]>
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, |
ff91cf74 | 42 | get_first, |
dd27fd17 | 43 | int_or_none, |
641ad5d8 | 44 | is_html, |
34921b43 | 45 | join_nonempty, |
48416bc4 | 46 | js_to_json, |
94278f72 | 47 | mimetype2ext, |
9c0d7f49 | 48 | network_exceptions, |
a6213a49 | 49 | NO_DEFAULT, |
11f9be09 | 50 | orderedSet, |
6310acf5 | 51 | parse_codecs, |
49bd8c66 | 52 | parse_count, |
7c80519c | 53 | parse_duration, |
7ea65411 | 54 | parse_iso8601, |
4dfbf869 | 55 | parse_qs, |
dca3ff4a | 56 | qualities, |
c0ac49bc | 57 | remove_end, |
3995d37d | 58 | remove_start, |
cf7e015f | 59 | smuggle_url, |
dbdaaa23 | 60 | str_or_none, |
c93d53f5 | 61 | str_to_int, |
f3aa3c3f | 62 | strftime_or_none, |
7c365c21 | 63 | traverse_obj, |
556dbe7f | 64 | try_get, |
c5e8d7af PH |
65 | unescapeHTML, |
66 | unified_strdate, | |
f0d785d3 | 67 | unified_timestamp, |
cf7e015f | 68 | unsmuggle_url, |
8bdd16b4 | 69 | update_url_query, |
21c340b8 | 70 | url_or_none, |
fe93e2c4 | 71 | urljoin, |
7c365c21 | 72 | variadic, |
c5e8d7af PH |
73 | ) |
74 | ||
5f6a1245 | 75 | |
000c15a4 | 76 | # any clients starting with _ cannot be explicity requested by the user |
77 | INNERTUBE_CLIENTS = { | |
78 | 'web': { | |
79 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
80 | 'INNERTUBE_CONTEXT': { | |
81 | 'client': { | |
82 | 'clientName': 'WEB', | |
18c7683d | 83 | 'clientVersion': '2.20211221.00.00', |
000c15a4 | 84 | } |
85 | }, | |
86 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 1 | |
87 | }, | |
88 | 'web_embedded': { | |
89 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
90 | 'INNERTUBE_CONTEXT': { | |
91 | 'client': { | |
92 | 'clientName': 'WEB_EMBEDDED_PLAYER', | |
18c7683d | 93 | 'clientVersion': '1.20211215.00.01', |
000c15a4 | 94 | }, |
95 | }, | |
96 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 56 | |
97 | }, | |
98 | 'web_music': { | |
99 | 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30', | |
100 | 'INNERTUBE_HOST': 'music.youtube.com', | |
101 | 'INNERTUBE_CONTEXT': { | |
102 | 'client': { | |
103 | 'clientName': 'WEB_REMIX', | |
18c7683d | 104 | 'clientVersion': '1.20211213.00.00', |
000c15a4 | 105 | } |
106 | }, | |
107 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 67, | |
108 | }, | |
e7e94f2a | 109 | 'web_creator': { |
18c7683d | 110 | 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo', |
e7e94f2a D |
111 | 'INNERTUBE_CONTEXT': { |
112 | 'client': { | |
113 | 'clientName': 'WEB_CREATOR', | |
18c7683d | 114 | 'clientVersion': '1.20211220.02.00', |
e7e94f2a D |
115 | } |
116 | }, | |
117 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 62, | |
118 | }, | |
000c15a4 | 119 | 'android': { |
18c7683d | 120 | 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w', |
000c15a4 | 121 | 'INNERTUBE_CONTEXT': { |
122 | 'client': { | |
123 | 'clientName': 'ANDROID', | |
18c7683d | 124 | 'clientVersion': '16.49', |
000c15a4 | 125 | } |
126 | }, | |
127 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 3, | |
b6de707d | 128 | 'REQUIRE_JS_PLAYER': False |
000c15a4 | 129 | }, |
130 | 'android_embedded': { | |
18c7683d | 131 | 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw', |
000c15a4 | 132 | 'INNERTUBE_CONTEXT': { |
133 | 'client': { | |
134 | 'clientName': 'ANDROID_EMBEDDED_PLAYER', | |
18c7683d | 135 | 'clientVersion': '16.49', |
000c15a4 | 136 | }, |
137 | }, | |
b6de707d | 138 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 55, |
139 | 'REQUIRE_JS_PLAYER': False | |
000c15a4 | 140 | }, |
141 | 'android_music': { | |
18c7683d | 142 | 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI', |
000c15a4 | 143 | 'INNERTUBE_CONTEXT': { |
144 | 'client': { | |
145 | 'clientName': 'ANDROID_MUSIC', | |
18c7683d | 146 | 'clientVersion': '4.57', |
000c15a4 | 147 | } |
148 | }, | |
149 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 21, | |
b6de707d | 150 | 'REQUIRE_JS_PLAYER': False |
000c15a4 | 151 | }, |
e7e94f2a | 152 | 'android_creator': { |
18c7683d | 153 | 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8', |
e7e94f2a D |
154 | 'INNERTUBE_CONTEXT': { |
155 | 'client': { | |
156 | 'clientName': 'ANDROID_CREATOR', | |
18c7683d | 157 | 'clientVersion': '21.47', |
e7e94f2a D |
158 | }, |
159 | }, | |
b6de707d | 160 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 14, |
161 | 'REQUIRE_JS_PLAYER': False | |
e7e94f2a | 162 | }, |
18c7683d | 163 | # iOS clients have HLS live streams. Setting device model to get 60fps formats. |
164 | # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558 | |
000c15a4 | 165 | 'ios': { |
18c7683d | 166 | 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc', |
000c15a4 | 167 | 'INNERTUBE_CONTEXT': { |
168 | 'client': { | |
169 | 'clientName': 'IOS', | |
18c7683d | 170 | 'clientVersion': '16.46', |
171 | 'deviceModel': 'iPhone14,3', | |
000c15a4 | 172 | } |
173 | }, | |
b6de707d | 174 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 5, |
175 | 'REQUIRE_JS_PLAYER': False | |
000c15a4 | 176 | }, |
177 | 'ios_embedded': { | |
000c15a4 | 178 | 'INNERTUBE_CONTEXT': { |
179 | 'client': { | |
180 | 'clientName': 'IOS_MESSAGES_EXTENSION', | |
18c7683d | 181 | 'clientVersion': '16.46', |
182 | 'deviceModel': 'iPhone14,3', | |
000c15a4 | 183 | }, |
184 | }, | |
b6de707d | 185 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 66, |
186 | 'REQUIRE_JS_PLAYER': False | |
000c15a4 | 187 | }, |
188 | 'ios_music': { | |
18c7683d | 189 | 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s', |
000c15a4 | 190 | 'INNERTUBE_CONTEXT': { |
191 | 'client': { | |
192 | 'clientName': 'IOS_MUSIC', | |
18c7683d | 193 | 'clientVersion': '4.57', |
000c15a4 | 194 | }, |
195 | }, | |
b6de707d | 196 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 26, |
197 | 'REQUIRE_JS_PLAYER': False | |
000c15a4 | 198 | }, |
e7e94f2a D |
199 | 'ios_creator': { |
200 | 'INNERTUBE_CONTEXT': { | |
201 | 'client': { | |
202 | 'clientName': 'IOS_CREATOR', | |
18c7683d | 203 | 'clientVersion': '21.47', |
e7e94f2a D |
204 | }, |
205 | }, | |
b6de707d | 206 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 15, |
207 | 'REQUIRE_JS_PLAYER': False | |
e7e94f2a | 208 | }, |
3619f78d | 209 | # mweb has 'ultralow' formats |
210 | # See: https://github.com/yt-dlp/yt-dlp/pull/557 | |
000c15a4 | 211 | 'mweb': { |
18c7683d | 212 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', |
000c15a4 | 213 | 'INNERTUBE_CONTEXT': { |
214 | 'client': { | |
215 | 'clientName': 'MWEB', | |
18c7683d | 216 | 'clientVersion': '2.20211221.01.00', |
000c15a4 | 217 | } |
218 | }, | |
219 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 2 | |
e7870111 D |
220 | }, |
221 | # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option) | |
222 | # See: https://github.com/zerodytrash/YouTube-Internal-Clients | |
223 | 'tv_embedded': { | |
224 | 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8', | |
225 | 'INNERTUBE_CONTEXT': { | |
226 | 'client': { | |
227 | 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER', | |
228 | 'clientVersion': '2.0', | |
229 | }, | |
230 | }, | |
231 | 'INNERTUBE_CONTEXT_CLIENT_NAME': 85 | |
232 | }, | |
000c15a4 | 233 | } |
234 | ||
235 | ||
e7870111 D |
236 | def _split_innertube_client(client_name): |
237 | variant, *base = client_name.rsplit('.', 1) | |
238 | if base: | |
239 | return variant, base[0], variant | |
240 | base, *variant = client_name.split('_', 1) | |
241 | return client_name, base, variant[0] if variant else None | |
242 | ||
243 | ||
000c15a4 | 244 | def build_innertube_clients(): |
2e4cacd0 | 245 | THIRD_PARTY = { |
e7870111 | 246 | 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL |
65c2fde2 | 247 | } |
e7870111 | 248 | BASE_CLIENTS = ('android', 'web', 'tv', 'ios', 'mweb') |
2e4cacd0 | 249 | priority = qualities(BASE_CLIENTS[::-1]) |
000c15a4 | 250 | |
251 | for client, ytcfg in tuple(INNERTUBE_CLIENTS.items()): | |
eca330cb | 252 | ytcfg.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8') |
000c15a4 | 253 | ytcfg.setdefault('INNERTUBE_HOST', 'www.youtube.com') |
b6de707d | 254 | ytcfg.setdefault('REQUIRE_JS_PLAYER', True) |
000c15a4 | 255 | ytcfg['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en') |
000c15a4 | 256 | |
e7870111 | 257 | _, base_client, variant = _split_innertube_client(client) |
2e4cacd0 | 258 | ytcfg['priority'] = 10 * priority(base_client) |
259 | ||
e48b3875 | 260 | if not variant: |
e7870111 D |
261 | INNERTUBE_CLIENTS[f'{client}_embedscreen'] = embedscreen = copy.deepcopy(ytcfg) |
262 | embedscreen['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED' | |
263 | embedscreen['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY | |
264 | embedscreen['priority'] -= 3 | |
265 | elif variant == 'embedded': | |
e48b3875 | 266 | ytcfg['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY |
000c15a4 | 267 | ytcfg['priority'] -= 2 |
e48b3875 | 268 | else: |
000c15a4 | 269 | ytcfg['priority'] -= 3 |
270 | ||
271 | ||
272 | build_innertube_clients() | |
273 | ||
274 | ||
de7f3446 | 275 | class YoutubeBaseInfoExtractor(InfoExtractor): |
b2e8bc1b | 276 | """Provide base functions for Youtube extractors""" |
e00eb564 | 277 | |
3462ffa8 | 278 | _RESERVED_NAMES = ( |
3cd786db | 279 | r'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|' |
182bda88 | 280 | r'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|' |
3619f78d | 281 | r'browse|oembed|get_video_info|iframe_api|s/player|' |
cd7c66cf | 282 | r'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout') |
3462ffa8 | 283 | |
3619f78d | 284 | _PLAYLIST_ID_RE = r'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)' |
285 | ||
52efa4b3 | 286 | # _NETRC_MACHINE = 'youtube' |
3619f78d | 287 | |
b2e8bc1b JMF |
288 | # If True it will raise an error if no login info is provided |
289 | _LOGIN_REQUIRED = False | |
290 | ||
d9190e44 RH |
291 | _INVIDIOUS_SITES = ( |
292 | # invidious-redirect websites | |
293 | r'(?:www\.)?redirect\.invidious\.io', | |
294 | r'(?:(?:www|dev)\.)?invidio\.us', | |
295 | # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md | |
296 | r'(?:www\.)?invidious\.pussthecat\.org', | |
297 | r'(?:www\.)?invidious\.zee\.li', | |
298 | r'(?:www\.)?invidious\.ethibox\.fr', | |
299 | r'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion', | |
4c968755 U |
300 | r'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion', |
301 | r'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion', | |
d9190e44 RH |
302 | # youtube-dl invidious instances list |
303 | r'(?:(?:www|no)\.)?invidiou\.sh', | |
304 | r'(?:(?:www|fi)\.)?invidious\.snopyta\.org', | |
305 | r'(?:www\.)?invidious\.kabi\.tk', | |
306 | r'(?:www\.)?invidious\.mastodon\.host', | |
307 | r'(?:www\.)?invidious\.zapashcanon\.fr', | |
308 | r'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks', | |
309 | r'(?:www\.)?invidious\.tinfoil-hat\.net', | |
310 | r'(?:www\.)?invidious\.himiko\.cloud', | |
311 | r'(?:www\.)?invidious\.reallyancient\.tech', | |
312 | r'(?:www\.)?invidious\.tube', | |
313 | r'(?:www\.)?invidiou\.site', | |
314 | r'(?:www\.)?invidious\.site', | |
315 | r'(?:www\.)?invidious\.xyz', | |
316 | r'(?:www\.)?invidious\.nixnet\.xyz', | |
317 | r'(?:www\.)?invidious\.048596\.xyz', | |
318 | r'(?:www\.)?invidious\.drycat\.fr', | |
319 | r'(?:www\.)?inv\.skyn3t\.in', | |
320 | r'(?:www\.)?tube\.poal\.co', | |
321 | r'(?:www\.)?tube\.connect\.cafe', | |
322 | r'(?:www\.)?vid\.wxzm\.sx', | |
323 | r'(?:www\.)?vid\.mint\.lgbt', | |
324 | r'(?:www\.)?vid\.puffyan\.us', | |
325 | r'(?:www\.)?yewtu\.be', | |
326 | r'(?:www\.)?yt\.elukerio\.org', | |
327 | r'(?:www\.)?yt\.lelux\.fi', | |
328 | r'(?:www\.)?invidious\.ggc-project\.de', | |
329 | r'(?:www\.)?yt\.maisputain\.ovh', | |
330 | r'(?:www\.)?ytprivate\.com', | |
331 | r'(?:www\.)?invidious\.13ad\.de', | |
332 | r'(?:www\.)?invidious\.toot\.koeln', | |
333 | r'(?:www\.)?invidious\.fdn\.fr', | |
334 | r'(?:www\.)?watch\.nettohikari\.com', | |
335 | r'(?:www\.)?invidious\.namazso\.eu', | |
336 | r'(?:www\.)?invidious\.silkky\.cloud', | |
337 | r'(?:www\.)?invidious\.exonip\.de', | |
338 | r'(?:www\.)?invidious\.riverside\.rocks', | |
339 | r'(?:www\.)?invidious\.blamefran\.net', | |
340 | r'(?:www\.)?invidious\.moomoo\.de', | |
341 | r'(?:www\.)?ytb\.trom\.tf', | |
342 | r'(?:www\.)?yt\.cyberhost\.uk', | |
343 | r'(?:www\.)?kgg2m7yk5aybusll\.onion', | |
344 | r'(?:www\.)?qklhadlycap4cnod\.onion', | |
345 | r'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion', | |
346 | r'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion', | |
347 | r'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion', | |
348 | r'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion', | |
349 | r'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p', | |
350 | r'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion', | |
351 | r'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion', | |
352 | r'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion', | |
353 | r'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion', | |
354 | r'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion', | |
355 | ) | |
356 | ||
cce889b9 | 357 | def _initialize_consent(self): |
358 | cookies = self._get_cookies('https://www.youtube.com/') | |
359 | if cookies.get('__Secure-3PSID'): | |
360 | return | |
361 | consent_id = None | |
362 | consent = cookies.get('CONSENT') | |
363 | if consent: | |
364 | if 'YES' in consent.value: | |
365 | return | |
366 | consent_id = self._search_regex( | |
367 | r'PENDING\+(\d+)', consent.value, 'consent', default=None) | |
368 | if not consent_id: | |
369 | consent_id = random.randint(100, 999) | |
370 | self._set_cookie('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id) | |
8d81f3e3 | 371 | |
f3aa3c3f | 372 | def _initialize_pref(self): |
373 | cookies = self._get_cookies('https://www.youtube.com/') | |
374 | pref_cookie = cookies.get('PREF') | |
375 | pref = {} | |
376 | if pref_cookie: | |
377 | try: | |
378 | pref = dict(compat_urlparse.parse_qsl(pref_cookie.value)) | |
379 | except ValueError: | |
380 | self.report_warning('Failed to parse user PREF cookie' + bug_reports_message()) | |
396a76f7 | 381 | pref.update({'hl': 'en', 'tz': 'UTC'}) |
f3aa3c3f | 382 | self._set_cookie('.youtube.com', name='PREF', value=compat_urllib_parse_urlencode(pref)) |
383 | ||
b2e8bc1b | 384 | def _real_initialize(self): |
f3aa3c3f | 385 | self._initialize_pref() |
cce889b9 | 386 | self._initialize_consent() |
a25bca9f | 387 | self._check_login_required() |
388 | ||
389 | def _check_login_required(self): | |
52efa4b3 | 390 | if (self._LOGIN_REQUIRED |
391 | and self.get_param('cookiefile') is None | |
392 | and self.get_param('cookiesfrombrowser') is None): | |
393 | self.raise_login_required('Login details are needed to download this content', method='cookies') | |
c5e8d7af | 394 | |
a0566bbf | 395 | _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;' |
29f7c58a | 396 | _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;' |
397 | _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)' | |
a0566bbf | 398 | |
000c15a4 | 399 | def _get_default_ytcfg(self, client='web'): |
400 | return copy.deepcopy(INNERTUBE_CLIENTS[client]) | |
109dd3b2 | 401 | |
000c15a4 | 402 | def _get_innertube_host(self, client='web'): |
403 | return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST'] | |
109dd3b2 | 404 | |
000c15a4 | 405 | def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'): |
109dd3b2 | 406 | # try_get but with fallback to default ytcfg client values when present |
407 | _func = lambda y: try_get(y, getter, expected_type) | |
408 | return _func(ytcfg) or _func(self._get_default_ytcfg(default_client)) | |
409 | ||
000c15a4 | 410 | def _extract_client_name(self, ytcfg, default_client='web'): |
3619f78d | 411 | return self._ytcfg_get_safe( |
412 | ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'], | |
413 | lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client) | |
109dd3b2 | 414 | |
000c15a4 | 415 | def _extract_client_version(self, ytcfg, default_client='web'): |
3619f78d | 416 | return self._ytcfg_get_safe( |
417 | ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'], | |
418 | lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client) | |
109dd3b2 | 419 | |
000c15a4 | 420 | def _extract_api_key(self, ytcfg=None, default_client='web'): |
109dd3b2 | 421 | return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client) |
422 | ||
000c15a4 | 423 | def _extract_context(self, ytcfg=None, default_client='web'): |
f3aa3c3f | 424 | context = get_first( |
425 | (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict) | |
396a76f7 | 426 | # Enforce language and tz for extraction |
427 | client_context = traverse_obj(context, 'client', expected_type=dict, default={}) | |
428 | client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0}) | |
109dd3b2 | 429 | return context |
430 | ||
cf87314d | 431 | _SAPISID = None |
432 | ||
109dd3b2 | 433 | def _generate_sapisidhash_header(self, origin='https://www.youtube.com'): |
a5c56234 | 434 | time_now = round(time.time()) |
cf87314d | 435 | if self._SAPISID is None: |
436 | yt_cookies = self._get_cookies('https://www.youtube.com') | |
437 | # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is. | |
438 | # See: https://github.com/yt-dlp/yt-dlp/issues/393 | |
439 | sapisid_cookie = dict_get( | |
440 | yt_cookies, ('__Secure-3PAPISID', 'SAPISID')) | |
441 | if sapisid_cookie and sapisid_cookie.value: | |
442 | self._SAPISID = sapisid_cookie.value | |
443 | self.write_debug('Extracted SAPISID cookie') | |
444 | # SAPISID cookie is required if not already present | |
445 | if not yt_cookies.get('SAPISID'): | |
446 | self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie') | |
447 | self._set_cookie( | |
448 | '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600) | |
449 | else: | |
450 | self._SAPISID = False | |
451 | if not self._SAPISID: | |
452 | return None | |
1974e99f | 453 | # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323 |
454 | sapisidhash = hashlib.sha1( | |
cf87314d | 455 | f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest() |
1974e99f | 456 | return f'SAPISIDHASH {time_now}_{sapisidhash}' |
a5c56234 M |
457 | |
458 | def _call_api(self, ep, query, video_id, fatal=True, headers=None, | |
f4f751af | 459 | note='Downloading API JSON', errnote='Unable to download API page', |
000c15a4 | 460 | context=None, api_key=None, api_hostname=None, default_client='web'): |
f4f751af | 461 | |
109dd3b2 | 462 | data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)} |
8bdd16b4 | 463 | data.update(query) |
11f9be09 | 464 | real_headers = self.generate_api_headers(default_client=default_client) |
f4f751af | 465 | real_headers.update({'content-type': 'application/json'}) |
466 | if headers: | |
467 | real_headers.update(headers) | |
545cc85d | 468 | return self._download_json( |
109dd3b2 | 469 | 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep), |
a5c56234 | 470 | video_id=video_id, fatal=fatal, note=note, errnote=errnote, |
f4f751af | 471 | data=json.dumps(data).encode('utf8'), headers=real_headers, |
5dbc77df | 472 | query={'key': api_key or self._extract_api_key(), 'prettyPrint': 'false'}) |
f4f751af | 473 | |
ac56cf38 | 474 | def extract_yt_initial_data(self, item_id, webpage, fatal=True): |
475 | data = self._search_regex( | |
476 | (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE), | |
477 | self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal) | |
478 | if data: | |
479 | return self._parse_json(data, item_id, fatal=fatal) | |
0c148415 | 480 | |
99e9e001 | 481 | @staticmethod |
482 | def _extract_session_index(*data): | |
483 | """ | |
484 | Index of current account in account list. | |
485 | See: https://github.com/yt-dlp/yt-dlp/pull/519 | |
486 | """ | |
487 | for ytcfg in data: | |
488 | session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX'])) | |
489 | if session_index is not None: | |
490 | return session_index | |
491 | ||
492 | # Deprecated? | |
493 | def _extract_identity_token(self, ytcfg=None, webpage=None): | |
a1c5d2ca M |
494 | if ytcfg: |
495 | token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str) | |
496 | if token: | |
497 | return token | |
99e9e001 | 498 | if webpage: |
499 | return self._search_regex( | |
500 | r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage, | |
501 | 'identity token', default=None, fatal=False) | |
a1c5d2ca M |
502 | |
503 | @staticmethod | |
fe93e2c4 | 504 | def _extract_account_syncid(*args): |
8ea3f7b9 | 505 | """ |
506 | Extract syncId required to download private playlists of secondary channels | |
fe93e2c4 | 507 | @params response and/or ytcfg |
8ea3f7b9 | 508 | """ |
fe93e2c4 | 509 | for data in args: |
510 | # ytcfg includes channel_syncid if on secondary channel | |
511 | delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID'], compat_str) | |
512 | if delegated_sid: | |
513 | return delegated_sid | |
514 | sync_ids = (try_get( | |
515 | data, (lambda x: x['responseContext']['mainAppWebResponseContext']['datasyncId'], | |
e6f21b3d | 516 | lambda x: x['DATASYNC_ID']), compat_str) or '').split('||') |
fe93e2c4 | 517 | if len(sync_ids) >= 2 and sync_ids[1]: |
518 | # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel | |
519 | # and just "user_syncid||" for primary channel. We only want the channel_syncid | |
520 | return sync_ids[0] | |
a1c5d2ca | 521 | |
ac56cf38 | 522 | @staticmethod |
523 | def _extract_visitor_data(*args): | |
524 | """ | |
525 | Extracts visitorData from an API response or ytcfg | |
526 | Appears to be used to track session state | |
527 | """ | |
9222c381 | 528 | return get_first( |
6c73052c | 529 | args, [('VISITOR_DATA', ('INNERTUBE_CONTEXT', 'client', 'visitorData'), ('responseContext', 'visitorData'))], |
9222c381 | 530 | expected_type=str) |
ac56cf38 | 531 | |
99e9e001 | 532 | @property |
533 | def is_authenticated(self): | |
534 | return bool(self._generate_sapisidhash_header()) | |
535 | ||
11f9be09 | 536 | def extract_ytcfg(self, video_id, webpage): |
8c54a305 | 537 | if not webpage: |
538 | return {} | |
29f7c58a | 539 | return self._parse_json( |
540 | self._search_regex( | |
541 | r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg', | |
f4f751af | 542 | default='{}'), video_id, fatal=False) or {} |
543 | ||
11f9be09 | 544 | def generate_api_headers( |
99e9e001 | 545 | self, *, ytcfg=None, account_syncid=None, session_index=None, |
546 | visitor_data=None, identity_token=None, api_hostname=None, default_client='web'): | |
547 | ||
11f9be09 | 548 | origin = 'https://' + (api_hostname if api_hostname else self._get_innertube_host(default_client)) |
f4f751af | 549 | headers = { |
109dd3b2 | 550 | 'X-YouTube-Client-Name': compat_str( |
11f9be09 | 551 | self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client=default_client)), |
552 | 'X-YouTube-Client-Version': self._extract_client_version(ytcfg, default_client), | |
99e9e001 | 553 | 'Origin': origin, |
554 | 'X-Youtube-Identity-Token': identity_token or self._extract_identity_token(ytcfg), | |
555 | 'X-Goog-PageId': account_syncid or self._extract_account_syncid(ytcfg), | |
ac56cf38 | 556 | 'X-Goog-Visitor-Id': visitor_data or self._extract_visitor_data(ytcfg) |
99e9e001 | 557 | } |
558 | if session_index is None: | |
314ee305 | 559 | session_index = self._extract_session_index(ytcfg) |
560 | if account_syncid or session_index is not None: | |
561 | headers['X-Goog-AuthUser'] = session_index if session_index is not None else 0 | |
99e9e001 | 562 | |
109dd3b2 | 563 | auth = self._generate_sapisidhash_header(origin) |
f4f751af | 564 | if auth is not None: |
565 | headers['Authorization'] = auth | |
109dd3b2 | 566 | headers['X-Origin'] = origin |
99e9e001 | 567 | return {h: v for h, v in headers.items() if v is not None} |
29f7c58a | 568 | |
a25bca9f | 569 | def _download_ytcfg(self, client, video_id): |
570 | url = { | |
571 | 'web': 'https://www.youtube.com', | |
572 | 'web_music': 'https://music.youtube.com', | |
573 | 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1' | |
574 | }.get(client) | |
575 | if not url: | |
576 | return {} | |
577 | webpage = self._download_webpage( | |
578 | url, video_id, fatal=False, note=f'Downloading {client.replace("_", " ").strip()} client config') | |
579 | return self.extract_ytcfg(video_id, webpage) or {} | |
580 | ||
2d6659b9 | 581 | @staticmethod |
582 | def _build_api_continuation_query(continuation, ctp=None): | |
583 | query = { | |
584 | 'continuation': continuation | |
585 | } | |
586 | # TODO: Inconsistency with clickTrackingParams. | |
587 | # Currently we have a fixed ctp contained within context (from ytcfg) | |
588 | # and a ctp in root query for continuation. | |
589 | if ctp: | |
590 | query['clickTracking'] = {'clickTrackingParams': ctp} | |
591 | return query | |
592 | ||
2d6659b9 | 593 | @classmethod |
594 | def _extract_next_continuation_data(cls, renderer): | |
595 | next_continuation = try_get( | |
596 | renderer, (lambda x: x['continuations'][0]['nextContinuationData'], | |
597 | lambda x: x['continuation']['reloadContinuationData']), dict) | |
598 | if not next_continuation: | |
599 | return | |
600 | continuation = next_continuation.get('continuation') | |
601 | if not continuation: | |
602 | return | |
603 | ctp = next_continuation.get('clickTrackingParams') | |
fe93e2c4 | 604 | return cls._build_api_continuation_query(continuation, ctp) |
2d6659b9 | 605 | |
606 | @classmethod | |
607 | def _extract_continuation_ep_data(cls, continuation_ep: dict): | |
608 | if isinstance(continuation_ep, dict): | |
609 | continuation = try_get( | |
610 | continuation_ep, lambda x: x['continuationCommand']['token'], compat_str) | |
611 | if not continuation: | |
612 | return | |
613 | ctp = continuation_ep.get('clickTrackingParams') | |
fe93e2c4 | 614 | return cls._build_api_continuation_query(continuation, ctp) |
2d6659b9 | 615 | |
616 | @classmethod | |
617 | def _extract_continuation(cls, renderer): | |
618 | next_continuation = cls._extract_next_continuation_data(renderer) | |
619 | if next_continuation: | |
620 | return next_continuation | |
fe93e2c4 | 621 | |
2d6659b9 | 622 | contents = [] |
623 | for key in ('contents', 'items'): | |
624 | contents.extend(try_get(renderer, lambda x: x[key], list) or []) | |
fe93e2c4 | 625 | |
2d6659b9 | 626 | for content in contents: |
627 | if not isinstance(content, dict): | |
628 | continue | |
629 | continuation_ep = try_get( | |
630 | content, (lambda x: x['continuationItemRenderer']['continuationEndpoint'], | |
631 | lambda x: x['continuationItemRenderer']['button']['buttonRenderer']['command']), | |
632 | dict) | |
633 | continuation = cls._extract_continuation_ep_data(continuation_ep) | |
634 | if continuation: | |
635 | return continuation | |
636 | ||
fe93e2c4 | 637 | @classmethod |
638 | def _extract_alerts(cls, data): | |
109dd3b2 | 639 | for alert_dict in try_get(data, lambda x: x['alerts'], list) or []: |
640 | if not isinstance(alert_dict, dict): | |
641 | continue | |
642 | for alert in alert_dict.values(): | |
643 | alert_type = alert.get('type') | |
644 | if not alert_type: | |
645 | continue | |
052e1350 | 646 | message = cls._get_text(alert, 'text') |
109dd3b2 | 647 | if message: |
648 | yield alert_type, message | |
649 | ||
c0ac49bc | 650 | def _report_alerts(self, alerts, expected=True, fatal=True, only_once=False): |
109dd3b2 | 651 | errors = [] |
652 | warnings = [] | |
653 | for alert_type, alert_message in alerts: | |
641ad5d8 | 654 | if alert_type.lower() == 'error' and fatal: |
109dd3b2 | 655 | errors.append([alert_type, alert_message]) |
656 | else: | |
657 | warnings.append([alert_type, alert_message]) | |
658 | ||
659 | for alert_type, alert_message in (warnings + errors[:-1]): | |
c0ac49bc | 660 | self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message), only_once=only_once) |
109dd3b2 | 661 | if errors: |
662 | raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected) | |
663 | ||
664 | def _extract_and_report_alerts(self, data, *args, **kwargs): | |
665 | return self._report_alerts(self._extract_alerts(data), *args, **kwargs) | |
666 | ||
47193e02 | 667 | def _extract_badges(self, renderer: dict): |
668 | badges = set() | |
669 | for badge in try_get(renderer, lambda x: x['badges'], list) or []: | |
670 | label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label'], compat_str) | |
671 | if label: | |
672 | badges.add(label.lower()) | |
673 | return badges | |
674 | ||
675 | @staticmethod | |
052e1350 | 676 | def _get_text(data, *path_list, max_runs=None): |
677 | for path in path_list or [None]: | |
678 | if path is None: | |
679 | obj = [data] | |
680 | else: | |
681 | obj = traverse_obj(data, path, default=[]) | |
682 | if not any(key is ... or isinstance(key, (list, tuple)) for key in variadic(path)): | |
683 | obj = [obj] | |
684 | for item in obj: | |
685 | text = try_get(item, lambda x: x['simpleText'], compat_str) | |
686 | if text: | |
687 | return text | |
688 | runs = try_get(item, lambda x: x['runs'], list) or [] | |
689 | if not runs and isinstance(item, list): | |
690 | runs = item | |
691 | ||
692 | runs = runs[:min(len(runs), max_runs or len(runs))] | |
693 | text = ''.join(traverse_obj(runs, (..., 'text'), expected_type=str, default=[])) | |
694 | if text: | |
695 | return text | |
47193e02 | 696 | |
f0d785d3 | 697 | def _get_count(self, data, *path_list): |
698 | count_text = self._get_text(data, *path_list) or '' | |
699 | count = parse_count(count_text) | |
700 | if count is None: | |
701 | count = str_to_int( | |
702 | self._search_regex(r'^([\d,]+)', re.sub(r'\s', '', count_text), 'count', default=None)) | |
703 | return count | |
704 | ||
a709d873 | 705 | @staticmethod |
706 | def _extract_thumbnails(data, *path_list): | |
707 | """ | |
708 | Extract thumbnails from thumbnails dict | |
709 | @param path_list: path list to level that contains 'thumbnails' key | |
710 | """ | |
711 | thumbnails = [] | |
712 | for path in path_list or [()]: | |
713 | for thumbnail in traverse_obj(data, (*variadic(path), 'thumbnails', ...), default=[]): | |
714 | thumbnail_url = url_or_none(thumbnail.get('url')) | |
715 | if not thumbnail_url: | |
716 | continue | |
717 | # Sometimes youtube gives a wrong thumbnail URL. See: | |
718 | # https://github.com/yt-dlp/yt-dlp/issues/233 | |
719 | # https://github.com/ytdl-org/youtube-dl/issues/28023 | |
720 | if 'maxresdefault' in thumbnail_url: | |
721 | thumbnail_url = thumbnail_url.split('?')[0] | |
722 | thumbnails.append({ | |
723 | 'url': thumbnail_url, | |
724 | 'height': int_or_none(thumbnail.get('height')), | |
725 | 'width': int_or_none(thumbnail.get('width')), | |
726 | }) | |
727 | return thumbnails | |
728 | ||
f3aa3c3f | 729 | @staticmethod |
730 | def extract_relative_time(relative_time_text): | |
731 | """ | |
732 | Extracts a relative time from string and converts to dt object | |
f0d785d3 | 733 | e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today' |
f3aa3c3f | 734 | """ |
f0d785d3 | 735 | 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 | 736 | if mobj: |
f0d785d3 | 737 | start = mobj.group('start') |
738 | if start: | |
739 | return datetime_from_str(start) | |
f3aa3c3f | 740 | try: |
f0d785d3 | 741 | return datetime_from_str('now-%s%s' % (mobj.group('time'), mobj.group('unit'))) |
f3aa3c3f | 742 | except ValueError: |
743 | return None | |
744 | ||
745 | def _extract_time_text(self, renderer, *path_list): | |
a25bca9f | 746 | """@returns (timestamp, time_text)""" |
f3aa3c3f | 747 | text = self._get_text(renderer, *path_list) or '' |
748 | dt = self.extract_relative_time(text) | |
749 | timestamp = None | |
750 | if isinstance(dt, datetime.datetime): | |
751 | timestamp = calendar.timegm(dt.timetuple()) | |
f0d785d3 | 752 | |
753 | if timestamp is None: | |
754 | timestamp = ( | |
755 | unified_timestamp(text) or unified_timestamp( | |
756 | self._search_regex( | |
17322130 | 757 | (r'([a-z]+\s*\d{1,2},?\s*20\d{2})', r'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'), |
396a76f7 | 758 | text.lower(), 'time text', default=None))) |
f0d785d3 | 759 | |
f3aa3c3f | 760 | if text and timestamp is None: |
17322130 | 761 | self.report_warning(f"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once=True) |
f3aa3c3f | 762 | return timestamp, text |
763 | ||
109dd3b2 | 764 | def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None, |
765 | ytcfg=None, check_get_keys=None, ep='browse', fatal=True, api_hostname=None, | |
000c15a4 | 766 | default_client='web'): |
109dd3b2 | 767 | response = None |
768 | last_error = None | |
769 | count = -1 | |
770 | retries = self.get_param('extractor_retries', 3) | |
771 | if check_get_keys is None: | |
