]>
Commit | Line | Data |
---|---|---|
c5e8d7af | 1 | # coding: utf-8 |
c5e8d7af | 2 | |
78caa52a PH |
3 | from __future__ import unicode_literals |
4 | ||
d92f5d5a | 5 | import calendar |
109dd3b2 | 6 | import copy |
fe93e2c4 | 7 | import datetime |
adbc4ec4 | 8 | import functools |
a5c56234 | 9 | import hashlib |
0ca96d48 | 10 | import itertools |
c5e8d7af | 11 | import json |
720c3099 | 12 | import math |
c4417ddb | 13 | import os.path |
d77ab8e2 | 14 | import random |
c5e8d7af | 15 | import re |
46383212 | 16 | import sys |
8a784c74 | 17 | import time |
e0df6211 | 18 | import traceback |
adbc4ec4 | 19 | import threading |
c5e8d7af | 20 | |
b05654f0 | 21 | from .common import InfoExtractor, SearchInfoExtractor |
4bb4a188 | 22 | from ..compat import ( |
edf3e38e | 23 | compat_chr, |
29f7c58a | 24 | compat_HTTPError, |
c5e8d7af | 25 | compat_parse_qs, |
545cc85d | 26 | compat_str, |
7fd002c0 | 27 | compat_urllib_parse_unquote_plus, |
15707c7e | 28 | compat_urllib_parse_urlencode, |
7c80519c | 29 | compat_urllib_parse_urlparse, |
7c61bd36 | 30 | compat_urlparse, |
4bb4a188 | 31 | ) |
545cc85d | 32 | from ..jsinterp import JSInterpreter |
4bb4a188 | 33 | from ..utils import ( |
720c3099 | 34 | bug_reports_message, |
c5e8d7af | 35 | clean_html, |
d92f5d5a | 36 | datetime_from_str, |
11f9be09 | 37 | dict_get, |
358de58c | 38 | error_to_compat_str, |
c5e8d7af | 39 | ExtractorError, |
2d30521a | 40 | float_or_none, |
11f9be09 | 41 | format_field, |
dd27fd17 | 42 | int_or_none, |
641ad5d8 | 43 | is_html, |
34921b43 | 44 | join_nonempty, |
48416bc4 | 45 | js_to_json, |
94278f72 | 46 | mimetype2ext, |
9c0d7f49 | 47 | network_exceptions, |
a6213a49 | 48 | NO_DEFAULT, |
11f9be09 | 49 | orderedSet, |
6310acf5 | 50 | parse_codecs, |
49bd8c66 | 51 | parse_count, |
7c80519c | 52 | parse_duration, |
7ea65411 | 53 | parse_iso8601, |
4dfbf869 | 54 | parse_qs, |
dca3ff4a | 55 | qualities, |
c0ac49bc | 56 | remove_end, |
3995d37d | 57 | remove_start, |
cf7e015f | 58 | smuggle_url, |
dbdaaa23 | 59 | str_or_none, |
c93d53f5 | 60 | str_to_int, |
f3aa3c3f | 61 | strftime_or_none, |
7c365c21 | 62 | traverse_obj, |
556dbe7f | 63 | try_get, |
c5e8d7af PH |
64 | unescapeHTML, |
65 | unified_strdate, | |
f0d785d3 | 66 | unified_timestamp, |
cf7e015f | 67 | unsmuggle_url, |
8bdd16b4 | 68 | update_url_query, |
21c340b8 | 69 | url_or_none, |
fe93e2c4 | 70 | urljoin, |
7c365c21 | 71 | variadic, |
c5e8d7af PH |
72 | ) |
73 | ||
5f6a1245 | 74 | |
720c3099 | 75 | def get_first(obj, keys, **kwargs): |
76 | return traverse_obj(obj, (..., *variadic(keys)), **kwargs, get_all=False) | |
77 | ||
78 | ||
000c15a4 | 79 | # any clients starting with _ cannot be explicity requested by the user |
80 | INNERTUBE_CLIENTS = { | |
81 | 'web': { | |
82 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
83 | 'INNERTUBE_CONTEXT': { | |
84 | 'client': { | |
85 | 'clientName': 'WEB', | |
18c7683d | 86 | 'clientVersion': '2.20211221.00.00', |
000c15a4 | 87 | } |
88 | }, | |
89 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 1 | |
90 | }, | |
91 | 'web_embedded': { | |
92 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
93 | 'INNERTUBE_CONTEXT': { | |
94 | 'client': { | |
95 | 'clientName': 'WEB_EMBEDDED_PLAYER', | |
18c7683d | 96 | 'clientVersion': '1.20211215.00.01', |
000c15a4 | 97 | }, |
98 | }, | |
99 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 56 | |
100 | }, | |
101 | 'web_music': { | |
102 | 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30', | |
103 | 'INNERTUBE_HOST': 'music.youtube.com', | |
104 | 'INNERTUBE_CONTEXT': { | |
105 | 'client': { | |
106 | 'clientName': 'WEB_REMIX', | |
18c7683d | 107 | 'clientVersion': '1.20211213.00.00', |
000c15a4 | 108 | } |
109 | }, | |
110 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 67, | |
111 | }, | |
e7e94f2a | 112 | 'web_creator': { |
18c7683d | 113 | 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo', |
e7e94f2a D |
114 | 'INNERTUBE_CONTEXT': { |
115 | 'client': { | |
116 | 'clientName': 'WEB_CREATOR', | |
18c7683d | 117 | 'clientVersion': '1.20211220.02.00', |
e7e94f2a D |
118 | } |
119 | }, | |
120 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 62, | |
121 | }, | |
000c15a4 | 122 | 'android': { |
18c7683d | 123 | 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w', |
000c15a4 | 124 | 'INNERTUBE_CONTEXT': { |
125 | 'client': { | |
126 | 'clientName': 'ANDROID', | |
18c7683d | 127 | 'clientVersion': '16.49', |
000c15a4 | 128 | } |
129 | }, | |
130 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 3, | |
b6de707d | 131 | 'REQUIRE_JS_PLAYER': False |
000c15a4 | 132 | }, |
133 | 'android_embedded': { | |
18c7683d | 134 | 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw', |
000c15a4 | 135 | 'INNERTUBE_CONTEXT': { |
136 | 'client': { | |
137 | 'clientName': 'ANDROID_EMBEDDED_PLAYER', | |
18c7683d | 138 | 'clientVersion': '16.49', |
000c15a4 | 139 | }, |
140 | }, | |
b6de707d | 141 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 55, |
142 | 'REQUIRE_JS_PLAYER': False | |
000c15a4 | 143 | }, |
144 | 'android_music': { | |
18c7683d | 145 | 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI', |
000c15a4 | 146 | 'INNERTUBE_CONTEXT': { |
147 | 'client': { | |
148 | 'clientName': 'ANDROID_MUSIC', | |
18c7683d | 149 | 'clientVersion': '4.57', |
000c15a4 | 150 | } |
151 | }, | |
152 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 21, | |
b6de707d | 153 | 'REQUIRE_JS_PLAYER': False |
000c15a4 | 154 | }, |
e7e94f2a | 155 | 'android_creator': { |
18c7683d | 156 | 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8', |
e7e94f2a D |
157 | 'INNERTUBE_CONTEXT': { |
158 | 'client': { | |
159 | 'clientName': 'ANDROID_CREATOR', | |
18c7683d | 160 | 'clientVersion': '21.47', |
e7e94f2a D |
161 | }, |
162 | }, | |
b6de707d | 163 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 14, |
164 | 'REQUIRE_JS_PLAYER': False | |
e7e94f2a | 165 | }, |
18c7683d | 166 | # iOS clients have HLS live streams. Setting device model to get 60fps formats. |
167 | # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558 | |
000c15a4 | 168 | 'ios': { |
18c7683d | 169 | 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc', |
000c15a4 | 170 | 'INNERTUBE_CONTEXT': { |
171 | 'client': { | |
172 | 'clientName': 'IOS', | |
18c7683d | 173 | 'clientVersion': '16.46', |
174 | 'deviceModel': 'iPhone14,3', | |
000c15a4 | 175 | } |
176 | }, | |
b6de707d | 177 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 5, |
178 | 'REQUIRE_JS_PLAYER': False | |
000c15a4 | 179 | }, |
180 | 'ios_embedded': { | |
000c15a4 | 181 | 'INNERTUBE_CONTEXT': { |
182 | 'client': { | |
183 | 'clientName': 'IOS_MESSAGES_EXTENSION', | |
18c7683d | 184 | 'clientVersion': '16.46', |
185 | 'deviceModel': 'iPhone14,3', | |
000c15a4 | 186 | }, |
187 | }, | |
b6de707d | 188 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 66, |
189 | 'REQUIRE_JS_PLAYER': False | |
000c15a4 | 190 | }, |
191 | 'ios_music': { | |
18c7683d | 192 | 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s', |
000c15a4 | 193 | 'INNERTUBE_CONTEXT': { |
194 | 'client': { | |
195 | 'clientName': 'IOS_MUSIC', | |
18c7683d | 196 | 'clientVersion': '4.57', |
000c15a4 | 197 | }, |
198 | }, | |
b6de707d | 199 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 26, |
200 | 'REQUIRE_JS_PLAYER': False | |
000c15a4 | 201 | }, |
e7e94f2a D |
202 | 'ios_creator': { |
203 | 'INNERTUBE_CONTEXT': { | |
204 | 'client': { | |
205 | 'clientName': 'IOS_CREATOR', | |
18c7683d | 206 | 'clientVersion': '21.47', |
e7e94f2a D |
207 | }, |
208 | }, | |
b6de707d | 209 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 15, |
210 | 'REQUIRE_JS_PLAYER': False | |
e7e94f2a | 211 | }, |
3619f78d | 212 | # mweb has 'ultralow' formats |
213 | # See: https://github.com/yt-dlp/yt-dlp/pull/557 | |
000c15a4 | 214 | 'mweb': { |
18c7683d | 215 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', |
000c15a4 | 216 | 'INNERTUBE_CONTEXT': { |
217 | 'client': { | |
218 | 'clientName': 'MWEB', | |
18c7683d | 219 | 'clientVersion': '2.20211221.01.00', |
000c15a4 | 220 | } |
221 | }, | |
222 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 2 | |
18c7683d | 223 | } |
000c15a4 | 224 | } |
225 | ||
226 | ||
227 | def build_innertube_clients(): | |
2e4cacd0 | 228 | THIRD_PARTY = { |
65c2fde2 | 229 | 'embedUrl': 'https://google.com', # Can be any valid URL |
230 | } | |
2e4cacd0 | 231 | BASE_CLIENTS = ('android', 'web', 'ios', 'mweb') |
232 | priority = qualities(BASE_CLIENTS[::-1]) | |
000c15a4 | 233 | |
234 | for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()): | |
eca330cb | 235 | ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8') |
000c15a4 | 236 | ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com') |
b6de707d | 237 | ytcfg.setdefault('REQUIRE_JS_PLAYER', True) |
000c15a4 | 238 | ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en') |
000c15a4 | 239 | |
2e4cacd0 | 240 | base_client, *variant = client.split('_') |
241 | ytcfg['priority'] = 10 * priority(base_client) | |
242 | ||
e48b3875 | 243 | if not variant: |
244 | INNERTUBE_CLIENTS[f'{client}_agegate'] = agegate_ytcfg = copy.deepcopy(ytcfg) | |
000c15a4 | 245 | agegate_ytcfg['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED' |
e48b3875 | 246 | agegate_ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY |
000c15a4 | 247 | agegate_ytcfg['priority'] -= 1 |
e48b3875 | 248 | elif variant == ['embedded']: |
249 | ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY | |
000c15a4 | 250 | ytcfg['priority'] -= 2 |
e48b3875 | 251 | else: |
000c15a4 | 252 | ytcfg['priority'] -= 3 |
253 | ||
254 | ||
255 | build_innertube_clients() | |
256 | ||
257 | ||
de7f3446 | 258 | class YoutubeBaseInfoExtractor(InfoExtractor): |
b2e8bc1b | 259 | """Provide base functions for Youtube extractors""" |
e00eb564 | 260 | |
3462ffa8 | 261 | _RESERVED_NAMES = ( |
3cd786db | 262 | r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|' |
182bda88 | 263 | r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|' |
3619f78d | 264 | r'browse|oembed|get_video_info|iframe_api|s/player|' |
cd7c66cf | 265 | r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout') |
3462ffa8 | 266 | |
3619f78d | 267 | _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)' |
268 | ||
b2e8bc1b | 269 | _NETRC_MACHINE = 'youtube' |
3619f78d | 270 | |
b2e8bc1b JMF |
271 | # If True it will raise an error if no login info is provided |
272 | _LOGIN_REQUIRED = False | |
273 | ||
d9190e44 RH |
274 | _INVIDIOUS_SITES = ( |
275 | # invidious-redirect websites | |
276 | r'(?:www\.)?redirect\.invidious\.io', | |
277 | r'(?:(?:www|dev)\.)?invidio\.us', | |
278 | # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md | |
279 | r'(?:www\.)?invidious\.pussthecat\.org', | |
280 | r'(?:www\.)?invidious\.zee\.li', | |
281 | r'(?:www\.)?invidious\.ethibox\.fr', | |
282 | r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion', | |
4c968755 U |
283 | r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion', |
284 | r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion', | |
d9190e44 RH |
285 | # youtube-dl invidious instances list |
286 | r'(?:(?:www|no)\.)?invidiou\.sh', | |
287 | r'(?:(?:www|fi)\.)?invidious\.snopyta\.org', | |
288 | r'(?:www\.)?invidious\.kabi\.tk', | |
289 | r'(?:www\.)?invidious\.mastodon\.host', | |
290 | r'(?:www\.)?invidious\.zapashcanon\.fr', | |
291 | r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks', | |
292 | r'(?:www\.)?invidious\.tinfoil-hat\.net', | |
293 | r'(?:www\.)?invidious\.himiko\.cloud', | |
294 | r'(?:www\.)?invidious\.reallyancient\.tech', | |
295 | r'(?:www\.)?invidious\.tube', | |
296 | r'(?:www\.)?invidiou\.site', | |
297 | r'(?:www\.)?invidious\.site', | |
298 | r'(?:www\.)?invidious\.xyz', | |
299 | r'(?:www\.)?invidious\.nixnet\.xyz', | |
300 | r'(?:www\.)?invidious\.048596\.xyz', | |
301 | r'(?:www\.)?invidious\.drycat\.fr', | |
302 | r'(?:www\.)?inv\.skyn3t\.in', | |
303 | r'(?:www\.)?tube\.poal\.co', | |
304 | r'(?:www\.)?tube\.connect\.cafe', | |
305 | r'(?:www\.)?vid\.wxzm\.sx', | |
306 | r'(?:www\.)?vid\.mint\.lgbt', | |
307 | r'(?:www\.)?vid\.puffyan\.us', | |
308 | r'(?:www\.)?yewtu\.be', | |
309 | r'(?:www\.)?yt\.elukerio\.org', | |
310 | r'(?:www\.)?yt\.lelux\.fi', | |
311 | r'(?:www\.)?invidious\.ggc-project\.de', | |
312 | r'(?:www\.)?yt\.maisputain\.ovh', | |
313 | r'(?:www\.)?ytprivate\.com', | |
314 | r'(?:www\.)?invidious\.13ad\.de', | |
315 | r'(?:www\.)?invidious\.toot\.koeln', | |
316 | r'(?:www\.)?invidious\.fdn\.fr', | |
317 | r'(?:www\.)?watch\.nettohikari\.com', | |
318 | r'(?:www\.)?invidious\.namazso\.eu', | |
319 | r'(?:www\.)?invidious\.silkky\.cloud', | |
320 | r'(?:www\.)?invidious\.exonip\.de', | |
321 | r'(?:www\.)?invidious\.riverside\.rocks', | |
322 | r'(?:www\.)?invidious\.blamefran\.net', | |
323 | r'(?:www\.)?invidious\.moomoo\.de', | |
324 | r'(?:www\.)?ytb\.trom\.tf', | |
325 | r'(?:www\.)?yt\.cyberhost\.uk', | |
326 | r'(?:www\.)?kgg2m7yk5aybusll\.onion', | |
327 | r'(?:www\.)?qklhadlycap4cnod\.onion', | |
328 | r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion', | |
329 | r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion', | |
330 | r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion', | |
331 | r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion', | |
332 | r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p', | |
333 | r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion', | |
334 | r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion', | |
335 | r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion', | |
336 | r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion', | |
337 | r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion', | |
338 | ) | |
339 | ||
b2e8bc1b | 340 | def _login(self): |
83317f69 | 341 | """ |
342 | Attempt to log in to YouTube. | |
83317f69 | 343 | If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. |
344 | """ | |
9d5d4d64 | 345 | |
982ee69a MB |
346 | if (self._LOGIN_REQUIRED |
347 | and self.get_param('cookiefile') is None | |
348 | and self.get_param('cookiesfrombrowser') is None): | |
9d5d4d64 | 349 | self.raise_login_required( |
350 | 'Login details are needed to download this content', method='cookies') | |
68217024 | 351 | username, password = self._get_login_info() |
9d5d4d64 | 352 | if username: |
24b0a72b | 353 | self.report_warning(f'Cannot login to YouTube using username and password. {self._LOGIN_HINTS["cookies"]}') |
b2e8bc1b | 354 | |
cce889b9 | 355 | def _initialize_consent(self): |
356 | cookies = self._get_cookies('https://www.youtube.com/') | |
357 | if cookies.get('__Secure-3PSID'): | |
358 | return | |
359 | consent_id = None | |
360 | consent = cookies.get('CONSENT') | |
361 | if consent: | |
362 | if 'YES' in consent.value: | |
363 | return | |
364 | consent_id = self._search_regex( | |
365 | r'PENDING\+(\d+)', consent.value, 'consent', default=None) | |
366 | if not consent_id: | |
367 | consent_id = random.randint(100, 999) | |
368 | self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id) | |
8d81f3e3 | 369 | |
f3aa3c3f | 370 | def _initialize_pref(self): |
371 | cookies = self._get_cookies('https://www.youtube.com/') | |
372 | pref_cookie = cookies.get('PREF') | |
373 | pref = {} | |
374 | if pref_cookie: | |
375 | try: | |
376 | pref = dict(compat_urlparse.parse_qsl(pref_cookie.value)) | |
377 | except ValueError: | |
378 | self.report_warning('Failed to parse user PREF cookie' + bug_reports_message()) | |
396a76f7 | 379 | pref.update({'hl': 'en', 'tz': 'UTC'}) |
f3aa3c3f | 380 | self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref)) |
381 | ||
b2e8bc1b | 382 | def _real_initialize(self): |
f3aa3c3f | 383 | self._initialize_pref() |
cce889b9 | 384 | self._initialize_consent() |
24b0a72b | 385 | self._login() |
c5e8d7af | 386 | |
a0566bbf | 387 | _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;' |
29f7c58a | 388 | _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;' |
389 | _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)' | |
a0566bbf | 390 | |
000c15a4 | 391 | def _get_default_ytcfg(self, client='web'): |
392 | return copy.deepcopy(INNERTUBE_CLIENTS[client]) | |
109dd3b2 | 393 | |
000c15a4 | 394 | def _get_innertube_host(self, client='web'): |
395 | return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST'] | |
109dd3b2 | 396 | |
000c15a4 | 397 | def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'): |
109dd3b2 | 398 | # try_get but with fallback to default ytcfg client values when present |
399 | _func = lambda y: try_get(y, getter, expected_type) | |
400 | return _func(ytcfg) or _func(self._get_default_ytcfg(default_client)) | |
401 | ||
000c15a4 | 402 | def _extract_client_name(self, ytcfg, default_client='web'): |
3619f78d | 403 | return self._ytcfg_get_safe( |
404 | ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'], | |
405 | lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client) | |
109dd3b2 | 406 | |
000c15a4 | 407 | def _extract_client_version(self, ytcfg, default_client='web'): |
3619f78d | 408 | return self._ytcfg_get_safe( |
409 | ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'], | |
410 | lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client) | |
109dd3b2 | 411 | |
000c15a4 | 412 | def _extract_api_key(self, ytcfg=None, default_client='web'): |
109dd3b2 | 413 | return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client) |
414 | ||
000c15a4 | 415 | def _extract_context(self, ytcfg=None, default_client='web'): |
f3aa3c3f | 416 | context = get_first( |
417 | (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict) | |
396a76f7 | 418 | # Enforce language and tz for extraction |
419 | client_context = traverse_obj(context, 'client', expected_type=dict, default={}) | |
420 | client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0}) | |
109dd3b2 | 421 | return context |
422 | ||
cf87314d | 423 | _SAPISID = None |
424 | ||
109dd3b2 | 425 | def _generate_sapisidhash_header(self, origin='https://www.youtube.com'): |
a5c56234 | 426 | time_now = round(time.time()) |
cf87314d | 427 | if self._SAPISID is None: |
428 | yt_cookies = self._get_cookies('https://www.youtube.com') | |
429 | # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is. | |
430 | # See: https://github.com/yt-dlp/yt-dlp/issues/393 | |
431 | sapisid_cookie = dict_get( | |
432 | yt_cookies, ('__Secure-3PAPISID', 'SAPISID')) | |
433 | if sapisid_cookie and sapisid_cookie.value: | |
434 | self._SAPISID = sapisid_cookie.value | |
435 | self.write_debug('Extracted SAPISID cookie') | |
436 | # SAPISID cookie is required if not already present | |
437 | if not yt_cookies.get('SAPISID'): | |
438 | self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie') | |
439 | self._set_cookie( | |
440 | '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600) | |
441 | else: | |
442 | self._SAPISID = False | |
443 | if not self._SAPISID: | |
444 | return None | |
1974e99f | 445 | # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323 |
446 | sapisidhash = hashlib.sha1( | |
cf87314d | 447 | f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest() |
1974e99f | 448 | return f'SAPISIDHASH {time_now}_{sapisidhash}' |
a5c56234 M |
449 | |
450 | def _call_api(self, ep, query, video_id, fatal=True, headers=None, | |
f4f751af | 451 | note='Downloading API JSON', errnote='Unable to download API page', |
000c15a4 | 452 | context=None, api_key=None, api_hostname=None, default_client='web'): |
f4f751af | 453 | |
109dd3b2 | 454 | data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)} |
8bdd16b4 | 455 | data.update(query) |
11f9be09 | 456 | real_headers = self.generate_api_headers(default_client=default_client) |
f4f751af | 457 | real_headers.update({'content-type': 'application/json'}) |
458 | if headers: | |
459 | real_headers.update(headers) | |
545cc85d | 460 | return self._download_json( |
109dd3b2 | 461 | 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep), |
a5c56234 | 462 | video_id=video_id, fatal=fatal, note=note, errnote=errnote, |
f4f751af | 463 | data=json.dumps(data).encode('utf8'), headers=real_headers, |
464 | query={'key': api_key or self._extract_api_key()}) | |
465 | ||
ac56cf38 | 466 | def extract_yt_initial_data(self, item_id, webpage, fatal=True): |
467 | data = self._search_regex( | |
468 | (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE), | |
469 | self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal) | |
470 | if data: | |
471 | return self._parse_json(data, item_id, fatal=fatal) | |
0c148415 | 472 | |
99e9e001 | 473 | @staticmethod |
474 | def _extract_session_index(*data): | |
475 | """ | |
476 | Index of current account in account list. | |
477 | See: https://github.com/yt-dlp/yt-dlp/pull/519 | |
478 | """ | |
479 | for ytcfg in data: | |
480 | session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX'])) | |
481 | if session_index is not None: | |
482 | return session_index | |
483 | ||
484 | # Deprecated? | |
485 | def _extract_identity_token(self, ytcfg=None, webpage=None): | |
a1c5d2ca M |
486 | if ytcfg: |
487 | token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str) | |
488 | if token: | |
489 | return token | |
99e9e001 | 490 | if webpage: |
491 | return self._search_regex( | |
492 | r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage, | |
493 | 'identity token', default=None, fatal=False) | |
a1c5d2ca M |
494 | |
495 | @staticmethod | |
fe93e2c4 | 496 | def _extract_account_syncid(*args): |
8ea3f7b9 | 497 | """ |
498 | Extract syncId required to download private playlists of secondary channels | |
fe93e2c4 | 499 | @params response and/or ytcfg |
8ea3f7b9 | 500 | """ |
fe93e2c4 | 501 | for data in args: |
502 | # ytcfg includes channel_syncid if on secondary channel | |
503 | delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str) | |
504 | if delegated_sid: | |
505 | return delegated_sid | |
506 | sync_ids = (try_get( | |
507 | data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'], | |
e6f21b3d | 508 | lambda x: x['DATASYNC_ID']), compat_str) or '').split('||') |
fe93e2c4 | 509 | if len(sync_ids) >= 2 and sync_ids[1]: |
510 | # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel | |
511 | # and just "user_syncid||" for primary channel. We only want the channel_syncid | |
512 | return sync_ids[0] | |
a1c5d2ca | 513 | |
ac56cf38 | 514 | @staticmethod |
515 | def _extract_visitor_data(*args): | |
516 | """ | |
517 | Extracts visitorData from an API response or ytcfg | |
518 | Appears to be used to track session state | |
519 | """ | |
9222c381 | 520 | return get_first( |
6c73052c | 521 | args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))], |
9222c381 | 522 | expected_type=str) |
ac56cf38 | 523 | |
99e9e001 | 524 | @property |
525 | def is_authenticated(self): | |
526 | return bool(self._generate_sapisidhash_header()) | |
527 | ||
11f9be09 | 528 | def extract_ytcfg(self, video_id, webpage): |
8c54a305 | 529 | if not webpage: |
530 | return {} | |
29f7c58a | 531 | return self._parse_json( |
532 | self._search_regex( | |
533 | r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg', | |
f4f751af | 534 | default='{}'), video_id, fatal=False) or {} |
535 | ||
11f9be09 | 536 | def generate_api_headers( |
99e9e001 | 537 | self, *, ytcfg=None, account_syncid=None, session_index=None, |
538 | visitor_data=None, identity_token=None, api_hostname=None, default_client='web'): | |
539 | ||
11f9be09 | 540 | origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client)) |
f4f751af | 541 | headers = { |
109dd3b2 | 542 | 'X-YouTube-Client-Name': compat_str( |
11f9be09 | 543 | self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)), |
544 | 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client), | |
99e9e001 | 545 | 'Origin': origin, |
546 | 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg), | |
547 | 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg), | |
ac56cf38 | 548 | 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg) |
99e9e001 | 549 | } |
550 | if session_index is None: | |
314ee305 | 551 | session_index = self._extract_session_index(ytcfg) |
552 | if account_syncid or session_index is not None: | |
553 | headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0 | |
99e9e001 | 554 | |
109dd3b2 | 555 | auth = self._generate_sapisidhash_header(origin) |
f4f751af | 556 | if auth is not None: |
557 | headers['Authorization'] = auth | |
109dd3b2 | 558 | headers['X-Origin'] = origin |
99e9e001 | 559 | return {h: v for h, v in headers.items() if v is not None} |
29f7c58a | 560 | |
2d6659b9 | 561 | @staticmethod |
562 | def _build_api_continuation_query(continuation, ctp=None): | |
563 | query = { | |
564 | 'continuation': continuation | |
565 | } | |
566 | # TODO: Inconsistency with clickTrackingParams. | |
567 | # Currently we have a fixed ctp contained within context (from ytcfg) | |
568 | # and a ctp in root query for continuation. | |
569 | if ctp: | |
570 | query['clickTracking'] = {'clickTrackingParams': ctp} | |
571 | return query | |
572 | ||
2d6659b9 | 573 | @classmethod |
574 | def _extract_next_continuation_data(cls, renderer): | |
575 | next_continuation = try_get( | |
576 | renderer, (lambda x: x['continuations'][0]['nextContinuationData'], | |
577 | lambda x: x['continuation']['reloadContinuationData']), dict) | |
578 | if not next_continuation: | |
579 | return | |
580 | continuation = next_continuation.get('continuation') | |
581 | if not continuation: | |
582 | return | |
583 | ctp = next_continuation.get('clickTrackingParams') | |
fe93e2c4 | 584 | return cls._build_api_continuation_query(continuation, ctp) |
2d6659b9 | 585 | |
586 | @classmethod | |
587 | def _extract_continuation_ep_data(cls, continuation_ep: dict): | |
588 | if isinstance(continuation_ep, dict): | |
589 | continuation = try_get( | |
590 | continuation_ep, lambda x: x['continuationCommand']['token'], compat_str) | |
591 | if not continuation: | |
592 | return | |
593 | ctp = continuation_ep.get('clickTrackingParams') | |
fe93e2c4 | 594 | return cls._build_api_continuation_query(continuation, ctp) |
2d6659b9 | 595 | |
596 | @classmethod | |
597 | def _extract_continuation(cls, renderer): | |
598 | next_continuation = cls._extract_next_continuation_data(renderer) | |
599 | if next_continuation: | |
600 | return next_continuation | |
fe93e2c4 | 601 | |
2d6659b9 | 602 | contents = [] |
603 | for key in ('contents', 'items'): | |
604 | contents.extend(try_get(renderer, lambda x: x[key], list) or []) | |
fe93e2c4 | 605 | |
2d6659b9 | 606 | for content in contents: |
607 | if not isinstance(content, dict): | |
608 | continue | |
609 | continuation_ep = try_get( | |
610 | content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'], | |
611 | lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']), | |
612 | dict) | |
613 | continuation = cls._extract_continuation_ep_data(continuation_ep) | |
614 | if continuation: | |
615 | return continuation | |
616 | ||
fe93e2c4 | 617 | @classmethod |
618 | def _extract_alerts(cls, data): | |
109dd3b2 | 619 | for alert_dict in try_get(data, lambda x: x['alerts'], list) or []: |
620 | if not isinstance(alert_dict, dict): | |
621 | continue | |
622 | for alert in alert_dict.values(): | |
623 | alert_type = alert.get('type') | |
624 | if not alert_type: | |
625 | continue | |
052e1350 | 626 | message = cls._get_text(alert, 'text') |
109dd3b2 | 627 | if message: |
628 | yield alert_type, message | |
629 | ||
c0ac49bc | 630 | def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False): |
109dd3b2 | 631 | errors = [] |
632 | warnings = [] | |
633 | for alert_type, alert_message in alerts: | |
641ad5d8 | 634 | if alert_type.lower() == 'error' and fatal: |
109dd3b2 | 635 | errors.append([alert_type, alert_message]) |
636 | else: | |
637 | warnings.append([alert_type, alert_message]) | |
638 | ||
639 | for alert_type, alert_message in (warnings + errors[:-1]): | |
c0ac49bc | 640 | self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message), only_once=only_once) |
109dd3b2 | 641 | if errors: |
642 | raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected) | |
643 | ||
644 | def _extract_and_report_alerts(self, data, *args, **kwargs): | |
645 | return self._report_alerts(self._extract_alerts(data), *args, **kwargs) | |
646 | ||
47193e02 | 647 | def _extract_badges(self, renderer: dict): |
648 | badges = set() | |
649 | for badge in try_get(renderer, lambda x: x['badges'], list) or []: | |
650 | label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str) | |
651 | if label: | |
652 | badges.add(label.lower()) | |
653 | return badges | |
654 | ||
655 | @staticmethod | |
052e1350 | 656 | def _get_text(data, *path_list, max_runs=None): |
657 | for path in path_list or [None]: | |
658 | if path is None: | |
659 | obj = [data] | |
660 | else: | |
661 | obj = traverse_obj(data, path, default=[]) | |
662 | if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)): | |
663 | obj = [obj] | |
664 | for item in obj: | |
665 | text = try_get(item, lambda x: x['simpleText'], compat_str) | |
666 | if text: | |
667 | return text | |
668 | runs = try_get(item, lambda x: x['runs'], list) or [] | |
669 | if not runs and isinstance(item, list): | |
670 | runs = item | |
671 | ||
672 | runs = runs[:min(len(runs), max_runs or len(runs))] | |
673 | text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[])) | |
674 | if text: | |
675 | return text | |
47193e02 | 676 | |
f0d785d3 | 677 | def _get_count(self, data, *path_list): |
678 | count_text = self._get_text(data, *path_list) or '' | |
679 | count = parse_count(count_text) | |
680 | if count is None: | |
681 | count = str_to_int( | |
682 | self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None)) | |
683 | return count | |
684 | ||
a709d873 | 685 | @staticmethod |
686 | def _extract_thumbnails(data, *path_list): | |
687 | """ | |
688 | Extract thumbnails from thumbnails dict | |
689 | @param path_list: path list to level that contains 'thumbnails' key | |
690 | """ | |
691 | thumbnails = [] | |
692 | for path in path_list or [()]: | |
693 | for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]): | |
694 | thumbnail_url = url_or_none(thumbnail.get('url')) | |
695 | if not thumbnail_url: | |
696 | continue | |
697 | # Sometimes youtube gives a wrong thumbnail URL. See: | |
698 | # https://github.com/yt-dlp/yt-dlp/issues/233 | |
699 | # https://github.com/ytdl-org/youtube-dl/issues/28023 | |
700 | if 'maxresdefault' in thumbnail_url: | |
701 | thumbnail_url = thumbnail_url.split('?')[0] | |
702 | thumbnails.append({ | |
703 | 'url': thumbnail_url, | |
704 | 'height': int_or_none(thumbnail.get('height')), | |
705 | 'width': int_or_none(thumbnail.get('width')), | |
706 | }) | |
707 | return thumbnails | |
708 | ||
f3aa3c3f | 709 | @staticmethod |
710 | def extract_relative_time(relative_time_text): | |
711 | """ | |
712 | Extracts a relative time from string and converts to dt object | |
f0d785d3 | 713 | e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today' |
f3aa3c3f | 714 | """ |
f0d785d3 | 715 | 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) |
f3aa3c3f | 716 | if mobj: |
f0d785d3 | 717 | start = mobj.group('start') |
718 | if start: | |
719 | return datetime_from_str(start) | |
f3aa3c3f | 720 | try: |
f0d785d3 | 721 | return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit'))) |
f3aa3c3f | 722 | except ValueError: |
723 | return None | |
724 | ||
725 | def _extract_time_text(self, renderer, *path_list): | |
726 | text = self._get_text(renderer, *path_list) or '' | |
727 | dt = self.extract_relative_time(text) | |
728 | timestamp = None | |
729 | if isinstance(dt, datetime.datetime): | |
730 | timestamp = calendar.timegm(dt.timetuple()) | |
f0d785d3 | 731 | |
732 | if timestamp is None: | |
733 | timestamp = ( | |
734 | unified_timestamp(text) or unified_timestamp( | |
735 | self._search_regex( | |
396a76f7 | 736 | (r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*on)?\s*(.+\d)', r'\w+[\s,\.-]*\w+[\s,\.-]+20\d{2}'), |
737 | text.lower(), 'time text', default=None))) | |
f0d785d3 | 738 | |
f3aa3c3f | 739 | if text and timestamp is None: |
