]>
Commit | Line | Data |
---|---|---|
c5e8d7af | 1 | # coding: utf-8 |
c5e8d7af | 2 | |
78caa52a PH |
3 | from __future__ import unicode_literals |
4 | ||
5 | ||
0ca96d48 | 6 | import itertools |
c5e8d7af | 7 | import json |
c4417ddb | 8 | import os.path |
d77ab8e2 | 9 | import random |
c5e8d7af | 10 | import re |
42939b61 | 11 | import time |
e0df6211 | 12 | import traceback |
c5e8d7af | 13 | |
b05654f0 | 14 | from .common import InfoExtractor, SearchInfoExtractor |
2b25cb5d | 15 | from ..jsinterp import JSInterpreter |
54256267 | 16 | from ..swfinterp import SWFInterpreter |
4bb4a188 | 17 | from ..compat import ( |
edf3e38e | 18 | compat_chr, |
f8c55c66 | 19 | compat_HTTPError, |
8d81f3e3 | 20 | compat_kwargs, |
c5e8d7af | 21 | compat_parse_qs, |
7fd002c0 S |
22 | compat_urllib_parse_unquote, |
23 | compat_urllib_parse_unquote_plus, | |
15707c7e | 24 | compat_urllib_parse_urlencode, |
7c80519c | 25 | compat_urllib_parse_urlparse, |
7c61bd36 | 26 | compat_urlparse, |
c5e8d7af | 27 | compat_str, |
4bb4a188 PH |
28 | ) |
29 | from ..utils import ( | |
27019dbb | 30 | bool_or_none, |
c5e8d7af | 31 | clean_html, |
026fbedc | 32 | dict_get, |
9b9c5355 | 33 | error_to_compat_str, |
351f37c0 | 34 | extract_attributes, |
c5e8d7af | 35 | ExtractorError, |
2d30521a | 36 | float_or_none, |
4bb4a188 PH |
37 | get_element_by_attribute, |
38 | get_element_by_id, | |
dd27fd17 | 39 | int_or_none, |
94278f72 | 40 | mimetype2ext, |
4bb4a188 | 41 | orderedSet, |
6310acf5 | 42 | parse_codecs, |
7c80519c | 43 | parse_duration, |
54fc90aa | 44 | qualities, |
0cb58b02 | 45 | remove_quotes, |
3995d37d | 46 | remove_start, |
cf7e015f | 47 | smuggle_url, |
dbdaaa23 | 48 | str_or_none, |
c93d53f5 | 49 | str_to_int, |
556dbe7f | 50 | try_get, |
c5e8d7af PH |
51 | unescapeHTML, |
52 | unified_strdate, | |
cf7e015f | 53 | unsmuggle_url, |
81c2f20b | 54 | uppercase_escape, |
21c340b8 | 55 | url_or_none, |
6e6bc8da | 56 | urlencode_postdata, |
c5e8d7af PH |
57 | ) |
58 | ||
5f6a1245 | 59 | |
de7f3446 | 60 | class YoutubeBaseInfoExtractor(InfoExtractor): |
b2e8bc1b JMF |
61 | """Provide base functions for Youtube extractors""" |
62 | _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' | |
9303ce3e | 63 | _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge' |
e00eb564 S |
64 | |
65 | _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup' | |
3995d37d S |
66 | _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge' |
67 | _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}' | |
e00eb564 | 68 | |
b2e8bc1b JMF |
69 | _NETRC_MACHINE = 'youtube' |
70 | # If True it will raise an error if no login info is provided | |
71 | _LOGIN_REQUIRED = False | |
72 | ||
409b9324 | 73 | _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)[0-9A-Za-z-_]{10,}' |
d0ba5587 | 74 | |
b2e8bc1b | 75 | def _set_language(self): |
810fb84d PH |
76 | self._set_cookie( |
77 | '.youtube.com', 'PREF', 'f1=50000000&hl=en', | |
42939b61 | 78 | # YouTube sets the expire time to about two months |
810fb84d | 79 | expire_time=time.time() + 2 * 30 * 24 * 3600) |
b2e8bc1b | 80 | |
25f14e9f S |
81 | def _ids_to_results(self, ids): |
82 | return [ | |
83 | self.url_result(vid_id, 'Youtube', video_id=vid_id) | |
84 | for vid_id in ids] | |
85 | ||
b2e8bc1b | 86 | def _login(self): |
83317f69 | 87 | """ |
88 | Attempt to log in to YouTube. | |
89 | True is returned if successful or skipped. | |
90 | False is returned if login failed. | |
91 | ||
92 | If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. | |
93 | """ | |
68217024 | 94 | username, password = self._get_login_info() |
b2e8bc1b JMF |
95 | # No authentication to be performed |
96 | if username is None: | |
70d35d16 | 97 | if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None: |
69ea8ca4 | 98 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
83317f69 | 99 | return True |
b2e8bc1b | 100 | |
7cc3570e PH |
101 | login_page = self._download_webpage( |
102 | self._LOGIN_URL, None, | |
69ea8ca4 PH |
103 | note='Downloading login page', |
104 | errnote='unable to fetch login page', fatal=False) | |
7cc3570e PH |
105 | if login_page is False: |
106 | return | |
b2e8bc1b | 107 | |
1212e997 | 108 | login_form = self._hidden_inputs(login_page) |
c5e8d7af | 109 | |
e00eb564 S |
110 | def req(url, f_req, note, errnote): |
111 | data = login_form.copy() | |
112 | data.update({ | |
113 | 'pstMsg': 1, | |
114 | 'checkConnection': 'youtube', | |
115 | 'checkedDomains': 'youtube', | |
116 | 'hl': 'en', | |
117 | 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]', | |
3995d37d | 118 | 'f.req': json.dumps(f_req), |
e00eb564 S |
119 | 'flowName': 'GlifWebSignIn', |
120 | 'flowEntry': 'ServiceLogin', | |
baf67a60 S |
121 | # TODO: reverse actual botguard identifier generation algo |
122 | 'bgRequest': '["identifier",""]', | |
041bc3ad | 123 | }) |
e00eb564 S |
124 | return self._download_json( |
125 | url, None, note=note, errnote=errnote, | |
126 | transform_source=lambda s: re.sub(r'^[^[]*', '', s), | |
127 | fatal=False, | |
128 | data=urlencode_postdata(data), headers={ | |
129 | 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8', | |
130 | 'Google-Accounts-XSRF': 1, | |
131 | }) | |
132 | ||
3995d37d S |
133 | def warn(message): |
134 | self._downloader.report_warning(message) | |
135 | ||
136 | lookup_req = [ | |
137 | username, | |
138 | None, [], None, 'US', None, None, 2, False, True, | |
139 | [ | |
140 | None, None, | |
141 | [2, 1, None, 1, | |
142 | 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn', | |
143 | None, [], 4], | |
144 | 1, [None, None, []], None, None, None, True | |
145 | ], | |
146 | username, | |
147 | ] | |
148 | ||
e00eb564 | 149 | lookup_results = req( |
3995d37d | 150 | self._LOOKUP_URL, lookup_req, |
e00eb564 S |
151 | 'Looking up account info', 'Unable to look up account info') |
152 | ||
153 | if lookup_results is False: | |
154 | return False | |
041bc3ad | 155 | |
3995d37d S |
156 | user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str) |
157 | if not user_hash: | |
158 | warn('Unable to extract user hash') | |
159 | return False | |
160 | ||
161 | challenge_req = [ | |
162 | user_hash, | |
163 | None, 1, None, [1, None, None, None, [password, None, True]], | |
164 | [ | |
165 | None, None, [2, 1, None, 1, 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn', None, [], 4], | |
166 | 1, [None, None, []], None, None, None, True | |
167 | ]] | |
83317f69 | 168 | |
3995d37d S |
169 | challenge_results = req( |
170 | self._CHALLENGE_URL, challenge_req, | |
171 | 'Logging in', 'Unable to log in') | |
83317f69 | 172 | |
3995d37d | 173 | if challenge_results is False: |
e00eb564 | 174 | return |
83317f69 | 175 | |
3995d37d S |
176 | login_res = try_get(challenge_results, lambda x: x[0][5], list) |
177 | if login_res: | |
178 | login_msg = try_get(login_res, lambda x: x[5], compat_str) | |
179 | warn( | |
180 | 'Unable to login: %s' % 'Invalid password' | |
181 | if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg) | |
182 | return False | |
183 | ||
184 | res = try_get(challenge_results, lambda x: x[0][-1], list) | |
185 | if not res: | |
186 | warn('Unable to extract result entry') | |
187 | return False | |
188 | ||
9a6628aa S |
189 | login_challenge = try_get(res, lambda x: x[0][0], list) |
190 | if login_challenge: | |
191 | challenge_str = try_get(login_challenge, lambda x: x[2], compat_str) | |
192 | if challenge_str == 'TWO_STEP_VERIFICATION': | |
3995d37d S |
193 | # SEND_SUCCESS - TFA code has been successfully sent to phone |
194 | # QUOTA_EXCEEDED - reached the limit of TFA codes | |
9a6628aa | 195 | status = try_get(login_challenge, lambda x: x[5], compat_str) |
3995d37d S |
196 | if status == 'QUOTA_EXCEEDED': |
197 | warn('Exceeded the limit of TFA codes, try later') | |
198 | return False | |
199 | ||
200 | tl = try_get(challenge_results, lambda x: x[1][2], compat_str) | |
201 | if not tl: | |
202 | warn('Unable to extract TL') | |
203 | return False | |
204 | ||
205 | tfa_code = self._get_tfa_info('2-step verification code') | |
206 | ||
207 | if not tfa_code: | |
208 | warn( | |
209 | 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>' | |
210 | '(Note that only TOTP (Google Authenticator App) codes work at this time.)') | |
211 | return False | |
212 | ||
213 | tfa_code = remove_start(tfa_code, 'G-') | |
214 | ||
215 | tfa_req = [ | |
216 | user_hash, None, 2, None, | |
217 | [ | |
218 | 9, None, None, None, None, None, None, None, | |
219 | [None, tfa_code, True, 2] | |
220 | ]] | |
221 | ||
222 | tfa_results = req( | |
223 | self._TFA_URL.format(tl), tfa_req, | |
224 | 'Submitting TFA code', 'Unable to submit TFA code') | |
225 | ||
226 | if tfa_results is False: | |
227 | return False | |
228 | ||
229 | tfa_res = try_get(tfa_results, lambda x: x[0][5], list) | |
230 | if tfa_res: | |
231 | tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str) | |
232 | warn( | |
233 | 'Unable to finish TFA: %s' % 'Invalid TFA code' | |
234 | if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg) | |
235 | return False | |
236 | ||
237 | check_cookie_url = try_get( | |
238 | tfa_results, lambda x: x[0][-1][2], compat_str) | |
9a6628aa S |
239 | else: |
240 | CHALLENGES = { | |
241 | 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.", | |
242 | 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.', | |
243 | 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.", | |
244 | } | |
245 | challenge = CHALLENGES.get( | |
246 | challenge_str, | |
247 | '%s returned error %s.' % (self.IE_NAME, challenge_str)) | |
248 | warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge) | |
249 | return False | |
3995d37d S |
250 | else: |
251 | check_cookie_url = try_get(res, lambda x: x[2], compat_str) | |
252 | ||
253 | if not check_cookie_url: | |
254 | warn('Unable to extract CheckCookie URL') | |
255 | return False | |
e00eb564 S |
256 | |
257 | check_cookie_results = self._download_webpage( | |
3995d37d S |
258 | check_cookie_url, None, 'Checking cookie', fatal=False) |
259 | ||
260 | if check_cookie_results is False: | |
261 | return False | |
e00eb564 | 262 | |
3995d37d S |
263 | if 'https://myaccount.google.com/' not in check_cookie_results: |
264 | warn('Unable to log in') | |
b2e8bc1b | 265 | return False |
e00eb564 | 266 | |
b2e8bc1b JMF |
267 | return True |
268 | ||
30226342 | 269 | def _download_webpage_handle(self, *args, **kwargs): |
c1148516 S |
270 | query = kwargs.get('query', {}).copy() |
271 | query['disable_polymer'] = 'true' | |
272 | kwargs['query'] = query | |
30226342 | 273 | return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle( |
8d81f3e3 S |
274 | *args, **compat_kwargs(kwargs)) |
275 | ||
b2e8bc1b JMF |
276 | def _real_initialize(self): |
277 | if self._downloader is None: | |
278 | return | |
42939b61 | 279 | self._set_language() |
b2e8bc1b JMF |
280 | if not self._login(): |
281 | return | |
c5e8d7af | 282 | |
8377574c | 283 | |
8e7aad20 | 284 | class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor): |
061a75ed | 285 | # Extract entries from page with "Load more" button |
648e6a1f S |
286 | def _entries(self, page, playlist_id): |
287 | more_widget_html = content_html = page | |
288 | for page_num in itertools.count(1): | |
061a75ed S |
289 | for entry in self._process_page(content_html): |
290 | yield entry | |
648e6a1f S |
291 | |
292 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) | |
293 | if not mobj: | |
294 | break | |
295 | ||
f8c55c66 S |
296 | count = 0 |
297 | retries = 3 | |
298 | while count <= retries: | |
299 | try: | |
300 | # Downloading page may result in intermittent 5xx HTTP error | |
301 | # that is usually worked around with a retry | |
302 | more = self._download_json( | |
303 | 'https://youtube.com/%s' % mobj.group('more'), playlist_id, | |
304 | 'Downloading page #%s%s' | |
305 | % (page_num, ' (retry #%d)' % count if count else ''), | |
306 | transform_source=uppercase_escape) | |
307 | break | |
308 | except ExtractorError as e: | |
309 | if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503): | |
310 | count += 1 | |
311 | if count <= retries: | |
312 | continue | |
313 | raise | |
314 | ||
648e6a1f S |
315 | content_html = more['content_html'] |
316 | if not content_html.strip(): | |
317 | # Some webpages show a "Load more" button but they don't | |
318 | # have more videos | |
319 | break | |
320 | more_widget_html = more['load_more_widget_html'] | |
321 | ||
061a75ed S |
322 | |
323 | class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): | |
324 | def _process_page(self, content): | |
325 | for video_id, video_title in self.extract_videos_from_page(content): | |
326 | yield self.url_result(video_id, 'Youtube', video_id, video_title) | |
327 | ||
351f37c0 S |
328 | def extract_videos_from_page_impl(self, video_re, page, ids_in_page, titles_in_page): |
329 | for mobj in re.finditer(video_re, page): | |
648e6a1f S |
330 | # The link with index 0 is not the first video of the playlist (not sure if still actual) |
331 | if 'index' in mobj.groupdict() and mobj.group('id') == '0': | |
332 | continue | |
333 | video_id = mobj.group('id') | |
351f37c0 S |
334 | video_title = unescapeHTML( |
335 | mobj.group('title')) if 'title' in mobj.groupdict() else None | |
648e6a1f S |
336 | if video_title: |
337 | video_title = video_title.strip() | |
351f37c0 S |
338 | if video_title == '► Play all': |
339 | video_title = None | |
648e6a1f S |
340 | try: |
341 | idx = ids_in_page.index(video_id) | |
342 | if video_title and not titles_in_page[idx]: | |
343 | titles_in_page[idx] = video_title | |
344 | except ValueError: | |
345 | ids_in_page.append(video_id) | |
346 | titles_in_page.append(video_title) | |
351f37c0 S |
347 | |
348 | def extract_videos_from_page(self, page): | |
349 | ids_in_page = [] | |
350 | titles_in_page = [] | |
351 | self.extract_videos_from_page_impl( | |
352 | self._VIDEO_RE, page, ids_in_page, titles_in_page) | |
648e6a1f S |
353 | return zip(ids_in_page, titles_in_page) |
354 | ||
355 | ||
061a75ed S |
356 | class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): |
357 | def _process_page(self, content): | |
6dee688e S |
358 | for playlist_id in orderedSet(re.findall( |
359 | r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"', | |
360 | content)): | |
061a75ed S |
361 | yield self.url_result( |
362 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist') | |
363 | ||
0c148415 S |
364 | def _real_extract(self, url): |
365 | playlist_id = self._match_id(url) | |
366 | webpage = self._download_webpage(url, playlist_id) | |
0c148415 | 367 | title = self._og_search_title(webpage, fatal=False) |
061a75ed | 368 | return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title) |
0c148415 S |
369 | |
370 | ||
360e1ca5 | 371 | class YoutubeIE(YoutubeBaseInfoExtractor): |
78caa52a | 372 | IE_DESC = 'YouTube.com' |
cb7dfeea | 373 | _VALID_URL = r"""(?x)^ |
c5e8d7af | 374 | ( |
edb53e2d | 375 | (?:https?://|//) # http(s):// or protocol-independent URL |
cb7dfeea | 376 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/| |
484aaeb2 | 377 | (?:www\.)?deturl\.com/www\.youtube\.com/| |
e70dc1d1 | 378 | (?:www\.)?pwnyoutube\.com/| |
8b561bfc | 379 | (?:www\.)?hooktube\.com/| |
f7000f3a | 380 | (?:www\.)?yourepeat\.com/| |
e69ae5b9 | 381 | tube\.majestyc\.net/| |
ba036333 | 382 | # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances |
77d95677 | 383 | (?:(?:www|dev)\.)?invidio\.us/| |
ba036333 | 384 | (?:(?:www|no)\.)?invidiou\.sh/| |
385 | (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/| | |
8ae113ca | 386 | (?:www\.)?invidious\.kabi\.tk/| |
ba036333 | 387 | (?:www\.)?invidious\.enkirton\.net/| |
388 | (?:www\.)?invidious\.13ad\.de/| | |
791d2e81 | 389 | (?:www\.)?invidious\.mastodon\.host/| |
ba036333 | 390 | (?:www\.)?tube\.poal\.co/| |
8ae113ca | 391 | (?:www\.)?vid\.wxzm\.sx/| |
e69ae5b9 | 392 | youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains |
c5e8d7af PH |
393 | (?:.*?\#/)? # handle anchor (#/) redirect urls |
394 | (?: # the various things that can precede the ID: | |
ac7553d0 | 395 | (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/ |
c5e8d7af | 396 | |(?: # or the v= param in all its forms |
f7000f3a | 397 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) |
c5e8d7af | 398 | (?:\?|\#!?) # the params delimiter ? or # or #! |
040ac686 | 399 | (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY) |
c5e8d7af PH |
400 | v= |
401 | ) | |
f4b05232 | 402 | )) |
cbaed4bb S |
403 | |(?: |
404 | youtu\.be| # just youtu.be/xxxx | |
6d4fc66b S |
405 | vid\.plus| # or vid.plus/xxxx |
406 | zwearz\.com/watch| # or zwearz.com/watch/xxxx | |
cbaed4bb | 407 | )/ |
edb53e2d | 408 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= |
f4b05232 | 409 | ) |
c5e8d7af | 410 | )? # all until now is optional -> you can pass the naked ID |
8963d9c2 | 411 | ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID |
d0ba5587 S |
412 | (?!.*?\blist= |
413 | (?: | |
414 | %(playlist_id)s| # combined list/video URLs are handled by the playlist IE | |
