
3801 | # may be different from the stream date. Although not in UTC, we will prefer it in this case. | |
3802 | # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139 | |
3803 | upload_date = ( | |
3804 | unified_strdate(get_first(microformats, 'uploadDate')) | |
3805 | or unified_strdate(search_meta('uploadDate'))) | |
3806 | if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'): | |
3807 | upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') or upload_date | |
3808 | info['upload_date'] = upload_date | |
3809 | ||
3810 | for to, frm in fallbacks.items(): | |
3811 | if not info.get(to): | |
3812 | info[to] = info.get(frm) | |
3813 | ||
3814 | for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]: | |
3815 | v = info.get(s_k) | |
3816 | if v: | |
3817 | info[d_k] = v | |
3818 | ||
3819 | is_private = get_first(video_details, 'isPrivate', expected_type=bool) | |
3820 | is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool) | |
3821 | is_membersonly = None | |
3822 | is_premium = None | |
3823 | if initial_data and is_private is not None: | |
3824 | is_membersonly = False | |
3825 | is_premium = False | |
3826 | contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or [] | |
3827 | badge_labels = set() | |
3828 | for content in contents: | |
3829 | if not isinstance(content, dict): | |
3830 | continue | |
3831 | badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer'))) | |
3832 | for badge_label in badge_labels: | |
3833 | if badge_label.lower() == 'members only': | |
3834 | is_membersonly = True | |
3835 | elif badge_label.lower() == 'premium': | |
3836 | is_premium = True | |
3837 | elif badge_label.lower() == 'unlisted': | |
3838 | is_unlisted = True | |
3839 | ||
3840 | info['availability'] = self._availability( | |
3841 | is_private=is_private, | |
3842 | needs_premium=is_premium, | |
3843 | needs_subscription=is_membersonly, | |
3844 | needs_auth=info['age_limit'] >= 18, | |
3845 | is_unlisted=None if is_private is None else is_unlisted) | |
3846 | ||
3847 | info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage) | |
3848 | ||
3849 | self.mark_watched(video_id, player_responses) | |
3850 | ||
3851 | return info | |
3852 | ||
3853 | ||
3854 | class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor): | |
3855 | ||
3856 | @staticmethod | |
3857 | def passthrough_smuggled_data(func): | |
3858 | def _smuggle(entries, smuggled_data): | |
3859 | for entry in entries: | |
3860 | # TODO: Convert URL to music.youtube instead. | |
3861 | # Do we need to passthrough any other smuggled_data? | |
3862 | entry['url'] = smuggle_url(entry['url'], smuggled_data) | |
3863 | yield entry | |
3864 | ||
3865 | @functools.wraps(func) | |
3866 | def wrapper(self, url): | |
3867 | url, smuggled_data = unsmuggle_url(url, {}) | |
3868 | if self.is_music_url(url): | |
3869 | smuggled_data['is_music_url'] = True | |
3870 | info_dict = func(self, url, smuggled_data) | |
3871 | if smuggled_data and info_dict.get('entries'): | |
3872 | info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data) | |
3873 | return info_dict | |
3874 | return wrapper | |
3875 | ||
3876 | def _extract_channel_id(self, webpage): | |
3877 | channel_id = self._html_search_meta( | |
3878 | 'channelId', webpage, 'channel id', default=None) | |
3879 | if channel_id: | |
3880 | return channel_id | |
3881 | channel_url = self._html_search_meta( | |
3882 | ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url', | |
3883 | 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad', | |
3884 | 'twitter:app:url:googleplay'), webpage, 'channel url') | |
3885 | return self._search_regex( | |
3886 | r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+', | |
3887 | channel_url, 'channel id') | |
3888 | ||
3889 | @staticmethod | |
3890 | def _extract_basic_item_renderer(item): | |
3891 | # Modified from _extract_grid_item_renderer | |
3892 | known_basic_renderers = ( | |
3893 | 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer' | |
3894 | ) | |
3895 | for key, renderer in item.items(): | |
3896 | if not isinstance(renderer, dict): | |
3897 | continue | |
3898 | elif key in known_basic_renderers: | |
3899 | return renderer | |
3900 | elif key.startswith('grid') and key.endswith('Renderer'): | |
3901 | return renderer | |
3902 | ||
3903 | def _grid_entries(self, grid_renderer): | |
3904 | for item in grid_renderer['items']: | |
3905 | if not isinstance(item, dict): | |
3906 | continue | |
3907 | renderer = self._extract_basic_item_renderer(item) | |
3908 | if not isinstance(renderer, dict): | |
3909 | continue | |
3910 | title = self._get_text(renderer, 'title') | |
3911 | ||
3912 | # playlist | |
3913 | playlist_id = renderer.get('playlistId') | |
3914 | if playlist_id: | |
3915 | yield self.url_result( | |
3916 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, | |
3917 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id, | |
3918 | video_title=title) | |
3919 | continue | |
3920 | # video | |
3921 | video_id = renderer.get('videoId') | |
3922 | if video_id: | |
3923 | yield self._extract_video(renderer) | |
3924 | continue | |
3925 | # channel | |
3926 | channel_id = renderer.get('channelId') | |
3927 | if channel_id: | |
3928 | yield self.url_result( | |
3929 | 'https://www.youtube.com/channel/%s' % channel_id, | |
3930 | ie=YoutubeTabIE.ie_key(), video_title=title) | |
3931 | continue | |
3932 | # generic endpoint URL support | |
3933 | ep_url = urljoin('https://www.youtube.com/', try_get( | |
3934 | renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'], | |
3935 | compat_str)) | |
3936 | if ep_url: | |
3937 | for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE): | |
3938 | if ie.suitable(ep_url): | |
3939 | yield self.url_result( | |
3940 | ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title) | |
3941 | break | |
3942 | ||
3943 | def _music_reponsive_list_entry(self, renderer): | |
3944 | video_id = traverse_obj(renderer, ('playlistItemData', 'videoId')) | |
3945 | if video_id: | |
3946 | return self.url_result(f'https://music.youtube.com/watch?v={video_id}', | |
3947 | ie=YoutubeIE.ie_key(), video_id=video_id) | |
3948 | playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId')) | |
3949 | if playlist_id: | |
3950 | video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId')) | |
3951 | if video_id: | |
3952 | return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}', | |
3953 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
3954 | return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}', | |
3955 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
3956 | browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId')) | |
3957 | if browse_id: | |
3958 | return self.url_result(f'https://music.youtube.com/browse/{browse_id}', | |
3959 | ie=YoutubeTabIE.ie_key(), video_id=browse_id) | |
3960 | ||
3961 | def _shelf_entries_from_content(self, shelf_renderer): | |
3962 | content = shelf_renderer.get('content') | |
3963 | if not isinstance(content, dict): | |
3964 | return | |
3965 | renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer') | |
3966 | if renderer: | |
3967 | # TODO: add support for nested playlists so each shelf is processed | |
3968 | # as separate playlist | |
3969 | # TODO: this includes only first N items | |
3970 | yield from self._grid_entries(renderer) | |
3971 | renderer = content.get('horizontalListRenderer') | |
3972 | if renderer: | |
3973 | # TODO | |
3974 | pass | |
3975 | ||
3976 | def _shelf_entries(self, shelf_renderer, skip_channels=False): | |
3977 | ep = try_get( | |
3978 | shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], | |
3979 | compat_str) | |
3980 | shelf_url = urljoin('https://www.youtube.com', ep) | |
3981 | if shelf_url: | |
3982 | # Skipping links to another channels, note that checking for | |
3983 | # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL | |
3984 | # will not work | |
3985 | if skip_channels and '/channels?' in shelf_url: | |
3986 | return | |
3987 | title = self._get_text(shelf_renderer, 'title') | |
3988 | yield self.url_result(shelf_url, video_title=title) | |
3989 | # Shelf may not contain shelf URL, fallback to extraction from content | |
3990 | yield from self._shelf_entries_from_content(shelf_renderer) | |
3991 | ||
3992 | def _playlist_entries(self, video_list_renderer): | |
3993 | for content in video_list_renderer['contents']: | |
3994 | if not isinstance(content, dict): | |
3995 | continue | |
3996 | renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer') | |
3997 | if not isinstance(renderer, dict): | |
3998 | continue | |
3999 | video_id = renderer.get('videoId') | |
4000 | if not video_id: | |
4001 | continue | |
4002 | yield self._extract_video(renderer) | |
4003 | ||
4004 | def _rich_entries(self, rich_grid_renderer): | |
4005 | renderer = try_get( | |
4006 | rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {} | |
4007 | video_id = renderer.get('videoId') | |
4008 | if not video_id: | |
4009 | return | |
4010 | yield self._extract_video(renderer) | |
4011 | ||
4012 | def _video_entry(self, video_renderer): | |
4013 | video_id = video_renderer.get('videoId') | |
4014 | if video_id: | |
4015 | return self._extract_video(video_renderer) | |
4016 | ||
4017 | def _hashtag_tile_entry(self, hashtag_tile_renderer): | |
4018 | url = urljoin('https://youtube.com', traverse_obj( | |
4019 | hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url'))) | |
4020 | if url: | |
4021 | return self.url_result( | |
4022 | url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag')) | |
4023 | ||
4024 | def _post_thread_entries(self, post_thread_renderer): | |
4025 | post_renderer = try_get( | |
4026 | post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict) | |
4027 | if not post_renderer: | |
4028 | return | |
4029 | # video attachment | |
4030 | video_renderer = try_get( | |
4031 | post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {} | |
4032 | video_id = video_renderer.get('videoId') | |
4033 | if video_id: | |
4034 | entry = self._extract_video(video_renderer) | |
4035 | if entry: | |
4036 | yield entry | |
4037 | # playlist attachment | |
4038 | playlist_id = try_get( | |
4039 | post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str) | |
4040 | if playlist_id: | |
4041 | yield self.url_result( | |
4042 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, | |
4043 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
4044 | # inline video links | |
4045 | runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or [] | |
4046 | for run in runs: | |
4047 | if not isinstance(run, dict): | |
4048 | continue | |
4049 | ep_url = try_get( | |
4050 | run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str) | |
4051 | if not ep_url: | |
4052 | continue | |
4053 | if not YoutubeIE.suitable(ep_url): | |
4054 | continue | |
4055 | ep_video_id = YoutubeIE._match_id(ep_url) | |
4056 | if video_id == ep_video_id: | |
4057 | continue | |
4058 | yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id) | |
4059 | ||
4060 | def _post_thread_continuation_entries(self, post_thread_continuation): | |
4061 | contents = post_thread_continuation.get('contents') | |
4062 | if not isinstance(contents, list): | |
4063 | return | |
4064 | for content in contents: | |
4065 | renderer = content.get('backstagePostThreadRenderer') | |
4066 | if isinstance(renderer, dict): | |
4067 | yield from self._post_thread_entries(renderer) | |
4068 | continue | |
4069 | renderer = content.get('videoRenderer') | |
4070 | if isinstance(renderer, dict): | |
4071 | yield self._video_entry(renderer) | |
4072 | ||
4073 | r''' # unused | |
4074 | def _rich_grid_entries(self, contents): | |
4075 | for content in contents: | |
4076 | video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict) | |
4077 | if video_renderer: | |
4078 | entry = self._video_entry(video_renderer) | |
4079 | if entry: | |
4080 | yield entry | |
4081 | ''' | |
4082 | ||