740 | self.report_warning('Cannot parse localized time text' + bug_reports_message(), only_once=True) | |
741 | return timestamp, text | |
742 | ||
109dd3b2 | 743 | def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None, |
744 | ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None, | |
000c15a4 | 745 | default_client='web'): |
109dd3b2 | 746 | response = None |
747 | last_error = None | |
748 | count = -1 | |
749 | retries = self.get_param('extractor_retries', 3) | |
750 | if check_get_keys is None: | |
751 | check_get_keys = [] | |
752 | while count < retries: | |
753 | count += 1 | |
754 | if last_error: | |
c0ac49bc | 755 | self.report_warning('%s. Retrying ...' % remove_end(last_error, '.')) |
109dd3b2 | 756 | try: |
757 | response = self._call_api( | |
758 | ep=ep, fatal=True, headers=headers, | |
759 | video_id=item_id, query=query, | |
760 | context=self._extract_context(ytcfg, default_client), | |
761 | api_key=self._extract_api_key(ytcfg, default_client), | |
762 | api_hostname=api_hostname, default_client=default_client, | |
763 | note='%s%s' % (note, ' (retry #%d)' % count if count else '')) | |
764 | except ExtractorError as e: | |
9c0d7f49 | 765 | if isinstance(e.cause, network_exceptions): |
87e8e8a7 | 766 | if isinstance(e.cause, compat_HTTPError): |
767 | first_bytes = e.cause.read(512) | |
768 | if not is_html(first_bytes): | |
769 | yt_error = try_get( | |
770 | self._parse_json( | |
771 | self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False), | |
772 | lambda x: x['error']['message'], compat_str) | |
773 | if yt_error: | |
774 | self._report_alerts([('ERROR', yt_error)], fatal=False) | |
109dd3b2 | 775 | # Downloading page may result in intermittent 5xx HTTP error |
776 | # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289 | |
9c0d7f49 | 777 | # We also want to catch all other network exceptions since errors in later pages can be troublesome |
778 | # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210 | |
779 | if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429): | |
526d74ec | 780 | last_error = error_to_compat_str(e.cause or e.msg) |
9c0d7f49 | 781 | if count < retries: |
782 | continue | |
109dd3b2 | 783 | if fatal: |
784 | raise | |
785 | else: | |
786 | self.report_warning(error_to_compat_str(e)) | |
787 | return | |
788 | ||
789 | else: | |
109dd3b2 | 790 | try: |
ac56cf38 | 791 | self._extract_and_report_alerts(response, only_once=True) |
109dd3b2 | 792 | except ExtractorError as e: |
c0ac49bc | 793 | # YouTube servers may return errors we want to retry on in a 200 OK response |
794 | # See: https://github.com/yt-dlp/yt-dlp/issues/839 | |
795 | if 'unknown error' in e.msg.lower(): | |
796 | last_error = e.msg | |
797 | continue | |
109dd3b2 | 798 | if fatal: |
799 | raise | |
800 | self.report_warning(error_to_compat_str(e)) | |
801 | return | |
802 | if not check_get_keys or dict_get(response, check_get_keys): | |
803 | break | |
804 | # Youtube sometimes sends incomplete data | |
805 | # See: https://github.com/ytdl-org/youtube-dl/issues/28194 | |
806 | last_error = 'Incomplete data received' | |
807 | if count >= retries: | |
808 | if fatal: | |
809 | raise ExtractorError(last_error) | |
810 | else: | |
811 | self.report_warning(last_error) | |
812 | return | |
813 | return response | |
814 | ||
9297939e | 815 | @staticmethod |
816 | def is_music_url(url): | |
817 | return re.match(r'https?://music\.youtube\.com/', url) is not None | |
818 | ||
30a074c2 | 819 | def _extract_video(self, renderer): |
820 | video_id = renderer.get('videoId') | |
052e1350 | 821 | title = self._get_text(renderer, 'title') |
822 | description = self._get_text(renderer, 'descriptionSnippet') | |
a353beba | 823 | duration = parse_duration(self._get_text( |
824 | renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text'))) | |
f0d785d3 | 825 | view_count = self._get_count(renderer, 'viewCountText') |
fe93e2c4 | 826 | |
052e1350 | 827 | uploader = self._get_text(renderer, 'ownerText', 'shortBylineText') |
f3aa3c3f | 828 | channel_id = traverse_obj( |
829 | renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), expected_type=str, get_all=False) | |
830 | timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText') | |
831 | scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False)) | |
832 | overlay_style = traverse_obj( | |
833 | renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all=False, expected_type=str) | |
834 | badges = self._extract_badges(renderer) | |
a709d873 | 835 | thumbnails = self._extract_thumbnails(renderer, 'thumbnail') |
836 | ||
30a074c2 | 837 | return { |
39ed931e | 838 | '_type': 'url', |
30a074c2 | 839 | 'ie_key': YoutubeIE.ie_key(), |
840 | 'id': video_id, | |
5e3f2f8f | 841 | 'url': f'https://www.youtube.com/watch?v={video_id}', |
30a074c2 | 842 | 'title': title, |
843 | 'description': description, | |
844 | 'duration': duration, | |
845 | 'view_count': view_count, | |
846 | 'uploader': uploader, | |
f3aa3c3f | 847 | 'channel_id': channel_id, |
a709d873 | 848 | 'thumbnails': thumbnails, |
a30a6ed3 | 849 | 'upload_date': strftime_or_none(timestamp, '%Y%m%d') if self._configuration_arg('approximate_date', ie_key='youtubetab') else None, |
f3aa3c3f | 850 | 'live_status': ('is_upcoming' if scheduled_timestamp is not None |
851 | else 'was_live' if 'streamed' in time_text.lower() | |
852 | else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges | |
853 | else None), | |
854 | 'release_timestamp': scheduled_timestamp, | |
855 | 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges) | |
30a074c2 | 856 | } |
857 | ||
0c148415 | 858 | |
360e1ca5 | 859 | class YoutubeIE(YoutubeBaseInfoExtractor): |
96565c7e | 860 | IE_DESC = 'YouTube' |
cb7dfeea | 861 | _VALID_URL = r"""(?x)^ |
c5e8d7af | 862 | ( |
edb53e2d | 863 | (?:https?://|//) # http(s):// or protocol-independent URL |
bc2ca1bb | 864 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com| |
865 | (?:www\.)?deturl\.com/www\.youtube\.com| | |
866 | (?:www\.)?pwnyoutube\.com| | |
867 | (?:www\.)?hooktube\.com| | |
868 | (?:www\.)?yourepeat\.com| | |
869 | tube\.majestyc\.net| | |
870 | %(invidious)s| | |
871 | youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains | |
c5e8d7af PH |
872 | (?:.*?\#/)? # handle anchor (#/) redirect urls |
873 | (?: # the various things that can precede the ID: | |
b6ce9bb0 | 874 | (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/ |
c5e8d7af | 875 | |(?: # or the v= param in all its forms |
f7000f3a | 876 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) |
c5e8d7af | 877 | (?:\?|\#!?) # the params delimiter ? or # or #! |
040ac686 | 878 | (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY) |
c5e8d7af PH |
879 | v= |
880 | ) | |
f4b05232 | 881 | )) |
cbaed4bb S |
882 | |(?: |
883 | youtu\.be| # just youtu.be/xxxx | |
6d4fc66b S |
884 | vid\.plus| # or vid.plus/xxxx |
885 | zwearz\.com/watch| # or zwearz.com/watch/xxxx | |
bc2ca1bb | 886 | %(invidious)s |
cbaed4bb | 887 | )/ |
edb53e2d | 888 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= |
f4b05232 | 889 | ) |
c5e8d7af | 890 | )? # all until now is optional -> you can pass the naked ID |
201c1459 | 891 | (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID |
c5e8d7af | 892 | (?(1).+)? # if we found the ID, everything can follow |
9297939e | 893 | (?:\#|$)""" % { |
d9190e44 | 894 | 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), |
bc2ca1bb | 895 | } |
e40c758c | 896 | _PLAYER_INFO_RE = ( |
cc2db878 | 897 | r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player', |
898 | r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$', | |
545cc85d | 899 | r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$', |
e40c758c | 900 | ) |
2c62dc26 | 901 | _formats = { |
c2d3cb4c | 902 | '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, |
903 | '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
904 | '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
905 | '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}, | |
906 | '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}, | |
907 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
908 | '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
909 | '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
3834d3e3 | 910 | # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well |
c2d3cb4c | 911 | '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}, |
912 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
913 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
914 | '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
915 | '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
916 | '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
e1a0bfdf | 917 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, |
c2d3cb4c | 918 | '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, |
919 | '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
e1a0bfdf | 920 | |
921 | ||
922 | # 3D videos | |
c2d3cb4c | 923 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, |
924 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
925 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
926 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
e1a0bfdf | 927 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}, |
928 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
929 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
836a086c | 930 | |
96fb5605 | 931 | # Apple HTTP Live Streaming |
11f12195 | 932 | '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
c2d3cb4c | 933 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
934 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
935 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
936 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
937 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
e1a0bfdf | 938 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
939 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}, | |
2c62dc26 PH |
940 | |
941 | # DASH mp4 video | |
d23028a8 S |
942 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}, |
943 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
944 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
945 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
946 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
067aa17e | 947 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559) |
d23028a8 S |
948 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}, |
949 | '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
950 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
951 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
952 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
953 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
836a086c | 954 | |
f6f1fc92 | 955 | # Dash mp4 audio |
d23028a8 S |
956 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}, |
957 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}, | |
958 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}, | |
959 | '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
960 | '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
961 | '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}, | |
962 | '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}, | |
836a086c AZ |
963 | |
964 | # Dash webm | |
d23028a8 S |
965 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, |
966 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
967 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
968 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
969 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
970 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
971 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}, | |
972 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
973 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
974 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
975 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
976 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
977 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
978 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
979 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
4c6b4764 | 980 | # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug) |
d23028a8 S |
981 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, |
982 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
983 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
984 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
985 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
986 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
2c62dc26 PH |
987 | |
988 | # Dash webm audio | |
d23028a8 S |
989 | '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}, |
990 | '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}, | |
ce6b9a2d | 991 | |
0857baad | 992 | # Dash webm audio with opus inside |
d23028a8 S |
993 | '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}, |
994 | '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}, | |
995 | '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}, | |
0857baad | 996 | |
ce6b9a2d PH |
997 | # RTMP (unnamed) |
998 | '_rtmp': {'protocol': 'rtmp'}, | |
b85eae0f S |
999 | |
1000 | # av01 video only formats sometimes served with "unknown" codecs | |
9b5fa9ee TOH |
1001 | '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}, |
1002 | '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}, | |
1003 | '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'}, | |
1004 | '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'}, | |
1005 | '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'}, | |
1006 | '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'}, | |
1007 | '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}, | |
1008 | '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}, | |
c5e8d7af | 1009 | } |
29f7c58a | 1010 | _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt') |
836a086c | 1011 | |
fd5c4aab S |
1012 | _GEO_BYPASS = False |
1013 | ||
78caa52a | 1014 | IE_NAME = 'youtube' |
2eb88d95 PH |
1015 | _TESTS = [ |
1016 | { | |
2d3d2997 | 1017 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9', |
4bc3a23e PH |
1018 | 'info_dict': { |
1019 | 'id': 'BaW_jenozKc', | |
1020 | 'ext': 'mp4', | |
3867038a | 1021 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', |
4bc3a23e PH |
1022 | 'uploader': 'Philipp Hagemeister', |
1023 | 'uploader_id': 'phihag', | |
ec85ded8 | 1024 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', |
ff9f925b | 1025 | 'channel': 'Philipp Hagemeister', |
dd4c4492 S |
1026 | 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', |
1027 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', | |
4bc3a23e | 1028 | 'upload_date': '20121002', |
ff9f925b | 1029 | 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22', |
4bc3a23e | 1030 | 'categories': ['Science & Technology'], |
3867038a | 1031 | 'tags': ['youtube-dl'], |
556dbe7f | 1032 | 'duration': 10, |
dbdaaa23 | 1033 | 'view_count': int, |
3e7c1224 | 1034 | 'like_count': int, |
ff9f925b | 1035 | 'availability': 'public', |
1036 | 'playable_in_embed': True, | |
1037 | 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg', | |
1038 | 'live_status': 'not_live', | |
1039 | 'age_limit': 0, | |
7c80519c | 1040 | 'start_time': 1, |
297a564b | 1041 | 'end_time': 9, |
6c73052c | 1042 | 'channel_follower_count': int |
2eb88d95 | 1043 | } |
0e853ca4 | 1044 | }, |
fccd3771 | 1045 | { |
4bc3a23e PH |
1046 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', |
1047 | 'note': 'Embed-only video (#1746)', | |
1048 | 'info_dict': { | |
1049 | 'id': 'yZIXLfi8CZQ', | |
1050 | 'ext': 'mp4', | |
1051 | 'upload_date': '20120608', | |
1052 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
1053 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
1054 | 'uploader': 'SET India', | |
94bfcd23 | 1055 | 'uploader_id': 'setindia', |
ec85ded8 | 1056 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia', |
94bfcd23 | 1057 | 'age_limit': 18, |
545cc85d | 1058 | }, |
1059 | 'skip': 'Private video', | |
fccd3771 | 1060 | }, |
11b56058 | 1061 | { |
8bdd16b4 | 1062 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ', |
11b56058 PM |
1063 | 'note': 'Use the first video ID in the URL', |
1064 | 'info_dict': { | |
1065 | 'id': 'BaW_jenozKc', | |
1066 | 'ext': 'mp4', | |
3867038a | 1067 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', |
11b56058 PM |
1068 | 'uploader': 'Philipp Hagemeister', |
1069 | 'uploader_id': 'phihag', | |
ec85ded8 | 1070 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', |
976ae3ea | 1071 | 'channel': 'Philipp Hagemeister', |
1072 | 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', | |
1073 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', | |
11b56058 | 1074 | 'upload_date': '20121002', |
976ae3ea | 1075 | 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22', |
11b56058 | 1076 | 'categories': ['Science & Technology'], |
3867038a | 1077 | 'tags': ['youtube-dl'], |
556dbe7f | 1078 | 'duration': 10, |
dbdaaa23 | 1079 | 'view_count': int, |
11b56058 | 1080 | 'like_count': int, |
976ae3ea | 1081 | 'availability': 'public', |
1082 | 'playable_in_embed': True, | |
1083 | 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg', | |
1084 | 'live_status': 'not_live', | |
1085 | 'age_limit': 0, | |
6c73052c | 1086 | 'channel_follower_count': int |
34a7de29 S |
1087 | }, |
1088 | 'params': { | |
1089 | 'skip_download': True, | |
1090 | }, | |
11b56058 | 1091 | }, |
dd27fd17 | 1092 | { |
2d3d2997 | 1093 | 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I', |
4bc3a23e PH |
1094 | 'note': '256k DASH audio (format 141) via DASH manifest', |
1095 | 'info_dict': { | |
1096 | 'id': 'a9LDPn-MO4I', | |
1097 | 'ext': 'm4a', | |
1098 | 'upload_date': '20121002', | |
1099 | 'uploader_id': '8KVIDEO', | |
ec85ded8 | 1100 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO', |
4bc3a23e PH |
1101 | 'description': '', |
1102 | 'uploader': '8KVIDEO', | |
1103 | 'title': 'UHDTV TEST 8K VIDEO.mp4' | |
4919603f | 1104 | }, |
4bc3a23e PH |
1105 | 'params': { |
1106 | 'youtube_include_dash_manifest': True, | |
1107 | 'format': '141', | |
4919603f | 1108 | }, |
de3c7fe0 | 1109 | 'skip': 'format 141 not served anymore', |
dd27fd17 | 1110 | }, |
8bdd16b4 | 1111 | # DASH manifest with encrypted signature |
1112 | { | |
1113 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', | |
1114 | 'info_dict': { | |
1115 | 'id': 'IB3lcPjvWLA', | |
1116 | 'ext': 'm4a', | |
1117 | 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson', | |
1118 | 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf', | |
1119 | 'duration': 244, | |
1120 | 'uploader': 'AfrojackVEVO', | |
1121 | 'uploader_id': 'AfrojackVEVO', | |
1122 | 'upload_date': '20131011', | |
cc2db878 | 1123 | 'abr': 129.495, |
976ae3ea | 1124 | 'like_count': int, |
1125 | 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg', | |
1126 | 'playable_in_embed': True, | |
1127 | 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg', | |
1128 | 'view_count': int, | |
1129 | 'track': 'The Spark', | |
1130 | 'live_status': 'not_live', | |
1131 | 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp', | |
1132 | 'channel': 'Afrojack', | |
1133 | 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO', | |
1134 | 'tags': 'count:19', | |
1135 | 'availability': 'public', | |
1136 | 'categories': ['Music'], | |
1137 | 'age_limit': 0, | |
1138 | 'alt_title': 'The Spark', | |
6c73052c | 1139 | 'channel_follower_count': int |
8bdd16b4 | 1140 | }, |
1141 | 'params': { | |
1142 | 'youtube_include_dash_manifest': True, | |
1143 | 'format': '141/bestaudio[ext=m4a]', | |
1144 | }, | |
1145 | }, | |
65c2fde2 | 1146 | # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000 |
c522adb1 | 1147 | { |
65c2fde2 | 1148 | 'note': 'Embed allowed age-gate video', |
2d3d2997 | 1149 | 'url': 'https://youtube.com/watch?v=HtVdAasjOgU', |
c522adb1 JMF |
1150 | 'info_dict': { |
1151 | 'id': 'HtVdAasjOgU', | |
1152 | 'ext': 'mp4', | |
1153 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
ec85ded8 | 1154 | 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', |
556dbe7f | 1155 | 'duration': 142, |
c522adb1 JMF |
1156 | 'uploader': 'The Witcher', |
1157 | 'uploader_id': 'WitcherGame', | |
ec85ded8 | 1158 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame', |
c522adb1 | 1159 | 'upload_date': '20140605', |
34952f09 | 1160 | 'age_limit': 18, |
976ae3ea | 1161 | 'categories': ['Gaming'], |
1162 | 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp', | |
1163 | 'availability': 'needs_auth', | |
1164 | 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg', | |
1165 | 'like_count': int, | |
1166 | 'channel': 'The Witcher', | |
1167 | 'live_status': 'not_live', | |
1168 | 'tags': 'count:17', | |
1169 | 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg', | |
1170 | 'playable_in_embed': True, | |
1171 | 'view_count': int, | |
6c73052c | 1172 | 'channel_follower_count': int |
c522adb1 JMF |
1173 | }, |
1174 | }, | |
65c2fde2 | 1175 | { |
1176 | 'note': 'Age-gate video with embed allowed in public site', | |
1177 | 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U', | |
1178 | 'info_dict': { | |
1179 | 'id': 'HsUATh_Nc2U', | |
1180 | 'ext': 'mp4', | |
1181 | 'title': 'Godzilla 2 (Official Video)', | |
1182 | 'description': 'md5:bf77e03fcae5529475e500129b05668a', | |
1183 | 'upload_date': '20200408', | |
1184 | 'uploader_id': 'FlyingKitty900', | |
1185 | 'uploader': 'FlyingKitty', | |
1186 | 'age_limit': 18, | |
976ae3ea | 1187 | 'availability': 'needs_auth', |
1188 | 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg', | |
1189 | 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900', | |
1190 | 'channel': 'FlyingKitty', | |
1191 | 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg', | |
1192 | 'view_count': int, | |
1193 | 'categories': ['Entertainment'], | |
1194 | 'live_status': 'not_live', | |
1195 | 'tags': ['Flyingkitty', 'godzilla 2'], | |
1196 | 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg', | |
1197 | 'like_count': int, | |
1198 | 'duration': 177, | |
1199 | 'playable_in_embed': True, | |
6c73052c | 1200 | 'channel_follower_count': int |
65c2fde2 | 1201 | }, |
1202 | }, | |
1203 | { | |
1204 | 'note': 'Age-gate video embedable only with clientScreen=EMBED', | |
1205 | 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg', | |
1206 | 'info_dict': { | |
1207 | 'id': 'Tq92D6wQ1mg', | |
1208 | 'title': '[MMD] Adios - EVERGLOW [+Motion DL]', | |
3619f78d | 1209 | 'ext': 'mp4', |
1210 | 'upload_date': '20191227', | |
65c2fde2 | 1211 | 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ', |
1212 | 'uploader': 'Projekt Melody', | |
1213 | 'description': 'md5:17eccca93a786d51bc67646756894066', | |
1214 | 'age_limit': 18, | |
976ae3ea | 1215 | 'like_count': int, |
1216 | 'availability': 'needs_auth', | |
1217 | 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ', | |
1218 | 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ', | |
1219 | 'view_count': int, | |
1220 | 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp', | |
1221 | 'channel': 'Projekt Melody', | |
1222 | 'live_status': 'not_live', | |
1223 | 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'], | |
1224 | 'playable_in_embed': True, | |
1225 | 'categories': ['Entertainment'], | |
1226 | 'duration': 106, | |
1227 | 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ', | |
6c73052c | 1228 | 'channel_follower_count': int |
65c2fde2 | 1229 | }, |
1230 | }, | |
1231 | { | |
1232 | 'note': 'Non-Agegated non-embeddable video', | |
1233 | 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY', | |
1234 | 'info_dict': { | |
1235 | 'id': 'MeJVWBSsPAY', | |
1236 | 'ext': 'mp4', | |
1237 | 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)', | |
1238 | 'uploader': 'Herr Lurik', | |
1239 | 'uploader_id': 'st3in234', | |
1240 | 'description': 'Fan Video. Music & Lyrics by OOMPH!.', | |
1241 | 'upload_date': '20130730', | |
976ae3ea | 1242 | 'track': 'Such mich find mich', |
1243 | 'age_limit': 0, | |
1244 | 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'], | |
1245 | 'like_count': int, | |
1246 | 'playable_in_embed': False, | |
1247 | 'creator': 'OOMPH!', | |
1248 | 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg', | |
1249 | 'view_count': int, | |
1250 | 'alt_title': 'Such mich find mich', | |
1251 | 'duration': 210, | |
1252 | 'channel': 'Herr Lurik', | |
1253 | 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA', | |
1254 | 'categories': ['Music'], | |
1255 | 'availability': 'public', | |
1256 | 'uploader_url': 'http://www.youtube.com/user/st3in234', | |
1257 | 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA', | |
1258 | 'live_status': 'not_live', | |
1259 | 'artist': 'OOMPH!', | |
6c73052c | 1260 | 'channel_follower_count': int |
65c2fde2 | 1261 | }, |
1262 | }, | |
1263 | { | |
1264 | 'note': 'Non-bypassable age-gated video', | |
1265 | 'url': 'https://youtube.com/watch?v=Cr381pDsSsA', | |
1266 | 'only_matching': True, | |
1267 | }, | |
8bdd16b4 | 1268 | # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421) |
1269 | # YouTube Red ad is not captured for creator | |
1270 | { | |
1271 | 'url': '__2ABJjxzNo', | |
1272 | 'info_dict': { | |
1273 | 'id': '__2ABJjxzNo', | |
1274 | 'ext': 'mp4', | |
1275 | 'duration': 266, | |
1276 | 'upload_date': '20100430', | |
1277 | 'uploader_id': 'deadmau5', | |
1278 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5', | |
545cc85d | 1279 | 'creator': 'deadmau5', |
1280 | 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336', | |
8bdd16b4 | 1281 | 'uploader': 'deadmau5', |
1282 | 'title': 'Deadmau5 - Some Chords (HD)', | |
545cc85d | 1283 | 'alt_title': 'Some Chords', |
976ae3ea | 1284 | 'availability': 'public', |
1285 | 'tags': 'count:14', | |
1286 | 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ', | |
1287 | 'view_count': int, | |
1288 | 'live_status': 'not_live', | |
1289 | 'channel': 'deadmau5', | |
1290 | 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp', | |
1291 | 'like_count': int, | |
1292 | 'track': 'Some Chords', | |
1293 | 'artist': 'deadmau5', | |
1294 | 'playable_in_embed': True, | |
1295 | 'age_limit': 0, | |
1296 | 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ', | |
1297 | 'categories': ['Music'], | |
1298 | 'album': 'Some Chords', | |
6c73052c | 1299 | 'channel_follower_count': int |
8bdd16b4 | 1300 | }, |
1301 | 'expected_warnings': [ | |
1302 | 'DASH manifest missing', | |
1303 | ] | |
1304 | }, | |
067aa17e | 1305 | # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431) |
e52a40ab PH |
1306 | { |
1307 | 'url': 'lqQg6PlCWgI', | |
1308 | 'info_dict': { | |
1309 | 'id': 'lqQg6PlCWgI', | |
1310 | 'ext': 'mp4', | |
556dbe7f | 1311 | 'duration': 6085, |
90227264 | 1312 | 'upload_date': '20150827', |
cbe2bd91 | 1313 | 'uploader_id': 'olympic', |
ec85ded8 | 1314 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic', |
cbe2bd91 | 1315 | 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', |
11f9be09 | 1316 | 'uploader': 'Olympics', |
cbe2bd91 | 1317 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', |
976ae3ea | 1318 | 'like_count': int, |
1319 | 'release_timestamp': 1343767800, | |
1320 | 'playable_in_embed': True, | |
1321 | 'categories': ['Sports'], | |
1322 | 'release_date': '20120731', | |
1323 | 'channel': 'Olympics', | |
1324 | 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'], | |
1325 | 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q', | |
1326 | 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg', | |
1327 | 'age_limit': 0, | |
1328 | 'availability': 'public', | |
1329 | 'live_status': 'was_live', | |
1330 | 'view_count': int, | |
1331 | 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q', | |
6c73052c | 1332 | 'channel_follower_count': int |
cbe2bd91 PH |
1333 | }, |
1334 | 'params': { | |
1335 | 'skip_download': 'requires avconv', | |
e52a40ab | 1336 | } |
cbe2bd91 | 1337 | }, |
6271f1ca PH |
1338 | # Non-square pixels |
1339 | { | |
1340 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
1341 | 'info_dict': { | |
1342 | 'id': '_b-2C3KPAM0', | |
1343 | 'ext': 'mp4', | |
1344 | 'stretched_ratio': 16 / 9., | |
556dbe7f | 1345 | 'duration': 85, |
6271f1ca PH |
1346 | 'upload_date': '20110310', |
1347 | 'uploader_id': 'AllenMeow', | |
ec85ded8 | 1348 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow', |
6271f1ca | 1349 | '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', |
eb6793ba | 1350 | 'uploader': '孫ᄋᄅ', |
6271f1ca | 1351 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', |
976ae3ea | 1352 | 'playable_in_embed': True, |
1353 | 'channel': '孫ᄋᄅ', | |
1354 | 'age_limit': 0, | |
1355 | 'tags': 'count:11', | |
1356 | 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw', | |
1357 | 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw', | |
1358 | 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg', | |
1359 | 'view_count': int, | |
1360 | 'categories': ['People & Blogs'], | |
1361 | 'like_count': int, | |
1362 | 'live_status': 'not_live', | |
1363 | 'availability': 'unlisted', | |
6c73052c | 1364 | 'channel_follower_count': int |
6271f1ca | 1365 | }, |
06b491eb S |
1366 | }, |
1367 | # url_encoded_fmt_stream_map is empty string | |
1368 | { | |
1369 | 'url': 'qEJwOuvDf7I', | |
1370 | 'info_dict': { | |
1371 | 'id': 'qEJwOuvDf7I', | |
f57b7835 | 1372 | 'ext': 'webm', |
06b491eb S |
1373 | 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', |
1374 | 'description': '', | |
1375 | 'upload_date': '20150404', | |
1376 | 'uploader_id': 'spbelect', | |
1377 | 'uploader': 'Наблюдатели Петербурга', | |
1378 | }, | |
1379 | 'params': { | |
1380 | 'skip_download': 'requires avconv', | |
e323cf3f S |
1381 | }, |
1382 | 'skip': 'This live event has ended.', | |
06b491eb | 1383 | }, |
067aa17e | 1384 | # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097) |
da77d856 S |
1385 | { |
1386 | 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y', | |
1387 | 'info_dict': { | |
1388 | 'id': 'FIl7x6_3R5Y', | |
eb6793ba | 1389 | 'ext': 'webm', |
da77d856 S |
1390 | 'title': 'md5:7b81415841e02ecd4313668cde88737a', |
1391 | 'description': 'md5:116377fd2963b81ec4ce64b542173306', | |
556dbe7f | 1392 | 'duration': 220, |
da77d856 S |
1393 | 'upload_date': '20150625', |
1394 | 'uploader_id': 'dorappi2000', | |
ec85ded8 | 1395 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000', |
da77d856 | 1396 | 'uploader': 'dorappi2000', |
eb6793ba | 1397 | 'formats': 'mincount:31', |
da77d856 | 1398 | }, |
eb6793ba | 1399 | 'skip': 'not actual anymore', |
2ee8f5d8 | 1400 | }, |
8a1a26ce YCH |
1401 | # DASH manifest with segment_list |
1402 | { | |
1403 | 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8', | |
1404 | 'md5': '8ce563a1d667b599d21064e982ab9e31', | |
1405 | 'info_dict': { | |
1406 | 'id': 'CsmdDsKjzN8', | |
1407 | 'ext': 'mp4', | |
17ee98e1 | 1408 | 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510 |
8a1a26ce YCH |
1409 | 'uploader': 'Airtek', |
1410 | 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', | |
1411 | 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ', | |
1412 | 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', | |
1413 | }, | |
1414 | 'params': { | |
1415 | 'youtube_include_dash_manifest': True, | |
1416 | 'format': '135', # bestvideo | |
be49068d S |
1417 | }, |
1418 | 'skip': 'This live event has ended.', | |
2ee8f5d8 | 1419 | }, |
cf7e015f S |
1420 | { |
1421 | # Multifeed videos (multiple cameras), URL is for Main Camera | |
545cc85d | 1422 | 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg', |
cf7e015f | 1423 | 'info_dict': { |
545cc85d | 1424 | 'id': 'jvGDaLqkpTg', |
1425 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever', | |
1426 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
cf7e015f S |
1427 | }, |
1428 | 'playlist': [{ | |
1429 | 'info_dict': { | |
545cc85d | 1430 | 'id': 'jvGDaLqkpTg', |
cf7e015f | 1431 | 'ext': 'mp4', |
545cc85d | 1432 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)', |
1433 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1434 | 'duration': 10643, | |