415 | WL # WL are handled by the watch later IE | |
416 | ) | |
417 | ) | |
c5e8d7af | 418 | (?(1).+)? # if we found the ID, everything can follow |
d0ba5587 | 419 | $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} |
c5e8d7af | 420 | _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' |
2c62dc26 | 421 | _formats = { |
c2d3cb4c | 422 | '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, |
423 | '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
424 | '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
425 | '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}, | |
426 | '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}, | |
427 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
428 | '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
429 | '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
3834d3e3 | 430 | # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well |
c2d3cb4c | 431 | '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}, |
432 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
433 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
434 | '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
435 | '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
436 | '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
e1a0bfdf | 437 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, |
c2d3cb4c | 438 | '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, |
439 | '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
e1a0bfdf | 440 | |
441 | ||
442 | # 3D videos | |
c2d3cb4c | 443 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, |
444 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
445 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
446 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
e1a0bfdf | 447 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}, |
448 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
449 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
836a086c | 450 | |
96fb5605 | 451 | # Apple HTTP Live Streaming |
11f12195 | 452 | '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
c2d3cb4c | 453 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
454 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
455 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
456 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
457 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
e1a0bfdf | 458 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
459 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}, | |
2c62dc26 PH |
460 | |
461 | # DASH mp4 video | |
d23028a8 S |
462 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}, |
463 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
464 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
465 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
466 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
067aa17e | 467 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559) |
d23028a8 S |
468 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}, |
469 | '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
470 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
471 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
472 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
473 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
836a086c | 474 | |
f6f1fc92 | 475 | # Dash mp4 audio |
d23028a8 S |
476 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}, |
477 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}, | |
478 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}, | |
479 | '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
480 | '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
481 | '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}, | |
482 | '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}, | |
836a086c AZ |
483 | |
484 | # Dash webm | |
d23028a8 S |
485 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, |
486 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
487 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
488 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
489 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
490 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
491 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}, | |
492 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
493 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
494 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
495 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
496 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
497 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
498 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
499 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
4c6b4764 | 500 | # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug) |
d23028a8 S |
501 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, |
502 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
503 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
504 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
505 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
506 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
2c62dc26 PH |
507 | |
508 | # Dash webm audio | |
d23028a8 S |
509 | '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}, |
510 | '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}, | |
ce6b9a2d | 511 | |
0857baad | 512 | # Dash webm audio with opus inside |
d23028a8 S |
513 | '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}, |
514 | '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}, | |
515 | '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}, | |
0857baad | 516 | |
ce6b9a2d PH |
517 | # RTMP (unnamed) |
518 | '_rtmp': {'protocol': 'rtmp'}, | |
b85eae0f S |
519 | |
520 | # av01 video only formats sometimes served with "unknown" codecs | |
521 | '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
522 | '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
523 | '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
524 | '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}, | |
c5e8d7af | 525 | } |
19041a38 | 526 | _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt') |
836a086c | 527 | |
fd5c4aab S |
528 | _GEO_BYPASS = False |
529 | ||
78caa52a | 530 | IE_NAME = 'youtube' |
2eb88d95 PH |
531 | _TESTS = [ |
532 | { | |
2d3d2997 | 533 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9', |
4bc3a23e PH |
534 | 'info_dict': { |
535 | 'id': 'BaW_jenozKc', | |
536 | 'ext': 'mp4', | |
537 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
538 | 'uploader': 'Philipp Hagemeister', | |
539 | 'uploader_id': 'phihag', | |
ec85ded8 | 540 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', |
dd4c4492 S |
541 | 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', |
542 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', | |
4bc3a23e PH |
543 | 'upload_date': '20121002', |
544 | 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .', | |
545 | 'categories': ['Science & Technology'], | |
000b6b5a | 546 | 'tags': ['youtube-dl'], |
556dbe7f | 547 | 'duration': 10, |
dbdaaa23 | 548 | 'view_count': int, |
3e7c1224 PH |
549 | 'like_count': int, |
550 | 'dislike_count': int, | |
7c80519c | 551 | 'start_time': 1, |
297a564b | 552 | 'end_time': 9, |
2eb88d95 | 553 | } |
0e853ca4 | 554 | }, |
0e853ca4 | 555 | { |
2d3d2997 | 556 | 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY', |
4bc3a23e PH |
557 | 'note': 'Test generic use_cipher_signature video (#897)', |
558 | 'info_dict': { | |
559 | 'id': 'UxxajLWwzqY', | |
560 | 'ext': 'mp4', | |
561 | 'upload_date': '20120506', | |
562 | 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', | |
0cb58b02 | 563 | 'alt_title': 'I Love It (feat. Charli XCX)', |
7caf9830 | 564 | 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8', |
000b6b5a S |
565 | 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli', |
566 | 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop', | |
567 | 'iconic ep', 'iconic', 'love', 'it'], | |
556dbe7f | 568 | 'duration': 180, |
4bc3a23e PH |
569 | 'uploader': 'Icona Pop', |
570 | 'uploader_id': 'IconaPop', | |
ec85ded8 | 571 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop', |
0cb58b02 | 572 | 'creator': 'Icona Pop', |
936784b2 S |
573 | 'track': 'I Love It (feat. Charli XCX)', |
574 | 'artist': 'Icona Pop', | |
2eb88d95 | 575 | } |
c108eb73 JMF |
576 | }, |
577 | { | |
4bc3a23e PH |
578 | 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ', |
579 | 'note': 'Test VEVO video with age protection (#956)', | |
580 | 'info_dict': { | |
581 | 'id': '07FYdnEawAQ', | |
582 | 'ext': 'mp4', | |
583 | 'upload_date': '20130703', | |
4fe54c12 | 584 | 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)', |
0cb58b02 | 585 | 'alt_title': 'Tunnel Vision', |
4fe54c12 | 586 | 'description': 'md5:07dab3356cde4199048e4c7cd93471e1', |
556dbe7f | 587 | 'duration': 419, |
4bc3a23e PH |
588 | 'uploader': 'justintimberlakeVEVO', |
589 | 'uploader_id': 'justintimberlakeVEVO', | |
ec85ded8 | 590 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO', |
0cb58b02 | 591 | 'creator': 'Justin Timberlake', |
7e72694b | 592 | 'track': 'Tunnel Vision', |
936784b2 | 593 | 'artist': 'Justin Timberlake', |
34952f09 | 594 | 'age_limit': 18, |
c108eb73 JMF |
595 | } |
596 | }, | |
fccd3771 | 597 | { |
4bc3a23e PH |
598 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', |
599 | 'note': 'Embed-only video (#1746)', | |
600 | 'info_dict': { | |
601 | 'id': 'yZIXLfi8CZQ', | |
602 | 'ext': 'mp4', | |
603 | 'upload_date': '20120608', | |
604 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
605 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
606 | 'uploader': 'SET India', | |
94bfcd23 | 607 | 'uploader_id': 'setindia', |
ec85ded8 | 608 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia', |
94bfcd23 | 609 | 'age_limit': 18, |
fccd3771 PH |
610 | } |
611 | }, | |
11b56058 | 612 | { |
2d3d2997 | 613 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY', |
11b56058 PM |
614 | 'note': 'Use the first video ID in the URL', |
615 | 'info_dict': { | |
616 | 'id': 'BaW_jenozKc', | |
617 | 'ext': 'mp4', | |
618 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
619 | 'uploader': 'Philipp Hagemeister', | |
620 | 'uploader_id': 'phihag', | |
ec85ded8 | 621 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', |
11b56058 PM |
622 | 'upload_date': '20121002', |
623 | 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .', | |
624 | 'categories': ['Science & Technology'], | |
625 | 'tags': ['youtube-dl'], | |
556dbe7f | 626 | 'duration': 10, |
dbdaaa23 | 627 | 'view_count': int, |
11b56058 PM |
628 | 'like_count': int, |
629 | 'dislike_count': int, | |
34a7de29 S |
630 | }, |
631 | 'params': { | |
632 | 'skip_download': True, | |
633 | }, | |
11b56058 | 634 | }, |
dd27fd17 | 635 | { |
2d3d2997 | 636 | 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I', |
4bc3a23e PH |
637 | 'note': '256k DASH audio (format 141) via DASH manifest', |
638 | 'info_dict': { | |
639 | 'id': 'a9LDPn-MO4I', | |
640 | 'ext': 'm4a', | |
641 | 'upload_date': '20121002', | |
642 | 'uploader_id': '8KVIDEO', | |
ec85ded8 | 643 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO', |
4bc3a23e PH |
644 | 'description': '', |
645 | 'uploader': '8KVIDEO', | |
646 | 'title': 'UHDTV TEST 8K VIDEO.mp4' | |
4919603f | 647 | }, |
4bc3a23e PH |
648 | 'params': { |
649 | 'youtube_include_dash_manifest': True, | |
650 | 'format': '141', | |
4919603f | 651 | }, |
de3c7fe0 | 652 | 'skip': 'format 141 not served anymore', |
dd27fd17 | 653 | }, |
3489b7d2 JMF |
654 | # DASH manifest with encrypted signature |
655 | { | |
78caa52a PH |
656 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', |
657 | 'info_dict': { | |
658 | 'id': 'IB3lcPjvWLA', | |
659 | 'ext': 'm4a', | |
4fe54c12 S |
660 | 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson', |
661 | 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf', | |
556dbe7f | 662 | 'duration': 244, |
78caa52a PH |
663 | 'uploader': 'AfrojackVEVO', |
664 | 'uploader_id': 'AfrojackVEVO', | |
665 | 'upload_date': '20131011', | |
3489b7d2 | 666 | }, |
4bc3a23e | 667 | 'params': { |
78caa52a | 668 | 'youtube_include_dash_manifest': True, |
de3c7fe0 | 669 | 'format': '141/bestaudio[ext=m4a]', |
3489b7d2 JMF |
670 | }, |
671 | }, | |
aaeb86f6 S |
672 | # JS player signature function name containing $ |
673 | { | |
674 | 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM', | |
675 | 'info_dict': { | |
676 | 'id': 'nfWlot6h_JM', | |
677 | 'ext': 'm4a', | |
678 | 'title': 'Taylor Swift - Shake It Off', | |
4fe54c12 | 679 | 'description': 'md5:bec2185232c05479482cb5a9b82719bf', |
556dbe7f | 680 | 'duration': 242, |
aaeb86f6 S |
681 | 'uploader': 'TaylorSwiftVEVO', |
682 | 'uploader_id': 'TaylorSwiftVEVO', | |
683 | 'upload_date': '20140818', | |
0cb58b02 | 684 | 'creator': 'Taylor Swift', |
aaeb86f6 S |
685 | }, |
686 | 'params': { | |
687 | 'youtube_include_dash_manifest': True, | |
de3c7fe0 | 688 | 'format': '141/bestaudio[ext=m4a]', |
aaeb86f6 S |
689 | }, |
690 | }, | |
aa79ac0c PH |
691 | # Controversy video |
692 | { | |
693 | 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8', | |
694 | 'info_dict': { | |
695 | 'id': 'T4XJQO3qol8', | |
696 | 'ext': 'mp4', | |
556dbe7f | 697 | 'duration': 219, |
aa79ac0c | 698 | 'upload_date': '20100909', |
4fe54c12 | 699 | 'uploader': 'Amazing Atheist', |
aa79ac0c | 700 | 'uploader_id': 'TheAmazingAtheist', |
ec85ded8 | 701 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist', |
aa79ac0c PH |
702 | 'title': 'Burning Everyone\'s Koran', |
703 | 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html', | |
704 | } | |
c522adb1 JMF |
705 | }, |
706 | # Normal age-gate video (No vevo, embed allowed) | |
707 | { | |
2d3d2997 | 708 | 'url': 'https://youtube.com/watch?v=HtVdAasjOgU', |
c522adb1 JMF |
709 | 'info_dict': { |
710 | 'id': 'HtVdAasjOgU', | |
711 | 'ext': 'mp4', | |
712 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
ec85ded8 | 713 | 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', |
556dbe7f | 714 | 'duration': 142, |
c522adb1 JMF |
715 | 'uploader': 'The Witcher', |
716 | 'uploader_id': 'WitcherGame', | |
ec85ded8 | 717 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame', |
c522adb1 | 718 | 'upload_date': '20140605', |
34952f09 | 719 | 'age_limit': 18, |
c522adb1 JMF |
720 | }, |
721 | }, | |
fccae2b9 S |
722 | # Age-gate video with encrypted signature |
723 | { | |
2d3d2997 | 724 | 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU', |
fccae2b9 S |
725 | 'info_dict': { |
726 | 'id': '6kLq3WMV1nU', | |
4fe54c12 | 727 | 'ext': 'mp4', |
fccae2b9 S |
728 | 'title': 'Dedication To My Ex (Miss That) (Lyric Video)', |
729 | 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', | |
eb6793ba | 730 | 'duration': 246, |
fccae2b9 S |
731 | 'uploader': 'LloydVEVO', |
732 | 'uploader_id': 'LloydVEVO', | |
ec85ded8 | 733 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO', |
fccae2b9 | 734 | 'upload_date': '20110629', |
34952f09 | 735 | 'age_limit': 18, |
fccae2b9 S |
736 | }, |
737 | }, | |
067aa17e | 738 | # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421) |
7d02dcfa | 739 | # YouTube Red ad is not captured for creator |
774e208f PH |
740 | { |
741 | 'url': '__2ABJjxzNo', | |
742 | 'info_dict': { | |
743 | 'id': '__2ABJjxzNo', | |
744 | 'ext': 'mp4', | |
556dbe7f | 745 | 'duration': 266, |
774e208f PH |
746 | 'upload_date': '20100430', |
747 | 'uploader_id': 'deadmau5', | |
ec85ded8 | 748 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5', |
0cb58b02 | 749 | 'creator': 'deadmau5', |
774e208f PH |
750 | 'description': 'md5:12c56784b8032162bb936a5f76d55360', |
751 | 'uploader': 'deadmau5', | |
752 | 'title': 'Deadmau5 - Some Chords (HD)', | |
0cb58b02 | 753 | 'alt_title': 'Some Chords', |
774e208f PH |
754 | }, |
755 | 'expected_warnings': [ | |
756 | 'DASH manifest missing', | |
757 | ] | |
e52a40ab | 758 | }, |
067aa17e | 759 | # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431) |
e52a40ab PH |
760 | { |
761 | 'url': 'lqQg6PlCWgI', | |
762 | 'info_dict': { | |
763 | 'id': 'lqQg6PlCWgI', | |
764 | 'ext': 'mp4', | |
556dbe7f | 765 | 'duration': 6085, |
90227264 | 766 | 'upload_date': '20150827', |
cbe2bd91 | 767 | 'uploader_id': 'olympic', |
ec85ded8 | 768 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic', |
cbe2bd91 | 769 | 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', |
be49068d | 770 | 'uploader': 'Olympic', |
cbe2bd91 PH |
771 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', |
772 | }, | |
773 | 'params': { | |
774 | 'skip_download': 'requires avconv', | |
e52a40ab | 775 | } |
cbe2bd91 | 776 | }, |
6271f1ca PH |
777 | # Non-square pixels |
778 | { | |
779 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
780 | 'info_dict': { | |
781 | 'id': '_b-2C3KPAM0', | |
782 | 'ext': 'mp4', | |