772 | check_get_keys = [] | |
773 | while count < retries: | |
774 | count += 1 | |
775 | if last_error: | |
c0ac49bc | 776 | self.report_warning('%s. Retrying ...' % remove_end(last_error, '.')) |
109dd3b2 | 777 | try: |
778 | response = self._call_api( | |
779 | ep=ep, fatal=True, headers=headers, | |
780 | video_id=item_id, query=query, | |
781 | context=self._extract_context(ytcfg, default_client), | |
782 | api_key=self._extract_api_key(ytcfg, default_client), | |
783 | api_hostname=api_hostname, default_client=default_client, | |
784 | note='%s%s' % (note, ' (retry #%d)' % count if count else '')) | |
785 | except ExtractorError as e: | |
9c0d7f49 | 786 | if isinstance(e.cause, network_exceptions): |
87e8e8a7 | 787 | if isinstance(e.cause, compat_HTTPError): |
788 | first_bytes = e.cause.read(512) | |
789 | if not is_html(first_bytes): | |
790 | yt_error = try_get( | |
791 | self._parse_json( | |
792 | self._webpage_read_content(e.cause, None, item_id, prefix=first_bytes) or '{}', item_id, fatal=False), | |
793 | lambda x: x['error']['message'], compat_str) | |
794 | if yt_error: | |
795 | self._report_alerts([('ERROR', yt_error)], fatal=False) | |
109dd3b2 | 796 | # Downloading page may result in intermittent 5xx HTTP error |
797 | # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289 | |
9c0d7f49 | 798 | # We also want to catch all other network exceptions since errors in later pages can be troublesome |
799 | # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210 | |
800 | if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429): | |
526d74ec | 801 | last_error = error_to_compat_str(e.cause or e.msg) |
9c0d7f49 | 802 | if count < retries: |
803 | continue | |
109dd3b2 | 804 | if fatal: |
805 | raise | |
806 | else: | |
807 | self.report_warning(error_to_compat_str(e)) | |
808 | return | |
809 | ||
810 | else: | |
109dd3b2 | 811 | try: |
ac56cf38 | 812 | self._extract_and_report_alerts(response, only_once=True) |
109dd3b2 | 813 | except ExtractorError as e: |
c0ac49bc | 814 | # YouTube servers may return errors we want to retry on in a 200 OK response |
815 | # See: https://github.com/yt-dlp/yt-dlp/issues/839 | |
816 | if 'unknown error' in e.msg.lower(): | |
817 | last_error = e.msg | |
818 | continue | |
109dd3b2 | 819 | if fatal: |
820 | raise | |
821 | self.report_warning(error_to_compat_str(e)) | |
822 | return | |
823 | if not check_get_keys or dict_get(response, check_get_keys): | |
824 | break | |
825 | # Youtube sometimes sends incomplete data | |
826 | # See: https://github.com/ytdl-org/youtube-dl/issues/28194 | |
827 | last_error = 'Incomplete data received' | |
828 | if count >= retries: | |
829 | if fatal: | |
830 | raise ExtractorError(last_error) | |
831 | else: | |
832 | self.report_warning(last_error) | |
833 | return | |
834 | return response | |
835 | ||
9297939e | 836 | @staticmethod |
837 | def is_music_url(url): | |
838 | return re.match(r'https?://music\.youtube\.com/', url) is not None | |
839 | ||
30a074c2 | 840 | def _extract_video(self, renderer): |
841 | video_id = renderer.get('videoId') | |
052e1350 | 842 | title = self._get_text(renderer, 'title') |
843 | description = self._get_text(renderer, 'descriptionSnippet') | |
a353beba | 844 | duration = parse_duration(self._get_text( |
845 | renderer, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text'))) | |
1c1b2f96 | 846 | if duration is None: |
847 | duration = parse_duration(self._search_regex( | |
848 | r'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$', | |
849 | traverse_obj(renderer, ('title', 'accessibility', 'accessibilityData', 'label'), default='', expected_type=str), | |
850 | video_id, default=None, group='duration')) | |
851 | ||
f0d785d3 | 852 | view_count = self._get_count(renderer, 'viewCountText') |
fe93e2c4 | 853 | |
052e1350 | 854 | uploader = self._get_text(renderer, 'ownerText', 'shortBylineText') |
f3aa3c3f | 855 | channel_id = traverse_obj( |
a44ca5a4 | 856 | renderer, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), |
857 | expected_type=str, get_all=False) | |
f3aa3c3f | 858 | timestamp, time_text = self._extract_time_text(renderer, 'publishedTimeText') |
859 | scheduled_timestamp = str_to_int(traverse_obj(renderer, ('upcomingEventData', 'startTime'), get_all=False)) | |
860 | overlay_style = traverse_obj( | |
a44ca5a4 | 861 | renderer, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), |
862 | get_all=False, expected_type=str) | |
f3aa3c3f | 863 | badges = self._extract_badges(renderer) |
a709d873 | 864 | thumbnails = self._extract_thumbnails(renderer, 'thumbnail') |
fd2ad7cb | 865 | navigation_url = urljoin('https://www.youtube.com/', traverse_obj( |
a44ca5a4 | 866 | renderer, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'), |
867 | expected_type=str)) or '' | |
fd2ad7cb | 868 | url = f'https://www.youtube.com/watch?v={video_id}' |
a44ca5a4 | 869 | if overlay_style == 'SHORTS' or '/shorts/' in navigation_url: |
fd2ad7cb | 870 | url = f'https://www.youtube.com/shorts/{video_id}' |
a709d873 | 871 | |
30a074c2 | 872 | return { |
39ed931e | 873 | '_type': 'url', |
30a074c2 | 874 | 'ie_key': YoutubeIE.ie_key(), |
875 | 'id': video_id, | |
fd2ad7cb | 876 | 'url': url, |
30a074c2 | 877 | 'title': title, |
878 | 'description': description, | |
879 | 'duration': duration, | |
880 | 'view_count': view_count, | |
881 | 'uploader': uploader, | |
f3aa3c3f | 882 | 'channel_id': channel_id, |
a709d873 | 883 | 'thumbnails': thumbnails, |
a44ca5a4 | 884 | 'upload_date': (strftime_or_none(timestamp, '%Y%m%d') |
885 | if self._configuration_arg('approximate_date', ie_key='youtubetab') | |
886 | else None), | |
f3aa3c3f | 887 | 'live_status': ('is_upcoming' if scheduled_timestamp is not None |
888 | else 'was_live' if 'streamed' in time_text.lower() | |
889 | else 'is_live' if overlay_style is not None and overlay_style == 'LIVE' or 'live now' in badges | |
890 | else None), | |
891 | 'release_timestamp': scheduled_timestamp, | |
892 | 'availability': self._availability(needs_premium='premium' in badges, needs_subscription='members only' in badges) | |
30a074c2 | 893 | } |
894 | ||
0c148415 | 895 | |
360e1ca5 | 896 | class YoutubeIE(YoutubeBaseInfoExtractor): |
96565c7e | 897 | IE_DESC = 'YouTube' |
cb7dfeea | 898 | _VALID_URL = r"""(?x)^ |
c5e8d7af | 899 | ( |
edb53e2d | 900 | (?:https?://|//) # http(s):// or protocol-independent URL |
bc2ca1bb | 901 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com| |
902 | (?:www\.)?deturl\.com/www\.youtube\.com| | |
903 | (?:www\.)?pwnyoutube\.com| | |
904 | (?:www\.)?hooktube\.com| | |
905 | (?:www\.)?yourepeat\.com| | |
906 | tube\.majestyc\.net| | |
907 | %(invidious)s| | |
908 | youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains | |
c5e8d7af PH |
909 | (?:.*?\#/)? # handle anchor (#/) redirect urls |
910 | (?: # the various things that can precede the ID: | |
b6ce9bb0 | 911 | (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/ |
c5e8d7af | 912 | |(?: # or the v= param in all its forms |
f7000f3a | 913 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) |
c5e8d7af | 914 | (?:\?|\#!?) # the params delimiter ? or # or #! |
040ac686 | 915 | (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY) |
c5e8d7af PH |
916 | v= |
917 | ) | |
f4b05232 | 918 | )) |
cbaed4bb S |
919 | |(?: |
920 | youtu\.be| # just youtu.be/xxxx | |
6d4fc66b S |
921 | vid\.plus| # or vid.plus/xxxx |
922 | zwearz\.com/watch| # or zwearz.com/watch/xxxx | |
bc2ca1bb | 923 | %(invidious)s |
cbaed4bb | 924 | )/ |
edb53e2d | 925 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= |
f4b05232 | 926 | ) |
c5e8d7af | 927 | )? # all until now is optional -> you can pass the naked ID |
201c1459 | 928 | (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID |
c5e8d7af | 929 | (?(1).+)? # if we found the ID, everything can follow |
9297939e | 930 | (?:\#|$)""" % { |
d9190e44 | 931 | 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), |
bc2ca1bb | 932 | } |
e40c758c | 933 | _PLAYER_INFO_RE = ( |
cc2db878 | 934 | r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player', |
935 | 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$', | |
545cc85d | 936 | r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$', |
e40c758c | 937 | ) |
2c62dc26 | 938 | _formats = { |
c2d3cb4c | 939 | '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, |
940 | '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
941 | '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
942 | '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}, | |
943 | '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}, | |
944 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
945 | '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
946 | '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
3834d3e3 | 947 | # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well |
c2d3cb4c | 948 | '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}, |
949 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
950 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
951 | '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
952 | '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
953 | '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
e1a0bfdf | 954 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, |
c2d3cb4c | 955 | '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, |
956 | '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
e1a0bfdf | 957 | |
958 | ||
959 | # 3D videos | |
c2d3cb4c | 960 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, |
961 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
962 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
963 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
e1a0bfdf | 964 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}, |
965 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
966 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
836a086c | 967 | |
96fb5605 | 968 | # Apple HTTP Live Streaming |
11f12195 | 969 | '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
c2d3cb4c | 970 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
971 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
972 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
973 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
974 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
e1a0bfdf | 975 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
976 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}, | |
2c62dc26 PH |
977 | |
978 | # DASH mp4 video | |
d23028a8 S |
979 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}, |
980 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
981 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
982 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
983 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
067aa17e | 984 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559) |
d23028a8 S |
985 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}, |
986 | '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
987 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
988 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
989 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
990 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
836a086c | 991 | |
f6f1fc92 | 992 | # Dash mp4 audio |
d23028a8 S |
993 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}, |
994 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}, | |
995 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}, | |
996 | '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
997 | '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
998 | '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}, | |
999 | '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}, | |
836a086c AZ |
1000 | |
1001 | # Dash webm | |
d23028a8 S |
1002 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, |
1003 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1004 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1005 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1006 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1007 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
1008 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}, | |
1009 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1010 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1011 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1012 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1013 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1014 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1015 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1016 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
4c6b4764 | 1017 | # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug) |
d23028a8 S |
1018 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, |
1019 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
1020 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
1021 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
1022 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
1023 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
2c62dc26 PH |
1024 | |
1025 | # Dash webm audio | |
d23028a8 S |
1026 | '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}, |
1027 | '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}, | |
ce6b9a2d | 1028 | |
0857baad | 1029 | # Dash webm audio with opus inside |
d23028a8 S |
1030 | '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}, |
1031 | '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}, | |
1032 | '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}, | |
0857baad | 1033 | |
ce6b9a2d PH |
1034 | # RTMP (unnamed) |
1035 | '_rtmp': {'protocol': 'rtmp'}, | |
b85eae0f S |
1036 | |
1037 | # av01 video only formats sometimes served with "unknown" codecs | |
9b5fa9ee TOH |
1038 | '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}, |
1039 | '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}, | |
1040 | '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'}, | |
1041 | '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'}, | |
1042 | '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'}, | |
1043 | '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'}, | |
1044 | '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}, | |
1045 | '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}, | |
c5e8d7af | 1046 | } |
29f7c58a | 1047 | _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt') |
836a086c | 1048 | |
fd5c4aab S |
1049 | _GEO_BYPASS = False |
1050 | ||
78caa52a | 1051 | IE_NAME = 'youtube' |
2eb88d95 PH |
1052 | _TESTS = [ |
1053 | { | |
2d3d2997 | 1054 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9', |
4bc3a23e PH |
1055 | 'info_dict': { |
1056 | 'id': 'BaW_jenozKc', | |
1057 | 'ext': 'mp4', | |
3867038a | 1058 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', |
4bc3a23e PH |
1059 | 'uploader': 'Philipp Hagemeister', |
1060 | 'uploader_id': 'phihag', | |
ec85ded8 | 1061 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', |
ff9f925b | 1062 | 'channel': 'Philipp Hagemeister', |
dd4c4492 S |
1063 | 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', |
1064 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', | |
4bc3a23e | 1065 | 'upload_date': '20121002', |
ff9f925b | 1066 | 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22', |
4bc3a23e | 1067 | 'categories': ['Science & Technology'], |
3867038a | 1068 | 'tags': ['youtube-dl'], |
556dbe7f | 1069 | 'duration': 10, |
dbdaaa23 | 1070 | 'view_count': int, |
3e7c1224 | 1071 | 'like_count': int, |
ff9f925b | 1072 | 'availability': 'public', |
1073 | 'playable_in_embed': True, | |
1074 | 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg', | |
1075 | 'live_status': 'not_live', | |
1076 | 'age_limit': 0, | |
7c80519c | 1077 | 'start_time': 1, |
297a564b | 1078 | 'end_time': 9, |
6c73052c | 1079 | 'channel_follower_count': int |
2eb88d95 | 1080 | } |
0e853ca4 | 1081 | }, |
fccd3771 | 1082 | { |
4bc3a23e PH |
1083 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', |
1084 | 'note': 'Embed-only video (#1746)', | |
1085 | 'info_dict': { | |
1086 | 'id': 'yZIXLfi8CZQ', | |
1087 | 'ext': 'mp4', | |
1088 | 'upload_date': '20120608', | |
1089 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
1090 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
1091 | 'uploader': 'SET India', | |
94bfcd23 | 1092 | 'uploader_id': 'setindia', |
ec85ded8 | 1093 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia', |
94bfcd23 | 1094 | 'age_limit': 18, |
545cc85d | 1095 | }, |
1096 | 'skip': 'Private video', | |
fccd3771 | 1097 | }, |
11b56058 | 1098 | { |
8bdd16b4 | 1099 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ', |
11b56058 PM |
1100 | 'note': 'Use the first video ID in the URL', |
1101 | 'info_dict': { | |
1102 | 'id': 'BaW_jenozKc', | |
1103 | 'ext': 'mp4', | |
3867038a | 1104 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', |
11b56058 PM |
1105 | 'uploader': 'Philipp Hagemeister', |
1106 | 'uploader_id': 'phihag', | |
ec85ded8 | 1107 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', |
976ae3ea | 1108 | 'channel': 'Philipp Hagemeister', |
1109 | 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', | |
1110 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', | |
11b56058 | 1111 | 'upload_date': '20121002', |
976ae3ea | 1112 | 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22', |
11b56058 | 1113 | 'categories': ['Science & Technology'], |
3867038a | 1114 | 'tags': ['youtube-dl'], |
556dbe7f | 1115 | 'duration': 10, |
dbdaaa23 | 1116 | 'view_count': int, |
11b56058 | 1117 | 'like_count': int, |
976ae3ea | 1118 | 'availability': 'public', |
1119 | 'playable_in_embed': True, | |
1120 | 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg', | |
1121 | 'live_status': 'not_live', | |
1122 | 'age_limit': 0, | |
6c73052c | 1123 | 'channel_follower_count': int |
34a7de29 S |
1124 | }, |
1125 | 'params': { | |
1126 | 'skip_download': True, | |
1127 | }, | |
11b56058 | 1128 | }, |
dd27fd17 | 1129 | { |
2d3d2997 | 1130 | 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I', |
4bc3a23e PH |
1131 | 'note': '256k DASH audio (format 141) via DASH manifest', |
1132 | 'info_dict': { | |
1133 | 'id': 'a9LDPn-MO4I', | |
1134 | 'ext': 'm4a', | |
1135 | 'upload_date': '20121002', | |
1136 | 'uploader_id': '8KVIDEO', | |
ec85ded8 | 1137 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO', |
4bc3a23e PH |
1138 | 'description': '', |
1139 | 'uploader': '8KVIDEO', | |
1140 | 'title': 'UHDTV TEST 8K VIDEO.mp4' | |
4919603f | 1141 | }, |
4bc3a23e PH |
1142 | 'params': { |
1143 | 'youtube_include_dash_manifest': True, | |
1144 | 'format': '141', | |
4919603f | 1145 | }, |
de3c7fe0 | 1146 | 'skip': 'format 141 not served anymore', |
dd27fd17 | 1147 | }, |
8bdd16b4 | 1148 | # DASH manifest with encrypted signature |
1149 | { | |
1150 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', | |
1151 | 'info_dict': { | |
1152 | 'id': 'IB3lcPjvWLA', | |
1153 | 'ext': 'm4a', | |
1154 | 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson', | |
1155 | 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf', | |
1156 | 'duration': 244, | |
1157 | 'uploader': 'AfrojackVEVO', | |
1158 | 'uploader_id': 'AfrojackVEVO', | |
1159 | 'upload_date': '20131011', | |
cc2db878 | 1160 | 'abr': 129.495, |
976ae3ea | 1161 | 'like_count': int, |
1162 | 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg', | |
1163 | 'playable_in_embed': True, | |
1164 | 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg', | |
1165 | 'view_count': int, | |
1166 | 'track': 'The Spark', | |
1167 | 'live_status': 'not_live', | |
1168 | 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp', | |
1169 | 'channel': 'Afrojack', | |
1170 | 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO', | |
1171 | 'tags': 'count:19', | |
1172 | 'availability': 'public', | |
1173 | 'categories': ['Music'], | |
1174 | 'age_limit': 0, | |
1175 | 'alt_title': 'The Spark', | |
6c73052c | 1176 | 'channel_follower_count': int |
8bdd16b4 | 1177 | }, |
1178 | 'params': { | |
1179 | 'youtube_include_dash_manifest': True, | |
1180 | 'format': '141/bestaudio[ext=m4a]', | |
1181 | }, | |
1182 | }, | |
65c2fde2 | 1183 | # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000 |
c522adb1 | 1184 | { |
65c2fde2 | 1185 | 'note': 'Embed allowed age-gate video', |
2d3d2997 | 1186 | 'url': 'https://youtube.com/watch?v=HtVdAasjOgU', |
c522adb1 JMF |
1187 | 'info_dict': { |
1188 | 'id': 'HtVdAasjOgU', | |
1189 | 'ext': 'mp4', | |
1190 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
ec85ded8 | 1191 | 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', |
556dbe7f | 1192 | 'duration': 142, |
c522adb1 JMF |
1193 | 'uploader': 'The Witcher', |
1194 | 'uploader_id': 'WitcherGame', | |
ec85ded8 | 1195 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame', |
c522adb1 | 1196 | 'upload_date': '20140605', |
34952f09 | 1197 | 'age_limit': 18, |
976ae3ea | 1198 | 'categories': ['Gaming'], |
1199 | 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp', | |
1200 | 'availability': 'needs_auth', | |
1201 | 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg', | |
1202 | 'like_count': int, | |
1203 | 'channel': 'The Witcher', | |
1204 | 'live_status': 'not_live', | |
1205 | 'tags': 'count:17', | |
1206 | 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg', | |
1207 | 'playable_in_embed': True, | |
1208 | 'view_count': int, | |
6c73052c | 1209 | 'channel_follower_count': int |
c522adb1 JMF |
1210 | }, |
1211 | }, | |
65c2fde2 | 1212 | { |
1213 | 'note': 'Age-gate video with embed allowed in public site', | |
1214 | 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U', | |
1215 | 'info_dict': { | |
1216 | 'id': 'HsUATh_Nc2U', | |
1217 | 'ext': 'mp4', | |
1218 | 'title': 'Godzilla 2 (Official Video)', | |
1219 | 'description': 'md5:bf77e03fcae5529475e500129b05668a', | |
1220 | 'upload_date': '20200408', | |
1221 | 'uploader_id': 'FlyingKitty900', | |
1222 | 'uploader': 'FlyingKitty', | |
1223 | 'age_limit': 18, | |
976ae3ea | 1224 | 'availability': 'needs_auth', |
1225 | 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg', | |
1226 | 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900', | |
1227 | 'channel': 'FlyingKitty', | |
1228 | 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg', | |
1229 | 'view_count': int, | |
1230 | 'categories': ['Entertainment'], | |
1231 | 'live_status': 'not_live', | |
1232 | 'tags': ['Flyingkitty', 'godzilla 2'], | |
1233 | 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg', | |
1234 | 'like_count': int, | |
1235 | 'duration': 177, | |
1236 | 'playable_in_embed': True, | |
6c73052c | 1237 | 'channel_follower_count': int |
65c2fde2 | 1238 | }, |
1239 | }, | |
1240 | { | |
1241 | 'note': 'Age-gate video embedable only with clientScreen=EMBED', | |
1242 | 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg', | |
1243 | 'info_dict': { | |
1244 | 'id': 'Tq92D6wQ1mg', | |
1245 | 'title': '[MMD] Adios - EVERGLOW [+Motion DL]', | |
3619f78d | 1246 | 'ext': 'mp4', |
17322130 | 1247 | 'upload_date': '20191228', |
65c2fde2 | 1248 | 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ', |
1249 | 'uploader': 'Projekt Melody', | |
1250 | 'description': 'md5:17eccca93a786d51bc67646756894066', | |
1251 | 'age_limit': 18, | |
976ae3ea | 1252 | 'like_count': int, |
1253 | 'availability': 'needs_auth', | |
1254 | 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ', | |
1255 | 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ', | |
1256 | 'view_count': int, | |
1257 | 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp', | |
1258 | 'channel': 'Projekt Melody', | |
1259 | 'live_status': 'not_live', | |
1260 | 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'], | |
1261 | 'playable_in_embed': True, | |
1262 | 'categories': ['Entertainment'], | |
1263 | 'duration': 106, | |
1264 | 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ', | |
6c73052c | 1265 | 'channel_follower_count': int |
65c2fde2 | 1266 | }, |
1267 | }, | |
1268 | { | |
1269 | 'note': 'Non-Agegated non-embeddable video', | |
1270 | 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY', | |
1271 | 'info_dict': { | |
1272 | 'id': 'MeJVWBSsPAY', | |
1273 | 'ext': 'mp4', | |
1274 | 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)', | |
1275 | 'uploader': 'Herr Lurik', | |
1276 | 'uploader_id': 'st3in234', | |
1277 | 'description': 'Fan Video. Music & Lyrics by OOMPH!.', | |
1278 | 'upload_date': '20130730', | |
976ae3ea | 1279 | 'track': 'Such mich find mich', |
1280 | 'age_limit': 0, | |
1281 | 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'], | |
1282 | 'like_count': int, | |
1283 | 'playable_in_embed': False, | |
1284 | 'creator': 'OOMPH!', | |
1285 | 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg', | |
1286 | 'view_count': int, | |
1287 | 'alt_title': 'Such mich find mich', | |
1288 | 'duration': 210, | |
1289 | 'channel': 'Herr Lurik', | |
1290 | 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA', | |
1291 | 'categories': ['Music'], | |
1292 | 'availability': 'public', | |
1293 | 'uploader_url': 'http://www.youtube.com/user/st3in234', | |
1294 | 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA', | |
1295 | 'live_status': 'not_live', | |
1296 | 'artist': 'OOMPH!', | |
6c73052c | 1297 | 'channel_follower_count': int |
65c2fde2 | 1298 | }, |
1299 | }, | |
1300 | { | |
1301 | 'note': 'Non-bypassable age-gated video', | |
1302 | 'url': 'https://youtube.com/watch?v=Cr381pDsSsA', | |
1303 | 'only_matching': True, | |
1304 | }, | |
8bdd16b4 | 1305 | # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421) |
1306 | # YouTube Red ad is not captured for creator | |
1307 | { | |
1308 | 'url': '__2ABJjxzNo', | |
1309 | 'info_dict': { | |
1310 | 'id': '__2ABJjxzNo', | |
1311 | 'ext': 'mp4', | |
1312 | 'duration': 266, | |
1313 | 'upload_date': '20100430', | |
1314 | 'uploader_id': 'deadmau5', | |
1315 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5', | |
545cc85d | 1316 | 'creator': 'deadmau5', |
1317 | 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336', | |
8bdd16b4 | 1318 | 'uploader': 'deadmau5', |
1319 | 'title': 'Deadmau5 - Some Chords (HD)', | |
545cc85d | 1320 | 'alt_title': 'Some Chords', |
976ae3ea | 1321 | 'availability': 'public', |
1322 | 'tags': 'count:14', | |
1323 | 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ', | |
1324 | 'view_count': int, | |
1325 | 'live_status': 'not_live', | |
1326 | 'channel': 'deadmau5', | |
1327 | 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp', | |
1328 | 'like_count': int, | |
1329 | 'track': 'Some Chords', | |
1330 | 'artist': 'deadmau5', | |
1331 | 'playable_in_embed': True, | |
1332 | 'age_limit': 0, | |
1333 | 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ', | |
1334 | 'categories': ['Music'], | |
1335 | 'album': 'Some Chords', | |
6c73052c | 1336 | 'channel_follower_count': int |
8bdd16b4 | 1337 | }, |
1338 | 'expected_warnings': [ | |
1339 | 'DASH manifest missing', | |
1340 | ] | |
1341 | }, | |
067aa17e | 1342 | # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431) |
e52a40ab PH |
1343 | { |
1344 | 'url': 'lqQg6PlCWgI', | |
1345 | 'info_dict': { | |
1346 | 'id': 'lqQg6PlCWgI', | |
1347 | 'ext': 'mp4', | |
556dbe7f | 1348 | 'duration': 6085, |
90227264 | 1349 | 'upload_date': '20150827', |
cbe2bd91 | 1350 | 'uploader_id': 'olympic', |
ec85ded8 | 1351 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic', |
cbe2bd91 | 1352 | 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', |
11f9be09 | 1353 | 'uploader': 'Olympics', |
cbe2bd91 | 1354 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', |
976ae3ea | 1355 | 'like_count': int, |
1356 | 'release_timestamp': 1343767800, | |
1357 | 'playable_in_embed': True, | |
1358 | 'categories': ['Sports'], | |
1359 | 'release_date': '20120731', | |
1360 | 'channel': 'Olympics', | |
1361 | 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'], | |
1362 | 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q', | |
1363 | 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg', | |
1364 | 'age_limit': 0, | |
1365 | 'availability': 'public', | |
1366 | 'live_status': 'was_live', | |
1367 | 'view_count': int, | |
1368 | 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q', | |
6c73052c | 1369 | 'channel_follower_count': int |
cbe2bd91 PH |
1370 | }, |
1371 | 'params': { | |
1372 | 'skip_download': 'requires avconv', | |
e52a40ab | 1373 | } |
cbe2bd91 | 1374 | }, |
6271f1ca PH |
1375 | # Non-square pixels |
1376 | { | |
1377 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
1378 | 'info_dict': { | |
1379 | 'id': '_b-2C3KPAM0', | |
1380 | 'ext': 'mp4', | |
1381 | 'stretched_ratio': 16 / 9., | |
556dbe7f | 1382 | 'duration': 85, |
6271f1ca PH |
1383 | 'upload_date': '20110310', |
1384 | 'uploader_id': 'AllenMeow', | |
ec85ded8 | 1385 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow', |
6271f1ca | 1386 | '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 | 1387 | 'uploader': '孫ᄋᄅ', |
6271f1ca | 1388 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', |
976ae3ea | 1389 | 'playable_in_embed': True, |
1390 | 'channel': '孫ᄋᄅ', | |
1391 | 'age_limit': 0, | |
1392 | 'tags': 'count:11', | |
1393 | 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw', | |
1394 | 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw', | |
1395 | 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg', | |
1396 | 'view_count': int, | |
1397 | 'categories': ['People & Blogs'], | |
1398 | 'like_count': int, | |
1399 | 'live_status': 'not_live', | |
1400 | 'availability': 'unlisted', | |
6c73052c | 1401 | 'channel_follower_count': int |
6271f1ca | 1402 | }, |
06b491eb S |
1403 | }, |
1404 | # url_encoded_fmt_stream_map is empty string | |
1405 | { | |
1406 | 'url': 'qEJwOuvDf7I', | |
1407 | 'info_dict': { | |
1408 | 'id': 'qEJwOuvDf7I', | |
f57b7835 | 1409 | 'ext': 'webm', |
06b491eb S |
1410 | 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', |
1411 | 'description': '', | |
1412 | 'upload_date': '20150404', | |
1413 | 'uploader_id': 'spbelect', | |
1414 | 'uploader': 'Наблюдатели Петербурга', | |
1415 | }, | |
1416 | 'params': { | |
1417 | 'skip_download': 'requires avconv', | |
e323cf3f S |
1418 | }, |
1419 | 'skip': 'This live event has ended.', | |
06b491eb | 1420 | }, |
067aa17e | 1421 | # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097) |
da77d856 S |
1422 | { |
1423 | 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y', | |
1424 | 'info_dict': { | |
1425 | 'id': 'FIl7x6_3R5Y', | |
eb6793ba | 1426 | 'ext': 'webm', |
da77d856 S |
1427 | 'title': 'md5:7b81415841e02ecd4313668cde88737a', |
1428 | 'description': 'md5:116377fd2963b81ec4ce64b542173306', | |
556dbe7f | 1429 | 'duration': 220, |
da77d856 S |
1430 | 'upload_date': '20150625', |
1431 | 'uploader_id': 'dorappi2000', | |
ec85ded8 | 1432 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000', |
da77d856 | 1433 | 'uploader': 'dorappi2000', |
eb6793ba | 1434 | 'formats': 'mincount:31', |
da77d856 | 1435 | }, |
eb6793ba | 1436 | 'skip': 'not actual anymore', |
2ee8f5d8 | 1437 | }, |
8a1a26ce YCH |
1438 | # DASH manifest with segment_list |
1439 | { | |
1440 | 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8', | |
1441 | 'md5': '8ce563a1d667b599d21064e982ab9e31', | |
1442 | 'info_dict': { | |
1443 | 'id': 'CsmdDsKjzN8', | |
1444 | 'ext': 'mp4', | |
17ee98e1 | 1445 | 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510 |
8a1a26ce YCH |
1446 | 'uploader': 'Airtek', |
1447 | 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', | |
1448 | 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ', | |
1449 | 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', | |
1450 | }, | |
1451 | 'params': { | |
1452 | 'youtube_include_dash_manifest': True, | |
1453 | 'format': '135', # bestvideo | |
be49068d S |
1454 | }, |
1455 | 'skip': 'This live event has ended.', | |
2ee8f5d8 | 1456 | }, |
cf7e015f S |
1457 | { |
1458 | # Multifeed videos (multiple cameras), URL is for Main Camera | |
545cc85d | 1459 | 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg', |
cf7e015f | 1460 | 'info_dict': { |
545cc85d | 1461 | 'id': 'jvGDaLqkpTg', |
1462 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever', | |
1463 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
cf7e015f S |
1464 | }, |
1465 | 'playlist': [{ | |
1466 | 'info_dict': { | |
545cc85d | 1467 | 'id': 'jvGDaLqkpTg', |
cf7e015f | 1468 | 'ext': 'mp4', |
545cc85d | 1469 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)', |