1435 | 'upload_date': '20161111', | |
1436 | 'uploader': 'Team PGP', | |
1437 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1438 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
cf7e015f S |
1439 | }, |
1440 | }, { | |
1441 | 'info_dict': { | |
545cc85d | 1442 | 'id': '3AKt1R1aDnw', |
cf7e015f | 1443 | 'ext': 'mp4', |
545cc85d | 1444 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)', |
1445 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1446 | 'duration': 10991, | |
1447 | 'upload_date': '20161111', | |
1448 | 'uploader': 'Team PGP', | |
1449 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1450 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
cf7e015f S |
1451 | }, |
1452 | }, { | |
1453 | 'info_dict': { | |
545cc85d | 1454 | 'id': 'RtAMM00gpVc', |
cf7e015f | 1455 | 'ext': 'mp4', |
545cc85d | 1456 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)', |
1457 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1458 | 'duration': 10995, | |
1459 | 'upload_date': '20161111', | |
1460 | 'uploader': 'Team PGP', | |
1461 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1462 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
cf7e015f S |
1463 | }, |
1464 | }, { | |
1465 | 'info_dict': { | |
545cc85d | 1466 | 'id': '6N2fdlP3C5U', |
cf7e015f | 1467 | 'ext': 'mp4', |
545cc85d | 1468 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)', |
1469 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1470 | 'duration': 10990, | |
1471 | 'upload_date': '20161111', | |
1472 | 'uploader': 'Team PGP', | |
1473 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1474 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
cf7e015f S |
1475 | }, |
1476 | }], | |
1477 | 'params': { | |
1478 | 'skip_download': True, | |
1479 | }, | |
65c2fde2 | 1480 | 'skip': 'Not multifeed anymore', |
cbaed4bb | 1481 | }, |
f9f49d87 | 1482 | { |
067aa17e | 1483 | # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536) |
f9f49d87 S |
1484 | 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo', |
1485 | 'info_dict': { | |
1486 | 'id': 'gVfLd0zydlo', | |
1487 | 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30', | |
1488 | }, | |
1489 | 'playlist_count': 2, | |
be49068d | 1490 | 'skip': 'Not multifeed anymore', |
f9f49d87 | 1491 | }, |
cbaed4bb | 1492 | { |
2d3d2997 | 1493 | 'url': 'https://vid.plus/FlRa-iH7PGw', |
cbaed4bb | 1494 | 'only_matching': True, |
0e49d9a6 | 1495 | }, |
6d4fc66b | 1496 | { |
2d3d2997 | 1497 | 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html', |
6d4fc66b S |
1498 | 'only_matching': True, |
1499 | }, | |
0e49d9a6 | 1500 | { |
067aa17e | 1501 | # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468) |
a8776b10 | 1502 | # Also tests cut-off URL expansion in video description (see |
067aa17e S |
1503 | # https://github.com/ytdl-org/youtube-dl/issues/1892, |
1504 | # https://github.com/ytdl-org/youtube-dl/issues/8164) | |
0e49d9a6 LL |
1505 | 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg', |
1506 | 'info_dict': { | |
1507 | 'id': 'lsguqyKfVQg', | |
1508 | 'ext': 'mp4', | |
1509 | 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21', | |
11f9be09 | 1510 | 'alt_title': 'Dark Walk', |
0e49d9a6 | 1511 | 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a', |
556dbe7f | 1512 | 'duration': 133, |
0e49d9a6 LL |
1513 | 'upload_date': '20151119', |
1514 | 'uploader_id': 'IronSoulElf', | |
ec85ded8 | 1515 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf', |
0e49d9a6 | 1516 | 'uploader': 'IronSoulElf', |
11f9be09 | 1517 | 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan', |
1518 | 'track': 'Dark Walk', | |
1519 | 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan', | |
92bc97d3 | 1520 | 'album': 'Position Music - Production Music Vol. 143 - Dark Walk', |
976ae3ea | 1521 | 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp', |
1522 | 'categories': ['Film & Animation'], | |
1523 | 'view_count': int, | |
1524 | 'live_status': 'not_live', | |
1525 | 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ', | |
1526 | 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ', | |
1527 | 'tags': 'count:13', | |
1528 | 'availability': 'public', | |
1529 | 'channel': 'IronSoulElf', | |
1530 | 'playable_in_embed': True, | |
1531 | 'like_count': int, | |
1532 | 'age_limit': 0, | |
6c73052c | 1533 | 'channel_follower_count': int |
0e49d9a6 LL |
1534 | }, |
1535 | 'params': { | |
1536 | 'skip_download': True, | |
1537 | }, | |
1538 | }, | |
61f92af1 | 1539 | { |
067aa17e | 1540 | # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468) |
61f92af1 S |
1541 | 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8', |
1542 | 'only_matching': True, | |
1543 | }, | |
313dfc45 LL |
1544 | { |
1545 | # Video with yt:stretch=17:0 | |
1546 | 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM', | |
1547 | 'info_dict': { | |
1548 | 'id': 'Q39EVAstoRM', | |
1549 | 'ext': 'mp4', | |
1550 | 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4', | |
1551 | 'description': 'md5:ee18a25c350637c8faff806845bddee9', | |
1552 | 'upload_date': '20151107', | |
1553 | 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA', | |
1554 | 'uploader': 'CH GAMER DROID', | |
1555 | }, | |
1556 | 'params': { | |
1557 | 'skip_download': True, | |
1558 | }, | |
be49068d | 1559 | 'skip': 'This video does not exist.', |
313dfc45 | 1560 | }, |
201c1459 | 1561 | { |
1562 | # Video with incomplete 'yt:stretch=16:' | |
1563 | 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI', | |
1564 | 'only_matching': True, | |
1565 | }, | |
7caf9830 S |
1566 | { |
1567 | # Video licensed under Creative Commons | |
1568 | 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA', | |
1569 | 'info_dict': { | |
1570 | 'id': 'M4gD1WSo5mA', | |
1571 | 'ext': 'mp4', | |
1572 | 'title': 'md5:e41008789470fc2533a3252216f1c1d1', | |
1573 | 'description': 'md5:a677553cf0840649b731a3024aeff4cc', | |
556dbe7f | 1574 | 'duration': 721, |
7caf9830 S |
1575 | 'upload_date': '20150127', |
1576 | 'uploader_id': 'BerkmanCenter', | |
ec85ded8 | 1577 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter', |
556dbe7f | 1578 | 'uploader': 'The Berkman Klein Center for Internet & Society', |
7caf9830 | 1579 | 'license': 'Creative Commons Attribution license (reuse allowed)', |
976ae3ea | 1580 | 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA', |
1581 | 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA', | |
1582 | 'like_count': int, | |
1583 | 'age_limit': 0, | |
1584 | 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'], | |
1585 | 'channel': 'The Berkman Klein Center for Internet & Society', | |
1586 | 'availability': 'public', | |
1587 | 'view_count': int, | |
1588 | 'categories': ['Education'], | |
1589 | 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp', | |
1590 | 'live_status': 'not_live', | |
1591 | 'playable_in_embed': True, | |
6c73052c | 1592 | 'channel_follower_count': int |
7caf9830 S |
1593 | }, |
1594 | 'params': { | |
1595 | 'skip_download': True, | |
1596 | }, | |
1597 | }, | |
fd050249 S |
1598 | { |
1599 | # Channel-like uploader_url | |
1600 | 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg', | |
1601 | 'info_dict': { | |
1602 | 'id': 'eQcmzGIKrzg', | |
1603 | 'ext': 'mp4', | |
1604 | 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders', | |
545cc85d | 1605 | 'description': 'md5:13a2503d7b5904ef4b223aa101628f39', |
556dbe7f | 1606 | 'duration': 4060, |
fd050249 | 1607 | 'upload_date': '20151119', |
eb6793ba | 1608 | 'uploader': 'Bernie Sanders', |
fd050249 | 1609 | 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg', |
ec85ded8 | 1610 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg', |
fd050249 | 1611 | 'license': 'Creative Commons Attribution license (reuse allowed)', |
976ae3ea | 1612 | 'playable_in_embed': True, |
1613 | 'tags': 'count:12', | |
1614 | 'like_count': int, | |
1615 | 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg', | |
1616 | 'age_limit': 0, | |
1617 | 'availability': 'public', | |
1618 | 'categories': ['News & Politics'], | |
1619 | 'channel': 'Bernie Sanders', | |
1620 | 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp', | |
1621 | 'view_count': int, | |
1622 | 'live_status': 'not_live', | |
1623 | 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg', | |
6c73052c | 1624 | 'channel_follower_count': int |
fd050249 S |
1625 | }, |
1626 | 'params': { | |
1627 | 'skip_download': True, | |
1628 | }, | |
1629 | }, | |
040ac686 S |
1630 | { |
1631 | 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY', | |
1632 | 'only_matching': True, | |
7f29cf54 S |
1633 | }, |
1634 | { | |
067aa17e | 1635 | # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059) |
7f29cf54 S |
1636 | 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo', |
1637 | 'only_matching': True, | |
6496ccb4 S |
1638 | }, |
1639 | { | |
1640 | # Rental video preview | |
1641 | 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg', | |
1642 | 'info_dict': { | |
1643 | 'id': 'uGpuVWrhIzE', | |
1644 | 'ext': 'mp4', | |
1645 | 'title': 'Piku - Trailer', | |
1646 | 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb', | |
1647 | 'upload_date': '20150811', | |
1648 | 'uploader': 'FlixMatrix', | |
1649 | 'uploader_id': 'FlixMatrixKaravan', | |
ec85ded8 | 1650 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan', |
6496ccb4 S |
1651 | 'license': 'Standard YouTube License', |
1652 | }, | |
1653 | 'params': { | |
1654 | 'skip_download': True, | |
1655 | }, | |
eb6793ba | 1656 | 'skip': 'This video is not available.', |
022a5d66 | 1657 | }, |
12afdc2a S |
1658 | { |
1659 | # YouTube Red video with episode data | |
1660 | 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4', | |
1661 | 'info_dict': { | |
1662 | 'id': 'iqKdEhx-dD4', | |
1663 | 'ext': 'mp4', | |
1664 | 'title': 'Isolation - Mind Field (Ep 1)', | |
545cc85d | 1665 | 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd', |
556dbe7f | 1666 | 'duration': 2085, |
12afdc2a S |
1667 | 'upload_date': '20170118', |
1668 | 'uploader': 'Vsauce', | |
1669 | 'uploader_id': 'Vsauce', | |
1670 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce', | |
12afdc2a S |
1671 | 'series': 'Mind Field', |
1672 | 'season_number': 1, | |
1673 | 'episode_number': 1, | |
976ae3ea | 1674 | 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp', |
1675 | 'tags': 'count:12', | |
1676 | 'view_count': int, | |
1677 | 'availability': 'public', | |
1678 | 'age_limit': 0, | |
1679 | 'channel': 'Vsauce', | |
1680 | 'episode': 'Episode 1', | |
1681 | 'categories': ['Entertainment'], | |
1682 | 'season': 'Season 1', | |
1683 | 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA', | |
1684 | 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA', | |
1685 | 'like_count': int, | |
1686 | 'playable_in_embed': True, | |
1687 | 'live_status': 'not_live', | |
6c73052c | 1688 | 'channel_follower_count': int |
12afdc2a S |
1689 | }, |
1690 | 'params': { | |
1691 | 'skip_download': True, | |
1692 | }, | |
1693 | 'expected_warnings': [ | |
1694 | 'Skipping DASH manifest', | |
1695 | ], | |
1696 | }, | |
c7121fa7 S |
1697 | { |
1698 | # The following content has been identified by the YouTube community | |
1699 | # as inappropriate or offensive to some audiences. | |
1700 | 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI', | |
1701 | 'info_dict': { | |
1702 | 'id': '6SJNVb0GnPI', | |
1703 | 'ext': 'mp4', | |
1704 | 'title': 'Race Differences in Intelligence', | |
1705 | 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1', | |
1706 | 'duration': 965, | |
1707 | 'upload_date': '20140124', | |
1708 | 'uploader': 'New Century Foundation', | |
1709 | 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg', | |
1710 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg', | |
c7121fa7 S |
1711 | }, |
1712 | 'params': { | |
1713 | 'skip_download': True, | |
1714 | }, | |
545cc85d | 1715 | 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.', |
c7121fa7 | 1716 | }, |
022a5d66 S |
1717 | { |
1718 | # itag 212 | |
1719 | 'url': '1t24XAntNCY', | |
1720 | 'only_matching': True, | |
fd5c4aab S |
1721 | }, |
1722 | { | |
1723 | # geo restricted to JP | |
1724 | 'url': 'sJL6WA-aGkQ', | |
1725 | 'only_matching': True, | |
1726 | }, | |
cd5a74a2 S |
1727 | { |
1728 | 'url': 'https://invidio.us/watch?v=BaW_jenozKc', | |
1729 | 'only_matching': True, | |
1730 | }, | |
bc2ca1bb | 1731 | { |
1732 | 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc', | |
1733 | 'only_matching': True, | |
1734 | }, | |
1735 | { | |
1736 | # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m | |
1737 | 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA', | |
1738 | 'only_matching': True, | |
1739 | }, | |
825cd268 RA |
1740 | { |
1741 | # DRM protected | |
1742 | 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc', | |
1743 | 'only_matching': True, | |
4fe54c12 S |
1744 | }, |
1745 | { | |
1746 | # Video with unsupported adaptive stream type formats | |
1747 | 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U', | |
1748 | 'info_dict': { | |
1749 | 'id': 'Z4Vy8R84T1U', | |
1750 | 'ext': 'mp4', | |
1751 | 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta', | |
1752 | 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', | |
1753 | 'duration': 433, | |
1754 | 'upload_date': '20130923', | |
1755 | 'uploader': 'Amelia Putri Harwita', | |
1756 | 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q', | |
1757 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q', | |
1758 | 'formats': 'maxcount:10', | |
1759 | }, | |
1760 | 'params': { | |
1761 | 'skip_download': True, | |
1762 | 'youtube_include_dash_manifest': False, | |
1763 | }, | |
5429d6a9 | 1764 | 'skip': 'not actual anymore', |
5caabd3c | 1765 | }, |
1766 | { | |
822b9d9c | 1767 | # Youtube Music Auto-generated description |
5caabd3c | 1768 | 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs', |
1769 | 'info_dict': { | |
1770 | 'id': 'MgNrAu2pzNs', | |
1771 | 'ext': 'mp4', | |
1772 | 'title': 'Voyeur Girl', | |
1773 | 'description': 'md5:7ae382a65843d6df2685993e90a8628f', | |
1774 | 'upload_date': '20190312', | |
5429d6a9 S |
1775 | 'uploader': 'Stephen - Topic', |
1776 | 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA', | |
5caabd3c | 1777 | 'artist': 'Stephen', |
1778 | 'track': 'Voyeur Girl', | |
1779 | 'album': 'it\'s too much love to know my dear', | |
1780 | 'release_date': '20190313', | |
1781 | 'release_year': 2019, | |
976ae3ea | 1782 | 'alt_title': 'Voyeur Girl', |
1783 | 'view_count': int, | |
1784 | 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA', | |
1785 | 'playable_in_embed': True, | |
1786 | 'like_count': int, | |
1787 | 'categories': ['Music'], | |
1788 | 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA', | |
1789 | 'channel': 'Stephen', | |
1790 | 'availability': 'public', | |
1791 | 'creator': 'Stephen', | |
1792 | 'duration': 169, | |
1793 | 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp', | |
1794 | 'age_limit': 0, | |
1795 | 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA', | |
1796 | 'tags': 'count:11', | |
1797 | 'live_status': 'not_live', | |
6c73052c | 1798 | 'channel_follower_count': int |
5caabd3c | 1799 | }, |
1800 | 'params': { | |
1801 | 'skip_download': True, | |
1802 | }, | |
1803 | }, | |
66b48727 RA |
1804 | { |
1805 | 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q', | |
1806 | 'only_matching': True, | |
1807 | }, | |
011e75e6 S |
1808 | { |
1809 | # invalid -> valid video id redirection | |
1810 | 'url': 'DJztXj2GPfl', | |
1811 | 'info_dict': { | |
1812 | 'id': 'DJztXj2GPfk', | |
1813 | 'ext': 'mp4', | |
1814 | 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)', | |
1815 | 'description': 'md5:bf577a41da97918e94fa9798d9228825', | |
1816 | 'upload_date': '20090125', | |
1817 | 'uploader': 'Prochorowka', | |
1818 | 'uploader_id': 'Prochorowka', | |
1819 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka', | |
1820 | 'artist': 'Panjabi MC', | |
1821 | 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix', | |
1822 | 'album': 'Beware of the Boys (Mundian To Bach Ke)', | |
1823 | }, | |
1824 | 'params': { | |
1825 | 'skip_download': True, | |
1826 | }, | |
545cc85d | 1827 | 'skip': 'Video unavailable', |
ea74e00b DP |
1828 | }, |
1829 | { | |
1830 | # empty description results in an empty string | |
1831 | 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k', | |
1832 | 'info_dict': { | |
1833 | 'id': 'x41yOUIvK2k', | |
1834 | 'ext': 'mp4', | |
1835 | 'title': 'IMG 3456', | |
1836 | 'description': '', | |
1837 | 'upload_date': '20170613', | |
1838 | 'uploader_id': 'ElevageOrVert', | |
1839 | 'uploader': 'ElevageOrVert', | |
976ae3ea | 1840 | 'view_count': int, |
1841 | 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp', | |
1842 | 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert', | |
1843 | 'like_count': int, | |
1844 | 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw', | |
1845 | 'tags': [], | |
1846 | 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw', | |
1847 | 'availability': 'public', | |
1848 | 'age_limit': 0, | |
1849 | 'categories': ['Pets & Animals'], | |
1850 | 'duration': 7, | |
1851 | 'playable_in_embed': True, | |
1852 | 'live_status': 'not_live', | |
1853 | 'channel': 'ElevageOrVert', | |
6c73052c | 1854 | 'channel_follower_count': int |
ea74e00b DP |
1855 | }, |
1856 | 'params': { | |
1857 | 'skip_download': True, | |
1858 | }, | |
1859 | }, | |
a0566bbf | 1860 | { |
29f7c58a | 1861 | # with '};' inside yt initial data (see [1]) |
1862 | # see [2] for an example with '};' inside ytInitialPlayerResponse | |
1863 | # 1. https://github.com/ytdl-org/youtube-dl/issues/27093 | |
1864 | # 2. https://github.com/ytdl-org/youtube-dl/issues/27216 | |
a0566bbf | 1865 | 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no', |
1866 | 'info_dict': { | |
1867 | 'id': 'CHqg6qOn4no', | |
1868 | 'ext': 'mp4', | |
1869 | 'title': 'Part 77 Sort a list of simple types in c#', | |
1870 | 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc', | |
1871 | 'upload_date': '20130831', | |
1872 | 'uploader_id': 'kudvenkat', | |
1873 | 'uploader': 'kudvenkat', | |
976ae3ea | 1874 | 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q', |
1875 | 'like_count': int, | |
1876 | 'uploader_url': 'http://www.youtube.com/user/kudvenkat', | |
1877 | 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q', | |
1878 | 'live_status': 'not_live', | |
1879 | 'categories': ['Education'], | |
1880 | 'availability': 'public', | |
1881 | 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg', | |
1882 | 'tags': 'count:12', | |
1883 | 'playable_in_embed': True, | |
1884 | 'age_limit': 0, | |
1885 | 'view_count': int, | |
1886 | 'duration': 522, | |
1887 | 'channel': 'kudvenkat', | |
6c73052c | 1888 | 'channel_follower_count': int |
a0566bbf | 1889 | }, |
1890 | 'params': { | |
1891 | 'skip_download': True, | |
1892 | }, | |
1893 | }, | |
29f7c58a | 1894 | { |
1895 | # another example of '};' in ytInitialData | |
1896 | 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY', | |
1897 | 'only_matching': True, | |
1898 | }, | |
1899 | { | |
1900 | 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ', | |
1901 | 'only_matching': True, | |
1902 | }, | |
545cc85d | 1903 | { |
cc2db878 | 1904 | # https://github.com/ytdl-org/youtube-dl/pull/28094 |
1905 | 'url': 'OtqTfy26tG0', | |
1906 | 'info_dict': { | |
1907 | 'id': 'OtqTfy26tG0', | |
1908 | 'ext': 'mp4', | |
1909 | 'title': 'Burn Out', | |
1910 | 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131', | |
1911 | 'upload_date': '20141120', | |
1912 | 'uploader': 'The Cinematic Orchestra - Topic', | |
1913 | 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw', | |
1914 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw', | |
1915 | 'artist': 'The Cinematic Orchestra', | |
1916 | 'track': 'Burn Out', | |
1917 | 'album': 'Every Day', | |
976ae3ea | 1918 | 'like_count': int, |
1919 | 'live_status': 'not_live', | |
1920 | 'alt_title': 'Burn Out', | |
1921 | 'duration': 614, | |
1922 | 'age_limit': 0, | |
1923 | 'view_count': int, | |
1924 | 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw', | |
1925 | 'creator': 'The Cinematic Orchestra', | |
1926 | 'channel': 'The Cinematic Orchestra', | |
1927 | 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'], | |
1928 | 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw', | |
1929 | 'availability': 'public', | |
1930 | 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg', | |
1931 | 'categories': ['Music'], | |
1932 | 'playable_in_embed': True, | |
6c73052c | 1933 | 'channel_follower_count': int |
cc2db878 | 1934 | }, |
1935 | 'params': { | |
1936 | 'skip_download': True, | |
1937 | }, | |
545cc85d | 1938 | }, |
bc2ca1bb | 1939 | { |
1940 | # controversial video, only works with bpctr when authenticated with cookies | |
1941 | 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg', | |
1942 | 'only_matching': True, | |
1943 | }, | |
a1a7907b | 1944 | { |
1945 | # controversial video, requires bpctr/contentCheckOk | |
1946 | 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc', | |
1947 | 'info_dict': { | |
1948 | 'id': 'SZJvDhaSDnc', | |
1949 | 'ext': 'mp4', | |
1950 | 'title': 'San Diego teen commits suicide after bullying over embarrassing video', | |
1951 | 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ', | |
976ae3ea | 1952 | 'uploader': 'CBS Mornings', |
11f9be09 | 1953 | 'uploader_id': 'CBSThisMorning', |
a1a7907b | 1954 | 'upload_date': '20140716', |
976ae3ea | 1955 | 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7', |
1956 | 'duration': 170, | |
1957 | 'categories': ['News & Politics'], | |
1958 | 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning', | |
1959 | 'view_count': int, | |
1960 | 'channel': 'CBS Mornings', | |
1961 | 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'], | |
1962 | 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg', | |
1963 | 'age_limit': 18, | |
1964 | 'availability': 'needs_auth', | |
1965 | 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ', | |
1966 | 'like_count': int, | |
1967 | 'live_status': 'not_live', | |
1968 | 'playable_in_embed': True, | |
6c73052c | 1969 | 'channel_follower_count': int |
a1a7907b | 1970 | } |
1971 | }, | |
f7ad7160 | 1972 | { |
1973 | # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685 | |
1974 | 'url': 'cBvYw8_A0vQ', | |
1975 | 'info_dict': { | |
1976 | 'id': 'cBvYw8_A0vQ', | |
1977 | 'ext': 'mp4', | |
1978 | 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き', | |
1979 | 'description': 'md5:ea770e474b7cd6722b4c95b833c03630', | |
1980 | 'upload_date': '20201120', | |
1981 | 'uploader': 'Walk around Japan', | |
1982 | 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw', | |
1983 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw', | |
976ae3ea | 1984 | 'duration': 1456, |
1985 | 'categories': ['Travel & Events'], | |
1986 | 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw', | |
1987 | 'view_count': int, | |
1988 | 'channel': 'Walk around Japan', | |
1989 | 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'], | |
1990 | 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp', | |
1991 | 'age_limit': 0, | |
1992 | 'availability': 'public', | |
1993 | 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw', | |
1994 | 'live_status': 'not_live', | |
1995 | 'playable_in_embed': True, | |
6c73052c | 1996 | 'channel_follower_count': int |
f7ad7160 | 1997 | }, |
1998 | 'params': { | |
1999 | 'skip_download': True, | |
2000 | }, | |
0fb983f6 | 2001 | }, { |
2002 | # Has multiple audio streams | |
2003 | 'url': 'WaOKSUlf4TM', | |
2004 | 'only_matching': True | |
9297939e | 2005 | }, { |
2006 | # Requires Premium: has format 141 when requested using YTM url | |
2007 | 'url': 'https://music.youtube.com/watch?v=XclachpHxis', | |
2008 | 'only_matching': True | |
2009 | }, { | |
120916da | 2010 | # multiple subtitles with same lang_code |
2011 | 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug', | |
2012 | 'only_matching': True, | |
109dd3b2 | 2013 | }, { |
2014 | # Force use android client fallback | |
2015 | 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY', | |
2016 | 'info_dict': { | |
2017 | 'id': 'YOelRv7fMxY', | |
11f9be09 | 2018 | 'title': 'DIGGING A SECRET TUNNEL Part 1', |
109dd3b2 | 2019 | 'ext': '3gp', |
2020 | 'upload_date': '20210624', | |
2021 | 'channel_id': 'UCp68_FLety0O-n9QU6phsgw', | |
2022 | 'uploader': 'colinfurze', | |
11f9be09 | 2023 | 'uploader_id': 'colinfurze', |
109dd3b2 | 2024 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw', |
976ae3ea | 2025 | 'description': 'md5:5d5991195d599b56cd0c4148907eec50', |
2026 | 'duration': 596, | |
2027 | 'categories': ['Entertainment'], | |
2028 | 'uploader_url': 'http://www.youtube.com/user/colinfurze', | |
2029 | 'view_count': int, | |
2030 | 'channel': 'colinfurze', | |
2031 | 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'], | |
2032 | 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg', | |
2033 | 'age_limit': 0, | |
2034 | 'availability': 'public', | |
2035 | 'like_count': int, | |
2036 | 'live_status': 'not_live', | |
2037 | 'playable_in_embed': True, | |
6c73052c | 2038 | 'channel_follower_count': int |
109dd3b2 | 2039 | }, |
2040 | 'params': { | |
2041 | 'format': '17', # 3gp format available on android | |
2042 | 'extractor_args': {'youtube': {'player_client': ['android']}}, | |
2043 | }, | |
120916da | 2044 | }, |
109dd3b2 | 2045 | { |
2046 | # Skip download of additional client configs (remix client config in this case) | |
2047 | 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs', | |
2048 | 'only_matching': True, | |
2049 | 'params': { | |
2050 | 'extractor_args': {'youtube': {'player_skip': ['configs']}}, | |
2051 | }, | |
8fc54b12 | 2052 | }, { |
2053 | # shorts | |
2054 | 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY', | |
2055 | 'only_matching': True, | |
9222c381 | 2056 | }, { |
2057 | 'note': 'Storyboards', | |
2058 | 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8', | |
2059 | 'info_dict': { | |
2060 | 'id': '5KLPxDtMqe8', | |
2061 | 'ext': 'mhtml', | |
2062 | 'format_id': 'sb0', | |
2063 | 'title': 'Your Brain is Plastic', | |
2064 | 'uploader_id': 'scishow', | |
2065 | 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc', | |
2066 | 'upload_date': '20140324', | |
2067 | 'uploader': 'SciShow', | |
976ae3ea | 2068 | 'like_count': int, |
2069 | 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow', | |
2070 | 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow', | |
2071 | 'view_count': int, | |
2072 | 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg', | |
2073 | 'playable_in_embed': True, | |
2074 | 'tags': 'count:12', | |
2075 | 'uploader_url': 'http://www.youtube.com/user/scishow', | |
2076 | 'availability': 'public', | |
2077 | 'channel': 'SciShow', | |
2078 | 'live_status': 'not_live', | |
2079 | 'duration': 248, | |
2080 | 'categories': ['Education'], | |
2081 | 'age_limit': 0, | |
6c73052c | 2082 | 'channel_follower_count': int |
9222c381 | 2083 | }, 'params': {'format': 'mhtml', 'skip_download': True} |
992f9a73 | 2084 | }, { |
2085 | # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939) | |
2086 | 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4', | |
2087 | 'info_dict': { | |
2088 | 'id': '2NUZ8W2llS4', | |
2089 | 'ext': 'mp4', | |
2090 | 'title': 'The NP that test your phone performance 🙂', | |
2091 | 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d', | |
2092 | 'uploader': 'Leon Nguyen', | |
2093 | 'uploader_id': 'VNSXIII', | |
2094 | 'uploader_url': 'http://www.youtube.com/user/VNSXIII', | |
2095 | 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA', | |
2096 | 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA', | |
2097 | 'duration': 21, | |
2098 | 'view_count': int, | |
2099 | 'age_limit': 0, | |
2100 | 'categories': ['Gaming'], | |
2101 | 'tags': 'count:23', | |
2102 | 'playable_in_embed': True, | |
2103 | 'live_status': 'not_live', | |
2104 | 'upload_date': '20220103', | |
2105 | 'like_count': int, | |
2106 | 'availability': 'public', | |
2107 | 'channel': 'Leon Nguyen', | |
2108 | 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp', | |
2109 | 'channel_follower_count': int | |
2110 | } | |
2111 | }, { | |
2112 | # date text is premiered video, ensure upload date in UTC (published 1641172509) | |
2113 | 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM', | |
2114 | 'info_dict': { | |
2115 | 'id': 'mzZzzBU6lrM', | |
2116 | 'ext': 'mp4', | |
2117 | 'title': 'I Met GeorgeNotFound In Real Life...', | |
2118 | 'description': 'md5:cca98a355c7184e750f711f3a1b22c84', | |
2119 | 'uploader': 'Quackity', | |
2120 | 'uploader_id': 'QuackityHQ', | |
2121 | 'uploader_url': 'http://www.youtube.com/user/QuackityHQ', | |
2122 | 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q', | |
2123 | 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q', | |
2124 | 'duration': 955, | |
2125 | 'view_count': int, | |
2126 | 'age_limit': 0, | |
2127 | 'categories': ['Entertainment'], | |
2128 | 'tags': 'count:26', | |
2129 | 'playable_in_embed': True, | |
2130 | 'live_status': 'not_live', | |
2131 | 'release_timestamp': 1641172509, | |
2132 | 'release_date': '20220103', | |
2133 | 'upload_date': '20220103', | |
2134 | 'like_count': int, | |
2135 | 'availability': 'public', | |
2136 | 'channel': 'Quackity', | |
2137 | 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg', | |
2138 | 'channel_follower_count': int | |
2139 | } | |
2140 | }, | |
2141 | { # continuous livestream. Microformat upload date should be preferred. | |
2142 | # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27 | |
2143 | 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU', | |
2144 | 'info_dict': { | |
2145 | 'id': 'kgx4WGK0oNU', | |
2146 | '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}', | |
2147 | 'ext': 'mp4', | |
2148 | 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA', | |
2149 | 'availability': 'public', | |
2150 | 'age_limit': 0, | |
2151 | 'release_timestamp': 1637975704, | |
2152 | 'upload_date': '20210619', | |
2153 | 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA', | |
2154 | 'live_status': 'is_live', | |
2155 | 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg', | |
2156 | 'uploader': '阿鲍Abao', | |
2157 | 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA', | |
2158 | 'channel': 'Abao in Tokyo', | |
2159 | 'channel_follower_count': int, | |
2160 | 'release_date': '20211127', | |
2161 | 'tags': 'count:39', | |
2162 | 'categories': ['People & Blogs'], | |
2163 | 'like_count': int, | |
2164 | 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA', | |
2165 | 'view_count': int, | |
2166 | 'playable_in_embed': True, | |
2167 | 'description': 'md5:2ef1d002cad520f65825346e2084e49d', | |
2168 | }, | |
2169 | 'params': {'skip_download': True} | |
2170 | }, | |
2eb88d95 PH |
2171 | ] |
2172 | ||
201c1459 | 2173 | @classmethod |
2174 | def suitable(cls, url): | |
4dfbf869 | 2175 | from ..utils import parse_qs |
2176 | ||
201c1459 | 2177 | qs = parse_qs(url) |
2178 | if qs.get('list', [None])[0]: | |
2179 | return False | |
2180 | return super(YoutubeIE, cls).suitable(url) | |
2181 | ||
e0df6211 PH |
2182 | def __init__(self, *args, **kwargs): |
2183 | super(YoutubeIE, self).__init__(*args, **kwargs) | |
545cc85d | 2184 | self._code_cache = {} |
83799698 | 2185 | self._player_cache = {} |
e0df6211 | 2186 | |
adbc4ec4 | 2187 | def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data): |
adbc4ec4 THD |
2188 | lock = threading.Lock() |
2189 | ||
2190 | is_live = True | |
185bf310 | 2191 | start_time = time.time() |
adbc4ec4 THD |
2192 | formats = [f for f in formats if f.get('is_from_start')] |
2193 | ||
185bf310 | 2194 | def refetch_manifest(format_id, delay): |
2195 | nonlocal formats, start_time, is_live | |
2196 | if time.time() <= start_time + delay: | |
adbc4ec4 THD |
2197 | return |
2198 | ||
2199 | _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url) | |
2200 | video_details = traverse_obj( | |
2201 | prs, (..., 'videoDetails'), expected_type=dict, default=[]) | |