783 | 'stretched_ratio': 16 / 9., | |
556dbe7f | 784 | 'duration': 85, |
6271f1ca PH |
785 | 'upload_date': '20110310', |
786 | 'uploader_id': 'AllenMeow', | |
ec85ded8 | 787 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow', |
6271f1ca | 788 | '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 | 789 | 'uploader': '孫ᄋᄅ', |
6271f1ca PH |
790 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', |
791 | }, | |
06b491eb S |
792 | }, |
793 | # url_encoded_fmt_stream_map is empty string | |
794 | { | |
795 | 'url': 'qEJwOuvDf7I', | |
796 | 'info_dict': { | |
797 | 'id': 'qEJwOuvDf7I', | |
f57b7835 | 798 | 'ext': 'webm', |
06b491eb S |
799 | 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', |
800 | 'description': '', | |
801 | 'upload_date': '20150404', | |
802 | 'uploader_id': 'spbelect', | |
803 | 'uploader': 'Наблюдатели Петербурга', | |
804 | }, | |
805 | 'params': { | |
806 | 'skip_download': 'requires avconv', | |
e323cf3f S |
807 | }, |
808 | 'skip': 'This live event has ended.', | |
06b491eb | 809 | }, |
067aa17e | 810 | # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097) |
da77d856 S |
811 | { |
812 | 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y', | |
813 | 'info_dict': { | |
814 | 'id': 'FIl7x6_3R5Y', | |
eb6793ba | 815 | 'ext': 'webm', |
da77d856 S |
816 | 'title': 'md5:7b81415841e02ecd4313668cde88737a', |
817 | 'description': 'md5:116377fd2963b81ec4ce64b542173306', | |
556dbe7f | 818 | 'duration': 220, |
da77d856 S |
819 | 'upload_date': '20150625', |
820 | 'uploader_id': 'dorappi2000', | |
ec85ded8 | 821 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000', |
da77d856 | 822 | 'uploader': 'dorappi2000', |
eb6793ba | 823 | 'formats': 'mincount:31', |
da77d856 | 824 | }, |
eb6793ba | 825 | 'skip': 'not actual anymore', |
2ee8f5d8 | 826 | }, |
8a1a26ce YCH |
827 | # DASH manifest with segment_list |
828 | { | |
829 | 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8', | |
830 | 'md5': '8ce563a1d667b599d21064e982ab9e31', | |
831 | 'info_dict': { | |
832 | 'id': 'CsmdDsKjzN8', | |
833 | 'ext': 'mp4', | |
17ee98e1 | 834 | 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510 |
8a1a26ce YCH |
835 | 'uploader': 'Airtek', |
836 | 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', | |
837 | 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ', | |
838 | 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', | |
839 | }, | |
840 | 'params': { | |
841 | 'youtube_include_dash_manifest': True, | |
842 | 'format': '135', # bestvideo | |
be49068d S |
843 | }, |
844 | 'skip': 'This live event has ended.', | |
2ee8f5d8 | 845 | }, |
cf7e015f S |
846 | { |
847 | # Multifeed videos (multiple cameras), URL is for Main Camera | |
848 | 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs', | |
849 | 'info_dict': { | |
850 | 'id': 'jqWvoWXjCVs', | |
851 | 'title': 'teamPGP: Rocket League Noob Stream', | |
852 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
853 | }, | |
854 | 'playlist': [{ | |
855 | 'info_dict': { | |
856 | 'id': 'jqWvoWXjCVs', | |
857 | 'ext': 'mp4', | |
858 | 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)', | |
859 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 860 | 'duration': 7335, |
cf7e015f S |
861 | 'upload_date': '20150721', |
862 | 'uploader': 'Beer Games Beer', | |
863 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 864 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 865 | 'license': 'Standard YouTube License', |
cf7e015f S |
866 | }, |
867 | }, { | |
868 | 'info_dict': { | |
869 | 'id': '6h8e8xoXJzg', | |
870 | 'ext': 'mp4', | |
871 | 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)', | |
872 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 873 | 'duration': 7337, |
cf7e015f S |
874 | 'upload_date': '20150721', |
875 | 'uploader': 'Beer Games Beer', | |
876 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 877 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 878 | 'license': 'Standard YouTube License', |
cf7e015f S |
879 | }, |
880 | }, { | |
881 | 'info_dict': { | |
882 | 'id': 'PUOgX5z9xZw', | |
883 | 'ext': 'mp4', | |
884 | 'title': 'teamPGP: Rocket League Noob Stream (grizzle)', | |
885 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 886 | 'duration': 7337, |
cf7e015f S |
887 | 'upload_date': '20150721', |
888 | 'uploader': 'Beer Games Beer', | |
889 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 890 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 891 | 'license': 'Standard YouTube License', |
cf7e015f S |
892 | }, |
893 | }, { | |
894 | 'info_dict': { | |
895 | 'id': 'teuwxikvS5k', | |
896 | 'ext': 'mp4', | |
897 | 'title': 'teamPGP: Rocket League Noob Stream (zim)', | |
898 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 899 | 'duration': 7334, |
cf7e015f S |
900 | 'upload_date': '20150721', |
901 | 'uploader': 'Beer Games Beer', | |
902 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 903 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 904 | 'license': 'Standard YouTube License', |
cf7e015f S |
905 | }, |
906 | }], | |
907 | 'params': { | |
908 | 'skip_download': True, | |
909 | }, | |
4fe54c12 | 910 | 'skip': 'This video is not available.', |
cbaed4bb | 911 | }, |
f9f49d87 | 912 | { |
067aa17e | 913 | # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536) |
f9f49d87 S |
914 | 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo', |
915 | 'info_dict': { | |
916 | 'id': 'gVfLd0zydlo', | |
917 | 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30', | |
918 | }, | |
919 | 'playlist_count': 2, | |
be49068d | 920 | 'skip': 'Not multifeed anymore', |
f9f49d87 | 921 | }, |
cbaed4bb | 922 | { |
2d3d2997 | 923 | 'url': 'https://vid.plus/FlRa-iH7PGw', |
cbaed4bb | 924 | 'only_matching': True, |
0e49d9a6 | 925 | }, |
6d4fc66b | 926 | { |
2d3d2997 | 927 | 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html', |
6d4fc66b S |
928 | 'only_matching': True, |
929 | }, | |
0e49d9a6 | 930 | { |
067aa17e | 931 | # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468) |
a8776b10 | 932 | # Also tests cut-off URL expansion in video description (see |
067aa17e S |
933 | # https://github.com/ytdl-org/youtube-dl/issues/1892, |
934 | # https://github.com/ytdl-org/youtube-dl/issues/8164) | |
0e49d9a6 LL |
935 | 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg', |
936 | 'info_dict': { | |
937 | 'id': 'lsguqyKfVQg', | |
938 | 'ext': 'mp4', | |
939 | 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21', | |
eb6793ba | 940 | 'alt_title': 'Dark Walk - Position Music', |
0e49d9a6 | 941 | 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a', |
556dbe7f | 942 | 'duration': 133, |
0e49d9a6 LL |
943 | 'upload_date': '20151119', |
944 | 'uploader_id': 'IronSoulElf', | |
ec85ded8 | 945 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf', |
0e49d9a6 | 946 | 'uploader': 'IronSoulElf', |
eb6793ba S |
947 | 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', |
948 | 'track': 'Dark Walk - Position Music', | |
949 | 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', | |
92bc97d3 | 950 | 'album': 'Position Music - Production Music Vol. 143 - Dark Walk', |
0e49d9a6 LL |
951 | }, |
952 | 'params': { | |
953 | 'skip_download': True, | |
954 | }, | |
955 | }, | |
61f92af1 | 956 | { |
067aa17e | 957 | # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468) |
61f92af1 S |
958 | 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8', |
959 | 'only_matching': True, | |
960 | }, | |
313dfc45 LL |
961 | { |
962 | # Video with yt:stretch=17:0 | |
963 | 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM', | |
964 | 'info_dict': { | |
965 | 'id': 'Q39EVAstoRM', | |
966 | 'ext': 'mp4', | |
967 | 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4', | |
968 | 'description': 'md5:ee18a25c350637c8faff806845bddee9', | |
969 | 'upload_date': '20151107', | |
970 | 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA', | |
971 | 'uploader': 'CH GAMER DROID', | |
972 | }, | |
973 | 'params': { | |
974 | 'skip_download': True, | |
975 | }, | |
be49068d | 976 | 'skip': 'This video does not exist.', |
313dfc45 | 977 | }, |
7caf9830 S |
978 | { |
979 | # Video licensed under Creative Commons | |
980 | 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA', | |
981 | 'info_dict': { | |
982 | 'id': 'M4gD1WSo5mA', | |
983 | 'ext': 'mp4', | |
984 | 'title': 'md5:e41008789470fc2533a3252216f1c1d1', | |
985 | 'description': 'md5:a677553cf0840649b731a3024aeff4cc', | |
556dbe7f | 986 | 'duration': 721, |
7caf9830 S |
987 | 'upload_date': '20150127', |
988 | 'uploader_id': 'BerkmanCenter', | |
ec85ded8 | 989 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter', |
556dbe7f | 990 | 'uploader': 'The Berkman Klein Center for Internet & Society', |
7caf9830 S |
991 | 'license': 'Creative Commons Attribution license (reuse allowed)', |
992 | }, | |
993 | 'params': { | |
994 | 'skip_download': True, | |
995 | }, | |
996 | }, | |
fd050249 S |
997 | { |
998 | # Channel-like uploader_url | |
999 | 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg', | |
1000 | 'info_dict': { | |
1001 | 'id': 'eQcmzGIKrzg', | |
1002 | 'ext': 'mp4', | |
1003 | 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders', | |
1004 | 'description': 'md5:dda0d780d5a6e120758d1711d062a867', | |
556dbe7f | 1005 | 'duration': 4060, |
fd050249 | 1006 | 'upload_date': '20151119', |
eb6793ba | 1007 | 'uploader': 'Bernie Sanders', |
fd050249 | 1008 | 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg', |
ec85ded8 | 1009 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg', |
fd050249 S |
1010 | 'license': 'Creative Commons Attribution license (reuse allowed)', |
1011 | }, | |
1012 | 'params': { | |
1013 | 'skip_download': True, | |
1014 | }, | |
1015 | }, | |
040ac686 S |
1016 | { |
1017 | 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY', | |
1018 | 'only_matching': True, | |
7f29cf54 S |
1019 | }, |
1020 | { | |
067aa17e | 1021 | # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059) |
7f29cf54 S |
1022 | 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo', |
1023 | 'only_matching': True, | |
6496ccb4 S |
1024 | }, |
1025 | { | |
1026 | # Rental video preview | |
1027 | 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg', | |
1028 | 'info_dict': { | |
1029 | 'id': 'uGpuVWrhIzE', | |
1030 | 'ext': 'mp4', | |
1031 | 'title': 'Piku - Trailer', | |
1032 | 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb', | |
1033 | 'upload_date': '20150811', | |
1034 | 'uploader': 'FlixMatrix', | |
1035 | 'uploader_id': 'FlixMatrixKaravan', | |
ec85ded8 | 1036 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan', |
6496ccb4 S |
1037 | 'license': 'Standard YouTube License', |
1038 | }, | |
1039 | 'params': { | |
1040 | 'skip_download': True, | |
1041 | }, | |
eb6793ba | 1042 | 'skip': 'This video is not available.', |
022a5d66 | 1043 | }, |
12afdc2a S |
1044 | { |
1045 | # YouTube Red video with episode data | |
1046 | 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4', | |
1047 | 'info_dict': { | |
1048 | 'id': 'iqKdEhx-dD4', | |
1049 | 'ext': 'mp4', | |
1050 | 'title': 'Isolation - Mind Field (Ep 1)', | |
4fe54c12 | 1051 | 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f', |
556dbe7f | 1052 | 'duration': 2085, |
12afdc2a S |
1053 | 'upload_date': '20170118', |
1054 | 'uploader': 'Vsauce', | |
1055 | 'uploader_id': 'Vsauce', | |
1056 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce', | |
12afdc2a S |
1057 | 'series': 'Mind Field', |
1058 | 'season_number': 1, | |
1059 | 'episode_number': 1, | |
1060 | }, | |
1061 | 'params': { | |
1062 | 'skip_download': True, | |
1063 | }, | |
1064 | 'expected_warnings': [ | |
1065 | 'Skipping DASH manifest', | |
1066 | ], | |
1067 | }, | |
c7121fa7 S |
1068 | { |
1069 | # The following content has been identified by the YouTube community | |
1070 | # as inappropriate or offensive to some audiences. | |
1071 | 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI', | |
1072 | 'info_dict': { | |
1073 | 'id': '6SJNVb0GnPI', | |
1074 | 'ext': 'mp4', | |
1075 | 'title': 'Race Differences in Intelligence', | |
1076 | 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1', | |
1077 | 'duration': 965, | |
1078 | 'upload_date': '20140124', | |
1079 | 'uploader': 'New Century Foundation', | |
1080 | 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg', | |
1081 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg', | |
c7121fa7 S |
1082 | }, |
1083 | 'params': { | |
1084 | 'skip_download': True, | |
1085 | }, | |
1086 | }, | |
022a5d66 S |
1087 | { |
1088 | # itag 212 | |
1089 | 'url': '1t24XAntNCY', | |
1090 | 'only_matching': True, | |
fd5c4aab S |
1091 | }, |
1092 | { | |
1093 | # geo restricted to JP | |
1094 | 'url': 'sJL6WA-aGkQ', | |
1095 | 'only_matching': True, | |
1096 | }, | |
d0ba5587 S |
1097 | { |
1098 | 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', | |
1099 | 'only_matching': True, | |
1100 | }, | |
cd5a74a2 S |
1101 | { |
1102 | 'url': 'https://invidio.us/watch?v=BaW_jenozKc', | |
1103 | 'only_matching': True, | |
1104 | }, | |
825cd268 RA |
1105 | { |
1106 | # DRM protected | |
1107 | 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc', | |
1108 | 'only_matching': True, | |
4fe54c12 S |
1109 | }, |
1110 | { | |
1111 | # Video with unsupported adaptive stream type formats | |
1112 | 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U', | |
1113 | 'info_dict': { | |
1114 | 'id': 'Z4Vy8R84T1U', | |
1115 | 'ext': 'mp4', | |
1116 | 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta', | |
1117 | 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e', | |
1118 | 'duration': 433, | |
1119 | 'upload_date': '20130923', | |
1120 | 'uploader': 'Amelia Putri Harwita', | |
1121 | 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q', | |
1122 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q', | |
1123 | 'formats': 'maxcount:10', | |
1124 | }, | |
1125 | 'params': { | |
1126 | 'skip_download': True, | |
1127 | 'youtube_include_dash_manifest': False, | |
1128 | }, | |
5caabd3c | 1129 | }, |
1130 | { | |
822b9d9c | 1131 | # Youtube Music Auto-generated description |
5caabd3c | 1132 | 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs', |
1133 | 'info_dict': { | |
1134 | 'id': 'MgNrAu2pzNs', | |
1135 | 'ext': 'mp4', | |
1136 | 'title': 'Voyeur Girl', | |
1137 | 'description': 'md5:7ae382a65843d6df2685993e90a8628f', | |
1138 | 'upload_date': '20190312', | |
1139 | 'uploader': 'Various Artists - Topic', | |
1140 | 'uploader_id': 'UCVWKBi1ELZn0QX2CBLSkiyw', | |
1141 | 'artist': 'Stephen', | |
1142 | 'track': 'Voyeur Girl', | |
1143 | 'album': 'it\'s too much love to know my dear', | |
1144 | 'release_date': '20190313', | |
1145 | 'release_year': 2019, | |
1146 | }, | |
1147 | 'params': { | |
1148 | 'skip_download': True, | |
1149 | }, | |
1150 | }, | |
1151 | { | |
822b9d9c | 1152 | # Youtube Music Auto-generated description |
5caabd3c | 1153 | # Retrieve 'artist' field from 'Artist:' in video description |
1154 | # when it is present on youtube music video | |
5caabd3c | 1155 | 'url': 'https://www.youtube.com/watch?v=k0jLE7tTwjY', |
1156 | 'info_dict': { | |
1157 | 'id': 'k0jLE7tTwjY', | |
1158 | 'ext': 'mp4', | |
1159 | 'title': 'Latch Feat. Sam Smith', | |
1160 | 'description': 'md5:3cb1e8101a7c85fcba9b4fb41b951335', | |
1161 | 'upload_date': '20150110', | |
1162 | 'uploader': 'Various Artists - Topic', | |
1163 | 'uploader_id': 'UCNkEcmYdjrH4RqtNgh7BZ9w', | |
1164 | 'artist': 'Disclosure', | |
1165 | 'track': 'Latch Feat. Sam Smith', | |
1166 | 'album': 'Latch Featuring Sam Smith', | |
1167 | 'release_date': '20121008', | |
1168 | 'release_year': 2012, | |
1169 | }, | |
1170 | 'params': { | |
1171 | 'skip_download': True, | |
1172 | }, | |
1173 | }, | |
1174 | { | |
822b9d9c | 1175 | # Youtube Music Auto-generated description |
5caabd3c | 1176 | # handle multiple artists on youtube music video |
1177 | 'url': 'https://www.youtube.com/watch?v=74qn0eJSjpA', | |
1178 | 'info_dict': { | |
1179 | 'id': '74qn0eJSjpA', | |
1180 | 'ext': 'mp4', | |
1181 | 'title': 'Eastside', | |
1182 | 'description': 'md5:290516bb73dcbfab0dcc4efe6c3de5f2', | |
1183 | 'upload_date': '20180710', | |
1184 | 'uploader': 'Benny Blanco - Topic', | |
1185 | 'uploader_id': 'UCzqz_ksRu_WkIzmivMdIS7A', | |
1186 | 'artist': 'benny blanco, Halsey, Khalid', | |
1187 | 'track': 'Eastside', | |
1188 | 'album': 'Eastside', | |
1189 | 'release_date': '20180713', | |
1190 | 'release_year': 2018, | |
1191 | }, | |
1192 | 'params': { | |
1193 | 'skip_download': True, | |
1194 | }, | |
1195 | }, | |
1196 | { | |
822b9d9c | 1197 | # Youtube Music Auto-generated description |
5caabd3c | 1198 | # handle youtube music video with release_year and no release_date |
1199 | 'url': 'https://www.youtube.com/watch?v=-hcAI0g-f5M', | |
1200 | 'info_dict': { | |
1201 | 'id': '-hcAI0g-f5M', | |
1202 | 'ext': 'mp4', | |
1203 | 'title': 'Put It On Me', | |
1204 | 'description': 'md5:93c55acc682ae7b0c668f2e34e1c069e', | |
1205 | 'upload_date': '20180426', | |