1470 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1471 | 'duration': 10643, | |
1472 | 'upload_date': '20161111', | |
1473 | 'uploader': 'Team PGP', | |
1474 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1475 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
cf7e015f S |
1476 | }, |
1477 | }, { | |
1478 | 'info_dict': { | |
545cc85d | 1479 | 'id': '3AKt1R1aDnw', |
cf7e015f | 1480 | 'ext': 'mp4', |
545cc85d | 1481 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)', |
1482 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1483 | 'duration': 10991, | |
1484 | 'upload_date': '20161111', | |
1485 | 'uploader': 'Team PGP', | |
1486 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1487 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
cf7e015f S |
1488 | }, |
1489 | }, { | |
1490 | 'info_dict': { | |
545cc85d | 1491 | 'id': 'RtAMM00gpVc', |
cf7e015f | 1492 | 'ext': 'mp4', |
545cc85d | 1493 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)', |
1494 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1495 | 'duration': 10995, | |
1496 | 'upload_date': '20161111', | |
1497 | 'uploader': 'Team PGP', | |
1498 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1499 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
cf7e015f S |
1500 | }, |
1501 | }, { | |
1502 | 'info_dict': { | |
545cc85d | 1503 | 'id': '6N2fdlP3C5U', |
cf7e015f | 1504 | 'ext': 'mp4', |
545cc85d | 1505 | 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)', |
1506 | 'description': 'md5:e03b909557865076822aa169218d6a5d', | |
1507 | 'duration': 10990, | |
1508 | 'upload_date': '20161111', | |
1509 | 'uploader': 'Team PGP', | |
1510 | 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg', | |
1511 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg', | |
cf7e015f S |
1512 | }, |
1513 | }], | |
1514 | 'params': { | |
1515 | 'skip_download': True, | |
1516 | }, | |
65c2fde2 | 1517 | 'skip': 'Not multifeed anymore', |
cbaed4bb | 1518 | }, |
f9f49d87 | 1519 | { |
067aa17e | 1520 | # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536) |
f9f49d87 S |
1521 | 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo', |
1522 | 'info_dict': { | |
1523 | 'id': 'gVfLd0zydlo', | |
1524 | 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30', | |
1525 | }, | |
1526 | 'playlist_count': 2, | |
be49068d | 1527 | 'skip': 'Not multifeed anymore', |
f9f49d87 | 1528 | }, |
cbaed4bb | 1529 | { |
2d3d2997 | 1530 | 'url': 'https://vid.plus/FlRa-iH7PGw', |
cbaed4bb | 1531 | 'only_matching': True, |
0e49d9a6 | 1532 | }, |
6d4fc66b | 1533 | { |
2d3d2997 | 1534 | 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html', |
6d4fc66b S |
1535 | 'only_matching': True, |
1536 | }, | |
0e49d9a6 | 1537 | { |
067aa17e | 1538 | # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468) |
a8776b10 | 1539 | # Also tests cut-off URL expansion in video description (see |
067aa17e S |
1540 | # https://github.com/ytdl-org/youtube-dl/issues/1892, |
1541 | # https://github.com/ytdl-org/youtube-dl/issues/8164) | |
0e49d9a6 LL |
1542 | 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg', |
1543 | 'info_dict': { | |
1544 | 'id': 'lsguqyKfVQg', | |
1545 | 'ext': 'mp4', | |
1546 | 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21', | |
11f9be09 | 1547 | 'alt_title': 'Dark Walk', |
0e49d9a6 | 1548 | 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a', |
556dbe7f | 1549 | 'duration': 133, |
0e49d9a6 LL |
1550 | 'upload_date': '20151119', |
1551 | 'uploader_id': 'IronSoulElf', | |
ec85ded8 | 1552 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf', |
0e49d9a6 | 1553 | 'uploader': 'IronSoulElf', |
11f9be09 | 1554 | 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan', |
1555 | 'track': 'Dark Walk', | |
1556 | 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan', | |
92bc97d3 | 1557 | 'album': 'Position Music - Production Music Vol. 143 - Dark Walk', |
976ae3ea | 1558 | 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp', |
1559 | 'categories': ['Film & Animation'], | |
1560 | 'view_count': int, | |
1561 | 'live_status': 'not_live', | |
1562 | 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ', | |
1563 | 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ', | |
1564 | 'tags': 'count:13', | |
1565 | 'availability': 'public', | |
1566 | 'channel': 'IronSoulElf', | |
1567 | 'playable_in_embed': True, | |
1568 | 'like_count': int, | |
1569 | 'age_limit': 0, | |
6c73052c | 1570 | 'channel_follower_count': int |
0e49d9a6 LL |
1571 | }, |
1572 | 'params': { | |
1573 | 'skip_download': True, | |
1574 | }, | |
1575 | }, | |
61f92af1 | 1576 | { |
067aa17e | 1577 | # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468) |
61f92af1 S |
1578 | 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8', |
1579 | 'only_matching': True, | |
1580 | }, | |
313dfc45 LL |
1581 | { |
1582 | # Video with yt:stretch=17:0 | |
1583 | 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM', | |
1584 | 'info_dict': { | |
1585 | 'id': 'Q39EVAstoRM', | |
1586 | 'ext': 'mp4', | |
1587 | 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4', | |
1588 | 'description': 'md5:ee18a25c350637c8faff806845bddee9', | |
1589 | 'upload_date': '20151107', | |
1590 | 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA', | |
1591 | 'uploader': 'CH GAMER DROID', | |
1592 | }, | |
1593 | 'params': { | |
1594 | 'skip_download': True, | |
1595 | }, | |
be49068d | 1596 | 'skip': 'This video does not exist.', |
313dfc45 | 1597 | }, |
201c1459 | 1598 | { |
1599 | # Video with incomplete 'yt:stretch=16:' | |
1600 | 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI', | |
1601 | 'only_matching': True, | |
1602 | }, | |
7caf9830 S |
1603 | { |
1604 | # Video licensed under Creative Commons | |
1605 | 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA', | |
1606 | 'info_dict': { | |
1607 | 'id': 'M4gD1WSo5mA', | |
1608 | 'ext': 'mp4', | |
1609 | 'title': 'md5:e41008789470fc2533a3252216f1c1d1', | |
1610 | 'description': 'md5:a677553cf0840649b731a3024aeff4cc', | |
556dbe7f | 1611 | 'duration': 721, |
17322130 | 1612 | 'upload_date': '20150128', |
7caf9830 | 1613 | 'uploader_id': 'BerkmanCenter', |
ec85ded8 | 1614 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter', |
556dbe7f | 1615 | 'uploader': 'The Berkman Klein Center for Internet & Society', |
7caf9830 | 1616 | 'license': 'Creative Commons Attribution license (reuse allowed)', |
976ae3ea | 1617 | 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA', |
1618 | 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA', | |
1619 | 'like_count': int, | |
1620 | 'age_limit': 0, | |
1621 | 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'], | |
1622 | 'channel': 'The Berkman Klein Center for Internet & Society', | |
1623 | 'availability': 'public', | |
1624 | 'view_count': int, | |
1625 | 'categories': ['Education'], | |
1626 | 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp', | |
1627 | 'live_status': 'not_live', | |
1628 | 'playable_in_embed': True, | |
6c73052c | 1629 | 'channel_follower_count': int |
7caf9830 S |
1630 | }, |
1631 | 'params': { | |
1632 | 'skip_download': True, | |
1633 | }, | |
1634 | }, | |
fd050249 S |
1635 | { |
1636 | # Channel-like uploader_url | |
1637 | 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg', | |
1638 | 'info_dict': { | |
1639 | 'id': 'eQcmzGIKrzg', | |
1640 | 'ext': 'mp4', | |
1641 | 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders', | |
545cc85d | 1642 | 'description': 'md5:13a2503d7b5904ef4b223aa101628f39', |
556dbe7f | 1643 | 'duration': 4060, |
17322130 | 1644 | 'upload_date': '20151120', |
eb6793ba | 1645 | 'uploader': 'Bernie Sanders', |
fd050249 | 1646 | 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg', |
ec85ded8 | 1647 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg', |
fd050249 | 1648 | 'license': 'Creative Commons Attribution license (reuse allowed)', |
976ae3ea | 1649 | 'playable_in_embed': True, |
1650 | 'tags': 'count:12', | |
1651 | 'like_count': int, | |
1652 | 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg', | |
1653 | 'age_limit': 0, | |
1654 | 'availability': 'public', | |
1655 | 'categories': ['News & Politics'], | |
1656 | 'channel': 'Bernie Sanders', | |
1657 | 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp', | |
1658 | 'view_count': int, | |
1659 | 'live_status': 'not_live', | |
1660 | 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg', | |
6c73052c | 1661 | 'channel_follower_count': int |
fd050249 S |
1662 | }, |
1663 | 'params': { | |
1664 | 'skip_download': True, | |
1665 | }, | |
1666 | }, | |
040ac686 S |
1667 | { |
1668 | 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY', | |
1669 | 'only_matching': True, | |
7f29cf54 S |
1670 | }, |
1671 | { | |
067aa17e | 1672 | # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059) |
7f29cf54 S |
1673 | 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo', |
1674 | 'only_matching': True, | |
6496ccb4 S |
1675 | }, |
1676 | { | |
1677 | # Rental video preview | |
1678 | 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg', | |
1679 | 'info_dict': { | |
1680 | 'id': 'uGpuVWrhIzE', | |
1681 | 'ext': 'mp4', | |
1682 | 'title': 'Piku - Trailer', | |
1683 | 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb', | |
1684 | 'upload_date': '20150811', | |
1685 | 'uploader': 'FlixMatrix', | |
1686 | 'uploader_id': 'FlixMatrixKaravan', | |
ec85ded8 | 1687 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan', |
6496ccb4 S |
1688 | 'license': 'Standard YouTube License', |
1689 | }, | |
1690 | 'params': { | |
1691 | 'skip_download': True, | |
1692 | }, | |
eb6793ba | 1693 | 'skip': 'This video is not available.', |
022a5d66 | 1694 | }, |
12afdc2a S |
1695 | { |
1696 | # YouTube Red video with episode data | |
1697 | 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4', | |
1698 | 'info_dict': { | |
1699 | 'id': 'iqKdEhx-dD4', | |
1700 | 'ext': 'mp4', | |
1701 | 'title': 'Isolation - Mind Field (Ep 1)', | |
545cc85d | 1702 | 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd', |
556dbe7f | 1703 | 'duration': 2085, |
12afdc2a S |
1704 | 'upload_date': '20170118', |
1705 | 'uploader': 'Vsauce', | |
1706 | 'uploader_id': 'Vsauce', | |
1707 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce', | |
12afdc2a S |
1708 | 'series': 'Mind Field', |
1709 | 'season_number': 1, | |
1710 | 'episode_number': 1, | |
976ae3ea | 1711 | 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp', |
1712 | 'tags': 'count:12', | |
1713 | 'view_count': int, | |
1714 | 'availability': 'public', | |
1715 | 'age_limit': 0, | |
1716 | 'channel': 'Vsauce', | |
1717 | 'episode': 'Episode 1', | |
1718 | 'categories': ['Entertainment'], | |
1719 | 'season': 'Season 1', | |
1720 | 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA', | |
1721 | 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA', | |
1722 | 'like_count': int, | |
1723 | 'playable_in_embed': True, | |
1724 | 'live_status': 'not_live', | |
6c73052c | 1725 | 'channel_follower_count': int |
12afdc2a S |
1726 | }, |
1727 | 'params': { | |
1728 | 'skip_download': True, | |
1729 | }, | |
1730 | 'expected_warnings': [ | |
1731 | 'Skipping DASH manifest', | |
1732 | ], | |
1733 | }, | |
c7121fa7 S |
1734 | { |
1735 | # The following content has been identified by the YouTube community | |
1736 | # as inappropriate or offensive to some audiences. | |
1737 | 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI', | |
1738 | 'info_dict': { | |
1739 | 'id': '6SJNVb0GnPI', | |
1740 | 'ext': 'mp4', | |
1741 | 'title': 'Race Differences in Intelligence', | |
1742 | 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1', | |
1743 | 'duration': 965, | |
1744 | 'upload_date': '20140124', | |
1745 | 'uploader': 'New Century Foundation', | |
1746 | 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg', | |
1747 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg', | |
c7121fa7 S |
1748 | }, |
1749 | 'params': { | |
1750 | 'skip_download': True, | |
1751 | }, | |
545cc85d | 1752 | 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.', |
c7121fa7 | 1753 | }, |
022a5d66 S |
1754 | { |
1755 | # itag 212 | |
1756 | 'url': '1t24XAntNCY', | |
1757 | 'only_matching': True, | |
fd5c4aab S |
1758 | }, |
1759 | { | |
1760 | # geo restricted to JP | |
1761 | 'url': 'sJL6WA-aGkQ', | |
1762 | 'only_matching': True, | |
1763 | }, | |
cd5a74a2 S |
1764 | { |
1765 | 'url': 'https://invidio.us/watch?v=BaW_jenozKc', | |
1766 | 'only_matching': True, | |
1767 | }, | |
bc2ca1bb | 1768 | { |
1769 | 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc', | |
1770 | 'only_matching': True, | |
1771 | }, | |
1772 | { | |
1773 | # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m | |
1774 | 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA', | |
1775 | 'only_matching': True, | |
1776 | }, | |
825cd268 RA |
1777 | { |
1778 | # DRM protected | |
1779 | 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc', | |
1780 | 'only_matching': True, | |
4fe54c12 S |
1781 | }, |
1782 | { | |
1783 | # Video with unsupported adaptive stream type formats | |
1784 | 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U', | |
1785 | 'info_dict': { | |
1786 | 'id': 'Z4Vy8R84T1U', | |
1787 | 'ext': 'mp4', | |
1788 | 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta', | |
1789 | 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', | |
1790 | 'duration': 433, | |
1791 | 'upload_date': '20130923', | |
1792 | 'uploader': 'Amelia Putri Harwita', | |
1793 | 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q', | |
1794 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q', | |
1795 | 'formats': 'maxcount:10', | |
1796 | }, | |
1797 | 'params': { | |
1798 | 'skip_download': True, | |
1799 | 'youtube_include_dash_manifest': False, | |
1800 | }, | |
5429d6a9 | 1801 | 'skip': 'not actual anymore', |
5caabd3c | 1802 | }, |
1803 | { | |
822b9d9c | 1804 | # Youtube Music Auto-generated description |
5caabd3c | 1805 | 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs', |
1806 | 'info_dict': { | |
1807 | 'id': 'MgNrAu2pzNs', | |
1808 | 'ext': 'mp4', | |
1809 | 'title': 'Voyeur Girl', | |
1810 | 'description': 'md5:7ae382a65843d6df2685993e90a8628f', | |
1811 | 'upload_date': '20190312', | |
5429d6a9 S |
1812 | 'uploader': 'Stephen - Topic', |
1813 | 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA', | |
5caabd3c | 1814 | 'artist': 'Stephen', |
1815 | 'track': 'Voyeur Girl', | |
1816 | 'album': 'it\'s too much love to know my dear', | |
1817 | 'release_date': '20190313', | |
1818 | 'release_year': 2019, | |
976ae3ea | 1819 | 'alt_title': 'Voyeur Girl', |
1820 | 'view_count': int, | |
1821 | 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA', | |
1822 | 'playable_in_embed': True, | |
1823 | 'like_count': int, | |
1824 | 'categories': ['Music'], | |
1825 | 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA', | |
1826 | 'channel': 'Stephen', | |
1827 | 'availability': 'public', | |
1828 | 'creator': 'Stephen', | |
1829 | 'duration': 169, | |
1830 | 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp', | |
1831 | 'age_limit': 0, | |
1832 | 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA', | |
1833 | 'tags': 'count:11', | |
1834 | 'live_status': 'not_live', | |
6c73052c | 1835 | 'channel_follower_count': int |
5caabd3c | 1836 | }, |
1837 | 'params': { | |
1838 | 'skip_download': True, | |
1839 | }, | |
1840 | }, | |
66b48727 RA |
1841 | { |
1842 | 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q', | |
1843 | 'only_matching': True, | |
1844 | }, | |
011e75e6 S |
1845 | { |
1846 | # invalid -> valid video id redirection | |
1847 | 'url': 'DJztXj2GPfl', | |
1848 | 'info_dict': { | |
1849 | 'id': 'DJztXj2GPfk', | |
1850 | 'ext': 'mp4', | |
1851 | 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)', | |
1852 | 'description': 'md5:bf577a41da97918e94fa9798d9228825', | |
1853 | 'upload_date': '20090125', | |
1854 | 'uploader': 'Prochorowka', | |
1855 | 'uploader_id': 'Prochorowka', | |
1856 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka', | |
1857 | 'artist': 'Panjabi MC', | |
1858 | 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix', | |
1859 | 'album': 'Beware of the Boys (Mundian To Bach Ke)', | |
1860 | }, | |
1861 | 'params': { | |
1862 | 'skip_download': True, | |
1863 | }, | |
545cc85d | 1864 | 'skip': 'Video unavailable', |
ea74e00b DP |
1865 | }, |
1866 | { | |
1867 | # empty description results in an empty string | |
1868 | 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k', | |
1869 | 'info_dict': { | |
1870 | 'id': 'x41yOUIvK2k', | |
1871 | 'ext': 'mp4', | |
1872 | 'title': 'IMG 3456', | |
1873 | 'description': '', | |
1874 | 'upload_date': '20170613', | |
1875 | 'uploader_id': 'ElevageOrVert', | |
1876 | 'uploader': 'ElevageOrVert', | |
976ae3ea | 1877 | 'view_count': int, |
1878 | 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp', | |
1879 | 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert', | |
1880 | 'like_count': int, | |
1881 | 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw', | |
1882 | 'tags': [], | |
1883 | 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw', | |
1884 | 'availability': 'public', | |
1885 | 'age_limit': 0, | |
1886 | 'categories': ['Pets & Animals'], | |
1887 | 'duration': 7, | |
1888 | 'playable_in_embed': True, | |
1889 | 'live_status': 'not_live', | |
1890 | 'channel': 'ElevageOrVert', | |
6c73052c | 1891 | 'channel_follower_count': int |
ea74e00b DP |
1892 | }, |
1893 | 'params': { | |
1894 | 'skip_download': True, | |
1895 | }, | |
1896 | }, | |
a0566bbf | 1897 | { |
29f7c58a | 1898 | # with '};' inside yt initial data (see [1]) |
1899 | # see [2] for an example with '};' inside ytInitialPlayerResponse | |
1900 | # 1. https://github.com/ytdl-org/youtube-dl/issues/27093 | |
1901 | # 2. https://github.com/ytdl-org/youtube-dl/issues/27216 | |
a0566bbf | 1902 | 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no', |
1903 | 'info_dict': { | |
1904 | 'id': 'CHqg6qOn4no', | |
1905 | 'ext': 'mp4', | |
1906 | 'title': 'Part 77 Sort a list of simple types in c#', | |
1907 | 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc', | |
1908 | 'upload_date': '20130831', | |
1909 | 'uploader_id': 'kudvenkat', | |
1910 | 'uploader': 'kudvenkat', | |
976ae3ea | 1911 | 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q', |
1912 | 'like_count': int, | |
1913 | 'uploader_url': 'http://www.youtube.com/user/kudvenkat', | |
1914 | 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q', | |
1915 | 'live_status': 'not_live', | |
1916 | 'categories': ['Education'], | |
1917 | 'availability': 'public', | |
1918 | 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg', | |
1919 | 'tags': 'count:12', | |
1920 | 'playable_in_embed': True, | |
1921 | 'age_limit': 0, | |
1922 | 'view_count': int, | |
1923 | 'duration': 522, | |
1924 | 'channel': 'kudvenkat', | |
6c73052c | 1925 | 'channel_follower_count': int |
a0566bbf | 1926 | }, |
1927 | 'params': { | |
1928 | 'skip_download': True, | |
1929 | }, | |
1930 | }, | |
29f7c58a | 1931 | { |
1932 | # another example of '};' in ytInitialData | |
1933 | 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY', | |
1934 | 'only_matching': True, | |
1935 | }, | |
1936 | { | |
1937 | 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ', | |
1938 | 'only_matching': True, | |
1939 | }, | |
545cc85d | 1940 | { |
cc2db878 | 1941 | # https://github.com/ytdl-org/youtube-dl/pull/28094 |
1942 | 'url': 'OtqTfy26tG0', | |
1943 | 'info_dict': { | |
1944 | 'id': 'OtqTfy26tG0', | |
1945 | 'ext': 'mp4', | |
1946 | 'title': 'Burn Out', | |
1947 | 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131', | |
1948 | 'upload_date': '20141120', | |
1949 | 'uploader': 'The Cinematic Orchestra - Topic', | |
1950 | 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw', | |
1951 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw', | |
1952 | 'artist': 'The Cinematic Orchestra', | |
1953 | 'track': 'Burn Out', | |
1954 | 'album': 'Every Day', | |
976ae3ea | 1955 | 'like_count': int, |
1956 | 'live_status': 'not_live', | |
1957 | 'alt_title': 'Burn Out', | |
1958 | 'duration': 614, | |
1959 | 'age_limit': 0, | |
1960 | 'view_count': int, | |
1961 | 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw', | |
1962 | 'creator': 'The Cinematic Orchestra', | |
1963 | 'channel': 'The Cinematic Orchestra', | |
1964 | 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'], | |
1965 | 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw', | |
1966 | 'availability': 'public', | |
1967 | 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg', | |
1968 | 'categories': ['Music'], | |
1969 | 'playable_in_embed': True, | |
6c73052c | 1970 | 'channel_follower_count': int |
cc2db878 | 1971 | }, |
1972 | 'params': { | |
1973 | 'skip_download': True, | |
1974 | }, | |
545cc85d | 1975 | }, |
bc2ca1bb | 1976 | { |
1977 | # controversial video, only works with bpctr when authenticated with cookies | |
1978 | 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg', | |
1979 | 'only_matching': True, | |
1980 | }, | |
a1a7907b | 1981 | { |
1982 | # controversial video, requires bpctr/contentCheckOk | |
1983 | 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc', | |
1984 | 'info_dict': { | |
1985 | 'id': 'SZJvDhaSDnc', | |
1986 | 'ext': 'mp4', | |
1987 | 'title': 'San Diego teen commits suicide after bullying over embarrassing video', | |
1988 | 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ', | |
976ae3ea | 1989 | 'uploader': 'CBS Mornings', |
11f9be09 | 1990 | 'uploader_id': 'CBSThisMorning', |
a1a7907b | 1991 | 'upload_date': '20140716', |
976ae3ea | 1992 | 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7', |
1993 | 'duration': 170, | |
1994 | 'categories': ['News & Politics'], | |
1995 | 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning', | |
1996 | 'view_count': int, | |
1997 | 'channel': 'CBS Mornings', | |
1998 | 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'], | |
1999 | 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg', | |
2000 | 'age_limit': 18, | |
2001 | 'availability': 'needs_auth', | |
2002 | 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ', | |
2003 | 'like_count': int, | |
2004 | 'live_status': 'not_live', | |
2005 | 'playable_in_embed': True, | |
6c73052c | 2006 | 'channel_follower_count': int |
a1a7907b | 2007 | } |
2008 | }, | |
f7ad7160 | 2009 | { |
2010 | # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685 | |
2011 | 'url': 'cBvYw8_A0vQ', | |
2012 | 'info_dict': { | |
2013 | 'id': 'cBvYw8_A0vQ', | |
2014 | 'ext': 'mp4', | |
2015 | 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き', | |
2016 | 'description': 'md5:ea770e474b7cd6722b4c95b833c03630', | |
2017 | 'upload_date': '20201120', | |
2018 | 'uploader': 'Walk around Japan', | |
2019 | 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw', | |
2020 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw', | |
976ae3ea | 2021 | 'duration': 1456, |
2022 | 'categories': ['Travel & Events'], | |
2023 | 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw', | |
2024 | 'view_count': int, | |
2025 | 'channel': 'Walk around Japan', | |
2026 | 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'], | |
2027 | 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp', | |
2028 | 'age_limit': 0, | |
2029 | 'availability': 'public', | |
2030 | 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw', | |
2031 | 'live_status': 'not_live', | |
2032 | 'playable_in_embed': True, | |
6c73052c | 2033 | 'channel_follower_count': int |
f7ad7160 | 2034 | }, |
2035 | 'params': { | |
2036 | 'skip_download': True, | |
2037 | }, | |
0fb983f6 | 2038 | }, { |
2039 | # Has multiple audio streams | |
2040 | 'url': 'WaOKSUlf4TM', | |
2041 | 'only_matching': True | |
9297939e | 2042 | }, { |
2043 | # Requires Premium: has format 141 when requested using YTM url | |
2044 | 'url': 'https://music.youtube.com/watch?v=XclachpHxis', | |
2045 | 'only_matching': True | |
2046 | }, { | |
120916da | 2047 | # multiple subtitles with same lang_code |
2048 | 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug', | |
2049 | 'only_matching': True, | |
109dd3b2 | 2050 | }, { |
2051 | # Force use android client fallback | |
2052 | 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY', | |
2053 | 'info_dict': { | |
2054 | 'id': 'YOelRv7fMxY', | |
11f9be09 | 2055 | 'title': 'DIGGING A SECRET TUNNEL Part 1', |
109dd3b2 | 2056 | 'ext': '3gp', |
2057 | 'upload_date': '20210624', | |
2058 | 'channel_id': 'UCp68_FLety0O-n9QU6phsgw', | |
2059 | 'uploader': 'colinfurze', | |
11f9be09 | 2060 | 'uploader_id': 'colinfurze', |
109dd3b2 | 2061 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw', |
976ae3ea | 2062 | 'description': 'md5:5d5991195d599b56cd0c4148907eec50', |
2063 | 'duration': 596, | |
2064 | 'categories': ['Entertainment'], | |
2065 | 'uploader_url': 'http://www.youtube.com/user/colinfurze', | |
2066 | 'view_count': int, | |
2067 | 'channel': 'colinfurze', | |
2068 | 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'], | |
2069 | 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg', | |
2070 | 'age_limit': 0, | |
2071 | 'availability': 'public', | |
2072 | 'like_count': int, | |
2073 | 'live_status': 'not_live', | |
2074 | 'playable_in_embed': True, | |
6c73052c | 2075 | 'channel_follower_count': int |
109dd3b2 | 2076 | }, |
2077 | 'params': { | |
2078 | 'format': '17', # 3gp format available on android | |
2079 | 'extractor_args': {'youtube': {'player_client': ['android']}}, | |
2080 | }, | |
120916da | 2081 | }, |
109dd3b2 | 2082 | { |
2083 | # Skip download of additional client configs (remix client config in this case) | |
2084 | 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs', | |
2085 | 'only_matching': True, | |
2086 | 'params': { | |
2087 | 'extractor_args': {'youtube': {'player_skip': ['configs']}}, | |
2088 | }, | |
8fc54b12 | 2089 | }, { |
2090 | # shorts | |
2091 | 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY', | |
2092 | 'only_matching': True, | |
9222c381 | 2093 | }, { |
2094 | 'note': 'Storyboards', | |
2095 | 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8', | |
2096 | 'info_dict': { | |
2097 | 'id': '5KLPxDtMqe8', | |
2098 | 'ext': 'mhtml', | |
2099 | 'format_id': 'sb0', | |
2100 | 'title': 'Your Brain is Plastic', | |
2101 | 'uploader_id': 'scishow', | |
2102 | 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc', | |
2103 | 'upload_date': '20140324', | |
2104 | 'uploader': 'SciShow', | |
976ae3ea | 2105 | 'like_count': int, |
2106 | 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow', | |
2107 | 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow', | |
2108 | 'view_count': int, | |
2109 | 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg', | |
2110 | 'playable_in_embed': True, | |
2111 | 'tags': 'count:12', | |
2112 | 'uploader_url': 'http://www.youtube.com/user/scishow', | |
2113 | 'availability': 'public', | |
2114 | 'channel': 'SciShow', | |
2115 | 'live_status': 'not_live', | |
2116 | 'duration': 248, | |
2117 | 'categories': ['Education'], | |
2118 | 'age_limit': 0, | |
6c73052c | 2119 | 'channel_follower_count': int |
9222c381 | 2120 | }, 'params': {'format': 'mhtml', 'skip_download': True} |
992f9a73 | 2121 | }, { |
2122 | # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939) | |
2123 | 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4', | |
2124 | 'info_dict': { | |
2125 | 'id': '2NUZ8W2llS4', | |
2126 | 'ext': 'mp4', | |
2127 | 'title': 'The NP that test your phone performance 🙂', | |
2128 | 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d', | |
2129 | 'uploader': 'Leon Nguyen', | |
2130 | 'uploader_id': 'VNSXIII', | |
2131 | 'uploader_url': 'http://www.youtube.com/user/VNSXIII', | |
2132 | 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA', | |
2133 | 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA', | |
2134 | 'duration': 21, | |
2135 | 'view_count': int, | |
2136 | 'age_limit': 0, | |
2137 | 'categories': ['Gaming'], | |
2138 | 'tags': 'count:23', | |
2139 | 'playable_in_embed': True, | |
2140 | 'live_status': 'not_live', | |
2141 | 'upload_date': '20220103', | |
2142 | 'like_count': int, | |
2143 | 'availability': 'public', | |
2144 | 'channel': 'Leon Nguyen', | |
2145 | 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp', | |
2146 | 'channel_follower_count': int | |
2147 | } | |
2148 | }, { | |
2149 | # date text is premiered video, ensure upload date in UTC (published 1641172509) | |
2150 | 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM', | |
2151 | 'info_dict': { | |
2152 | 'id': 'mzZzzBU6lrM', | |
2153 | 'ext': 'mp4', | |
2154 | 'title': 'I Met GeorgeNotFound In Real Life...', | |
2155 | 'description': 'md5:cca98a355c7184e750f711f3a1b22c84', | |
2156 | 'uploader': 'Quackity', | |
2157 | 'uploader_id': 'QuackityHQ', | |
2158 | 'uploader_url': 'http://www.youtube.com/user/QuackityHQ', | |
2159 | 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q', | |
2160 | 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q', | |
2161 | 'duration': 955, | |
2162 | 'view_count': int, | |
2163 | 'age_limit': 0, | |
2164 | 'categories': ['Entertainment'], | |
2165 | 'tags': 'count:26', | |
2166 | 'playable_in_embed': True, | |
2167 | 'live_status': 'not_live', | |
2168 | 'release_timestamp': 1641172509, | |
2169 | 'release_date': '20220103', | |
2170 | 'upload_date': '20220103', | |
2171 | 'like_count': int, | |
2172 | 'availability': 'public', | |
2173 | 'channel': 'Quackity', | |
2174 | 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg', | |
2175 | 'channel_follower_count': int | |
2176 | } | |
2177 | }, | |
2178 | { # continuous livestream. Microformat upload date should be preferred. | |
2179 | # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27 | |
2180 | 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU', | |
2181 | 'info_dict': { | |
2182 | 'id': 'kgx4WGK0oNU', | |
2183 | '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}', | |
2184 | 'ext': 'mp4', | |
2185 | 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA', | |
2186 | 'availability': 'public', | |
2187 | 'age_limit': 0, | |
2188 | 'release_timestamp': 1637975704, | |
2189 | 'upload_date': '20210619', | |
2190 | 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA', | |
2191 | 'live_status': 'is_live', | |
2192 | 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg', | |
2193 | 'uploader': '阿鲍Abao', | |
2194 | 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA', | |
2195 | 'channel': 'Abao in Tokyo', | |
2196 | 'channel_follower_count': int, | |
2197 | 'release_date': '20211127', | |
2198 | 'tags': 'count:39', | |
2199 | 'categories': ['People & Blogs'], | |
2200 | 'like_count': int, | |
2201 | 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA', | |
2202 | 'view_count': int, | |
2203 | 'playable_in_embed': True, | |
2204 | 'description': 'md5:2ef1d002cad520f65825346e2084e49d', | |
2205 | }, | |
2206 | 'params': {'skip_download': True} | |
2207 | }, | |
2eb88d95 PH |
2208 | ] |
2209 | ||
201c1459 | 2210 | @classmethod |
2211 | def suitable(cls, url): | |
4dfbf869 | 2212 | from ..utils import parse_qs |
2213 | ||
201c1459 | 2214 | qs = parse_qs(url) |
2215 | if qs.get('list', [None])[0]: | |
2216 | return False | |
2217 | return super(YoutubeIE, cls).suitable(url) | |
2218 | ||
e0df6211 PH |
2219 | def __init__(self, *args, **kwargs): |
2220 | super(YoutubeIE, self).__init__(*args, **kwargs) | |
545cc85d | 2221 | self._code_cache = {} |
83799698 | 2222 | self._player_cache = {} |
e0df6211 | 2223 | |
adbc4ec4 | 2224 | def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data): |
adbc4ec4 THD |
2225 | lock = threading.Lock() |
2226 | ||
2227 | is_live = True | |
185bf310 | 2228 | start_time = time.time() |
adbc4ec4 THD |
2229 | formats = [f for f in formats if f.get('is_from_start')] |
2230 | ||
185bf310 | 2231 | def refetch_manifest(format_id, delay): |
2232 | nonlocal formats, start_time, is_live | |
2233 | if time.time() <= start_time + delay: | |
adbc4ec4 THD |
2234 | return |
2235 | ||
2236 | _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url) | |
2237 | video_details = traverse_obj( | |
2238 | prs, (..., 'videoDetails'), expected_type=dict, default=[]) | |
2239 | microformats = traverse_obj( | |
2240 | prs, (..., 'microformat', 'playerMicroformatRenderer'), | |
2241 | expected_type=dict, default=[]) | |
2242 | _, is_live, _, formats = self._list_formats(video_id, microformats, video_details, prs, player_url) | |
185bf310 | 2243 | start_time = time.time() |
adbc4ec4 | 2244 | |
185bf310 | 2245 | def mpd_feed(format_id, delay): |
adbc4ec4 THD |
2246 | """ |
2247 | @returns (manifest_url, manifest_stream_number, is_live) or None | |