4083 | def _extract_entries(self, parent_renderer, continuation_list): | |
4084 | # continuation_list is modified in-place with continuation_list = [continuation_token] | |
4085 | continuation_list[:] = [None] | |
4086 | contents = try_get(parent_renderer, lambda x: x['contents'], list) or [] | |
4087 | for content in contents: | |
4088 | if not isinstance(content, dict): | |
4089 | continue | |
4090 | is_renderer = traverse_obj( | |
4091 | content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation', | |
4092 | expected_type=dict) | |
4093 | if not is_renderer: | |
4094 | renderer = content.get('richItemRenderer') | |
4095 | if renderer: | |
4096 | for entry in self._rich_entries(renderer): | |
4097 | yield entry | |
4098 | continuation_list[0] = self._extract_continuation(parent_renderer) | |
4099 | continue | |
4100 | isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or [] | |
4101 | for isr_content in isr_contents: | |
4102 | if not isinstance(isr_content, dict): | |
4103 | continue | |
4104 | ||
4105 | known_renderers = { | |
4106 | 'playlistVideoListRenderer': self._playlist_entries, | |
4107 | 'gridRenderer': self._grid_entries, | |
4108 | 'reelShelfRenderer': self._grid_entries, | |
4109 | 'shelfRenderer': self._shelf_entries, | |
4110 | 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)], | |
4111 | 'backstagePostThreadRenderer': self._post_thread_entries, | |
4112 | 'videoRenderer': lambda x: [self._video_entry(x)], | |
4113 | 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}), | |
4114 | 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}), | |
4115 | 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)] | |
4116 | } | |
4117 | for key, renderer in isr_content.items(): | |
4118 | if key not in known_renderers: | |
4119 | continue | |
4120 | for entry in known_renderers[key](renderer): | |
4121 | if entry: | |
4122 | yield entry | |
4123 | continuation_list[0] = self._extract_continuation(renderer) | |
4124 | break | |
4125 | ||
4126 | if not continuation_list[0]: | |
4127 | continuation_list[0] = self._extract_continuation(is_renderer) | |
4128 | ||
4129 | if not continuation_list[0]: | |
4130 | continuation_list[0] = self._extract_continuation(parent_renderer) | |
4131 | ||
4132 | def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data): | |
4133 | continuation_list = [None] | |
4134 | extract_entries = lambda x: self._extract_entries(x, continuation_list) | |
4135 | tab_content = try_get(tab, lambda x: x['content'], dict) | |
4136 | if not tab_content: | |
4137 | return | |
4138 | parent_renderer = ( | |
4139 | try_get(tab_content, lambda x: x['sectionListRenderer'], dict) | |
4140 | or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {}) | |
4141 | yield from extract_entries(parent_renderer) | |
4142 | continuation = continuation_list[0] | |
4143 | ||
4144 | for page_num in itertools.count(1): | |
4145 | if not continuation: | |
4146 | break | |
4147 | headers = self.generate_api_headers( | |
4148 | ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data) | |
4149 | response = self._extract_response( | |
4150 | item_id=f'{item_id} page {page_num}', | |
4151 | query=continuation, headers=headers, ytcfg=ytcfg, | |
4152 | check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints')) | |
4153 | ||
4154 | if not response: | |
4155 | break | |
4156 | # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases | |
4157 | # See: https://github.com/ytdl-org/youtube-dl/issues/28702 | |
4158 | visitor_data = self._extract_visitor_data(response) or visitor_data | |
4159 | ||
4160 | known_continuation_renderers = { | |
4161 | 'playlistVideoListContinuation': self._playlist_entries, | |
4162 | 'gridContinuation': self._grid_entries, | |
4163 | 'itemSectionContinuation': self._post_thread_continuation_entries, | |
4164 | 'sectionListContinuation': extract_entries, # for feeds | |
4165 | } | |
4166 | continuation_contents = try_get( | |
4167 | response, lambda x: x['continuationContents'], dict) or {} | |
4168 | continuation_renderer = None | |
4169 | for key, value in continuation_contents.items(): | |
4170 | if key not in known_continuation_renderers: | |
4171 | continue | |
4172 | continuation_renderer = value | |
4173 | continuation_list = [None] | |
4174 | yield from known_continuation_renderers[key](continuation_renderer) | |
4175 | continuation = continuation_list[0] or self._extract_continuation(continuation_renderer) | |
4176 | break | |
4177 | if continuation_renderer: | |
4178 | continue | |
4179 | ||
4180 | known_renderers = { | |
4181 | 'videoRenderer': (self._grid_entries, 'items'), # for membership tab | |
4182 | 'gridPlaylistRenderer': (self._grid_entries, 'items'), | |
4183 | 'gridVideoRenderer': (self._grid_entries, 'items'), | |
4184 | 'gridChannelRenderer': (self._grid_entries, 'items'), | |
4185 | 'playlistVideoRenderer': (self._playlist_entries, 'contents'), | |
4186 | 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds | |
4187 | 'richItemRenderer': (extract_entries, 'contents'), # for hashtag | |
4188 | 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents') | |
4189 | } | |
4190 | on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints')) | |
4191 | continuation_items = try_get( | |
4192 | on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list) | |
4193 | continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {} | |
4194 | video_items_renderer = None | |
4195 | for key, value in continuation_item.items(): | |
4196 | if key not in known_renderers: | |
4197 | continue | |
4198 | video_items_renderer = {known_renderers[key][1]: continuation_items} | |
4199 | continuation_list = [None] | |
4200 | yield from known_renderers[key][0](video_items_renderer) | |
4201 | continuation = continuation_list[0] or self._extract_continuation(video_items_renderer) | |
4202 | break | |
4203 | if video_items_renderer: | |
4204 | continue | |
4205 | break | |
4206 | ||
4207 | @staticmethod | |
4208 | def _extract_selected_tab(tabs, fatal=True): | |
4209 | for tab in tabs: | |
4210 | renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {} | |
4211 | if renderer.get('selected') is True: | |
4212 | return renderer | |
4213 | else: | |
4214 | if fatal: | |
4215 | raise ExtractorError('Unable to find selected tab') | |
4216 | ||
4217 | def _extract_uploader(self, data): | |
4218 | uploader = {} | |
4219 | renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {} | |
4220 | owner = try_get( | |
4221 | renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict) | |
4222 | if owner: | |
4223 | owner_text = owner.get('text') | |
4224 | uploader['uploader'] = self._search_regex( | |
4225 | r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text) | |
4226 | uploader['uploader_id'] = try_get( | |
4227 | owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str) | |
4228 | uploader['uploader_url'] = urljoin( | |
4229 | 'https://www.youtube.com/', | |
4230 | try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str)) | |
4231 | return {k: v for k, v in uploader.items() if v is not None} | |
4232 | ||
4233 | def _extract_from_tabs(self, item_id, ytcfg, data, tabs): | |
4234 | playlist_id = title = description = channel_url = channel_name = channel_id = None | |
4235 | tags = [] | |
4236 | ||
4237 | selected_tab = self._extract_selected_tab(tabs) | |
4238 | primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') | |
4239 | renderer = try_get( | |
4240 | data, lambda x: x['metadata']['channelMetadataRenderer'], dict) | |
4241 | if renderer: | |
4242 | channel_name = renderer.get('title') | |
4243 | channel_url = renderer.get('channelUrl') | |
4244 | channel_id = renderer.get('externalId') | |
4245 | else: | |
4246 | renderer = try_get( | |
4247 | data, lambda x: x['metadata']['playlistMetadataRenderer'], dict) | |
4248 | ||
4249 | if renderer: | |
4250 | title = renderer.get('title') | |
4251 | description = renderer.get('description', '') | |
4252 | playlist_id = channel_id | |
4253 | tags = renderer.get('keywords', '').split() | |
4254 | ||
4255 | # We can get the uncropped banner/avatar by replacing the crop params with '=s0' | |
4256 | # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714 | |
4257 | def _get_uncropped(url): | |
4258 | return url_or_none((url or '').split('=')[0] + '=s0') | |
4259 | ||
4260 | avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar') | |
4261 | if avatar_thumbnails: | |
4262 | uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url']) | |
4263 | if uncropped_avatar: | |
4264 | avatar_thumbnails.append({ | |
4265 | 'url': uncropped_avatar, | |
4266 | 'id': 'avatar_uncropped', | |
4267 | 'preference': 1 | |
4268 | }) | |
4269 | ||
4270 | channel_banners = self._extract_thumbnails( | |
4271 | data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner'])) | |
4272 | for banner in channel_banners: | |
4273 | banner['preference'] = -10 | |
4274 | ||
4275 | if channel_banners: | |
4276 | uncropped_banner = _get_uncropped(channel_banners[0]['url']) | |
4277 | if uncropped_banner: | |
4278 | channel_banners.append({ | |
4279 | 'url': uncropped_banner, | |
4280 | 'id': 'banner_uncropped', | |
4281 | 'preference': -5 | |
4282 | }) | |
4283 | ||
4284 | primary_thumbnails = self._extract_thumbnails( | |
4285 | primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail')) | |
4286 | ||
4287 | if playlist_id is None: | |
4288 | playlist_id = item_id | |
4289 | ||
4290 | playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats') | |
4291 | last_updated_unix, _ = self._extract_time_text(playlist_stats, 2) | |
4292 | if title is None: | |
4293 | title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id | |
4294 | title += format_field(selected_tab, 'title', ' - %s') | |
4295 | title += format_field(selected_tab, 'expandedText', ' - %s') | |
4296 | ||
4297 | metadata = { | |
4298 | 'playlist_id': playlist_id, | |
4299 | 'playlist_title': title, | |
4300 | 'playlist_description': description, | |
4301 | 'uploader': channel_name, | |
4302 | 'uploader_id': channel_id, | |
4303 | 'uploader_url': channel_url, | |
4304 | 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners, | |
4305 | 'tags': tags, | |
4306 | 'view_count': self._get_count(playlist_stats, 1), | |
4307 | 'availability': self._extract_availability(data), | |
4308 | 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'), | |
4309 | 'playlist_count': self._get_count(playlist_stats, 0), | |
4310 | 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')), | |
4311 | } | |
4312 | if not channel_id: | |
4313 | metadata.update(self._extract_uploader(data)) | |
4314 | metadata.update({ | |
4315 | 'channel': metadata['uploader'], | |
4316 | 'channel_id': metadata['uploader_id'], | |
4317 | 'channel_url': metadata['uploader_url']}) | |
4318 | return self.playlist_result( | |
4319 | self._entries( | |
4320 | selected_tab, playlist_id, ytcfg, | |
4321 | self._extract_account_syncid(ytcfg, data), | |
4322 | self._extract_visitor_data(data, ytcfg)), | |
4323 | **metadata) | |
4324 | ||
4325 | def _extract_inline_playlist(self, playlist, playlist_id, data, ytcfg): | |
4326 | first_id = last_id = response = None | |
4327 | for page_num in itertools.count(1): | |
4328 | videos = list(self._playlist_entries(playlist)) | |
4329 | if not videos: | |
4330 | return | |
4331 | start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1 | |
4332 | if start >= len(videos): | |
4333 | return | |
4334 | yield from videos[start:] | |
4335 | first_id = first_id or videos[0]['id'] | |
4336 | last_id = videos[-1]['id'] | |
4337 | watch_endpoint = try_get( | |
4338 | playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint']) | |
4339 | headers = self.generate_api_headers( | |
4340 | ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data), | |
4341 | visitor_data=self._extract_visitor_data(response, data, ytcfg)) | |
4342 | query = { | |
4343 | 'playlistId': playlist_id, | |
4344 | 'videoId': watch_endpoint.get('videoId') or last_id, | |