1206 | 'uploader': 'Matt Maeson - Topic', | |
1207 | 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ', | |
1208 | 'artist': 'Matt Maeson', | |
1209 | 'track': 'Put It On Me', | |
1210 | 'album': 'The Hearse', | |
1211 | 'release_date': None, | |
1212 | 'release_year': 2018, | |
1213 | }, | |
1214 | 'params': { | |
1215 | 'skip_download': True, | |
1216 | }, | |
1217 | }, | |
2eb88d95 PH |
1218 | ] |
1219 | ||
e0df6211 PH |
1220 | def __init__(self, *args, **kwargs): |
1221 | super(YoutubeIE, self).__init__(*args, **kwargs) | |
83799698 | 1222 | self._player_cache = {} |
e0df6211 | 1223 | |
c5e8d7af PH |
1224 | def report_video_info_webpage_download(self, video_id): |
1225 | """Report attempt to download video info webpage.""" | |
69ea8ca4 | 1226 | self.to_screen('%s: Downloading video info webpage' % video_id) |
c5e8d7af | 1227 | |
c5e8d7af PH |
1228 | def report_information_extraction(self, video_id): |
1229 | """Report attempt to extract video information.""" | |
69ea8ca4 | 1230 | self.to_screen('%s: Extracting video information' % video_id) |
c5e8d7af PH |
1231 | |
1232 | def report_unavailable_format(self, video_id, format): | |
1233 | """Report extracted video URL.""" | |
69ea8ca4 | 1234 | self.to_screen('%s: Format %s not available' % (video_id, format)) |
c5e8d7af PH |
1235 | |
1236 | def report_rtmp_download(self): | |
1237 | """Indicate the download will use the RTMP protocol.""" | |
69ea8ca4 | 1238 | self.to_screen('RTMP download detected') |
c5e8d7af | 1239 | |
60064c53 PH |
1240 | def _signature_cache_id(self, example_sig): |
1241 | """ Return a string representation of a signature """ | |
78caa52a | 1242 | return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) |
60064c53 PH |
1243 | |
1244 | def _extract_signature_function(self, video_id, player_url, example_sig): | |
cf010131 | 1245 | id_m = re.match( |
63529e93 | 1246 | r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$', |
cf010131 | 1247 | player_url) |
c081b35c PH |
1248 | if not id_m: |
1249 | raise ExtractorError('Cannot identify player %r' % player_url) | |
e0df6211 PH |
1250 | player_type = id_m.group('ext') |
1251 | player_id = id_m.group('id') | |
1252 | ||
c4417ddb | 1253 | # Read from filesystem cache |
60064c53 PH |
1254 | func_id = '%s_%s_%s' % ( |
1255 | player_type, player_id, self._signature_cache_id(example_sig)) | |
c4417ddb | 1256 | assert os.path.basename(func_id) == func_id |
a0e07d31 | 1257 | |
69ea8ca4 | 1258 | cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) |
a0e07d31 | 1259 | if cache_spec is not None: |
78caa52a | 1260 | return lambda s: ''.join(s[i] for i in cache_spec) |
83799698 | 1261 | |
6d1a55a5 PH |
1262 | download_note = ( |
1263 | 'Downloading player %s' % player_url | |
1264 | if self._downloader.params.get('verbose') else | |
1265 | 'Downloading %s player %s' % (player_type, player_id) | |
1266 | ) | |
e0df6211 PH |
1267 | if player_type == 'js': |
1268 | code = self._download_webpage( | |
1269 | player_url, video_id, | |
6d1a55a5 | 1270 | note=download_note, |
69ea8ca4 | 1271 | errnote='Download of %s failed' % player_url) |
83799698 | 1272 | res = self._parse_sig_js(code) |
c4417ddb | 1273 | elif player_type == 'swf': |
e0df6211 PH |
1274 | urlh = self._request_webpage( |
1275 | player_url, video_id, | |
6d1a55a5 | 1276 | note=download_note, |
69ea8ca4 | 1277 | errnote='Download of %s failed' % player_url) |
e0df6211 | 1278 | code = urlh.read() |
83799698 | 1279 | res = self._parse_sig_swf(code) |
e0df6211 PH |
1280 | else: |
1281 | assert False, 'Invalid player type %r' % player_type | |
1282 | ||
785521bf PH |
1283 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
1284 | cache_res = res(test_string) | |
1285 | cache_spec = [ord(c) for c in cache_res] | |
83799698 | 1286 | |
69ea8ca4 | 1287 | self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) |
83799698 PH |
1288 | return res |
1289 | ||
60064c53 | 1290 | def _print_sig_code(self, func, example_sig): |
edf3e38e PH |
1291 | def gen_sig_code(idxs): |
1292 | def _genslice(start, end, step): | |
78caa52a | 1293 | starts = '' if start == 0 else str(start) |
8bcc8756 | 1294 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' |
69ea8ca4 | 1295 | steps = '' if step == 1 else (':%d' % step) |
78caa52a | 1296 | return 's[%s%s%s]' % (starts, ends, steps) |
edf3e38e PH |
1297 | |
1298 | step = None | |
7af808a5 PH |
1299 | # Quelch pyflakes warnings - start will be set when step is set |
1300 | start = '(Never used)' | |
edf3e38e PH |
1301 | for i, prev in zip(idxs[1:], idxs[:-1]): |
1302 | if step is not None: | |
1303 | if i - prev == step: | |
1304 | continue | |
1305 | yield _genslice(start, prev, step) | |
1306 | step = None | |
1307 | continue | |
1308 | if i - prev in [-1, 1]: | |
1309 | step = i - prev | |
1310 | start = prev | |
1311 | continue | |
1312 | else: | |
78caa52a | 1313 | yield 's[%d]' % prev |
edf3e38e | 1314 | if step is None: |
78caa52a | 1315 | yield 's[%d]' % i |
edf3e38e PH |
1316 | else: |
1317 | yield _genslice(start, i, step) | |
1318 | ||
78caa52a | 1319 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
c705320f | 1320 | cache_res = func(test_string) |
edf3e38e | 1321 | cache_spec = [ord(c) for c in cache_res] |
78caa52a | 1322 | expr_code = ' + '.join(gen_sig_code(cache_spec)) |
60064c53 PH |
1323 | signature_id_tuple = '(%s)' % ( |
1324 | ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) | |
69ea8ca4 | 1325 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' |
78caa52a | 1326 | ' return %s\n') % (signature_id_tuple, expr_code) |
69ea8ca4 | 1327 | self.to_screen('Extracted signature function:\n' + code) |
edf3e38e | 1328 | |
e0df6211 PH |
1329 | def _parse_sig_js(self, jscode): |
1330 | funcname = self._search_regex( | |
abefc03f S |
1331 | (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', |
1332 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
31ce6e99 | 1333 | r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)', |
abefc03f S |
1334 | # Obsolete patterns |
1335 | r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
9a47fa35 | 1336 | r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(', |
abefc03f S |
1337 | r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(', |
1338 | r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1339 | r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1340 | r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1341 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1342 | r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('), | |
3c90cc8b | 1343 | jscode, 'Initial JS player signature function name', group='sig') |
2b25cb5d PH |
1344 | |
1345 | jsi = JSInterpreter(jscode) | |
1346 | initial_function = jsi.extract_function(funcname) | |
e0df6211 PH |
1347 | return lambda s: initial_function([s]) |
1348 | ||
1349 | def _parse_sig_swf(self, file_contents): | |
54256267 | 1350 | swfi = SWFInterpreter(file_contents) |
78caa52a | 1351 | TARGET_CLASSNAME = 'SignatureDecipher' |
54256267 | 1352 | searched_class = swfi.extract_class(TARGET_CLASSNAME) |
78caa52a | 1353 | initial_function = swfi.extract_function(searched_class, 'decipher') |
e0df6211 PH |
1354 | return lambda s: initial_function([s]) |
1355 | ||
83799698 | 1356 | def _decrypt_signature(self, s, video_id, player_url, age_gate=False): |
257a2501 | 1357 | """Turn the encrypted s field into a working signature""" |
6b37f0be | 1358 | |
c8bf86d5 | 1359 | if player_url is None: |
69ea8ca4 | 1360 | raise ExtractorError('Cannot decrypt signature without player_url') |
920de7a2 | 1361 | |
69ea8ca4 | 1362 | if player_url.startswith('//'): |
78caa52a | 1363 | player_url = 'https:' + player_url |
3c90cc8b S |
1364 | elif not re.match(r'https?://', player_url): |
1365 | player_url = compat_urlparse.urljoin( | |
1366 | 'https://www.youtube.com', player_url) | |
c8bf86d5 | 1367 | try: |
62af3a0e | 1368 | player_id = (player_url, self._signature_cache_id(s)) |
c8bf86d5 PH |
1369 | if player_id not in self._player_cache: |
1370 | func = self._extract_signature_function( | |
60064c53 | 1371 | video_id, player_url, s |
c8bf86d5 PH |
1372 | ) |
1373 | self._player_cache[player_id] = func | |
1374 | func = self._player_cache[player_id] | |
1375 | if self._downloader.params.get('youtube_print_sig_code'): | |
60064c53 | 1376 | self._print_sig_code(func, s) |
c8bf86d5 PH |
1377 | return func(s) |
1378 | except Exception as e: | |
1379 | tb = traceback.format_exc() | |
1380 | raise ExtractorError( | |
78caa52a | 1381 | 'Signature extraction failed: ' + tb, cause=e) |
e0df6211 | 1382 | |
360e1ca5 | 1383 | def _get_subtitles(self, video_id, webpage): |
de7f3446 | 1384 | try: |
60e47a26 | 1385 | subs_doc = self._download_xml( |
38c2e5b8 | 1386 | 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, |
7fad1c63 JMF |
1387 | video_id, note=False) |
1388 | except ExtractorError as err: | |
9b9c5355 | 1389 | self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err)) |
de7f3446 | 1390 | return {} |
de7f3446 JMF |
1391 | |
1392 | sub_lang_list = {} | |
60e47a26 JMF |
1393 | for track in subs_doc.findall('track'): |
1394 | lang = track.attrib['lang_code'] | |
7e660ac1 LD |
1395 | if lang in sub_lang_list: |
1396 | continue | |
360e1ca5 | 1397 | sub_formats = [] |
23d17e4b | 1398 | for ext in self._SUBTITLE_FORMATS: |
15707c7e | 1399 | params = compat_urllib_parse_urlencode({ |
360e1ca5 JMF |
1400 | 'lang': lang, |
1401 | 'v': video_id, | |
1402 | 'fmt': ext, | |
1403 | 'name': track.attrib['name'].encode('utf-8'), | |
1404 | }) | |
1405 | sub_formats.append({ | |
1406 | 'url': 'https://www.youtube.com/api/timedtext?' + params, | |
1407 | 'ext': ext, | |
1408 | }) | |
1409 | sub_lang_list[lang] = sub_formats | |
de7f3446 | 1410 | if not sub_lang_list: |
69ea8ca4 | 1411 | self._downloader.report_warning('video doesn\'t have subtitles') |
de7f3446 JMF |
1412 | return {} |
1413 | return sub_lang_list | |
1414 | ||
a72778d3 S |
1415 | def _get_ytplayer_config(self, video_id, webpage): |
1416 | patterns = ( | |
526b3b07 S |
1417 | # User data may contain arbitrary character sequences that may affect |
1418 | # JSON extraction with regex, e.g. when '};' is contained the second | |
1419 | # regex won't capture the whole JSON. Yet working around by trying more | |
1420 | # concrete regex first keeping in mind proper quoted string handling | |
1421 | # to be implemented in future that will replace this workaround (see | |
067aa17e S |
1422 | # https://github.com/ytdl-org/youtube-dl/issues/7468, |
1423 | # https://github.com/ytdl-org/youtube-dl/pull/7599) | |
a72778d3 S |
1424 | r';ytplayer\.config\s*=\s*({.+?});ytplayer', |
1425 | r';ytplayer\.config\s*=\s*({.+?});', | |
1426 | ) | |
1427 | config = self._search_regex( | |
1428 | patterns, webpage, 'ytplayer.config', default=None) | |
1429 | if config: | |
1430 | return self._parse_json( | |
1431 | uppercase_escape(config), video_id, fatal=False) | |
0e49d9a6 | 1432 | |
360e1ca5 | 1433 | def _get_automatic_captions(self, video_id, webpage): |
de7f3446 JMF |
1434 | """We need the webpage for getting the captions url, pass it as an |
1435 | argument to speed up the process.""" | |
69ea8ca4 | 1436 | self.to_screen('%s: Looking for automatic captions' % video_id) |
a72778d3 | 1437 | player_config = self._get_ytplayer_config(video_id, webpage) |
78caa52a | 1438 | err_msg = 'Couldn\'t find automatic captions for %s' % video_id |
a72778d3 | 1439 | if not player_config: |
de7f3446 JMF |
1440 | self._downloader.report_warning(err_msg) |
1441 | return {} | |
de7f3446 | 1442 | try: |
0792d563 | 1443 | args = player_config['args'] |
b78b292f S |
1444 | caption_url = args.get('ttsurl') |
1445 | if caption_url: | |
1446 | timestamp = args['timestamp'] | |
1447 | # We get the available subtitles | |
15707c7e | 1448 | list_params = compat_urllib_parse_urlencode({ |
b78b292f S |
1449 | 'type': 'list', |
1450 | 'tlangs': 1, | |
1451 | 'asrs': 1, | |
1452 | }) | |
1453 | list_url = caption_url + '&' + list_params | |
1454 | caption_list = self._download_xml(list_url, video_id) | |
1455 | original_lang_node = caption_list.find('track') | |
1456 | if original_lang_node is None: | |
1457 | self._downloader.report_warning('Video doesn\'t have automatic captions') | |
1458 | return {} | |
1459 | original_lang = original_lang_node.attrib['lang_code'] | |
1460 | caption_kind = original_lang_node.attrib.get('kind', '') | |
1461 | ||
1462 | sub_lang_list = {} | |
1463 | for lang_node in caption_list.findall('target'): | |
1464 | sub_lang = lang_node.attrib['lang_code'] | |
1465 | sub_formats = [] | |
1466 | for ext in self._SUBTITLE_FORMATS: | |
15707c7e | 1467 | params = compat_urllib_parse_urlencode({ |
b78b292f S |
1468 | 'lang': original_lang, |
1469 | 'tlang': sub_lang, | |
1470 | 'fmt': ext, | |
1471 | 'ts': timestamp, | |
1472 | 'kind': caption_kind, | |
1473 | }) | |
1474 | sub_formats.append({ | |
1475 | 'url': caption_url + '&' + params, | |
1476 | 'ext': ext, | |
1477 | }) | |
1478 | sub_lang_list[sub_lang] = sub_formats | |
1479 | return sub_lang_list | |
1480 | ||
ddbb4c5c S |
1481 | def make_captions(sub_url, sub_langs): |
1482 | parsed_sub_url = compat_urllib_parse_urlparse(sub_url) | |
1483 | caption_qs = compat_parse_qs(parsed_sub_url.query) | |
1484 | captions = {} | |
1485 | for sub_lang in sub_langs: | |
1486 | sub_formats = [] | |
1487 | for ext in self._SUBTITLE_FORMATS: | |
1488 | caption_qs.update({ | |
1489 | 'tlang': [sub_lang], | |
1490 | 'fmt': [ext], | |
1491 | }) | |
1492 | sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace( | |
1493 | query=compat_urllib_parse_urlencode(caption_qs, True))) | |
1494 | sub_formats.append({ | |
1495 | 'url': sub_url, | |
1496 | 'ext': ext, | |
1497 | }) | |
1498 | captions[sub_lang] = sub_formats | |
1499 | return captions | |
1500 | ||
1501 | # New captions format as of 22.06.2017 | |
1502 | player_response = args.get('player_response') | |
1503 | if player_response and isinstance(player_response, compat_str): | |
1504 | player_response = self._parse_json( | |
1505 | player_response, video_id, fatal=False) | |
1506 | if player_response: | |
1507 | renderer = player_response['captions']['playerCaptionsTracklistRenderer'] | |
1508 | base_url = renderer['captionTracks'][0]['baseUrl'] | |
1509 | sub_lang_list = [] | |
1510 | for lang in renderer['translationLanguages']: | |
1511 | lang_code = lang.get('languageCode') | |
1512 | if lang_code: | |
1513 | sub_lang_list.append(lang_code) | |
1514 | return make_captions(base_url, sub_lang_list) | |
1515 | ||
b78b292f S |
1516 | # Some videos don't provide ttsurl but rather caption_tracks and |
1517 | # caption_translation_languages (e.g. 20LmZk1hakA) | |
ddbb4c5c | 1518 | # Does not used anymore as of 22.06.2017 |
b78b292f S |
1519 | caption_tracks = args['caption_tracks'] |
1520 | caption_translation_languages = args['caption_translation_languages'] | |
1521 | caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0] | |
ddbb4c5c | 1522 | sub_lang_list = [] |
b78b292f S |
1523 | for lang in caption_translation_languages.split(','): |
1524 | lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang)) | |
1525 | sub_lang = lang_qs.get('lc', [None])[0] | |
ddbb4c5c S |
1526 | if sub_lang: |
1527 | sub_lang_list.append(sub_lang) | |
1528 | return make_captions(caption_url, sub_lang_list) | |
de7f3446 JMF |
1529 | # An extractor error can be raise by the download process if there are |
1530 | # no automatic captions but there are subtitles | |
ddbb4c5c | 1531 | except (KeyError, IndexError, ExtractorError): |
de7f3446 JMF |
1532 | self._downloader.report_warning(err_msg) |
1533 | return {} | |
1534 | ||
21c340b8 S |
1535 | def _mark_watched(self, video_id, video_info, player_response): |
1536 | playback_url = url_or_none(try_get( | |
1537 | player_response, | |
1538 | lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get( | |
1539 | video_info, lambda x: x['videostats_playback_base_url'][0])) | |
d77ab8e2 S |
1540 | if not playback_url: |
1541 | return | |
1542 | parsed_playback_url = compat_urlparse.urlparse(playback_url) | |
1543 | qs = compat_urlparse.parse_qs(parsed_playback_url.query) | |
1544 | ||
1545 | # cpn generation algorithm is reverse engineered from base.js. | |
1546 | # In fact it works even with dummy cpn. | |
1547 | CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_' | |
1548 | cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))) | |
1549 | ||
1550 | qs.update({ | |
1551 | 'ver': ['2'], | |
1552 | 'cpn': [cpn], | |
1553 | }) | |
1554 | playback_url = compat_urlparse.urlunparse( | |
15707c7e | 1555 | parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True))) |
d77ab8e2 S |
1556 | |
1557 | self._download_webpage( | |
1558 | playback_url, video_id, 'Marking watched', | |
1559 | 'Unable to mark watched', fatal=False) | |
1560 | ||
66c9fa36 S |
1561 | @staticmethod |
1562 | def _extract_urls(webpage): | |
1563 | # Embedded YouTube player | |
1564 | entries = [ | |
1565 | unescapeHTML(mobj.group('url')) | |