2248 | """ | |
2249 | with lock: | |
185bf310 | 2250 | refetch_manifest(format_id, delay) |
adbc4ec4 THD |
2251 | |
2252 | f = next((f for f in formats if f['format_id'] == format_id), None) | |
2253 | if not f: | |
185bf310 | 2254 | if not is_live: |
2255 | self.to_screen(f'{video_id}: Video is no longer live') | |
2256 | else: | |
2257 | self.report_warning( | |
2258 | f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}') | |
adbc4ec4 THD |
2259 | return None |
2260 | return f['manifest_url'], f['manifest_stream_number'], is_live | |
2261 | ||
2262 | for f in formats: | |
a539f065 | 2263 | f['is_live'] = True |
adbc4ec4 THD |
2264 | f['protocol'] = 'http_dash_segments_generator' |
2265 | f['fragments'] = functools.partial( | |
2266 | self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed) | |
2267 | ||
2268 | def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx): | |
2269 | FETCH_SPAN, MAX_DURATION = 5, 432000 | |
2270 | ||
2271 | mpd_url, stream_number, is_live = None, None, True | |
2272 | ||
2273 | begin_index = 0 | |
2274 | download_start_time = ctx.get('start') or time.time() | |
2275 | ||
2276 | lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION | |
2277 | if lack_early_segments: | |
2278 | self.report_warning(bug_reports_message( | |
2279 | 'Starting download from the last 120 hours of the live stream since ' | |
2280 | 'YouTube does not have data before that. If you think this is wrong,'), only_once=True) | |
2281 | lack_early_segments = True | |
2282 | ||
2283 | known_idx, no_fragment_score, last_segment_url = begin_index, 0, None | |
2284 | fragments, fragment_base_url = None, None | |
2285 | ||
a539f065 | 2286 | def _extract_sequence_from_mpd(refresh_sequence, immediate): |
adbc4ec4 THD |
2287 | nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url |
2288 | # Obtain from MPD's maximum seq value | |
2289 | old_mpd_url = mpd_url | |
185bf310 | 2290 | last_error = ctx.pop('last_error', None) |
a539f065 | 2291 | expire_fast = immediate or last_error and isinstance(last_error, compat_HTTPError) and last_error.code == 403 |
185bf310 | 2292 | mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000) |
2293 | or (mpd_url, stream_number, False)) | |
2294 | if not refresh_sequence: | |
2295 | if expire_fast and not is_live: | |
2296 | return False, last_seq | |
2297 | elif old_mpd_url == mpd_url: | |
2298 | return True, last_seq | |
adbc4ec4 THD |
2299 | try: |
2300 | fmts, _ = self._extract_mpd_formats_and_subtitles( | |
2301 | mpd_url, None, note=False, errnote=False, fatal=False) | |
2302 | except ExtractorError: | |
2303 | fmts = None | |
2304 | if not fmts: | |
a539f065 | 2305 | no_fragment_score += 2 |
adbc4ec4 THD |
2306 | return False, last_seq |
2307 | fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number) | |
2308 | fragments = fmt_info['fragments'] | |
2309 | fragment_base_url = fmt_info['fragment_base_url'] | |
2310 | assert fragment_base_url | |
2311 | ||
2312 | _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1)) | |
2313 | return True, _last_seq | |
2314 | ||
2315 | while is_live: | |
2316 | fetch_time = time.time() | |
2317 | if no_fragment_score > 30: | |
2318 | return | |
2319 | if last_segment_url: | |
2320 | # Obtain from "X-Head-Seqnum" header value from each segment | |
2321 | try: | |
2322 | urlh = self._request_webpage( | |
2323 | last_segment_url, None, note=False, errnote=False, fatal=False) | |
2324 | except ExtractorError: | |
2325 | urlh = None | |
2326 | last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum'])) | |
2327 | if last_seq is None: | |
a539f065 | 2328 | no_fragment_score += 2 |
adbc4ec4 THD |
2329 | last_segment_url = None |
2330 | continue | |
2331 | else: | |
a539f065 LNO |
2332 | should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15) |
2333 | no_fragment_score += 2 | |
185bf310 | 2334 | if not should_continue: |
adbc4ec4 THD |
2335 | continue |
2336 | ||
2337 | if known_idx > last_seq: | |
2338 | last_segment_url = None | |
2339 | continue | |
2340 | ||
2341 | last_seq += 1 | |
2342 | ||
2343 | if begin_index < 0 and known_idx < 0: | |
2344 | # skip from the start when it's negative value | |
2345 | known_idx = last_seq + begin_index | |
2346 | if lack_early_segments: | |
2347 | known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration'])) | |
2348 | try: | |
2349 | for idx in range(known_idx, last_seq): | |
2350 | # do not update sequence here or you'll get skipped some part of it | |
a539f065 | 2351 | should_continue, _ = _extract_sequence_from_mpd(False, False) |
185bf310 | 2352 | if not should_continue: |
adbc4ec4 THD |
2353 | known_idx = idx - 1 |
2354 | raise ExtractorError('breaking out of outer loop') | |
2355 | last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx) | |
2356 | yield { | |
2357 | 'url': last_segment_url, | |
2358 | } | |
2359 | if known_idx == last_seq: | |
2360 | no_fragment_score += 5 | |
2361 | else: | |
2362 | no_fragment_score = 0 | |
2363 | known_idx = last_seq | |
2364 | except ExtractorError: | |
2365 | continue | |
2366 | ||
2367 | time.sleep(max(0, FETCH_SPAN + fetch_time - time.time())) | |
2368 | ||
b6de707d | 2369 | def _extract_player_url(self, *ytcfgs, webpage=None): |
2370 | player_url = traverse_obj( | |
2371 | ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'), | |
2372 | get_all=False, expected_type=compat_str) | |
11f9be09 | 2373 | if not player_url: |
b6de707d | 2374 | return |
60f393e4 | 2375 | return urljoin('https://www.youtube.com', player_url) |
109dd3b2 | 2376 | |
b6de707d | 2377 | def _download_player_url(self, video_id, fatal=False): |
2378 | res = self._download_webpage( | |
2379 | 'https://www.youtube.com/iframe_api', | |
2380 | note='Downloading iframe API JS', video_id=video_id, fatal=fatal) | |
2381 | if res: | |
2382 | player_version = self._search_regex( | |
2383 | r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal) | |
2384 | if player_version: | |
2385 | return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js' | |
2386 | ||
60064c53 PH |
2387 | def _signature_cache_id(self, example_sig): |
2388 | """ Return a string representation of a signature """ | |
78caa52a | 2389 | return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) |
60064c53 | 2390 | |
e40c758c S |
2391 | @classmethod |
2392 | def _extract_player_info(cls, player_url): | |
2393 | for player_re in cls._PLAYER_INFO_RE: | |
2394 | id_m = re.search(player_re, player_url) | |
2395 | if id_m: | |
2396 | break | |
2397 | else: | |
c081b35c | 2398 | raise ExtractorError('Cannot identify player %r' % player_url) |
545cc85d | 2399 | return id_m.group('id') |
e40c758c | 2400 | |
404f611f | 2401 | def _load_player(self, video_id, player_url, fatal=True): |
109dd3b2 | 2402 | player_id = self._extract_player_info(player_url) |
2403 | if player_id not in self._code_cache: | |
1276a43a | 2404 | code = self._download_webpage( |
109dd3b2 | 2405 | player_url, video_id, fatal=fatal, |
2406 | note='Downloading player ' + player_id, | |
2407 | errnote='Download of %s failed' % player_url) | |
1276a43a | 2408 | if code: |
2409 | self._code_cache[player_id] = code | |
404f611f | 2410 | return self._code_cache.get(player_id) |
109dd3b2 | 2411 | |
e40c758c | 2412 | def _extract_signature_function(self, video_id, player_url, example_sig): |
545cc85d | 2413 | player_id = self._extract_player_info(player_url) |
e0df6211 | 2414 | |
c4417ddb | 2415 | # Read from filesystem cache |
545cc85d | 2416 | func_id = 'js_%s_%s' % ( |
2417 | player_id, self._signature_cache_id(example_sig)) | |
c4417ddb | 2418 | assert os.path.basename(func_id) == func_id |
a0e07d31 | 2419 | |
69ea8ca4 | 2420 | cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) |
a0e07d31 | 2421 | if cache_spec is not None: |
78caa52a | 2422 | return lambda s: ''.join(s[i] for i in cache_spec) |
83799698 | 2423 | |
404f611f | 2424 | code = self._load_player(video_id, player_url) |
2425 | if code: | |
109dd3b2 | 2426 | res = self._parse_sig_js(code) |
e0df6211 | 2427 | |
109dd3b2 | 2428 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
2429 | cache_res = res(test_string) | |
2430 | cache_spec = [ord(c) for c in cache_res] | |
83799698 | 2431 | |
109dd3b2 | 2432 | self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) |
2433 | return res | |
83799698 | 2434 | |
60064c53 | 2435 | def _print_sig_code(self, func, example_sig): |
404f611f | 2436 | if not self.get_param('youtube_print_sig_code'): |
2437 | return | |
2438 | ||
edf3e38e PH |
2439 | def gen_sig_code(idxs): |
2440 | def _genslice(start, end, step): | |
78caa52a | 2441 | starts = '' if start == 0 else str(start) |
8bcc8756 | 2442 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' |
69ea8ca4 | 2443 | steps = '' if step == 1 else (':%d' % step) |
78caa52a | 2444 | return 's[%s%s%s]' % (starts, ends, steps) |
edf3e38e PH |
2445 | |
2446 | step = None | |
7af808a5 PH |
2447 | # Quelch pyflakes warnings - start will be set when step is set |
2448 | start = '(Never used)' | |
edf3e38e PH |
2449 | for i, prev in zip(idxs[1:], idxs[:-1]): |
2450 | if step is not None: | |
2451 | if i - prev == step: | |
2452 | continue | |
2453 | yield _genslice(start, prev, step) | |
2454 | step = None | |
2455 | continue | |
2456 | if i - prev in [-1, 1]: | |
2457 | step = i - prev | |
2458 | start = prev | |
2459 | continue | |
2460 | else: | |
78caa52a | 2461 | yield 's[%d]' % prev |
edf3e38e | 2462 | if step is None: |
78caa52a | 2463 | yield 's[%d]' % i |
edf3e38e PH |
2464 | else: |
2465 | yield _genslice(start, i, step) | |
2466 | ||
78caa52a | 2467 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
c705320f | 2468 | cache_res = func(test_string) |
edf3e38e | 2469 | cache_spec = [ord(c) for c in cache_res] |
78caa52a | 2470 | expr_code = ' + '.join(gen_sig_code(cache_spec)) |
60064c53 PH |
2471 | signature_id_tuple = '(%s)' % ( |
2472 | ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) | |
69ea8ca4 | 2473 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' |
78caa52a | 2474 | ' return %s\n') % (signature_id_tuple, expr_code) |
69ea8ca4 | 2475 | self.to_screen('Extracted signature function:\n' + code) |
edf3e38e | 2476 | |
e0df6211 PH |
2477 | def _parse_sig_js(self, jscode): |
2478 | funcname = self._search_regex( | |
abefc03f S |
2479 | (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', |
2480 | 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 |
2481 | r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)', |
2482 | r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)', | |
2483 | 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}\(a,\d+\)', | |
2484 | 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 | 2485 | r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', |
abefc03f S |
2486 | # Obsolete patterns |
2487 | r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
9a47fa35 | 2488 | r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(', |
abefc03f S |
2489 | r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(', |
2490 | r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2491 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2492 | r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2493 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
2494 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('), | |
3c90cc8b | 2495 | jscode, 'Initial JS player signature function name', group='sig') |
2b25cb5d PH |
2496 | |
2497 | jsi = JSInterpreter(jscode) | |
2498 | initial_function = jsi.extract_function(funcname) | |
e0df6211 PH |
2499 | return lambda s: initial_function([s]) |
2500 | ||
545cc85d | 2501 | def _decrypt_signature(self, s, video_id, player_url): |
257a2501 | 2502 | """Turn the encrypted s field into a working signature""" |
6b37f0be | 2503 | |
c8bf86d5 | 2504 | if player_url is None: |
69ea8ca4 | 2505 | raise ExtractorError('Cannot decrypt signature without player_url') |
920de7a2 | 2506 | |
c8bf86d5 | 2507 | try: |
62af3a0e | 2508 | player_id = (player_url, self._signature_cache_id(s)) |
c8bf86d5 PH |
2509 | if player_id not in self._player_cache: |
2510 | func = self._extract_signature_function( | |
60064c53 | 2511 | video_id, player_url, s |
c8bf86d5 PH |
2512 | ) |
2513 | self._player_cache[player_id] = func | |
2514 | func = self._player_cache[player_id] | |
404f611f | 2515 | self._print_sig_code(func, s) |
c8bf86d5 PH |
2516 | return func(s) |
2517 | except Exception as e: | |
404f611f | 2518 | raise ExtractorError('Signature extraction failed: ' + traceback.format_exc(), cause=e) |
2519 | ||
2520 | def _decrypt_nsig(self, s, video_id, player_url): | |
2521 | """Turn the encrypted n field into a working signature""" | |
2522 | if player_url is None: | |
2523 | raise ExtractorError('Cannot decrypt nsig without player_url') | |
60f393e4 | 2524 | player_url = urljoin('https://www.youtube.com', player_url) |
404f611f | 2525 | |
2526 | sig_id = ('nsig_value', s) | |
2527 | if sig_id in self._player_cache: | |
2528 | return self._player_cache[sig_id] | |
2529 | ||
2530 | try: | |
2531 | player_id = ('nsig', player_url) | |
2532 | if player_id not in self._player_cache: | |
2533 | self._player_cache[player_id] = self._extract_n_function(video_id, player_url) | |
2534 | func = self._player_cache[player_id] | |
2535 | self._player_cache[sig_id] = func(s) | |
2536 | self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}') | |
2537 | return self._player_cache[sig_id] | |
2538 | except Exception as e: | |
aa9369a2 | 2539 | raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id) |
404f611f | 2540 | |
2541 | def _extract_n_function_name(self, jscode): | |
48416bc4 | 2542 | nfunc, idx = self._search_regex( |
c571b3a6 | 2543 | r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)', |
48416bc4 | 2544 | jscode, 'Initial JS player n function name', group=('nfunc', 'idx')) |
2545 | if not idx: | |
2546 | return nfunc | |
2547 | return json.loads(js_to_json(self._search_regex( | |
a7d4acc0 | 2548 | rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode, |
48416bc4 | 2549 | f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)] |
404f611f | 2550 | |
2551 | def _extract_n_function(self, video_id, player_url): | |
2552 | player_id = self._extract_player_info(player_url) | |
2553 | func_code = self._downloader.cache.load('youtube-nsig', player_id) | |
2554 | ||
2555 | if func_code: | |
2556 | jsi = JSInterpreter(func_code) | |
2557 | else: | |
2558 | jscode = self._load_player(video_id, player_url) | |
2559 | funcname = self._extract_n_function_name(jscode) | |
2560 | jsi = JSInterpreter(jscode) | |
2561 | func_code = jsi.extract_function_code(funcname) | |
2562 | self._downloader.cache.store('youtube-nsig', player_id, func_code) | |
2563 | ||
2564 | if self.get_param('youtube_print_sig_code'): | |
2565 | self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n') | |
2566 | ||
2567 | return lambda s: jsi.extract_function_from_code(*func_code)([s]) | |
e0df6211 | 2568 | |
109dd3b2 | 2569 | def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False): |
2570 | """ | |
2571 | Extract signatureTimestamp (sts) | |
2572 | Required to tell API what sig/player version is in use. | |
2573 | """ | |
2574 | sts = None | |
2575 | if isinstance(ytcfg, dict): | |
2576 | sts = int_or_none(ytcfg.get('STS')) | |
2577 | ||
2578 | if not sts: | |
2579 | # Attempt to extract from player | |
2580 | if player_url is None: | |
2581 | error_msg = 'Cannot extract signature timestamp without player_url.' | |
2582 | if fatal: | |
2583 | raise ExtractorError(error_msg) | |
2584 | self.report_warning(error_msg) | |
2585 | return | |
404f611f | 2586 | code = self._load_player(video_id, player_url, fatal=fatal) |
2587 | if code: | |
109dd3b2 | 2588 | sts = int_or_none(self._search_regex( |
2589 | r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code, | |
2590 | 'JS player signature timestamp', group='sts', fatal=fatal)) | |
2591 | return sts | |
2592 | ||
11f9be09 | 2593 | def _mark_watched(self, video_id, player_responses): |
9222c381 | 2594 | playback_url = get_first( |
2595 | player_responses, ('playbackTracking', 'videostatsPlaybackUrl', 'baseUrl'), | |
2596 | expected_type=url_or_none) | |
d77ab8e2 | 2597 | if not playback_url: |
352d63fd | 2598 | self.report_warning('Unable to mark watched') |
d77ab8e2 S |
2599 | return |
2600 | parsed_playback_url = compat_urlparse.urlparse(playback_url) | |
2601 | qs = compat_urlparse.parse_qs(parsed_playback_url.query) | |
2602 | ||
2603 | # cpn generation algorithm is reverse engineered from base.js. | |
2604 | # In fact it works even with dummy cpn. | |
2605 | CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_' | |
2606 | cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))) | |
2607 | ||
2608 | qs.update({ | |
2609 | 'ver': ['2'], | |
2610 | 'cpn': [cpn], | |
2611 | }) | |
2612 | playback_url = compat_urlparse.urlunparse( | |
15707c7e | 2613 | parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True))) |
d77ab8e2 S |
2614 | |
2615 | self._download_webpage( | |
2616 | playback_url, video_id, 'Marking watched', | |
2617 | 'Unable to mark watched', fatal=False) | |
2618 | ||
66c9fa36 S |
2619 | @staticmethod |
2620 | def _extract_urls(webpage): | |
2621 | # Embedded YouTube player | |
2622 | entries = [ | |
2623 | unescapeHTML(mobj.group('url')) | |
2624 | for mobj in re.finditer(r'''(?x) | |
2625 | (?: | |
2626 | <iframe[^>]+?src=| | |
2627 | data-video-url=| | |
2628 | <embed[^>]+?src=| | |
2629 | embedSWF\(?:\s*| | |
2630 | <object[^>]+data=| | |
2631 | new\s+SWFObject\( | |
2632 | ) | |
2633 | (["\']) | |
2634 | (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ | |
f2332f18 | 2635 | (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?) |
66c9fa36 S |
2636 | \1''', webpage)] |
2637 | ||
2638 | # lazyYT YouTube embed | |
2639 | entries.extend(list(map( | |
2640 | unescapeHTML, | |
2641 | re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)))) | |
2642 | ||
2643 | # Wordpress "YouTube Video Importer" plugin | |
2644 | matches = re.findall(r'''(?x)<div[^>]+ | |
2645 | class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+ | |
2646 | data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage) | |
2647 | entries.extend(m[-1] for m in matches) | |
2648 | ||
2649 | return entries | |
2650 | ||
2651 | @staticmethod | |
2652 | def _extract_url(webpage): | |
2653 | urls = YoutubeIE._extract_urls(webpage) | |
2654 | return urls[0] if urls else None | |
2655 | ||
97665381 PH |
2656 | @classmethod |
2657 | def extract_id(cls, url): | |
2658 | mobj = re.match(cls._VALID_URL, url, re.VERBOSE) | |
c5e8d7af | 2659 | if mobj is None: |
69ea8ca4 | 2660 | raise ExtractorError('Invalid URL: %s' % url) |
5ad28e7f | 2661 | return mobj.group('id') |
c5e8d7af | 2662 | |
7c365c21 | 2663 | def _extract_chapters_from_json(self, data, duration): |
2664 | chapter_list = traverse_obj( | |
2665 | data, ( | |
2666 | 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer', | |
2667 | 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters' | |
2668 | ), expected_type=list) | |
2669 | ||
2670 | return self._extract_chapters( | |
2671 | chapter_list, | |
2672 | chapter_time=lambda chapter: float_or_none( | |
2673 | traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000), | |
2674 | chapter_title=lambda chapter: traverse_obj( | |
2675 | chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str), | |
2676 | duration=duration) | |
2677 | ||
2678 | def _extract_chapters_from_engagement_panel(self, data, duration): | |
2679 | content_list = traverse_obj( | |
8bdd16b4 | 2680 | data, |
7c365c21 | 2681 | ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'), |
da503b7a | 2682 | expected_type=list, default=[]) |
052e1350 | 2683 | chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription')) |
2684 | chapter_title = lambda chapter: self._get_text(chapter, 'title') | |
7c365c21 | 2685 | |
2686 | return next(( | |
2687 | filter(None, ( | |
2688 | self._extract_chapters( | |
2689 | traverse_obj(contents, (..., 'macroMarkersListItemRenderer')), | |
2690 | chapter_time, chapter_title, duration) | |
2691 | for contents in content_list | |
2692 | ))), []) | |
2693 | ||
2694 | def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration): | |
84213ea8 | 2695 | chapters = [] |
7c365c21 | 2696 | last_chapter = {'start_time': 0} |
2697 | for idx, chapter in enumerate(chapter_list or []): | |
2698 | title = chapter_title(chapter) | |
84213ea8 S |
2699 | start_time = chapter_time(chapter) |
2700 | if start_time is None: | |
2701 | continue | |
7c365c21 | 2702 | last_chapter['end_time'] = start_time |
2703 | if start_time < last_chapter['start_time']: | |
2704 | if idx == 1: | |
2705 | chapters.pop() | |
2706 | self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title']) | |
2707 | else: | |
2708 | self.report_warning(f'Invalid start time for chapter "{title}"') | |
2709 | continue | |
2710 | last_chapter = {'start_time': start_time, 'title': title} | |
2711 | chapters.append(last_chapter) | |
2712 | last_chapter['end_time'] = duration | |
84213ea8 S |
2713 | return chapters |
2714 | ||
545cc85d | 2715 | def _extract_yt_initial_variable(self, webpage, regex, video_id, name): |
2716 | return self._parse_json(self._search_regex( | |
2717 | (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE), | |
2718 | regex), webpage, name, default='{}'), video_id, fatal=False) | |
84213ea8 | 2719 | |
a1c5d2ca M |
2720 | def _extract_comment(self, comment_renderer, parent=None): |
2721 | comment_id = comment_renderer.get('commentId') | |
2722 | if not comment_id: | |
2723 | return | |
fe93e2c4 | 2724 | |
052e1350 | 2725 | text = self._get_text(comment_renderer, 'contentText') |
fe93e2c4 | 2726 | |
49bd8c66 | 2727 | # note: timestamp is an estimate calculated from the current time and time_text |
f3aa3c3f | 2728 | timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText') |
052e1350 | 2729 | author = self._get_text(comment_renderer, 'authorText') |
a1c5d2ca M |
2730 | author_id = try_get(comment_renderer, |
2731 | lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str) | |
fe93e2c4 | 2732 | |
49bd8c66 | 2733 | votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'], |
2734 | lambda x: x['likeCount']), compat_str)) or 0 | |
a1c5d2ca M |
2735 | author_thumbnail = try_get(comment_renderer, |
2736 | lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str) | |
2737 | ||
2738 | author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool) | |
97524332 | 2739 | is_favorited = 'creatorHeart' in (try_get( |
2740 | comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {}) | |
a1c5d2ca M |
2741 | return { |
2742 | 'id': comment_id, | |
2743 | 'text': text, | |
d92f5d5a | 2744 | 'timestamp': timestamp, |
a1c5d2ca M |
2745 | 'time_text': time_text, |
2746 | 'like_count': votes, | |
97524332 | 2747 | 'is_favorited': is_favorited, |
a1c5d2ca M |
2748 | 'author': author, |
2749 | 'author_id': author_id, | |
2750 | 'author_thumbnail': author_thumbnail, | |
2751 | 'author_is_uploader': author_is_uploader, | |
2752 | 'parent': parent or 'root' | |
2753 | } | |
2754 | ||
46383212 | 2755 | def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None): |
2756 | ||
2757 | get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0] | |
2d6659b9 | 2758 | |
2759 | def extract_header(contents): | |
2d6659b9 | 2760 | _continuation = None |
2761 | for content in contents: | |
46383212 | 2762 | comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer') |
f0d785d3 | 2763 | expected_comment_count = self._get_count( |
2764 | comments_header_renderer, 'countText', 'commentsCount') | |
fe93e2c4 | 2765 | |
2d6659b9 | 2766 | if expected_comment_count: |
46383212 | 2767 | tracker['est_total'] = expected_comment_count |
2768 | self.to_screen(f'Downloading ~{expected_comment_count} comments') | |
2769 | comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top | |
2d6659b9 | 2770 | |
2771 | sort_menu_item = try_get( | |
2772 | comments_header_renderer, | |
2773 | lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {} | |
2774 | sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {} | |
2775 | ||
2776 | _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item) | |
2777 | if not _continuation: | |
2778 | continue | |
2779 | ||
46383212 | 2780 | sort_text = str_or_none(sort_menu_item.get('title')) |
2781 | if not sort_text: | |
2d6659b9 | 2782 | sort_text = 'top comments' if comment_sort_index == 0 else 'newest first' |
46383212 | 2783 | self.to_screen('Sorting comments by %s' % sort_text.lower()) |
2d6659b9 | 2784 | break |
a2160aa4 | 2785 | return _continuation |
a1c5d2ca | 2786 | |
2d6659b9 | 2787 | def extract_thread(contents): |
a1c5d2ca | 2788 | if not parent: |
46383212 | 2789 | tracker['current_page_thread'] = 0 |
a1c5d2ca | 2790 | for content in contents: |
46383212 | 2791 | if not parent and tracker['total_parent_comments'] >= max_parents: |
2792 | yield | |
a1c5d2ca | 2793 | comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer']) |
46383212 | 2794 | comment_renderer = get_first( |
2795 | (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]], | |
2796 | expected_type=dict, default={}) | |
a1c5d2ca | 2797 | |
a1c5d2ca M |
2798 | comment = self._extract_comment(comment_renderer, parent) |
2799 | if not comment: | |
2800 | continue | |
46383212 | 2801 | |
2802 | tracker['running_total'] += 1 | |
2803 | tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1 | |
a1c5d2ca | 2804 | yield comment |
46383212 | 2805 | |
a1c5d2ca M |
2806 | # Attempt to get the replies |
2807 | comment_replies_renderer = try_get( | |
2808 | comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict) | |
2809 | ||
2810 | if comment_replies_renderer: | |
46383212 | 2811 | tracker['current_page_thread'] += 1 |
a1c5d2ca | 2812 | comment_entries_iter = self._comment_entries( |
99e9e001 | 2813 | comment_replies_renderer, ytcfg, video_id, |
46383212 | 2814 | parent=comment.get('id'), tracker=tracker) |
2815 | for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))): | |
a1c5d2ca M |
2816 | yield reply_comment |
2817 | ||
46383212 | 2818 | # Keeps track of counts across recursive calls |
2819 | if not tracker: | |
2820 | tracker = dict( | |
2821 | running_total=0, | |
2822 | est_total=0, | |
2823 | current_page_thread=0, | |
2824 | total_parent_comments=0, | |
2825 | total_reply_comments=0) | |
2826 | ||
2827 | # TODO: Deprecated | |
2d6659b9 | 2828 | # YouTube comments have a max depth of 2 |
46383212 | 2829 | max_depth = int_or_none(get_single_config_arg('max_comment_depth')) |
2830 | if max_depth: | |
2831 | self._downloader.deprecation_warning( | |
2832 | '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.') | |
2d6659b9 | 2833 | if max_depth == 1 and parent: |
2834 | return | |
a1c5d2ca | 2835 | |
46383212 | 2836 | max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map( |
2837 | lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4) | |
2d6659b9 | 2838 | |
46383212 | 2839 | continuation = self._extract_continuation(root_continuation_data) |
aae16f6e | 2840 | message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1) |
2841 | if message and not parent: | |
2842 | self.report_warning(message, video_id=video_id) | |
2843 | ||
46383212 | 2844 | response = None |
2d6659b9 | 2845 | is_first_continuation = parent is None |
a1c5d2ca M |
2846 | |
2847 | for page_num in itertools.count(0): | |
2848 | if not continuation: | |
2849 | break | |
46383212 | 2850 | headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response)) |
2851 | comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})" | |
2d6659b9 | 2852 | if page_num == 0: |
2853 | if is_first_continuation: | |
2854 | note_prefix = 'Downloading comment section API JSON' | |
a1c5d2ca | 2855 | else: |
2d6659b9 | 2856 | note_prefix = ' Downloading comment API JSON reply thread %d %s' % ( |
46383212 | 2857 | tracker['current_page_thread'], comment_prog_str) |
2d6659b9 | 2858 | else: |
2859 | note_prefix = '%sDownloading comment%s API JSON page %d %s' % ( | |
2860 | ' ' if parent else '', ' replies' if parent else '', | |
2861 | page_num, comment_prog_str) | |
2862 | ||
2863 | response = self._extract_response( | |
fe93e2c4 | 2864 | item_id=None, query=continuation, |
2d6659b9 | 2865 | ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix, |
46383212 | 2866 | check_get_keys='onResponseReceivedEndpoints') |
a1c5d2ca | 2867 | |
46383212 | 2868 | continuation_contents = traverse_obj( |
2869 | response, 'onResponseReceivedEndpoints', expected_type=list, default=[]) | |
a1c5d2ca | 2870 | |
2d6659b9 | 2871 | continuation = None |
46383212 | 2872 | for continuation_section in continuation_contents: |
2873 | continuation_items = traverse_obj( | |
2874 | continuation_section, | |
2875 | (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'), | |
2876 | get_all=False, expected_type=list) or [] | |
2877 | if is_first_continuation: | |
2878 | continuation = extract_header(continuation_items) | |
2879 | is_first_continuation = False | |
2d6659b9 | 2880 | if continuation: |
a1c5d2ca | 2881 | break |
46383212 | 2882 | continue |
a1c5d2ca | 2883 | |
46383212 | 2884 | for entry in extract_thread(continuation_items): |
2885 | if not entry: | |
2886 | return | |
2887 | yield entry | |
2888 | continuation = self._extract_continuation({'contents': continuation_items}) | |
2889 | if continuation: | |
2d6659b9 | 2890 | break |
a1c5d2ca | 2891 | |
a2160aa4 | 2892 | def _get_comments(self, ytcfg, video_id, contents, webpage): |
a1c5d2ca | 2893 | """Entry for comment extraction""" |
2d6659b9 | 2894 | def _real_comment_extract(contents): |
aae16f6e | 2895 | renderer = next(( |
2896 | item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={}) | |
2897 | if item.get('sectionIdentifier') == 'comment-item-section'), None) | |
2898 | yield from self._comment_entries(renderer, ytcfg, video_id) | |
99e9e001 | 2899 | |
a2160aa4 | 2900 | max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0]) |
a2160aa4 | 2901 | return itertools.islice(_real_comment_extract(contents), 0, max_comments) |
a1c5d2ca | 2902 | |
109dd3b2 | 2903 | @staticmethod |
99e9e001 | 2904 | def _get_checkok_params(): |
2905 | return {'contentCheckOk': True, 'racyCheckOk': True} | |
2906 | ||
2907 | @classmethod | |
2908 | def _generate_player_context(cls, sts=None): | |
109dd3b2 | 2909 | context = { |
2910 | 'html5Preference': 'HTML5_PREF_WANTS', | |
2911 | } | |
2912 | if sts is not None: | |
2913 | context['signatureTimestamp'] = sts | |
2914 | return { | |
2915 | 'playbackContext': { | |
2916 | 'contentPlaybackContext': context | |
a1a7907b | 2917 | }, |
99e9e001 | 2918 | **cls._get_checkok_params() |
109dd3b2 | 2919 | } |
2920 | ||
e7e94f2a D |
2921 | @staticmethod |
2922 | def _is_agegated(player_response): | |
2923 | if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')): | |
9275f62c | 2924 | return True |
e7e94f2a D |
2925 | |
2926 | reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[]) | |
2927 | AGE_GATE_REASONS = ( | |
2928 | 'confirm your age', 'age-restricted', 'inappropriate', # reason | |
2929 | 'age_verification_required', 'age_check_required', # status | |
2930 | ) | |
2931 | return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons) | |
2932 | ||
2933 | @staticmethod | |
2934 | def _is_unplayable(player_response): | |
2935 | return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE' | |
9275f62c | 2936 | |
99e9e001 | 2937 | def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr): |
109dd3b2 | 2938 | |
11f9be09 | 2939 | session_index = self._extract_session_index(player_ytcfg, master_ytcfg) |
2940 | syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr) | |
b6de707d | 2941 | sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None |
11f9be09 | 2942 | headers = self.generate_api_headers( |
99e9e001 | 2943 | ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client) |
9297939e | 2944 | |
11f9be09 | 2945 | yt_query = {'videoId': video_id} |
2946 | yt_query.update(self._generate_player_context(sts)) | |
2947 | return self._extract_response( | |
2948 | item_id=video_id, ep='player', query=yt_query, | |
379e44ed | 2949 | ytcfg=player_ytcfg, headers=headers, fatal=True, |
000c15a4 | 2950 | default_client=client, |
11f9be09 | 2951 | note='Downloading %s player API JSON' % client.replace('_', ' ').strip() |
2952 | ) or None | |
2953 | ||
11f9be09 | 2954 | def _get_requested_clients(self, url, smuggled_data): |
b4c055ba | 2955 | requested_clients = [] |
d0d012d4 | 2956 | default = ['android', 'web'] |
000c15a4 | 2957 | allowed_clients = sorted( |
2958 | [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'], | |
2959 | key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True) | |