4345 | 'index': watch_endpoint.get('index') or len(videos), | |
4346 | 'params': watch_endpoint.get('params') or 'OAE%3D' | |
4347 | } | |
4348 | response = self._extract_response( | |
4349 | item_id='%s page %d' % (playlist_id, page_num), | |
4350 | query=query, ep='next', headers=headers, ytcfg=ytcfg, | |
4351 | check_get_keys='contents' | |
4352 | ) | |
4353 | playlist = try_get( | |
4354 | response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict) | |
4355 | ||
4356 | def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg): | |
4357 | title = playlist.get('title') or try_get( | |
4358 | data, lambda x: x['titleText']['simpleText'], compat_str) | |
4359 | playlist_id = playlist.get('playlistId') or item_id | |
4360 | ||
4361 | # Delegating everything except mix playlists to regular tab-based playlist URL | |
4362 | playlist_url = urljoin(url, try_get( | |
4363 | playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], | |
4364 | compat_str)) | |
4365 | ||
4366 | # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1] | |
4367 | # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg | |
4368 | is_known_unviewable = re.fullmatch(r'MLCT|RLTD[\w-]{22}', playlist_id) | |
4369 | ||
4370 | if playlist_url and playlist_url != url and not is_known_unviewable: | |
4371 | return self.url_result( | |
4372 | playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id, | |
4373 | video_title=title) | |
4374 | ||
4375 | return self.playlist_result( | |
4376 | self._extract_inline_playlist(playlist, playlist_id, data, ytcfg), | |
4377 | playlist_id=playlist_id, playlist_title=title) | |
4378 | ||
4379 | def _extract_availability(self, data): | |
4380 | """ | |
4381 | Gets the availability of a given playlist/tab. | |
4382 | Note: Unless YouTube tells us explicitly, we do not assume it is public | |
4383 | @param data: response | |
4384 | """ | |
4385 | is_private = is_unlisted = None | |
4386 | renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {} | |
4387 | badge_labels = self._extract_badges(renderer) | |
4388 | ||
4389 | # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge | |
4390 | privacy_dropdown_entries = try_get( | |
4391 | renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or [] | |
4392 | for renderer_dict in privacy_dropdown_entries: | |
4393 | is_selected = try_get( | |
4394 | renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False | |
4395 | if not is_selected: | |
4396 | continue | |
4397 | label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label')) | |
4398 | if label: | |
4399 | badge_labels.add(label.lower()) | |
4400 | break | |
4401 | ||
4402 | for badge_label in badge_labels: | |
4403 | if badge_label == 'unlisted': | |
4404 | is_unlisted = True | |
4405 | elif badge_label == 'private': | |
4406 | is_private = True | |
4407 | elif badge_label == 'public': | |
4408 | is_unlisted = is_private = False | |
4409 | return self._availability(is_private, False, False, False, is_unlisted) | |
4410 | ||
4411 | @staticmethod | |
4412 | def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict): | |
4413 | sidebar_renderer = try_get( | |
4414 | data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or [] | |
4415 | for item in sidebar_renderer: | |
4416 | renderer = try_get(item, lambda x: x[info_renderer], expected_type) | |
4417 | if renderer: | |
4418 | return renderer | |
4419 | ||
4420 | def _reload_with_unavailable_videos(self, item_id, data, ytcfg): | |
4421 | """ | |
4422 | Get playlist with unavailable videos if the 'show unavailable videos' button exists. | |
4423 | """ | |
4424 | browse_id = params = None | |
4425 | renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') | |
4426 | if not renderer: | |
4427 | return | |
4428 | menu_renderer = try_get( | |
4429 | renderer, lambda x: x['menu']['menuRenderer']['items'], list) or [] | |
4430 | for menu_item in menu_renderer: | |
4431 | if not isinstance(menu_item, dict): | |
4432 | continue | |
4433 | nav_item_renderer = menu_item.get('menuNavigationItemRenderer') | |
4434 | text = try_get( | |
4435 | nav_item_renderer, lambda x: x['text']['simpleText'], compat_str) | |
4436 | if not text or text.lower() != 'show unavailable videos': | |
4437 | continue | |
4438 | browse_endpoint = try_get( | |
4439 | nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {} | |
4440 | browse_id = browse_endpoint.get('browseId') | |
4441 | params = browse_endpoint.get('params') | |
4442 | break | |
4443 | ||
4444 | headers = self.generate_api_headers( | |
4445 | ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data), | |
4446 | visitor_data=self._extract_visitor_data(data, ytcfg)) | |
4447 | query = { | |
4448 | 'params': params or 'wgYCCAA=', | |
4449 | 'browseId': browse_id or 'VL%s' % item_id | |
4450 | } | |
4451 | return self._extract_response( | |
4452 | item_id=item_id, headers=headers, query=query, | |
4453 | check_get_keys='contents', fatal=False, ytcfg=ytcfg, | |
4454 | note='Downloading API JSON with unavailable videos') | |
4455 | ||
4456 | @functools.cached_property | |
4457 | def skip_webpage(self): | |
4458 | return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) | |
4459 | ||
4460 | def _extract_webpage(self, url, item_id, fatal=True): | |
4461 | retries = self.get_param('extractor_retries', 3) | |
4462 | count = -1 | |
4463 | webpage = data = last_error = None | |
4464 | while count < retries: | |
4465 | count += 1 | |
4466 | # Sometimes youtube returns a webpage with incomplete ytInitialData | |
4467 | # See: https://github.com/yt-dlp/yt-dlp/issues/116 | |
4468 | if last_error: | |
4469 | self.report_warning('%s. Retrying ...' % last_error) | |
4470 | try: | |
4471 | webpage = self._download_webpage( | |
4472 | url, item_id, | |
4473 | note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',)) | |
4474 | data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {} | |
4475 | except ExtractorError as e: | |
4476 | if isinstance(e.cause, network_exceptions): | |
4477 | if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429): | |
4478 | last_error = error_to_compat_str(e.cause or e.msg) | |
4479 | if count < retries: | |
4480 | continue | |
4481 | if fatal: | |
4482 | raise | |
4483 | self.report_warning(error_to_compat_str(e)) | |
4484 | break | |
4485 | else: | |
4486 | try: | |
4487 | self._extract_and_report_alerts(data) | |
4488 | except ExtractorError as e: | |
4489 | if fatal: | |
4490 | raise | |
4491 | self.report_warning(error_to_compat_str(e)) | |
4492 | break | |
4493 | ||
4494 | if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')): | |
4495 | break | |
4496 | ||
4497 | last_error = 'Incomplete yt initial data received' | |
4498 | if count >= retries: | |
4499 | if fatal: | |
4500 | raise ExtractorError(last_error) | |
4501 | self.report_warning(last_error) | |
4502 | break | |
4503 | ||
4504 | return webpage, data | |
4505 | ||
4506 | def _report_playlist_authcheck(self, ytcfg, fatal=True): | |
4507 | """Use if failed to extract ytcfg (and data) from initial webpage""" | |
4508 | if not ytcfg and self.is_authenticated: | |
4509 | msg = 'Playlists that require authentication may not extract correctly without a successful webpage download' | |
4510 | if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal: | |
4511 | raise ExtractorError( | |
4512 | f'{msg}. If you are not downloading private content, or ' | |
4513 | 'your cookies are only for the first account and channel,' | |
4514 | ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check', | |
4515 | expected=True) | |
4516 | self.report_warning(msg, only_once=True) | |
4517 | ||
4518 | def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'): | |
4519 | data = None | |
4520 | if not self.skip_webpage: | |
4521 | webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal) | |
4522 | ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage) | |
4523 | # Reject webpage data if redirected to home page without explicitly requesting | |
4524 | selected_tab = self._extract_selected_tab(traverse_obj( | |
4525 | data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {} | |
4526 | if (url != 'https://www.youtube.com/feed/recommended' | |
4527 | and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page | |
4528 | and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])): | |
4529 | msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page' | |
4530 | if fatal: | |
4531 | raise ExtractorError(msg, expected=True) | |
4532 | self.report_warning(msg, only_once=True) | |
4533 | if not data: | |
4534 | self._report_playlist_authcheck(ytcfg, fatal=fatal) | |
4535 | data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client) | |
4536 | return data, ytcfg | |
4537 | ||
4538 | def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'): | |
4539 | headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client) | |
4540 | resolve_response = self._extract_response( | |
4541 | item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal, | |
4542 | ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client) | |
4543 | endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'} | |
4544 | for ep_key, ep in endpoints.items(): | |
4545 | params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict) | |
4546 | if params: | |
4547 | return self._extract_response( | |
4548 | item_id=item_id, query=params, ep=ep, headers=headers, | |
4549 | ytcfg=ytcfg, fatal=fatal, default_client=default_client, | |
4550 | check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')) | |
4551 | err_note = 'Failed to resolve url (does the playlist exist?)' | |
4552 | if fatal: | |
4553 | raise ExtractorError(err_note, expected=True) | |
4554 | self.report_warning(err_note, item_id) | |
4555 | ||
4556 | _SEARCH_PARAMS = None | |
4557 | ||
4558 | def _search_results(self, query, params=NO_DEFAULT, default_client='web'): | |
4559 | data = {'query': query} | |
4560 | if params is NO_DEFAULT: | |
4561 | params = self._SEARCH_PARAMS | |
4562 | if params: | |
4563 | data['params'] = params | |
4564 | ||
4565 | content_keys = ( | |
4566 | ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'), | |
4567 | ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'), | |
4568 | # ytmusic search | |
4569 | ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'), | |
4570 | ('continuationContents', ), | |
4571 | ) | |
4572 | display_id = f'query "{query}"' | |
4573 | check_get_keys = tuple({keys[0] for keys in content_keys}) | |
4574 | ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {} | |
4575 | self._report_playlist_authcheck(ytcfg, fatal=False) | |
4576 | ||
4577 | continuation_list = [None] | |
4578 | search = None | |
4579 | for page_num in itertools.count(1): | |
4580 | data.update(continuation_list[0] or {}) | |
4581 | headers = self.generate_api_headers( | |
4582 | ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client) | |
4583 | search = self._extract_response( | |
4584 | item_id=f'{display_id} page {page_num}', ep='search', query=data, | |
4585 | default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers) | |
4586 | slr_contents = traverse_obj(search, *content_keys) | |
4587 | yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list) | |
4588 | if not continuation_list[0]: | |
4589 | break | |
4590 | ||
4591 | ||
4592 | class YoutubeTabIE(YoutubeTabBaseInfoExtractor): | |
4593 | IE_DESC = 'YouTube Tabs' | |
4594 | _VALID_URL = r'''(?x: | |
4595 | https?:// | |
4596 | (?:\w+\.)? | |
4597 | (?: | |
4598 | youtube(?:kids)?\.com| | |
4599 | %(invidious)s | |
4600 | )/ | |
4601 | (?: | |
4602 | (?P<channel_type>channel|c|user|browse)/| | |
4603 | (?P<not_channel> | |
4604 | feed/|hashtag/| | |
4605 | (?:playlist|watch)\?.*?\blist= | |
4606 | )| | |
4607 | (?!(?:%(reserved_names)s)\b) # Direct URLs | |
4608 | ) | |
4609 | (?P<id>[^/?\#&]+) | |
4610 | )''' % { | |
4611 | 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES, | |
4612 | 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), | |