2202 | microformats = traverse_obj( | |
2203 | prs, (..., 'microformat', 'playerMicroformatRenderer'), | |
2204 | expected_type=dict, default=[]) | |
2205 | _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url) | |
185bf310 | 2206 | start_time = time.time() |
adbc4ec4 | 2207 | |
185bf310 | 2208 | def mpd_feed(format_id, delay): |
adbc4ec4 THD |
2209 | """ |
2210 | @returns (manifest_url, manifest_stream_number, is_live) or None | |
2211 | """ | |
2212 | with lock: | |
185bf310 | 2213 | refetch_manifest(format_id, delay) |
adbc4ec4 THD |
2214 | |
2215 | f = next((f for f in formats if f['format_id'] == format_id), None) | |
2216 | if not f: | |
185bf310 | 2217 | if not is_live: |
2218 | self.to_screen(f'{video_id}: Video is no longer live') | |
2219 | else: | |
2220 | self.report_warning( | |
2221 | f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}') | |
adbc4ec4 THD |
2222 | return None |
2223 | return f['manifest_url'], f['manifest_stream_number'], is_live | |
2224 | ||
2225 | for f in formats: | |
a539f065 | 2226 | f['is_live'] = True |
adbc4ec4 THD |
2227 | f['protocol'] = 'http_dash_segments_generator' |
2228 | f['fragments'] = functools.partial( | |
2229 | self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed) | |
2230 | ||
2231 | def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx): | |
2232 | FETCH_SPAN, MAX_DURATION = 5, 432000 | |
2233 | ||
2234 | mpd_url, stream_number, is_live = None, None, True | |
2235 | ||
2236 | begin_index = 0 | |
2237 | download_start_time = ctx.get('start') or time.time() | |
2238 | ||
2239 | lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION | |
2240 | if lack_early_segments: | |
2241 | self.report_warning(bug_reports_message( | |
2242 | 'Starting download from the last 120 hours of the live stream since ' | |
2243 | 'YouTube does not have data before that. If you think this is wrong,'), only_once=True) | |
2244 | lack_early_segments = True | |
2245 | ||
2246 | known_idx, no_fragment_score, last_segment_url = begin_index, 0, None | |
2247 | fragments, fragment_base_url = None, None | |
2248 | ||
a539f065 | 2249 | def _extract_sequence_from_mpd(refresh_sequence, immediate): |
adbc4ec4 THD |
2250 | nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url |
2251 | # Obtain from MPD's maximum seq value | |
2252 | old_mpd_url = mpd_url | |
185bf310 | 2253 | last_error = ctx.pop('last_error', None) |
a539f065 | 2254 | expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403 |
185bf310 | 2255 | mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000) |
2256 | or (mpd_url, stream_number, False)) | |
2257 | if not refresh_sequence: | |
2258 | if expire_fast and not is_live: | |
2259 | return False, last_seq | |
2260 | elif old_mpd_url == mpd_url: | |
2261 | return True, last_seq | |
adbc4ec4 THD |
2262 | try: |
2263 | fmts, _ = self._extract_mpd_formats_and_subtitles( | |
2264 | mpd_url, None, note=False, errnote=False, fatal=False) | |
2265 | except ExtractorError: | |
2266 | fmts = None | |
2267 | if not fmts: | |
a539f065 | 2268 | no_fragment_score += 2 |
adbc4ec4 THD |
2269 | return False, last_seq |
2270 | fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number) | |
2271 | fragments = fmt_info['fragments'] | |
2272 | fragment_base_url = fmt_info['fragment_base_url'] | |
2273 | assert fragment_base_url | |
2274 | ||
2275 | _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1)) | |
2276 | return True, _last_seq | |
2277 | ||
2278 | while is_live: | |
2279 | fetch_time = time.time() | |
2280 | if no_fragment_score > 30: | |
2281 | return | |
2282 | if last_segment_url: | |
2283 | # Obtain from "X-Head-Seqnum" header value from each segment | |
2284 | try: | |
2285 | urlh = self._request_webpage( | |
2286 | last_segment_url, None, note=False, errnote=False, fatal=False) | |
2287 | except ExtractorError: | |
2288 | urlh = None | |
2289 | last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum'])) | |
2290 | if last_seq is None: | |
a539f065 | 2291 | no_fragment_score += 2 |
adbc4ec4 THD |
2292 | last_segment_url = None |
2293 | continue | |
2294 | else: | |
a539f065 LNO |
2295 | should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15) |
2296 | no_fragment_score += 2 | |
185bf310 | 2297 | if not should_continue: |
adbc4ec4 THD |
2298 | continue |
2299 | ||
2300 | if known_idx > last_seq: | |
2301 | last_segment_url = None | |
2302 | continue | |
2303 | ||
2304 | last_seq += 1 | |
2305 | ||
2306 | if begin_index < 0 and known_idx < 0: | |
2307 | # skip from the start when it's negative value | |
2308 | known_idx = last_seq + begin_index | |
2309 | if lack_early_segments: | |
2310 | known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration'])) | |
2311 | try: | |
2312 | for idx in range(known_idx, last_seq): | |
2313 | # do not update sequence here or you'll get skipped some part of it | |
a539f065 | 2314 | should_continue, _ = _extract_sequence_from_mpd(False, False) |
185bf310 | 2315 | if not should_continue: |
adbc4ec4 THD |
2316 | known_idx = idx - 1 |
2317 | raise ExtractorError('breaking out of outer loop') | |
2318 | last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx) | |
2319 | yield { | |
2320 | 'url': last_segment_url, | |
2321 | } | |
2322 | if known_idx == last_seq: | |
2323 | no_fragment_score += 5 | |
2324 | else: | |
2325 | no_fragment_score = 0 | |
2326 | known_idx = last_seq | |
2327 | except ExtractorError: | |
2328 | continue | |
2329 | ||
2330 | time.sleep(max(0, FETCH_SPAN + fetch_time - time.time())) | |
2331 | ||
b6de707d | 2332 | def _extract_player_url(self, *ytcfgs, webpage=None): |
2333 | player_url = traverse_obj( | |
2334 | ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'), | |
2335 | get_all=False, expected_type=compat_str) | |
11f9be09 | 2336 | if not player_url: |
b6de707d | 2337 | return |
60f393e4 | 2338 | return urljoin('https://www.youtube.com', player_url) |
109dd3b2 | 2339 | |
b6de707d | 2340 | def _download_player_url(self, video_id, fatal=False): |
2341 | res = self._download_webpage( | |
2342 | 'https://www.youtube.com/iframe_api', | |
2343 | note='Downloading iframe API JS', video_id=video_id, fatal=fatal) | |
2344 | if res: | |
2345 | player_version = self._search_regex( | |
2346 | r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal) | |
2347 | if player_version: | |
2348 | return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js' | |
2349 | ||
60064c53 PH |
2350 | def _signature_cache_id(self, example_sig): |
2351 | """ Return a string representation of a signature """ | |
78caa52a | 2352 | return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) |
60064c53 | 2353 | |
e40c758c S |
2354 | @classmethod |
2355 | def _extract_player_info(cls, player_url): | |
2356 | for player_re in cls._PLAYER_INFO_RE: | |
2357 | id_m = re.search(player_re, player_url) | |
2358 | if id_m: | |
2359 | break | |
2360 | else: | |
c081b35c | 2361 | raise ExtractorError('Cannot identify player %r' % player_url) |
545cc85d | 2362 | return id_m.group('id') |
e40c758c | 2363 | |
404f611f | 2364 | def _load_player(self, video_id, player_url, fatal=True): |
109dd3b2 | 2365 | player_id = self._extract_player_info(player_url) |
2366 | if player_id not in self._code_cache: | |
1276a43a | 2367 | code = self._download_webpage( |
109dd3b2 | 2368 | player_url, video_id, fatal=fatal, |
2369 | note='Downloading player ' + player_id, | |
2370 | errnote='Download of %s failed' % player_url) | |
1276a43a | 2371 | if code: |
2372 | self._code_cache[player_id] = code | |
404f611f | 2373 | return self._code_cache.get(player_id) |
109dd3b2 | 2374 | |
e40c758c | 2375 | def _extract_signature_function(self, video_id, player_url, example_sig): |
545cc85d | 2376 | player_id = self._extract_player_info(player_url) |
e0df6211 | 2377 | |
c4417ddb | 2378 | # Read from filesystem cache |
545cc85d | 2379 | func_id = 'js_%s_%s' % ( |
2380 | player_id, self._signature_cache_id(example_sig)) | |
c4417ddb | 2381 | assert os.path.basename(func_id) == func_id |
a0e07d31 | 2382 | |
69ea8ca4 | 2383 | cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) |
a0e07d31 | 2384 | if cache_spec is not None: |
78caa52a | 2385 | return lambda s: ''.join(s[i] for i in cache_spec) |
83799698 | 2386 | |
404f611f | 2387 | code = self._load_player(video_id, player_url) |
2388 | if code: | |
109dd3b2 | 2389 | res = self._parse_sig_js(code) |
e0df6211 | 2390 | |
109dd3b2 | 2391 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
2392 | cache_res = res(test_string) | |
2393 | cache_spec = [ord(c) for c in cache_res] | |
83799698 | 2394 | |
109dd3b2 | 2395 | self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) |
2396 | return res | |
83799698 | 2397 | |
60064c53 | 2398 | def _print_sig_code(self, func, example_sig): |
404f611f | 2399 | if not self.get_param('youtube_print_sig_code'): |
2400 | return | |
2401 | ||
edf3e38e PH |
2402 | def gen_sig_code(idxs): |
2403 | def _genslice(start, end, step): | |
78caa52a | 2404 | starts = '' if start == 0 else str(start) |
8bcc8756 | 2405 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' |
69ea8ca4 | 2406 | steps = '' if step == 1 else (':%d' % step) |
78caa52a | 2407 | return 's[%s%s%s]' % (starts, ends, steps) |
edf3e38e PH |
2408 | |
2409 | step = None | |
7af808a5 PH |
2410 | # Quelch pyflakes warnings - start will be set when step is set |
2411 | start = '(Never used)' | |
edf3e38e PH |
2412 | for i, prev in zip(idxs[1:], idxs[:-1]): |
2413 | if step is not None: | |
2414 | if i - prev == step: | |
2415 | continue | |
2416 | yield _genslice(start, prev, step) | |
2417 | step = None | |
2418 | continue | |
2419 | if i - prev in [-1, 1]: | |
2420 | step = i - prev | |
2421 | start = prev | |
2422 | continue | |
2423 | else: | |
78caa52a | 2424 | yield 's[%d]' % prev |
edf3e38e | 2425 | if step is None: |
78caa52a | 2426 | yield 's[%d]' % i |
edf3e38e PH |
2427 | else: |
2428 | yield _genslice(start, i, step) | |
2429 | ||
78caa52a | 2430 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
c705320f | 2431 | cache_res = func(test_string) |
edf3e38e | 2432 | cache_spec = [ord(c) for c in cache_res] |
78caa52a | 2433 | expr_code = ' + '.join(gen_sig_code(cache_spec)) |
60064c53 PH |
2434 | signature_id_tuple = '(%s)' % ( |
2435 | ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) | |
69ea8ca4 | 2436 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' |
78caa52a | 2437 | ' return %s\n') % (signature_id_tuple, expr_code) |
69ea8ca4 | 2438 | self.to_screen('Extracted signature function:\n' + code) |
edf3e38e | 2439 | |
e0df6211 PH |
2440 | def _parse_sig_js(self, jscode): |
2441 | funcname = self._search_regex( | |
abefc03f S |
2442 | (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', |
2443 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
858a65ec P |
2444 | r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)', |
2445 | r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)', | |
2446 | 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}\(a,\d+\)', | |
2447 | 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\(\s*""\s*\)', | |
31ce6e99 | 2448 | r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', |
abefc03f S |
2449 | # Obsolete patterns |
2450 | r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
9a47fa35 | 2451 | r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(', |
abefc03f S |
2452 | r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(', |
2453 | r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2454 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2455 | r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2456 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2457 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('), | |
3c90cc8b | 2458 | jscode, 'Initial JS player signature function name', group='sig') |
2b25cb5d PH |
2459 | |
2460 | jsi = JSInterpreter(jscode) | |
2461 | initial_function = jsi.extract_function(funcname) | |
e0df6211 PH |
2462 | return lambda s: initial_function([s]) |
2463 | ||
545cc85d | 2464 | def _decrypt_signature(self, s, video_id, player_url): |
257a2501 | 2465 | """Turn the encrypted s field into a working signature""" |
6b37f0be | 2466 | |
c8bf86d5 | 2467 | if player_url is None: |
69ea8ca4 | 2468 | raise ExtractorError('Cannot decrypt signature without player_url') |
920de7a2 | 2469 | |
c8bf86d5 | 2470 | try: |
62af3a0e | 2471 | player_id = (player_url, self._signature_cache_id(s)) |
c8bf86d5 PH |
2472 | if player_id not in self._player_cache: |
2473 | func = self._extract_signature_function( | |
60064c53 | 2474 | video_id, player_url, s |
c8bf86d5 PH |
2475 | ) |
2476 | self._player_cache[player_id] = func | |
2477 | func = self._player_cache[player_id] | |
404f611f | 2478 | self._print_sig_code(func, s) |
c8bf86d5 PH |
2479 | return func(s) |
2480 | except Exception as e: | |
404f611f | 2481 | raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e) |
2482 | ||
2483 | def _decrypt_nsig(self, s, video_id, player_url): | |
2484 | """Turn the encrypted n field into a working signature""" | |
2485 | if player_url is None: | |
2486 | raise ExtractorError('Cannot decrypt nsig without player_url') | |
60f393e4 | 2487 | player_url = urljoin('https://www.youtube.com', player_url) |
404f611f | 2488 | |
2489 | sig_id = ('nsig_value', s) | |
2490 | if sig_id in self._player_cache: | |
2491 | return self._player_cache[sig_id] | |
2492 | ||
2493 | try: | |
2494 | player_id = ('nsig', player_url) | |
2495 | if player_id not in self._player_cache: | |
2496 | self._player_cache[player_id] = self._extract_n_function(video_id, player_url) | |
2497 | func = self._player_cache[player_id] | |
2498 | self._player_cache[sig_id] = func(s) | |
2499 | self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}') | |
2500 | return self._player_cache[sig_id] | |
2501 | except Exception as e: | |
aa9369a2 | 2502 | raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id) |
404f611f | 2503 | |
2504 | def _extract_n_function_name(self, jscode): | |
48416bc4 | 2505 | nfunc, idx = self._search_regex( |
c571b3a6 | 2506 | r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)', |
48416bc4 | 2507 | jscode, 'Initial JS player n function name', group=('nfunc', 'idx')) |
2508 | if not idx: | |
2509 | return nfunc | |
2510 | return json.loads(js_to_json(self._search_regex( | |
a7d4acc0 | 2511 | rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode, |
48416bc4 | 2512 | f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)] |
404f611f | 2513 | |
2514 | def _extract_n_function(self, video_id, player_url): | |
2515 | player_id = self._extract_player_info(player_url) | |
2516 | func_code = self._downloader.cache.load('youtube-nsig', player_id) | |
2517 | ||
2518 | if func_code: | |
2519 | jsi = JSInterpreter(func_code) | |
2520 | else: | |
2521 | jscode = self._load_player(video_id, player_url) | |
2522 | funcname = self._extract_n_function_name(jscode) | |
2523 | jsi = JSInterpreter(jscode) | |
2524 | func_code = jsi.extract_function_code(funcname) | |
2525 | self._downloader.cache.store('youtube-nsig', player_id, func_code) | |
2526 | ||
2527 | if self.get_param('youtube_print_sig_code'): | |
2528 | self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n') | |
2529 | ||
2530 | return lambda s: jsi.extract_function_from_code(*func_code)([s]) | |
e0df6211 | 2531 | |
109dd3b2 | 2532 | def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False): |
2533 | """ | |
2534 | Extract signatureTimestamp (sts) | |
2535 | Required to tell API what sig/player version is in use. | |
2536 | """ | |
2537 | sts = None | |
2538 | if isinstance(ytcfg, dict): | |
2539 | sts = int_or_none(ytcfg.get('STS')) | |
2540 | ||
2541 | if not sts: | |
2542 | # Attempt to extract from player | |
2543 | if player_url is None: | |
2544 | error_msg = 'Cannot extract signature timestamp without player_url.' | |
2545 | if fatal: | |
2546 | raise ExtractorError(error_msg) | |
2547 | self.report_warning(error_msg) | |
2548 | return | |
404f611f | 2549 | code = self._load_player(video_id, player_url, fatal=fatal) |
2550 | if code: | |
109dd3b2 | 2551 | sts = int_or_none(self._search_regex( |
2552 | r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code, | |
2553 | 'JS player signature timestamp', group='sts', fatal=fatal)) | |
2554 | return sts | |
2555 | ||
11f9be09 | 2556 | def _mark_watched(self, video_id, player_responses): |
9222c381 | 2557 | playback_url = get_first( |
2558 | player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'), | |
2559 | expected_type=url_or_none) | |
d77ab8e2 | 2560 | if not playback_url: |
352d63fd | 2561 | self.report_warning('Unable to mark watched') |
d77ab8e2 S |
2562 | return |
2563 | parsed_playback_url = compat_urlparse.urlparse(playback_url) | |
2564 | qs = compat_urlparse.parse_qs(parsed_playback_url.query) | |
2565 | ||
2566 | # cpn generation algorithm is reverse engineered from base.js. | |
2567 | # In fact it works even with dummy cpn. | |
2568 | CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_' | |
2569 | cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))) | |
2570 | ||
2571 | qs.update({ | |
2572 | 'ver': ['2'], | |
2573 | 'cpn': [cpn], | |
2574 | }) | |
2575 | playback_url = compat_urlparse.urlunparse( | |
15707c7e | 2576 | parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True))) |
d77ab8e2 S |
2577 | |
2578 | self._download_webpage( | |
2579 | playback_url, video_id, 'Marking watched', | |
2580 | 'Unable to mark watched', fatal=False) | |
2581 | ||
66c9fa36 S |
2582 | @staticmethod |
2583 | def _extract_urls(webpage): | |
2584 | # Embedded YouTube player | |
2585 | entries = [ | |
2586 | unescapeHTML(mobj.group('url')) | |
2587 | for mobj in re.finditer(r'''(?x) | |
2588 | (?: | |
2589 | <iframe[^>]+?src=| | |
2590 | data-video-url=| | |
2591 | <embed[^>]+?src=| | |
2592 | embedSWF\(?:\s*| | |
2593 | <object[^>]+data=| | |
2594 | new\s+SWFObject\( | |
2595 | ) | |
2596 | (["\']) | |
2597 | (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ | |
f2332f18 | 2598 | (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?) |
66c9fa36 S |
2599 | \1''', webpage)] |
2600 | ||
2601 | # lazyYT YouTube embed | |
2602 | entries.extend(list(map( | |
2603 | unescapeHTML, | |
2604 | re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)))) | |
2605 | ||
2606 | # Wordpress "YouTube Video Importer" plugin | |
2607 | matches = re.findall(r'''(?x)<div[^>]+ | |
2608 | class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+ | |
2609 | data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage) | |
2610 | entries.extend(m[-1] for m in matches) | |
2611 | ||
2612 | return entries | |
2613 | ||
2614 | @staticmethod | |
2615 | def _extract_url(webpage): | |
2616 | urls = YoutubeIE._extract_urls(webpage) | |
2617 | return urls[0] if urls else None | |
2618 | ||
97665381 PH |
2619 | @classmethod |
2620 | def extract_id(cls, url): | |
2621 | mobj = re.match(cls._VALID_URL, url, re.VERBOSE) | |
c5e8d7af | 2622 | if mobj is None: |
69ea8ca4 | 2623 | raise ExtractorError('Invalid URL: %s' % url) |
5ad28e7f | 2624 | return mobj.group('id') |
c5e8d7af | 2625 | |
7c365c21 | 2626 | def _extract_chapters_from_json(self, data, duration): |
2627 | chapter_list = traverse_obj( | |
2628 | data, ( | |
2629 | 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer', | |
2630 | 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters' | |
2631 | ), expected_type=list) | |
2632 | ||
2633 | return self._extract_chapters( | |
2634 | chapter_list, | |
2635 | chapter_time=lambda chapter: float_or_none( | |
2636 | traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000), | |
2637 | chapter_title=lambda chapter: traverse_obj( | |
2638 | chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str), | |
2639 | duration=duration) | |
2640 | ||
2641 | def _extract_chapters_from_engagement_panel(self, data, duration): | |
2642 | content_list = traverse_obj( | |
8bdd16b4 | 2643 | data, |
7c365c21 | 2644 | ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'), |
da503b7a | 2645 | expected_type=list, default=[]) |
052e1350 | 2646 | chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription')) |
2647 | chapter_title = lambda chapter: self._get_text(chapter, 'title') | |
7c365c21 | 2648 | |
2649 | return next(( | |
2650 | filter(None, ( | |
2651 | self._extract_chapters( | |
2652 | traverse_obj(contents, (..., 'macroMarkersListItemRenderer')), | |
2653 | chapter_time, chapter_title, duration) | |
2654 | for contents in content_list | |
2655 | ))), []) | |
2656 | ||
2657 | def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration): | |
84213ea8 | 2658 | chapters = [] |
7c365c21 | 2659 | last_chapter = {'start_time': 0} |
2660 | for idx, chapter in enumerate(chapter_list or []): | |
2661 | title = chapter_title(chapter) | |
84213ea8 S |
2662 | start_time = chapter_time(chapter) |
2663 | if start_time is None: | |
2664 | continue | |
7c365c21 | 2665 | last_chapter['end_time'] = start_time |
2666 | if start_time < last_chapter['start_time']: | |
2667 | if idx == 1: | |
2668 | chapters.pop() | |
2669 | self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title']) | |
2670 | else: | |
2671 | self.report_warning(f'Invalid start time for chapter "{title}"') | |
2672 | continue | |
2673 | last_chapter = {'start_time': start_time, 'title': title} | |
2674 | chapters.append(last_chapter) | |
2675 | last_chapter['end_time'] = duration | |
84213ea8 S |
2676 | return chapters |
2677 | ||
545cc85d | 2678 | def _extract_yt_initial_variable(self, webpage, regex, video_id, name): |
2679 | return self._parse_json(self._search_regex( | |
2680 | (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE), | |
2681 | regex), webpage, name, default='{}'), video_id, fatal=False) | |
84213ea8 | 2682 | |
a1c5d2ca M |
2683 | def _extract_comment(self, comment_renderer, parent=None): |
2684 | comment_id = comment_renderer.get('commentId') | |
2685 | if not comment_id: | |
2686 | return | |
fe93e2c4 | 2687 | |
052e1350 | 2688 | text = self._get_text(comment_renderer, 'contentText') |
fe93e2c4 | 2689 | |
49bd8c66 | 2690 | # note: timestamp is an estimate calculated from the current time and time_text |
f3aa3c3f | 2691 | timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText') |
052e1350 | 2692 | author = self._get_text(comment_renderer, 'authorText') |
a1c5d2ca M |
2693 | author_id = try_get(comment_renderer, |
2694 | lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str) | |
fe93e2c4 | 2695 | |
49bd8c66 | 2696 | votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'], |
2697 | lambda x: x['likeCount']), compat_str)) or 0 | |
a1c5d2ca M |
2698 | author_thumbnail = try_get(comment_renderer, |
2699 | lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str) | |
2700 | ||
2701 | author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool) | |
97524332 | 2702 | is_favorited = 'creatorHeart' in (try_get( |
2703 | comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {}) | |
a1c5d2ca M |
2704 | return { |
2705 | 'id': comment_id, | |
2706 | 'text': text, | |
d92f5d5a | 2707 | 'timestamp': timestamp, |
a1c5d2ca M |
2708 | 'time_text': time_text, |
2709 | 'like_count': votes, | |
97524332 | 2710 | 'is_favorited': is_favorited, |
a1c5d2ca M |
2711 | 'author': author, |
2712 | 'author_id': author_id, | |
2713 | 'author_thumbnail': author_thumbnail, | |
2714 | 'author_is_uploader': author_is_uploader, | |
2715 | 'parent': parent or 'root' | |
2716 | } | |
2717 | ||
46383212 | 2718 | def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None): |
2719 | ||
2720 | get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0] | |
2d6659b9 | 2721 | |
2722 | def extract_header(contents): | |
2d6659b9 | 2723 | _continuation = None |
2724 | for content in contents: | |
46383212 | 2725 | comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer') |
f0d785d3 | 2726 | expected_comment_count = self._get_count( |
2727 | comments_header_renderer, 'countText', 'commentsCount') | |
fe93e2c4 | 2728 | |
2d6659b9 | 2729 | if expected_comment_count: |
46383212 | 2730 | tracker['est_total'] = expected_comment_count |
2731 | self.to_screen(f'Downloading ~{expected_comment_count} comments') | |
2732 | comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top | |
2d6659b9 | 2733 | |
2734 | sort_menu_item = try_get( | |
2735 | comments_header_renderer, | |
2736 | lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {} | |
2737 | sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {} | |
2738 | ||
2739 | _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item) | |
2740 | if not _continuation: | |
2741 | continue | |
2742 | ||
46383212 | 2743 | sort_text = str_or_none(sort_menu_item.get('title')) |
2744 | if not sort_text: | |
2d6659b9 | 2745 | sort_text = 'top comments' if comment_sort_index == 0 else 'newest first' |
46383212 | 2746 | self.to_screen('Sorting comments by %s' % sort_text.lower()) |
2d6659b9 | 2747 | break |
a2160aa4 | 2748 | return _continuation |
a1c5d2ca | 2749 | |
2d6659b9 | 2750 | def extract_thread(contents): |
a1c5d2ca | 2751 | if not parent: |
46383212 | 2752 | tracker['current_page_thread'] = 0 |
a1c5d2ca | 2753 | for content in contents: |
46383212 | 2754 | if not parent and tracker['total_parent_comments'] >= max_parents: |
2755 | yield | |
a1c5d2ca | 2756 | comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer']) |
46383212 | 2757 | comment_renderer = get_first( |
2758 | (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]], | |
2759 | expected_type=dict, default={}) | |
a1c5d2ca | 2760 | |
a1c5d2ca M |
2761 | comment = self._extract_comment(comment_renderer, parent) |
2762 | if not comment: | |
2763 | continue | |
46383212 | 2764 | |
2765 | tracker['running_total'] += 1 | |
2766 | tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1 | |
a1c5d2ca | 2767 | yield comment |
46383212 | 2768 | |
a1c5d2ca M |
2769 | # Attempt to get the replies |
2770 | comment_replies_renderer = try_get( | |
2771 | comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict) | |
2772 | ||
2773 | if comment_replies_renderer: | |
46383212 | 2774 | tracker['current_page_thread'] += 1 |
a1c5d2ca | 2775 | comment_entries_iter = self._comment_entries( |
99e9e001 | 2776 | comment_replies_renderer, ytcfg, video_id, |
46383212 | 2777 | parent=comment.get('id'), tracker=tracker) |
2778 | for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))): | |
a1c5d2ca M |
2779 | yield reply_comment |
2780 | ||
46383212 | 2781 | # Keeps track of counts across recursive calls |
2782 | if not tracker: | |
2783 | tracker = dict( | |
2784 | running_total=0, | |
2785 | est_total=0, | |
2786 | current_page_thread=0, | |
2787 | total_parent_comments=0, | |
2788 | total_reply_comments=0) | |
2789 | ||
2790 | # TODO: Deprecated | |
2d6659b9 | 2791 | # YouTube comments have a max depth of 2 |
46383212 | 2792 | max_depth = int_or_none(get_single_config_arg('max_comment_depth')) |
2793 | if max_depth: | |
2794 | self._downloader.deprecation_warning( | |
2795 | '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.') | |
2d6659b9 | 2796 | if max_depth == 1 and parent: |
2797 | return | |
a1c5d2ca | 2798 | |
46383212 | 2799 | max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map( |
2800 | lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4) | |
2d6659b9 | 2801 | |
46383212 | 2802 | continuation = self._extract_continuation(root_continuation_data) |
aae16f6e | 2803 | message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1) |
2804 | if message and not parent: | |
2805 | self.report_warning(message, video_id=video_id) | |
2806 | ||
46383212 | 2807 | response = None |
2d6659b9 | 2808 | is_first_continuation = parent is None |
a1c5d2ca M |
2809 | |
2810 | for page_num in itertools.count(0): | |
2811 | if not continuation: | |
2812 | break | |
46383212 | 2813 | headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)) |
2814 | comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})" | |
2d6659b9 | 2815 | if page_num == 0: |
2816 | if is_first_continuation: | |
2817 | note_prefix = 'Downloading comment section API JSON' | |
a1c5d2ca | 2818 | else: |
2d6659b9 | 2819 | note_prefix = ' Downloading comment API JSON reply thread %d %s' % ( |
46383212 | 2820 | tracker['current_page_thread'], comment_prog_str) |
2d6659b9 | 2821 | else: |
2822 | note_prefix = '%sDownloading comment%s API JSON page %d %s' % ( | |
2823 | ' ' if parent else '', ' replies' if parent else '', | |
2824 | page_num, comment_prog_str) | |
2825 | ||
2826 | response = self._extract_response( | |
fe93e2c4 | 2827 | item_id=None, query=continuation, |
2d6659b9 | 2828 | ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix, |
46383212 | 2829 | check_get_keys='onResponseReceivedEndpoints') |
a1c5d2ca | 2830 | |
46383212 | 2831 | continuation_contents = traverse_obj( |
2832 | response, 'onResponseReceivedEndpoints', expected_type=list, default=[]) | |
a1c5d2ca | 2833 | |
2d6659b9 | 2834 | continuation = None |
46383212 | 2835 | for continuation_section in continuation_contents: |
2836 | continuation_items = traverse_obj( | |
2837 | continuation_section, | |
2838 | (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'), | |
2839 | get_all=False, expected_type=list) or [] | |
2840 | if is_first_continuation: | |
2841 | continuation = extract_header(continuation_items) | |
2842 | is_first_continuation = False | |
2d6659b9 | 2843 | if continuation: |
a1c5d2ca | 2844 | break |
46383212 | 2845 | continue |
a1c5d2ca | 2846 | |
46383212 | 2847 | for entry in extract_thread(continuation_items): |
2848 | if not entry: | |
2849 | return | |
2850 | yield entry | |
2851 | continuation = self._extract_continuation({'contents': continuation_items}) | |
2852 | if continuation: | |
2d6659b9 | 2853 | break |
a1c5d2ca | 2854 | |
a2160aa4 | 2855 | def _get_comments(self, ytcfg, video_id, contents, webpage): |
a1c5d2ca | 2856 | """Entry for comment extraction""" |
2d6659b9 | 2857 | def _real_comment_extract(contents): |
aae16f6e | 2858 | renderer = next(( |
2859 | item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={}) | |
2860 | if item.get('sectionIdentifier') == 'comment-item-section'), None) | |
2861 | yield from self._comment_entries(renderer, ytcfg, video_id) | |
99e9e001 | 2862 | |
a2160aa4 | 2863 | max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0]) |
a2160aa4 | 2864 | return itertools.islice(_real_comment_extract(contents), 0, max_comments) |
a1c5d2ca | 2865 | |
109dd3b2 | 2866 | @staticmethod |
99e9e001 | 2867 | def _get_checkok_params(): |
2868 | return {'contentCheckOk': True, 'racyCheckOk': True} | |
2869 | ||
2870 | @classmethod | |
2871 | def _generate_player_context(cls, sts=None): | |
109dd3b2 | 2872 | context = { |
2873 | 'html5Preference': 'HTML5_PREF_WANTS', | |
2874 | } | |
2875 | if sts is not None: | |
2876 | context['signatureTimestamp'] = sts | |
2877 | return { | |
2878 | 'playbackContext': { | |
2879 | 'contentPlaybackContext': context | |
a1a7907b | 2880 | }, |
99e9e001 | 2881 | **cls._get_checkok_params() |
109dd3b2 | 2882 | } |
2883 | ||
e7e94f2a D |
2884 | @staticmethod |
2885 | def _is_agegated(player_response): | |
2886 | if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')): | |
9275f62c | 2887 | return True |
e7e94f2a D |
2888 | |
2889 | reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[]) | |
2890 | AGE_GATE_REASONS = ( | |
2891 | 'confirm your age', 'age-restricted', 'inappropriate', # reason | |
2892 | 'age_verification_required', 'age_check_required', # status | |
2893 | ) | |
2894 | return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons) | |
2895 | ||
2896 | @staticmethod | |
2897 | def _is_unplayable(player_response): | |
2898 | return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE' | |
9275f62c | 2899 | |
99e9e001 | 2900 | def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr): |
109dd3b2 | 2901 | |
11f9be09 | 2902 | session_index = self._extract_session_index(player_ytcfg, master_ytcfg) |
2903 | syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr) | |
b6de707d | 2904 | sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None |