1566 | for mobj in re.finditer(r'''(?x) | |
1567 | (?: | |
1568 | <iframe[^>]+?src=| | |
1569 | data-video-url=| | |
1570 | <embed[^>]+?src=| | |
1571 | embedSWF\(?:\s*| | |
1572 | <object[^>]+data=| | |
1573 | new\s+SWFObject\( | |
1574 | ) | |
1575 | (["\']) | |
1576 | (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ | |
f2332f18 | 1577 | (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?) |
66c9fa36 S |
1578 | \1''', webpage)] |
1579 | ||
1580 | # lazyYT YouTube embed | |
1581 | entries.extend(list(map( | |
1582 | unescapeHTML, | |
1583 | re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)))) | |
1584 | ||
1585 | # Wordpress "YouTube Video Importer" plugin | |
1586 | matches = re.findall(r'''(?x)<div[^>]+ | |
1587 | class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+ | |
1588 | data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage) | |
1589 | entries.extend(m[-1] for m in matches) | |
1590 | ||
1591 | return entries | |
1592 | ||
1593 | @staticmethod | |
1594 | def _extract_url(webpage): | |
1595 | urls = YoutubeIE._extract_urls(webpage) | |
1596 | return urls[0] if urls else None | |
1597 | ||
97665381 PH |
1598 | @classmethod |
1599 | def extract_id(cls, url): | |
1600 | mobj = re.match(cls._VALID_URL, url, re.VERBOSE) | |
c5e8d7af | 1601 | if mobj is None: |
69ea8ca4 | 1602 | raise ExtractorError('Invalid URL: %s' % url) |
c5e8d7af PH |
1603 | video_id = mobj.group(2) |
1604 | return video_id | |
1605 | ||
9cafc3fd S |
1606 | @staticmethod |
1607 | def _extract_chapters(description, duration): | |
1608 | if not description: | |
1609 | return None | |
1610 | chapter_lines = re.findall( | |
1611 | r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)', | |
1612 | description) | |
1613 | if not chapter_lines: | |
1614 | return None | |
1615 | chapters = [] | |
1616 | for next_num, (chapter_line, time_point) in enumerate( | |
1617 | chapter_lines, start=1): | |
1618 | start_time = parse_duration(time_point) | |
1619 | if start_time is None: | |
1620 | continue | |
39d4c1be S |
1621 | if start_time > duration: |
1622 | break | |
9cafc3fd S |
1623 | end_time = (duration if next_num == len(chapter_lines) |
1624 | else parse_duration(chapter_lines[next_num][1])) | |
1625 | if end_time is None: | |
1626 | continue | |
39d4c1be S |
1627 | if end_time > duration: |
1628 | end_time = duration | |
1629 | if start_time > end_time: | |
1630 | break | |
9cafc3fd S |
1631 | chapter_title = re.sub( |
1632 | r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-') | |
1633 | chapter_title = re.sub(r'\s+', ' ', chapter_title) | |
1634 | chapters.append({ | |
1635 | 'start_time': start_time, | |
1636 | 'end_time': end_time, | |
1637 | 'title': chapter_title, | |
1638 | }) | |
1639 | return chapters | |
1640 | ||
c5e8d7af | 1641 | def _real_extract(self, url): |
cf7e015f S |
1642 | url, smuggled_data = unsmuggle_url(url, {}) |
1643 | ||
7e8c0af0 | 1644 | proto = ( |
78caa52a PH |
1645 | 'http' if self._downloader.params.get('prefer_insecure', False) |
1646 | else 'https') | |
7e8c0af0 | 1647 | |
7c80519c | 1648 | start_time = None |
297a564b | 1649 | end_time = None |
7c80519c JMF |
1650 | parsed_url = compat_urllib_parse_urlparse(url) |
1651 | for component in [parsed_url.fragment, parsed_url.query]: | |
1652 | query = compat_parse_qs(component) | |
297a564b | 1653 | if start_time is None and 't' in query: |
7c80519c | 1654 | start_time = parse_duration(query['t'][0]) |
2929fa0e JMF |
1655 | if start_time is None and 'start' in query: |
1656 | start_time = parse_duration(query['start'][0]) | |
297a564b JMF |
1657 | if end_time is None and 'end' in query: |
1658 | end_time = parse_duration(query['end'][0]) | |
7c80519c | 1659 | |
c5e8d7af PH |
1660 | # Extract original video URL from URL with redirection, like age verification, using next_url parameter |
1661 | mobj = re.search(self._NEXT_URL_RE, url) | |
1662 | if mobj: | |
7fd002c0 | 1663 | url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/') |
97665381 | 1664 | video_id = self.extract_id(url) |
c5e8d7af PH |
1665 | |
1666 | # Get video webpage | |
aa79ac0c | 1667 | url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id |
a1f934b1 | 1668 | video_webpage = self._download_webpage(url, video_id) |
c5e8d7af PH |
1669 | |
1670 | # Attempt to extract SWF player URL | |
e0df6211 | 1671 | mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) |
c5e8d7af PH |
1672 | if mobj is not None: |
1673 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) | |
1674 | else: | |
1675 | player_url = None | |
1676 | ||
d8d24a92 S |
1677 | dash_mpds = [] |
1678 | ||
1679 | def add_dash_mpd(video_info): | |
1680 | dash_mpd = video_info.get('dashmpd') | |
1681 | if dash_mpd and dash_mpd[0] not in dash_mpds: | |
1682 | dash_mpds.append(dash_mpd[0]) | |
1683 | ||
561b456e S |
1684 | def add_dash_mpd_pr(pl_response): |
1685 | dash_mpd = url_or_none(try_get( | |
1686 | pl_response, lambda x: x['streamingData']['dashManifestUrl'], | |
1687 | compat_str)) | |
1688 | if dash_mpd and dash_mpd not in dash_mpds: | |
1689 | dash_mpds.append(dash_mpd) | |
1690 | ||
c7121fa7 S |
1691 | is_live = None |
1692 | view_count = None | |
1693 | ||
1694 | def extract_view_count(v_info): | |
1695 | return int_or_none(try_get(v_info, lambda x: x['view_count'][0])) | |
1696 | ||
026fbedc S |
1697 | def extract_token(v_info): |
1698 | return dict_get(v_info, ('account_playback_token', 'accountPlaybackToken', 'token')) | |
1699 | ||
c2d125d9 S |
1700 | def extract_player_response(player_response, video_id): |
1701 | pl_response = str_or_none(player_response) | |
1702 | if not pl_response: | |
1703 | return | |
1704 | pl_response = self._parse_json(pl_response, video_id, fatal=False) | |
1705 | if isinstance(pl_response, dict): | |
1706 | add_dash_mpd_pr(pl_response) | |
1707 | return pl_response | |
1708 | ||
dbdaaa23 S |
1709 | player_response = {} |
1710 | ||
c5e8d7af | 1711 | # Get video info |
6449cd80 | 1712 | embed_webpage = None |
c108eb73 | 1713 | if re.search(r'player-age-gate-content">', video_webpage) is not None: |
c108eb73 JMF |
1714 | age_gate = True |
1715 | # We simulate the access to the video from www.youtube.com/v/{video_id} | |
1716 | # this can be viewed without login into Youtube | |
beb95e77 CL |
1717 | url = proto + '://www.youtube.com/embed/%s' % video_id |
1718 | embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage') | |
15707c7e | 1719 | data = compat_urllib_parse_urlencode({ |
2c57c7fa JMF |
1720 | 'video_id': video_id, |
1721 | 'eurl': 'https://youtube.googleapis.com/v/' + video_id, | |
c084c934 | 1722 | 'sts': self._search_regex( |
beb95e77 | 1723 | r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''), |
2c57c7fa | 1724 | }) |
7e8c0af0 | 1725 | video_info_url = proto + '://www.youtube.com/get_video_info?' + data |
94bd3613 PH |
1726 | video_info_webpage = self._download_webpage( |
1727 | video_info_url, video_id, | |
20436c30 | 1728 | note='Refetching age-gated info webpage', |
94bd3613 | 1729 | errnote='unable to download video info webpage') |
c5e8d7af | 1730 | video_info = compat_parse_qs(video_info_webpage) |
c2d125d9 S |
1731 | pl_response = video_info.get('player_response', [None])[0] |
1732 | player_response = extract_player_response(pl_response, video_id) | |
d8d24a92 | 1733 | add_dash_mpd(video_info) |
c2d125d9 | 1734 | view_count = extract_view_count(video_info) |
c108eb73 JMF |
1735 | else: |
1736 | age_gate = False | |
bc93bdb5 | 1737 | video_info = None |
dc4e4f90 | 1738 | sts = None |
d8d24a92 | 1739 | # Try looking directly into the video webpage |
a72778d3 S |
1740 | ytplayer_config = self._get_ytplayer_config(video_id, video_webpage) |
1741 | if ytplayer_config: | |
4e62ebe2 | 1742 | args = ytplayer_config['args'] |
4c76aa06 | 1743 | if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'): |
d8d24a92 S |
1744 | # Convert to the same format returned by compat_parse_qs |
1745 | video_info = dict((k, [v]) for k, v in args.items()) | |
1746 | add_dash_mpd(video_info) | |
6496ccb4 S |
1747 | # Rental video is not rented but preview is available (e.g. |
1748 | # https://www.youtube.com/watch?v=yYr8q0y5Jfg, | |
067aa17e | 1749 | # https://github.com/ytdl-org/youtube-dl/issues/10532) |
6496ccb4 S |
1750 | if not video_info and args.get('ypc_vid'): |
1751 | return self.url_result( | |
1752 | args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid']) | |
2fe1ff85 JMF |
1753 | if args.get('livestream') == '1' or args.get('live_playback') == 1: |
1754 | is_live = True | |
dc4e4f90 | 1755 | sts = ytplayer_config.get('sts') |
dbdaaa23 | 1756 | if not player_response: |
c2d125d9 | 1757 | player_response = extract_player_response(args.get('player_response'), video_id) |
0a3cf9ad | 1758 | if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): |
561b456e | 1759 | add_dash_mpd_pr(player_response) |
0a3cf9ad S |
1760 | # We also try looking in get_video_info since it may contain different dashmpd |
1761 | # URL that points to a DASH manifest with possibly different itag set (some itags | |
1762 | # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH | |
1763 | # manifest pointed by get_video_info's dashmpd). | |
1764 | # The general idea is to take a union of itags of both DASH manifests (for example | |
067aa17e | 1765 | # video with such 'manifest behavior' see https://github.com/ytdl-org/youtube-dl/issues/6093) |
4e62ebe2 | 1766 | self.report_video_info_webpage_download(video_id) |
a61ce714 | 1767 | for el in ('embedded', 'detailpage', 'vevo', ''): |
dc4e4f90 S |
1768 | query = { |
1769 | 'video_id': video_id, | |
1770 | 'ps': 'default', | |
1771 | 'eurl': '', | |
1772 | 'gl': 'US', | |
1773 | 'hl': 'en', | |
1774 | } | |
1775 | if el: | |
1776 | query['el'] = el | |
1777 | if sts: | |
1778 | query['sts'] = sts | |
810fb84d | 1779 | video_info_webpage = self._download_webpage( |
dc4e4f90 | 1780 | '%s://www.youtube.com/get_video_info' % proto, |
4e62ebe2 | 1781 | video_id, note=False, |
dc4e4f90 S |
1782 | errnote='unable to download video info webpage', |
1783 | fatal=False, query=query) | |
1784 | if not video_info_webpage: | |
1785 | continue | |
0a3cf9ad | 1786 | get_video_info = compat_parse_qs(video_info_webpage) |
dbdaaa23 S |
1787 | if not player_response: |
1788 | pl_response = get_video_info.get('player_response', [None])[0] | |
c2d125d9 | 1789 | player_response = extract_player_response(pl_response, video_id) |
fd545fc6 | 1790 | add_dash_mpd(get_video_info) |
c7121fa7 S |
1791 | if view_count is None: |
1792 | view_count = extract_view_count(get_video_info) | |
0a3cf9ad S |
1793 | if not video_info: |
1794 | video_info = get_video_info | |
026fbedc | 1795 | get_token = extract_token(get_video_info) |
56667d62 | 1796 | if get_token: |
89ea063e S |
1797 | # Different get_video_info requests may report different results, e.g. |
1798 | # some may report video unavailability, but some may serve it without | |
067aa17e | 1799 | # any complaint (see https://github.com/ytdl-org/youtube-dl/issues/7362, |
89ea063e S |
1800 | # the original webpage as well as el=info and el=embedded get_video_info |
1801 | # requests report video unavailability due to geo restriction while | |
1802 | # el=detailpage succeeds and returns valid data). This is probably | |
1803 | # due to YouTube measures against IP ranges of hosting providers. | |
1804 | # Working around by preferring the first succeeded video_info containing | |
1805 | # the token if no such video_info yet was found. | |
026fbedc | 1806 | token = extract_token(video_info) |
56667d62 | 1807 | if not token: |
44b2264f | 1808 | video_info = get_video_info |
4e62ebe2 | 1809 | break |
bbb7c3f7 YCH |
1810 | |
1811 | def extract_unavailable_message(): | |
0add33ab S |
1812 | messages = [] |
1813 | for tag, kind in (('h1', 'message'), ('div', 'submessage')): | |
1814 | msg = self._html_search_regex( | |
1815 | r'(?s)<{tag}[^>]+id=["\']unavailable-{kind}["\'][^>]*>(.+?)</{tag}>'.format(tag=tag, kind=kind), | |
1816 | video_webpage, 'unavailable %s' % kind, default=None) | |
1817 | if msg: | |
1818 | messages.append(msg) | |
1819 | if messages: | |
1820 | return '\n'.join(messages) | |
bbb7c3f7 | 1821 | |
15be3eb5 RA |
1822 | if not video_info: |
1823 | unavailable_message = extract_unavailable_message() | |
1824 | if not unavailable_message: | |
1825 | unavailable_message = 'Unable to extract video data' | |
1826 | raise ExtractorError( | |
1827 | 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id) | |
1828 | ||
dbdaaa23 S |
1829 | video_details = try_get( |
1830 | player_response, lambda x: x['videoDetails'], dict) or {} | |
1831 | ||
8dbf751a RA |
1832 | video_title = video_info.get('title', [None])[0] or video_details.get('title') |
1833 | if not video_title: | |
cf7e015f S |
1834 | self._downloader.report_warning('Unable to extract video title') |
1835 | video_title = '_' | |
1836 | ||
9cafc3fd | 1837 | description_original = video_description = get_element_by_id("eow-description", video_webpage) |
cf7e015f | 1838 | if video_description: |
fa4bc6e7 RA |
1839 | |
1840 | def replace_url(m): | |
1841 | redir_url = compat_urlparse.urljoin(url, m.group(1)) | |
1842 | parsed_redir_url = compat_urllib_parse_urlparse(redir_url) | |
1843 | if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect': | |
1844 | qs = compat_parse_qs(parsed_redir_url.query) | |
1845 | q = qs.get('q') | |
1846 | if q and q[0]: | |
1847 | return q[0] | |
1848 | return redir_url | |
1849 | ||
9cafc3fd | 1850 | description_original = video_description = re.sub(r'''(?x) |
cf7e015f | 1851 | <a\s+ |
25cb7a0e | 1852 | (?:[a-zA-Z-]+="[^"]*"\s+)*? |
23f13e97 | 1853 | (?:title|href)="([^"]+)"\s+ |
25cb7a0e | 1854 | (?:[a-zA-Z-]+="[^"]*"\s+)*? |
525cedb9 | 1855 | class="[^"]*"[^>]*> |
23f13e97 | 1856 | [^<]+\.{3}\s* |
cf7e015f | 1857 | </a> |
fa4bc6e7 | 1858 | ''', replace_url, video_description) |
cf7e015f S |
1859 | video_description = clean_html(video_description) |
1860 | else: | |
8dbf751a | 1861 | video_description = self._html_search_meta('description', video_webpage) or video_details.get('shortDescription') |
cf7e015f | 1862 | |
8fe10494 | 1863 | if not smuggled_data.get('force_singlefeed', False): |
5e1eddb9 | 1864 | if not self._downloader.params.get('noplaylist'): |
8fe10494 S |
1865 | multifeed_metadata_list = try_get( |
1866 | player_response, | |
1867 | lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'], | |
1868 | compat_str) or try_get( | |
1869 | video_info, lambda x: x['multifeed_metadata_list'][0], compat_str) | |
1870 | if multifeed_metadata_list: | |
1871 | entries = [] | |
1872 | feed_ids = [] | |
1873 | for feed in multifeed_metadata_list.split(','): | |
1874 | # Unquote should take place before split on comma (,) since textual | |
1875 | # fields may contain comma as well (see | |
067aa17e | 1876 | # https://github.com/ytdl-org/youtube-dl/issues/8536) |
8fe10494 S |
1877 | feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed)) |
1878 | entries.append({ | |
1879 | '_type': 'url_transparent', | |
1880 | 'ie_key': 'Youtube', | |
1881 | 'url': smuggle_url( | |
1882 | '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]), | |
1883 | {'force_singlefeed': True}), | |
1884 | 'title': '%s (%s)' % (video_title, feed_data['title'][0]), | |
1885 | }) | |
1886 | feed_ids.append(feed_data['id'][0]) | |
1887 | self.to_screen( | |
1888 | 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' | |
1889 | % (', '.join(feed_ids), video_id)) | |
1890 | return self.playlist_result(entries, video_id, video_title, video_description) | |
1891 | else: | |
1892 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
cf7e015f | 1893 | |
c7121fa7 | 1894 | if view_count is None: |
1c9c8de2 | 1895 | view_count = extract_view_count(video_info) |
dbdaaa23 S |
1896 | if view_count is None and video_details: |
1897 | view_count = int_or_none(video_details.get('viewCount')) | |
1d699755 | 1898 | |
27019dbb | 1899 | if is_live is None: |
898238e9 | 1900 | is_live = bool_or_none(video_details.get('isLive')) |
27019dbb | 1901 | |
c5e8d7af PH |
1902 | # Check for "rental" videos |
1903 | if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: | |
067aa17e | 1904 | raise ExtractorError('"rental" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True) |
c5e8d7af | 1905 | |
c63ca0ee S |
1906 | def _extract_filesize(media_url): |
1907 | return int_or_none(self._search_regex( | |
1908 | r'\bclen[=/](\d+)', media_url, 'filesize', default=None)) | |
1909 | ||
c5e8d7af PH |
1910 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): |
1911 | self.report_rtmp_download() | |
dd27fd17 PH |
1912 | formats = [{ |
1913 | 'format_id': '_rtmp', | |
1914 | 'protocol': 'rtmp', | |
1915 | 'url': video_info['conn'][0], | |
1916 | 'player_url': player_url, | |
1917 | }] | |
391dd6f0 | 1918 | elif not is_live and (len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1): |
5f6a1245 | 1919 | encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] |
00fe14fc | 1920 | if 'rtmpe%3Dyes' in encoded_url_map: |