4613 | } | |
4614 | IE_NAME = 'youtube:tab' | |
4615 | ||
4616 | _TESTS = [{ | |
4617 | 'note': 'playlists, multipage', | |
4618 | 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid', | |
4619 | 'playlist_mincount': 94, | |
4620 | 'info_dict': { | |
4621 | 'id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
4622 | 'title': 'Igor Kleiner - Playlists', | |
4623 | 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', | |
4624 | 'uploader': 'Igor Kleiner', | |
4625 | 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
4626 | 'channel': 'Igor Kleiner', | |
4627 | 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
4628 | 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'], | |
4629 | 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', | |
4630 | 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', | |
4631 | 'channel_follower_count': int | |
4632 | }, | |
4633 | }, { | |
4634 | 'note': 'playlists, multipage, different order', | |
4635 | 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', | |
4636 | 'playlist_mincount': 94, | |
4637 | 'info_dict': { | |
4638 | 'id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
4639 | 'title': 'Igor Kleiner - Playlists', | |
4640 | 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', | |
4641 | 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
4642 | 'uploader': 'Igor Kleiner', | |
4643 | 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', | |
4644 | 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'], | |
4645 | 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
4646 | 'channel': 'Igor Kleiner', | |
4647 | 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', | |
4648 | 'channel_follower_count': int | |
4649 | }, | |
4650 | }, { | |
4651 | 'note': 'playlists, series', | |
4652 | 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3', | |
4653 | 'playlist_mincount': 5, | |
4654 | 'info_dict': { | |
4655 | 'id': 'UCYO_jab_esuFRV4b17AJtAw', | |
4656 | 'title': '3Blue1Brown - Playlists', | |
4657 | 'description': 'md5:e1384e8a133307dd10edee76e875d62f', | |
4658 | 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
4659 | 'uploader': '3Blue1Brown', | |
4660 | 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', | |
4661 | 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', | |
4662 | 'channel': '3Blue1Brown', | |
4663 | 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
4664 | 'tags': ['Mathematics'], | |
4665 | 'channel_follower_count': int | |
4666 | }, | |
4667 | }, { | |
4668 | 'note': 'playlists, singlepage', | |
4669 | 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', | |
4670 | 'playlist_mincount': 4, | |
4671 | 'info_dict': { | |
4672 | 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
4673 | 'title': 'ThirstForScience - Playlists', | |
4674 | 'description': 'md5:609399d937ea957b0f53cbffb747a14c', | |
4675 | 'uploader': 'ThirstForScience', | |
4676 | 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
4677 | 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ', | |
4678 | 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ', | |
4679 | 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
4680 | 'tags': 'count:13', | |
4681 | 'channel': 'ThirstForScience', | |
4682 | 'channel_follower_count': int | |
4683 | } | |
4684 | }, { | |
4685 | 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', | |
4686 | 'only_matching': True, | |
4687 | }, { | |
4688 | 'note': 'basic, single video playlist', | |
4689 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
4690 | 'info_dict': { | |
4691 | 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
4692 | 'uploader': 'Sergey M.', | |
4693 | 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
4694 | 'title': 'youtube-dl public playlist', | |
4695 | 'description': '', | |
4696 | 'tags': [], | |
4697 | 'view_count': int, | |
4698 | 'modified_date': '20201130', | |
4699 | 'channel': 'Sergey M.', | |
4700 | 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
4701 | 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4702 | 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4703 | }, | |
4704 | 'playlist_count': 1, | |
4705 | }, { | |
4706 | 'note': 'empty playlist', | |
4707 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', | |
4708 | 'info_dict': { | |
4709 | 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
4710 | 'uploader': 'Sergey M.', | |
4711 | 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', | |
4712 | 'title': 'youtube-dl empty playlist', | |
4713 | 'tags': [], | |
4714 | 'channel': 'Sergey M.', | |
4715 | 'description': '', | |
4716 | 'modified_date': '20160902', | |
4717 | 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
4718 | 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4719 | 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4720 | }, | |
4721 | 'playlist_count': 0, | |
4722 | }, { | |
4723 | 'note': 'Home tab', | |
4724 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured', | |
4725 | 'info_dict': { | |
4726 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4727 | 'title': 'lex will - Home', | |
4728 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4729 | 'uploader': 'lex will', | |
4730 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4731 | 'channel': 'lex will', | |
4732 | 'tags': ['bible', 'history', 'prophesy'], | |
4733 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4734 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4735 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4736 | 'channel_follower_count': int | |
4737 | }, | |
4738 | 'playlist_mincount': 2, | |
4739 | }, { | |
4740 | 'note': 'Videos tab', | |
4741 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos', | |
4742 | 'info_dict': { | |
4743 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4744 | 'title': 'lex will - Videos', | |
4745 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4746 | 'uploader': 'lex will', | |
4747 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4748 | 'tags': ['bible', 'history', 'prophesy'], | |
4749 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4750 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4751 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4752 | 'channel': 'lex will', | |
4753 | 'channel_follower_count': int | |
4754 | }, | |
4755 | 'playlist_mincount': 975, | |
4756 | }, { | |
4757 | 'note': 'Videos tab, sorted by popular', | |
4758 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid', | |
4759 | 'info_dict': { | |
4760 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4761 | 'title': 'lex will - Videos', | |
4762 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4763 | 'uploader': 'lex will', | |
4764 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4765 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4766 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4767 | 'channel': 'lex will', | |
4768 | 'tags': ['bible', 'history', 'prophesy'], | |
4769 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4770 | 'channel_follower_count': int | |
4771 | }, | |
4772 | 'playlist_mincount': 199, | |
4773 | }, { | |
4774 | 'note': 'Playlists tab', | |
4775 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists', | |
4776 | 'info_dict': { | |
4777 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4778 | 'title': 'lex will - Playlists', | |
4779 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4780 | 'uploader': 'lex will', | |
4781 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4782 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4783 | 'channel': 'lex will', | |
4784 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4785 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4786 | 'tags': ['bible', 'history', 'prophesy'], | |
4787 | 'channel_follower_count': int | |
4788 | }, | |
4789 | 'playlist_mincount': 17, | |
4790 | }, { | |
4791 | 'note': 'Community tab', | |
4792 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community', | |
4793 | 'info_dict': { | |
4794 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4795 | 'title': 'lex will - Community', | |
4796 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4797 | 'uploader': 'lex will', | |
4798 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4799 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4800 | 'channel': 'lex will', | |
4801 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4802 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4803 | 'tags': ['bible', 'history', 'prophesy'], | |
4804 | 'channel_follower_count': int | |
4805 | }, | |
4806 | 'playlist_mincount': 18, | |
4807 | }, { | |
4808 | 'note': 'Channels tab', | |
4809 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels', | |
4810 | 'info_dict': { | |
4811 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4812 | 'title': 'lex will - Channels', | |
4813 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4814 | 'uploader': 'lex will', | |
4815 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4816 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4817 | 'channel': 'lex will', | |
4818 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4819 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4820 | 'tags': ['bible', 'history', 'prophesy'], | |
4821 | 'channel_follower_count': int | |
4822 | }, | |
4823 | 'playlist_mincount': 12, | |
4824 | }, { | |
4825 | 'note': 'Search tab', | |
4826 | 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra', | |
4827 | 'playlist_mincount': 40, | |
4828 | 'info_dict': { | |
4829 | 'id': 'UCYO_jab_esuFRV4b17AJtAw', | |
4830 | 'title': '3Blue1Brown - Search - linear algebra', | |
4831 | 'description': 'md5:e1384e8a133307dd10edee76e875d62f', | |
4832 | 'uploader': '3Blue1Brown', | |
4833 | 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
4834 | 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', | |
4835 | 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', | |
4836 | 'tags': ['Mathematics'], | |
4837 | 'channel': '3Blue1Brown', | |
4838 | 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
4839 | 'channel_follower_count': int | |
4840 | }, | |
4841 | }, { | |
4842 | 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4843 | 'only_matching': True, | |
4844 | }, { | |
4845 | 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4846 | 'only_matching': True, | |
4847 | }, { | |
4848 | 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4849 | 'only_matching': True, | |
4850 | }, { | |
4851 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
4852 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
4853 | 'info_dict': { | |
4854 | 'title': '29C3: Not my department', | |
4855 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
4856 | 'uploader': 'Christiaan008', | |
4857 | 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg', | |
4858 | 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268', | |
4859 | 'tags': [], | |
4860 | 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008', | |
4861 | 'view_count': int, | |
4862 | 'modified_date': '20150605', | |
4863 | 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg', | |
4864 | 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008', | |
4865 | 'channel': 'Christiaan008', | |
4866 | }, | |
4867 | 'playlist_count': 96, | |
4868 | }, { | |
4869 | 'note': 'Large playlist', | |
4870 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
4871 | 'info_dict': { | |
4872 | 'title': 'Uploads from Cauchemar', | |
4873 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', | |
4874 | 'uploader': 'Cauchemar', | |
4875 | 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q', | |
4876 | 'channel_url': 'https://www.youtube.com/c/Cauchemar89', | |
4877 | 'tags': [], | |
4878 | 'modified_date': r're:\d{8}', | |
4879 | 'channel': 'Cauchemar', | |
4880 | 'uploader_url': 'https://www.youtube.com/c/Cauchemar89', | |
4881 | 'view_count': int, | |
4882 | 'description': '', | |