11f9be09 | 2905 | headers = self.generate_api_headers( |
99e9e001 | 2906 | ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client) |
9297939e | 2907 | |
11f9be09 | 2908 | yt_query = {'videoId': video_id} |
2909 | yt_query.update(self._generate_player_context(sts)) | |
2910 | return self._extract_response( | |
2911 | item_id=video_id, ep='player', query=yt_query, | |
379e44ed | 2912 | ytcfg=player_ytcfg, headers=headers, fatal=True, |
000c15a4 | 2913 | default_client=client, |
11f9be09 | 2914 | note='Downloading %s player API JSON' % client.replace('_', ' ').strip() |
2915 | ) or None | |
2916 | ||
11f9be09 | 2917 | def _get_requested_clients(self, url, smuggled_data): |
b4c055ba | 2918 | requested_clients = [] |
d0d012d4 | 2919 | default = ['android', 'web'] |
000c15a4 | 2920 | allowed_clients = sorted( |
2921 | [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'], | |
2922 | key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True) | |
b4c055ba | 2923 | for client in self._configuration_arg('player_client'): |
2924 | if client in allowed_clients: | |
2925 | requested_clients.append(client) | |
d0d012d4 | 2926 | elif client == 'default': |
2927 | requested_clients.extend(default) | |
b4c055ba | 2928 | elif client == 'all': |
2929 | requested_clients.extend(allowed_clients) | |
2930 | else: | |
2931 | self.report_warning(f'Skipping unsupported client {client}') | |
11f9be09 | 2932 | if not requested_clients: |
d0d012d4 | 2933 | requested_clients = default |
cf7e015f | 2934 | |
11f9be09 | 2935 | if smuggled_data.get('is_music_url') or self.is_music_url(url): |
2936 | requested_clients.extend( | |
e7e94f2a | 2937 | f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS) |
dbdaaa23 | 2938 | |
11f9be09 | 2939 | return orderedSet(requested_clients) |
cf7e015f | 2940 | |
c0bc527b M |
2941 | def _extract_player_ytcfg(self, client, video_id): |
2942 | url = { | |
2943 | 'web_music': 'https://music.youtube.com', | |
2944 | 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1' | |
2945 | }.get(client) | |
2946 | if not url: | |
2947 | return {} | |
18c7683d | 2948 | webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip()) |
c0bc527b M |
2949 | return self.extract_ytcfg(video_id, webpage) or {} |
2950 | ||
99e9e001 | 2951 | def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg): |
11f9be09 | 2952 | initial_pr = None |
2953 | if webpage: | |
2954 | initial_pr = self._extract_yt_initial_variable( | |
2955 | webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE, | |
2956 | video_id, 'initial player response') | |
6b09401b | 2957 | |
c0bc527b M |
2958 | original_clients = clients |
2959 | clients = clients[::-1] | |
b6de707d | 2960 | prs = [] |
e7e94f2a D |
2961 | |
2962 | def append_client(client_name): | |
2963 | if client_name in INNERTUBE_CLIENTS and client_name not in original_clients: | |
2964 | clients.append(client_name) | |
2965 | ||
379e44ed | 2966 | # Android player_response does not have microFormats which are needed for |
2967 | # extraction of some data. So we return the initial_pr with formats | |
2968 | # stripped out even if not requested by the user | |
2969 | # See: https://github.com/yt-dlp/yt-dlp/issues/501 | |
379e44ed | 2970 | if initial_pr: |
2971 | pr = dict(initial_pr) | |
2972 | pr['streamingData'] = None | |
b6de707d | 2973 | prs.append(pr) |
379e44ed | 2974 | |
2975 | last_error = None | |
b6de707d | 2976 | tried_iframe_fallback = False |
2977 | player_url = None | |
c0bc527b M |
2978 | while clients: |
2979 | client = clients.pop() | |
11f9be09 | 2980 | player_ytcfg = master_ytcfg if client == 'web' else {} |
c0bc527b M |
2981 | if 'configs' not in self._configuration_arg('player_skip'): |
2982 | player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg | |
c0bc527b | 2983 | |
b6de707d | 2984 | player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage) |
2985 | require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER') | |
2986 | if 'js' in self._configuration_arg('player_skip'): | |
2987 | require_js_player = False | |
2988 | player_url = None | |
2989 | ||
2990 | if not player_url and not tried_iframe_fallback and require_js_player: | |
2991 | player_url = self._download_player_url(video_id) | |
2992 | tried_iframe_fallback = True | |
2993 | ||
379e44ed | 2994 | try: |
2995 | pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response( | |
99e9e001 | 2996 | client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr) |
379e44ed | 2997 | except ExtractorError as e: |
2998 | if last_error: | |
2999 | self.report_warning(last_error) | |
3000 | last_error = e | |
3001 | continue | |
3002 | ||
11f9be09 | 3003 | if pr: |
b6de707d | 3004 | prs.append(pr) |
c0bc527b | 3005 | |
e7e94f2a | 3006 | # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in |
99e9e001 | 3007 | if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated: |
e7e94f2a D |
3008 | append_client(client.replace('_agegate', '_creator')) |
3009 | elif self._is_agegated(pr): | |
3010 | append_client(f'{client}_agegate') | |
c0bc527b | 3011 | |
379e44ed | 3012 | if last_error: |
b6de707d | 3013 | if not len(prs): |
379e44ed | 3014 | raise last_error |
3015 | self.report_warning(last_error) | |
b6de707d | 3016 | return prs, player_url |
11f9be09 | 3017 | |
3018 | def _extract_formats(self, streaming_data, video_id, player_url, is_live): | |
a0bb6ce5 | 3019 | itags, stream_ids = {}, [] |
2a9c6dcd | 3020 | itag_qualities, res_qualities = {}, {} |
d3fc8074 | 3021 | q = qualities([ |
2a9c6dcd | 3022 | # Normally tiny is the smallest video-only formats. But |
3023 | # audio-only formats with unknown quality may get tagged as tiny | |
3024 | 'tiny', | |
3025 | 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats | |
d3fc8074 | 3026 | 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres' |
3027 | ]) | |
11f9be09 | 3028 | streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[]) |
0ad92dfb | 3029 | approx_duration = max(traverse_obj(streaming_formats, (..., 'approxDurationMs'), expected_type=float_or_none) or [0]) or None |
9297939e | 3030 | |
545cc85d | 3031 | for fmt in streaming_formats: |
3032 | if fmt.get('targetDurationSec') or fmt.get('drmFamilies'): | |
3033 | continue | |
321bf820 | 3034 | |
cc2db878 | 3035 | itag = str_or_none(fmt.get('itag')) |
9297939e | 3036 | audio_track = fmt.get('audioTrack') or {} |
3037 | stream_id = '%s.%s' % (itag or '', audio_track.get('id', '')) | |
3038 | if stream_id in stream_ids: | |
3039 | continue | |
3040 | ||
cc2db878 | 3041 | quality = fmt.get('quality') |
2a9c6dcd | 3042 | height = int_or_none(fmt.get('height')) |
d3fc8074 | 3043 | if quality == 'tiny' or not quality: |
3044 | quality = fmt.get('audioQuality', '').lower() or quality | |
2a9c6dcd | 3045 | # The 3gp format (17) in android client has a quality of "small", |
3046 | # but is actually worse than other formats | |
3047 | if itag == '17': | |
3048 | quality = 'tiny' | |
3049 | if quality: | |
3050 | if itag: | |
3051 | itag_qualities[itag] = quality | |
3052 | if height: | |
3053 | res_qualities[height] = quality | |
cc2db878 | 3054 | # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment |
3055 | # (adding `&sq=0` to the URL) and parsing emsg box to determine the | |
3056 | # number of fragment that would subsequently requested with (`&sq=N`) | |
3057 | if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF': | |
3058 | continue | |
3059 | ||
545cc85d | 3060 | fmt_url = fmt.get('url') |
3061 | if not fmt_url: | |
3062 | sc = compat_parse_qs(fmt.get('signatureCipher')) | |
3063 | fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0])) | |
3064 | encrypted_sig = try_get(sc, lambda x: x['s'][0]) | |
3065 | if not (sc and fmt_url and encrypted_sig): | |
3066 | continue | |
545cc85d | 3067 | if not player_url: |
201e9eaa | 3068 | continue |
545cc85d | 3069 | signature = self._decrypt_signature(sc['s'][0], video_id, player_url) |
3070 | sp = try_get(sc, lambda x: x['sp'][0]) or 'signature' | |
3071 | fmt_url += '&' + sp + '=' + signature | |
3072 | ||
404f611f | 3073 | query = parse_qs(fmt_url) |
3074 | throttled = False | |
b2916526 | 3075 | if query.get('n'): |
404f611f | 3076 | try: |
3077 | fmt_url = update_url_query(fmt_url, { | |
3078 | 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)}) | |
3079 | except ExtractorError as e: | |
aa9369a2 | 3080 | self.report_warning( |
3081 | f'nsig extraction failed: You may experience throttling for some formats\n' | |
3082 | f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True) | |
404f611f | 3083 | throttled = True |
3084 | ||
545cc85d | 3085 | if itag: |
a0bb6ce5 | 3086 | itags[itag] = 'https' |
9297939e | 3087 | stream_ids.append(stream_id) |
3088 | ||
0ad92dfb | 3089 | tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) |
ab6df717 | 3090 | language_preference = ( |
3091 | 10 if audio_track.get('audioIsDefault') and 10 | |
3092 | else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10 | |
3093 | else -1) | |
0ad92dfb | 3094 | # Some formats may have much smaller duration than others (possibly damaged during encoding) |
3095 | # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823 | |
3096 | is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) < approx_duration - 10000) | |
08d30158 | 3097 | if is_damaged: |
3098 | self.report_warning(f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True) | |
545cc85d | 3099 | dct = { |
3100 | 'asr': int_or_none(fmt.get('audioSampleRate')), | |
3101 | 'filesize': int_or_none(fmt.get('contentLength')), | |
3102 | 'format_id': itag, | |
34921b43 | 3103 | 'format_note': join_nonempty( |
26e8e044 | 3104 | '%s%s' % (audio_track.get('displayName') or '', |
ab6df717 | 3105 | ' (default)' if language_preference > 0 else ''), |
404f611f | 3106 | fmt.get('qualityLabel') or quality.replace('audio_quality_', ''), |
0ad92dfb | 3107 | throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '), |
c18d4482 | 3108 | 'source_preference': -10 if throttled else -1, |
a4211baf | 3109 | 'fps': int_or_none(fmt.get('fps')) or None, |
2a9c6dcd | 3110 | 'height': height, |
dca3ff4a | 3111 | 'quality': q(quality), |
cc2db878 | 3112 | 'tbr': tbr, |
545cc85d | 3113 | 'url': fmt_url, |
2a9c6dcd | 3114 | 'width': int_or_none(fmt.get('width')), |
ab6df717 | 3115 | 'language': join_nonempty(audio_track.get('id', '').split('.')[0], |
3116 | 'desc' if language_preference < -1 else ''), | |
3117 | 'language_preference': language_preference, | |
a405b38f | 3118 | # Strictly de-prioritize damaged and 3gp formats |
3119 | 'preference': -10 if is_damaged else -2 if itag == '17' else None, | |
545cc85d | 3120 | } |
60bdb7bd | 3121 | mime_mobj = re.match( |
3122 | r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '') | |
3123 | if mime_mobj: | |
3124 | dct['ext'] = mimetype2ext(mime_mobj.group(1)) | |
3125 | dct.update(parse_codecs(mime_mobj.group(2))) | |
cc2db878 | 3126 | no_audio = dct.get('acodec') == 'none' |
3127 | no_video = dct.get('vcodec') == 'none' | |
3128 | if no_audio: | |
3129 | dct['vbr'] = tbr | |
3130 | if no_video: | |
3131 | dct['abr'] = tbr | |
3132 | if no_audio or no_video: | |
545cc85d | 3133 | dct['downloader_options'] = { |
3134 | # Youtube throttles chunks >~10M | |
3135 | 'http_chunk_size': 10485760, | |
bf1317d2 | 3136 | } |
7c60c33e | 3137 | if dct.get('ext'): |
3138 | dct['container'] = dct['ext'] + '_dash' | |
11f9be09 | 3139 | yield dct |
545cc85d | 3140 | |
adbc4ec4 | 3141 | live_from_start = is_live and self.get_param('live_from_start') |
4bb6b02f | 3142 | skip_manifests = self._configuration_arg('skip') |
adbc4ec4 THD |
3143 | if not self.get_param('youtube_include_hls_manifest', True): |
3144 | skip_manifests.append('hls') | |
3145 | get_dash = 'dash' not in skip_manifests and ( | |
3146 | not is_live or live_from_start or self._configuration_arg('include_live_dash')) | |
3147 | get_hls = not live_from_start and 'hls' not in skip_manifests | |
5d3a0e79 | 3148 | |
a0bb6ce5 | 3149 | def process_manifest_format(f, proto, itag): |
3150 | if itag in itags: | |
3151 | if itags[itag] == proto or f'{itag}-{proto}' in itags: | |
3152 | return False | |
3153 | itag = f'{itag}-{proto}' | |
3154 | if itag: | |
3155 | f['format_id'] = itag | |
3156 | itags[itag] = proto | |
3157 | ||
3158 | f['quality'] = next(( | |
3159 | q(qdict[val]) | |
e339d25a | 3160 | for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities)) |
a0bb6ce5 | 3161 | if val in qdict), -1) |
3162 | return True | |
2a9c6dcd | 3163 | |
11f9be09 | 3164 | for sd in streaming_data: |
5d3a0e79 | 3165 | hls_manifest_url = get_hls and sd.get('hlsManifestUrl') |
9297939e | 3166 | if hls_manifest_url: |
2a9c6dcd | 3167 | for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False): |
a0bb6ce5 | 3168 | if process_manifest_format(f, 'hls', self._search_regex( |
3169 | r'/itag/(\d+)', f['url'], 'itag', default=None)): | |
3170 | yield f | |
545cc85d | 3171 | |
5d3a0e79 | 3172 | dash_manifest_url = get_dash and sd.get('dashManifestUrl') |
3173 | if dash_manifest_url: | |
2a9c6dcd | 3174 | for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False): |
a0bb6ce5 | 3175 | if process_manifest_format(f, 'dash', f['format_id']): |
3176 | f['filesize'] = int_or_none(self._search_regex( | |
3177 | r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None)) | |
adbc4ec4 THD |
3178 | if live_from_start: |
3179 | f['is_from_start'] = True | |
3180 | ||
a0bb6ce5 | 3181 | yield f |
11f9be09 | 3182 | |
720c3099 | 3183 | def _extract_storyboard(self, player_responses, duration): |
3184 | spec = get_first( | |
3185 | player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1] | |
596379e2 | 3186 | base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None)) |
3187 | if not base_url: | |
720c3099 | 3188 | return |
720c3099 | 3189 | L = len(spec) - 1 |
3190 | for i, args in enumerate(spec): | |
3191 | args = args.split('#') | |
3192 | counts = list(map(int_or_none, args[:5])) | |
3193 | if len(args) != 8 or not all(counts): | |
3194 | self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}') | |
3195 | continue | |
3196 | width, height, frame_count, cols, rows = counts | |
3197 | N, sigh = args[6:] | |
3198 | ||
3199 | url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}' | |
3200 | fragment_count = frame_count / (cols * rows) | |
3201 | fragment_duration = duration / fragment_count | |
3202 | yield { | |
3203 | 'format_id': f'sb{i}', | |
3204 | 'format_note': 'storyboard', | |
3205 | 'ext': 'mhtml', | |
3206 | 'protocol': 'mhtml', | |
3207 | 'acodec': 'none', | |
3208 | 'vcodec': 'none', | |
3209 | 'url': url, | |
3210 | 'width': width, | |
3211 | 'height': height, | |
3212 | 'fragments': [{ | |
3213 | 'path': url.replace('$M', str(j)), | |
3214 | 'duration': min(fragment_duration, duration - (j * fragment_duration)), | |
3215 | } for j in range(math.ceil(fragment_count))], | |
3216 | } | |
3217 | ||
adbc4ec4 | 3218 | def _download_player_responses(self, url, smuggled_data, video_id, webpage_url): |
b6de707d | 3219 | webpage = None |
3220 | if 'webpage' not in self._configuration_arg('player_skip'): | |
3221 | webpage = self._download_webpage( | |
3222 | webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False) | |
11f9be09 | 3223 | |
3224 | master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg() | |
11f9be09 | 3225 | |
b6de707d | 3226 | player_responses, player_url = self._extract_player_responses( |
11f9be09 | 3227 | self._get_requested_clients(url, smuggled_data), |
99e9e001 | 3228 | video_id, webpage, master_ytcfg) |
11f9be09 | 3229 | |
adbc4ec4 THD |
3230 | return webpage, master_ytcfg, player_responses, player_url |
3231 | ||
3232 | def _list_formats(self, video_id, microformats, video_details, player_responses, player_url): | |
3233 | live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails')) | |
3234 | is_live = get_first(video_details, 'isLive') | |
3235 | if is_live is None: | |
3236 | is_live = get_first(live_broadcast_details, 'isLiveNow') | |
3237 | ||
3238 | streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[]) | |
3239 | formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live)) | |
3240 | ||
3241 | return live_broadcast_details, is_live, streaming_data, formats | |
3242 | ||
3243 | def _real_extract(self, url): | |
3244 | url, smuggled_data = unsmuggle_url(url, {}) | |
3245 | video_id = self._match_id(url) | |
3246 | ||
3247 | base_url = self.http_scheme() + '//www.youtube.com/' | |
3248 | webpage_url = base_url + 'watch?v=' + video_id | |
3249 | ||
3250 | webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url) | |
3251 | ||
11f9be09 | 3252 | playability_statuses = traverse_obj( |
3253 | player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[]) | |
3254 | ||
3255 | trailer_video_id = get_first( | |
3256 | playability_statuses, | |
3257 | ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'), | |
3258 | expected_type=str) | |
3259 | if trailer_video_id: | |
3260 | return self.url_result( | |
3261 | trailer_video_id, self.ie_key(), trailer_video_id) | |
3262 | ||
3263 | search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None)) | |
3264 | if webpage else (lambda x: None)) | |
3265 | ||
3266 | video_details = traverse_obj( | |
3267 | player_responses, (..., 'videoDetails'), expected_type=dict, default=[]) | |
3268 | microformats = traverse_obj( | |
3269 | player_responses, (..., 'microformat', 'playerMicroformatRenderer'), | |
3270 | expected_type=dict, default=[]) | |
3271 | video_title = ( | |
3272 | get_first(video_details, 'title') | |
3273 | or self._get_text(microformats, (..., 'title')) | |
3274 | or search_meta(['og:title', 'twitter:title', 'title'])) | |
3275 | video_description = get_first(video_details, 'shortDescription') | |
3276 | ||
d89257f3 | 3277 | multifeed_metadata_list = get_first( |
3278 | player_responses, | |
3279 | ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'), | |
3280 | expected_type=str) | |
3281 | if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'): | |
3282 | if self.get_param('noplaylist'): | |
11f9be09 | 3283 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) |
d89257f3 | 3284 | else: |
3285 | entries = [] | |
3286 | feed_ids = [] | |
3287 | for feed in multifeed_metadata_list.split(','): | |
3288 | # Unquote should take place before split on comma (,) since textual | |
3289 | # fields may contain comma as well (see | |
3290 | # https://github.com/ytdl-org/youtube-dl/issues/8536) | |
3291 | feed_data = compat_parse_qs( | |
3292 | compat_urllib_parse_unquote_plus(feed)) | |
3293 | ||
3294 | def feed_entry(name): | |
3295 | return try_get( | |
3296 | feed_data, lambda x: x[name][0], compat_str) | |
3297 | ||
3298 | feed_id = feed_entry('id') | |
3299 | if not feed_id: | |
3300 | continue | |
3301 | feed_title = feed_entry('title') | |
3302 | title = video_title | |
3303 | if feed_title: | |
3304 | title += ' (%s)' % feed_title | |
3305 | entries.append({ | |
3306 | '_type': 'url_transparent', | |
3307 | 'ie_key': 'Youtube', | |
3308 | 'url': smuggle_url( | |
3309 | '%swatch?v=%s' % (base_url, feed_data['id'][0]), | |
3310 | {'force_singlefeed': True}), | |
3311 | 'title': title, | |
3312 | }) | |
3313 | feed_ids.append(feed_id) | |
3314 | self.to_screen( | |
3315 | 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' | |
3316 | % (', '.join(feed_ids), video_id)) | |
3317 | return self.playlist_result( | |
3318 | entries, video_id, video_title, video_description) | |
11f9be09 | 3319 | |
adbc4ec4 | 3320 | live_broadcast_details, is_live, streaming_data, formats = self._list_formats(video_id, microformats, video_details, player_responses, player_url) |
bf1317d2 | 3321 | |
545cc85d | 3322 | if not formats: |
11f9be09 | 3323 | if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')): |
88acdbc2 | 3324 | self.report_drm(video_id) |
11f9be09 | 3325 | pemr = get_first( |
3326 | playability_statuses, | |
3327 | ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {} | |
3328 | reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason') | |
3329 | subreason = clean_html(self._get_text(pemr, 'subreason') or '') | |
545cc85d | 3330 | if subreason: |
545cc85d | 3331 | if subreason == 'The uploader has not made this video available in your country.': |
11f9be09 | 3332 | countries = get_first(microformats, 'availableCountries') |
545cc85d | 3333 | if not countries: |
3334 | regions_allowed = search_meta('regionsAllowed') | |
3335 | countries = regions_allowed.split(',') if regions_allowed else None | |
b7da73eb | 3336 | self.raise_geo_restricted(subreason, countries, metadata_available=True) |
11f9be09 | 3337 | reason += f'. {subreason}' |
545cc85d | 3338 | if reason: |
b7da73eb | 3339 | self.raise_no_formats(reason, expected=True) |
bf1317d2 | 3340 | |
11f9be09 | 3341 | keywords = get_first(video_details, 'keywords', expected_type=list) or [] |
545cc85d | 3342 | if not keywords and webpage: |
3343 | keywords = [ | |
3344 | unescapeHTML(m.group('content')) | |
3345 | for m in re.finditer(self._meta_regex('og:video:tag'), webpage)] | |
3346 | for keyword in keywords: | |
3347 | if keyword.startswith('yt:stretch='): | |
201c1459 | 3348 | mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword) |
3349 | if mobj: | |
3350 | # NB: float is intentional for forcing float division | |
3351 | w, h = (float(v) for v in mobj.groups()) | |
3352 | if w > 0 and h > 0: | |
3353 | ratio = w / h | |
3354 | for f in formats: | |
3355 | if f.get('vcodec') != 'none': | |
3356 | f['stretched_ratio'] = ratio | |
3357 | break | |
a709d873 | 3358 | thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail')) |
ff2751ac | 3359 | thumbnail_url = search_meta(['og:image', 'twitter:image']) |
3360 | if thumbnail_url: | |
3361 | thumbnails.append({ | |
3362 | 'url': thumbnail_url, | |
ff2751ac | 3363 | }) |
fccf5021 | 3364 | original_thumbnails = thumbnails.copy() |
3365 | ||
0ba692ac | 3366 | # The best resolution thumbnails sometimes does not appear in the webpage |
3367 | # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340 | |
cca80fe6 | 3368 | # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029> |
e820fbaa | 3369 | thumbnail_names = [ |
3370 | 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3', | |
cca80fe6 | 3371 | 'hqdefault', 'hq1', 'hq2', 'hq3', '0', |
3372 | 'mqdefault', 'mq1', 'mq2', 'mq3', | |
3373 | 'default', '1', '2', '3' | |
3374 | ] | |
cca80fe6 | 3375 | n_thumbnail_names = len(thumbnail_names) |
0ba692ac | 3376 | thumbnails.extend({ |
3377 | 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format( | |
3378 | video_id=video_id, name=name, ext=ext, | |
3379 | webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''), | |
cca80fe6 | 3380 | } for name in thumbnail_names for ext in ('webp', 'jpg')) |
0ba692ac | 3381 | for thumb in thumbnails: |
cca80fe6 | 3382 | i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names) |
0ba692ac | 3383 | thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i) |
ff2751ac | 3384 | self._remove_duplicate_formats(thumbnails) |
fccf5021 | 3385 | self._downloader._sort_thumbnails(original_thumbnails) |
545cc85d | 3386 | |
7ea65411 | 3387 | category = get_first(microformats, 'category') or search_meta('genre') |
3388 | channel_id = str_or_none( | |
3389 | get_first(video_details, 'channelId') | |
3390 | or get_first(microformats, 'externalChannelId') | |
3391 | or search_meta('channelId')) | |
3392 | duration = int_or_none( | |
3393 | get_first(video_details, 'lengthSeconds') | |
3394 | or get_first(microformats, 'lengthSeconds') | |
3395 | or parse_duration(search_meta('duration'))) or None | |
3396 | owner_profile_url = get_first(microformats, 'ownerProfileUrl') | |
3397 | ||
3398 | live_content = get_first(video_details, 'isLiveContent') | |
3399 | is_upcoming = get_first(video_details, 'isUpcoming') | |
3400 | if is_live is None: | |
3401 | if is_upcoming or live_content is False: | |
3402 | is_live = False | |
3403 | if is_upcoming is None and (live_content or is_live): | |
3404 | is_upcoming = False | |
adbc4ec4 THD |
3405 | live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp')) |
3406 | live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp')) | |
3407 | if not duration and live_end_time and live_start_time: | |
3408 | duration = live_end_time - live_start_time | |
3409 | ||
3410 | if is_live and self.get_param('live_from_start'): | |
3411 | self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data) | |
7ea65411 | 3412 | |
720c3099 | 3413 | formats.extend(self._extract_storyboard(player_responses, duration)) |
3414 | ||
3415 | # Source is given priority since formats that throttle are given lower source_preference | |
3416 | # When throttling issue is fully fixed, remove this | |
3417 | self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto')) | |
3418 | ||
545cc85d | 3419 | info = { |
3420 | 'id': video_id, | |
39ca3b5c | 3421 | 'title': video_title, |
545cc85d | 3422 | 'formats': formats, |
3423 | 'thumbnails': thumbnails, | |
fccf5021 | 3424 | # The best thumbnail that we are sure exists. Prevents unnecessary |
3425 | # URL checking if user don't care about getting the best possible thumbnail | |
3426 | 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')), | |
545cc85d | 3427 | 'description': video_description, |
11f9be09 | 3428 | 'uploader': get_first(video_details, 'author'), |
545cc85d | 3429 | 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None, |
3430 | 'uploader_url': owner_profile_url, | |
3431 | 'channel_id': channel_id, | |
e0ddbd02 | 3432 | 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'), |
545cc85d | 3433 | 'duration': duration, |
3434 | 'view_count': int_or_none( | |
11f9be09 | 3435 | get_first((video_details, microformats), (..., 'viewCount')) |
545cc85d | 3436 | or search_meta('interactionCount')), |
11f9be09 | 3437 | 'average_rating': float_or_none(get_first(video_details, 'averageRating')), |
545cc85d | 3438 | 'age_limit': 18 if ( |
11f9be09 | 3439 | get_first(microformats, 'isFamilySafe') is False |
545cc85d | 3440 | or search_meta('isFamilyFriendly') == 'false' |
3441 | or search_meta('og:restrictions:age') == '18+') else 0, | |
3442 | 'webpage_url': webpage_url, | |
3443 | 'categories': [category] if category else None, | |
3444 | 'tags': keywords, | |
11f9be09 | 3445 | 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'), |
7ea65411 | 3446 | 'is_live': is_live, |
3447 | 'was_live': (False if is_live or is_upcoming or live_content is False | |
3448 | else None if is_live is None or is_upcoming is None | |
3449 | else live_content), | |
3450 | 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL | |
adbc4ec4 | 3451 | 'release_timestamp': live_start_time, |
545cc85d | 3452 | } |
b477fc13 | 3453 | |
3944e7af | 3454 | pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict) |
545cc85d | 3455 | if pctr: |
ecdc9049 | 3456 | def get_lang_code(track): |
3457 | return (remove_start(track.get('vssId') or '', '.').replace('.', '-') | |
3458 | or track.get('languageCode')) | |
3459 | ||
3460 | # Converted into dicts to remove duplicates | |
3461 | captions = { | |
3462 | get_lang_code(sub): sub | |
3463 | for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])} | |
3464 | translation_languages = { | |
3465 | lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1) | |
3466 | for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])} | |
3467 | ||
774d79cc | 3468 | def process_language(container, base_url, lang_code, sub_name, query): |
120916da | 3469 | lang_subs = container.setdefault(lang_code, []) |
545cc85d | 3470 | for fmt in self._SUBTITLE_FORMATS: |
3471 | query.update({ | |
3472 | 'fmt': fmt, | |
3473 | }) | |
3474 | lang_subs.append({ | |
3475 | 'ext': fmt, | |
60f393e4 | 3476 | 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)), |
774d79cc | 3477 | 'name': sub_name, |
545cc85d | 3478 | }) |
7e72694b | 3479 | |
ecdc9049 | 3480 | subtitles, automatic_captions = {}, {} |
3481 | for lang_code, caption_track in captions.items(): | |
3482 | base_url = caption_track.get('baseUrl') | |
545cc85d | 3483 | if not base_url: |
3484 | continue | |
ecdc9049 | 3485 | lang_name = self._get_text(caption_track, 'name', max_runs=1) |
545cc85d | 3486 | if caption_track.get('kind') != 'asr': |
545cc85d | 3487 | if not lang_code: |
3488 | continue | |
3489 | process_language( | |
ecdc9049 | 3490 | subtitles, base_url, lang_code, lang_name, {}) |
3491 | if not caption_track.get('isTranslatable'): | |
3492 | continue | |
3944e7af | 3493 | for trans_code, trans_name in translation_languages.items(): |
3494 | if not trans_code: | |
545cc85d | 3495 | continue |
ecdc9049 | 3496 | if caption_track.get('kind') != 'asr': |
3497 | trans_code += f'-{lang_code}' | |
3498 | trans_name += format_field(lang_name, template=' from %s') | |
d49669ac | 3499 | # Add an "-orig" label to the original language so that it can be distinguished. |
3500 | # The subs are returned without "-orig" as well for compatibility | |
0c8d9e5f | 3501 | if lang_code == f'a-{trans_code}': |
3502 | process_language( | |
d49669ac | 3503 | automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {}) |
3504 | # Setting tlang=lang returns damaged subtitles. | |
3505 | # Not using lang_code == f'a-{trans_code}' here for future-proofing | |
3506 | orig_lang = parse_qs(base_url).get('lang', [None])[-1] | |
3507 | process_language(automatic_captions, base_url, trans_code, trans_name, | |
3508 | {} if orig_lang == trans_code else {'tlang': trans_code}) | |
ecdc9049 | 3509 | info['automatic_captions'] = automatic_captions |
3510 | info['subtitles'] = subtitles | |
7e72694b | 3511 | |
545cc85d | 3512 | parsed_url = compat_urllib_parse_urlparse(url) |
3513 | for component in [parsed_url.fragment, parsed_url.query]: | |
3514 | query = compat_parse_qs(component) | |
3515 | for k, v in query.items(): | |
3516 | for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]: | |
3517 | d_k += '_time' | |
3518 | if d_k not in info and k in s_ks: | |
3519 | info[d_k] = parse_duration(query[k][0]) | |
822b9d9c RA |
3520 | |
3521 | # Youtube Music Auto-generated description | |
822b9d9c | 3522 | if video_description: |
38d70284 | 3523 | mobj = re.search(r'(?s)(?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?.+\nAuto-generated by YouTube\.\s*$', video_description) |
822b9d9c | 3524 | if mobj: |
822b9d9c RA |
3525 | release_year = mobj.group('release_year') |
3526 | release_date = mobj.group('release_date') | |
3527 | if release_date: | |
3528 | release_date = release_date.replace('-', '') | |
3529 | if not release_year: | |
545cc85d | 3530 | release_year = release_date[:4] |
3531 | info.update({ | |
3532 | 'album': mobj.group('album'.strip()), | |
3533 | 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')), | |
3534 | 'track': mobj.group('track').strip(), | |
3535 | 'release_date': release_date, | |
cc2db878 | 3536 | 'release_year': int_or_none(release_year), |
545cc85d | 3537 | }) |
7e72694b | 3538 | |
545cc85d | 3539 | initial_data = None |
3540 | if webpage: | |
3541 | initial_data = self._extract_yt_initial_variable( | |
3542 | webpage, self._YT_INITIAL_DATA_RE, video_id, | |
3543 | 'yt initial data') | |
3544 | if not initial_data: | |
99e9e001 | 3545 | query = {'videoId': video_id} |
3546 | query.update(self._get_checkok_params()) | |
109dd3b2 | 3547 | initial_data = self._extract_response( |
3548 | item_id=video_id, ep='next', fatal=False, | |
99e9e001 | 3549 | ytcfg=master_ytcfg, query=query, |
3550 | headers=self.generate_api_headers(ytcfg=master_ytcfg), | |
109dd3b2 | 3551 | note='Downloading initial data API JSON') |
545cc85d | 3552 | |
c60ee3a2 | 3553 | try: |
3554 | # This will error if there is no livechat | |
3555 | initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation'] | |
ecdc9049 | 3556 | info.setdefault('subtitles', {})['live_chat'] = [{ |
c60ee3a2 | 3557 | 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies |
3558 | 'video_id': video_id, | |
3559 | 'ext': 'json', | |
f6745c49 | 3560 | 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay', |
c60ee3a2 | 3561 | }] |
3562 | except (KeyError, IndexError, TypeError): | |
3563 | pass | |
545cc85d | 3564 | |
3565 | if initial_data: | |
7c365c21 | 3566 | info['chapters'] = ( |