b4c055ba | 2960 | for client in self._configuration_arg('player_client'): |
2961 | if client in allowed_clients: | |
2962 | requested_clients.append(client) | |
d0d012d4 | 2963 | elif client == 'default': |
2964 | requested_clients.extend(default) | |
b4c055ba | 2965 | elif client == 'all': |
2966 | requested_clients.extend(allowed_clients) | |
2967 | else: | |
2968 | self.report_warning(f'Skipping unsupported client {client}') | |
11f9be09 | 2969 | if not requested_clients: |
d0d012d4 | 2970 | requested_clients = default |
cf7e015f | 2971 | |
11f9be09 | 2972 | if smuggled_data.get('is_music_url') or self.is_music_url(url): |
2973 | requested_clients.extend( | |
e7e94f2a | 2974 | f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS) |
dbdaaa23 | 2975 | |
11f9be09 | 2976 | return orderedSet(requested_clients) |
cf7e015f | 2977 | |
99e9e001 | 2978 | def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg): |
11f9be09 | 2979 | initial_pr = None |
2980 | if webpage: | |
2981 | initial_pr = self._extract_yt_initial_variable( | |
2982 | webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE, | |
2983 | video_id, 'initial player response') | |
6b09401b | 2984 | |
ae729626 | 2985 | all_clients = set(clients) |
c0bc527b | 2986 | clients = clients[::-1] |
b6de707d | 2987 | prs = [] |
e7e94f2a | 2988 | |
ae729626 | 2989 | def append_client(*client_names): |
e7870111 | 2990 | """ Append the first client name that exists but not already used """ |
ae729626 | 2991 | for client_name in client_names: |
e7870111 D |
2992 | actual_client = _split_innertube_client(client_name)[0] |
2993 | if actual_client in INNERTUBE_CLIENTS: | |
2994 | if actual_client not in all_clients: | |
ae729626 | 2995 | clients.append(client_name) |
e7870111 D |
2996 | all_clients.add(actual_client) |
2997 | return | |
e7e94f2a | 2998 | |
379e44ed | 2999 | # Android player_response does not have microFormats which are needed for |
3000 | # extraction of some data. So we return the initial_pr with formats | |
3001 | # stripped out even if not requested by the user | |
3002 | # See: https://github.com/yt-dlp/yt-dlp/issues/501 | |
379e44ed | 3003 | if initial_pr: |
3004 | pr = dict(initial_pr) | |
3005 | pr['streamingData'] = None | |
b6de707d | 3006 | prs.append(pr) |
379e44ed | 3007 | |
3008 | last_error = None | |
b6de707d | 3009 | tried_iframe_fallback = False |
3010 | player_url = None | |
c0bc527b | 3011 | while clients: |
e7870111 | 3012 | client, base_client, variant = _split_innertube_client(clients.pop()) |
11f9be09 | 3013 | player_ytcfg = master_ytcfg if client == 'web' else {} |
a25bca9f | 3014 | if 'configs' not in self._configuration_arg('player_skip') and client != 'web': |
3015 | player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg | |
c0bc527b | 3016 | |
b6de707d | 3017 | player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage) |
3018 | require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER') | |
3019 | if 'js' in self._configuration_arg('player_skip'): | |
3020 | require_js_player = False | |
3021 | player_url = None | |
3022 | ||
3023 | if not player_url and not tried_iframe_fallback and require_js_player: | |
3024 | player_url = self._download_player_url(video_id) | |
3025 | tried_iframe_fallback = True | |
3026 | ||
379e44ed | 3027 | try: |
3028 | pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response( | |
99e9e001 | 3029 | client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr) |
379e44ed | 3030 | except ExtractorError as e: |
3031 | if last_error: | |
3032 | self.report_warning(last_error) | |
3033 | last_error = e | |
3034 | continue | |
3035 | ||
11f9be09 | 3036 | if pr: |
b6de707d | 3037 | prs.append(pr) |
c0bc527b | 3038 | |
e7e94f2a | 3039 | # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in |
e7870111 D |
3040 | if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated: |
3041 | append_client(f'{base_client}_creator') | |
e7e94f2a | 3042 | elif self._is_agegated(pr): |
e7870111 D |
3043 | if variant == 'tv_embedded': |
3044 | append_client(f'{base_client}_embedded') | |
3045 | elif not variant: | |
3046 | append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded') | |
c0bc527b | 3047 | |
379e44ed | 3048 | if last_error: |
b6de707d | 3049 | if not len(prs): |
379e44ed | 3050 | raise last_error |
3051 | self.report_warning(last_error) | |
b6de707d | 3052 | return prs, player_url |
11f9be09 | 3053 | |
a1b2d843 | 3054 | def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration): |
a0bb6ce5 | 3055 | itags, stream_ids = {}, [] |
2a9c6dcd | 3056 | itag_qualities, res_qualities = {}, {} |
d3fc8074 | 3057 | q = qualities([ |
2a9c6dcd | 3058 | # Normally tiny is the smallest video-only formats. But |
3059 | # audio-only formats with unknown quality may get tagged as tiny | |
3060 | 'tiny', | |
3061 | 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats | |
d3fc8074 | 3062 | 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres' |
3063 | ]) | |
11f9be09 | 3064 | streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[]) |
9297939e | 3065 | |
545cc85d | 3066 | for fmt in streaming_formats: |
727029c5 | 3067 | if fmt.get('targetDurationSec'): |
545cc85d | 3068 | continue |
321bf820 | 3069 | |
cc2db878 | 3070 | itag = str_or_none(fmt.get('itag')) |
9297939e | 3071 | audio_track = fmt.get('audioTrack') or {} |
3072 | stream_id = '%s.%s' % (itag or '', audio_track.get('id', '')) | |
3073 | if stream_id in stream_ids: | |
3074 | continue | |
3075 | ||
cc2db878 | 3076 | quality = fmt.get('quality') |
2a9c6dcd | 3077 | height = int_or_none(fmt.get('height')) |
d3fc8074 | 3078 | if quality == 'tiny' or not quality: |
3079 | quality = fmt.get('audioQuality', '').lower() or quality | |
2a9c6dcd | 3080 | # The 3gp format (17) in android client has a quality of "small", |
3081 | # but is actually worse than other formats | |
3082 | if itag == '17': | |
3083 | quality = 'tiny' | |
3084 | if quality: | |
3085 | if itag: | |
3086 | itag_qualities[itag] = quality | |
3087 | if height: | |
3088 | res_qualities[height] = quality | |
cc2db878 | 3089 | # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment |
3090 | # (adding `&sq=0` to the URL) and parsing emsg box to determine the | |
3091 | # number of fragment that would subsequently requested with (`&sq=N`) | |
3092 | if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF': | |
3093 | continue | |
3094 | ||
545cc85d | 3095 | fmt_url = fmt.get('url') |
3096 | if not fmt_url: | |
3097 | sc = compat_parse_qs(fmt.get('signatureCipher')) | |
3098 | fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0])) | |
3099 | encrypted_sig = try_get(sc, lambda x: x['s'][0]) | |
3100 | if not (sc and fmt_url and encrypted_sig): | |
3101 | continue | |
545cc85d | 3102 | if not player_url: |
201e9eaa | 3103 | continue |
545cc85d | 3104 | signature = self._decrypt_signature(sc['s'][0], video_id, player_url) |
3105 | sp = try_get(sc, lambda x: x['sp'][0]) or 'signature' | |
3106 | fmt_url += '&' + sp + '=' + signature | |
3107 | ||
404f611f | 3108 | query = parse_qs(fmt_url) |
3109 | throttled = False | |
b2916526 | 3110 | if query.get('n'): |
404f611f | 3111 | try: |
3112 | fmt_url = update_url_query(fmt_url, { | |
3113 | 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)}) | |
3114 | except ExtractorError as e: | |
aa9369a2 | 3115 | self.report_warning( |
3116 | f'nsig extraction failed: You may experience throttling for some formats\n' | |
3117 | f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True) | |
404f611f | 3118 | throttled = True |
3119 | ||
545cc85d | 3120 | if itag: |
a0bb6ce5 | 3121 | itags[itag] = 'https' |
9297939e | 3122 | stream_ids.append(stream_id) |
3123 | ||
0ad92dfb | 3124 | tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) |
ab6df717 | 3125 | language_preference = ( |
3126 | 10 if audio_track.get('audioIsDefault') and 10 | |
3127 | else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10 | |
3128 | else -1) | |
0ad92dfb | 3129 | # Some formats may have much smaller duration than others (possibly damaged during encoding) |
3130 | # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823 | |
a1b2d843 | 3131 | # Make sure to avoid false positives with small duration differences. |
3132 | # Eg: __2ABJjxzNo, ySuUZEjARPY | |
3133 | is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500) | |
08d30158 | 3134 | if is_damaged: |
3135 | self.report_warning(f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True) | |
545cc85d | 3136 | dct = { |
3137 | 'asr': int_or_none(fmt.get('audioSampleRate')), | |
3138 | 'filesize': int_or_none(fmt.get('contentLength')), | |
3139 | 'format_id': itag, | |
34921b43 | 3140 | 'format_note': join_nonempty( |
26e8e044 | 3141 | '%s%s' % (audio_track.get('displayName') or '', |
ab6df717 | 3142 | ' (default)' if language_preference > 0 else ''), |
404f611f | 3143 | fmt.get('qualityLabel') or quality.replace('audio_quality_', ''), |
0ad92dfb | 3144 | throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '), |
c18d4482 | 3145 | 'source_preference': -10 if throttled else -1, |
a4211baf | 3146 | 'fps': int_or_none(fmt.get('fps')) or None, |
2a9c6dcd | 3147 | 'height': height, |
dca3ff4a | 3148 | 'quality': q(quality), |
727029c5 | 3149 | 'has_drm': bool(fmt.get('drmFamilies')), |
cc2db878 | 3150 | 'tbr': tbr, |
545cc85d | 3151 | 'url': fmt_url, |
2a9c6dcd | 3152 | 'width': int_or_none(fmt.get('width')), |
ab6df717 | 3153 | 'language': join_nonempty(audio_track.get('id', '').split('.')[0], |
3154 | 'desc' if language_preference < -1 else ''), | |
3155 | 'language_preference': language_preference, | |
a405b38f | 3156 | # Strictly de-prioritize damaged and 3gp formats |
3157 | 'preference': -10 if is_damaged else -2 if itag == '17' else None, | |
545cc85d | 3158 | } |
60bdb7bd | 3159 | mime_mobj = re.match( |
3160 | r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '') | |
3161 | if mime_mobj: | |
3162 | dct['ext'] = mimetype2ext(mime_mobj.group(1)) | |
3163 | dct.update(parse_codecs(mime_mobj.group(2))) | |
cc2db878 | 3164 | no_audio = dct.get('acodec') == 'none' |
3165 | no_video = dct.get('vcodec') == 'none' | |
3166 | if no_audio: | |
3167 | dct['vbr'] = tbr | |
3168 | if no_video: | |
3169 | dct['abr'] = tbr | |
3170 | if no_audio or no_video: | |
545cc85d | 3171 | dct['downloader_options'] = { |
3172 | # Youtube throttles chunks >~10M | |
3173 | 'http_chunk_size': 10485760, | |
bf1317d2 | 3174 | } |
7c60c33e | 3175 | if dct.get('ext'): |
3176 | dct['container'] = dct['ext'] + '_dash' | |
11f9be09 | 3177 | yield dct |
545cc85d | 3178 | |
adbc4ec4 | 3179 | live_from_start = is_live and self.get_param('live_from_start') |
4bb6b02f | 3180 | skip_manifests = self._configuration_arg('skip') |
adbc4ec4 THD |
3181 | if not self.get_param('youtube_include_hls_manifest', True): |
3182 | skip_manifests.append('hls') | |
3183 | get_dash = 'dash' not in skip_manifests and ( | |
3184 | not is_live or live_from_start or self._configuration_arg('include_live_dash')) | |
3185 | get_hls = not live_from_start and 'hls' not in skip_manifests | |
5d3a0e79 | 3186 | |
a0bb6ce5 | 3187 | def process_manifest_format(f, proto, itag): |
3188 | if itag in itags: | |
3189 | if itags[itag] == proto or f'{itag}-{proto}' in itags: | |
3190 | return False | |
3191 | itag = f'{itag}-{proto}' | |
3192 | if itag: | |
3193 | f['format_id'] = itag | |
3194 | itags[itag] = proto | |
3195 | ||
3196 | f['quality'] = next(( | |
3197 | q(qdict[val]) | |
e339d25a | 3198 | for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities)) |
a0bb6ce5 | 3199 | if val in qdict), -1) |
3200 | return True | |
2a9c6dcd | 3201 | |
11f9be09 | 3202 | for sd in streaming_data: |
5d3a0e79 | 3203 | hls_manifest_url = get_hls and sd.get('hlsManifestUrl') |
9297939e | 3204 | if hls_manifest_url: |
2a9c6dcd | 3205 | for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False): |
a0bb6ce5 | 3206 | if process_manifest_format(f, 'hls', self._search_regex( |
3207 | r'/itag/(\d+)', f['url'], 'itag', default=None)): | |
3208 | yield f | |
545cc85d | 3209 | |
5d3a0e79 | 3210 | dash_manifest_url = get_dash and sd.get('dashManifestUrl') |
3211 | if dash_manifest_url: | |
2a9c6dcd | 3212 | for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False): |
a0bb6ce5 | 3213 | if process_manifest_format(f, 'dash', f['format_id']): |
3214 | f['filesize'] = int_or_none(self._search_regex( | |
3215 | r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None)) | |
adbc4ec4 THD |
3216 | if live_from_start: |
3217 | f['is_from_start'] = True | |
3218 | ||
a0bb6ce5 | 3219 | yield f |
11f9be09 | 3220 | |
720c3099 | 3221 | def _extract_storyboard(self, player_responses, duration): |
3222 | spec = get_first( | |
3223 | player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1] | |
596379e2 | 3224 | base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None)) |
3225 | if not base_url: | |
720c3099 | 3226 | return |
720c3099 | 3227 | L = len(spec) - 1 |
3228 | for i, args in enumerate(spec): | |
3229 | args = args.split('#') | |
3230 | counts = list(map(int_or_none, args[:5])) | |
3231 | if len(args) != 8 or not all(counts): | |
3232 | self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}') | |
3233 | continue | |
3234 | width, height, frame_count, cols, rows = counts | |
3235 | N, sigh = args[6:] | |
3236 | ||
3237 | url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}' | |
3238 | fragment_count = frame_count / (cols * rows) | |
3239 | fragment_duration = duration / fragment_count | |
3240 | yield { | |
3241 | 'format_id': f'sb{i}', | |
3242 | 'format_note': 'storyboard', | |
3243 | 'ext': 'mhtml', | |
3244 | 'protocol': 'mhtml', | |
3245 | 'acodec': 'none', | |
3246 | 'vcodec': 'none', | |
3247 | 'url': url, | |
3248 | 'width': width, | |
3249 | 'height': height, | |
3250 | 'fragments': [{ | |
b3edc806 | 3251 | 'url': url.replace('$M', str(j)), |
720c3099 | 3252 | 'duration': min(fragment_duration, duration - (j * fragment_duration)), |
3253 | } for j in range(math.ceil(fragment_count))], | |
3254 | } | |
3255 | ||
adbc4ec4 | 3256 | def _download_player_responses(self, url, smuggled_data, video_id, webpage_url): |
b6de707d | 3257 | webpage = None |
3258 | if 'webpage' not in self._configuration_arg('player_skip'): | |
3259 | webpage = self._download_webpage( | |
3260 | webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False) | |
11f9be09 | 3261 | |
3262 | master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg() | |
11f9be09 | 3263 | |
b6de707d | 3264 | player_responses, player_url = self._extract_player_responses( |
11f9be09 | 3265 | self._get_requested_clients(url, smuggled_data), |
99e9e001 | 3266 | video_id, webpage, master_ytcfg) |
11f9be09 | 3267 | |
adbc4ec4 THD |
3268 | return webpage, master_ytcfg, player_responses, player_url |
3269 | ||
a1b2d843 | 3270 | def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None): |
adbc4ec4 THD |
3271 | live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails')) |
3272 | is_live = get_first(video_details, 'isLive') | |
3273 | if is_live is None: | |
3274 | is_live = get_first(live_broadcast_details, 'isLiveNow') | |
3275 | ||
3276 | streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[]) | |
a1b2d843 | 3277 | formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration)) |
adbc4ec4 THD |
3278 | |
3279 | return live_broadcast_details, is_live, streaming_data, formats | |
3280 | ||
3281 | def _real_extract(self, url): | |
3282 | url, smuggled_data = unsmuggle_url(url, {}) | |
3283 | video_id = self._match_id(url) | |
3284 | ||
3285 | base_url = self.http_scheme() + '//www.youtube.com/' | |
3286 | webpage_url = base_url + 'watch?v=' + video_id | |
3287 | ||
3288 | webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url) | |
3289 | ||
11f9be09 | 3290 | playability_statuses = traverse_obj( |
3291 | player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[]) | |
3292 | ||
3293 | trailer_video_id = get_first( | |
3294 | playability_statuses, | |
3295 | ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'), | |
3296 | expected_type=str) | |
3297 | if trailer_video_id: | |
3298 | return self.url_result( | |
3299 | trailer_video_id, self.ie_key(), trailer_video_id) | |
3300 | ||
3301 | search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None)) | |
3302 | if webpage else (lambda x: None)) | |
3303 | ||
3304 | video_details = traverse_obj( | |
3305 | player_responses, (..., 'videoDetails'), expected_type=dict, default=[]) | |
3306 | microformats = traverse_obj( | |
3307 | player_responses, (..., 'microformat', 'playerMicroformatRenderer'), | |
3308 | expected_type=dict, default=[]) | |
3309 | video_title = ( | |
3310 | get_first(video_details, 'title') | |
3311 | or self._get_text(microformats, (..., 'title')) | |
3312 | or search_meta(['og:title', 'twitter:title', 'title'])) | |
3313 | video_description = get_first(video_details, 'shortDescription') | |
3314 | ||
d89257f3 | 3315 | multifeed_metadata_list = get_first( |
3316 | player_responses, | |
3317 | ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'), | |
3318 | expected_type=str) | |
3319 | if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'): | |
3320 | if self.get_param('noplaylist'): | |
11f9be09 | 3321 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) |
d89257f3 | 3322 | else: |
3323 | entries = [] | |
3324 | feed_ids = [] | |
3325 | for feed in multifeed_metadata_list.split(','): | |
3326 | # Unquote should take place before split on comma (,) since textual | |
3327 | # fields may contain comma as well (see | |
3328 | # https://github.com/ytdl-org/youtube-dl/issues/8536) | |
3329 | feed_data = compat_parse_qs( | |
3330 | compat_urllib_parse_unquote_plus(feed)) | |
3331 | ||
3332 | def feed_entry(name): | |
3333 | return try_get( | |
3334 | feed_data, lambda x: x[name][0], compat_str) | |
3335 | ||
3336 | feed_id = feed_entry('id') | |
3337 | if not feed_id: | |
3338 | continue | |
3339 | feed_title = feed_entry('title') | |
3340 | title = video_title | |
3341 | if feed_title: | |
3342 | title += ' (%s)' % feed_title | |
3343 | entries.append({ | |
3344 | '_type': 'url_transparent', | |
3345 | 'ie_key': 'Youtube', | |
3346 | 'url': smuggle_url( | |
3347 | '%swatch?v=%s' % (base_url, feed_data['id'][0]), | |
3348 | {'force_singlefeed': True}), | |
3349 | 'title': title, | |
3350 | }) | |
3351 | feed_ids.append(feed_id) | |
3352 | self.to_screen( | |
3353 | 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' | |
3354 | % (', '.join(feed_ids), video_id)) | |
3355 | return self.playlist_result( | |
3356 | entries, video_id, video_title, video_description) | |
11f9be09 | 3357 | |
a1b2d843 | 3358 | duration = int_or_none( |
3359 | get_first(video_details, 'lengthSeconds') | |
3360 | or get_first(microformats, 'lengthSeconds') | |
3361 | or parse_duration(search_meta('duration'))) or None | |
3362 | ||
3363 | live_broadcast_details, is_live, streaming_data, formats = self._list_formats( | |
3364 | video_id, microformats, video_details, player_responses, player_url, duration) | |
bf1317d2 | 3365 | |
545cc85d | 3366 | if not formats: |
11f9be09 | 3367 | if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')): |
88acdbc2 | 3368 | self.report_drm(video_id) |
11f9be09 | 3369 | pemr = get_first( |
3370 | playability_statuses, | |
3371 | ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {} | |
3372 | reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason') | |
3373 | subreason = clean_html(self._get_text(pemr, 'subreason') or '') | |
545cc85d | 3374 | if subreason: |
545cc85d | 3375 | if subreason == 'The uploader has not made this video available in your country.': |
11f9be09 | 3376 | countries = get_first(microformats, 'availableCountries') |
545cc85d | 3377 | if not countries: |
3378 | regions_allowed = search_meta('regionsAllowed') | |
3379 | countries = regions_allowed.split(',') if regions_allowed else None | |
b7da73eb | 3380 | self.raise_geo_restricted(subreason, countries, metadata_available=True) |
11f9be09 | 3381 | reason += f'. {subreason}' |
545cc85d | 3382 | if reason: |
b7da73eb | 3383 | self.raise_no_formats(reason, expected=True) |
bf1317d2 | 3384 | |
11f9be09 | 3385 | keywords = get_first(video_details, 'keywords', expected_type=list) or [] |
545cc85d | 3386 | if not keywords and webpage: |
3387 | keywords = [ | |
3388 | unescapeHTML(m.group('content')) | |
3389 | for m in re.finditer(self._meta_regex('og:video:tag'), webpage)] | |
3390 | for keyword in keywords: | |
3391 | if keyword.startswith('yt:stretch='): | |
201c1459 | 3392 | mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword) |
3393 | if mobj: | |
3394 | # NB: float is intentional for forcing float division | |
3395 | w, h = (float(v) for v in mobj.groups()) | |
3396 | if w > 0 and h > 0: | |
3397 | ratio = w / h | |
3398 | for f in formats: | |
3399 | if f.get('vcodec') != 'none': | |
3400 | f['stretched_ratio'] = ratio | |
3401 | break | |
a709d873 | 3402 | thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail')) |
ff2751ac | 3403 | thumbnail_url = search_meta(['og:image', 'twitter:image']) |
3404 | if thumbnail_url: | |
3405 | thumbnails.append({ | |
3406 | 'url': thumbnail_url, | |
ff2751ac | 3407 | }) |
fccf5021 | 3408 | original_thumbnails = thumbnails.copy() |
3409 | ||
0ba692ac | 3410 | # The best resolution thumbnails sometimes does not appear in the webpage |
3411 | # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340 | |
cca80fe6 | 3412 | # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029> |
e820fbaa | 3413 | thumbnail_names = [ |
3414 | 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3', | |
cca80fe6 | 3415 | 'hqdefault', 'hq1', 'hq2', 'hq3', '0', |
3416 | 'mqdefault', 'mq1', 'mq2', 'mq3', | |
3417 | 'default', '1', '2', '3' | |
3418 | ] | |
cca80fe6 | 3419 | n_thumbnail_names = len(thumbnail_names) |
0ba692ac | 3420 | thumbnails.extend({ |
3421 | 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format( | |
3422 | video_id=video_id, name=name, ext=ext, | |
3423 | webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''), | |
cca80fe6 | 3424 | } for name in thumbnail_names for ext in ('webp', 'jpg')) |
0ba692ac | 3425 | for thumb in thumbnails: |
cca80fe6 | 3426 | i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names) |
0ba692ac | 3427 | thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i) |
ff2751ac | 3428 | self._remove_duplicate_formats(thumbnails) |
fccf5021 | 3429 | self._downloader._sort_thumbnails(original_thumbnails) |
545cc85d | 3430 | |
7ea65411 | 3431 | category = get_first(microformats, 'category') or search_meta('genre') |
3432 | channel_id = str_or_none( | |
3433 | get_first(video_details, 'channelId') | |
3434 | or get_first(microformats, 'externalChannelId') | |
3435 | or search_meta('channelId')) | |
7ea65411 | 3436 | owner_profile_url = get_first(microformats, 'ownerProfileUrl') |
3437 | ||
3438 | live_content = get_first(video_details, 'isLiveContent') | |
3439 | is_upcoming = get_first(video_details, 'isUpcoming') | |
3440 | if is_live is None: | |
3441 | if is_upcoming or live_content is False: | |
3442 | is_live = False | |
3443 | if is_upcoming is None and (live_content or is_live): | |
3444 | is_upcoming = False | |
adbc4ec4 THD |
3445 | live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp')) |
3446 | live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp')) | |
3447 | if not duration and live_end_time and live_start_time: | |
3448 | duration = live_end_time - live_start_time | |
3449 | ||
3450 | if is_live and self.get_param('live_from_start'): | |
3451 | self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data) | |
7ea65411 | 3452 | |
720c3099 | 3453 | formats.extend(self._extract_storyboard(player_responses, duration)) |
3454 | ||
3455 | # Source is given priority since formats that throttle are given lower source_preference | |
3456 | # When throttling issue is fully fixed, remove this | |
3457 | self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto')) | |
3458 | ||
545cc85d | 3459 | info = { |
3460 | 'id': video_id, | |
39ca3b5c | 3461 | 'title': video_title, |
545cc85d | 3462 | 'formats': formats, |
3463 | 'thumbnails': thumbnails, | |
fccf5021 | 3464 | # The best thumbnail that we are sure exists. Prevents unnecessary |
3465 | # URL checking if user don't care about getting the best possible thumbnail | |
3466 | 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')), | |
545cc85d | 3467 | 'description': video_description, |
11f9be09 | 3468 | 'uploader': get_first(video_details, 'author'), |
545cc85d | 3469 | 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None, |
3470 | 'uploader_url': owner_profile_url, | |
3471 | 'channel_id': channel_id, | |
e0ddbd02 | 3472 | 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'), |
545cc85d | 3473 | 'duration': duration, |
3474 | 'view_count': int_or_none( | |
11f9be09 | 3475 | get_first((video_details, microformats), (..., 'viewCount')) |
545cc85d | 3476 | or search_meta('interactionCount')), |
11f9be09 | 3477 | 'average_rating': float_or_none(get_first(video_details, 'averageRating')), |
545cc85d | 3478 | 'age_limit': 18 if ( |
11f9be09 | 3479 | get_first(microformats, 'isFamilySafe') is False |
545cc85d | 3480 | or search_meta('isFamilyFriendly') == 'false' |
3481 | or search_meta('og:restrictions:age') == '18+') else 0, | |
3482 | 'webpage_url': webpage_url, | |
3483 | 'categories': [category] if category else None, | |
3484 | 'tags': keywords, | |
11f9be09 | 3485 | 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'), |
7ea65411 | 3486 | 'is_live': is_live, |
3487 | 'was_live': (False if is_live or is_upcoming or live_content is False | |
3488 | else None if is_live is None or is_upcoming is None | |
3489 | else live_content), | |
3490 | 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL | |
adbc4ec4 | 3491 | 'release_timestamp': live_start_time, |
545cc85d | 3492 | } |
b477fc13 | 3493 | |
3944e7af | 3494 | pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict) |
545cc85d | 3495 | if pctr: |
ecdc9049 | 3496 | def get_lang_code(track): |
3497 | return (remove_start(track.get('vssId') or '', '.').replace('.', '-') | |
3498 | or track.get('languageCode')) | |
3499 | ||
3500 | # Converted into dicts to remove duplicates | |
3501 | captions = { | |
3502 | get_lang_code(sub): sub | |
3503 | for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])} | |
3504 | translation_languages = { | |
3505 | lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1) | |
3506 | for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])} | |
3507 | ||
774d79cc | 3508 | def process_language(container, base_url, lang_code, sub_name, query): |
120916da | 3509 | lang_subs = container.setdefault(lang_code, []) |
545cc85d | 3510 | for fmt in self._SUBTITLE_FORMATS: |
3511 | query.update({ | |
3512 | 'fmt': fmt, | |
3513 | }) | |
3514 | lang_subs.append({ | |
3515 | 'ext': fmt, | |
60f393e4 | 3516 | 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)), |
774d79cc | 3517 | 'name': sub_name, |
545cc85d | 3518 | }) |
7e72694b | 3519 | |
ecdc9049 | 3520 | subtitles, automatic_captions = {}, {} |
3521 | for lang_code, caption_track in captions.items(): | |
3522 | base_url = caption_track.get('baseUrl') | |
1235d333 | 3523 | orig_lang = parse_qs(base_url).get('lang', [None])[-1] |
545cc85d | 3524 | if not base_url: |
3525 | continue | |
ecdc9049 | 3526 | lang_name = self._get_text(caption_track, 'name', max_runs=1) |
545cc85d | 3527 | if caption_track.get('kind') != 'asr': |
545cc85d | 3528 | if not lang_code: |
3529 | continue | |
3530 | process_language( | |
ecdc9049 | 3531 | subtitles, base_url, lang_code, lang_name, {}) |
3532 | if not caption_track.get('isTranslatable'): | |
3533 | continue | |
3944e7af | 3534 | for trans_code, trans_name in translation_languages.items(): |
3535 | if not trans_code: | |
545cc85d | 3536 | continue |
1235d333 | 3537 | orig_trans_code = trans_code |
ecdc9049 | 3538 | if caption_track.get('kind') != 'asr': |
18e49408 | 3539 | if 'translated_subs' in self._configuration_arg('skip'): |
3540 | continue | |
ecdc9049 | 3541 | trans_code += f'-{lang_code}' |
3542 | trans_name += format_field(lang_name, template=' from %s') | |
d49669ac | 3543 | # Add an "-orig" label to the original language so that it can be distinguished. |
3544 | # The subs are returned without "-orig" as well for compatibility | |
1235d333 | 3545 | if lang_code == f'a-{orig_trans_code}': |
0c8d9e5f | 3546 | process_language( |
d49669ac | 3547 | automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {}) |
3548 | # Setting tlang=lang returns damaged subtitles. | |
d49669ac | 3549 | process_language(automatic_captions, base_url, trans_code, trans_name, |
1235d333 | 3550 | {} if orig_lang == orig_trans_code else {'tlang': trans_code}) |
ecdc9049 | 3551 | info['automatic_captions'] = automatic_captions |
3552 | info['subtitles'] = subtitles | |
7e72694b | 3553 | |
545cc85d | 3554 | parsed_url = compat_urllib_parse_urlparse(url) |
3555 | for component in [parsed_url.fragment, parsed_url.query]: | |
3556 | query = compat_parse_qs(component) | |
3557 | for k, v in query.items(): | |
3558 | for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]: | |
3559 | d_k += '_time' | |
3560 | if d_k not in info and k in s_ks: | |
3561 | info[d_k] = parse_duration(query[k][0]) | |
822b9d9c RA |
3562 | |
3563 | # Youtube Music Auto-generated description | |
822b9d9c | 3564 | if video_description: |
38d70284 | 3565 | 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 | 3566 | if mobj: |
822b9d9c RA |
3567 | release_year = mobj.group('release_year') |
3568 | release_date = mobj.group('release_date') | |
3569 | if release_date: | |
3570 | release_date = release_date.replace('-', '') | |
3571 | if not release_year: | |
545cc85d | 3572 | release_year = release_date[:4] |
3573 | info.update({ | |
3574 | 'album': mobj.group('album'.strip()), | |
3575 | 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')), | |
3576 | 'track': mobj.group('track').strip(), | |
3577 | 'release_date': release_date, | |
cc2db878 | 3578 | 'release_year': int_or_none(release_year), |
545cc85d | 3579 | }) |
7e72694b | 3580 | |
545cc85d | 3581 | initial_data = None |
3582 | if webpage: | |
3583 | initial_data = self._extract_yt_initial_variable( | |
3584 | webpage, self._YT_INITIAL_DATA_RE, video_id, | |
3585 | 'yt initial data') | |
3586 | if not initial_data: | |
99e9e001 | 3587 | query = {'videoId': video_id} |
3588 | query.update(self._get_checkok_params()) | |
109dd3b2 | 3589 | initial_data = self._extract_response( |
3590 | item_id=video_id, ep='next', fatal=False, | |
99e9e001 | 3591 | ytcfg=master_ytcfg, query=query, |
3592 | headers=self.generate_api_headers(ytcfg=master_ytcfg), | |
109dd3b2 | 3593 | note='Downloading initial data API JSON') |
545cc85d | 3594 | |
c60ee3a2 | 3595 | try: |
3596 | # This will error if there is no livechat | |
3597 | initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation'] | |
ecdc9049 | 3598 | info.setdefault('subtitles', {})['live_chat'] = [{ |
c60ee3a2 | 3599 | 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies |
3600 | 'video_id': video_id, | |
3601 | 'ext': 'json', | |
f6745c49 | 3602 | 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay', |
c60ee3a2 | 3603 | }] |
3604 | except (KeyError, IndexError, TypeError): | |
3605 | pass | |
545cc85d | 3606 | |
3607 | if initial_data: | |
7c365c21 | 3608 | info['chapters'] = ( |
3609 | self._extract_chapters_from_json(initial_data, duration) | |
3610 | or self._extract_chapters_from_engagement_panel(initial_data, duration) | |
3611 | or None) | |
545cc85d | 3612 | |
17322130 | 3613 | contents = traverse_obj( |
3614 | initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'), | |
3615 | expected_type=list, default=[]) | |
3616 | ||
3617 | vpir = get_first(contents, 'videoPrimaryInfoRenderer') | |
3618 | if vpir: | |
3619 | stl = vpir.get('superTitleLink') | |
3620 | if stl: | |
3621 | stl = self._get_text(stl) | |
3622 | if try_get( | |
3623 | vpir, | |
3624 | lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN': | |
3625 | info['location'] = stl | |
3626 | else: | |
3627 | mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl) | |
3628 | if mobj: | |
545cc85d | 3629 | info.update({ |
17322130 | 3630 | 'series': mobj.group(1), |
3631 | 'season_number': int(mobj.group(2)), | |
3632 | 'episode_number': int(mobj.group(3)), | |
545cc85d | 3633 | }) |
17322130 | 3634 | for tlb in (try_get( |
3635 | vpir, | |
3636 | lambda x: x['videoActions']['menuRenderer']['topLevelButtons'], | |
3637 | list) or []): | |
3638 | tbr = tlb.get('toggleButtonRenderer') or {} | |
3639 | for getter, regex in [( | |