4883 | 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q', | |
4884 | }, | |
4885 | 'playlist_mincount': 1123, | |
4886 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], | |
4887 | }, { | |
4888 | 'note': 'even larger playlist, 8832 videos', | |
4889 | 'url': 'http://www.youtube.com/user/NASAgovVideo/videos', | |
4890 | 'only_matching': True, | |
4891 | }, { | |
4892 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
4893 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
4894 | 'info_dict': { | |
4895 | 'title': 'Uploads from Interstellar Movie', | |
4896 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
4897 | 'uploader': 'Interstellar Movie', | |
4898 | 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA', | |
4899 | 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie', | |
4900 | 'tags': [], | |
4901 | 'view_count': int, | |
4902 | 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA', | |
4903 | 'channel_url': 'https://www.youtube.com/c/InterstellarMovie', | |
4904 | 'channel': 'Interstellar Movie', | |
4905 | 'description': '', | |
4906 | 'modified_date': r're:\d{8}', | |
4907 | }, | |
4908 | 'playlist_mincount': 21, | |
4909 | }, { | |
4910 | 'note': 'Playlist with "show unavailable videos" button', | |
4911 | 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q', | |
4912 | 'info_dict': { | |
4913 | 'title': 'Uploads from Phim Siêu Nhân Nhật Bản', | |
4914 | 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q', | |
4915 | 'uploader': 'Phim Siêu Nhân Nhật Bản', | |
4916 | 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q', | |
4917 | 'view_count': int, | |
4918 | 'channel': 'Phim Siêu Nhân Nhật Bản', | |
4919 | 'tags': [], | |
4920 | 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q', | |
4921 | 'description': '', | |
4922 | 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q', | |
4923 | 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q', | |
4924 | 'modified_date': r're:\d{8}', | |
4925 | }, | |
4926 | 'playlist_mincount': 200, | |
4927 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], | |
4928 | }, { | |
4929 | 'note': 'Playlist with unavailable videos in page 7', | |
4930 | 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w', | |
4931 | 'info_dict': { | |
4932 | 'title': 'Uploads from BlankTV', | |
4933 | 'id': 'UU8l9frL61Yl5KFOl87nIm2w', | |
4934 | 'uploader': 'BlankTV', | |
4935 | 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w', | |
4936 | 'channel': 'BlankTV', | |
4937 | 'channel_url': 'https://www.youtube.com/c/blanktv', | |
4938 | 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w', | |
4939 | 'view_count': int, | |
4940 | 'tags': [], | |
4941 | 'uploader_url': 'https://www.youtube.com/c/blanktv', | |
4942 | 'modified_date': r're:\d{8}', | |
4943 | 'description': '', | |
4944 | }, | |
4945 | 'playlist_mincount': 1000, | |
4946 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], | |
4947 | }, { | |
4948 | 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844', | |
4949 | 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
4950 | 'info_dict': { | |
4951 | 'title': 'Data Analysis with Dr Mike Pound', | |
4952 | 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
4953 | 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA', | |
4954 | 'uploader': 'Computerphile', | |
4955 | 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487', | |
4956 | 'uploader_url': 'https://www.youtube.com/user/Computerphile', | |
4957 | 'tags': [], | |
4958 | 'view_count': int, | |
4959 | 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA', | |
4960 | 'channel_url': 'https://www.youtube.com/user/Computerphile', | |
4961 | 'channel': 'Computerphile', | |
4962 | }, | |
4963 | 'playlist_mincount': 11, | |
4964 | }, { | |
4965 | 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
4966 | 'only_matching': True, | |
4967 | }, { | |
4968 | 'note': 'Playlist URL that does not actually serve a playlist', | |
4969 | 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', | |
4970 | 'info_dict': { | |
4971 | 'id': 'FqZTN594JQw', | |
4972 | 'ext': 'webm', | |
4973 | 'title': "Smiley's People 01 detective, Adventure Series, Action", | |
4974 | 'uploader': 'STREEM', | |
4975 | 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng', | |
4976 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng', | |
4977 | 'upload_date': '20150526', | |
4978 | 'license': 'Standard YouTube License', | |
4979 | 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', | |
4980 | 'categories': ['People & Blogs'], | |
4981 | 'tags': list, | |
4982 | 'view_count': int, | |
4983 | 'like_count': int, | |
4984 | }, | |
4985 | 'params': { | |
4986 | 'skip_download': True, | |
4987 | }, | |
4988 | 'skip': 'This video is not available.', | |
4989 | 'add_ie': [YoutubeIE.ie_key()], | |
4990 | }, { | |
4991 | 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g', | |
4992 | 'only_matching': True, | |
4993 | }, { | |
4994 | 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', | |
4995 | 'only_matching': True, | |
4996 | }, { | |
4997 | 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live', | |
4998 | 'info_dict': { | |
4999 | 'id': 'GgL890LIznQ', # This will keep changing | |
5000 | 'ext': 'mp4', | |
5001 | 'title': str, | |
5002 | 'uploader': 'Sky News', | |
5003 | 'uploader_id': 'skynews', | |
5004 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews', | |
5005 | 'upload_date': r're:\d{8}', | |
5006 | 'description': str, | |
5007 | 'categories': ['News & Politics'], | |
5008 | 'tags': list, | |
5009 | 'like_count': int, | |
5010 | 'release_timestamp': 1642502819, | |
5011 | 'channel': 'Sky News', | |
5012 | 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ', | |
5013 | 'age_limit': 0, | |
5014 | 'view_count': int, | |
5015 | 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg', | |
5016 | 'playable_in_embed': True, | |
5017 | 'release_date': '20220118', | |
5018 | 'availability': 'public', | |
5019 | 'live_status': 'is_live', | |
5020 | 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ', | |
5021 | 'channel_follower_count': int | |
5022 | }, | |
5023 | 'params': { | |
5024 | 'skip_download': True, | |
5025 | }, | |
5026 | 'expected_warnings': ['Ignoring subtitle tracks found in '], | |
5027 | }, { | |
5028 | 'url': 'https://www.youtube.com/user/TheYoungTurks/live', | |
5029 | 'info_dict': { | |
5030 | 'id': 'a48o2S1cPoo', | |
5031 | 'ext': 'mp4', | |
5032 | 'title': 'The Young Turks - Live Main Show', | |
5033 | 'uploader': 'The Young Turks', | |
5034 | 'uploader_id': 'TheYoungTurks', | |
5035 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks', | |
5036 | 'upload_date': '20150715', | |
5037 | 'license': 'Standard YouTube License', | |
5038 | 'description': 'md5:438179573adcdff3c97ebb1ee632b891', | |
5039 | 'categories': ['News & Politics'], | |
5040 | 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], | |
5041 | 'like_count': int, | |
5042 | }, | |
5043 | 'params': { | |
5044 | 'skip_download': True, | |
5045 | }, | |
5046 | 'only_matching': True, | |
5047 | }, { | |
5048 | 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', | |
5049 | 'only_matching': True, | |
5050 | }, { | |
5051 | 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', | |
5052 | 'only_matching': True, | |
5053 | }, { | |
5054 | 'note': 'A channel that is not live. Should raise error', | |
5055 | 'url': 'https://www.youtube.com/user/numberphile/live', | |
5056 | 'only_matching': True, | |
5057 | }, { | |
5058 | 'url': 'https://www.youtube.com/feed/trending', | |
5059 | 'only_matching': True, | |
5060 | }, { | |
5061 | 'url': 'https://www.youtube.com/feed/library', | |
5062 | 'only_matching': True, | |
5063 | }, { | |
5064 | 'url': 'https://www.youtube.com/feed/history', | |
5065 | 'only_matching': True, | |
5066 | }, { | |
5067 | 'url': 'https://www.youtube.com/feed/subscriptions', | |
5068 | 'only_matching': True, | |
5069 | }, { | |
5070 | 'url': 'https://www.youtube.com/feed/watch_later', | |
5071 | 'only_matching': True, | |
5072 | }, { | |
5073 | 'note': 'Recommended - redirects to home page.', | |
5074 | 'url': 'https://www.youtube.com/feed/recommended', | |
5075 | 'only_matching': True, | |
5076 | }, { | |
5077 | 'note': 'inline playlist with not always working continuations', | |
5078 | 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C', | |
5079 | 'only_matching': True, | |
5080 | }, { | |
5081 | 'url': 'https://www.youtube.com/course', | |
5082 | 'only_matching': True, | |
5083 | }, { | |
5084 | 'url': 'https://www.youtube.com/zsecurity', | |
5085 | 'only_matching': True, | |
5086 | }, { | |
5087 | 'url': 'http://www.youtube.com/NASAgovVideo/videos', | |
5088 | 'only_matching': True, | |
5089 | }, { | |
5090 | 'url': 'https://www.youtube.com/TheYoungTurks/live', | |
5091 | 'only_matching': True, | |
5092 | }, { | |
5093 | 'url': 'https://www.youtube.com/hashtag/cctv9', | |
5094 | 'info_dict': { | |
5095 | 'id': 'cctv9', | |
5096 | 'title': '#cctv9', | |
5097 | 'tags': [], | |
5098 | }, | |
5099 | 'playlist_mincount': 350, | |
5100 | }, { | |
5101 | 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU', | |
5102 | 'only_matching': True, | |
5103 | }, { | |
5104 | 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist', | |
5105 | 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', | |
5106 | 'only_matching': True | |
5107 | }, { | |
5108 | 'note': '/browse/ should redirect to /channel/', | |
5109 | 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng', | |
5110 | 'only_matching': True | |
5111 | }, { | |
5112 | 'note': 'VLPL, should redirect to playlist?list=PL...', | |
5113 | 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', | |
5114 | 'info_dict': { | |
5115 | 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', | |
5116 | 'uploader': 'NoCopyrightSounds', | |
5117 | 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!', | |
5118 | 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg', | |
5119 | 'title': 'NCS Releases', | |
5120 | 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds', | |
5121 | 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds', | |
5122 | 'modified_date': r're:\d{8}', | |
5123 | 'view_count': int, | |
5124 | 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg', | |
5125 | 'tags': [], | |
5126 | 'channel': 'NoCopyrightSounds', | |
5127 | }, | |
5128 | 'playlist_mincount': 166, | |
5129 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], | |
5130 | }, { | |
5131 | 'note': 'Topic, should redirect to playlist?list=UU...', | |
5132 | 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw', | |
5133 | 'info_dict': { | |
5134 | 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw', | |
5135 | 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', | |
5136 | 'title': 'Uploads from Royalty Free Music - Topic', | |
5137 | 'uploader': 'Royalty Free Music - Topic', | |
5138 | 'tags': [], | |
5139 | 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', | |
5140 | 'channel': 'Royalty Free Music - Topic', | |
5141 | 'view_count': int, | |
5142 | 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
5143 | 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
5144 | 'modified_date': r're:\d{8}', | |
5145 | 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
5146 | 'description': '', | |
5147 | }, | |
5148 | 'expected_warnings': [ | |
5149 | 'The URL does not have a videos tab', | |
5150 | r'[Uu]navailable videos (are|will be) hidden', | |
5151 | ], | |
5152 | 'playlist_mincount': 101, | |
5153 | }, { | |
5154 | 'note': 'Topic without a UU playlist', | |
5155 | 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg', | |
5156 | 'info_dict': { | |
5157 | 'id': 'UCtFRv9O2AHqOZjjynzrv-xg', | |
5158 | 'title': 'UCtFRv9O2AHqOZjjynzrv-xg', | |
5159 | 'tags': [], | |
5160 | }, | |
5161 | 'expected_warnings': [ | |
5162 | 'the playlist redirect gave error', | |
5163 | ], | |
5164 | 'playlist_mincount': 9, | |
5165 | }, { | |
5166 | 'note': 'Youtube music Album', | |