3567 | self._extract_chapters_from_json(initial_data, duration) | |
3568 | or self._extract_chapters_from_engagement_panel(initial_data, duration) | |
3569 | or None) | |
545cc85d | 3570 | |
3571 | contents = try_get( | |
3572 | initial_data, | |
3573 | lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], | |
3574 | list) or [] | |
3575 | for content in contents: | |
3576 | vpir = content.get('videoPrimaryInfoRenderer') | |
3577 | if vpir: | |
992f9a73 | 3578 | info['upload_date'] = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') |
545cc85d | 3579 | stl = vpir.get('superTitleLink') |
3580 | if stl: | |
fe93e2c4 | 3581 | stl = self._get_text(stl) |
545cc85d | 3582 | if try_get( |
3583 | vpir, | |
3584 | lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN': | |
3585 | info['location'] = stl | |
3586 | else: | |
3587 | mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl) | |
3588 | if mobj: | |
3589 | info.update({ | |
3590 | 'series': mobj.group(1), | |
3591 | 'season_number': int(mobj.group(2)), | |
3592 | 'episode_number': int(mobj.group(3)), | |
3593 | }) | |
3594 | for tlb in (try_get( | |
3595 | vpir, | |
3596 | lambda x: x['videoActions']['menuRenderer']['topLevelButtons'], | |
3597 | list) or []): | |
3598 | tbr = tlb.get('toggleButtonRenderer') or {} | |
3599 | for getter, regex in [( | |
3600 | lambda x: x['defaultText']['accessibility']['accessibilityData'], | |
3601 | r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([ | |
3602 | lambda x: x['accessibility'], | |
3603 | lambda x: x['accessibilityData']['accessibilityData'], | |
3604 | ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]: | |
3605 | label = (try_get(tbr, getter, dict) or {}).get('label') | |
3606 | if label: | |
3607 | mobj = re.match(regex, label) | |
3608 | if mobj: | |
3609 | info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count')) | |
3610 | break | |
3611 | sbr_tooltip = try_get( | |
3612 | vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip']) | |
3613 | if sbr_tooltip: | |
3614 | like_count, dislike_count = sbr_tooltip.split(' / ') | |
3615 | info.update({ | |
3616 | 'like_count': str_to_int(like_count), | |
3617 | 'dislike_count': str_to_int(dislike_count), | |
3618 | }) | |
3619 | vsir = content.get('videoSecondaryInfoRenderer') | |
3620 | if vsir: | |
6c73052c | 3621 | vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer')) |
3622 | info.update({ | |
3623 | 'channel': self._get_text(vor, 'title'), | |
3624 | 'channel_follower_count': self._get_count(vor, 'subscriberCountText')}) | |
3625 | ||
545cc85d | 3626 | rows = try_get( |
3627 | vsir, | |
3628 | lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'], | |
3629 | list) or [] | |
3630 | multiple_songs = False | |
3631 | for row in rows: | |
3632 | if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True: | |
3633 | multiple_songs = True | |
3634 | break | |
3635 | for row in rows: | |
3636 | mrr = row.get('metadataRowRenderer') or {} | |
3637 | mrr_title = mrr.get('title') | |
3638 | if not mrr_title: | |
3639 | continue | |
052e1350 | 3640 | mrr_title = self._get_text(mrr, 'title') |
3641 | mrr_contents_text = self._get_text(mrr, ('contents', 0)) | |
545cc85d | 3642 | if mrr_title == 'License': |
3643 | info['license'] = mrr_contents_text | |
3644 | elif not multiple_songs: | |
3645 | if mrr_title == 'Album': | |
3646 | info['album'] = mrr_contents_text | |
3647 | elif mrr_title == 'Artist': | |
3648 | info['artist'] = mrr_contents_text | |
3649 | elif mrr_title == 'Song': | |
3650 | info['track'] = mrr_contents_text | |
3651 | ||
3652 | fallbacks = { | |
3653 | 'channel': 'uploader', | |
3654 | 'channel_id': 'uploader_id', | |
3655 | 'channel_url': 'uploader_url', | |
3656 | } | |
992f9a73 | 3657 | |
3658 | # The upload date for scheduled and current live streams / premieres in microformats | |
3659 | # is generally the true upload date. Although not in UTC, we will prefer that in this case. | |
3660 | # Note this changes to the published date when the stream/premiere has finished. | |
3661 | # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139 | |
3662 | if not info.get('upload_date') or info.get('is_live') or info.get('live_status') == 'is_upcoming': | |
3663 | info['upload_date'] = ( | |
3664 | unified_strdate(get_first(microformats, 'uploadDate')) | |
3665 | or unified_strdate(search_meta('uploadDate')) | |
3666 | or info.get('upload_date')) | |
3667 | ||
545cc85d | 3668 | for to, frm in fallbacks.items(): |
3669 | if not info.get(to): | |
3670 | info[to] = info.get(frm) | |
3671 | ||
3672 | for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]: | |
3673 | v = info.get(s_k) | |
3674 | if v: | |
3675 | info[d_k] = v | |
b84071c0 | 3676 | |
11f9be09 | 3677 | is_private = get_first(video_details, 'isPrivate', expected_type=bool) |
3678 | is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool) | |
c224251a | 3679 | is_membersonly = None |
b28f8d24 | 3680 | is_premium = None |
c224251a M |
3681 | if initial_data and is_private is not None: |
3682 | is_membersonly = False | |
b28f8d24 | 3683 | is_premium = False |
47193e02 | 3684 | contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or [] |
3685 | badge_labels = set() | |
3686 | for content in contents: | |
3687 | if not isinstance(content, dict): | |
3688 | continue | |
3689 | badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer'))) | |
3690 | for badge_label in badge_labels: | |
3691 | if badge_label.lower() == 'members only': | |
3692 | is_membersonly = True | |
3693 | elif badge_label.lower() == 'premium': | |
3694 | is_premium = True | |
3695 | elif badge_label.lower() == 'unlisted': | |
3696 | is_unlisted = True | |
c224251a | 3697 | |
c224251a M |
3698 | info['availability'] = self._availability( |
3699 | is_private=is_private, | |
b28f8d24 | 3700 | needs_premium=is_premium, |
c224251a M |
3701 | needs_subscription=is_membersonly, |
3702 | needs_auth=info['age_limit'] >= 18, | |
3703 | is_unlisted=None if is_private is None else is_unlisted) | |
3704 | ||
a2160aa4 | 3705 | info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage) |
4ea3be0a | 3706 | |
11f9be09 | 3707 | self.mark_watched(video_id, player_responses) |
d77ab8e2 | 3708 | |
545cc85d | 3709 | return info |
c5e8d7af | 3710 | |
a61fd4cf | 3711 | |
a6213a49 | 3712 | class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor): |
5f6a1245 | 3713 | |
182bda88 | 3714 | @staticmethod |
3715 | def passthrough_smuggled_data(func): | |
3716 | def _smuggle(entries, smuggled_data): | |
3717 | for entry in entries: | |
3718 | # TODO: Convert URL to music.youtube instead. | |
3719 | # Do we need to passthrough any other smuggled_data? | |
3720 | entry['url'] = smuggle_url(entry['url'], smuggled_data) | |
3721 | yield entry | |
3722 | ||
3723 | @functools.wraps(func) | |
3724 | def wrapper(self, url): | |
3725 | url, smuggled_data = unsmuggle_url(url, {}) | |
3726 | if self.is_music_url(url): | |
3727 | smuggled_data['is_music_url'] = True | |
3728 | info_dict = func(self, url, smuggled_data) | |
3729 | if smuggled_data and info_dict.get('entries'): | |
3730 | info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data) | |
3731 | return info_dict | |
3732 | return wrapper | |
3733 | ||
a6213a49 | 3734 | def _extract_channel_id(self, webpage): |
3735 | channel_id = self._html_search_meta( | |
3736 | 'channelId', webpage, 'channel id', default=None) | |
3737 | if channel_id: | |
3738 | return channel_id | |
3739 | channel_url = self._html_search_meta( | |
3740 | ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url', | |
3741 | 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad', | |
3742 | 'twitter:app:url:googleplay'), webpage, 'channel url') | |
3743 | return self._search_regex( | |
3744 | r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+', | |
3745 | channel_url, 'channel id') | |
15f6397c | 3746 | |
8bdd16b4 | 3747 | @staticmethod |
cd7c66cf | 3748 | def _extract_basic_item_renderer(item): |
3749 | # Modified from _extract_grid_item_renderer | |
201c1459 | 3750 | known_basic_renderers = ( |
3751 | 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer' | |
cd7c66cf | 3752 | ) |
3753 | for key, renderer in item.items(): | |
201c1459 | 3754 | if not isinstance(renderer, dict): |
cd7c66cf | 3755 | continue |
201c1459 | 3756 | elif key in known_basic_renderers: |
3757 | return renderer | |
3758 | elif key.startswith('grid') and key.endswith('Renderer'): | |
3759 | return renderer | |
8bdd16b4 | 3760 | |
8bdd16b4 | 3761 | def _grid_entries(self, grid_renderer): |
3762 | for item in grid_renderer['items']: | |
3763 | if not isinstance(item, dict): | |
39b62db1 | 3764 | continue |
cd7c66cf | 3765 | renderer = self._extract_basic_item_renderer(item) |
8bdd16b4 | 3766 | if not isinstance(renderer, dict): |
3767 | continue | |
052e1350 | 3768 | title = self._get_text(renderer, 'title') |
fe93e2c4 | 3769 | |
8bdd16b4 | 3770 | # playlist |
3771 | playlist_id = renderer.get('playlistId') | |
3772 | if playlist_id: | |
3773 | yield self.url_result( | |
3774 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, | |
3775 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id, | |
3776 | video_title=title) | |
201c1459 | 3777 | continue |
8bdd16b4 | 3778 | # video |
3779 | video_id = renderer.get('videoId') | |
3780 | if video_id: | |
3781 | yield self._extract_video(renderer) | |
201c1459 | 3782 | continue |
8bdd16b4 | 3783 | # channel |
3784 | channel_id = renderer.get('channelId') | |
3785 | if channel_id: | |
8bdd16b4 | 3786 | yield self.url_result( |
3787 | 'https://www.youtube.com/channel/%s' % channel_id, | |
3788 | ie=YoutubeTabIE.ie_key(), video_title=title) | |
201c1459 | 3789 | continue |
3790 | # generic endpoint URL support | |
3791 | ep_url = urljoin('https://www.youtube.com/', try_get( | |
3792 | renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'], | |
3793 | compat_str)) | |
3794 | if ep_url: | |
3795 | for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE): | |
3796 | if ie.suitable(ep_url): | |
3797 | yield self.url_result( | |
3798 | ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title) | |
3799 | break | |
8bdd16b4 | 3800 | |
16aa9ea4 | 3801 | def _music_reponsive_list_entry(self, renderer): |
3802 | video_id = traverse_obj(renderer, ('playlistItemData', 'videoId')) | |
3803 | if video_id: | |
3804 | return self.url_result(f'https://music.youtube.com/watch?v={video_id}', | |
3805 | ie=YoutubeIE.ie_key(), video_id=video_id) | |
3806 | playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId')) | |
3807 | if playlist_id: | |
3808 | video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId')) | |
3809 | if video_id: | |
3810 | return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}', | |
3811 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
3812 | return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}', | |
3813 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
3814 | browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId')) | |
3815 | if browse_id: | |
3816 | return self.url_result(f'https://music.youtube.com/browse/{browse_id}', | |
3817 | ie=YoutubeTabIE.ie_key(), video_id=browse_id) | |
3818 | ||
3d3dddc9 | 3819 | def _shelf_entries_from_content(self, shelf_renderer): |
3820 | content = shelf_renderer.get('content') | |
3821 | if not isinstance(content, dict): | |
8bdd16b4 | 3822 | return |
cd7c66cf | 3823 | renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer') |
3d3dddc9 | 3824 | if renderer: |
3825 | # TODO: add support for nested playlists so each shelf is processed | |
3826 | # as separate playlist | |
3827 | # TODO: this includes only first N items | |
3828 | for entry in self._grid_entries(renderer): | |
3829 | yield entry | |
3830 | renderer = content.get('horizontalListRenderer') | |
3831 | if renderer: | |
3832 | # TODO | |
3833 | pass | |
8bdd16b4 | 3834 | |
29f7c58a | 3835 | def _shelf_entries(self, shelf_renderer, skip_channels=False): |
8bdd16b4 | 3836 | ep = try_get( |
3837 | shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], | |
3838 | compat_str) | |
3839 | shelf_url = urljoin('https://www.youtube.com', ep) | |
3d3dddc9 | 3840 | if shelf_url: |
29f7c58a | 3841 | # Skipping links to another channels, note that checking for |
3842 | # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL | |
3843 | # will not work | |
3844 | if skip_channels and '/channels?' in shelf_url: | |
3845 | return | |
052e1350 | 3846 | title = self._get_text(shelf_renderer, 'title') |
3d3dddc9 | 3847 | yield self.url_result(shelf_url, video_title=title) |
3848 | # Shelf may not contain shelf URL, fallback to extraction from content | |
3849 | for entry in self._shelf_entries_from_content(shelf_renderer): | |
3850 | yield entry | |
c5e8d7af | 3851 | |
8bdd16b4 | 3852 | def _playlist_entries(self, video_list_renderer): |
3853 | for content in video_list_renderer['contents']: | |
3854 | if not isinstance(content, dict): | |
3855 | continue | |
3856 | renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer') | |
3857 | if not isinstance(renderer, dict): | |
3858 | continue | |
3859 | video_id = renderer.get('videoId') | |
3860 | if not video_id: | |
3861 | continue | |
3862 | yield self._extract_video(renderer) | |
07aeced6 | 3863 | |
3462ffa8 | 3864 | def _rich_entries(self, rich_grid_renderer): |
3865 | renderer = try_get( | |
70d5c17b | 3866 | rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {} |
3462ffa8 | 3867 | video_id = renderer.get('videoId') |
3868 | if not video_id: | |
3869 | return | |
3870 | yield self._extract_video(renderer) | |
3871 | ||
8bdd16b4 | 3872 | def _video_entry(self, video_renderer): |
3873 | video_id = video_renderer.get('videoId') | |
3874 | if video_id: | |
3875 | return self._extract_video(video_renderer) | |
dacb3a86 | 3876 | |
8bdd16b4 | 3877 | def _post_thread_entries(self, post_thread_renderer): |
3878 | post_renderer = try_get( | |
3879 | post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict) | |
3880 | if not post_renderer: | |
3881 | return | |
3882 | # video attachment | |
3883 | video_renderer = try_get( | |
895b0931 | 3884 | post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {} |
3885 | video_id = video_renderer.get('videoId') | |
3886 | if video_id: | |
3887 | entry = self._extract_video(video_renderer) | |
8bdd16b4 | 3888 | if entry: |
3889 | yield entry | |
895b0931 | 3890 | # playlist attachment |
3891 | playlist_id = try_get( | |
3892 | post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str) | |
3893 | if playlist_id: | |
3894 | yield self.url_result( | |
e28f1c0a | 3895 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, |
3896 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
8bdd16b4 | 3897 | # inline video links |
3898 | runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or [] | |
3899 | for run in runs: | |
3900 | if not isinstance(run, dict): | |
3901 | continue | |
3902 | ep_url = try_get( | |
3903 | run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str) | |
3904 | if not ep_url: | |
3905 | continue | |
3906 | if not YoutubeIE.suitable(ep_url): | |
3907 | continue | |
3908 | ep_video_id = YoutubeIE._match_id(ep_url) | |
3909 | if video_id == ep_video_id: | |
3910 | continue | |
895b0931 | 3911 | yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id) |
dacb3a86 | 3912 | |
8bdd16b4 | 3913 | def _post_thread_continuation_entries(self, post_thread_continuation): |
3914 | contents = post_thread_continuation.get('contents') | |
3915 | if not isinstance(contents, list): | |
3916 | return | |
3917 | for content in contents: | |
3918 | renderer = content.get('backstagePostThreadRenderer') | |
3919 | if not isinstance(renderer, dict): | |
3920 | continue | |
3921 | for entry in self._post_thread_entries(renderer): | |
3922 | yield entry | |
07aeced6 | 3923 | |
39ed931e | 3924 | r''' # unused |
3925 | def _rich_grid_entries(self, contents): | |
3926 | for content in contents: | |
3927 | video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict) | |
3928 | if video_renderer: | |
3929 | entry = self._video_entry(video_renderer) | |
3930 | if entry: | |
3931 | yield entry | |
3932 | ''' | |
a6213a49 | 3933 | def _extract_entries(self, parent_renderer, continuation_list): |
3934 | # continuation_list is modified in-place with continuation_list = [continuation_token] | |
3935 | continuation_list[:] = [None] | |
3936 | contents = try_get(parent_renderer, lambda x: x['contents'], list) or [] | |
3937 | for content in contents: | |
3938 | if not isinstance(content, dict): | |
3939 | continue | |
16aa9ea4 | 3940 | is_renderer = traverse_obj( |
3941 | content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation', | |
3942 | expected_type=dict) | |
a6213a49 | 3943 | if not is_renderer: |
3944 | renderer = content.get('richItemRenderer') | |
3945 | if renderer: | |
3946 | for entry in self._rich_entries(renderer): | |
3947 | yield entry | |
3948 | continuation_list[0] = self._extract_continuation(parent_renderer) | |
3949 | continue | |
3950 | isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or [] | |
3951 | for isr_content in isr_contents: | |
3952 | if not isinstance(isr_content, dict): | |
8bdd16b4 | 3953 | continue |
69184e41 | 3954 | |
a6213a49 | 3955 | known_renderers = { |
3956 | 'playlistVideoListRenderer': self._playlist_entries, | |
3957 | 'gridRenderer': self._grid_entries, | |
3958 | 'shelfRenderer': lambda x: self._shelf_entries(x), | |
16aa9ea4 | 3959 | 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)], |
a6213a49 | 3960 | 'backstagePostThreadRenderer': self._post_thread_entries, |
3961 | 'videoRenderer': lambda x: [self._video_entry(x)], | |
a61fd4cf | 3962 | 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}), |
3963 | 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}), | |
a6213a49 | 3964 | } |
3965 | for key, renderer in isr_content.items(): | |
3966 | if key not in known_renderers: | |
3967 | continue | |
3968 | for entry in known_renderers[key](renderer): | |
3969 | if entry: | |
3970 | yield entry | |
3971 | continuation_list[0] = self._extract_continuation(renderer) | |
3972 | break | |
70d5c17b | 3973 | |
3974 | if not continuation_list[0]: | |
a6213a49 | 3975 | continuation_list[0] = self._extract_continuation(is_renderer) |
3462ffa8 | 3976 | |
a6213a49 | 3977 | if not continuation_list[0]: |
3978 | continuation_list[0] = self._extract_continuation(parent_renderer) | |
3979 | ||
3980 | def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data): | |
3981 | continuation_list = [None] | |
3982 | extract_entries = lambda x: self._extract_entries(x, continuation_list) | |
29f7c58a | 3983 | tab_content = try_get(tab, lambda x: x['content'], dict) |
3984 | if not tab_content: | |
3985 | return | |
3462ffa8 | 3986 | parent_renderer = ( |
29f7c58a | 3987 | try_get(tab_content, lambda x: x['sectionListRenderer'], dict) |
3988 | or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {}) | |
70d5c17b | 3989 | for entry in extract_entries(parent_renderer): |
3990 | yield entry | |
3462ffa8 | 3991 | continuation = continuation_list[0] |
d069eca7 | 3992 | |
8bdd16b4 | 3993 | for page_num in itertools.count(1): |
3994 | if not continuation: | |
3995 | break | |
99e9e001 | 3996 | headers = self.generate_api_headers( |
3997 | ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data) | |
79360d99 | 3998 | response = self._extract_response( |
3999 | item_id='%s page %s' % (item_id, page_num), | |
fe93e2c4 | 4000 | query=continuation, headers=headers, ytcfg=ytcfg, |
79360d99 | 4001 | check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints')) |
a5c56234 M |
4002 | |
4003 | if not response: | |
8bdd16b4 | 4004 | break |
ac56cf38 | 4005 | # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases |
4006 | # See: https://github.com/ytdl-org/youtube-dl/issues/28702 | |
4007 | visitor_data = self._extract_visitor_data(response) or visitor_data | |
ebf1b291 | 4008 | |
69184e41 | 4009 | known_continuation_renderers = { |
4010 | 'playlistVideoListContinuation': self._playlist_entries, | |
4011 | 'gridContinuation': self._grid_entries, | |
4012 | 'itemSectionContinuation': self._post_thread_continuation_entries, | |
4013 | 'sectionListContinuation': extract_entries, # for feeds | |
4014 | } | |
8bdd16b4 | 4015 | continuation_contents = try_get( |
69184e41 | 4016 | response, lambda x: x['continuationContents'], dict) or {} |
4017 | continuation_renderer = None | |
4018 | for key, value in continuation_contents.items(): | |
4019 | if key not in known_continuation_renderers: | |
3462ffa8 | 4020 | continue |
69184e41 | 4021 | continuation_renderer = value |
4022 | continuation_list = [None] | |
4023 | for entry in known_continuation_renderers[key](continuation_renderer): | |
4024 | yield entry | |
4025 | continuation = continuation_list[0] or self._extract_continuation(continuation_renderer) | |
4026 | break | |
4027 | if continuation_renderer: | |
4028 | continue | |
c5e8d7af | 4029 | |
a1b535bd | 4030 | known_renderers = { |
4031 | 'gridPlaylistRenderer': (self._grid_entries, 'items'), | |
4032 | 'gridVideoRenderer': (self._grid_entries, 'items'), | |
d61fc646 | 4033 | 'gridChannelRenderer': (self._grid_entries, 'items'), |
a1b535bd | 4034 | 'playlistVideoRenderer': (self._playlist_entries, 'contents'), |
cd7c66cf | 4035 | 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds |
9ba5705a | 4036 | 'richItemRenderer': (extract_entries, 'contents'), # for hashtag |
26fe8ffe | 4037 | 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents') |
a1b535bd | 4038 | } |
cce889b9 | 4039 | on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints')) |
8bdd16b4 | 4040 | continuation_items = try_get( |
cce889b9 | 4041 | on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list) |
a1b535bd | 4042 | continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {} |
4043 | video_items_renderer = None | |
4044 | for key, value in continuation_item.items(): | |
4045 | if key not in known_renderers: | |
8bdd16b4 | 4046 | continue |
a1b535bd | 4047 | video_items_renderer = {known_renderers[key][1]: continuation_items} |
9ba5705a | 4048 | continuation_list = [None] |
a1b535bd | 4049 | for entry in known_renderers[key][0](video_items_renderer): |
4050 | yield entry | |
9ba5705a | 4051 | continuation = continuation_list[0] or self._extract_continuation(video_items_renderer) |
a1b535bd | 4052 | break |
4053 | if video_items_renderer: | |
4054 | continue | |
8bdd16b4 | 4055 | break |
9558dcec | 4056 | |
8bdd16b4 | 4057 | @staticmethod |
7c219ea6 | 4058 | def _extract_selected_tab(tabs, fatal=True): |
8bdd16b4 | 4059 | for tab in tabs: |
cd684175 | 4060 | renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {} |
4061 | if renderer.get('selected') is True: | |
4062 | return renderer | |
2b3c2546 | 4063 | else: |
7c219ea6 | 4064 | if fatal: |
4065 | raise ExtractorError('Unable to find selected tab') | |
b82f815f | 4066 | |
47193e02 | 4067 | @classmethod |
4068 | def _extract_uploader(cls, data): | |
8bdd16b4 | 4069 | uploader = {} |
47193e02 | 4070 | renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {} |
4071 | owner = try_get( | |
4072 | renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict) | |
4073 | if owner: | |
4074 | uploader['uploader'] = owner.get('text') | |
4075 | uploader['uploader_id'] = try_get( | |
4076 | owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str) | |
4077 | uploader['uploader_url'] = urljoin( | |
4078 | 'https://www.youtube.com/', | |
4079 | try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str)) | |
9c3fe2ef | 4080 | return {k: v for k, v in uploader.items() if v is not None} |
8bdd16b4 | 4081 | |
ac56cf38 | 4082 | def _extract_from_tabs(self, item_id, ytcfg, data, tabs): |
b60419c5 | 4083 | playlist_id = title = description = channel_url = channel_name = channel_id = None |
ac56cf38 | 4084 | tags = [] |
b60419c5 | 4085 | |
8bdd16b4 | 4086 | selected_tab = self._extract_selected_tab(tabs) |
f0d785d3 | 4087 | primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') |
8bdd16b4 | 4088 | renderer = try_get( |
4089 | data, lambda x: x['metadata']['channelMetadataRenderer'], dict) | |
4090 | if renderer: | |
b60419c5 | 4091 | channel_name = renderer.get('title') |
4092 | channel_url = renderer.get('channelUrl') | |
4093 | channel_id = renderer.get('externalId') | |
39ed931e | 4094 | else: |
64c0d954 | 4095 | renderer = try_get( |
4096 | data, lambda x: x['metadata']['playlistMetadataRenderer'], dict) | |
39ed931e | 4097 | |
8bdd16b4 | 4098 | if renderer: |
4099 | title = renderer.get('title') | |
ecc97af3 | 4100 | description = renderer.get('description', '') |
b60419c5 | 4101 | playlist_id = channel_id |
4102 | tags = renderer.get('keywords', '').split() | |
b60419c5 | 4103 | |
301d07fc | 4104 | # We can get the uncropped banner/avatar by replacing the crop params with '=s0' |
4105 | # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714 | |
4106 | def _get_uncropped(url): | |
4107 | return url_or_none((url or '').split('=')[0] + '=s0') | |
4108 | ||
4109 | avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar') | |
4110 | if avatar_thumbnails: | |
4111 | uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url']) | |
4112 | if uncropped_avatar: | |
4113 | avatar_thumbnails.append({ | |
4114 | 'url': uncropped_avatar, | |
4115 | 'id': 'avatar_uncropped', | |
4116 | 'preference': 1 | |
4117 | }) | |
4118 | ||
4119 | channel_banners = self._extract_thumbnails( | |
4120 | data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner'])) | |
4121 | for banner in channel_banners: | |
4122 | banner['preference'] = -10 | |
4123 | ||
4124 | if channel_banners: | |
4125 | uncropped_banner = _get_uncropped(channel_banners[0]['url']) | |
4126 | if uncropped_banner: | |
4127 | channel_banners.append({ | |
4128 | 'url': uncropped_banner, | |
4129 | 'id': 'banner_uncropped', | |
4130 | 'preference': -5 | |
4131 | }) | |
4132 | ||
4133 | primary_thumbnails = self._extract_thumbnails( | |
4134 | primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail')) | |
a709d873 | 4135 | |
3462ffa8 | 4136 | if playlist_id is None: |
70d5c17b | 4137 | playlist_id = item_id |
f0d785d3 | 4138 | |
4139 | playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats') | |
4140 | last_updated_unix, _ = self._extract_time_text(playlist_stats, 2) | |
70d5c17b | 4141 | if title is None: |
f0d785d3 | 4142 | title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id |
b60419c5 | 4143 | title += format_field(selected_tab, 'title', ' - %s') |
cd684175 | 4144 | title += format_field(selected_tab, 'expandedText', ' - %s') |
f0d785d3 | 4145 | |
b60419c5 | 4146 | metadata = { |
4147 | 'playlist_id': playlist_id, | |
4148 | 'playlist_title': title, | |
4149 | 'playlist_description': description, | |
4150 | 'uploader': channel_name, | |
4151 | 'uploader_id': channel_id, | |
4152 | 'uploader_url': channel_url, | |
301d07fc | 4153 | 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners, |
b60419c5 | 4154 | 'tags': tags, |
f0d785d3 | 4155 | 'view_count': self._get_count(playlist_stats, 1), |
4156 | 'availability': self._extract_availability(data), | |
4157 | 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'), | |
6c73052c | 4158 | 'playlist_count': self._get_count(playlist_stats, 0), |
4159 | 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')), | |
b60419c5 | 4160 | } |
4161 | if not channel_id: | |
4162 | metadata.update(self._extract_uploader(data)) | |
4163 | metadata.update({ | |
4164 | 'channel': metadata['uploader'], | |
4165 | 'channel_id': metadata['uploader_id'], | |
4166 | 'channel_url': metadata['uploader_url']}) | |
4167 | return self.playlist_result( | |
d069eca7 | 4168 | self._entries( |
ac56cf38 | 4169 | selected_tab, playlist_id, ytcfg, |
4170 | self._extract_account_syncid(ytcfg, data), | |
4171 | self._extract_visitor_data(data, ytcfg)), | |
b60419c5 | 4172 | **metadata) |
73c4ac2c | 4173 | |
ac56cf38 | 4174 | def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg): |
4175 | first_id = last_id = response = None | |
2be71994 | 4176 | for page_num in itertools.count(1): |
cd7c66cf | 4177 | videos = list(self._playlist_entries(playlist)) |
4178 | if not videos: | |
4179 | return | |
2be71994 | 4180 | start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1 |
4181 | if start >= len(videos): | |
4182 | return | |
4183 | for video in videos[start:]: | |
4184 | if video['id'] == first_id: | |
4185 | self.to_screen('First video %s found again; Assuming end of Mix' % first_id) | |
4186 | return | |
4187 | yield video | |
4188 | first_id = first_id or videos[0]['id'] | |
4189 | last_id = videos[-1]['id'] | |
79360d99 | 4190 | watch_endpoint = try_get( |
4191 | playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint']) | |
ac56cf38 | 4192 | headers = self.generate_api_headers( |
4193 | ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data), | |
4194 | visitor_data=self._extract_visitor_data(response, data, ytcfg)) | |
79360d99 | 4195 | query = { |
4196 | 'playlistId': playlist_id, | |
4197 | 'videoId': watch_endpoint.get('videoId') or last_id, | |
4198 | 'index': watch_endpoint.get('index') or len(videos), | |
4199 | 'params': watch_endpoint.get('params') or 'OAE%3D' | |
4200 | } | |
4201 | response = self._extract_response( | |
4202 | item_id='%s page %d' % (playlist_id, page_num), | |
fe93e2c4 | 4203 | query=query, ep='next', headers=headers, ytcfg=ytcfg, |
79360d99 | 4204 | check_get_keys='contents' |
4205 | ) | |
cd7c66cf | 4206 | playlist = try_get( |
79360d99 | 4207 | response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict) |
cd7c66cf | 4208 | |
ac56cf38 | 4209 | def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg): |
8bdd16b4 | 4210 | title = playlist.get('title') or try_get( |
4211 | data, lambda x: x['titleText']['simpleText'], compat_str) | |
4212 | playlist_id = playlist.get('playlistId') or item_id | |
cd7c66cf | 4213 | |
4214 | # Delegating everything except mix playlists to regular tab-based playlist URL | |
29f7c58a | 4215 | playlist_url = urljoin(url, try_get( |
4216 | playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], | |
4217 | compat_str)) | |
4218 | if playlist_url and playlist_url != url: | |
4219 | return self.url_result( | |
4220 | playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id, | |
4221 | video_title=title) | |
cd7c66cf | 4222 | |
8bdd16b4 | 4223 | return self.playlist_result( |
ac56cf38 | 4224 | self._extract_mix_playlist(playlist, playlist_id, data, ytcfg), |
cd7c66cf | 4225 | playlist_id=playlist_id, playlist_title=title) |
c5e8d7af | 4226 | |
47193e02 | 4227 | def _extract_availability(self, data): |
4228 | """ | |
4229 | Gets the availability of a given playlist/tab. | |
4230 | Note: Unless YouTube tells us explicitly, we do not assume it is public | |
4231 | @param data: response | |
4232 | """ | |
4233 | is_private = is_unlisted = None | |
4234 | renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {} | |
4235 | badge_labels = self._extract_badges(renderer) | |
4236 | ||
4237 | # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge | |
4238 | privacy_dropdown_entries = try_get( | |
4239 | renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or [] | |
4240 | for renderer_dict in privacy_dropdown_entries: | |
4241 | is_selected = try_get( | |
4242 | renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False | |
4243 | if not is_selected: | |
4244 | continue | |
052e1350 | 4245 | label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label')) |
47193e02 | 4246 | if label: |
4247 | badge_labels.add(label.lower()) | |
4248 | break | |
4249 | ||
4250 | for badge_label in badge_labels: | |
4251 | if badge_label == 'unlisted': | |
4252 | is_unlisted = True | |
4253 | elif badge_label == 'private': | |
4254 | is_private = True | |
4255 | elif badge_label == 'public': | |
4256 | is_unlisted = is_private = False | |
4257 | return self._availability(is_private, False, False, False, is_unlisted) | |
4258 | ||
4259 | @staticmethod | |
4260 | def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict): | |
4261 | sidebar_renderer = try_get( | |