3640 | lambda x: x['defaultText']['accessibility']['accessibilityData'], | |
3641 | r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([ | |
3642 | lambda x: x['accessibility'], | |
3643 | lambda x: x['accessibilityData']['accessibilityData'], | |
3644 | ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]: | |
3645 | label = (try_get(tbr, getter, dict) or {}).get('label') | |
3646 | if label: | |
3647 | mobj = re.match(regex, label) | |
3648 | if mobj: | |
3649 | info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count')) | |
545cc85d | 3650 | break |
17322130 | 3651 | sbr_tooltip = try_get( |
3652 | vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip']) | |
3653 | if sbr_tooltip: | |
3654 | like_count, dislike_count = sbr_tooltip.split(' / ') | |
3655 | info.update({ | |
3656 | 'like_count': str_to_int(like_count), | |
3657 | 'dislike_count': str_to_int(dislike_count), | |
3658 | }) | |
3659 | vsir = get_first(contents, 'videoSecondaryInfoRenderer') | |
3660 | if vsir: | |
3661 | vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer')) | |
3662 | info.update({ | |
3663 | 'channel': self._get_text(vor, 'title'), | |
3664 | 'channel_follower_count': self._get_count(vor, 'subscriberCountText')}) | |
3665 | ||
3666 | rows = try_get( | |
3667 | vsir, | |
3668 | lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'], | |
3669 | list) or [] | |
3670 | multiple_songs = False | |
3671 | for row in rows: | |
3672 | if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True: | |
3673 | multiple_songs = True | |
3674 | break | |
3675 | for row in rows: | |
3676 | mrr = row.get('metadataRowRenderer') or {} | |
3677 | mrr_title = mrr.get('title') | |
3678 | if not mrr_title: | |
3679 | continue | |
3680 | mrr_title = self._get_text(mrr, 'title') | |
3681 | mrr_contents_text = self._get_text(mrr, ('contents', 0)) | |
3682 | if mrr_title == 'License': | |
3683 | info['license'] = mrr_contents_text | |
3684 | elif not multiple_songs: | |
3685 | if mrr_title == 'Album': | |
3686 | info['album'] = mrr_contents_text | |
3687 | elif mrr_title == 'Artist': | |
3688 | info['artist'] = mrr_contents_text | |
3689 | elif mrr_title == 'Song': | |
3690 | info['track'] = mrr_contents_text | |
545cc85d | 3691 | |
3692 | fallbacks = { | |
3693 | 'channel': 'uploader', | |
3694 | 'channel_id': 'uploader_id', | |
3695 | 'channel_url': 'uploader_url', | |
3696 | } | |
992f9a73 | 3697 | |
17322130 | 3698 | # The upload date for scheduled, live and past live streams / premieres in microformats |
3699 | # may be different from the stream date. Although not in UTC, we will prefer it in this case. | |
992f9a73 | 3700 | # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139 |
17322130 | 3701 | upload_date = ( |
3702 | unified_strdate(get_first(microformats, 'uploadDate')) | |
3703 | or unified_strdate(search_meta('uploadDate'))) | |
3704 | if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'): | |
3705 | upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d') | |
3706 | info['upload_date'] = upload_date | |
992f9a73 | 3707 | |
545cc85d | 3708 | for to, frm in fallbacks.items(): |
3709 | if not info.get(to): | |
3710 | info[to] = info.get(frm) | |
3711 | ||
3712 | for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]: | |
3713 | v = info.get(s_k) | |
3714 | if v: | |
3715 | info[d_k] = v | |
b84071c0 | 3716 | |
11f9be09 | 3717 | is_private = get_first(video_details, 'isPrivate', expected_type=bool) |
3718 | is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool) | |
c224251a | 3719 | is_membersonly = None |
b28f8d24 | 3720 | is_premium = None |
c224251a M |
3721 | if initial_data and is_private is not None: |
3722 | is_membersonly = False | |
b28f8d24 | 3723 | is_premium = False |
47193e02 | 3724 | contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or [] |
3725 | badge_labels = set() | |
3726 | for content in contents: | |
3727 | if not isinstance(content, dict): | |
3728 | continue | |
3729 | badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer'))) | |
3730 | for badge_label in badge_labels: | |
3731 | if badge_label.lower() == 'members only': | |
3732 | is_membersonly = True | |
3733 | elif badge_label.lower() == 'premium': | |
3734 | is_premium = True | |
3735 | elif badge_label.lower() == 'unlisted': | |
3736 | is_unlisted = True | |
c224251a | 3737 | |
c224251a M |
3738 | info['availability'] = self._availability( |
3739 | is_private=is_private, | |
b28f8d24 | 3740 | needs_premium=is_premium, |
c224251a M |
3741 | needs_subscription=is_membersonly, |
3742 | needs_auth=info['age_limit'] >= 18, | |
3743 | is_unlisted=None if is_private is None else is_unlisted) | |
3744 | ||
a2160aa4 | 3745 | info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage) |
4ea3be0a | 3746 | |
11f9be09 | 3747 | self.mark_watched(video_id, player_responses) |
d77ab8e2 | 3748 | |
545cc85d | 3749 | return info |
c5e8d7af | 3750 | |
a61fd4cf | 3751 | |
a6213a49 | 3752 | class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor): |
5f6a1245 | 3753 | |
182bda88 | 3754 | @staticmethod |
3755 | def passthrough_smuggled_data(func): | |
3756 | def _smuggle(entries, smuggled_data): | |
3757 | for entry in entries: | |
3758 | # TODO: Convert URL to music.youtube instead. | |
3759 | # Do we need to passthrough any other smuggled_data? | |
3760 | entry['url'] = smuggle_url(entry['url'], smuggled_data) | |
3761 | yield entry | |
3762 | ||
3763 | @functools.wraps(func) | |
3764 | def wrapper(self, url): | |
3765 | url, smuggled_data = unsmuggle_url(url, {}) | |
3766 | if self.is_music_url(url): | |
3767 | smuggled_data['is_music_url'] = True | |
3768 | info_dict = func(self, url, smuggled_data) | |
3769 | if smuggled_data and info_dict.get('entries'): | |
3770 | info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data) | |
3771 | return info_dict | |
3772 | return wrapper | |
3773 | ||
a6213a49 | 3774 | def _extract_channel_id(self, webpage): |
3775 | channel_id = self._html_search_meta( | |
3776 | 'channelId', webpage, 'channel id', default=None) | |
3777 | if channel_id: | |
3778 | return channel_id | |
3779 | channel_url = self._html_search_meta( | |
3780 | ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url', | |
3781 | 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad', | |
3782 | 'twitter:app:url:googleplay'), webpage, 'channel url') | |
3783 | return self._search_regex( | |
3784 | r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+', | |
3785 | channel_url, 'channel id') | |
15f6397c | 3786 | |
8bdd16b4 | 3787 | @staticmethod |
cd7c66cf | 3788 | def _extract_basic_item_renderer(item): |
3789 | # Modified from _extract_grid_item_renderer | |
201c1459 | 3790 | known_basic_renderers = ( |
a17526e4 | 3791 | 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer' |
cd7c66cf | 3792 | ) |
3793 | for key, renderer in item.items(): | |
201c1459 | 3794 | if not isinstance(renderer, dict): |
cd7c66cf | 3795 | continue |
201c1459 | 3796 | elif key in known_basic_renderers: |
3797 | return renderer | |
3798 | elif key.startswith('grid') and key.endswith('Renderer'): | |
3799 | return renderer | |
8bdd16b4 | 3800 | |
8bdd16b4 | 3801 | def _grid_entries(self, grid_renderer): |
3802 | for item in grid_renderer['items']: | |
3803 | if not isinstance(item, dict): | |
39b62db1 | 3804 | continue |
cd7c66cf | 3805 | renderer = self._extract_basic_item_renderer(item) |
8bdd16b4 | 3806 | if not isinstance(renderer, dict): |
3807 | continue | |
052e1350 | 3808 | title = self._get_text(renderer, 'title') |
fe93e2c4 | 3809 | |
8bdd16b4 | 3810 | # playlist |
3811 | playlist_id = renderer.get('playlistId') | |
3812 | if playlist_id: | |
3813 | yield self.url_result( | |
3814 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, | |
3815 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id, | |
3816 | video_title=title) | |
201c1459 | 3817 | continue |
8bdd16b4 | 3818 | # video |
3819 | video_id = renderer.get('videoId') | |
3820 | if video_id: | |
3821 | yield self._extract_video(renderer) | |
201c1459 | 3822 | continue |
8bdd16b4 | 3823 | # channel |
3824 | channel_id = renderer.get('channelId') | |
3825 | if channel_id: | |
8bdd16b4 | 3826 | yield self.url_result( |
3827 | 'https://www.youtube.com/channel/%s' % channel_id, | |
3828 | ie=YoutubeTabIE.ie_key(), video_title=title) | |
201c1459 | 3829 | continue |
3830 | # generic endpoint URL support | |
3831 | ep_url = urljoin('https://www.youtube.com/', try_get( | |
3832 | renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'], | |
3833 | compat_str)) | |
3834 | if ep_url: | |
3835 | for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE): | |
3836 | if ie.suitable(ep_url): | |
3837 | yield self.url_result( | |
3838 | ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title) | |
3839 | break | |
8bdd16b4 | 3840 | |
16aa9ea4 | 3841 | def _music_reponsive_list_entry(self, renderer): |
3842 | video_id = traverse_obj(renderer, ('playlistItemData', 'videoId')) | |
3843 | if video_id: | |
3844 | return self.url_result(f'https://music.youtube.com/watch?v={video_id}', | |
3845 | ie=YoutubeIE.ie_key(), video_id=video_id) | |
3846 | playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId')) | |
3847 | if playlist_id: | |
3848 | video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId')) | |
3849 | if video_id: | |
3850 | return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}', | |
3851 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
3852 | return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}', | |
3853 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
3854 | browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId')) | |
3855 | if browse_id: | |
3856 | return self.url_result(f'https://music.youtube.com/browse/{browse_id}', | |
3857 | ie=YoutubeTabIE.ie_key(), video_id=browse_id) | |
3858 | ||
3d3dddc9 | 3859 | def _shelf_entries_from_content(self, shelf_renderer): |
3860 | content = shelf_renderer.get('content') | |
3861 | if not isinstance(content, dict): | |
8bdd16b4 | 3862 | return |
cd7c66cf | 3863 | renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer') |
3d3dddc9 | 3864 | if renderer: |
3865 | # TODO: add support for nested playlists so each shelf is processed | |
3866 | # as separate playlist | |
3867 | # TODO: this includes only first N items | |
3868 | for entry in self._grid_entries(renderer): | |
3869 | yield entry | |
3870 | renderer = content.get('horizontalListRenderer') | |
3871 | if renderer: | |
3872 | # TODO | |
3873 | pass | |
8bdd16b4 | 3874 | |
29f7c58a | 3875 | def _shelf_entries(self, shelf_renderer, skip_channels=False): |
8bdd16b4 | 3876 | ep = try_get( |
3877 | shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], | |
3878 | compat_str) | |
3879 | shelf_url = urljoin('https://www.youtube.com', ep) | |
3d3dddc9 | 3880 | if shelf_url: |
29f7c58a | 3881 | # Skipping links to another channels, note that checking for |
3882 | # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL | |
3883 | # will not work | |
3884 | if skip_channels and '/channels?' in shelf_url: | |
3885 | return | |
052e1350 | 3886 | title = self._get_text(shelf_renderer, 'title') |
3d3dddc9 | 3887 | yield self.url_result(shelf_url, video_title=title) |
3888 | # Shelf may not contain shelf URL, fallback to extraction from content | |
3889 | for entry in self._shelf_entries_from_content(shelf_renderer): | |
3890 | yield entry | |
c5e8d7af | 3891 | |
8bdd16b4 | 3892 | def _playlist_entries(self, video_list_renderer): |
3893 | for content in video_list_renderer['contents']: | |
3894 | if not isinstance(content, dict): | |
3895 | continue | |
3896 | renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer') | |
3897 | if not isinstance(renderer, dict): | |
3898 | continue | |
3899 | video_id = renderer.get('videoId') | |
3900 | if not video_id: | |
3901 | continue | |
3902 | yield self._extract_video(renderer) | |
07aeced6 | 3903 | |
3462ffa8 | 3904 | def _rich_entries(self, rich_grid_renderer): |
3905 | renderer = try_get( | |
70d5c17b | 3906 | rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {} |
3462ffa8 | 3907 | video_id = renderer.get('videoId') |
3908 | if not video_id: | |
3909 | return | |
3910 | yield self._extract_video(renderer) | |
3911 | ||
8bdd16b4 | 3912 | def _video_entry(self, video_renderer): |
3913 | video_id = video_renderer.get('videoId') | |
3914 | if video_id: | |
3915 | return self._extract_video(video_renderer) | |
dacb3a86 | 3916 | |
ad210f4f | 3917 | def _hashtag_tile_entry(self, hashtag_tile_renderer): |
3918 | url = urljoin('https://youtube.com', traverse_obj( | |
3919 | hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url'))) | |
3920 | if url: | |
3921 | return self.url_result( | |
3922 | url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag')) | |
3923 | ||
8bdd16b4 | 3924 | def _post_thread_entries(self, post_thread_renderer): |
3925 | post_renderer = try_get( | |
3926 | post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict) | |
3927 | if not post_renderer: | |
3928 | return | |
3929 | # video attachment | |
3930 | video_renderer = try_get( | |
895b0931 | 3931 | post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {} |
3932 | video_id = video_renderer.get('videoId') | |
3933 | if video_id: | |
3934 | entry = self._extract_video(video_renderer) | |
8bdd16b4 | 3935 | if entry: |
3936 | yield entry | |
895b0931 | 3937 | # playlist attachment |
3938 | playlist_id = try_get( | |
3939 | post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str) | |
3940 | if playlist_id: | |
3941 | yield self.url_result( | |
e28f1c0a | 3942 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, |
3943 | ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
8bdd16b4 | 3944 | # inline video links |
3945 | runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or [] | |
3946 | for run in runs: | |
3947 | if not isinstance(run, dict): | |
3948 | continue | |
3949 | ep_url = try_get( | |
3950 | run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str) | |
3951 | if not ep_url: | |
3952 | continue | |
3953 | if not YoutubeIE.suitable(ep_url): | |
3954 | continue | |
3955 | ep_video_id = YoutubeIE._match_id(ep_url) | |
3956 | if video_id == ep_video_id: | |
3957 | continue | |
895b0931 | 3958 | yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id) |
dacb3a86 | 3959 | |
8bdd16b4 | 3960 | def _post_thread_continuation_entries(self, post_thread_continuation): |
3961 | contents = post_thread_continuation.get('contents') | |
3962 | if not isinstance(contents, list): | |
3963 | return | |
3964 | for content in contents: | |
3965 | renderer = content.get('backstagePostThreadRenderer') | |
3966 | if not isinstance(renderer, dict): | |
3967 | continue | |
3968 | for entry in self._post_thread_entries(renderer): | |
3969 | yield entry | |
07aeced6 | 3970 | |
39ed931e | 3971 | r''' # unused |
3972 | def _rich_grid_entries(self, contents): | |
3973 | for content in contents: | |
3974 | video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict) | |
3975 | if video_renderer: | |
3976 | entry = self._video_entry(video_renderer) | |
3977 | if entry: | |
3978 | yield entry | |
3979 | ''' | |
52efa4b3 | 3980 | |
a6213a49 | 3981 | def _extract_entries(self, parent_renderer, continuation_list): |
3982 | # continuation_list is modified in-place with continuation_list = [continuation_token] | |
3983 | continuation_list[:] = [None] | |
3984 | contents = try_get(parent_renderer, lambda x: x['contents'], list) or [] | |
3985 | for content in contents: | |
3986 | if not isinstance(content, dict): | |
3987 | continue | |
16aa9ea4 | 3988 | is_renderer = traverse_obj( |
3989 | content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation', | |
3990 | expected_type=dict) | |
a6213a49 | 3991 | if not is_renderer: |
3992 | renderer = content.get('richItemRenderer') | |
3993 | if renderer: | |
3994 | for entry in self._rich_entries(renderer): | |
3995 | yield entry | |
3996 | continuation_list[0] = self._extract_continuation(parent_renderer) | |
3997 | continue | |
3998 | isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or [] | |
3999 | for isr_content in isr_contents: | |
4000 | if not isinstance(isr_content, dict): | |
8bdd16b4 | 4001 | continue |
69184e41 | 4002 | |
a6213a49 | 4003 | known_renderers = { |
4004 | 'playlistVideoListRenderer': self._playlist_entries, | |
4005 | 'gridRenderer': self._grid_entries, | |
a17526e4 | 4006 | 'reelShelfRenderer': self._grid_entries, |
4007 | 'shelfRenderer': self._shelf_entries, | |
16aa9ea4 | 4008 | 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)], |
a6213a49 | 4009 | 'backstagePostThreadRenderer': self._post_thread_entries, |
4010 | 'videoRenderer': lambda x: [self._video_entry(x)], | |
a61fd4cf | 4011 | 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}), |
4012 | 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}), | |
ad210f4f | 4013 | 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)] |
a6213a49 | 4014 | } |
4015 | for key, renderer in isr_content.items(): | |
4016 | if key not in known_renderers: | |
4017 | continue | |
4018 | for entry in known_renderers[key](renderer): | |
4019 | if entry: | |
4020 | yield entry | |
4021 | continuation_list[0] = self._extract_continuation(renderer) | |
4022 | break | |
70d5c17b | 4023 | |
4024 | if not continuation_list[0]: | |
a6213a49 | 4025 | continuation_list[0] = self._extract_continuation(is_renderer) |
3462ffa8 | 4026 | |
a6213a49 | 4027 | if not continuation_list[0]: |
4028 | continuation_list[0] = self._extract_continuation(parent_renderer) | |
4029 | ||
4030 | def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data): | |
4031 | continuation_list = [None] | |
4032 | extract_entries = lambda x: self._extract_entries(x, continuation_list) | |
29f7c58a | 4033 | tab_content = try_get(tab, lambda x: x['content'], dict) |
4034 | if not tab_content: | |
4035 | return | |
3462ffa8 | 4036 | parent_renderer = ( |
29f7c58a | 4037 | try_get(tab_content, lambda x: x['sectionListRenderer'], dict) |
4038 | or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {}) | |
70d5c17b | 4039 | for entry in extract_entries(parent_renderer): |
4040 | yield entry | |
3462ffa8 | 4041 | continuation = continuation_list[0] |
d069eca7 | 4042 | |
8bdd16b4 | 4043 | for page_num in itertools.count(1): |
4044 | if not continuation: | |
4045 | break | |
99e9e001 | 4046 | headers = self.generate_api_headers( |
4047 | ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data) | |
79360d99 | 4048 | response = self._extract_response( |
4049 | item_id='%s page %s' % (item_id, page_num), | |
fe93e2c4 | 4050 | query=continuation, headers=headers, ytcfg=ytcfg, |
79360d99 | 4051 | check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints')) |
a5c56234 M |
4052 | |
4053 | if not response: | |
8bdd16b4 | 4054 | break |
ac56cf38 | 4055 | # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases |
4056 | # See: https://github.com/ytdl-org/youtube-dl/issues/28702 | |
4057 | visitor_data = self._extract_visitor_data(response) or visitor_data | |
ebf1b291 | 4058 | |
69184e41 | 4059 | known_continuation_renderers = { |
4060 | 'playlistVideoListContinuation': self._playlist_entries, | |
4061 | 'gridContinuation': self._grid_entries, | |
4062 | 'itemSectionContinuation': self._post_thread_continuation_entries, | |
4063 | 'sectionListContinuation': extract_entries, # for feeds | |
4064 | } | |
8bdd16b4 | 4065 | continuation_contents = try_get( |
69184e41 | 4066 | response, lambda x: x['continuationContents'], dict) or {} |
4067 | continuation_renderer = None | |
4068 | for key, value in continuation_contents.items(): | |
4069 | if key not in known_continuation_renderers: | |
3462ffa8 | 4070 | continue |
69184e41 | 4071 | continuation_renderer = value |
4072 | continuation_list = [None] | |
4073 | for entry in known_continuation_renderers[key](continuation_renderer): | |
4074 | yield entry | |
4075 | continuation = continuation_list[0] or self._extract_continuation(continuation_renderer) | |
4076 | break | |
4077 | if continuation_renderer: | |
4078 | continue | |
c5e8d7af | 4079 | |
a1b535bd | 4080 | known_renderers = { |
e4b98809 | 4081 | 'videoRenderer': (self._grid_entries, 'items'), # for membership tab |
a1b535bd | 4082 | 'gridPlaylistRenderer': (self._grid_entries, 'items'), |
4083 | 'gridVideoRenderer': (self._grid_entries, 'items'), | |
d61fc646 | 4084 | 'gridChannelRenderer': (self._grid_entries, 'items'), |
a1b535bd | 4085 | 'playlistVideoRenderer': (self._playlist_entries, 'contents'), |
cd7c66cf | 4086 | 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds |
9ba5705a | 4087 | 'richItemRenderer': (extract_entries, 'contents'), # for hashtag |
26fe8ffe | 4088 | 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents') |
a1b535bd | 4089 | } |
cce889b9 | 4090 | on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints')) |
8bdd16b4 | 4091 | continuation_items = try_get( |
cce889b9 | 4092 | on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list) |
a1b535bd | 4093 | continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {} |
4094 | video_items_renderer = None | |
4095 | for key, value in continuation_item.items(): | |
4096 | if key not in known_renderers: | |
8bdd16b4 | 4097 | continue |
a1b535bd | 4098 | video_items_renderer = {known_renderers[key][1]: continuation_items} |
9ba5705a | 4099 | continuation_list = [None] |
a1b535bd | 4100 | for entry in known_renderers[key][0](video_items_renderer): |
4101 | yield entry | |
9ba5705a | 4102 | continuation = continuation_list[0] or self._extract_continuation(video_items_renderer) |
a1b535bd | 4103 | break |
4104 | if video_items_renderer: | |
4105 | continue | |
8bdd16b4 | 4106 | break |
9558dcec | 4107 | |
8bdd16b4 | 4108 | @staticmethod |
7c219ea6 | 4109 | def _extract_selected_tab(tabs, fatal=True): |
8bdd16b4 | 4110 | for tab in tabs: |
cd684175 | 4111 | renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {} |
4112 | if renderer.get('selected') is True: | |
4113 | return renderer | |
2b3c2546 | 4114 | else: |
7c219ea6 | 4115 | if fatal: |
4116 | raise ExtractorError('Unable to find selected tab') | |
b82f815f | 4117 | |
61d3665d | 4118 | def _extract_uploader(self, data): |
8bdd16b4 | 4119 | uploader = {} |
61d3665d | 4120 | renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {} |
47193e02 | 4121 | owner = try_get( |
4122 | renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict) | |
4123 | if owner: | |
61d3665d | 4124 | owner_text = owner.get('text') |
4125 | uploader['uploader'] = self._search_regex( | |
4126 | r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text) | |
47193e02 | 4127 | uploader['uploader_id'] = try_get( |
4128 | owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str) | |
4129 | uploader['uploader_url'] = urljoin( | |
4130 | 'https://www.youtube.com/', | |
4131 | try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str)) | |
9c3fe2ef | 4132 | return {k: v for k, v in uploader.items() if v is not None} |
8bdd16b4 | 4133 | |
ac56cf38 | 4134 | def _extract_from_tabs(self, item_id, ytcfg, data, tabs): |
b60419c5 | 4135 | playlist_id = title = description = channel_url = channel_name = channel_id = None |
ac56cf38 | 4136 | tags = [] |
b60419c5 | 4137 | |
8bdd16b4 | 4138 | selected_tab = self._extract_selected_tab(tabs) |
f0d785d3 | 4139 | primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') |
8bdd16b4 | 4140 | renderer = try_get( |
4141 | data, lambda x: x['metadata']['channelMetadataRenderer'], dict) | |
4142 | if renderer: | |
b60419c5 | 4143 | channel_name = renderer.get('title') |
4144 | channel_url = renderer.get('channelUrl') | |
4145 | channel_id = renderer.get('externalId') | |
39ed931e | 4146 | else: |
64c0d954 | 4147 | renderer = try_get( |
4148 | data, lambda x: x['metadata']['playlistMetadataRenderer'], dict) | |
39ed931e | 4149 | |
8bdd16b4 | 4150 | if renderer: |
4151 | title = renderer.get('title') | |
ecc97af3 | 4152 | description = renderer.get('description', '') |
b60419c5 | 4153 | playlist_id = channel_id |
4154 | tags = renderer.get('keywords', '').split() | |
b60419c5 | 4155 | |
301d07fc | 4156 | # We can get the uncropped banner/avatar by replacing the crop params with '=s0' |
4157 | # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714 | |
4158 | def _get_uncropped(url): | |
4159 | return url_or_none((url or '').split('=')[0] + '=s0') | |
4160 | ||
4161 | avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar') | |
4162 | if avatar_thumbnails: | |
4163 | uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url']) | |
4164 | if uncropped_avatar: | |
4165 | avatar_thumbnails.append({ | |
4166 | 'url': uncropped_avatar, | |
4167 | 'id': 'avatar_uncropped', | |
4168 | 'preference': 1 | |
4169 | }) | |
4170 | ||
4171 | channel_banners = self._extract_thumbnails( | |
4172 | data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner'])) | |
4173 | for banner in channel_banners: | |
4174 | banner['preference'] = -10 | |
4175 | ||
4176 | if channel_banners: | |
4177 | uncropped_banner = _get_uncropped(channel_banners[0]['url']) | |
4178 | if uncropped_banner: | |
4179 | channel_banners.append({ | |
4180 | 'url': uncropped_banner, | |
4181 | 'id': 'banner_uncropped', | |
4182 | 'preference': -5 | |
4183 | }) | |
4184 | ||
4185 | primary_thumbnails = self._extract_thumbnails( | |
a17526e4 | 4186 | primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail')) |
a709d873 | 4187 | |
3462ffa8 | 4188 | if playlist_id is None: |
70d5c17b | 4189 | playlist_id = item_id |
f0d785d3 | 4190 | |
4191 | playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats') | |
4192 | last_updated_unix, _ = self._extract_time_text(playlist_stats, 2) | |
70d5c17b | 4193 | if title is None: |
f0d785d3 | 4194 | title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id |
b60419c5 | 4195 | title += format_field(selected_tab, 'title', ' - %s') |
cd684175 | 4196 | title += format_field(selected_tab, 'expandedText', ' - %s') |
f0d785d3 | 4197 | |
b60419c5 | 4198 | metadata = { |
4199 | 'playlist_id': playlist_id, | |
4200 | 'playlist_title': title, | |
4201 | 'playlist_description': description, | |
4202 | 'uploader': channel_name, | |
4203 | 'uploader_id': channel_id, | |
4204 | 'uploader_url': channel_url, | |
301d07fc | 4205 | 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners, |
b60419c5 | 4206 | 'tags': tags, |
f0d785d3 | 4207 | 'view_count': self._get_count(playlist_stats, 1), |
4208 | 'availability': self._extract_availability(data), | |
4209 | 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'), | |
6c73052c | 4210 | 'playlist_count': self._get_count(playlist_stats, 0), |
4211 | 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')), | |
b60419c5 | 4212 | } |
4213 | if not channel_id: | |
4214 | metadata.update(self._extract_uploader(data)) | |
4215 | metadata.update({ | |
4216 | 'channel': metadata['uploader'], | |
4217 | 'channel_id': metadata['uploader_id'], | |
4218 | 'channel_url': metadata['uploader_url']}) | |
4219 | return self.playlist_result( | |
d069eca7 | 4220 | self._entries( |
ac56cf38 | 4221 | selected_tab, playlist_id, ytcfg, |
4222 | self._extract_account_syncid(ytcfg, data), | |
4223 | self._extract_visitor_data(data, ytcfg)), | |
b60419c5 | 4224 | **metadata) |
73c4ac2c | 4225 | |
ac56cf38 | 4226 | def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg): |
4227 | first_id = last_id = response = None | |
2be71994 | 4228 | for page_num in itertools.count(1): |
cd7c66cf | 4229 | videos = list(self._playlist_entries(playlist)) |
4230 | if not videos: | |
4231 | return | |
2be71994 | 4232 | start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1 |
4233 | if start >= len(videos): | |
4234 | return | |
4235 | for video in videos[start:]: | |
4236 | if video['id'] == first_id: | |
4237 | self.to_screen('First video %s found again; Assuming end of Mix' % first_id) | |
4238 | return | |
4239 | yield video | |
4240 | first_id = first_id or videos[0]['id'] | |
4241 | last_id = videos[-1]['id'] | |
79360d99 | 4242 | watch_endpoint = try_get( |
4243 | playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint']) | |
ac56cf38 | 4244 | headers = self.generate_api_headers( |
4245 | ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data), | |
4246 | visitor_data=self._extract_visitor_data(response, data, ytcfg)) | |
79360d99 | 4247 | query = { |
4248 | 'playlistId': playlist_id, | |
4249 | 'videoId': watch_endpoint.get('videoId') or last_id, | |
4250 | 'index': watch_endpoint.get('index') or len(videos), | |
4251 | 'params': watch_endpoint.get('params') or 'OAE%3D' | |
4252 | } | |
4253 | response = self._extract_response( | |
4254 | item_id='%s page %d' % (playlist_id, page_num), | |
fe93e2c4 | 4255 | query=query, ep='next', headers=headers, ytcfg=ytcfg, |
79360d99 | 4256 | check_get_keys='contents' |
4257 | ) | |
cd7c66cf | 4258 | playlist = try_get( |
79360d99 | 4259 | response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict) |
cd7c66cf | 4260 | |
ac56cf38 | 4261 | def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg): |
8bdd16b4 | 4262 | title = playlist.get('title') or try_get( |
4263 | data, lambda x: x['titleText']['simpleText'], compat_str) | |
4264 | playlist_id = playlist.get('playlistId') or item_id | |
cd7c66cf | 4265 | |
4266 | # Delegating everything except mix playlists to regular tab-based playlist URL | |
29f7c58a | 4267 | playlist_url = urljoin(url, try_get( |
4268 | playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'], | |
4269 | compat_str)) | |
4270 | if playlist_url and playlist_url != url: | |
4271 | return self.url_result( | |
4272 | playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id, | |
4273 | video_title=title) | |
cd7c66cf | 4274 | |
8bdd16b4 | 4275 | return self.playlist_result( |
ac56cf38 | 4276 | self._extract_mix_playlist(playlist, playlist_id, data, ytcfg), |
cd7c66cf | 4277 | playlist_id=playlist_id, playlist_title=title) |
c5e8d7af | 4278 | |
47193e02 | 4279 | def _extract_availability(self, data): |
4280 | """ | |
4281 | Gets the availability of a given playlist/tab. | |
4282 | Note: Unless YouTube tells us explicitly, we do not assume it is public | |
4283 | @param data: response | |
4284 | """ | |
4285 | is_private = is_unlisted = None | |
4286 | renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {} | |
4287 | badge_labels = self._extract_badges(renderer) | |
4288 | ||
4289 | # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge | |
4290 | privacy_dropdown_entries = try_get( | |
4291 | renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or [] | |
4292 | for renderer_dict in privacy_dropdown_entries: | |
4293 | is_selected = try_get( | |
4294 | renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False | |
4295 | if not is_selected: | |
4296 | continue | |
052e1350 | 4297 | label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label')) |
47193e02 | 4298 | if label: |
4299 | badge_labels.add(label.lower()) | |
4300 | break | |
4301 | ||
4302 | for badge_label in badge_labels: | |
4303 | if badge_label == 'unlisted': | |
4304 | is_unlisted = True | |
4305 | elif badge_label == 'private': | |
4306 | is_private = True | |
4307 | elif badge_label == 'public': | |
4308 | is_unlisted = is_private = False | |
4309 | return self._availability(is_private, False, False, False, is_unlisted) | |
4310 | ||
4311 | @staticmethod | |
4312 | def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict): | |
4313 | sidebar_renderer = try_get( | |
4314 | data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or [] | |
4315 | for item in sidebar_renderer: | |
4316 | renderer = try_get(item, lambda x: x[info_renderer], expected_type) | |
4317 | if renderer: | |
4318 | return renderer | |
4319 | ||
ac56cf38 | 4320 | def _reload_with_unavailable_videos(self, item_id, data, ytcfg): |
358de58c | 4321 | """ |
4322 | Get playlist with unavailable videos if the 'show unavailable videos' button exists. | |
4323 | """ | |
5d342002 | 4324 | browse_id = params = None |
47193e02 | 4325 | renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') |
4326 | if not renderer: | |
4327 | return | |
4328 | menu_renderer = try_get( | |
4329 | renderer, lambda x: x['menu']['menuRenderer']['items'], list) or [] | |
4330 | for menu_item in menu_renderer: | |
4331 | if not isinstance(menu_item, dict): | |
358de58c | 4332 | continue |
47193e02 | 4333 | nav_item_renderer = menu_item.get('menuNavigationItemRenderer') |
4334 | text = try_get( | |
4335 | nav_item_renderer, lambda x: x['text']['simpleText'], compat_str) | |
4336 | if not text or text.lower() != 'show unavailable videos': | |
4337 | continue | |
4338 | browse_endpoint = try_get( | |