5167 | 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE', | |
5168 | 'info_dict': { | |
5169 | 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0', | |
5170 | 'title': 'Album - Royalty Free Music Library V2 (50 Songs)', | |
5171 | 'tags': [], | |
5172 | 'view_count': int, | |
5173 | 'description': '', | |
5174 | 'availability': 'unlisted', | |
5175 | 'modified_date': r're:\d{8}', | |
5176 | }, | |
5177 | 'playlist_count': 50, | |
5178 | }, { | |
5179 | 'note': 'unlisted single video playlist', | |
5180 | 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', | |
5181 | 'info_dict': { | |
5182 | 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q', | |
5183 | 'uploader': 'colethedj', | |
5184 | 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', | |
5185 | 'title': 'yt-dlp unlisted playlist test', | |
5186 | 'availability': 'unlisted', | |
5187 | 'tags': [], | |
5188 | 'modified_date': '20211208', | |
5189 | 'channel': 'colethedj', | |
5190 | 'view_count': int, | |
5191 | 'description': '', | |
5192 | 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q', | |
5193 | 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q', | |
5194 | 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q', | |
5195 | }, | |
5196 | 'playlist_count': 1, | |
5197 | }, { | |
5198 | 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData', | |
5199 | 'url': 'https://www.youtube.com/feed/recommended', | |
5200 | 'info_dict': { | |
5201 | 'id': 'recommended', | |
5202 | 'title': 'recommended', | |
5203 | 'tags': [], | |
5204 | }, | |
5205 | 'playlist_mincount': 50, | |
5206 | 'params': { | |
5207 | 'skip_download': True, | |
5208 | 'extractor_args': {'youtubetab': {'skip': ['webpage']}} | |
5209 | }, | |
5210 | }, { | |
5211 | 'note': 'API Fallback: /videos tab, sorted by oldest first', | |
5212 | 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid', | |
5213 | 'info_dict': { | |
5214 | 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', | |
5215 | 'title': 'Cody\'sLab - Videos', | |
5216 | 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa', | |
5217 | 'uploader': 'Cody\'sLab', | |
5218 | 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', | |
5219 | 'channel': 'Cody\'sLab', | |
5220 | 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', | |
5221 | 'tags': [], | |
5222 | 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw', | |
5223 | 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw', | |
5224 | 'channel_follower_count': int | |
5225 | }, | |
5226 | 'playlist_mincount': 650, | |
5227 | 'params': { | |
5228 | 'skip_download': True, | |
5229 | 'extractor_args': {'youtubetab': {'skip': ['webpage']}} | |
5230 | }, | |
5231 | }, { | |
5232 | 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...', | |
5233 | 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw', | |
5234 | 'info_dict': { | |
5235 | 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw', | |
5236 | 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', | |
5237 | 'title': 'Uploads from Royalty Free Music - Topic', | |
5238 | 'uploader': 'Royalty Free Music - Topic', | |
5239 | 'modified_date': r're:\d{8}', | |
5240 | 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', | |
5241 | 'description': '', | |
5242 | 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
5243 | 'tags': [], | |
5244 | 'channel': 'Royalty Free Music - Topic', | |
5245 | 'view_count': int, | |
5246 | 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
5247 | }, | |
5248 | 'expected_warnings': [ | |
5249 | 'does not have a videos tab', | |
5250 | r'[Uu]navailable videos (are|will be) hidden', | |
5251 | ], | |
5252 | 'playlist_mincount': 101, | |
5253 | 'params': { | |
5254 | 'skip_download': True, | |
5255 | 'extractor_args': {'youtubetab': {'skip': ['webpage']}} | |
5256 | }, | |
5257 | }, { | |
5258 | 'note': 'non-standard redirect to regional channel', | |
5259 | 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ', | |
5260 | 'only_matching': True | |
5261 | }, { | |
5262 | 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")', | |
5263 | 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6', | |
5264 | 'info_dict': { | |
5265 | 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6', | |
5266 | 'modified_date': '20220407', | |
5267 | 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q', | |
5268 | 'tags': [], | |
5269 | 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q', | |
5270 | 'uploader': 'pukkandan', | |
5271 | 'availability': 'unlisted', | |
5272 | 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q', | |
5273 | 'channel': 'pukkandan', | |
5274 | 'description': 'Test for collaborative playlist', | |
5275 | 'title': 'yt-dlp test - collaborative playlist', | |
5276 | 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q', | |
5277 | }, | |
5278 | 'playlist_mincount': 2 | |
5279 | }] | |
5280 | ||
5281 | @classmethod | |
5282 | def suitable(cls, url): | |
5283 | return False if YoutubeIE.suitable(url) else super().suitable(url) | |
5284 | ||
5285 | _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$') | |
5286 | ||
5287 | @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data | |
5288 | def _real_extract(self, url, smuggled_data): | |
5289 | item_id = self._match_id(url) | |
5290 | url = compat_urlparse.urlunparse( | |
5291 | compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com')) | |
5292 | compat_opts = self.get_param('compat_opts', []) | |
5293 | ||
5294 | def get_mobj(url): | |
5295 | mobj = self._URL_RE.match(url).groupdict() | |
5296 | mobj.update((k, '') for k, v in mobj.items() if v is None) | |
5297 | return mobj | |
5298 | ||
5299 | mobj, redirect_warning = get_mobj(url), None | |
5300 | # Youtube returns incomplete data if tabname is not lower case | |
5301 | pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel'] | |
5302 | if is_channel: | |
5303 | if smuggled_data.get('is_music_url'): | |
5304 | if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist | |
5305 | item_id = item_id[2:] | |
5306 | pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False | |
5307 | elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist | |
5308 | mdata = self._extract_tab_endpoint( | |
5309 | f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music') | |
5310 | murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'), | |
5311 | get_all=False, expected_type=compat_str) | |
5312 | if not murl: | |
5313 | raise ExtractorError('Failed to resolve album to playlist') | |
5314 | return self.url_result(murl, ie=YoutubeTabIE.ie_key()) | |
5315 | elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/ | |
5316 | pre = f'https://www.youtube.com/channel/{item_id}' | |
5317 | ||
5318 | original_tab_name = tab | |
5319 | if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts: | |
5320 | # Home URLs should redirect to /videos/ | |
5321 | redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. ' | |
5322 | 'To download only the videos in the home page, add a "/featured" to the URL') | |
5323 | tab = '/videos' | |
5324 | ||
5325 | url = ''.join((pre, tab, post)) | |
5326 | mobj = get_mobj(url) | |
5327 | ||
5328 | # Handle both video/playlist URLs | |
5329 | qs = parse_qs(url) | |
5330 | video_id, playlist_id = (qs.get(key, [None])[0] for key in ('v', 'list')) | |
5331 | ||
5332 | if not video_id and mobj['not_channel'].startswith('watch'): | |
5333 | if not playlist_id: | |
5334 | # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable | |
5335 | raise ExtractorError('Unable to recognize tab page') | |
5336 | # Common mistake: https://www.youtube.com/watch?list=playlist_id | |
5337 | self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}') | |
5338 | url = f'https://www.youtube.com/playlist?list={playlist_id}' | |
5339 | mobj = get_mobj(url) | |
5340 | ||
5341 | if video_id and playlist_id: | |
5342 | if self.get_param('noplaylist'): | |
5343 | self.to_screen(f'Downloading just video {video_id} because of --no-playlist') | |
5344 | return self.url_result(f'https://www.youtube.com/watch?v={video_id}', | |
5345 | ie=YoutubeIE.ie_key(), video_id=video_id) | |
5346 | self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}') | |
5347 | ||
5348 | data, ytcfg = self._extract_data(url, item_id) | |
5349 | ||
5350 | # YouTube may provide a non-standard redirect to the regional channel | |
5351 | # See: https://github.com/yt-dlp/yt-dlp/issues/2694 | |
5352 | redirect_url = traverse_obj( | |
5353 | data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False) | |
5354 | if redirect_url and 'no-youtube-channel-redirect' not in compat_opts: | |
5355 | redirect_url = ''.join(( | |
5356 | urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post'])) | |
5357 | self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}') | |
5358 | return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key()) | |
5359 | ||
5360 | tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list) | |
5361 | if tabs: | |
5362 | selected_tab = self._extract_selected_tab(tabs) | |
5363 | selected_tab_name = selected_tab.get('title', '').lower() | |
5364 | if selected_tab_name == 'home': | |
5365 | selected_tab_name = 'featured' | |
5366 | requested_tab_name = mobj['tab'][1:] | |
5367 | if 'no-youtube-channel-redirect' not in compat_opts: | |
5368 | if requested_tab_name == 'live': | |
5369 | # Live tab should have redirected to the video | |
5370 | raise ExtractorError('The channel is not currently live', expected=True) | |
5371 | if requested_tab_name not in ('', selected_tab_name): | |
5372 | redirect_warning = f'The channel does not have a {requested_tab_name} tab' | |
5373 | if not original_tab_name: | |
5374 | if item_id[:2] == 'UC': | |
5375 | # Topic channels don't have /videos. Use the equivalent playlist instead | |
5376 | pl_id = f'UU{item_id[2:]}' | |
5377 | pl_url = f'https://www.youtube.com/playlist?list={pl_id}' | |
5378 | try: | |
5379 | data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True) | |
5380 | except ExtractorError: | |
5381 | redirect_warning += ' and the playlist redirect gave error' | |
5382 | else: | |
5383 | item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name | |
5384 | redirect_warning += f'. Redirecting to playlist {pl_id} instead' | |
5385 | if selected_tab_name and selected_tab_name != requested_tab_name: | |
5386 | redirect_warning += f'. {selected_tab_name} tab is being downloaded instead' | |
5387 | else: | |
5388 | raise ExtractorError(redirect_warning, expected=True) | |
5389 | ||
5390 | if redirect_warning: | |
5391 | self.to_screen(redirect_warning) | |
5392 | self.write_debug(f'Final URL: {url}') | |
5393 | ||
5394 | # YouTube sometimes provides a button to reload playlist with unavailable videos. | |
5395 | if 'no-youtube-unavailable-videos' not in compat_opts: | |
5396 | data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data | |
5397 | self._extract_and_report_alerts(data, only_once=True) | |
5398 | tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list) | |
5399 | if tabs: | |
5400 | return self._extract_from_tabs(item_id, ytcfg, data, tabs) | |
5401 | ||
5402 | playlist = traverse_obj( | |
5403 | data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict) | |
5404 | if playlist: | |
5405 | return self._extract_from_playlist(item_id, url, data, playlist, ytcfg) | |
5406 | ||
5407 | video_id = traverse_obj( | |
5408 | data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id | |
5409 | if video_id: | |
5410 | if mobj['tab'] != '/live': # live tab is expected to redirect to video | |
5411 | self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}') | |
5412 | return self.url_result(f'https://www.youtube.com/watch?v={video_id}', | |
5413 | ie=YoutubeIE.ie_key(), video_id=video_id) | |
5414 | ||
5415 | raise ExtractorError('Unable to recognize tab page') | |
5416 | ||
5417 | ||
5418 | class YoutubePlaylistIE(InfoExtractor): | |
5419 | IE_DESC = 'YouTube playlists' | |
5420 | _VALID_URL = r'''(?x)(?: | |