4262 | data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or [] | |
4263 | for item in sidebar_renderer: | |
4264 | renderer = try_get(item, lambda x: x[info_renderer], expected_type) | |
4265 | if renderer: | |
4266 | return renderer | |
4267 | ||
ac56cf38 | 4268 | def _reload_with_unavailable_videos(self, item_id, data, ytcfg): |
358de58c | 4269 | """ |
4270 | Get playlist with unavailable videos if the 'show unavailable videos' button exists. | |
4271 | """ | |
5d342002 | 4272 | browse_id = params = None |
47193e02 | 4273 | renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') |
4274 | if not renderer: | |
4275 | return | |
4276 | menu_renderer = try_get( | |
4277 | renderer, lambda x: x['menu']['menuRenderer']['items'], list) or [] | |
4278 | for menu_item in menu_renderer: | |
4279 | if not isinstance(menu_item, dict): | |
358de58c | 4280 | continue |
47193e02 | 4281 | nav_item_renderer = menu_item.get('menuNavigationItemRenderer') |
4282 | text = try_get( | |
4283 | nav_item_renderer, lambda x: x['text']['simpleText'], compat_str) | |
4284 | if not text or text.lower() != 'show unavailable videos': | |
4285 | continue | |
4286 | browse_endpoint = try_get( | |
4287 | nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {} | |
4288 | browse_id = browse_endpoint.get('browseId') | |
4289 | params = browse_endpoint.get('params') | |
4290 | break | |
5d342002 | 4291 | |
11f9be09 | 4292 | headers = self.generate_api_headers( |
99e9e001 | 4293 | ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data), |
ac56cf38 | 4294 | visitor_data=self._extract_visitor_data(data, ytcfg)) |
47193e02 | 4295 | query = { |
4296 | 'params': params or 'wgYCCAA=', | |
4297 | 'browseId': browse_id or 'VL%s' % item_id | |
4298 | } | |
4299 | return self._extract_response( | |
4300 | item_id=item_id, headers=headers, query=query, | |
fe93e2c4 | 4301 | check_get_keys='contents', fatal=False, ytcfg=ytcfg, |
47193e02 | 4302 | note='Downloading API JSON with unavailable videos') |
358de58c | 4303 | |
ac56cf38 | 4304 | def _extract_webpage(self, url, item_id, fatal=True): |
a06916d9 | 4305 | retries = self.get_param('extractor_retries', 3) |
62bff2c1 | 4306 | count = -1 |
ac56cf38 | 4307 | webpage = data = last_error = None |
14fdfea9 | 4308 | while count < retries: |
62bff2c1 | 4309 | count += 1 |
14fdfea9 | 4310 | # Sometimes youtube returns a webpage with incomplete ytInitialData |
62bff2c1 | 4311 | # See: https://github.com/yt-dlp/yt-dlp/issues/116 |
ac56cf38 | 4312 | if last_error: |
c705177d | 4313 | self.report_warning('%s. Retrying ...' % last_error) |
ac56cf38 | 4314 | try: |
4315 | webpage = self._download_webpage( | |
4316 | url, item_id, | |
4317 | note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',)) | |
4318 | data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {} | |
4319 | except ExtractorError as e: | |
4320 | if isinstance(e.cause, network_exceptions): | |
4321 | if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429): | |
4322 | last_error = error_to_compat_str(e.cause or e.msg) | |
4323 | if count < retries: | |
4324 | continue | |
4325 | if fatal: | |
4326 | raise | |
4327 | self.report_warning(error_to_compat_str(e)) | |
14fdfea9 | 4328 | break |
ac56cf38 | 4329 | else: |
4330 | try: | |
4331 | self._extract_and_report_alerts(data) | |
4332 | except ExtractorError as e: | |
4333 | if fatal: | |
4334 | raise | |
4335 | self.report_warning(error_to_compat_str(e)) | |
4336 | break | |
4337 | ||
7c219ea6 | 4338 | if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')): |
ac56cf38 | 4339 | break |
4340 | ||
4341 | last_error = 'Incomplete yt initial data received' | |
4342 | if count >= retries: | |
4343 | if fatal: | |
4344 | raise ExtractorError(last_error) | |
4345 | self.report_warning(last_error) | |
4346 | break | |
4347 | ||
cd7c66cf | 4348 | return webpage, data |
4349 | ||
ac56cf38 | 4350 | def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'): |
4351 | data = None | |
4352 | if 'webpage' not in self._configuration_arg('skip'): | |
4353 | webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal) | |
4354 | ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage) | |
1108613f | 4355 | # Reject webpage data if redirected to home page without explicitly requesting |
4356 | selected_tab = self._extract_selected_tab(traverse_obj( | |
7c219ea6 | 4357 | data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {} |
1108613f | 4358 | if (url != 'https://www.youtube.com/feed/recommended' |
4359 | and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page | |
4360 | and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])): | |
4361 | msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page' | |
4362 | if fatal: | |
4363 | raise ExtractorError(msg, expected=True) | |
4364 | self.report_warning(msg, only_once=True) | |
ac56cf38 | 4365 | if not data: |
4366 | if not ytcfg and self.is_authenticated: | |
4367 | msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.' | |
4368 | if 'authcheck' not in self._configuration_arg('skip') and fatal: | |
4369 | raise ExtractorError( | |
4370 | msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,' | |
4371 | ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check', | |
4372 | expected=True) | |
4373 | self.report_warning(msg, only_once=True) | |
4374 | data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client) | |
4375 | return data, ytcfg | |
4376 | ||
4377 | def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'): | |
4378 | headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client) | |
4379 | resolve_response = self._extract_response( | |
4380 | item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal, | |
4381 | ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client) | |
4382 | endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'} | |
4383 | for ep_key, ep in endpoints.items(): | |
4384 | params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict) | |
4385 | if params: | |
4386 | return self._extract_response( | |
4387 | item_id=item_id, query=params, ep=ep, headers=headers, | |
4388 | ytcfg=ytcfg, fatal=fatal, default_client=default_client, | |
7c219ea6 | 4389 | check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')) |
ac56cf38 | 4390 | err_note = 'Failed to resolve url (does the playlist exist?)' |
4391 | if fatal: | |
4392 | raise ExtractorError(err_note, expected=True) | |
4393 | self.report_warning(err_note, item_id) | |
4394 | ||
a6213a49 | 4395 | _SEARCH_PARAMS = None |
4396 | ||
af5c1c55 | 4397 | def _search_results(self, query, params=NO_DEFAULT, default_client='web'): |
a6213a49 | 4398 | data = {'query': query} |
4399 | if params is NO_DEFAULT: | |
4400 | params = self._SEARCH_PARAMS | |
4401 | if params: | |
4402 | data['params'] = params | |
16aa9ea4 | 4403 | |
4404 | content_keys = ( | |
4405 | ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'), | |
4406 | ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'), | |
4407 | # ytmusic search | |
4408 | ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'), | |
4409 | ('continuationContents', ), | |
4410 | ) | |
4411 | check_get_keys = tuple(set(keys[0] for keys in content_keys)) | |
4412 | ||
a61fd4cf | 4413 | continuation_list = [None] |
a6213a49 | 4414 | for page_num in itertools.count(1): |
a61fd4cf | 4415 | data.update(continuation_list[0] or {}) |
a6213a49 | 4416 | search = self._extract_response( |
4417 | item_id='query "%s" page %s' % (query, page_num), ep='search', query=data, | |
af5c1c55 | 4418 | default_client=default_client, check_get_keys=check_get_keys) |
16aa9ea4 | 4419 | slr_contents = traverse_obj(search, *content_keys) |
4420 | yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list) | |
a61fd4cf | 4421 | if not continuation_list[0]: |
a6213a49 | 4422 | break |
4423 | ||
4424 | ||
4425 | class YoutubeTabIE(YoutubeTabBaseInfoExtractor): | |
4426 | IE_DESC = 'YouTube Tabs' | |
4427 | _VALID_URL = r'''(?x: | |
4428 | https?:// | |
4429 | (?:\w+\.)? | |
4430 | (?: | |
4431 | youtube(?:kids)?\.com| | |
4432 | %(invidious)s | |
4433 | )/ | |
4434 | (?: | |
4435 | (?P<channel_type>channel|c|user|browse)/| | |
4436 | (?P<not_channel> | |
4437 | feed/|hashtag/| | |
4438 | (?:playlist|watch)\?.*?\blist= | |
4439 | )| | |
4440 | (?!(?:%(reserved_names)s)\b) # Direct URLs | |
4441 | ) | |
4442 | (?P<id>[^/?\#&]+) | |
4443 | )''' % { | |
4444 | 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES, | |
4445 | 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), | |
4446 | } | |
4447 | IE_NAME = 'youtube:tab' | |
4448 | ||
4449 | _TESTS = [{ | |
4450 | 'note': 'playlists, multipage', | |
4451 | 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid', | |
4452 | 'playlist_mincount': 94, | |
4453 | 'info_dict': { | |
4454 | 'id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
976ae3ea | 4455 | 'title': 'Igor Kleiner - Playlists', |
a6213a49 | 4456 | 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', |
976ae3ea | 4457 | 'uploader': 'Igor Kleiner', |
a6213a49 | 4458 | 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', |
976ae3ea | 4459 | 'channel': 'Igor Kleiner', |
4460 | 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
4461 | 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'], | |
4462 | 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', | |
4463 | 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', | |
6c73052c | 4464 | 'channel_follower_count': int |
a6213a49 | 4465 | }, |
4466 | }, { | |
4467 | 'note': 'playlists, multipage, different order', | |
4468 | 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', | |
4469 | 'playlist_mincount': 94, | |
4470 | 'info_dict': { | |
4471 | 'id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
976ae3ea | 4472 | 'title': 'Igor Kleiner - Playlists', |
a6213a49 | 4473 | 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', |
4474 | 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
976ae3ea | 4475 | 'uploader': 'Igor Kleiner', |
4476 | 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', | |
4477 | 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'], | |
4478 | 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
4479 | 'channel': 'Igor Kleiner', | |
4480 | 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', | |
6c73052c | 4481 | 'channel_follower_count': int |
a6213a49 | 4482 | }, |
4483 | }, { | |
4484 | 'note': 'playlists, series', | |
4485 | 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3', | |
4486 | 'playlist_mincount': 5, | |
4487 | 'info_dict': { | |
4488 | 'id': 'UCYO_jab_esuFRV4b17AJtAw', | |
4489 | 'title': '3Blue1Brown - Playlists', | |
4490 | 'description': 'md5:e1384e8a133307dd10edee76e875d62f', | |
4491 | 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
4492 | 'uploader': '3Blue1Brown', | |
976ae3ea | 4493 | 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', |
4494 | 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', | |
4495 | 'channel': '3Blue1Brown', | |
4496 | 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
4497 | 'tags': ['Mathematics'], | |
6c73052c | 4498 | 'channel_follower_count': int |
a6213a49 | 4499 | }, |
4500 | }, { | |
4501 | 'note': 'playlists, singlepage', | |
4502 | 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', | |
4503 | 'playlist_mincount': 4, | |
4504 | 'info_dict': { | |
4505 | 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
4506 | 'title': 'ThirstForScience - Playlists', | |
4507 | 'description': 'md5:609399d937ea957b0f53cbffb747a14c', | |
4508 | 'uploader': 'ThirstForScience', | |
4509 | 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
976ae3ea | 4510 | 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ', |
4511 | 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ', | |
4512 | 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
4513 | 'tags': 'count:13', | |
4514 | 'channel': 'ThirstForScience', | |
6c73052c | 4515 | 'channel_follower_count': int |
a6213a49 | 4516 | } |
4517 | }, { | |
4518 | 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', | |
4519 | 'only_matching': True, | |
4520 | }, { | |
4521 | 'note': 'basic, single video playlist', | |
4522 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
4523 | 'info_dict': { | |
4524 | 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
4525 | 'uploader': 'Sergey M.', | |
4526 | 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
4527 | 'title': 'youtube-dl public playlist', | |
976ae3ea | 4528 | 'description': '', |
4529 | 'tags': [], | |
4530 | 'view_count': int, | |
4531 | 'modified_date': '20201130', | |
4532 | 'channel': 'Sergey M.', | |
4533 | 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
4534 | 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4535 | 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
a6213a49 | 4536 | }, |
4537 | 'playlist_count': 1, | |
4538 | }, { | |
4539 | 'note': 'empty playlist', | |
4540 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', | |
4541 | 'info_dict': { | |
4542 | 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
4543 | 'uploader': 'Sergey M.', | |
4544 | 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', | |
4545 | 'title': 'youtube-dl empty playlist', | |
976ae3ea | 4546 | 'tags': [], |
4547 | 'channel': 'Sergey M.', | |
4548 | 'description': '', | |
4549 | 'modified_date': '20160902', | |
4550 | 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
4551 | 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4552 | 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
a6213a49 | 4553 | }, |
4554 | 'playlist_count': 0, | |
4555 | }, { | |
4556 | 'note': 'Home tab', | |
4557 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured', | |
4558 | 'info_dict': { | |
4559 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4560 | 'title': 'lex will - Home', | |
4561 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4562 | 'uploader': 'lex will', | |
4563 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
976ae3ea | 4564 | 'channel': 'lex will', |
4565 | 'tags': ['bible', 'history', 'prophesy'], | |
4566 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4567 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4568 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
6c73052c | 4569 | 'channel_follower_count': int |
a6213a49 | 4570 | }, |
4571 | 'playlist_mincount': 2, | |
4572 | }, { | |
4573 | 'note': 'Videos tab', | |
4574 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos', | |
4575 | 'info_dict': { | |
4576 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4577 | 'title': 'lex will - Videos', | |
4578 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4579 | 'uploader': 'lex will', | |
4580 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
976ae3ea | 4581 | 'tags': ['bible', 'history', 'prophesy'], |
4582 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4583 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4584 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4585 | 'channel': 'lex will', | |
6c73052c | 4586 | 'channel_follower_count': int |
a6213a49 | 4587 | }, |
4588 | 'playlist_mincount': 975, | |
4589 | }, { | |
4590 | 'note': 'Videos tab, sorted by popular', | |
4591 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid', | |
4592 | 'info_dict': { | |
4593 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4594 | 'title': 'lex will - Videos', | |
4595 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4596 | 'uploader': 'lex will', | |
4597 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
976ae3ea | 4598 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', |
4599 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4600 | 'channel': 'lex will', | |
4601 | 'tags': ['bible', 'history', 'prophesy'], | |
4602 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
6c73052c | 4603 | 'channel_follower_count': int |
a6213a49 | 4604 | }, |
4605 | 'playlist_mincount': 199, | |
4606 | }, { | |
4607 | 'note': 'Playlists tab', | |
4608 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists', | |
4609 | 'info_dict': { | |
4610 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4611 | 'title': 'lex will - Playlists', | |
4612 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4613 | 'uploader': 'lex will', | |
4614 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
976ae3ea | 4615 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', |
4616 | 'channel': 'lex will', | |
4617 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4618 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4619 | 'tags': ['bible', 'history', 'prophesy'], | |
6c73052c | 4620 | 'channel_follower_count': int |
a6213a49 | 4621 | }, |
4622 | 'playlist_mincount': 17, | |
4623 | }, { | |
4624 | 'note': 'Community tab', | |
4625 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community', | |
4626 | 'info_dict': { | |
4627 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4628 | 'title': 'lex will - Community', | |
4629 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4630 | 'uploader': 'lex will', | |
4631 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
976ae3ea | 4632 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', |
4633 | 'channel': 'lex will', | |
4634 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4635 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4636 | 'tags': ['bible', 'history', 'prophesy'], | |
6c73052c | 4637 | 'channel_follower_count': int |
a6213a49 | 4638 | }, |
4639 | 'playlist_mincount': 18, | |
4640 | }, { | |
4641 | 'note': 'Channels tab', | |
4642 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels', | |
4643 | 'info_dict': { | |
4644 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4645 | 'title': 'lex will - Channels', | |
4646 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4647 | 'uploader': 'lex will', | |
4648 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
976ae3ea | 4649 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', |
4650 | 'channel': 'lex will', | |
4651 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4652 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4653 | 'tags': ['bible', 'history', 'prophesy'], | |
6c73052c | 4654 | 'channel_follower_count': int |
a6213a49 | 4655 | }, |
4656 | 'playlist_mincount': 12, | |
4657 | }, { | |
4658 | 'note': 'Search tab', | |
4659 | 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra', | |
4660 | 'playlist_mincount': 40, | |
4661 | 'info_dict': { | |
4662 | 'id': 'UCYO_jab_esuFRV4b17AJtAw', | |
4663 | 'title': '3Blue1Brown - Search - linear algebra', | |
4664 | 'description': 'md5:e1384e8a133307dd10edee76e875d62f', | |
4665 | 'uploader': '3Blue1Brown', | |
4666 | 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
976ae3ea | 4667 | 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', |
4668 | 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', | |
4669 | 'tags': ['Mathematics'], | |
4670 | 'channel': '3Blue1Brown', | |
4671 | 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
6c73052c | 4672 | 'channel_follower_count': int |
a6213a49 | 4673 | }, |
4674 | }, { | |
4675 | 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4676 | 'only_matching': True, | |
4677 | }, { | |
4678 | 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4679 | 'only_matching': True, | |
4680 | }, { | |
4681 | 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4682 | 'only_matching': True, | |
4683 | }, { | |
4684 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
4685 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
4686 | 'info_dict': { | |
4687 | 'title': '29C3: Not my department', | |
4688 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
4689 | 'uploader': 'Christiaan008', | |
4690 | 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg', | |
4691 | 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268', | |
976ae3ea | 4692 | 'tags': [], |
4693 | 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008', | |
4694 | 'view_count': int, | |
4695 | 'modified_date': '20150605', | |
4696 | 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg', | |
4697 | 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008', | |
4698 | 'channel': 'Christiaan008', | |
a6213a49 | 4699 | }, |
4700 | 'playlist_count': 96, | |
4701 | }, { | |
4702 | 'note': 'Large playlist', | |
4703 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
4704 | 'info_dict': { | |
4705 | 'title': 'Uploads from Cauchemar', | |
4706 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', | |
4707 | 'uploader': 'Cauchemar', | |
4708 | 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q', | |
976ae3ea | 4709 | 'channel_url': 'https://www.youtube.com/c/Cauchemar89', |
4710 | 'tags': [], | |
4711 | 'modified_date': r're:\d{8}', | |
4712 | 'channel': 'Cauchemar', | |
4713 | 'uploader_url': 'https://www.youtube.com/c/Cauchemar89', | |
4714 | 'view_count': int, | |
4715 | 'description': '', | |
4716 | 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q', | |
a6213a49 | 4717 | }, |
4718 | 'playlist_mincount': 1123, | |
976ae3ea | 4719 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], |
a6213a49 | 4720 | }, { |
4721 | 'note': 'even larger playlist, 8832 videos', | |
4722 | 'url': 'http://www.youtube.com/user/NASAgovVideo/videos', | |
4723 | 'only_matching': True, | |
4724 | }, { | |
4725 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
4726 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
4727 | 'info_dict': { | |
4728 | 'title': 'Uploads from Interstellar Movie', | |
4729 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
4730 | 'uploader': 'Interstellar Movie', | |
4731 | 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA', | |
976ae3ea | 4732 | 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie', |
4733 | 'tags': [], | |
4734 | 'view_count': int, | |
4735 | 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA', | |
4736 | 'channel_url': 'https://www.youtube.com/c/InterstellarMovie', | |
4737 | 'channel': 'Interstellar Movie', | |
4738 | 'description': '', | |
4739 | 'modified_date': r're:\d{8}', | |
a6213a49 | 4740 | }, |
4741 | 'playlist_mincount': 21, | |
4742 | }, { | |
4743 | 'note': 'Playlist with "show unavailable videos" button', | |
4744 | 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q', | |
4745 | 'info_dict': { | |
4746 | 'title': 'Uploads from Phim Siêu Nhân Nhật Bản', | |
4747 | 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q', | |
4748 | 'uploader': 'Phim Siêu Nhân Nhật Bản', | |
4749 | 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q', | |
976ae3ea | 4750 | 'view_count': int, |
4751 | 'channel': 'Phim Siêu Nhân Nhật Bản', | |
4752 | 'tags': [], | |
4753 | 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q', | |
4754 | 'description': '', | |
4755 | 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q', | |
4756 | 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q', | |
4757 | 'modified_date': r're:\d{8}', | |
a6213a49 | 4758 | }, |
4759 | 'playlist_mincount': 200, | |
976ae3ea | 4760 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], |
a6213a49 | 4761 | }, { |
4762 | 'note': 'Playlist with unavailable videos in page 7', | |
4763 | 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w', | |
4764 | 'info_dict': { | |
4765 | 'title': 'Uploads from BlankTV', | |
4766 | 'id': 'UU8l9frL61Yl5KFOl87nIm2w', | |
4767 | 'uploader': 'BlankTV', | |
4768 | 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w', | |
976ae3ea | 4769 | 'channel': 'BlankTV', |
4770 | 'channel_url': 'https://www.youtube.com/c/blanktv', | |
4771 | 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w', | |
4772 | 'view_count': int, | |
4773 | 'tags': [], | |
4774 | 'uploader_url': 'https://www.youtube.com/c/blanktv', | |
4775 | 'modified_date': r're:\d{8}', | |
4776 | 'description': '', | |
a6213a49 | 4777 | }, |
4778 | 'playlist_mincount': 1000, | |
976ae3ea | 4779 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], |
a6213a49 | 4780 | }, { |
4781 | 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844', | |
4782 | 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
4783 | 'info_dict': { | |
4784 | 'title': 'Data Analysis with Dr Mike Pound', | |
4785 | 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
4786 | 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA', | |
4787 | 'uploader': 'Computerphile', | |
4788 | 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487', | |
976ae3ea | 4789 | 'uploader_url': 'https://www.youtube.com/user/Computerphile', |
4790 | 'tags': [], | |
4791 | 'view_count': int, | |
4792 | 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA', | |
4793 | 'channel_url': 'https://www.youtube.com/user/Computerphile', | |
4794 | 'channel': 'Computerphile', | |
a6213a49 | 4795 | }, |
4796 | 'playlist_mincount': 11, | |
4797 | }, { | |
4798 | 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
4799 | 'only_matching': True, | |
4800 | }, { | |
4801 | 'note': 'Playlist URL that does not actually serve a playlist', | |
4802 | 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', | |
4803 | 'info_dict': { | |
4804 | 'id': 'FqZTN594JQw', | |
4805 | 'ext': 'webm', | |
4806 | 'title': "Smiley's People 01 detective, Adventure Series, Action", | |
4807 | 'uploader': 'STREEM', | |
4808 | 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng', | |
4809 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng', | |
4810 | 'upload_date': '20150526', | |
4811 | 'license': 'Standard YouTube License', | |
4812 | 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', | |
4813 | 'categories': ['People & Blogs'], | |
4814 | 'tags': list, | |
4815 | 'view_count': int, | |
4816 | 'like_count': int, | |
a6213a49 | 4817 | }, |
4818 | 'params': { | |
4819 | 'skip_download': True, | |
4820 | }, | |
4821 | 'skip': 'This video is not available.', | |
4822 | 'add_ie': [YoutubeIE.ie_key()], | |
4823 | }, { | |
4824 | 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g', | |
4825 | 'only_matching': True, | |
4826 | }, { | |
4827 | 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', | |
4828 | 'only_matching': True, | |
4829 | }, { | |
4830 | 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live', | |
4831 | 'info_dict': { | |
6c73052c | 4832 | 'id': 'GgL890LIznQ', # This will keep changing |
a6213a49 | 4833 | 'ext': 'mp4', |
976ae3ea | 4834 | 'title': str, |
a6213a49 | 4835 | 'uploader': 'Sky News', |
4836 | 'uploader_id': 'skynews', | |
4837 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews', | |
4838 | 'upload_date': r're:\d{8}', | |
976ae3ea | 4839 | 'description': str, |
a6213a49 | 4840 | 'categories': ['News & Politics'], |
4841 | 'tags': list, | |
4842 | 'like_count': int, | |
6c73052c | 4843 | 'release_timestamp': 1642502819, |
976ae3ea | 4844 | 'channel': 'Sky News', |
4845 | 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ', | |
4846 | 'age_limit': 0, | |
4847 | 'view_count': int, | |
6c73052c | 4848 | 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg', |
976ae3ea | 4849 | 'playable_in_embed': True, |
6c73052c | 4850 | 'release_date': '20220118', |
976ae3ea | 4851 | 'availability': 'public', |
4852 | 'live_status': 'is_live', | |
4853 | 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ', | |
6c73052c | 4854 | 'channel_follower_count': int |
a6213a49 | 4855 | }, |
4856 | 'params': { | |
4857 | 'skip_download': True, | |
4858 | }, | |
976ae3ea | 4859 | 'expected_warnings': ['Ignoring subtitle tracks found in '], |
a6213a49 | 4860 | }, { |
4861 | 'url': 'https://www.youtube.com/user/TheYoungTurks/live', | |
4862 | 'info_dict': { | |
4863 | 'id': 'a48o2S1cPoo', | |
4864 | 'ext': 'mp4', | |
4865 | 'title': 'The Young Turks - Live Main Show', | |
4866 | 'uploader': 'The Young Turks', | |
4867 | 'uploader_id': 'TheYoungTurks', | |
4868 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks', | |
4869 | 'upload_date': '20150715', | |
4870 | 'license': 'Standard YouTube License', | |
4871 | 'description': 'md5:438179573adcdff3c97ebb1ee632b891', | |
4872 | 'categories': ['News & Politics'], | |
4873 | 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], | |
4874 | 'like_count': int, | |
a6213a49 | 4875 | }, |
4876 | 'params': { | |
4877 | 'skip_download': True, | |
4878 | }, | |
4879 | 'only_matching': True, | |
4880 | }, { | |
4881 | 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', | |
4882 | 'only_matching': True, | |
4883 | }, { | |
4884 | 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', | |
4885 | 'only_matching': True, | |
4886 | }, { | |
4887 | 'note': 'A channel that is not live. Should raise error', | |
4888 | 'url': 'https://www.youtube.com/user/numberphile/live', | |
4889 | 'only_matching': True, | |
4890 | }, { | |
4891 | 'url': 'https://www.youtube.com/feed/trending', | |
4892 | 'only_matching': True, | |
4893 | }, { | |
4894 | 'url': 'https://www.youtube.com/feed/library', | |
4895 | 'only_matching': True, | |
4896 | }, { | |
4897 | 'url': 'https://www.youtube.com/feed/history', | |
4898 | 'only_matching': True, | |
4899 | }, { | |
4900 | 'url': 'https://www.youtube.com/feed/subscriptions', | |
4901 | 'only_matching': True, | |
4902 | }, { | |
4903 | 'url': 'https://www.youtube.com/feed/watch_later', | |
4904 | 'only_matching': True, | |
4905 | }, { | |
4906 | 'note': 'Recommended - redirects to home page.', | |
4907 | 'url': 'https://www.youtube.com/feed/recommended', | |
4908 | 'only_matching': True, | |
4909 | }, { | |
4910 | 'note': 'inline playlist with not always working continuations', | |
4911 | 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C', | |
4912 | 'only_matching': True, | |
4913 | }, { | |
4914 | 'url': 'https://www.youtube.com/course', | |
4915 | 'only_matching': True, | |
4916 | }, { | |
4917 | 'url': 'https://www.youtube.com/zsecurity', | |
4918 | 'only_matching': True, | |
4919 | }, { | |
4920 | 'url': 'http://www.youtube.com/NASAgovVideo/videos', | |
4921 | 'only_matching': True, | |
4922 | }, { | |
4923 | 'url': 'https://www.youtube.com/TheYoungTurks/live', | |
4924 | 'only_matching': True, | |
4925 | }, { | |
4926 | 'url': 'https://www.youtube.com/hashtag/cctv9', | |
4927 | 'info_dict': { | |
4928 | 'id': 'cctv9', | |
4929 | 'title': '#cctv9', | |
976ae3ea | 4930 | 'tags': [], |
a6213a49 | 4931 | }, |
4932 | 'playlist_mincount': 350, | |
4933 | }, { | |
4934 | 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU', | |
4935 | 'only_matching': True, | |
4936 | }, { | |
4937 | 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist', | |
4938 | 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', | |
4939 | 'only_matching': True | |
4940 | }, { | |
4941 | 'note': '/browse/ should redirect to /channel/', | |
4942 | 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng', | |
4943 | 'only_matching': True | |
4944 | }, { | |
4945 | 'note': 'VLPL, should redirect to playlist?list=PL...', | |
4946 | 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', | |
4947 | 'info_dict': { | |
4948 | 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', | |
4949 | 'uploader': 'NoCopyrightSounds', | |
4950 | 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!', | |
4951 | 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg', | |
4952 | 'title': 'NCS Releases', | |
976ae3ea | 4953 | 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds', |
4954 | 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds', | |
4955 | 'modified_date': r're:\d{8}', | |
4956 | 'view_count': int, | |
4957 | 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg', | |
4958 | 'tags': [], | |
4959 | 'channel': 'NoCopyrightSounds', | |
a6213a49 | 4960 | }, |
4961 | 'playlist_mincount': 166, | |
976ae3ea | 4962 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], |
a6213a49 | 4963 | }, { |
4964 | 'note': 'Topic, should redirect to playlist?list=UU...', | |
4965 | 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw', | |
4966 | 'info_dict': { | |
4967 | 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw', | |
4968 | 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', | |
4969 | 'title': 'Uploads from Royalty Free Music - Topic', | |
4970 | 'uploader': 'Royalty Free Music - Topic', | |