067aa17e | 1921 | raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True) |
3318832e | 1922 | formats_spec = {} |
82156fdb | 1923 | fmt_list = video_info.get('fmt_list', [''])[0] |
1924 | if fmt_list: | |
1925 | for fmt in fmt_list.split(','): | |
1926 | spec = fmt.split('/') | |
3318832e | 1927 | if len(spec) > 1: |
1928 | width_height = spec[1].split('x') | |
1929 | if len(width_height) == 2: | |
1930 | formats_spec[spec[0]] = { | |
1931 | 'resolution': spec[1], | |
1932 | 'width': int_or_none(width_height[0]), | |
1933 | 'height': int_or_none(width_height[1]), | |
1934 | } | |
54fc90aa | 1935 | q = qualities(['small', 'medium', 'hd720']) |
140a13f5 RA |
1936 | streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list) |
1937 | if streaming_formats: | |
1938 | for fmt in streaming_formats: | |
1939 | itag = str_or_none(fmt.get('itag')) | |
1940 | if not itag: | |
1941 | continue | |
1942 | quality = fmt.get('quality') | |
1943 | quality_label = fmt.get('qualityLabel') or quality | |
1944 | formats_spec[itag] = { | |
1945 | 'asr': int_or_none(fmt.get('audioSampleRate')), | |
1946 | 'filesize': int_or_none(fmt.get('contentLength')), | |
1947 | 'format_note': quality_label, | |
1948 | 'fps': int_or_none(fmt.get('fps')), | |
1949 | 'height': int_or_none(fmt.get('height')), | |
1950 | 'quality': q(quality), | |
1951 | # bitrate for itag 43 is always 2147483647 | |
1952 | 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None, | |
1953 | 'width': int_or_none(fmt.get('width')), | |
1954 | } | |
c9afb51c | 1955 | formats = [] |
00fe14fc | 1956 | for url_data_str in encoded_url_map.split(','): |
c5e8d7af | 1957 | url_data = compat_parse_qs(url_data_str) |
0d297518 | 1958 | if 'itag' not in url_data or 'url' not in url_data or url_data.get('drm_families'): |
201e9eaa | 1959 | continue |
2f483bc1 S |
1960 | stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0])) |
1961 | # Unsupported FORMAT_STREAM_TYPE_OTF | |
1962 | if stream_type == 3: | |
1963 | continue | |
201e9eaa PH |
1964 | format_id = url_data['itag'][0] |
1965 | url = url_data['url'][0] | |
1966 | ||
a49eccdf | 1967 | if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True): |
6449cd80 | 1968 | ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' |
beb95e77 | 1969 | jsplayer_url_json = self._search_regex( |
6449cd80 PH |
1970 | ASSETS_RE, |
1971 | embed_webpage if age_gate else video_webpage, | |
1972 | 'JS player URL (1)', default=None) | |
1973 | if not jsplayer_url_json and not age_gate: | |
1974 | # We need the embed website after all | |
1975 | if embed_webpage is None: | |
1976 | embed_url = proto + '://www.youtube.com/embed/%s' % video_id | |
1977 | embed_webpage = self._download_webpage( | |
1978 | embed_url, video_id, 'Downloading embed webpage') | |
1979 | jsplayer_url_json = self._search_regex( | |
1980 | ASSETS_RE, embed_webpage, 'JS player URL') | |
1981 | ||
beb95e77 | 1982 | player_url = json.loads(jsplayer_url_json) |
201e9eaa PH |
1983 | if player_url is None: |
1984 | player_url_json = self._search_regex( | |
1985 | r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', | |
78caa52a | 1986 | video_webpage, 'age gate player URL') |
201e9eaa PH |
1987 | player_url = json.loads(player_url_json) |
1988 | ||
a49eccdf YCH |
1989 | if 'sig' in url_data: |
1990 | url += '&signature=' + url_data['sig'][0] | |
1991 | elif 's' in url_data: | |
1992 | encrypted_sig = url_data['s'][0] | |
1993 | ||
201e9eaa | 1994 | if self._downloader.params.get('verbose'): |
cf010131 | 1995 | if player_url is None: |
201e9eaa PH |
1996 | player_version = 'unknown' |
1997 | player_desc = 'unknown' | |
1998 | else: | |
1999 | if player_url.endswith('swf'): | |
2000 | player_version = self._search_regex( | |
2001 | r'-(.+?)(?:/watch_as3)?\.swf$', player_url, | |
78caa52a | 2002 | 'flash player', fatal=False) |
201e9eaa | 2003 | player_desc = 'flash player %s' % player_version |
cf010131 | 2004 | else: |
201e9eaa | 2005 | player_version = self._search_regex( |
b62985a9 | 2006 | [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', |
63529e93 | 2007 | r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'], |
201e9eaa PH |
2008 | player_url, |
2009 | 'html5 player', fatal=False) | |
78caa52a | 2010 | player_desc = 'html5 player %s' % player_version |
201e9eaa | 2011 | |
60064c53 | 2012 | parts_sizes = self._signature_cache_id(encrypted_sig) |
69ea8ca4 | 2013 | self.to_screen('{%s} signature length %s, %s' % |
9e1a5b84 | 2014 | (format_id, parts_sizes, player_desc)) |
201e9eaa PH |
2015 | |
2016 | signature = self._decrypt_signature( | |
2017 | encrypted_sig, video_id, player_url, age_gate) | |
027ffdca S |
2018 | sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature' |
2019 | url += '&%s=%s' % (sp, signature) | |
201e9eaa PH |
2020 | if 'ratebypass' not in url: |
2021 | url += '&ratebypass=yes' | |
c9afb51c | 2022 | |
94278f72 YCH |
2023 | dct = { |
2024 | 'format_id': format_id, | |
2025 | 'url': url, | |
2026 | 'player_url': player_url, | |
2027 | } | |
2028 | if format_id in self._formats: | |
2029 | dct.update(self._formats[format_id]) | |
3318832e | 2030 | if format_id in formats_spec: |
2031 | dct.update(formats_spec[format_id]) | |
94278f72 | 2032 | |
aabc2be6 | 2033 | # Some itags are not included in DASH manifest thus corresponding formats will |
067aa17e | 2034 | # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993). |
aabc2be6 S |
2035 | # Trying to extract metadata from url_encoded_fmt_stream_map entry. |
2036 | mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0]) | |
2037 | width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None) | |
94278f72 | 2038 | |
c63ca0ee S |
2039 | filesize = int_or_none(url_data.get( |
2040 | 'clen', [None])[0]) or _extract_filesize(url) | |
2041 | ||
140a13f5 | 2042 | quality = url_data.get('quality', [None])[0] |
54fc90aa | 2043 | |
94278f72 | 2044 | more_fields = { |
c63ca0ee | 2045 | 'filesize': filesize, |
aabc2be6 | 2046 | 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000), |
c9afb51c AH |
2047 | 'width': width, |
2048 | 'height': height, | |
2049 | 'fps': int_or_none(url_data.get('fps', [None])[0]), | |
140a13f5 | 2050 | 'format_note': url_data.get('quality_label', [None])[0] or quality, |
54fc90aa | 2051 | 'quality': q(quality), |
c9afb51c | 2052 | } |
94278f72 YCH |
2053 | for key, value in more_fields.items(): |
2054 | if value: | |
2055 | dct[key] = value | |
aabc2be6 S |
2056 | type_ = url_data.get('type', [None])[0] |
2057 | if type_: | |
2058 | type_split = type_.split(';') | |
2059 | kind_ext = type_split[0].split('/') | |
2060 | if len(kind_ext) == 2: | |
94278f72 YCH |
2061 | kind, _ = kind_ext |
2062 | dct['ext'] = mimetype2ext(type_split[0]) | |
aabc2be6 S |
2063 | if kind in ('audio', 'video'): |
2064 | codecs = None | |
2065 | for mobj in re.finditer( | |
2066 | r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_): | |
2067 | if mobj.group('key') == 'codecs': | |
2068 | codecs = mobj.group('val') | |
2069 | break | |
2070 | if codecs: | |
6310acf5 | 2071 | dct.update(parse_codecs(codecs)) |
e4a60912 S |
2072 | if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none': |
2073 | dct['downloader_options'] = { | |
2074 | # Youtube throttles chunks >~10M | |
2075 | 'http_chunk_size': 10485760, | |
2076 | } | |
aabc2be6 | 2077 | formats.append(dct) |
c5e8d7af | 2078 | else: |
c3e54389 S |
2079 | manifest_url = ( |
2080 | url_or_none(try_get( | |
2081 | player_response, | |
2082 | lambda x: x['streamingData']['hlsManifestUrl'], | |
3089bc74 S |
2083 | compat_str)) |
2084 | or url_or_none(try_get( | |
c3e54389 S |
2085 | video_info, lambda x: x['hlsvp'][0], compat_str))) |
2086 | if manifest_url: | |
2087 | formats = [] | |
2088 | m3u8_formats = self._extract_m3u8_formats( | |
2089 | manifest_url, video_id, 'mp4', fatal=False) | |
2090 | for a_format in m3u8_formats: | |
2091 | itag = self._search_regex( | |
2092 | r'/itag/(\d+)/', a_format['url'], 'itag', default=None) | |
2093 | if itag: | |
2094 | a_format['format_id'] = itag | |
2095 | if itag in self._formats: | |
2096 | dct = self._formats[itag].copy() | |
2097 | dct.update(a_format) | |
2098 | a_format = dct | |
2099 | a_format['player_url'] = player_url | |
2100 | # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming | |
2101 | a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True' | |
2102 | formats.append(a_format) | |
2103 | else: | |
13577349 | 2104 | error_message = extract_unavailable_message() |
c3e54389 | 2105 | if not error_message: |
13577349 S |
2106 | error_message = clean_html(try_get( |
2107 | player_response, lambda x: x['playabilityStatus']['reason'], | |
2108 | compat_str)) | |
2109 | if not error_message: | |
2110 | error_message = clean_html( | |
2111 | try_get(video_info, lambda x: x['reason'][0], compat_str)) | |
c3e54389 S |
2112 | if error_message: |
2113 | raise ExtractorError(error_message, expected=True) | |
2114 | raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info') | |
c5e8d7af | 2115 | |
7e72694b | 2116 | # uploader |
dbdaaa23 S |
2117 | video_uploader = try_get( |
2118 | video_info, lambda x: x['author'][0], | |
2119 | compat_str) or str_or_none(video_details.get('author')) | |
7e72694b S |
2120 | if video_uploader: |
2121 | video_uploader = compat_urllib_parse_unquote_plus(video_uploader) | |
2122 | else: | |
2123 | self._downloader.report_warning('unable to extract uploader name') | |
2124 | ||
2125 | # uploader_id | |
2126 | video_uploader_id = None | |
2127 | video_uploader_url = None | |
2128 | mobj = re.search( | |
2129 | r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">', | |
2130 | video_webpage) | |
2131 | if mobj is not None: | |
2132 | video_uploader_id = mobj.group('uploader_id') | |
2133 | video_uploader_url = mobj.group('uploader_url') | |
2134 | else: | |
2135 | self._downloader.report_warning('unable to extract uploader nickname') | |
2136 | ||
b45a9e69 | 2137 | channel_id = ( |
3089bc74 S |
2138 | str_or_none(video_details.get('channelId')) |
2139 | or self._html_search_meta( | |
2140 | 'channelId', video_webpage, 'channel id', default=None) | |
2141 | or self._search_regex( | |
b45a9e69 | 2142 | r'data-channel-external-id=(["\'])(?P<id>(?:(?!\1).)+)\1', |
2143 | video_webpage, 'channel id', default=None, group='id')) | |
dd4c4492 S |
2144 | channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None |
2145 | ||
7e72694b S |
2146 | # thumbnail image |
2147 | # We try first to get a high quality image: | |
2148 | m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">', | |
2149 | video_webpage, re.DOTALL) | |
2150 | if m_thumb is not None: | |
2151 | video_thumbnail = m_thumb.group(1) | |
2152 | elif 'thumbnail_url' not in video_info: | |
2153 | self._downloader.report_warning('unable to extract video thumbnail') | |
2154 | video_thumbnail = None | |
2155 | else: # don't panic if we can't find it | |
2156 | video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0]) | |
2157 | ||
2158 | # upload date | |
2159 | upload_date = self._html_search_meta( | |
2160 | 'datePublished', video_webpage, 'upload date', default=None) | |
2161 | if not upload_date: | |
2162 | upload_date = self._search_regex( | |
2163 | [r'(?s)id="eow-date.*?>(.*?)</span>', | |
2164 | r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'], | |
2165 | video_webpage, 'upload date', default=None) | |
2166 | upload_date = unified_strdate(upload_date) | |
2167 | ||
2168 | video_license = self._html_search_regex( | |
2169 | r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li', | |
2170 | video_webpage, 'license', default=None) | |
2171 | ||
2172 | m_music = re.search( | |
2173 | r'''(?x) | |
2174 | <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s* | |
2175 | <ul[^>]*>\s* | |
2176 | <li>(?P<title>.+?) | |
2177 | by (?P<creator>.+?) | |
2178 | (?: | |
2179 | \(.+?\)| | |
2180 | <a[^>]* | |
2181 | (?: | |
2182 | \bhref=["\']/red[^>]*>| # drop possible | |
2183 | >\s*Listen ad-free with YouTube Red # YouTube Red ad | |
2184 | ) | |
2185 | .*? | |
2186 | )?</li | |
2187 | ''', | |
2188 | video_webpage) | |
2189 | if m_music: | |
2190 | video_alt_title = remove_quotes(unescapeHTML(m_music.group('title'))) | |
2191 | video_creator = clean_html(m_music.group('creator')) | |
2192 | else: | |
2193 | video_alt_title = video_creator = None | |
2194 | ||
2195 | def extract_meta(field): | |
2196 | return self._html_search_regex( | |
2197 | r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field, | |
2198 | video_webpage, field, default=None) | |
2199 | ||
2200 | track = extract_meta('Song') | |
2201 | artist = extract_meta('Artist') | |
92bc97d3 | 2202 | album = extract_meta('Album') |
822b9d9c RA |
2203 | |
2204 | # Youtube Music Auto-generated description | |
92bc97d3 | 2205 | release_date = release_year = None |
822b9d9c RA |
2206 | if video_description: |
2207 | mobj = re.search(r'(?s)Provided to YouTube by [^\n]+\n+(?P<track>[^·]+)·(?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]+))?', video_description) | |
2208 | if mobj: | |
2209 | if not track: | |
2210 | track = mobj.group('track').strip() | |
2211 | if not artist: | |
2212 | artist = mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')) | |
92bc97d3 RA |
2213 | if not album: |
2214 | album = mobj.group('album'.strip()) | |
822b9d9c RA |
2215 | release_year = mobj.group('release_year') |
2216 | release_date = mobj.group('release_date') | |
2217 | if release_date: | |
2218 | release_date = release_date.replace('-', '') | |
2219 | if not release_year: | |
2220 | release_year = int(release_date[:4]) | |
2221 | if release_year: | |
2222 | release_year = int(release_year) | |
7e72694b S |
2223 | |
2224 | m_episode = re.search( | |
2225 | r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>', | |
2226 | video_webpage) | |
2227 | if m_episode: | |
c2dd2dc0 | 2228 | series = unescapeHTML(m_episode.group('series')) |
7e72694b S |
2229 | season_number = int(m_episode.group('season')) |
2230 | episode_number = int(m_episode.group('episode')) | |
2231 | else: | |
2232 | series = season_number = episode_number = None | |
2233 | ||
2234 | m_cat_container = self._search_regex( | |
2235 | r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', | |
2236 | video_webpage, 'categories', default=None) | |
2237 | if m_cat_container: | |
2238 | category = self._html_search_regex( | |
2239 | r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', | |
2240 | default=None) | |
2241 | video_categories = None if category is None else [category] | |
2242 | else: | |
2243 | video_categories = None | |
2244 | ||
2245 | video_tags = [ | |
2246 | unescapeHTML(m.group('content')) | |
2247 | for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)] | |
2248 | ||
2249 | def _extract_count(count_name): | |
2250 | return str_to_int(self._search_regex( | |
2251 | r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>' | |
2252 | % re.escape(count_name), | |
2253 | video_webpage, count_name, default=None)) | |
2254 | ||
2255 | like_count = _extract_count('like') | |
2256 | dislike_count = _extract_count('dislike') | |
2257 | ||
dbdaaa23 S |
2258 | if view_count is None: |
2259 | view_count = str_to_int(self._search_regex( | |
2260 | r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage, | |
2261 | 'view count', default=None)) | |
2262 | ||
bf3c9326 S |
2263 | average_rating = ( |
2264 | float_or_none(video_details.get('averageRating')) | |
2265 | or try_get(video_info, lambda x: float_or_none(x['avg_rating'][0]))) | |
2266 | ||
7e72694b S |
2267 | # subtitles |
2268 | video_subtitles = self.extract_subtitles(video_id, video_webpage) | |
2269 | automatic_captions = self.extract_automatic_captions(video_id, video_webpage) | |
2270 | ||
2271 | video_duration = try_get( | |
2272 | video_info, lambda x: int_or_none(x['length_seconds'][0])) | |
dbdaaa23 S |
2273 | if not video_duration: |
2274 | video_duration = int_or_none(video_details.get('lengthSeconds')) | |
7e72694b S |
2275 | if not video_duration: |
2276 | video_duration = parse_duration(self._html_search_meta( | |
2277 | 'duration', video_webpage, 'video duration')) | |
2278 | ||
2279 | # annotations | |
2280 | video_annotations = None | |
2281 | if self._downloader.params.get('writeannotations', False): | |
64b6a4e9 RA |
2282 | xsrf_token = self._search_regex( |
2283 | r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>[A-Za-z0-9+/=]+)\2', | |
2284 | video_webpage, 'xsrf token', group='xsrf_token', fatal=False) | |
2285 | invideo_url = try_get( | |
2286 | player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str) | |
2287 | if xsrf_token and invideo_url: | |
2288 | xsrf_field_name = self._search_regex( | |
2289 | r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2', | |
2290 | video_webpage, 'xsrf field name', | |
2291 | group='xsrf_field_name', default='session_token') | |
2292 | video_annotations = self._download_webpage( | |
2293 | self._proto_relative_url(invideo_url), | |
2294 | video_id, note='Downloading annotations', | |
2295 | errnote='Unable to download video annotations', fatal=False, | |