4339 | nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {} | |
4340 | browse_id = browse_endpoint.get('browseId') | |
4341 | params = browse_endpoint.get('params') | |
4342 | break | |
5d342002 | 4343 | |
11f9be09 | 4344 | headers = self.generate_api_headers( |
99e9e001 | 4345 | ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data), |
ac56cf38 | 4346 | visitor_data=self._extract_visitor_data(data, ytcfg)) |
47193e02 | 4347 | query = { |
4348 | 'params': params or 'wgYCCAA=', | |
4349 | 'browseId': browse_id or 'VL%s' % item_id | |
4350 | } | |
4351 | return self._extract_response( | |
4352 | item_id=item_id, headers=headers, query=query, | |
fe93e2c4 | 4353 | check_get_keys='contents', fatal=False, ytcfg=ytcfg, |
47193e02 | 4354 | note='Downloading API JSON with unavailable videos') |
358de58c | 4355 | |
a25bca9f | 4356 | @property |
4357 | def skip_webpage(self): | |
4358 | return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) | |
4359 | ||
ac56cf38 | 4360 | def _extract_webpage(self, url, item_id, fatal=True): |
a06916d9 | 4361 | retries = self.get_param('extractor_retries', 3) |
62bff2c1 | 4362 | count = -1 |
ac56cf38 | 4363 | webpage = data = last_error = None |
14fdfea9 | 4364 | while count < retries: |
62bff2c1 | 4365 | count += 1 |
14fdfea9 | 4366 | # Sometimes youtube returns a webpage with incomplete ytInitialData |
62bff2c1 | 4367 | # See: https://github.com/yt-dlp/yt-dlp/issues/116 |
ac56cf38 | 4368 | if last_error: |
c705177d | 4369 | self.report_warning('%s. Retrying ...' % last_error) |
ac56cf38 | 4370 | try: |
4371 | webpage = self._download_webpage( | |
4372 | url, item_id, | |
4373 | note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',)) | |
4374 | data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {} | |
4375 | except ExtractorError as e: | |
4376 | if isinstance(e.cause, network_exceptions): | |
4377 | if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429): | |
4378 | last_error = error_to_compat_str(e.cause or e.msg) | |
4379 | if count < retries: | |
4380 | continue | |
4381 | if fatal: | |
4382 | raise | |
4383 | self.report_warning(error_to_compat_str(e)) | |
14fdfea9 | 4384 | break |
ac56cf38 | 4385 | else: |
4386 | try: | |
4387 | self._extract_and_report_alerts(data) | |
4388 | except ExtractorError as e: | |
4389 | if fatal: | |
4390 | raise | |
4391 | self.report_warning(error_to_compat_str(e)) | |
4392 | break | |
4393 | ||
7c219ea6 | 4394 | if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')): |
ac56cf38 | 4395 | break |
4396 | ||
4397 | last_error = 'Incomplete yt initial data received' | |
4398 | if count >= retries: | |
4399 | if fatal: | |
4400 | raise ExtractorError(last_error) | |
4401 | self.report_warning(last_error) | |
4402 | break | |
4403 | ||
cd7c66cf | 4404 | return webpage, data |
4405 | ||
a25bca9f | 4406 | def _report_playlist_authcheck(self, ytcfg, fatal=True): |
4407 | """Use if failed to extract ytcfg (and data) from initial webpage""" | |
4408 | if not ytcfg and self.is_authenticated: | |
4409 | msg = 'Playlists that require authentication may not extract correctly without a successful webpage download' | |
4410 | if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal: | |
4411 | raise ExtractorError( | |
4412 | f'{msg}. If you are not downloading private content, or ' | |
4413 | 'your cookies are only for the first account and channel,' | |
4414 | ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check', | |
4415 | expected=True) | |
4416 | self.report_warning(msg, only_once=True) | |
4417 | ||
ac56cf38 | 4418 | def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'): |
4419 | data = None | |
a25bca9f | 4420 | if not self.skip_webpage: |
ac56cf38 | 4421 | webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal) |
4422 | ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage) | |
1108613f | 4423 | # Reject webpage data if redirected to home page without explicitly requesting |
4424 | selected_tab = self._extract_selected_tab(traverse_obj( | |
7c219ea6 | 4425 | data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {} |
1108613f | 4426 | if (url != 'https://www.youtube.com/feed/recommended' |
4427 | and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page | |
4428 | and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])): | |
4429 | msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page' | |
4430 | if fatal: | |
4431 | raise ExtractorError(msg, expected=True) | |
4432 | self.report_warning(msg, only_once=True) | |
ac56cf38 | 4433 | if not data: |
a25bca9f | 4434 | self._report_playlist_authcheck(ytcfg, fatal=fatal) |
ac56cf38 | 4435 | data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client) |
4436 | return data, ytcfg | |
4437 | ||
4438 | def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'): | |
4439 | headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client) | |
4440 | resolve_response = self._extract_response( | |
4441 | item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal, | |
4442 | ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client) | |
4443 | endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'} | |
4444 | for ep_key, ep in endpoints.items(): | |
4445 | params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict) | |
4446 | if params: | |
4447 | return self._extract_response( | |
4448 | item_id=item_id, query=params, ep=ep, headers=headers, | |
4449 | ytcfg=ytcfg, fatal=fatal, default_client=default_client, | |
7c219ea6 | 4450 | check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')) |
ac56cf38 | 4451 | err_note = 'Failed to resolve url (does the playlist exist?)' |
4452 | if fatal: | |
4453 | raise ExtractorError(err_note, expected=True) | |
4454 | self.report_warning(err_note, item_id) | |
4455 | ||
a6213a49 | 4456 | _SEARCH_PARAMS = None |
4457 | ||
af5c1c55 | 4458 | def _search_results(self, query, params=NO_DEFAULT, default_client='web'): |
a6213a49 | 4459 | data = {'query': query} |
4460 | if params is NO_DEFAULT: | |
4461 | params = self._SEARCH_PARAMS | |
4462 | if params: | |
4463 | data['params'] = params | |
16aa9ea4 | 4464 | |
4465 | content_keys = ( | |
4466 | ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'), | |
4467 | ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'), | |
4468 | # ytmusic search | |
4469 | ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'), | |
4470 | ('continuationContents', ), | |
4471 | ) | |
a25bca9f | 4472 | display_id = f'query "{query}"' |
16aa9ea4 | 4473 | check_get_keys = tuple(set(keys[0] for keys in content_keys)) |
a25bca9f | 4474 | ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {} |
4475 | self._report_playlist_authcheck(ytcfg, fatal=False) | |
16aa9ea4 | 4476 | |
a61fd4cf | 4477 | continuation_list = [None] |
a25bca9f | 4478 | search = None |
a6213a49 | 4479 | for page_num in itertools.count(1): |
a61fd4cf | 4480 | data.update(continuation_list[0] or {}) |
a25bca9f | 4481 | headers = self.generate_api_headers( |
4482 | ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client) | |
a6213a49 | 4483 | search = self._extract_response( |
a25bca9f | 4484 | item_id=f'{display_id} page {page_num}', ep='search', query=data, |
4485 | default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers) | |
16aa9ea4 | 4486 | slr_contents = traverse_obj(search, *content_keys) |
4487 | yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list) | |
a61fd4cf | 4488 | if not continuation_list[0]: |
a6213a49 | 4489 | break |
4490 | ||
4491 | ||
4492 | class YoutubeTabIE(YoutubeTabBaseInfoExtractor): | |
4493 | IE_DESC = 'YouTube Tabs' | |
4494 | _VALID_URL = r'''(?x: | |
4495 | https?:// | |
4496 | (?:\w+\.)? | |
4497 | (?: | |
4498 | youtube(?:kids)?\.com| | |
4499 | %(invidious)s | |
4500 | )/ | |
4501 | (?: | |
4502 | (?P<channel_type>channel|c|user|browse)/| | |
4503 | (?P<not_channel> | |
4504 | feed/|hashtag/| | |
4505 | (?:playlist|watch)\?.*?\blist= | |
4506 | )| | |
4507 | (?!(?:%(reserved_names)s)\b) # Direct URLs | |
4508 | ) | |
4509 | (?P<id>[^/?\#&]+) | |
4510 | )''' % { | |
4511 | 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES, | |
4512 | 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), | |
4513 | } | |
4514 | IE_NAME = 'youtube:tab' | |
4515 | ||
4516 | _TESTS = [{ | |
4517 | 'note': 'playlists, multipage', | |
4518 | 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid', | |
4519 | 'playlist_mincount': 94, | |
4520 | 'info_dict': { | |
4521 | 'id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
976ae3ea | 4522 | 'title': 'Igor Kleiner - Playlists', |
a6213a49 | 4523 | 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', |
976ae3ea | 4524 | 'uploader': 'Igor Kleiner', |
a6213a49 | 4525 | 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', |
976ae3ea | 4526 | 'channel': 'Igor Kleiner', |
4527 | 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
4528 | 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'], | |
4529 | 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', | |
4530 | 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', | |
6c73052c | 4531 | 'channel_follower_count': int |
a6213a49 | 4532 | }, |
4533 | }, { | |
4534 | 'note': 'playlists, multipage, different order', | |
4535 | 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', | |
4536 | 'playlist_mincount': 94, | |
4537 | 'info_dict': { | |
4538 | 'id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
976ae3ea | 4539 | 'title': 'Igor Kleiner - Playlists', |
a6213a49 | 4540 | 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2', |
4541 | 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
976ae3ea | 4542 | 'uploader': 'Igor Kleiner', |
4543 | 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', | |
4544 | 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'], | |
4545 | 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg', | |
4546 | 'channel': 'Igor Kleiner', | |
4547 | 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg', | |
6c73052c | 4548 | 'channel_follower_count': int |
a6213a49 | 4549 | }, |
4550 | }, { | |
4551 | 'note': 'playlists, series', | |
4552 | 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3', | |
4553 | 'playlist_mincount': 5, | |
4554 | 'info_dict': { | |
4555 | 'id': 'UCYO_jab_esuFRV4b17AJtAw', | |
4556 | 'title': '3Blue1Brown - Playlists', | |
4557 | 'description': 'md5:e1384e8a133307dd10edee76e875d62f', | |
4558 | 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
4559 | 'uploader': '3Blue1Brown', | |
976ae3ea | 4560 | 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', |
4561 | 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', | |
4562 | 'channel': '3Blue1Brown', | |
4563 | 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
4564 | 'tags': ['Mathematics'], | |
6c73052c | 4565 | 'channel_follower_count': int |
a6213a49 | 4566 | }, |
4567 | }, { | |
4568 | 'note': 'playlists, singlepage', | |
4569 | 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', | |
4570 | 'playlist_mincount': 4, | |
4571 | 'info_dict': { | |
4572 | 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
4573 | 'title': 'ThirstForScience - Playlists', | |
4574 | 'description': 'md5:609399d937ea957b0f53cbffb747a14c', | |
4575 | 'uploader': 'ThirstForScience', | |
4576 | 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
976ae3ea | 4577 | 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ', |
4578 | 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ', | |
4579 | 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ', | |
4580 | 'tags': 'count:13', | |
4581 | 'channel': 'ThirstForScience', | |
6c73052c | 4582 | 'channel_follower_count': int |
a6213a49 | 4583 | } |
4584 | }, { | |
4585 | 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists', | |
4586 | 'only_matching': True, | |
4587 | }, { | |
4588 | 'note': 'basic, single video playlist', | |
4589 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
4590 | 'info_dict': { | |
4591 | 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
4592 | 'uploader': 'Sergey M.', | |
4593 | 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
4594 | 'title': 'youtube-dl public playlist', | |
976ae3ea | 4595 | 'description': '', |
4596 | 'tags': [], | |
4597 | 'view_count': int, | |
4598 | 'modified_date': '20201130', | |
4599 | 'channel': 'Sergey M.', | |
4600 | 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
4601 | 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4602 | 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
a6213a49 | 4603 | }, |
4604 | 'playlist_count': 1, | |
4605 | }, { | |
4606 | 'note': 'empty playlist', | |
4607 | 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', | |
4608 | 'info_dict': { | |
4609 | 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
4610 | 'uploader': 'Sergey M.', | |
4611 | 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf', | |
4612 | 'title': 'youtube-dl empty playlist', | |
976ae3ea | 4613 | 'tags': [], |
4614 | 'channel': 'Sergey M.', | |
4615 | 'description': '', | |
4616 | 'modified_date': '20160902', | |
4617 | 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA', | |
4618 | 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4619 | 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
a6213a49 | 4620 | }, |
4621 | 'playlist_count': 0, | |
4622 | }, { | |
4623 | 'note': 'Home tab', | |
4624 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured', | |
4625 | 'info_dict': { | |
4626 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4627 | 'title': 'lex will - Home', | |
4628 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4629 | 'uploader': 'lex will', | |
4630 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
976ae3ea | 4631 | 'channel': 'lex will', |
4632 | 'tags': ['bible', 'history', 'prophesy'], | |
4633 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4634 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4635 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
6c73052c | 4636 | 'channel_follower_count': int |
a6213a49 | 4637 | }, |
4638 | 'playlist_mincount': 2, | |
4639 | }, { | |
4640 | 'note': 'Videos tab', | |
4641 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos', | |
4642 | 'info_dict': { | |
4643 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4644 | 'title': 'lex will - Videos', | |
4645 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4646 | 'uploader': 'lex will', | |
4647 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
976ae3ea | 4648 | 'tags': ['bible', 'history', 'prophesy'], |
4649 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4650 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4651 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4652 | 'channel': 'lex will', | |
6c73052c | 4653 | 'channel_follower_count': int |
a6213a49 | 4654 | }, |
4655 | 'playlist_mincount': 975, | |
4656 | }, { | |
4657 | 'note': 'Videos tab, sorted by popular', | |
4658 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid', | |
4659 | 'info_dict': { | |
4660 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4661 | 'title': 'lex will - Videos', | |
4662 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4663 | 'uploader': 'lex will', | |
4664 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
976ae3ea | 4665 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', |
4666 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4667 | 'channel': 'lex will', | |
4668 | 'tags': ['bible', 'history', 'prophesy'], | |
4669 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
6c73052c | 4670 | 'channel_follower_count': int |
a6213a49 | 4671 | }, |
4672 | 'playlist_mincount': 199, | |
4673 | }, { | |
4674 | 'note': 'Playlists tab', | |
4675 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists', | |
4676 | 'info_dict': { | |
4677 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4678 | 'title': 'lex will - Playlists', | |
4679 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4680 | 'uploader': 'lex will', | |
4681 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
976ae3ea | 4682 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', |
4683 | 'channel': 'lex will', | |
4684 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4685 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4686 | 'tags': ['bible', 'history', 'prophesy'], | |
6c73052c | 4687 | 'channel_follower_count': int |
a6213a49 | 4688 | }, |
4689 | 'playlist_mincount': 17, | |
4690 | }, { | |
4691 | 'note': 'Community tab', | |
4692 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community', | |
4693 | 'info_dict': { | |
4694 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4695 | 'title': 'lex will - Community', | |
4696 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4697 | 'uploader': 'lex will', | |
4698 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
976ae3ea | 4699 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', |
4700 | 'channel': 'lex will', | |
4701 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4702 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4703 | 'tags': ['bible', 'history', 'prophesy'], | |
6c73052c | 4704 | 'channel_follower_count': int |
a6213a49 | 4705 | }, |
4706 | 'playlist_mincount': 18, | |
4707 | }, { | |
4708 | 'note': 'Channels tab', | |
4709 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels', | |
4710 | 'info_dict': { | |
4711 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4712 | 'title': 'lex will - Channels', | |
4713 | 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488', | |
4714 | 'uploader': 'lex will', | |
4715 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
976ae3ea | 4716 | 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', |
4717 | 'channel': 'lex will', | |
4718 | 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
4719 | 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
4720 | 'tags': ['bible', 'history', 'prophesy'], | |
6c73052c | 4721 | 'channel_follower_count': int |
a6213a49 | 4722 | }, |
4723 | 'playlist_mincount': 12, | |
4724 | }, { | |
4725 | 'note': 'Search tab', | |
4726 | 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra', | |
4727 | 'playlist_mincount': 40, | |
4728 | 'info_dict': { | |
4729 | 'id': 'UCYO_jab_esuFRV4b17AJtAw', | |
4730 | 'title': '3Blue1Brown - Search - linear algebra', | |
4731 | 'description': 'md5:e1384e8a133307dd10edee76e875d62f', | |
4732 | 'uploader': '3Blue1Brown', | |
4733 | 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
976ae3ea | 4734 | 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', |
4735 | 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw', | |
4736 | 'tags': ['Mathematics'], | |
4737 | 'channel': '3Blue1Brown', | |
4738 | 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw', | |
6c73052c | 4739 | 'channel_follower_count': int |
a6213a49 | 4740 | }, |
4741 | }, { | |
4742 | 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4743 | 'only_matching': True, | |
4744 | }, { | |
4745 | 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4746 | 'only_matching': True, | |
4747 | }, { | |
4748 | 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA', | |
4749 | 'only_matching': True, | |
4750 | }, { | |
4751 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
4752 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
4753 | 'info_dict': { | |
4754 | 'title': '29C3: Not my department', | |
4755 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
4756 | 'uploader': 'Christiaan008', | |
4757 | 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg', | |
4758 | 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268', | |
976ae3ea | 4759 | 'tags': [], |
4760 | 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008', | |
4761 | 'view_count': int, | |
4762 | 'modified_date': '20150605', | |
4763 | 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg', | |
4764 | 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008', | |
4765 | 'channel': 'Christiaan008', | |
a6213a49 | 4766 | }, |
4767 | 'playlist_count': 96, | |
4768 | }, { | |
4769 | 'note': 'Large playlist', | |
4770 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
4771 | 'info_dict': { | |
4772 | 'title': 'Uploads from Cauchemar', | |
4773 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', | |
4774 | 'uploader': 'Cauchemar', | |
4775 | 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q', | |
976ae3ea | 4776 | 'channel_url': 'https://www.youtube.com/c/Cauchemar89', |
4777 | 'tags': [], | |
4778 | 'modified_date': r're:\d{8}', | |
4779 | 'channel': 'Cauchemar', | |
4780 | 'uploader_url': 'https://www.youtube.com/c/Cauchemar89', | |
4781 | 'view_count': int, | |
4782 | 'description': '', | |
4783 | 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q', | |
a6213a49 | 4784 | }, |
4785 | 'playlist_mincount': 1123, | |
976ae3ea | 4786 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], |
a6213a49 | 4787 | }, { |
4788 | 'note': 'even larger playlist, 8832 videos', | |
4789 | 'url': 'http://www.youtube.com/user/NASAgovVideo/videos', | |
4790 | 'only_matching': True, | |
4791 | }, { | |
4792 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
4793 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
4794 | 'info_dict': { | |
4795 | 'title': 'Uploads from Interstellar Movie', | |
4796 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
4797 | 'uploader': 'Interstellar Movie', | |
4798 | 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA', | |
976ae3ea | 4799 | 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie', |
4800 | 'tags': [], | |
4801 | 'view_count': int, | |
4802 | 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA', | |
4803 | 'channel_url': 'https://www.youtube.com/c/InterstellarMovie', | |
4804 | 'channel': 'Interstellar Movie', | |
4805 | 'description': '', | |
4806 | 'modified_date': r're:\d{8}', | |
a6213a49 | 4807 | }, |
4808 | 'playlist_mincount': 21, | |
4809 | }, { | |
4810 | 'note': 'Playlist with "show unavailable videos" button', | |
4811 | 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q', | |
4812 | 'info_dict': { | |
4813 | 'title': 'Uploads from Phim Siêu Nhân Nhật Bản', | |
4814 | 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q', | |
4815 | 'uploader': 'Phim Siêu Nhân Nhật Bản', | |
4816 | 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q', | |
976ae3ea | 4817 | 'view_count': int, |
4818 | 'channel': 'Phim Siêu Nhân Nhật Bản', | |
4819 | 'tags': [], | |
4820 | 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q', | |
4821 | 'description': '', | |
4822 | 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q', | |
4823 | 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q', | |
4824 | 'modified_date': r're:\d{8}', | |
a6213a49 | 4825 | }, |
4826 | 'playlist_mincount': 200, | |
976ae3ea | 4827 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], |
a6213a49 | 4828 | }, { |
4829 | 'note': 'Playlist with unavailable videos in page 7', | |
4830 | 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w', | |
4831 | 'info_dict': { | |
4832 | 'title': 'Uploads from BlankTV', | |
4833 | 'id': 'UU8l9frL61Yl5KFOl87nIm2w', | |
4834 | 'uploader': 'BlankTV', | |
4835 | 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w', | |
976ae3ea | 4836 | 'channel': 'BlankTV', |
4837 | 'channel_url': 'https://www.youtube.com/c/blanktv', | |
4838 | 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w', | |
4839 | 'view_count': int, | |
4840 | 'tags': [], | |
4841 | 'uploader_url': 'https://www.youtube.com/c/blanktv', | |
4842 | 'modified_date': r're:\d{8}', | |
4843 | 'description': '', | |
a6213a49 | 4844 | }, |
4845 | 'playlist_mincount': 1000, | |
976ae3ea | 4846 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], |
a6213a49 | 4847 | }, { |
4848 | 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844', | |
4849 | 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
4850 | 'info_dict': { | |
4851 | 'title': 'Data Analysis with Dr Mike Pound', | |
4852 | 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
4853 | 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA', | |
4854 | 'uploader': 'Computerphile', | |
4855 | 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487', | |
976ae3ea | 4856 | 'uploader_url': 'https://www.youtube.com/user/Computerphile', |
4857 | 'tags': [], | |
4858 | 'view_count': int, | |
4859 | 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA', | |
4860 | 'channel_url': 'https://www.youtube.com/user/Computerphile', | |
4861 | 'channel': 'Computerphile', | |
a6213a49 | 4862 | }, |
4863 | 'playlist_mincount': 11, | |
4864 | }, { | |
4865 | 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc', | |
4866 | 'only_matching': True, | |
4867 | }, { | |
4868 | 'note': 'Playlist URL that does not actually serve a playlist', | |
4869 | 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', | |
4870 | 'info_dict': { | |
4871 | 'id': 'FqZTN594JQw', | |
4872 | 'ext': 'webm', | |
4873 | 'title': "Smiley's People 01 detective, Adventure Series, Action", | |
4874 | 'uploader': 'STREEM', | |
4875 | 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng', | |
4876 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng', | |
4877 | 'upload_date': '20150526', | |
4878 | 'license': 'Standard YouTube License', | |
4879 | 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', | |
4880 | 'categories': ['People & Blogs'], | |
4881 | 'tags': list, | |
4882 | 'view_count': int, | |
4883 | 'like_count': int, | |
a6213a49 | 4884 | }, |
4885 | 'params': { | |
4886 | 'skip_download': True, | |
4887 | }, | |
4888 | 'skip': 'This video is not available.', | |
4889 | 'add_ie': [YoutubeIE.ie_key()], | |
4890 | }, { | |
4891 | 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g', | |
4892 | 'only_matching': True, | |
4893 | }, { | |
4894 | 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', | |
4895 | 'only_matching': True, | |
4896 | }, { | |
4897 | 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live', | |
4898 | 'info_dict': { | |
6c73052c | 4899 | 'id': 'GgL890LIznQ', # This will keep changing |
a6213a49 | 4900 | 'ext': 'mp4', |
976ae3ea | 4901 | 'title': str, |
a6213a49 | 4902 | 'uploader': 'Sky News', |
4903 | 'uploader_id': 'skynews', | |
4904 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews', | |
4905 | 'upload_date': r're:\d{8}', | |
976ae3ea | 4906 | 'description': str, |
a6213a49 | 4907 | 'categories': ['News & Politics'], |
4908 | 'tags': list, | |
4909 | 'like_count': int, | |
6c73052c | 4910 | 'release_timestamp': 1642502819, |
976ae3ea | 4911 | 'channel': 'Sky News', |
4912 | 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ', | |
4913 | 'age_limit': 0, | |
4914 | 'view_count': int, | |
6c73052c | 4915 | 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg', |
976ae3ea | 4916 | 'playable_in_embed': True, |
6c73052c | 4917 | 'release_date': '20220118', |
976ae3ea | 4918 | 'availability': 'public', |
4919 | 'live_status': 'is_live', | |
4920 | 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ', | |
6c73052c | 4921 | 'channel_follower_count': int |
a6213a49 | 4922 | }, |
4923 | 'params': { | |
4924 | 'skip_download': True, | |
4925 | }, | |
976ae3ea | 4926 | 'expected_warnings': ['Ignoring subtitle tracks found in '], |
a6213a49 | 4927 | }, { |
4928 | 'url': 'https://www.youtube.com/user/TheYoungTurks/live', | |
4929 | 'info_dict': { | |
4930 | 'id': 'a48o2S1cPoo', | |
4931 | 'ext': 'mp4', | |
4932 | 'title': 'The Young Turks - Live Main Show', | |
4933 | 'uploader': 'The Young Turks', | |
4934 | 'uploader_id': 'TheYoungTurks', | |
4935 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks', | |
4936 | 'upload_date': '20150715', | |
4937 | 'license': 'Standard YouTube License', | |
4938 | 'description': 'md5:438179573adcdff3c97ebb1ee632b891', | |
4939 | 'categories': ['News & Politics'], | |
4940 | 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], | |
4941 | 'like_count': int, | |
a6213a49 | 4942 | }, |
4943 | 'params': { | |
4944 | 'skip_download': True, | |
4945 | }, | |
4946 | 'only_matching': True, | |
4947 | }, { | |
4948 | 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', | |
4949 | 'only_matching': True, | |
4950 | }, { | |
4951 | 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', | |
4952 | 'only_matching': True, | |
4953 | }, { | |
4954 | 'note': 'A channel that is not live. Should raise error', | |
4955 | 'url': 'https://www.youtube.com/user/numberphile/live', | |
4956 | 'only_matching': True, | |
4957 | }, { | |
4958 | 'url': 'https://www.youtube.com/feed/trending', | |
4959 | 'only_matching': True, | |
4960 | }, { | |
4961 | 'url': 'https://www.youtube.com/feed/library', | |
4962 | 'only_matching': True, | |
4963 | }, { | |
4964 | 'url': 'https://www.youtube.com/feed/history', | |
4965 | 'only_matching': True, | |
4966 | }, { | |
4967 | 'url': 'https://www.youtube.com/feed/subscriptions', | |
4968 | 'only_matching': True, | |
4969 | }, { | |
4970 | 'url': 'https://www.youtube.com/feed/watch_later', | |
4971 | 'only_matching': True, | |
4972 | }, { | |
4973 | 'note': 'Recommended - redirects to home page.', | |
4974 | 'url': 'https://www.youtube.com/feed/recommended', | |
4975 | 'only_matching': True, | |
4976 | }, { | |
4977 | 'note': 'inline playlist with not always working continuations', | |
4978 | 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C', | |
4979 | 'only_matching': True, | |
4980 | }, { | |
4981 | 'url': 'https://www.youtube.com/course', | |
4982 | 'only_matching': True, | |
4983 | }, { | |
4984 | 'url': 'https://www.youtube.com/zsecurity', | |
4985 | 'only_matching': True, | |
4986 | }, { | |
4987 | 'url': 'http://www.youtube.com/NASAgovVideo/videos', | |
4988 | 'only_matching': True, | |
4989 | }, { | |
4990 | 'url': 'https://www.youtube.com/TheYoungTurks/live', | |
4991 | 'only_matching': True, | |
4992 | }, { | |
4993 | 'url': 'https://www.youtube.com/hashtag/cctv9', | |
4994 | 'info_dict': { | |
4995 | 'id': 'cctv9', | |
4996 | 'title': '#cctv9', | |
976ae3ea | 4997 | 'tags': [], |
a6213a49 | 4998 | }, |
4999 | 'playlist_mincount': 350, | |
5000 | }, { | |
5001 | 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU', | |
5002 | 'only_matching': True, | |
5003 | }, { | |
5004 | 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist', | |
5005 | 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', | |
5006 | 'only_matching': True | |
5007 | }, { | |
5008 | 'note': '/browse/ should redirect to /channel/', | |
5009 | 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng', | |
5010 | 'only_matching': True | |
5011 | }, { | |
5012 | 'note': 'VLPL, should redirect to playlist?list=PL...', | |
5013 | 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', | |
5014 | 'info_dict': { | |
5015 | 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq', | |
5016 | 'uploader': 'NoCopyrightSounds', | |
5017 | 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!', | |
5018 | 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg', | |
5019 | 'title': 'NCS Releases', | |
976ae3ea | 5020 | 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds', |
5021 | 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds', | |
5022 | 'modified_date': r're:\d{8}', | |
5023 | 'view_count': int, | |
5024 | 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg', | |
5025 | 'tags': [], | |
5026 | 'channel': 'NoCopyrightSounds', | |
a6213a49 | 5027 | }, |
5028 | 'playlist_mincount': 166, | |
976ae3ea | 5029 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], |
a6213a49 | 5030 | }, { |
5031 | 'note': 'Topic, should redirect to playlist?list=UU...', | |
5032 | 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw', | |
5033 | 'info_dict': { | |
5034 | 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw', | |
5035 | 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', | |
5036 | 'title': 'Uploads from Royalty Free Music - Topic', | |
5037 | 'uploader': 'Royalty Free Music - Topic', | |
976ae3ea | 5038 | 'tags': [], |
5039 | 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', | |
5040 | 'channel': 'Royalty Free Music - Topic', | |
5041 | 'view_count': int, | |
5042 | 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
5043 | 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
5044 | 'modified_date': r're:\d{8}', | |
5045 | 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
5046 | 'description': '', | |
a6213a49 | 5047 | }, |
5048 | 'expected_warnings': [ | |
a6213a49 | 5049 | 'The URL does not have a videos tab', |
976ae3ea | 5050 | r'[Uu]navailable videos (are|will be) hidden', |
a6213a49 | 5051 | ], |
5052 | 'playlist_mincount': 101, | |
5053 | }, { | |
5054 | 'note': 'Topic without a UU playlist', | |
5055 | 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg', | |