976ae3ea | 4971 | 'tags': [], |
4972 | 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', | |
4973 | 'channel': 'Royalty Free Music - Topic', | |
4974 | 'view_count': int, | |
4975 | 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
4976 | 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
4977 | 'modified_date': r're:\d{8}', | |
4978 | 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
4979 | 'description': '', | |
a6213a49 | 4980 | }, |
4981 | 'expected_warnings': [ | |
a6213a49 | 4982 | 'The URL does not have a videos tab', |
976ae3ea | 4983 | r'[Uu]navailable videos (are|will be) hidden', |
a6213a49 | 4984 | ], |
4985 | 'playlist_mincount': 101, | |
4986 | }, { | |
4987 | 'note': 'Topic without a UU playlist', | |
4988 | 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg', | |
4989 | 'info_dict': { | |
4990 | 'id': 'UCtFRv9O2AHqOZjjynzrv-xg', | |
4991 | 'title': 'UCtFRv9O2AHqOZjjynzrv-xg', | |
976ae3ea | 4992 | 'tags': [], |
a6213a49 | 4993 | }, |
4994 | 'expected_warnings': [ | |
976ae3ea | 4995 | 'the playlist redirect gave error', |
a6213a49 | 4996 | ], |
4997 | 'playlist_mincount': 9, | |
4998 | }, { | |
4999 | 'note': 'Youtube music Album', | |
5000 | 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE', | |
5001 | 'info_dict': { | |
5002 | 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0', | |
5003 | 'title': 'Album - Royalty Free Music Library V2 (50 Songs)', | |
976ae3ea | 5004 | 'tags': [], |
5005 | 'view_count': int, | |
5006 | 'description': '', | |
5007 | 'availability': 'unlisted', | |
5008 | 'modified_date': r're:\d{8}', | |
a6213a49 | 5009 | }, |
5010 | 'playlist_count': 50, | |
5011 | }, { | |
5012 | 'note': 'unlisted single video playlist', | |
5013 | 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', | |
5014 | 'info_dict': { | |
5015 | 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q', | |
5016 | 'uploader': 'colethedj', | |
5017 | 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', | |
5018 | 'title': 'yt-dlp unlisted playlist test', | |
976ae3ea | 5019 | 'availability': 'unlisted', |
5020 | 'tags': [], | |
5021 | 'modified_date': '20211208', | |
5022 | 'channel': 'colethedj', | |
5023 | 'view_count': int, | |
5024 | 'description': '', | |
5025 | 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q', | |
5026 | 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q', | |
5027 | 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q', | |
a6213a49 | 5028 | }, |
5029 | 'playlist_count': 1, | |
5030 | }, { | |
5031 | 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData', | |
5032 | 'url': 'https://www.youtube.com/feed/recommended', | |
5033 | 'info_dict': { | |
5034 | 'id': 'recommended', | |
5035 | 'title': 'recommended', | |
6c73052c | 5036 | 'tags': [], |
a6213a49 | 5037 | }, |
5038 | 'playlist_mincount': 50, | |
5039 | 'params': { | |
5040 | 'skip_download': True, | |
5041 | 'extractor_args': {'youtubetab': {'skip': ['webpage']}} | |
5042 | }, | |
5043 | }, { | |
5044 | 'note': 'API Fallback: /videos tab, sorted by oldest first', | |
5045 | 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid', | |
5046 | 'info_dict': { | |
5047 | 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', | |
5048 | 'title': 'Cody\'sLab - Videos', | |
5049 | 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa', | |
5050 | 'uploader': 'Cody\'sLab', | |
5051 | 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', | |
976ae3ea | 5052 | 'channel': 'Cody\'sLab', |
5053 | 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', | |
5054 | 'tags': [], | |
5055 | 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw', | |
5056 | 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw', | |
6c73052c | 5057 | 'channel_follower_count': int |
a6213a49 | 5058 | }, |
5059 | 'playlist_mincount': 650, | |
5060 | 'params': { | |
5061 | 'skip_download': True, | |
5062 | 'extractor_args': {'youtubetab': {'skip': ['webpage']}} | |
5063 | }, | |
5064 | }, { | |
5065 | 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...', | |
5066 | 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw', | |
5067 | 'info_dict': { | |
5068 | 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw', | |
5069 | 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', | |
5070 | 'title': 'Uploads from Royalty Free Music - Topic', | |
5071 | 'uploader': 'Royalty Free Music - Topic', | |
976ae3ea | 5072 | 'modified_date': r're:\d{8}', |
5073 | 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', | |
5074 | 'description': '', | |
5075 | 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
5076 | 'tags': [], | |
5077 | 'channel': 'Royalty Free Music - Topic', | |
5078 | 'view_count': int, | |
5079 | 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
a6213a49 | 5080 | }, |
5081 | 'expected_warnings': [ | |
976ae3ea | 5082 | 'does not have a videos tab', |
5083 | r'[Uu]navailable videos (are|will be) hidden', | |
a6213a49 | 5084 | ], |
5085 | 'playlist_mincount': 101, | |
5086 | 'params': { | |
5087 | 'skip_download': True, | |
5088 | 'extractor_args': {'youtubetab': {'skip': ['webpage']}} | |
5089 | }, | |
7c219ea6 | 5090 | }, { |
5091 | 'note': 'non-standard redirect to regional channel', | |
5092 | 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ', | |
5093 | 'only_matching': True | |
a6213a49 | 5094 | }] |
5095 | ||
5096 | @classmethod | |
5097 | def suitable(cls, url): | |
5098 | return False if YoutubeIE.suitable(url) else super( | |
5099 | YoutubeTabIE, cls).suitable(url) | |
9297939e | 5100 | |
64f36541 | 5101 | _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$') |
fe03a6cd | 5102 | |
182bda88 | 5103 | @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data |
5104 | def _real_extract(self, url, smuggled_data): | |
cd7c66cf | 5105 | item_id = self._match_id(url) |
5106 | url = compat_urlparse.urlunparse( | |
5107 | compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com')) | |
a06916d9 | 5108 | compat_opts = self.get_param('compat_opts', []) |
cd7c66cf | 5109 | |
fe03a6cd | 5110 | def get_mobj(url): |
37e57a9f | 5111 | mobj = self._URL_RE.match(url).groupdict() |
07cce701 | 5112 | mobj.update((k, '') for k, v in mobj.items() if v is None) |
fe03a6cd | 5113 | return mobj |
5114 | ||
37e57a9f | 5115 | mobj, redirect_warning = get_mobj(url), None |
fe03a6cd | 5116 | # Youtube returns incomplete data if tabname is not lower case |
5117 | pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel'] | |
fe03a6cd | 5118 | if is_channel: |
5119 | if smuggled_data.get('is_music_url'): | |
37e57a9f | 5120 | if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist |
fe03a6cd | 5121 | item_id = item_id[2:] |
37e57a9f | 5122 | pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False |
5123 | elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist | |
ac56cf38 | 5124 | mdata = self._extract_tab_endpoint( |
37e57a9f | 5125 | f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music') |
5126 | murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'), | |
5127 | get_all=False, expected_type=compat_str) | |
ac56cf38 | 5128 | if not murl: |
37e57a9f | 5129 | raise ExtractorError('Failed to resolve album to playlist') |
ac56cf38 | 5130 | return self.url_result(murl, ie=YoutubeTabIE.ie_key()) |
37e57a9f | 5131 | elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/ |
5132 | pre = f'https://www.youtube.com/channel/{item_id}' | |
5133 | ||
64f36541 | 5134 | original_tab_name = tab |
fe03a6cd | 5135 | if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts: |
5136 | # Home URLs should redirect to /videos/ | |
37e57a9f | 5137 | redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. ' |
5138 | 'To download only the videos in the home page, add a "/featured" to the URL') | |
fe03a6cd | 5139 | tab = '/videos' |
5140 | ||
5141 | url = ''.join((pre, tab, post)) | |
5142 | mobj = get_mobj(url) | |
cd7c66cf | 5143 | |
5144 | # Handle both video/playlist URLs | |
201c1459 | 5145 | qs = parse_qs(url) |
37e57a9f | 5146 | video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')] |
cd7c66cf | 5147 | |
fe03a6cd | 5148 | if not video_id and mobj['not_channel'].startswith('watch'): |
cd7c66cf | 5149 | if not playlist_id: |
fe03a6cd | 5150 | # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable |
cd7c66cf | 5151 | raise ExtractorError('Unable to recognize tab page') |
fe03a6cd | 5152 | # Common mistake: https://www.youtube.com/watch?list=playlist_id |
37e57a9f | 5153 | self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}') |
5154 | url = f'https://www.youtube.com/playlist?list={playlist_id}' | |
18db7548 | 5155 | mobj = get_mobj(url) |
cd7c66cf | 5156 | |
5157 | if video_id and playlist_id: | |
a06916d9 | 5158 | if self.get_param('noplaylist'): |
37e57a9f | 5159 | self.to_screen(f'Downloading just video {video_id} because of --no-playlist') |
5160 | return self.url_result(f'https://www.youtube.com/watch?v={video_id}', | |
5161 | ie=YoutubeIE.ie_key(), video_id=video_id) | |
5162 | self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}') | |
cd7c66cf | 5163 | |
ac56cf38 | 5164 | data, ytcfg = self._extract_data(url, item_id) |
14fdfea9 | 5165 | |
7c219ea6 | 5166 | # YouTube may provide a non-standard redirect to the regional channel |
5167 | # See: https://github.com/yt-dlp/yt-dlp/issues/2694 | |
5168 | redirect_url = traverse_obj( | |
5169 | data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False) | |
5170 | if redirect_url and 'no-youtube-channel-redirect' not in compat_opts: | |
5171 | redirect_url = ''.join(( | |
5172 | urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post'])) | |
5173 | self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}') | |
5174 | return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key()) | |
5175 | ||
37e57a9f | 5176 | tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list) |
18db7548 | 5177 | if tabs: |
5178 | selected_tab = self._extract_selected_tab(tabs) | |
64f36541 | 5179 | selected_tab_name = selected_tab.get('title', '').lower() |
5180 | if selected_tab_name == 'home': | |
5181 | selected_tab_name = 'featured' | |
5182 | requested_tab_name = mobj['tab'][1:] | |
09f1580e | 5183 | if 'no-youtube-channel-redirect' not in compat_opts: |
64f36541 | 5184 | if requested_tab_name == 'live': |
09f1580e | 5185 | # Live tab should have redirected to the video |
5186 | raise ExtractorError('The channel is not currently live', expected=True) | |
64f36541 | 5187 | if requested_tab_name not in ('', selected_tab_name): |
5188 | redirect_warning = f'The channel does not have a {requested_tab_name} tab' | |
5189 | if not original_tab_name: | |
5190 | if item_id[:2] == 'UC': | |
5191 | # Topic channels don't have /videos. Use the equivalent playlist instead | |
5192 | pl_id = f'UU{item_id[2:]}' | |
5193 | pl_url = f'https://www.youtube.com/playlist?list={pl_id}' | |
5194 | try: | |
5195 | data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True) | |
5196 | except ExtractorError: | |
5197 | redirect_warning += ' and the playlist redirect gave error' | |
5198 | else: | |
5199 | item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name | |
5200 | redirect_warning += f'. Redirecting to playlist {pl_id} instead' | |
5201 | if selected_tab_name and selected_tab_name != requested_tab_name: | |
5202 | redirect_warning += f'. {selected_tab_name} tab is being downloaded instead' | |
5203 | else: | |
5204 | raise ExtractorError(redirect_warning, expected=True) | |
18db7548 | 5205 | |
37e57a9f | 5206 | if redirect_warning: |
64f36541 | 5207 | self.to_screen(redirect_warning) |
37e57a9f | 5208 | self.write_debug(f'Final URL: {url}') |
18db7548 | 5209 | |
358de58c | 5210 | # YouTube sometimes provides a button to reload playlist with unavailable videos. |
53ed7066 | 5211 | if 'no-youtube-unavailable-videos' not in compat_opts: |
ac56cf38 | 5212 | data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data |
c0ac49bc | 5213 | self._extract_and_report_alerts(data, only_once=True) |
37e57a9f | 5214 | tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list) |
8bdd16b4 | 5215 | if tabs: |
ac56cf38 | 5216 | return self._extract_from_tabs(item_id, ytcfg, data, tabs) |
cd7c66cf | 5217 | |
37e57a9f | 5218 | playlist = traverse_obj( |
5219 | data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict) | |
8bdd16b4 | 5220 | if playlist: |
ac56cf38 | 5221 | return self._extract_from_playlist(item_id, url, data, playlist, ytcfg) |
cd7c66cf | 5222 | |
37e57a9f | 5223 | video_id = traverse_obj( |
5224 | data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id | |
8bdd16b4 | 5225 | if video_id: |
09f1580e | 5226 | if mobj['tab'] != '/live': # live tab is expected to redirect to video |
37e57a9f | 5227 | self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}') |
5228 | return self.url_result(f'https://www.youtube.com/watch?v={video_id}', | |
5229 | ie=YoutubeIE.ie_key(), video_id=video_id) | |
cd7c66cf | 5230 | |
8bdd16b4 | 5231 | raise ExtractorError('Unable to recognize tab page') |
c5e8d7af | 5232 | |
c5e8d7af | 5233 | |
8bdd16b4 | 5234 | class YoutubePlaylistIE(InfoExtractor): |
96565c7e | 5235 | IE_DESC = 'YouTube playlists' |
8bdd16b4 | 5236 | _VALID_URL = r'''(?x)(?: |
5237 | (?:https?://)? | |
5238 | (?:\w+\.)? | |
5239 | (?: | |
5240 | (?: | |
5241 | youtube(?:kids)?\.com| | |
d9190e44 | 5242 | %(invidious)s |
8bdd16b4 | 5243 | ) |
5244 | /.*?\?.*?\blist= | |
5245 | )? | |
5246 | (?P<id>%(playlist_id)s) | |
d9190e44 RH |
5247 | )''' % { |
5248 | 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE, | |
5249 | 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), | |
5250 | } | |
8bdd16b4 | 5251 | IE_NAME = 'youtube:playlist' |
cdc628a4 | 5252 | _TESTS = [{ |
8bdd16b4 | 5253 | 'note': 'issue #673', |
5254 | 'url': 'PLBB231211A4F62143', | |
cdc628a4 | 5255 | 'info_dict': { |
8bdd16b4 | 5256 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', |
5257 | 'id': 'PLBB231211A4F62143', | |
976ae3ea | 5258 | 'uploader': 'Wickman', |
8bdd16b4 | 5259 | 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q', |
11f9be09 | 5260 | 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2', |
976ae3ea | 5261 | 'view_count': int, |
5262 | 'uploader_url': 'https://www.youtube.com/user/Wickydoo', | |
5263 | 'modified_date': r're:\d{8}', | |
5264 | 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q', | |
5265 | 'channel': 'Wickman', | |
5266 | 'tags': [], | |
5267 | 'channel_url': 'https://www.youtube.com/user/Wickydoo', | |
8bdd16b4 | 5268 | }, |
5269 | 'playlist_mincount': 29, | |
5270 | }, { | |
5271 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
5272 | 'info_dict': { | |
5273 | 'title': 'YDL_safe_search', | |
5274 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
5275 | }, | |
5276 | 'playlist_count': 2, | |
5277 | 'skip': 'This playlist is private', | |
9558dcec | 5278 | }, { |
8bdd16b4 | 5279 | 'note': 'embedded', |
5280 | 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
5281 | 'playlist_count': 4, | |
9558dcec | 5282 | 'info_dict': { |
8bdd16b4 | 5283 | 'title': 'JODA15', |
5284 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
5285 | 'uploader': 'milan', | |
5286 | 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw', | |
976ae3ea | 5287 | 'description': '', |
5288 | 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw', | |
5289 | 'tags': [], | |
5290 | 'modified_date': '20140919', | |
5291 | 'view_count': int, | |
5292 | 'channel': 'milan', | |
5293 | 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw', | |
5294 | 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw', | |
5295 | }, | |
5296 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], | |
cdc628a4 | 5297 | }, { |
8bdd16b4 | 5298 | 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', |
11f9be09 | 5299 | 'playlist_mincount': 654, |
8bdd16b4 | 5300 | 'info_dict': { |
5301 | 'title': '2018 Chinese New Singles (11/6 updated)', | |
5302 | 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
5303 | 'uploader': 'LBK', | |
5304 | 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA', | |
11f9be09 | 5305 | 'description': 'md5:da521864744d60a198e3a88af4db0d9d', |
976ae3ea | 5306 | 'channel': 'LBK', |
5307 | 'view_count': int, | |
5308 | 'channel_url': 'https://www.youtube.com/c/愛低音的國王', | |
5309 | 'tags': [], | |
5310 | 'uploader_url': 'https://www.youtube.com/c/愛低音的國王', | |
5311 | 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA', | |
5312 | 'modified_date': r're:\d{8}', | |
5313 | }, | |
5314 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], | |
daa0df9e | 5315 | }, { |
29f7c58a | 5316 | 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', |
5317 | 'only_matching': True, | |
5318 | }, { | |
5319 | # music album playlist | |
5320 | 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', | |
5321 | 'only_matching': True, | |
5322 | }] | |
5323 | ||
5324 | @classmethod | |
5325 | def suitable(cls, url): | |
201c1459 | 5326 | if YoutubeTabIE.suitable(url): |
5327 | return False | |
49a57e70 | 5328 | from ..utils import parse_qs |
201c1459 | 5329 | qs = parse_qs(url) |
5330 | if qs.get('v', [None])[0]: | |
5331 | return False | |
5332 | return super(YoutubePlaylistIE, cls).suitable(url) | |
29f7c58a | 5333 | |
5334 | def _real_extract(self, url): | |
5335 | playlist_id = self._match_id(url) | |
46953e7e | 5336 | is_music_url = YoutubeBaseInfoExtractor.is_music_url(url) |
9297939e | 5337 | url = update_url_query( |
5338 | 'https://www.youtube.com/playlist', | |
5339 | parse_qs(url) or {'list': playlist_id}) | |
5340 | if is_music_url: | |
5341 | url = smuggle_url(url, {'is_music_url': True}) | |
5342 | return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
29f7c58a | 5343 | |
5344 | ||
5345 | class YoutubeYtBeIE(InfoExtractor): | |
c76eb41b | 5346 | IE_DESC = 'youtu.be' |
29f7c58a | 5347 | _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} |
5348 | _TESTS = [{ | |
8bdd16b4 | 5349 | 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', |
5350 | 'info_dict': { | |
5351 | 'id': 'yeWKywCrFtk', | |
5352 | 'ext': 'mp4', | |
5353 | 'title': 'Small Scale Baler and Braiding Rugs', | |
5354 | 'uploader': 'Backus-Page House Museum', | |
5355 | 'uploader_id': 'backuspagemuseum', | |
5356 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum', | |
5357 | 'upload_date': '20161008', | |
5358 | 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', | |
5359 | 'categories': ['Nonprofits & Activism'], | |
5360 | 'tags': list, | |
5361 | 'like_count': int, | |
976ae3ea | 5362 | 'age_limit': 0, |
5363 | 'playable_in_embed': True, | |
5364 | 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp', | |
5365 | 'channel': 'Backus-Page House Museum', | |
5366 | 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw', | |
5367 | 'live_status': 'not_live', | |
5368 | 'view_count': int, | |
5369 | 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw', | |
5370 | 'availability': 'public', | |
5371 | 'duration': 59, | |
8bdd16b4 | 5372 | }, |
5373 | 'params': { | |
5374 | 'noplaylist': True, | |
5375 | 'skip_download': True, | |
5376 | }, | |
39e7107d | 5377 | }, { |
8bdd16b4 | 5378 | 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', |
39e7107d | 5379 | 'only_matching': True, |
cdc628a4 PH |
5380 | }] |
5381 | ||
8bdd16b4 | 5382 | def _real_extract(self, url): |
5ad28e7f | 5383 | mobj = self._match_valid_url(url) |
29f7c58a | 5384 | video_id = mobj.group('id') |
5385 | playlist_id = mobj.group('playlist_id') | |
8bdd16b4 | 5386 | return self.url_result( |
29f7c58a | 5387 | update_url_query('https://www.youtube.com/watch', { |
5388 | 'v': video_id, | |
5389 | 'list': playlist_id, | |
5390 | 'feature': 'youtu.be', | |
5391 | }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
8bdd16b4 | 5392 | |
5393 | ||
b6ce9bb0 | 5394 | class YoutubeLivestreamEmbedIE(InfoExtractor): |
5395 | IE_DESC = 'YouTube livestream embeds' | |
5396 | _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)' | |
5397 | _TESTS = [{ | |
5398 | 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA', | |
5399 | 'only_matching': True, | |
5400 | }] | |
5401 | ||
5402 | def _real_extract(self, url): | |
5403 | channel_id = self._match_id(url) | |
5404 | return self.url_result( | |
5405 | f'https://www.youtube.com/channel/{channel_id}/live', | |
5406 | ie=YoutubeTabIE.ie_key(), video_id=channel_id) | |
5407 | ||
5408 | ||
8bdd16b4 | 5409 | class YoutubeYtUserIE(InfoExtractor): |
96565c7e | 5410 | IE_DESC = 'YouTube user videos; "ytuser:" prefix' |
b6ce9bb0 | 5411 | IE_NAME = 'youtube:user' |
8bdd16b4 | 5412 | _VALID_URL = r'ytuser:(?P<id>.+)' |
5413 | _TESTS = [{ | |
5414 | 'url': 'ytuser:phihag', | |
5415 | 'only_matching': True, | |
5416 | }] | |
5417 | ||
5418 | def _real_extract(self, url): | |
5419 | user_id = self._match_id(url) | |
5420 | return self.url_result( | |
c586f9e8 | 5421 | 'https://www.youtube.com/user/%s/videos' % user_id, |
8bdd16b4 | 5422 | ie=YoutubeTabIE.ie_key(), video_id=user_id) |
9558dcec | 5423 | |
b05654f0 | 5424 | |
3d3dddc9 | 5425 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): |
70d5c17b | 5426 | IE_NAME = 'youtube:favorites' |
96565c7e | 5427 | IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)' |
70d5c17b | 5428 | _VALID_URL = r':ytfav(?:ou?rite)?s?' |
5429 | _LOGIN_REQUIRED = True | |
5430 | _TESTS = [{ | |
5431 | 'url': ':ytfav', | |
5432 | 'only_matching': True, | |
5433 | }, { | |
5434 | 'url': ':ytfavorites', | |
5435 | 'only_matching': True, | |
5436 | }] | |
5437 | ||
5438 | def _real_extract(self, url): | |
5439 | return self.url_result( | |
5440 | 'https://www.youtube.com/playlist?list=LL', | |
5441 | ie=YoutubeTabIE.ie_key()) | |
5442 | ||
5443 | ||
a6213a49 | 5444 | class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor): |
5445 | IE_DESC = 'YouTube search' | |
78caa52a | 5446 | IE_NAME = 'youtube:search' |
b05654f0 | 5447 | _SEARCH_KEY = 'ytsearch' |
a61fd4cf | 5448 | _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only |
84bbc545 | 5449 | _TESTS = [{ |
5450 | 'url': 'ytsearch5:youtube-dl test video', | |
5451 | 'playlist_count': 5, | |
5452 | 'info_dict': { | |
5453 | 'id': 'youtube-dl test video', | |
5454 | 'title': 'youtube-dl test video', | |
5455 | } | |
5456 | }] | |
b05654f0 | 5457 | |
a61fd4cf | 5458 | |
5f7cb91a | 5459 | class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor): |
cb7fb546 | 5460 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' |
a3dd9248 | 5461 | _SEARCH_KEY = 'ytsearchdate' |
a6213a49 | 5462 | IE_DESC = 'YouTube search, newest videos first' |
a61fd4cf | 5463 | _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date |
84bbc545 | 5464 | _TESTS = [{ |
5465 | 'url': 'ytsearchdate5:youtube-dl test video', | |
5466 | 'playlist_count': 5, | |
5467 | 'info_dict': { | |
5468 | 'id': 'youtube-dl test video', | |
5469 | 'title': 'youtube-dl test video', | |
5470 | } | |
5471 | }] | |
75dff0ee | 5472 | |
c9ae7b95 | 5473 | |
a6213a49 | 5474 | class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor): |
96565c7e | 5475 | IE_DESC = 'YouTube search URLs with sorting and filter support' |
386e1dd9 | 5476 | IE_NAME = YoutubeSearchIE.IE_NAME + '_url' |
182bda88 | 5477 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)' |
3462ffa8 | 5478 | _TESTS = [{ |
5479 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
5480 | 'playlist_mincount': 5, | |
5481 | 'info_dict': { | |
11f9be09 | 5482 | 'id': 'youtube-dl test video', |
3462ffa8 | 5483 | 'title': 'youtube-dl test video', |
5484 | } | |
a61fd4cf | 5485 | }, { |
5486 | 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D', | |
5487 | 'playlist_mincount': 5, | |
5488 | 'info_dict': { | |
5489 | 'id': 'python', | |
5490 | 'title': 'python', | |
5491 | } | |
5492 | ||
3462ffa8 | 5493 | }, { |
5494 | 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB', | |
5495 | 'only_matching': True, | |
5496 | }] | |
5497 | ||
5498 | def _real_extract(self, url): | |
4dfbf869 | 5499 | qs = parse_qs(url) |
386e1dd9 | 5500 | query = (qs.get('search_query') or qs.get('q'))[0] |
a6213a49 | 5501 | return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query) |
3462ffa8 | 5502 | |
5503 | ||
16aa9ea4 | 5504 | class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor): |
455a15e2 | 5505 | IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)' |
16aa9ea4 | 5506 | IE_NAME = 'youtube:music:search_url' |
5507 | _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)' | |
5508 | _TESTS = [{ | |
5509 | 'url': 'https://music.youtube.com/search?q=royalty+free+music', | |
5510 | 'playlist_count': 16, | |
5511 | 'info_dict': { | |
5512 | 'id': 'royalty free music', | |
5513 | 'title': 'royalty free music', | |
5514 | } | |
5515 | }, { | |
5516 | 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D', | |
5517 | 'playlist_mincount': 30, | |
5518 | 'info_dict': { | |
5519 | 'id': 'royalty free music - songs', | |
5520 | 'title': 'royalty free music - songs', | |
5521 | }, | |
5522 | 'params': {'extract_flat': 'in_playlist'} | |
5523 | }, { | |
5524 | 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists', | |
5525 | 'playlist_mincount': 30, | |
5526 | 'info_dict': { | |
5527 | 'id': 'royalty free music - community playlists', | |
5528 | 'title': 'royalty free music - community playlists', | |
5529 | }, | |
5530 | 'params': {'extract_flat': 'in_playlist'} | |
5531 | }] | |
5532 | ||
5533 | _SECTIONS = { | |
5534 | 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==', | |
5535 | 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==', | |
5536 | 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF', | |
5537 | 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==', | |
5538 | 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==', | |
5539 | 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==', | |
5540 | } | |
5541 | ||
5542 | def _real_extract(self, url): | |
5543 | qs = parse_qs(url) | |
5544 | query = (qs.get('search_query') or qs.get('q'))[0] | |
5545 | params = qs.get('sp', (None,))[0] | |
5546 | if params: | |
5547 | section = next((k for k, v in self._SECTIONS.items() if v == params), params) | |
5548 | else: | |
5549 | section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower() | |
5550 | params = self._SECTIONS.get(section) | |
5551 | if not params: | |
5552 | section = None | |
5553 | title = join_nonempty(query, section, delim=' - ') | |
af5c1c55 | 5554 | return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title) |
16aa9ea4 | 5555 | |
5556 | ||
182bda88 | 5557 | class YoutubeFeedsInfoExtractor(InfoExtractor): |
d7ae0639 | 5558 | """ |
25f14e9f | 5559 | Base class for feed extractors |
3d3dddc9 | 5560 | Subclasses must define the _FEED_NAME property. |
d7ae0639 | 5561 | """ |
b2e8bc1b | 5562 | _LOGIN_REQUIRED = True |
ef2f3c7f | 5563 | _TESTS = [] |
d7ae0639 JMF |
5564 | |
5565 | @property | |
5566 | def IE_NAME(self): | |
78caa52a | 5567 | return 'youtube:%s' % self._FEED_NAME |
04cc9617 | 5568 | |
3853309f | 5569 | def _real_extract(self, url): |
3d3dddc9 | 5570 | return self.url_result( |
182bda88 | 5571 | f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key()) |
25f14e9f S |
5572 | |
5573 | ||
ef2f3c7f | 5574 | class YoutubeWatchLaterIE(InfoExtractor): |
5575 | IE_NAME = 'youtube:watchlater' | |
96565c7e | 5576 | IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)' |
3d3dddc9 | 5577 | _VALID_URL = r':ytwatchlater' |
bc7a9cd8 | 5578 | _TESTS = [{ |
8bdd16b4 | 5579 | 'url': ':ytwatchlater', |
bc7a9cd8 S |
5580 | 'only_matching': True, |
5581 | }] | |
25f14e9f S |
5582 | |
5583 | def _real_extract(self, url): | |
ef2f3c7f | 5584 | return self.url_result( |
5585 | 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key()) | |
3462ffa8 | 5586 | |
5587 | ||
25f14e9f | 5588 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): |
96565c7e | 5589 | IE_DESC = 'YouTube recommended videos; ":ytrec" keyword' |
3d3dddc9 | 5590 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?' |
25f14e9f | 5591 | _FEED_NAME = 'recommended' |
45db527f | 5592 | _LOGIN_REQUIRED = False |
3d3dddc9 | 5593 | _TESTS = [{ |
5594 | 'url': ':ytrec', | |
5595 | 'only_matching': True, | |
5596 | }, { | |
5597 | 'url': ':ytrecommended', | |
5598 | 'only_matching': True, | |
5599 | }, { | |
5600 | 'url': 'https://youtube.com', | |
5601 | 'only_matching': True, | |
5602 | }] | |
1ed5b5c9 | 5603 | |
1ed5b5c9 | 5604 | |
25f14e9f | 5605 | class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): |
96565c7e | 5606 | IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)' |
3d3dddc9 | 5607 | _VALID_URL = r':ytsub(?:scription)?s?' |
25f14e9f | 5608 | _FEED_NAME = 'subscriptions' |
3d3dddc9 | 5609 | _TESTS = [{ |
5610 | 'url': ':ytsubs', | |
5611 | 'only_matching': True, | |
5612 | }, { | |
5613 | 'url': ':ytsubscriptions', | |
5614 | 'only_matching': True, | |
5615 | }] | |
1ed5b5c9 | 5616 | |
1ed5b5c9 | 5617 | |
25f14e9f | 5618 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): |
96565c7e | 5619 | IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)' |
a5c56234 | 5620 | _VALID_URL = r':ythis(?:tory)?' |
25f14e9f | 5621 | _FEED_NAME = 'history' |
3d3dddc9 | 5622 | _TESTS = [{ |
5623 | 'url': ':ythistory', | |
5624 | 'only_matching': True, | |
5625 | }] | |
1ed5b5c9 JMF |
5626 | |
5627 | ||
15870e90 PH |
5628 | class YoutubeTruncatedURLIE(InfoExtractor): |
5629 | IE_NAME = 'youtube:truncated_url' | |
5630 | IE_DESC = False # Do not list | |
975d35db | 5631 | _VALID_URL = r'''(?x) |
b95aab84 PH |
5632 | (?:https?://)? |
5633 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
5634 | (?:watch\?(?: | |
c4808c60 | 5635 | feature=[a-z_]+| |
b95aab84 PH |
5636 | annotation_id=annotation_[^&]+| |
5637 | x-yt-cl=[0-9]+| | |
c1708b89 | 5638 | hl=[^&]*| |
287be8c6 | 5639 | t=[0-9]+ |
b95aab84 PH |
5640 | )? |
5641 | | | |
5642 | attribution_link\?a=[^&]+ | |
5643 | ) | |
5644 | $ | |
975d35db | 5645 | ''' |
15870e90 | 5646 | |
c4808c60 | 5647 | _TESTS = [{ |
2d3d2997 | 5648 | 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041', |
c4808c60 | 5649 | 'only_matching': True, |
dc2fc736 | 5650 | }, { |
2d3d2997 | 5651 | 'url': 'https://www.youtube.com/watch?', |
dc2fc736 | 5652 | 'only_matching': True, |
b95aab84 PH |
5653 | }, { |
5654 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
5655 | 'only_matching': True, | |
5656 | }, { | |
5657 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
5658 | 'only_matching': True, | |
c1708b89 PH |
5659 | }, { |
5660 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
5661 | 'only_matching': True, | |
287be8c6 PH |
5662 | }, { |
5663 | 'url': 'https://www.youtube.com/watch?t=2372', | |
5664 | 'only_matching': True, | |
c4808c60 PH |
5665 | }] |
5666 | ||
15870e90 PH |
5667 | def _real_extract(self, url): |
5668 | raise ExtractorError( | |
78caa52a PH |
5669 | 'Did you forget to quote the URL? Remember that & is a meta ' |
5670 | 'character in most shells, so you want to put the URL in quotes, ' | |
3867038a | 5671 | 'like youtube-dl ' |
2d3d2997 | 5672 | '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' |
3867038a | 5673 | ' or simply youtube-dl BaW_jenozKc .', |
15870e90 | 5674 | expected=True) |
772fd5cc PH |
5675 | |
5676 | ||
3cd786db | 5677 | class YoutubeClipIE(InfoExtractor): |
5678 | IE_NAME = 'youtube:clip' | |
5679 | IE_DESC = False # Do not list | |
5680 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/' | |
5681 | ||
5682 | def _real_extract(self, url): | |
5683 | self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead') | |
5684 | return self.url_result(url, 'Generic') | |
5685 | ||
5686 | ||
772fd5cc PH |
5687 | class YoutubeTruncatedIDIE(InfoExtractor): |
5688 | IE_NAME = 'youtube:truncated_id' | |
5689 | IE_DESC = False # Do not list | |
b95aab84 | 5690 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' |
772fd5cc PH |
5691 | |
5692 | _TESTS = [{ | |
5693 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
5694 | 'only_matching': True, | |
5695 | }] | |
5696 | ||
5697 | def _real_extract(self, url): | |
5698 | video_id = self._match_id(url) | |
5699 | raise ExtractorError( | |
5700 | 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), | |
5701 | expected=True) |