2296 | data=urlencode_postdata({xsrf_field_name: xsrf_token})) | |
7e72694b S |
2297 | |
2298 | chapters = self._extract_chapters(description_original, video_duration) | |
2299 | ||
dd27fd17 | 2300 | # Look for the DASH manifest |
203fb43f | 2301 | if self._downloader.params.get('youtube_include_dash_manifest', True): |
77c6fb5b | 2302 | dash_mpd_fatal = True |
8ff648e4 | 2303 | for mpd_url in dash_mpds: |
d8d24a92 | 2304 | dash_formats = {} |
774e208f | 2305 | try: |
05d0d131 YCH |
2306 | def decrypt_sig(mobj): |
2307 | s = mobj.group(1) | |
2308 | dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) | |
2309 | return '/signature/%s' % dec_s | |
2310 | ||
8ff648e4 | 2311 | mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url) |
2d2fa82d | 2312 | |
8ff648e4 | 2313 | for df in self._extract_mpd_formats( |
2314 | mpd_url, video_id, fatal=dash_mpd_fatal, | |
2315 | formats_dict=self._formats): | |
c63ca0ee S |
2316 | if not df.get('filesize'): |
2317 | df['filesize'] = _extract_filesize(df['url']) | |
d8d24a92 S |
2318 | # Do not overwrite DASH format found in some previous DASH manifest |
2319 | if df['format_id'] not in dash_formats: | |
2320 | dash_formats[df['format_id']] = df | |
77c6fb5b S |
2321 | # Additional DASH manifests may end up in HTTP Error 403 therefore |
2322 | # allow them to fail without bug report message if we already have | |
2323 | # some DASH manifest succeeded. This is temporary workaround to reduce | |
2324 | # burst of bug reports until we figure out the reason and whether it | |
2325 | # can be fixed at all. | |
2326 | dash_mpd_fatal = False | |
774e208f PH |
2327 | except (ExtractorError, KeyError) as e: |
2328 | self.report_warning( | |
2329 | 'Skipping DASH manifest: %r' % e, video_id) | |
d8d24a92 | 2330 | if dash_formats: |
04b3b3df JMF |
2331 | # Remove the formats we found through non-DASH, they |
2332 | # contain less info and it can be wrong, because we use | |
2333 | # fixed values (for example the resolution). See | |
067aa17e | 2334 | # https://github.com/ytdl-org/youtube-dl/issues/5774 for an |
04b3b3df | 2335 | # example. |
d80265cc | 2336 | formats = [f for f in formats if f['format_id'] not in dash_formats.keys()] |
d8d24a92 | 2337 | formats.extend(dash_formats.values()) |
d80044c2 | 2338 | |
6271f1ca PH |
2339 | # Check for malformed aspect ratio |
2340 | stretched_m = re.search( | |
2341 | r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">', | |
2342 | video_webpage) | |
2343 | if stretched_m: | |
313dfc45 LL |
2344 | w = float(stretched_m.group('w')) |
2345 | h = float(stretched_m.group('h')) | |
5faf9fed S |
2346 | # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0). |
2347 | # We will only process correct ratios. | |
313dfc45 | 2348 | if w > 0 and h > 0: |
41f24c32 | 2349 | ratio = w / h |
313dfc45 LL |
2350 | for f in formats: |
2351 | if f.get('vcodec') != 'none': | |
2352 | f['stretched_ratio'] = ratio | |
6271f1ca | 2353 | |
026fbedc S |
2354 | if not formats: |
2355 | token = extract_token(video_info) | |
2356 | if not token: | |
2357 | if 'reason' in video_info: | |
2358 | if 'The uploader has not made this video available in your country.' in video_info['reason']: | |
2359 | regions_allowed = self._html_search_meta( | |
2360 | 'regionsAllowed', video_webpage, default=None) | |
2361 | countries = regions_allowed.split(',') if regions_allowed else None | |
2362 | self.raise_geo_restricted( | |
2363 | msg=video_info['reason'][0], countries=countries) | |
2364 | reason = video_info['reason'][0] | |
2365 | if 'Invalid parameters' in reason: | |
2366 | unavailable_message = extract_unavailable_message() | |
2367 | if unavailable_message: | |
2368 | reason = unavailable_message | |
2369 | raise ExtractorError( | |
2370 | 'YouTube said: %s' % reason, | |
2371 | expected=True, video_id=video_id) | |
2372 | else: | |
2373 | raise ExtractorError( | |
2374 | '"token" parameter not in video info for unknown reason', | |
2375 | video_id=video_id) | |
2376 | ||
0d297518 RA |
2377 | if not formats and (video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos'])): |
2378 | raise ExtractorError('This video is DRM protected.', expected=True) | |
2379 | ||
4bcc7bd1 | 2380 | self._sort_formats(formats) |
4ea3be0a | 2381 | |
21c340b8 | 2382 | self.mark_watched(video_id, video_info, player_response) |
d77ab8e2 | 2383 | |
4ea3be0a | 2384 | return { |
8bcc8756 JW |
2385 | 'id': video_id, |
2386 | 'uploader': video_uploader, | |
2387 | 'uploader_id': video_uploader_id, | |
fd050249 | 2388 | 'uploader_url': video_uploader_url, |
dd4c4492 S |
2389 | 'channel_id': channel_id, |
2390 | 'channel_url': channel_url, | |
8bcc8756 | 2391 | 'upload_date': upload_date, |
7caf9830 | 2392 | 'license': video_license, |
936784b2 | 2393 | 'creator': video_creator or artist, |
8bcc8756 | 2394 | 'title': video_title, |
936784b2 | 2395 | 'alt_title': video_alt_title or track, |
8bcc8756 JW |
2396 | 'thumbnail': video_thumbnail, |
2397 | 'description': video_description, | |
2398 | 'categories': video_categories, | |
000b6b5a | 2399 | 'tags': video_tags, |
8bcc8756 | 2400 | 'subtitles': video_subtitles, |
360e1ca5 | 2401 | 'automatic_captions': automatic_captions, |
8bcc8756 JW |
2402 | 'duration': video_duration, |
2403 | 'age_limit': 18 if age_gate else 0, | |
2404 | 'annotations': video_annotations, | |
9cafc3fd | 2405 | 'chapters': chapters, |
7e8c0af0 | 2406 | 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id, |
8bcc8756 | 2407 | 'view_count': view_count, |
4ea3be0a | 2408 | 'like_count': like_count, |
2409 | 'dislike_count': dislike_count, | |
bf3c9326 | 2410 | 'average_rating': average_rating, |
8bcc8756 | 2411 | 'formats': formats, |
2fe1ff85 | 2412 | 'is_live': is_live, |
7c80519c | 2413 | 'start_time': start_time, |
297a564b | 2414 | 'end_time': end_time, |
12afdc2a S |
2415 | 'series': series, |
2416 | 'season_number': season_number, | |
2417 | 'episode_number': episode_number, | |
936784b2 S |
2418 | 'track': track, |
2419 | 'artist': artist, | |
5caabd3c | 2420 | 'album': album, |
2421 | 'release_date': release_date, | |
2422 | 'release_year': release_year, | |
4ea3be0a | 2423 | } |
c5e8d7af | 2424 | |
5f6a1245 | 2425 | |
8e7aad20 | 2426 | class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): |
78caa52a | 2427 | IE_DESC = 'YouTube.com playlists' |
d67cc9fa | 2428 | _VALID_URL = r"""(?x)(?: |
c5e8d7af PH |
2429 | (?:https?://)? |
2430 | (?:\w+\.)? | |
c5e8d7af | 2431 | (?: |
c0345b82 S |
2432 | (?: |
2433 | youtube\.com| | |
2434 | invidio\.us | |
2435 | ) | |
2436 | / | |
feaa5ad7 | 2437 | (?: |
87dadd45 | 2438 | (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11})) |
feaa5ad7 S |
2439 | \? (?:.*?[&;])*? (?:p|a|list)= |
2440 | | p/ | |
2441 | )| | |
2442 | youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist= | |
c5e8d7af | 2443 | ) |
d67cc9fa | 2444 | ( |
409b9324 | 2445 | (?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)?[0-9A-Za-z-_]{10,} |
5f6a1245 | 2446 | # Top tracks, they can also include dots |
d67cc9fa JMF |
2447 | |(?:MC)[\w\.]* |
2448 | ) | |
c5e8d7af PH |
2449 | .* |
2450 | | | |
d0ba5587 S |
2451 | (%(playlist_id)s) |
2452 | )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} | |
8d81f3e3 | 2453 | _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' |
351f37c0 S |
2454 | _VIDEO_RE_TPL = r'href="\s*/watch\?v=%s(?:&(?:[^"]*?index=(?P<index>\d+))?(?:[^>]+>(?P<title>[^<]+))?)?' |
2455 | _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})' | |
78caa52a | 2456 | IE_NAME = 'youtube:playlist' |
81127aa5 PH |
2457 | _TESTS = [{ |
2458 | 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', | |
2459 | 'info_dict': { | |
2460 | 'title': 'ytdl test PL', | |
a1cf99d0 | 2461 | 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', |
81127aa5 PH |
2462 | }, |
2463 | 'playlist_count': 3, | |
9291475f PH |
2464 | }, { |
2465 | 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', | |
2466 | 'info_dict': { | |
acf757f4 | 2467 | 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', |
9291475f PH |
2468 | 'title': 'YDL_Empty_List', |
2469 | }, | |
2470 | 'playlist_count': 0, | |
4201ba13 | 2471 | 'skip': 'This playlist is private', |
9291475f PH |
2472 | }, { |
2473 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
2474 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
2475 | 'info_dict': { | |
2476 | 'title': '29C3: Not my department', | |
acf757f4 | 2477 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', |
13a75688 S |
2478 | 'uploader': 'Christiaan008', |
2479 | 'uploader_id': 'ChRiStIaAn008', | |
9291475f PH |
2480 | }, |
2481 | 'playlist_count': 95, | |
2482 | }, { | |
2483 | 'note': 'issue #673', | |
2484 | 'url': 'PLBB231211A4F62143', | |
2485 | 'info_dict': { | |
f46a8702 | 2486 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', |
acf757f4 | 2487 | 'id': 'PLBB231211A4F62143', |
13a75688 S |
2488 | 'uploader': 'Wickydoo', |
2489 | 'uploader_id': 'Wickydoo', | |
9291475f PH |
2490 | }, |
2491 | 'playlist_mincount': 26, | |
2492 | }, { | |
2493 | 'note': 'Large playlist', | |
2494 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
2495 | 'info_dict': { | |
2496 | 'title': 'Uploads from Cauchemar', | |
acf757f4 | 2497 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', |
13a75688 S |
2498 | 'uploader': 'Cauchemar', |
2499 | 'uploader_id': 'Cauchemar89', | |
9291475f PH |
2500 | }, |
2501 | 'playlist_mincount': 799, | |
2502 | }, { | |
2503 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
2504 | 'info_dict': { | |
2505 | 'title': 'YDL_safe_search', | |
acf757f4 | 2506 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', |
9291475f PH |
2507 | }, |
2508 | 'playlist_count': 2, | |
4201ba13 | 2509 | 'skip': 'This playlist is private', |
ac7553d0 PH |
2510 | }, { |
2511 | 'note': 'embedded', | |
2d3d2997 | 2512 | 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', |
ac7553d0 PH |
2513 | 'playlist_count': 4, |
2514 | 'info_dict': { | |
2515 | 'title': 'JODA15', | |
acf757f4 | 2516 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', |
13a75688 S |
2517 | 'uploader': 'milan', |
2518 | 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw', | |
ac7553d0 | 2519 | } |
87dadd45 S |
2520 | }, { |
2521 | 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
2522 | 'playlist_mincount': 485, | |
2523 | 'info_dict': { | |
13a75688 | 2524 | 'title': '2018 Chinese New Singles (11/6 updated)', |
87dadd45 | 2525 | 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', |
13a75688 S |
2526 | 'uploader': 'LBK', |
2527 | 'uploader_id': 'sdragonfang', | |
87dadd45 | 2528 | } |
6b08cdf6 PH |
2529 | }, { |
2530 | 'note': 'Embedded SWF player', | |
2d3d2997 | 2531 | 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0', |
6b08cdf6 PH |
2532 | 'playlist_count': 4, |
2533 | 'info_dict': { | |
2534 | 'title': 'JODA7', | |
acf757f4 | 2535 | 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ', |
13a75688 S |
2536 | }, |
2537 | 'skip': 'This playlist does not exist', | |
4b7df0d3 JMF |
2538 | }, { |
2539 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
2540 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
2541 | 'info_dict': { | |
acf757f4 PH |
2542 | 'title': 'Uploads from Interstellar Movie', |
2543 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
13a75688 S |
2544 | 'uploader': 'Interstellar Movie', |
2545 | 'uploader_id': 'InterstellarMovie1', | |
4b7df0d3 | 2546 | }, |
481cc733 | 2547 | 'playlist_mincount': 21, |
dacb3a86 S |
2548 | }, { |
2549 | # Playlist URL that does not actually serve a playlist | |
2550 | 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', | |
2551 | 'info_dict': { | |
2552 | 'id': 'FqZTN594JQw', | |
2553 | 'ext': 'webm', | |
2554 | 'title': "Smiley's People 01 detective, Adventure Series, Action", | |
2555 | 'uploader': 'STREEM', | |
2556 | 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng', | |
ec85ded8 | 2557 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng', |
dacb3a86 S |
2558 | 'upload_date': '20150526', |
2559 | 'license': 'Standard YouTube License', | |
2560 | 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', | |
2561 | 'categories': ['People & Blogs'], | |
2562 | 'tags': list, | |
dbdaaa23 | 2563 | 'view_count': int, |
dacb3a86 S |
2564 | 'like_count': int, |
2565 | 'dislike_count': int, | |
2566 | }, | |
2567 | 'params': { | |
2568 | 'skip_download': True, | |
2569 | }, | |
13a75688 | 2570 | 'skip': 'This video is not available.', |
dacb3a86 | 2571 | 'add_ie': [YoutubeIE.ie_key()], |
481cc733 S |
2572 | }, { |
2573 | 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', | |
2574 | 'info_dict': { | |
2575 | 'id': 'yeWKywCrFtk', | |
2576 | 'ext': 'mp4', | |
2577 | 'title': 'Small Scale Baler and Braiding Rugs', | |
2578 | 'uploader': 'Backus-Page House Museum', | |
2579 | 'uploader_id': 'backuspagemuseum', | |
ec85ded8 | 2580 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum', |
481cc733 | 2581 | 'upload_date': '20161008', |
481cc733 S |
2582 | 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', |
2583 | 'categories': ['Nonprofits & Activism'], | |
2584 | 'tags': list, | |
2585 | 'like_count': int, | |
2586 | 'dislike_count': int, | |
2587 | }, | |
2588 | 'params': { | |
2589 | 'noplaylist': True, | |
2590 | 'skip_download': True, | |
2591 | }, | |
2e18adec S |
2592 | }, { |
2593 | # https://github.com/ytdl-org/youtube-dl/issues/21844 | |
2594 | 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
2595 | 'info_dict': { | |
2596 | 'title': 'Data Analysis with Dr Mike Pound', | |
2597 | 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba', | |
2598 | 'uploader_id': 'Computerphile', | |
2599 | 'uploader': 'Computerphile', | |
2600 | }, | |
2601 | 'playlist_mincount': 11, | |
feaa5ad7 S |
2602 | }, { |
2603 | 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', | |
2604 | 'only_matching': True, | |
a6857510 S |
2605 | }, { |
2606 | 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', | |
2607 | 'only_matching': True, | |
409b9324 S |
2608 | }, { |
2609 | # music album playlist | |
2610 | 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', | |
2611 | 'only_matching': True, | |
c0345b82 S |
2612 | }, { |
2613 | 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU', | |
2614 | 'only_matching': True, | |
81127aa5 | 2615 | }] |
c5e8d7af | 2616 | |
880e1c52 JMF |
2617 | def _real_initialize(self): |
2618 | self._login() | |
2619 | ||
351f37c0 S |
2620 | def extract_videos_from_page(self, page): |
2621 | ids_in_page = [] | |
2622 | titles_in_page = [] | |
2623 | ||
2624 | for item in re.findall( | |
2625 | r'(<[^>]*\bdata-video-id\s*=\s*["\'][0-9A-Za-z_-]{11}[^>]+>)', page): | |
2626 | attrs = extract_attributes(item) | |
2627 | video_id = attrs['data-video-id'] | |
2628 | video_title = unescapeHTML(attrs.get('data-title')) | |
2629 | if video_title: | |
2630 | video_title = video_title.strip() | |
2631 | ids_in_page.append(video_id) | |
2632 | titles_in_page.append(video_title) | |
2633 | ||
2634 | # Fallback with old _VIDEO_RE | |
2635 | self.extract_videos_from_page_impl( | |
2636 | self._VIDEO_RE, page, ids_in_page, titles_in_page) | |
2637 | ||
2638 | # Relaxed fallbacks | |
2639 | self.extract_videos_from_page_impl( | |
2640 | r'href="\s*/watch\?v\s*=\s*(?P<id>[0-9A-Za-z_-]{11})', page, | |
2641 | ids_in_page, titles_in_page) | |
2642 | self.extract_videos_from_page_impl( | |
2643 | r'data-video-ids\s*=\s*["\'](?P<id>[0-9A-Za-z_-]{11})', page, | |
2644 | ids_in_page, titles_in_page) | |
2645 | ||
2646 | return zip(ids_in_page, titles_in_page) | |
2647 | ||
652cdaa2 | 2648 | def _extract_mix(self, playlist_id): |
99209c29 | 2649 | # The mixes are generated from a single video |
652cdaa2 | 2650 | # the id of the playlist is just 'RD' + video_id |
1b6182d8 JMF |
2651 | ids = [] |
2652 | last_id = playlist_id[-11:] | |
2653 | for n in itertools.count(1): | |
2654 | url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id) | |
2655 | webpage = self._download_webpage( | |
2656 | url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n)) | |
2657 | new_ids = orderedSet(re.findall( | |
2658 | r'''(?xs)data-video-username=".*?".*? | |
2659 | href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id), | |
2660 | webpage)) | |
2661 | # Fetch new pages until all the videos are repeated, it seems that | |
2662 | # there are always 51 unique videos. | |
2663 | new_ids = [_id for _id in new_ids if _id not in ids] | |
2664 | if not new_ids: | |
2665 | break | |
2666 | ids.extend(new_ids) | |
2667 | last_id = ids[-1] | |
2668 | ||
2669 | url_results = self._ids_to_results(ids) | |
2670 | ||
bc2f773b | 2671 | search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage) |
c9cc0bf5 | 2672 | title_span = ( |
3089bc74 S |
2673 | search_title('playlist-title') |
2674 | or search_title('title long-title') | |
2675 | or search_title('title')) | |
76d1700b | 2676 | title = clean_html(title_span) |
652cdaa2 JMF |
2677 | |
2678 | return self.playlist_result(url_results, playlist_id, title) | |