5056 | 'info_dict': { | |
5057 | 'id': 'UCtFRv9O2AHqOZjjynzrv-xg', | |
5058 | 'title': 'UCtFRv9O2AHqOZjjynzrv-xg', | |
976ae3ea | 5059 | 'tags': [], |
a6213a49 | 5060 | }, |
5061 | 'expected_warnings': [ | |
976ae3ea | 5062 | 'the playlist redirect gave error', |
a6213a49 | 5063 | ], |
5064 | 'playlist_mincount': 9, | |
5065 | }, { | |
5066 | 'note': 'Youtube music Album', | |
5067 | 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE', | |
5068 | 'info_dict': { | |
5069 | 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0', | |
5070 | 'title': 'Album - Royalty Free Music Library V2 (50 Songs)', | |
976ae3ea | 5071 | 'tags': [], |
5072 | 'view_count': int, | |
5073 | 'description': '', | |
5074 | 'availability': 'unlisted', | |
5075 | 'modified_date': r're:\d{8}', | |
a6213a49 | 5076 | }, |
5077 | 'playlist_count': 50, | |
5078 | }, { | |
5079 | 'note': 'unlisted single video playlist', | |
5080 | 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', | |
5081 | 'info_dict': { | |
5082 | 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q', | |
5083 | 'uploader': 'colethedj', | |
5084 | 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf', | |
5085 | 'title': 'yt-dlp unlisted playlist test', | |
976ae3ea | 5086 | 'availability': 'unlisted', |
5087 | 'tags': [], | |
5088 | 'modified_date': '20211208', | |
5089 | 'channel': 'colethedj', | |
5090 | 'view_count': int, | |
5091 | 'description': '', | |
5092 | 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q', | |
5093 | 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q', | |
5094 | 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q', | |
a6213a49 | 5095 | }, |
5096 | 'playlist_count': 1, | |
5097 | }, { | |
5098 | 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData', | |
5099 | 'url': 'https://www.youtube.com/feed/recommended', | |
5100 | 'info_dict': { | |
5101 | 'id': 'recommended', | |
5102 | 'title': 'recommended', | |
6c73052c | 5103 | 'tags': [], |
a6213a49 | 5104 | }, |
5105 | 'playlist_mincount': 50, | |
5106 | 'params': { | |
5107 | 'skip_download': True, | |
5108 | 'extractor_args': {'youtubetab': {'skip': ['webpage']}} | |
5109 | }, | |
5110 | }, { | |
5111 | 'note': 'API Fallback: /videos tab, sorted by oldest first', | |
5112 | 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid', | |
5113 | 'info_dict': { | |
5114 | 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', | |
5115 | 'title': 'Cody\'sLab - Videos', | |
5116 | 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa', | |
5117 | 'uploader': 'Cody\'sLab', | |
5118 | 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', | |
976ae3ea | 5119 | 'channel': 'Cody\'sLab', |
5120 | 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw', | |
5121 | 'tags': [], | |
5122 | 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw', | |
5123 | 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw', | |
6c73052c | 5124 | 'channel_follower_count': int |
a6213a49 | 5125 | }, |
5126 | 'playlist_mincount': 650, | |
5127 | 'params': { | |
5128 | 'skip_download': True, | |
5129 | 'extractor_args': {'youtubetab': {'skip': ['webpage']}} | |
5130 | }, | |
5131 | }, { | |
5132 | 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...', | |
5133 | 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw', | |
5134 | 'info_dict': { | |
5135 | 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw', | |
5136 | 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', | |
5137 | 'title': 'Uploads from Royalty Free Music - Topic', | |
5138 | 'uploader': 'Royalty Free Music - Topic', | |
976ae3ea | 5139 | 'modified_date': r're:\d{8}', |
5140 | 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw', | |
5141 | 'description': '', | |
5142 | 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
5143 | 'tags': [], | |
5144 | 'channel': 'Royalty Free Music - Topic', | |
5145 | 'view_count': int, | |
5146 | 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw', | |
a6213a49 | 5147 | }, |
5148 | 'expected_warnings': [ | |
976ae3ea | 5149 | 'does not have a videos tab', |
5150 | r'[Uu]navailable videos (are|will be) hidden', | |
a6213a49 | 5151 | ], |
5152 | 'playlist_mincount': 101, | |
5153 | 'params': { | |
5154 | 'skip_download': True, | |
5155 | 'extractor_args': {'youtubetab': {'skip': ['webpage']}} | |
5156 | }, | |
7c219ea6 | 5157 | }, { |
5158 | 'note': 'non-standard redirect to regional channel', | |
5159 | 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ', | |
5160 | 'only_matching': True | |
61d3665d | 5161 | }, { |
5162 | 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")', | |
5163 | 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6', | |
5164 | 'info_dict': { | |
5165 | 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6', | |
5166 | 'modified_date': '20220407', | |
5167 | 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q', | |
5168 | 'tags': [], | |
5169 | 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q', | |
5170 | 'uploader': 'pukkandan', | |
5171 | 'availability': 'unlisted', | |
5172 | 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q', | |
5173 | 'channel': 'pukkandan', | |
5174 | 'description': 'Test for collaborative playlist', | |
5175 | 'title': 'yt-dlp test - collaborative playlist', | |
5176 | 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q', | |
5177 | }, | |
5178 | 'playlist_mincount': 2 | |
a6213a49 | 5179 | }] |
5180 | ||
5181 | @classmethod | |
5182 | def suitable(cls, url): | |
5183 | return False if YoutubeIE.suitable(url) else super( | |
5184 | YoutubeTabIE, cls).suitable(url) | |
9297939e | 5185 | |
64f36541 | 5186 | _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$') |
fe03a6cd | 5187 | |
182bda88 | 5188 | @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data |
5189 | def _real_extract(self, url, smuggled_data): | |
cd7c66cf | 5190 | item_id = self._match_id(url) |
5191 | url = compat_urlparse.urlunparse( | |
5192 | compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com')) | |
a06916d9 | 5193 | compat_opts = self.get_param('compat_opts', []) |
cd7c66cf | 5194 | |
fe03a6cd | 5195 | def get_mobj(url): |
37e57a9f | 5196 | mobj = self._URL_RE.match(url).groupdict() |
07cce701 | 5197 | mobj.update((k, '') for k, v in mobj.items() if v is None) |
fe03a6cd | 5198 | return mobj |
5199 | ||
37e57a9f | 5200 | mobj, redirect_warning = get_mobj(url), None |
fe03a6cd | 5201 | # Youtube returns incomplete data if tabname is not lower case |
5202 | pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel'] | |
fe03a6cd | 5203 | if is_channel: |
5204 | if smuggled_data.get('is_music_url'): | |
37e57a9f | 5205 | if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist |
fe03a6cd | 5206 | item_id = item_id[2:] |
37e57a9f | 5207 | pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False |
5208 | elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist | |
ac56cf38 | 5209 | mdata = self._extract_tab_endpoint( |
37e57a9f | 5210 | f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music') |
5211 | murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'), | |
5212 | get_all=False, expected_type=compat_str) | |
ac56cf38 | 5213 | if not murl: |
37e57a9f | 5214 | raise ExtractorError('Failed to resolve album to playlist') |
ac56cf38 | 5215 | return self.url_result(murl, ie=YoutubeTabIE.ie_key()) |
37e57a9f | 5216 | elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/ |
5217 | pre = f'https://www.youtube.com/channel/{item_id}' | |
5218 | ||
64f36541 | 5219 | original_tab_name = tab |
fe03a6cd | 5220 | if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts: |
5221 | # Home URLs should redirect to /videos/ | |
37e57a9f | 5222 | redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. ' |
5223 | 'To download only the videos in the home page, add a "/featured" to the URL') | |
fe03a6cd | 5224 | tab = '/videos' |
5225 | ||
5226 | url = ''.join((pre, tab, post)) | |
5227 | mobj = get_mobj(url) | |
cd7c66cf | 5228 | |
5229 | # Handle both video/playlist URLs | |
201c1459 | 5230 | qs = parse_qs(url) |
37e57a9f | 5231 | video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')] |
cd7c66cf | 5232 | |
fe03a6cd | 5233 | if not video_id and mobj['not_channel'].startswith('watch'): |
cd7c66cf | 5234 | if not playlist_id: |
fe03a6cd | 5235 | # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable |
cd7c66cf | 5236 | raise ExtractorError('Unable to recognize tab page') |
fe03a6cd | 5237 | # Common mistake: https://www.youtube.com/watch?list=playlist_id |
37e57a9f | 5238 | self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}') |
5239 | url = f'https://www.youtube.com/playlist?list={playlist_id}' | |
18db7548 | 5240 | mobj = get_mobj(url) |
cd7c66cf | 5241 | |
5242 | if video_id and playlist_id: | |
a06916d9 | 5243 | if self.get_param('noplaylist'): |
37e57a9f | 5244 | self.to_screen(f'Downloading just video {video_id} because of --no-playlist') |
5245 | return self.url_result(f'https://www.youtube.com/watch?v={video_id}', | |
5246 | ie=YoutubeIE.ie_key(), video_id=video_id) | |
5247 | self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}') | |
cd7c66cf | 5248 | |
ac56cf38 | 5249 | data, ytcfg = self._extract_data(url, item_id) |
14fdfea9 | 5250 | |
7c219ea6 | 5251 | # YouTube may provide a non-standard redirect to the regional channel |
5252 | # See: https://github.com/yt-dlp/yt-dlp/issues/2694 | |
5253 | redirect_url = traverse_obj( | |
5254 | data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False) | |
5255 | if redirect_url and 'no-youtube-channel-redirect' not in compat_opts: | |
5256 | redirect_url = ''.join(( | |
5257 | urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post'])) | |
5258 | self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}') | |
5259 | return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key()) | |
5260 | ||
37e57a9f | 5261 | tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list) |
18db7548 | 5262 | if tabs: |
5263 | selected_tab = self._extract_selected_tab(tabs) | |
64f36541 | 5264 | selected_tab_name = selected_tab.get('title', '').lower() |
5265 | if selected_tab_name == 'home': | |
5266 | selected_tab_name = 'featured' | |
5267 | requested_tab_name = mobj['tab'][1:] | |
09f1580e | 5268 | if 'no-youtube-channel-redirect' not in compat_opts: |
64f36541 | 5269 | if requested_tab_name == 'live': |
09f1580e | 5270 | # Live tab should have redirected to the video |
5271 | raise ExtractorError('The channel is not currently live', expected=True) | |
64f36541 | 5272 | if requested_tab_name not in ('', selected_tab_name): |
5273 | redirect_warning = f'The channel does not have a {requested_tab_name} tab' | |
5274 | if not original_tab_name: | |
5275 | if item_id[:2] == 'UC': | |
5276 | # Topic channels don't have /videos. Use the equivalent playlist instead | |
5277 | pl_id = f'UU{item_id[2:]}' | |
5278 | pl_url = f'https://www.youtube.com/playlist?list={pl_id}' | |
5279 | try: | |
5280 | data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True) | |
5281 | except ExtractorError: | |
5282 | redirect_warning += ' and the playlist redirect gave error' | |
5283 | else: | |
5284 | item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name | |
5285 | redirect_warning += f'. Redirecting to playlist {pl_id} instead' | |
5286 | if selected_tab_name and selected_tab_name != requested_tab_name: | |
5287 | redirect_warning += f'. {selected_tab_name} tab is being downloaded instead' | |
5288 | else: | |
5289 | raise ExtractorError(redirect_warning, expected=True) | |
18db7548 | 5290 | |
37e57a9f | 5291 | if redirect_warning: |
64f36541 | 5292 | self.to_screen(redirect_warning) |
37e57a9f | 5293 | self.write_debug(f'Final URL: {url}') |
18db7548 | 5294 | |
358de58c | 5295 | # YouTube sometimes provides a button to reload playlist with unavailable videos. |
53ed7066 | 5296 | if 'no-youtube-unavailable-videos' not in compat_opts: |
ac56cf38 | 5297 | data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data |
c0ac49bc | 5298 | self._extract_and_report_alerts(data, only_once=True) |
37e57a9f | 5299 | tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list) |
8bdd16b4 | 5300 | if tabs: |
ac56cf38 | 5301 | return self._extract_from_tabs(item_id, ytcfg, data, tabs) |
cd7c66cf | 5302 | |
37e57a9f | 5303 | playlist = traverse_obj( |
5304 | data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict) | |
8bdd16b4 | 5305 | if playlist: |
ac56cf38 | 5306 | return self._extract_from_playlist(item_id, url, data, playlist, ytcfg) |
cd7c66cf | 5307 | |
37e57a9f | 5308 | video_id = traverse_obj( |
5309 | data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id | |
8bdd16b4 | 5310 | if video_id: |
09f1580e | 5311 | if mobj['tab'] != '/live': # live tab is expected to redirect to video |
37e57a9f | 5312 | self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}') |
5313 | return self.url_result(f'https://www.youtube.com/watch?v={video_id}', | |
5314 | ie=YoutubeIE.ie_key(), video_id=video_id) | |
cd7c66cf | 5315 | |
8bdd16b4 | 5316 | raise ExtractorError('Unable to recognize tab page') |
c5e8d7af | 5317 | |
c5e8d7af | 5318 | |
8bdd16b4 | 5319 | class YoutubePlaylistIE(InfoExtractor): |
96565c7e | 5320 | IE_DESC = 'YouTube playlists' |
8bdd16b4 | 5321 | _VALID_URL = r'''(?x)(?: |
5322 | (?:https?://)? | |
5323 | (?:\w+\.)? | |
5324 | (?: | |
5325 | (?: | |
5326 | youtube(?:kids)?\.com| | |
d9190e44 | 5327 | %(invidious)s |
8bdd16b4 | 5328 | ) |
5329 | /.*?\?.*?\blist= | |
5330 | )? | |
5331 | (?P<id>%(playlist_id)s) | |
d9190e44 RH |
5332 | )''' % { |
5333 | 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE, | |
5334 | 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES), | |
5335 | } | |
8bdd16b4 | 5336 | IE_NAME = 'youtube:playlist' |
cdc628a4 | 5337 | _TESTS = [{ |
8bdd16b4 | 5338 | 'note': 'issue #673', |
5339 | 'url': 'PLBB231211A4F62143', | |
cdc628a4 | 5340 | 'info_dict': { |
8bdd16b4 | 5341 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', |
5342 | 'id': 'PLBB231211A4F62143', | |
976ae3ea | 5343 | 'uploader': 'Wickman', |
8bdd16b4 | 5344 | 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q', |
11f9be09 | 5345 | 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2', |
976ae3ea | 5346 | 'view_count': int, |
5347 | 'uploader_url': 'https://www.youtube.com/user/Wickydoo', | |
5348 | 'modified_date': r're:\d{8}', | |
5349 | 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q', | |
5350 | 'channel': 'Wickman', | |
5351 | 'tags': [], | |
5352 | 'channel_url': 'https://www.youtube.com/user/Wickydoo', | |
8bdd16b4 | 5353 | }, |
5354 | 'playlist_mincount': 29, | |
5355 | }, { | |
5356 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
5357 | 'info_dict': { | |
5358 | 'title': 'YDL_safe_search', | |
5359 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
5360 | }, | |
5361 | 'playlist_count': 2, | |
5362 | 'skip': 'This playlist is private', | |
9558dcec | 5363 | }, { |
8bdd16b4 | 5364 | 'note': 'embedded', |
5365 | 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
5366 | 'playlist_count': 4, | |
9558dcec | 5367 | 'info_dict': { |
8bdd16b4 | 5368 | 'title': 'JODA15', |
5369 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
5370 | 'uploader': 'milan', | |
5371 | 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw', | |
976ae3ea | 5372 | 'description': '', |
5373 | 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw', | |
5374 | 'tags': [], | |
5375 | 'modified_date': '20140919', | |
5376 | 'view_count': int, | |
5377 | 'channel': 'milan', | |
5378 | 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw', | |
5379 | 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw', | |
5380 | }, | |
5381 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], | |
cdc628a4 | 5382 | }, { |
8bdd16b4 | 5383 | 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', |
11f9be09 | 5384 | 'playlist_mincount': 654, |
8bdd16b4 | 5385 | 'info_dict': { |
5386 | 'title': '2018 Chinese New Singles (11/6 updated)', | |
5387 | 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
5388 | 'uploader': 'LBK', | |
5389 | 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA', | |
11f9be09 | 5390 | 'description': 'md5:da521864744d60a198e3a88af4db0d9d', |
976ae3ea | 5391 | 'channel': 'LBK', |
5392 | 'view_count': int, | |
5393 | 'channel_url': 'https://www.youtube.com/c/愛低音的國王', | |
5394 | 'tags': [], | |
5395 | 'uploader_url': 'https://www.youtube.com/c/愛低音的國王', | |
5396 | 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA', | |
5397 | 'modified_date': r're:\d{8}', | |
5398 | }, | |
5399 | 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'], | |
daa0df9e | 5400 | }, { |
29f7c58a | 5401 | 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', |
5402 | 'only_matching': True, | |
5403 | }, { | |
5404 | # music album playlist | |
5405 | 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', | |
5406 | 'only_matching': True, | |
5407 | }] | |
5408 | ||
5409 | @classmethod | |
5410 | def suitable(cls, url): | |
201c1459 | 5411 | if YoutubeTabIE.suitable(url): |
5412 | return False | |
49a57e70 | 5413 | from ..utils import parse_qs |
201c1459 | 5414 | qs = parse_qs(url) |
5415 | if qs.get('v', [None])[0]: | |
5416 | return False | |
5417 | return super(YoutubePlaylistIE, cls).suitable(url) | |
29f7c58a | 5418 | |
5419 | def _real_extract(self, url): | |
5420 | playlist_id = self._match_id(url) | |
46953e7e | 5421 | is_music_url = YoutubeBaseInfoExtractor.is_music_url(url) |
9297939e | 5422 | url = update_url_query( |
5423 | 'https://www.youtube.com/playlist', | |
5424 | parse_qs(url) or {'list': playlist_id}) | |
5425 | if is_music_url: | |
5426 | url = smuggle_url(url, {'is_music_url': True}) | |
5427 | return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
29f7c58a | 5428 | |
5429 | ||
5430 | class YoutubeYtBeIE(InfoExtractor): | |
c76eb41b | 5431 | IE_DESC = 'youtu.be' |
29f7c58a | 5432 | _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} |
5433 | _TESTS = [{ | |
8bdd16b4 | 5434 | 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', |
5435 | 'info_dict': { | |
5436 | 'id': 'yeWKywCrFtk', | |
5437 | 'ext': 'mp4', | |
5438 | 'title': 'Small Scale Baler and Braiding Rugs', | |
5439 | 'uploader': 'Backus-Page House Museum', | |
5440 | 'uploader_id': 'backuspagemuseum', | |
5441 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum', | |
5442 | 'upload_date': '20161008', | |
5443 | 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', | |
5444 | 'categories': ['Nonprofits & Activism'], | |
5445 | 'tags': list, | |
5446 | 'like_count': int, | |
976ae3ea | 5447 | 'age_limit': 0, |
5448 | 'playable_in_embed': True, | |
5449 | 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp', | |
5450 | 'channel': 'Backus-Page House Museum', | |
5451 | 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw', | |
5452 | 'live_status': 'not_live', | |
5453 | 'view_count': int, | |
5454 | 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw', | |
5455 | 'availability': 'public', | |
5456 | 'duration': 59, | |
8bdd16b4 | 5457 | }, |
5458 | 'params': { | |
5459 | 'noplaylist': True, | |
5460 | 'skip_download': True, | |
5461 | }, | |
39e7107d | 5462 | }, { |
8bdd16b4 | 5463 | 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', |
39e7107d | 5464 | 'only_matching': True, |
cdc628a4 PH |
5465 | }] |
5466 | ||
8bdd16b4 | 5467 | def _real_extract(self, url): |
5ad28e7f | 5468 | mobj = self._match_valid_url(url) |
29f7c58a | 5469 | video_id = mobj.group('id') |
5470 | playlist_id = mobj.group('playlist_id') | |
8bdd16b4 | 5471 | return self.url_result( |
29f7c58a | 5472 | update_url_query('https://www.youtube.com/watch', { |
5473 | 'v': video_id, | |
5474 | 'list': playlist_id, | |
5475 | 'feature': 'youtu.be', | |
5476 | }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id) | |
8bdd16b4 | 5477 | |
5478 | ||
b6ce9bb0 | 5479 | class YoutubeLivestreamEmbedIE(InfoExtractor): |
5480 | IE_DESC = 'YouTube livestream embeds' | |
5481 | _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)' | |
5482 | _TESTS = [{ | |
5483 | 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA', | |
5484 | 'only_matching': True, | |
5485 | }] | |
5486 | ||
5487 | def _real_extract(self, url): | |
5488 | channel_id = self._match_id(url) | |
5489 | return self.url_result( | |
5490 | f'https://www.youtube.com/channel/{channel_id}/live', | |
5491 | ie=YoutubeTabIE.ie_key(), video_id=channel_id) | |
5492 | ||
5493 | ||
8bdd16b4 | 5494 | class YoutubeYtUserIE(InfoExtractor): |
96565c7e | 5495 | IE_DESC = 'YouTube user videos; "ytuser:" prefix' |
b6ce9bb0 | 5496 | IE_NAME = 'youtube:user' |
8bdd16b4 | 5497 | _VALID_URL = r'ytuser:(?P<id>.+)' |
5498 | _TESTS = [{ | |
5499 | 'url': 'ytuser:phihag', | |
5500 | 'only_matching': True, | |
5501 | }] | |
5502 | ||
5503 | def _real_extract(self, url): | |
5504 | user_id = self._match_id(url) | |
5505 | return self.url_result( | |
c586f9e8 | 5506 | 'https://www.youtube.com/user/%s/videos' % user_id, |
8bdd16b4 | 5507 | ie=YoutubeTabIE.ie_key(), video_id=user_id) |
9558dcec | 5508 | |
b05654f0 | 5509 | |
3d3dddc9 | 5510 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): |
70d5c17b | 5511 | IE_NAME = 'youtube:favorites' |
96565c7e | 5512 | IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)' |
70d5c17b | 5513 | _VALID_URL = r':ytfav(?:ou?rite)?s?' |
5514 | _LOGIN_REQUIRED = True | |
5515 | _TESTS = [{ | |
5516 | 'url': ':ytfav', | |
5517 | 'only_matching': True, | |
5518 | }, { | |
5519 | 'url': ':ytfavorites', | |
5520 | 'only_matching': True, | |
5521 | }] | |
5522 | ||
5523 | def _real_extract(self, url): | |
5524 | return self.url_result( | |
5525 | 'https://www.youtube.com/playlist?list=LL', | |
5526 | ie=YoutubeTabIE.ie_key()) | |
5527 | ||
5528 | ||
a6213a49 | 5529 | class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor): |
5530 | IE_DESC = 'YouTube search' | |
78caa52a | 5531 | IE_NAME = 'youtube:search' |
b05654f0 | 5532 | _SEARCH_KEY = 'ytsearch' |
a61fd4cf | 5533 | _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only |
84bbc545 | 5534 | _TESTS = [{ |
5535 | 'url': 'ytsearch5:youtube-dl test video', | |
5536 | 'playlist_count': 5, | |
5537 | 'info_dict': { | |
5538 | 'id': 'youtube-dl test video', | |
5539 | 'title': 'youtube-dl test video', | |
5540 | } | |
5541 | }] | |
b05654f0 | 5542 | |
a61fd4cf | 5543 | |
5f7cb91a | 5544 | class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor): |
cb7fb546 | 5545 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' |
a3dd9248 | 5546 | _SEARCH_KEY = 'ytsearchdate' |
a6213a49 | 5547 | IE_DESC = 'YouTube search, newest videos first' |
a61fd4cf | 5548 | _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date |
84bbc545 | 5549 | _TESTS = [{ |
5550 | 'url': 'ytsearchdate5:youtube-dl test video', | |
5551 | 'playlist_count': 5, | |
5552 | 'info_dict': { | |
5553 | 'id': 'youtube-dl test video', | |
5554 | 'title': 'youtube-dl test video', | |
5555 | } | |
5556 | }] | |
75dff0ee | 5557 | |
c9ae7b95 | 5558 | |
a6213a49 | 5559 | class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor): |
96565c7e | 5560 | IE_DESC = 'YouTube search URLs with sorting and filter support' |
386e1dd9 | 5561 | IE_NAME = YoutubeSearchIE.IE_NAME + '_url' |
182bda88 | 5562 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)' |
3462ffa8 | 5563 | _TESTS = [{ |
5564 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
5565 | 'playlist_mincount': 5, | |
5566 | 'info_dict': { | |
11f9be09 | 5567 | 'id': 'youtube-dl test video', |
3462ffa8 | 5568 | 'title': 'youtube-dl test video', |
5569 | } | |
a61fd4cf | 5570 | }, { |
5571 | 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D', | |
5572 | 'playlist_mincount': 5, | |
5573 | 'info_dict': { | |
5574 | 'id': 'python', | |
5575 | 'title': 'python', | |
5576 | } | |
ad210f4f | 5577 | }, { |
5578 | 'url': 'https://www.youtube.com/results?search_query=%23cats', | |
5579 | 'playlist_mincount': 1, | |
5580 | 'info_dict': { | |
5581 | 'id': '#cats', | |
5582 | 'title': '#cats', | |
5583 | 'entries': [{ | |
5584 | 'url': r're:https://(www\.)?youtube\.com/hashtag/cats', | |
5585 | 'title': '#cats', | |
5586 | }], | |
5587 | }, | |
3462ffa8 | 5588 | }, { |
5589 | 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB', | |
5590 | 'only_matching': True, | |
5591 | }] | |
5592 | ||
5593 | def _real_extract(self, url): | |
4dfbf869 | 5594 | qs = parse_qs(url) |
386e1dd9 | 5595 | query = (qs.get('search_query') or qs.get('q'))[0] |
a6213a49 | 5596 | return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query) |
3462ffa8 | 5597 | |
5598 | ||
16aa9ea4 | 5599 | class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor): |
455a15e2 | 5600 | IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)' |
16aa9ea4 | 5601 | IE_NAME = 'youtube:music:search_url' |
5602 | _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)' | |
5603 | _TESTS = [{ | |
5604 | 'url': 'https://music.youtube.com/search?q=royalty+free+music', | |
5605 | 'playlist_count': 16, | |
5606 | 'info_dict': { | |
5607 | 'id': 'royalty free music', | |
5608 | 'title': 'royalty free music', | |
5609 | } | |
5610 | }, { | |
5611 | 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D', | |
5612 | 'playlist_mincount': 30, | |
5613 | 'info_dict': { | |
5614 | 'id': 'royalty free music - songs', | |
5615 | 'title': 'royalty free music - songs', | |
5616 | }, | |
5617 | 'params': {'extract_flat': 'in_playlist'} | |
5618 | }, { | |
5619 | 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists', | |
5620 | 'playlist_mincount': 30, | |
5621 | 'info_dict': { | |
5622 | 'id': 'royalty free music - community playlists', | |
5623 | 'title': 'royalty free music - community playlists', | |
5624 | }, | |
5625 | 'params': {'extract_flat': 'in_playlist'} | |
5626 | }] | |
5627 | ||
5628 | _SECTIONS = { | |
5629 | 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==', | |
5630 | 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==', | |
5631 | 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF', | |
5632 | 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==', | |
5633 | 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==', | |
5634 | 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==', | |
5635 | } | |
5636 | ||
5637 | def _real_extract(self, url): | |
5638 | qs = parse_qs(url) | |
5639 | query = (qs.get('search_query') or qs.get('q'))[0] | |
5640 | params = qs.get('sp', (None,))[0] | |
5641 | if params: | |
5642 | section = next((k for k, v in self._SECTIONS.items() if v == params), params) | |
5643 | else: | |
5644 | section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower() | |
5645 | params = self._SECTIONS.get(section) | |
5646 | if not params: | |
5647 | section = None | |
5648 | title = join_nonempty(query, section, delim=' - ') | |
af5c1c55 | 5649 | return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title) |
16aa9ea4 | 5650 | |
5651 | ||
182bda88 | 5652 | class YoutubeFeedsInfoExtractor(InfoExtractor): |
d7ae0639 | 5653 | """ |
25f14e9f | 5654 | Base class for feed extractors |
3d3dddc9 | 5655 | Subclasses must define the _FEED_NAME property. |
d7ae0639 | 5656 | """ |
b2e8bc1b | 5657 | _LOGIN_REQUIRED = True |
a25bca9f | 5658 | |
5659 | def _real_initialize(self): | |
5660 | YoutubeBaseInfoExtractor._check_login_required(self) | |
d7ae0639 JMF |
5661 | |
5662 | @property | |
5663 | def IE_NAME(self): | |
78caa52a | 5664 | return 'youtube:%s' % self._FEED_NAME |
04cc9617 | 5665 | |
3853309f | 5666 | def _real_extract(self, url): |
3d3dddc9 | 5667 | return self.url_result( |
182bda88 | 5668 | f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key()) |
25f14e9f S |
5669 | |
5670 | ||
ef2f3c7f | 5671 | class YoutubeWatchLaterIE(InfoExtractor): |
5672 | IE_NAME = 'youtube:watchlater' | |
96565c7e | 5673 | IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)' |
3d3dddc9 | 5674 | _VALID_URL = r':ytwatchlater' |
bc7a9cd8 | 5675 | _TESTS = [{ |
8bdd16b4 | 5676 | 'url': ':ytwatchlater', |
bc7a9cd8 S |
5677 | 'only_matching': True, |
5678 | }] | |
25f14e9f S |
5679 | |
5680 | def _real_extract(self, url): | |
ef2f3c7f | 5681 | return self.url_result( |
5682 | 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key()) | |
3462ffa8 | 5683 | |
5684 | ||
25f14e9f | 5685 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): |
96565c7e | 5686 | IE_DESC = 'YouTube recommended videos; ":ytrec" keyword' |
3d3dddc9 | 5687 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?' |
25f14e9f | 5688 | _FEED_NAME = 'recommended' |
45db527f | 5689 | _LOGIN_REQUIRED = False |
3d3dddc9 | 5690 | _TESTS = [{ |
5691 | 'url': ':ytrec', | |
5692 | 'only_matching': True, | |
5693 | }, { | |
5694 | 'url': ':ytrecommended', | |
5695 | 'only_matching': True, | |
5696 | }, { | |
5697 | 'url': 'https://youtube.com', | |
5698 | 'only_matching': True, | |
5699 | }] | |
1ed5b5c9 | 5700 | |
1ed5b5c9 | 5701 | |
25f14e9f | 5702 | class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): |
96565c7e | 5703 | IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)' |
3d3dddc9 | 5704 | _VALID_URL = r':ytsub(?:scription)?s?' |
25f14e9f | 5705 | _FEED_NAME = 'subscriptions' |
3d3dddc9 | 5706 | _TESTS = [{ |
5707 | 'url': ':ytsubs', | |
5708 | 'only_matching': True, | |
5709 | }, { | |
5710 | 'url': ':ytsubscriptions', | |
5711 | 'only_matching': True, | |
5712 | }] | |
1ed5b5c9 | 5713 | |
1ed5b5c9 | 5714 | |
25f14e9f | 5715 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): |
96565c7e | 5716 | IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)' |
a5c56234 | 5717 | _VALID_URL = r':ythis(?:tory)?' |
25f14e9f | 5718 | _FEED_NAME = 'history' |
3d3dddc9 | 5719 | _TESTS = [{ |
5720 | 'url': ':ythistory', | |
5721 | 'only_matching': True, | |
5722 | }] | |
1ed5b5c9 JMF |
5723 | |
5724 | ||
15870e90 PH |
5725 | class YoutubeTruncatedURLIE(InfoExtractor): |
5726 | IE_NAME = 'youtube:truncated_url' | |
5727 | IE_DESC = False # Do not list | |
975d35db | 5728 | _VALID_URL = r'''(?x) |
b95aab84 PH |
5729 | (?:https?://)? |
5730 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
5731 | (?:watch\?(?: | |
c4808c60 | 5732 | feature=[a-z_]+| |
b95aab84 PH |
5733 | annotation_id=annotation_[^&]+| |
5734 | x-yt-cl=[0-9]+| | |
c1708b89 | 5735 | hl=[^&]*| |
287be8c6 | 5736 | t=[0-9]+ |
b95aab84 PH |
5737 | )? |
5738 | | | |
5739 | attribution_link\?a=[^&]+ | |
5740 | ) | |
5741 | $ | |
975d35db | 5742 | ''' |
15870e90 | 5743 | |
c4808c60 | 5744 | _TESTS = [{ |
2d3d2997 | 5745 | 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041', |
c4808c60 | 5746 | 'only_matching': True, |
dc2fc736 | 5747 | }, { |
2d3d2997 | 5748 | 'url': 'https://www.youtube.com/watch?', |
dc2fc736 | 5749 | 'only_matching': True, |
b95aab84 PH |
5750 | }, { |
5751 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
5752 | 'only_matching': True, | |
5753 | }, { | |
5754 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
5755 | 'only_matching': True, | |
c1708b89 PH |
5756 | }, { |
5757 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
5758 | 'only_matching': True, | |
287be8c6 PH |
5759 | }, { |
5760 | 'url': 'https://www.youtube.com/watch?t=2372', | |
5761 | 'only_matching': True, | |
c4808c60 PH |
5762 | }] |
5763 | ||
15870e90 PH |
5764 | def _real_extract(self, url): |
5765 | raise ExtractorError( | |
78caa52a PH |
5766 | 'Did you forget to quote the URL? Remember that & is a meta ' |
5767 | 'character in most shells, so you want to put the URL in quotes, ' | |
3867038a | 5768 | 'like youtube-dl ' |
2d3d2997 | 5769 | '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' |
3867038a | 5770 | ' or simply youtube-dl BaW_jenozKc .', |
15870e90 | 5771 | expected=True) |
772fd5cc PH |
5772 | |
5773 | ||
3cd786db | 5774 | class YoutubeClipIE(InfoExtractor): |
5775 | IE_NAME = 'youtube:clip' | |
5776 | IE_DESC = False # Do not list | |
5777 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/' | |
5778 | ||
5779 | def _real_extract(self, url): | |
5780 | self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead') | |
5781 | return self.url_result(url, 'Generic') | |
5782 | ||
5783 | ||
772fd5cc PH |
5784 | class YoutubeTruncatedIDIE(InfoExtractor): |
5785 | IE_NAME = 'youtube:truncated_id' | |
5786 | IE_DESC = False # Do not list | |
b95aab84 | 5787 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' |
772fd5cc PH |
5788 | |
5789 | _TESTS = [{ | |
5790 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
5791 | 'only_matching': True, | |
5792 | }] | |
5793 | ||
5794 | def _real_extract(self, url): | |
5795 | video_id = self._match_id(url) | |
5796 | raise ExtractorError( | |
5797 | 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), | |
5798 | expected=True) |