5421 | (?:https?://)? | |
5422 | (?:\w+\.)? | |
5423 | (?: | |
5424 | (?: | |
5425 | youtube(?:kids)?\.com| | |
5426 | %(invidious)s | |
5427 | ) | |
5428 | /.*?\?.*?\blist= | |
5429 | )? | |
5430 | (?P<id>%(playlist_id)s) | |
5431 | )''' % { | |
5432 | 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE, | |
5433 | 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), | |
5434 | } | |
5435 | IE_NAME = 'youtube:playlist' | |
5436 | _TESTS = [{ | |
5437 | 'note': 'issue #673', | |
5438 | 'url': 'PLBB231211A4F62143', | |
5439 | 'info_dict': { | |
5440 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', | |
5441 | 'id': 'PLBB231211A4F62143', | |
5442 | 'uploader': 'Wickman', | |
5443 | 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q', | |
5444 | 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2', | |
5445 | 'view_count': int, | |
5446 | 'uploader_url': 'https://www.youtube.com/user/Wickydoo', | |
5447 | 'modified_date': r're:\d{8}', | |
5448 | 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q', | |
5449 | 'channel': 'Wickman', | |
5450 | 'tags': [], | |
5451 | 'channel_url': 'https://www.youtube.com/user/Wickydoo', | |
5452 | }, | |
5453 | 'playlist_mincount': 29, | |
5454 | }, { | |
5455 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
5456 | 'info_dict': { | |
5457 | 'title': 'YDL_safe_search', | |
5458 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
5459 | }, | |
5460 | 'playlist_count': 2, | |
5461 | 'skip': 'This playlist is private', | |
5462 | }, { | |
5463 | 'note': 'embedded', | |
5464 | 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
5465 | 'playlist_count': 4, | |
5466 | 'info_dict': { | |
5467 | 'title': 'JODA15', | |
5468 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
5469 | 'uploader': 'milan', | |
5470 | 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw', | |
5471 | 'description': '', | |
5472 | 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw', | |
5473 | 'tags': [], | |
5474 | 'modified_date': '20140919', | |
5475 | 'view_count': int, | |
5476 | 'channel': 'milan', | |
5477 | 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw', | |
5478 | 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw', | |
5479 | }, | |
5480 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], | |
5481 | }, { | |
5482 | 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
5483 | 'playlist_mincount': 654, | |
5484 | 'info_dict': { | |
5485 | 'title': '2018 Chinese New Singles (11/6 updated)', | |
5486 | 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
5487 | 'uploader': 'LBK', | |
5488 | 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA', | |
5489 | 'description': 'md5:da521864744d60a198e3a88af4db0d9d', | |
5490 | 'channel': 'LBK', | |
5491 | 'view_count': int, | |
5492 | 'channel_url': 'https://www.youtube.com/c/愛低音的國王', | |
5493 | 'tags': [], | |
5494 | 'uploader_url': 'https://www.youtube.com/c/愛低音的國王', | |
5495 | 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA', | |
5496 | 'modified_date': r're:\d{8}', | |
5497 | }, | |
5498 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], | |
5499 | }, { | |
5500 | 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', | |
5501 | 'only_matching': True, | |
5502 | }, { | |
5503 | # music album playlist | |
5504 | 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', | |
5505 | 'only_matching': True, | |
5506 | }] | |
5507 | ||
5508 | @classmethod | |
5509 | def suitable(cls, url): | |
5510 | if YoutubeTabIE.suitable(url): | |
5511 | return False | |
5512 | from ..utils import parse_qs | |
5513 | qs = parse_qs(url) | |
5514 | if qs.get('v', [None])[0]: | |
5515 | return False | |
5516 | return super().suitable(url) | |
5517 | ||
5518 | def _real_extract(self, url): | |
5519 | playlist_id = self._match_id(url) | |
5520 | is_music_url = YoutubeBaseInfoExtractor.is_music_url(url) | |
5521 | url = update_url_query( | |
5522 | 'https://www.youtube.com/playlist', | |
5523 | parse_qs(url) or {'list': playlist_id}) | |
5524 | if is_music_url: | |
5525 | url = smuggle_url(url, {'is_music_url': True}) | |
5526 | return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
5527 | ||
5528 | ||
5529 | class YoutubeYtBeIE(InfoExtractor): | |
5530 | IE_DESC = 'youtu.be' | |
5531 | _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} | |
5532 | _TESTS = [{ | |
5533 | 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', | |
5534 | 'info_dict': { | |
5535 | 'id': 'yeWKywCrFtk', | |
5536 | 'ext': 'mp4', | |
5537 | 'title': 'Small Scale Baler and Braiding Rugs', | |
5538 | 'uploader': 'Backus-Page House Museum', | |
5539 | 'uploader_id': 'backuspagemuseum', | |
5540 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum', | |
5541 | 'upload_date': '20161008', | |
5542 | 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', | |
5543 | 'categories': ['Nonprofits & Activism'], | |
5544 | 'tags': list, | |
5545 | 'like_count': int, | |
5546 | 'age_limit': 0, | |
5547 | 'playable_in_embed': True, | |
5548 | 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp', | |
5549 | 'channel': 'Backus-Page House Museum', | |
5550 | 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw', | |
5551 | 'live_status': 'not_live', | |
5552 | 'view_count': int, | |
5553 | 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw', | |
5554 | 'availability': 'public', | |
5555 | 'duration': 59, | |
5556 | }, | |
5557 | 'params': { | |
5558 | 'noplaylist': True, | |
5559 | 'skip_download': True, | |
5560 | }, | |
5561 | }, { | |
5562 | 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', | |
5563 | 'only_matching': True, | |
5564 | }] | |
5565 | ||
5566 | def _real_extract(self, url): | |
5567 | mobj = self._match_valid_url(url) | |
5568 | video_id = mobj.group('id') | |
5569 | playlist_id = mobj.group('playlist_id') | |
5570 | return self.url_result( | |
5571 | update_url_query('https://www.youtube.com/watch', { | |
5572 | 'v': video_id, | |
5573 | 'list': playlist_id, | |
5574 | 'feature': 'youtu.be', | |
5575 | }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
5576 | ||
5577 | ||
5578 | class YoutubeLivestreamEmbedIE(InfoExtractor): | |
5579 | IE_DESC = 'YouTube livestream embeds' | |
5580 | _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)' | |
5581 | _TESTS = [{ | |
5582 | 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA', | |
5583 | 'only_matching': True, | |
5584 | }] | |
5585 | ||
5586 | def _real_extract(self, url): | |
5587 | channel_id = self._match_id(url) | |
5588 | return self.url_result( | |
5589 | f'https://www.youtube.com/channel/{channel_id}/live', | |
5590 | ie=YoutubeTabIE.ie_key(), video_id=channel_id) | |
5591 | ||
5592 | ||
5593 | class YoutubeYtUserIE(InfoExtractor): | |
5594 | IE_DESC = 'YouTube user videos; "ytuser:" prefix' | |
5595 | IE_NAME = 'youtube:user' | |
5596 | _VALID_URL = r'ytuser:(?P<id>.+)' | |
5597 | _TESTS = [{ | |
5598 | 'url': 'ytuser:phihag', | |
5599 | 'only_matching': True, | |
5600 | }] | |
5601 | ||
5602 | def _real_extract(self, url): | |
5603 | user_id = self._match_id(url) | |
5604 | return self.url_result( | |
5605 | 'https://www.youtube.com/user/%s/videos' % user_id, | |
5606 | ie=YoutubeTabIE.ie_key(), video_id=user_id) | |
5607 | ||
5608 | ||
5609 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): | |
5610 | IE_NAME = 'youtube:favorites' | |
5611 | IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)' | |
5612 | _VALID_URL = r':ytfav(?:ou?rite)?s?' | |
5613 | _LOGIN_REQUIRED = True | |
5614 | _TESTS = [{ | |
5615 | 'url': ':ytfav', | |
5616 | 'only_matching': True, | |
5617 | }, { | |
5618 | 'url': ':ytfavorites', | |
5619 | 'only_matching': True, | |
5620 | }] | |
5621 | ||
5622 | def _real_extract(self, url): | |
5623 | return self.url_result( | |
5624 | 'https://www.youtube.com/playlist?list=LL', | |
5625 | ie=YoutubeTabIE.ie_key()) | |
5626 | ||
5627 | ||
5628 | class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor): | |
5629 | IE_NAME = 'youtube:notif' | |
5630 | IE_DESC = 'YouTube notifications; ":ytnotif" keyword (requires cookies)' | |
5631 | _VALID_URL = r':ytnotif(?:ication)?s?' | |
5632 | _LOGIN_REQUIRED = True | |
5633 | _TESTS = [{ | |
5634 | 'url': ':ytnotif', | |
5635 | 'only_matching': True, | |
5636 | }, { | |
5637 | 'url': ':ytnotifications', | |
5638 | 'only_matching': True, | |
5639 | }] | |
5640 | ||
5641 | def _extract_notification_menu(self, response, continuation_list): | |
5642 | notification_list = traverse_obj( | |
5643 | response, | |
5644 | ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'), | |
5645 | ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'), | |
5646 | expected_type=list) or [] | |
5647 | continuation_list[0] = None | |
5648 | for item in notification_list: | |
5649 | entry = self._extract_notification_renderer(item.get('notificationRenderer')) | |
5650 | if entry: | |
5651 | yield entry | |
5652 | continuation = item.get('continuationItemRenderer') | |
5653 | if continuation: | |
5654 | continuation_list[0] = continuation | |
5655 | ||
5656 | def _extract_notification_renderer(self, notification): | |
5657 | video_id = traverse_obj( | |
5658 | notification, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) | |
5659 | url = f'https://www.youtube.com/watch?v={video_id}' | |
5660 | channel_id = None | |
5661 | if not video_id: | |
5662 | browse_ep = traverse_obj( | |
5663 | notification, ('navigationEndpoint', 'browseEndpoint'), expected_type=dict) | |
5664 | channel_id = traverse_obj(browse_ep, 'browseId', expected_type=str) | |
5665 | post_id = self._search_regex( | |
5666 | r'/post/(.+)', traverse_obj(browse_ep, 'canonicalBaseUrl', expected_type=str), | |
5667 | 'post id', default=None) | |
5668 | if not channel_id or not post_id: | |
5669 | return | |
5670 | # The direct /post url redirects to this in the browser | |
5671 | url = f'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}' | |
5672 | ||
5673 | channel = traverse_obj( | |
5674 | notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'), | |
5675 | expected_type=str) | |
5676 | notification_title = self._get_text(notification, 'shortMessage') | |
5677 | if notification_title: | |
5678 | notification_title = notification_title.replace('\xad', '') # remove soft hyphens | |
5679 | # TODO: handle recommended videos | |
5680 | title = self._search_regex( | |
5681 | rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title, | |
5682 | 'video title', default=None) | |
5683 | upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d') | |
5684 | if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key()) | |
5685 | else None) | |
5686 | return { | |
5687 | '_type': 'url', | |
5688 | 'url': url, | |
5689 | 'ie_key': (YoutubeIE if video_id else YoutubeTabIE).ie_key(), | |
5690 | 'video_id': video_id, | |
5691 | 'title': title, | |
5692 | 'channel_id': channel_id, | |
5693 | 'channel': channel, | |
5694 | 'thumbnails': self._extract_thumbnails(notification, 'videoThumbnail'), | |
5695 | 'upload_date': upload_date, | |
5696 | } | |
5697 | ||
5698 | def _notification_menu_entries(self, ytcfg): | |
5699 | continuation_list = [None] | |
5700 | response = None | |
5701 | for page in itertools.count(1): | |
5702 | ctoken = traverse_obj( | |
5703 | continuation_list, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type=str) | |
5704 | response = self._extract_response( | |
5705 | item_id=f'page {page}', query={'ctoken': ctoken} if ctoken else {}, ytcfg=ytcfg, | |
5706 | ep='notification/get_notification_menu', check_get_keys='actions', | |
5707 | headers=self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))) | |
5708 | yield from self._extract_notification_menu(response, continuation_list) | |
5709 | if not continuation_list[0]: | |
5710 | break | |
5711 | ||
5712 | def _real_extract(self, url): | |
5713 | display_id = 'notifications' | |
5714 | ytcfg = self._download_ytcfg('web', display_id) if not self.skip_webpage else {} | |
5715 | self._report_playlist_authcheck(ytcfg) | |
5716 | return self.playlist_result(self._notification_menu_entries(ytcfg), display_id, display_id) | |
5717 | ||
5718 | ||
5719 | class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor): | |
5720 | IE_DESC = 'YouTube search' | |
5721 | IE_NAME = 'youtube:search' | |
5722 | _SEARCH_KEY = 'ytsearch' | |
5723 | _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only | |
5724 | _TESTS = [{ | |
5725 | 'url': 'ytsearch5:youtube-dl test video', | |
5726 | 'playlist_count': 5, | |
5727 | 'info_dict': { | |
5728 | 'id': 'youtube-dl test video', | |
5729 | 'title': 'youtube-dl test video', | |
5730 | } | |
5731 | }] | |
5732 | ||
5733 | ||
5734 | class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor): | |
5735 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' | |
5736 | _SEARCH_KEY = 'ytsearchdate' | |
5737 | IE_DESC = 'YouTube search, newest videos first' | |
5738 | _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date | |
5739 | _TESTS = [{ | |
5740 | 'url': 'ytsearchdate5:youtube-dl test video', | |
5741 | 'playlist_count': 5, | |
5742 | 'info_dict': { | |
5743 | 'id': 'youtube-dl test video', | |
5744 | 'title': 'youtube-dl test video', | |
5745 | } | |
5746 | }] | |
5747 | ||
5748 | ||
5749 | class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor): | |
5750 | IE_DESC = 'YouTube search URLs with sorting and filter support' | |
5751 | IE_NAME = YoutubeSearchIE.IE_NAME + '_url' | |
5752 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)' | |
5753 | _TESTS = [{ | |
5754 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
5755 | 'playlist_mincount': 5, | |
5756 | 'info_dict': { | |
5757 | 'id': 'youtube-dl test video', | |
5758 | 'title': 'youtube-dl test video', | |
5759 | } | |
5760 | }, { | |
5761 | 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D', | |
5762 | 'playlist_mincount': 5, | |
5763 | 'info_dict': { | |
5764 | 'id': 'python', | |
5765 | 'title': 'python', | |
5766 | } | |
5767 | }, { | |
5768 | 'url': 'https://www.youtube.com/results?search_query=%23cats', | |
5769 | 'playlist_mincount': 1, | |
5770 | 'info_dict': { | |
5771 | 'id': '#cats', | |
5772 | 'title': '#cats', | |
5773 | 'entries': [{ | |
5774 | 'url': r're:https://(www\.)?youtube\.com/hashtag/cats', | |
5775 | 'title': '#cats', | |
5776 | }], | |
5777 | }, | |
5778 | }, { | |
5779 | 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB', | |
5780 | 'only_matching': True, | |
5781 | }] | |
5782 | ||
5783 | def _real_extract(self, url): | |
5784 | qs = parse_qs(url) | |
5785 | query = (qs.get('search_query') or qs.get('q'))[0] | |
5786 | return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query) | |
5787 | ||
5788 | ||
5789 | class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor): | |
5790 | IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)' | |
5791 | IE_NAME = 'youtube:music:search_url' | |
5792 | _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)' | |
5793 | _TESTS = [{ | |
5794 | 'url': 'https://music.youtube.com/search?q=royalty+free+music', | |
5795 | 'playlist_count': 16, | |
5796 | 'info_dict': { | |
5797 | 'id': 'royalty free music', | |
5798 | 'title': 'royalty free music', | |
5799 | } | |
5800 | }, { | |
5801 | 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D', | |
5802 | 'playlist_mincount': 30, | |
5803 | 'info_dict': { | |
5804 | 'id': 'royalty free music - songs', | |
5805 | 'title': 'royalty free music - songs', | |
5806 | }, | |
5807 | 'params': {'extract_flat': 'in_playlist'} | |
5808 | }, { | |
5809 | 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists', | |
5810 | 'playlist_mincount': 30, | |
5811 | 'info_dict': { | |
5812 | 'id': 'royalty free music - community playlists', | |
5813 | 'title': 'royalty free music - community playlists', | |
5814 | }, | |
5815 | 'params': {'extract_flat': 'in_playlist'} | |
5816 | }] | |
5817 | ||
5818 | _SECTIONS = { | |
5819 | 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==', | |
5820 | 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==', | |
5821 | 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF', | |
5822 | 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==', | |
5823 | 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==', | |
5824 | 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==', | |
5825 | } | |
5826 | ||
5827 | def _real_extract(self, url): | |
5828 | qs = parse_qs(url) | |
5829 | query = (qs.get('search_query') or qs.get('q'))[0] | |
5830 | params = qs.get('sp', (None,))[0] | |
5831 | if params: | |
5832 | section = next((k for k, v in self._SECTIONS.items() if v == params), params) | |
5833 | else: | |
5834 | section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower() | |
5835 | params = self._SECTIONS.get(section) | |
5836 | if not params: | |
5837 | section = None | |
5838 | title = join_nonempty(query, section, delim=' - ') | |
5839 | return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title) | |
5840 | ||
5841 | ||
5842 | class YoutubeFeedsInfoExtractor(InfoExtractor): | |
5843 | """ | |
5844 | Base class for feed extractors | |
5845 | Subclasses must re-define the _FEED_NAME property. | |
5846 | """ | |
5847 | _LOGIN_REQUIRED = True | |
5848 | _FEED_NAME = 'feeds' | |
5849 | ||
5850 | def _real_initialize(self): | |
5851 | YoutubeBaseInfoExtractor._check_login_required(self) | |
5852 | ||
5853 | @classproperty | |
5854 | def IE_NAME(self): | |
5855 | return f'youtube:{self._FEED_NAME}' | |
5856 | ||
5857 | def _real_extract(self, url): | |
5858 | return self.url_result( | |
5859 | f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key()) | |
5860 | ||
5861 | ||
5862 | class YoutubeWatchLaterIE(InfoExtractor): | |
5863 | IE_NAME = 'youtube:watchlater' | |
5864 | IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)' | |
5865 | _VALID_URL = r':ytwatchlater' | |
5866 | _TESTS = [{ | |
5867 | 'url': ':ytwatchlater', | |
5868 | 'only_matching': True, | |
5869 | }] | |
5870 | ||
5871 | def _real_extract(self, url): | |
5872 | return self.url_result( | |
5873 | 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key()) | |
5874 | ||
5875 | ||
5876 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): | |
5877 | IE_DESC = 'YouTube recommended videos; ":ytrec" keyword' | |
5878 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?' | |
5879 | _FEED_NAME = 'recommended' | |
5880 | _LOGIN_REQUIRED = False | |
5881 | _TESTS = [{ | |
5882 | 'url': ':ytrec', | |
5883 | 'only_matching': True, | |
5884 | }, { | |
5885 | 'url': ':ytrecommended', | |
5886 | 'only_matching': True, | |
5887 | }, { | |
5888 | 'url': 'https://youtube.com', | |
5889 | 'only_matching': True, | |
5890 | }] | |
5891 | ||
5892 | ||
5893 | class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): | |
5894 | IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)' | |
5895 | _VALID_URL = r':ytsub(?:scription)?s?' | |
5896 | _FEED_NAME = 'subscriptions' | |
5897 | _TESTS = [{ | |
5898 | 'url': ':ytsubs', | |
5899 | 'only_matching': True, | |
5900 | }, { | |
5901 | 'url': ':ytsubscriptions', | |
5902 | 'only_matching': True, | |
5903 | }] | |
5904 | ||
5905 | ||
5906 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): | |
5907 | IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)' | |
5908 | _VALID_URL = r':ythis(?:tory)?' | |
5909 | _FEED_NAME = 'history' | |
5910 | _TESTS = [{ | |
5911 | 'url': ':ythistory', | |
5912 | 'only_matching': True, | |
5913 | }] | |
5914 | ||
5915 | ||
5916 | class YoutubeStoriesIE(InfoExtractor): | |
5917 | IE_DESC = 'YouTube channel stories; "ytstories:" prefix' | |
5918 | IE_NAME = 'youtube:stories' | |
5919 | _VALID_URL = r'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$' | |
5920 | _TESTS = [{ | |
5921 | 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg', | |
5922 | 'only_matching': True, | |
5923 | }] | |
5924 | ||
5925 | def _real_extract(self, url): | |
5926 | playlist_id = f'RLTD{self._match_id(url)}' | |
5927 | return self.url_result( | |
5928 | f'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', | |
5929 | ie=YoutubeTabIE, video_id=playlist_id) | |
5930 | ||
5931 | ||
5932 | class YoutubeTruncatedURLIE(InfoExtractor): | |
5933 | IE_NAME = 'youtube:truncated_url' | |
5934 | IE_DESC = False # Do not list | |
5935 | _VALID_URL = r'''(?x) | |
5936 | (?:https?://)? | |
5937 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
5938 | (?:watch\?(?: | |
5939 | feature=[a-z_]+| | |
5940 | annotation_id=annotation_[^&]+| | |
5941 | x-yt-cl=[0-9]+| | |
5942 | hl=[^&]*| | |
5943 | t=[0-9]+ | |
5944 | )? | |
5945 | | | |
5946 | attribution_link\?a=[^&]+ | |
5947 | ) | |
5948 | $ | |
5949 | ''' | |
5950 | ||
5951 | _TESTS = [{ | |
5952 | 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041', | |
5953 | 'only_matching': True, | |
5954 | }, { | |
5955 | 'url': 'https://www.youtube.com/watch?', | |
5956 | 'only_matching': True, | |
5957 | }, { | |
5958 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
5959 | 'only_matching': True, | |
5960 | }, { | |
5961 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
5962 | 'only_matching': True, | |
5963 | }, { | |
5964 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
5965 | 'only_matching': True, | |
5966 | }, { | |
5967 | 'url': 'https://www.youtube.com/watch?t=2372', | |
5968 | 'only_matching': True, | |
5969 | }] | |
5970 | ||
5971 | def _real_extract(self, url): | |
5972 | raise ExtractorError( | |
5973 | 'Did you forget to quote the URL? Remember that & is a meta ' | |
5974 | 'character in most shells, so you want to put the URL in quotes, ' | |
5975 | 'like youtube-dl ' | |
5976 | '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' | |
5977 | ' or simply youtube-dl BaW_jenozKc .', | |
5978 | expected=True) | |
5979 | ||
5980 | ||
5981 | class YoutubeClipIE(YoutubeTabBaseInfoExtractor): | |
5982 | IE_NAME = 'youtube:clip' | |
5983 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)' | |
5984 | _TESTS = [{ | |
5985 | # FIXME: Other metadata should be extracted from the clip, not from the base video | |
5986 | 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ', | |
5987 | 'info_dict': { | |
5988 | 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ', | |
5989 | 'ext': 'mp4', | |
5990 | 'section_start': 29.0, | |
5991 | 'section_end': 39.7, | |
5992 | 'duration': 10.7, | |
5993 | } | |
5994 | }] | |
5995 | ||
5996 | def _real_extract(self, url): | |
5997 | clip_id = self._match_id(url) | |
5998 | _, data = self._extract_webpage(url, clip_id) | |
5999 | ||
6000 | video_id = traverse_obj(data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId')) | |
6001 | if not video_id: | |
6002 | raise ExtractorError('Unable to find video ID') | |
6003 | ||
6004 | clip_data = traverse_obj(data, ( | |
6005 | 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer', | |
6006 | 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ..., | |
6007 | 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command', | |
6008 | 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all=False) | |
6009 | ||
6010 | return { | |
6011 | '_type': 'url_transparent', | |
6012 | 'url': f'https://www.youtube.com/watch?v={video_id}', | |
6013 | 'ie_key': YoutubeIE.ie_key(), | |
6014 | 'id': clip_id, | |
6015 | 'section_start': int(clip_data['startTimeMs']) / 1000, | |
6016 | 'section_end': int(clip_data['endTimeMs']) / 1000, | |
6017 | } | |
6018 | ||
6019 | ||
6020 | class YoutubeTruncatedIDIE(InfoExtractor): | |
6021 | IE_NAME = 'youtube:truncated_id' | |
6022 | IE_DESC = False # Do not list | |
6023 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' | |
6024 | ||
6025 | _TESTS = [{ | |
6026 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
6027 | 'only_matching': True, | |
6028 | }] | |
6029 | ||
6030 | def _real_extract(self, url): | |
6031 | video_id = self._match_id(url) | |
6032 | raise ExtractorError( | |
6033 | f'Incomplete YouTube ID {video_id}. URL {url} looks truncated.', | |
6034 | expected=True) |