2679 | ||
448830ce | 2680 | def _extract_playlist(self, playlist_id): |
dbb94fb0 S |
2681 | url = self._TEMPLATE_URL % playlist_id |
2682 | page = self._download_webpage(url, playlist_id) | |
dbb94fb0 | 2683 | |
067aa17e | 2684 | # the yt-alert-message now has tabindex attribute (see https://github.com/ytdl-org/youtube-dl/issues/11604) |
8bc0800d | 2685 | for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page): |
39b62db1 YCH |
2686 | match = match.strip() |
2687 | # Check if the playlist exists or is private | |
4201ba13 S |
2688 | mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match) |
2689 | if mobj: | |
2690 | reason = mobj.group('reason') | |
2691 | message = 'This playlist %s' % reason | |
2692 | if 'private' in reason: | |
2693 | message += ', use --username or --netrc to access it' | |
2694 | message += '.' | |
2695 | raise ExtractorError(message, expected=True) | |
39b62db1 YCH |
2696 | elif re.match(r'[^<]*Invalid parameters[^<]*', match): |
2697 | raise ExtractorError( | |
2698 | 'Invalid parameters. Maybe URL is incorrect.', | |
2699 | expected=True) | |
2700 | elif re.match(r'[^<]*Choose your language[^<]*', match): | |
2701 | continue | |
2702 | else: | |
2703 | self.report_warning('Youtube gives an alert message: ' + match) | |
10c0e2d8 | 2704 | |
dbb94fb0 | 2705 | playlist_title = self._html_search_regex( |
63b4295d | 2706 | r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>', |
dacb3a86 | 2707 | page, 'title', default=None) |
c5e8d7af | 2708 | |
07aeced6 S |
2709 | _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref=' |
2710 | uploader = self._search_regex( | |
2711 | r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE, | |
2712 | page, 'uploader', default=None) | |
2713 | mobj = re.search( | |
2714 | r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE, | |
2715 | page) | |
2716 | if mobj: | |
2717 | uploader_id = mobj.group('uploader_id') | |
2718 | uploader_url = compat_urlparse.urljoin(url, mobj.group('path')) | |
2719 | else: | |
2720 | uploader_id = uploader_url = None | |
2721 | ||
dacb3a86 S |
2722 | has_videos = True |
2723 | ||
2724 | if not playlist_title: | |
2725 | try: | |
2726 | # Some playlist URLs don't actually serve a playlist (e.g. | |
2727 | # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4) | |
2728 | next(self._entries(page, playlist_id)) | |
2729 | except StopIteration: | |
2730 | has_videos = False | |
2731 | ||
07aeced6 | 2732 | playlist = self.playlist_result( |
dacb3a86 | 2733 | self._entries(page, playlist_id), playlist_id, playlist_title) |
07aeced6 S |
2734 | playlist.update({ |
2735 | 'uploader': uploader, | |
2736 | 'uploader_id': uploader_id, | |
2737 | 'uploader_url': uploader_url, | |
2738 | }) | |
2739 | ||
2740 | return has_videos, playlist | |
c5e8d7af | 2741 | |
ebf1b291 | 2742 | def _check_download_just_video(self, url, playlist_id): |
448830ce S |
2743 | # Check if it's a video-specific URL |
2744 | query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) | |
481cc733 | 2745 | video_id = query_dict.get('v', [None])[0] or self._search_regex( |
87dadd45 | 2746 | r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url, |
481cc733 S |
2747 | 'video id', default=None) |
2748 | if video_id: | |
448830ce S |
2749 | if self._downloader.params.get('noplaylist'): |
2750 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
dacb3a86 | 2751 | return video_id, self.url_result(video_id, 'Youtube', video_id=video_id) |
448830ce S |
2752 | else: |
2753 | self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) | |
dacb3a86 S |
2754 | return video_id, None |
2755 | return None, None | |
448830ce | 2756 | |
ebf1b291 S |
2757 | def _real_extract(self, url): |
2758 | # Extract playlist id | |
2759 | mobj = re.match(self._VALID_URL, url) | |
2760 | if mobj is None: | |
2761 | raise ExtractorError('Invalid URL: %s' % url) | |
2762 | playlist_id = mobj.group(1) or mobj.group(2) | |
2763 | ||
dacb3a86 | 2764 | video_id, video = self._check_download_just_video(url, playlist_id) |
ebf1b291 S |
2765 | if video: |
2766 | return video | |
2767 | ||
466a6145 | 2768 | if playlist_id.startswith(('RD', 'UL', 'PU')): |
448830ce S |
2769 | # Mixes require a custom extraction process |
2770 | return self._extract_mix(playlist_id) | |
2771 | ||
dacb3a86 S |
2772 | has_videos, playlist = self._extract_playlist(playlist_id) |
2773 | if has_videos or not video_id: | |
2774 | return playlist | |
2775 | ||
2776 | # Some playlist URLs don't actually serve a playlist (see | |
067aa17e | 2777 | # https://github.com/ytdl-org/youtube-dl/issues/10537). |
dacb3a86 S |
2778 | # Fallback to plain video extraction if there is a video id |
2779 | # along with playlist id. | |
2780 | return self.url_result(video_id, 'Youtube', video_id=video_id) | |
448830ce | 2781 | |
c5e8d7af | 2782 | |
648e6a1f | 2783 | class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): |
78caa52a | 2784 | IE_DESC = 'YouTube.com channels' |
cd5a74a2 | 2785 | _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)' |
eb0f3e7e | 2786 | _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos' |
648e6a1f | 2787 | _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?' |
78caa52a | 2788 | IE_NAME = 'youtube:channel' |
cdc628a4 PH |
2789 | _TESTS = [{ |
2790 | 'note': 'paginated channel', | |
2791 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
2792 | 'playlist_mincount': 91, | |
acf757f4 | 2793 | 'info_dict': { |
9170ca5b JMF |
2794 | 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w', |
2795 | 'title': 'Uploads from lex will', | |
13a75688 S |
2796 | 'uploader': 'lex will', |
2797 | 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
acf757f4 | 2798 | } |
5c43afd4 JMF |
2799 | }, { |
2800 | 'note': 'Age restricted channel', | |
2801 | # from https://www.youtube.com/user/DeusExOfficial | |
2802 | 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w', | |
2803 | 'playlist_mincount': 64, | |
2804 | 'info_dict': { | |
2805 | 'id': 'UUs0ifCMCm1icqRbqhUINa0w', | |
2806 | 'title': 'Uploads from Deus Ex', | |
13a75688 S |
2807 | 'uploader': 'Deus Ex', |
2808 | 'uploader_id': 'DeusExOfficial', | |
5c43afd4 | 2809 | }, |
cd5a74a2 S |
2810 | }, { |
2811 | 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA', | |
2812 | 'only_matching': True, | |
cdc628a4 | 2813 | }] |
c5e8d7af | 2814 | |
e462474e S |
2815 | @classmethod |
2816 | def suitable(cls, url): | |
f07e276a S |
2817 | return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url) |
2818 | else super(YoutubeChannelIE, cls).suitable(url)) | |
e462474e | 2819 | |
9558dcec S |
2820 | def _build_template_url(self, url, channel_id): |
2821 | return self._TEMPLATE_URL % channel_id | |
2822 | ||
c5e8d7af | 2823 | def _real_extract(self, url): |
9ff67727 | 2824 | channel_id = self._match_id(url) |
c5e8d7af | 2825 | |
9558dcec | 2826 | url = self._build_template_url(url, channel_id) |
386bdfa6 S |
2827 | |
2828 | # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778) | |
2829 | # Workaround by extracting as a playlist if managed to obtain channel playlist URL | |
2830 | # otherwise fallback on channel by page extraction | |
2831 | channel_page = self._download_webpage( | |
2832 | url + '?view=57', channel_id, | |
2833 | 'Downloading channel page', fatal=False) | |
2b3c2546 PH |
2834 | if channel_page is False: |
2835 | channel_playlist_id = False | |
2836 | else: | |
2837 | channel_playlist_id = self._html_search_meta( | |
2838 | 'channelId', channel_page, 'channel id', default=None) | |
2839 | if not channel_playlist_id: | |
73c4ac2c S |
2840 | channel_url = self._html_search_meta( |
2841 | ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'), | |
2842 | channel_page, 'channel url', default=None) | |
2843 | if channel_url: | |
2844 | channel_playlist_id = self._search_regex( | |
2845 | r'vnd\.youtube://user/([0-9A-Za-z_-]+)', | |
2846 | channel_url, 'channel id', default=None) | |
386bdfa6 S |
2847 | if channel_playlist_id and channel_playlist_id.startswith('UC'): |
2848 | playlist_id = 'UU' + channel_playlist_id[2:] | |
d2a9de78 IK |
2849 | return self.url_result( |
2850 | compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist') | |
386bdfa6 | 2851 | |
60bf45c8 | 2852 | channel_page = self._download_webpage(url, channel_id, 'Downloading page #1') |
31812a9e PH |
2853 | autogenerated = re.search(r'''(?x) |
2854 | class="[^"]*?(?: | |
2855 | channel-header-autogenerated-label| | |
2856 | yt-channel-title-autogenerated | |
2857 | )[^"]*"''', channel_page) is not None | |
c5e8d7af | 2858 | |
b9643eed JMF |
2859 | if autogenerated: |
2860 | # The videos are contained in a single page | |
2861 | # the ajax pages can't be used, they are empty | |
b82f815f | 2862 | entries = [ |
fb69240c S |
2863 | self.url_result( |
2864 | video_id, 'Youtube', video_id=video_id, | |
2865 | video_title=video_title) | |
8f02ad4f | 2866 | for video_id, video_title in self.extract_videos_from_page(channel_page)] |
b82f815f PH |
2867 | return self.playlist_result(entries, channel_id) |
2868 | ||
73c4ac2c S |
2869 | try: |
2870 | next(self._entries(channel_page, channel_id)) | |
2871 | except StopIteration: | |
2872 | alert_message = self._html_search_regex( | |
2873 | r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>', | |
2874 | channel_page, 'alert', default=None, group='alert') | |
2875 | if alert_message: | |
2876 | raise ExtractorError('Youtube said: %s' % alert_message, expected=True) | |
2877 | ||
648e6a1f | 2878 | return self.playlist_result(self._entries(channel_page, channel_id), channel_id) |
c5e8d7af PH |
2879 | |
2880 | ||
eb0f3e7e | 2881 | class YoutubeUserIE(YoutubeChannelIE): |
78caa52a | 2882 | IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)' |
ea696249 | 2883 | _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results|shared)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)' |
9558dcec | 2884 | _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos' |
78caa52a | 2885 | IE_NAME = 'youtube:user' |
c5e8d7af | 2886 | |
cdc628a4 PH |
2887 | _TESTS = [{ |
2888 | 'url': 'https://www.youtube.com/user/TheLinuxFoundation', | |
2889 | 'playlist_mincount': 320, | |
2890 | 'info_dict': { | |
73c4ac2c S |
2891 | 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ', |
2892 | 'title': 'Uploads from The Linux Foundation', | |
13a75688 S |
2893 | 'uploader': 'The Linux Foundation', |
2894 | 'uploader_id': 'TheLinuxFoundation', | |
cdc628a4 | 2895 | } |
9558dcec S |
2896 | }, { |
2897 | # Only available via https://www.youtube.com/c/12minuteathlete/videos | |
2898 | # but not https://www.youtube.com/user/12minuteathlete/videos | |
2899 | 'url': 'https://www.youtube.com/c/12minuteathlete/videos', | |
2900 | 'playlist_mincount': 249, | |
2901 | 'info_dict': { | |
2902 | 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ', | |
2903 | 'title': 'Uploads from 12 Minute Athlete', | |
13a75688 S |
2904 | 'uploader': '12 Minute Athlete', |
2905 | 'uploader_id': 'the12minuteathlete', | |
9558dcec | 2906 | } |
cdc628a4 PH |
2907 | }, { |
2908 | 'url': 'ytuser:phihag', | |
2909 | 'only_matching': True, | |
daa0df9e YCH |
2910 | }, { |
2911 | 'url': 'https://www.youtube.com/c/gametrailers', | |
2912 | 'only_matching': True, | |
9558dcec S |
2913 | }, { |
2914 | 'url': 'https://www.youtube.com/gametrailers', | |
2915 | 'only_matching': True, | |
73c4ac2c | 2916 | }, { |
0e879f43 | 2917 | # This channel is not available, geo restricted to JP |
73c4ac2c S |
2918 | 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos', |
2919 | 'only_matching': True, | |
cdc628a4 PH |
2920 | }] |
2921 | ||
e3ea4790 | 2922 | @classmethod |
f4b05232 | 2923 | def suitable(cls, url): |
e3ea4790 JMF |
2924 | # Don't return True if the url can be extracted with other youtube |
2925 | # extractor, the regex would is too permissive and it would match. | |
f3a58d46 | 2926 | other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls) |
2927 | if any(ie.suitable(url) for ie in other_yt_ies): | |
5f6a1245 JW |
2928 | return False |
2929 | else: | |
2930 | return super(YoutubeUserIE, cls).suitable(url) | |
f4b05232 | 2931 | |
9558dcec S |
2932 | def _build_template_url(self, url, channel_id): |
2933 | mobj = re.match(self._VALID_URL, url) | |
2934 | return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id')) | |
2935 | ||
b05654f0 | 2936 | |
f07e276a S |
2937 | class YoutubeLiveIE(YoutubeBaseInfoExtractor): |
2938 | IE_DESC = 'YouTube.com live streams' | |
073d5bf5 | 2939 | _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live' |
f07e276a S |
2940 | IE_NAME = 'youtube:live' |
2941 | ||
2942 | _TESTS = [{ | |
2d3d2997 | 2943 | 'url': 'https://www.youtube.com/user/TheYoungTurks/live', |
f07e276a S |
2944 | 'info_dict': { |
2945 | 'id': 'a48o2S1cPoo', | |
2946 | 'ext': 'mp4', | |
2947 | 'title': 'The Young Turks - Live Main Show', | |
2948 | 'uploader': 'The Young Turks', | |
2949 | 'uploader_id': 'TheYoungTurks', | |
ec85ded8 | 2950 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks', |
f07e276a S |
2951 | 'upload_date': '20150715', |
2952 | 'license': 'Standard YouTube License', | |
2953 | 'description': 'md5:438179573adcdff3c97ebb1ee632b891', | |
2954 | 'categories': ['News & Politics'], | |
2955 | 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], | |
2956 | 'like_count': int, | |
2957 | 'dislike_count': int, | |
2958 | }, | |
2959 | 'params': { | |
2960 | 'skip_download': True, | |
2961 | }, | |
2962 | }, { | |
2d3d2997 | 2963 | 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', |
f07e276a | 2964 | 'only_matching': True, |
c1b2a085 S |
2965 | }, { |
2966 | 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', | |
2967 | 'only_matching': True, | |
073d5bf5 S |
2968 | }, { |
2969 | 'url': 'https://www.youtube.com/TheYoungTurks/live', | |
2970 | 'only_matching': True, | |
f07e276a S |
2971 | }] |
2972 | ||
2973 | def _real_extract(self, url): | |
2974 | mobj = re.match(self._VALID_URL, url) | |
2975 | channel_id = mobj.group('id') | |
2976 | base_url = mobj.group('base_url') | |
2977 | webpage = self._download_webpage(url, channel_id, fatal=False) | |
2978 | if webpage: | |
2979 | page_type = self._og_search_property( | |
e7f3529f | 2980 | 'type', webpage, 'page type', default='') |
f07e276a S |
2981 | video_id = self._html_search_meta( |
2982 | 'videoId', webpage, 'video id', default=None) | |
e7f3529f S |
2983 | if page_type.startswith('video') and video_id and re.match( |
2984 | r'^[0-9A-Za-z_-]{11}$', video_id): | |
f07e276a S |
2985 | return self.url_result(video_id, YoutubeIE.ie_key()) |
2986 | return self.url_result(base_url) | |
2987 | ||
2988 | ||
e462474e S |
2989 | class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor): |
2990 | IE_DESC = 'YouTube.com user/channel playlists' | |
2991 | _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists' | |
2992 | IE_NAME = 'youtube:playlists' | |
0c148415 | 2993 | |
e568c223 | 2994 | _TESTS = [{ |
2d3d2997 | 2995 | 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', |
0c148415 S |
2996 | 'playlist_mincount': 4, |
2997 | 'info_dict': { | |
2998 | 'id': 'ThirstForScience', | |
13a75688 | 2999 | 'title': 'ThirstForScience', |
0c148415 | 3000 | }, |
e568c223 S |
3001 | }, { |
3002 | # with "Load more" button | |
2d3d2997 | 3003 | 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', |
e568c223 S |
3004 | 'playlist_mincount': 70, |
3005 | 'info_dict': { | |
3006 | 'id': 'igorkle1', | |
3007 | 'title': 'Игорь Клейнер', | |
3008 | }, | |
e462474e S |
3009 | }, { |
3010 | 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists', | |
3011 | 'playlist_mincount': 17, | |
3012 | 'info_dict': { | |
3013 | 'id': 'UCiU1dHvZObB2iP6xkJ__Icw', | |
3014 | 'title': 'Chem Player', | |
3015 | }, | |
13a75688 | 3016 | 'skip': 'Blocked', |
e568c223 | 3017 | }] |
0c148415 S |
3018 | |
3019 | ||
870f3bfc S |
3020 | class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor): |
3021 | _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?' | |
3022 | ||
3023 | ||
3024 | class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor): | |
78caa52a | 3025 | IE_DESC = 'YouTube.com searches' |
b4c08069 JMF |
3026 | # there doesn't appear to be a real limit, for example if you search for |
3027 | # 'python' you get more than 8.000.000 results | |
3028 | _MAX_RESULTS = float('inf') | |
78caa52a | 3029 | IE_NAME = 'youtube:search' |
b05654f0 | 3030 | _SEARCH_KEY = 'ytsearch' |
b4c08069 | 3031 | _EXTRA_QUERY_ARGS = {} |
9dd8e46a | 3032 | _TESTS = [] |
b05654f0 | 3033 | |
b05654f0 PH |
3034 | def _get_n_results(self, query, n): |
3035 | """Get a specified number of results for a query""" | |
3036 | ||
b4c08069 | 3037 | videos = [] |
b05654f0 PH |
3038 | limit = n |
3039 | ||
a22b2fd1 YCH |
3040 | url_query = { |
3041 | 'search_query': query.encode('utf-8'), | |
3042 | } | |
3043 | url_query.update(self._EXTRA_QUERY_ARGS) | |
3044 | result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query) | |
3045 | ||
b4c08069 | 3046 | for pagenum in itertools.count(1): |
b4c08069 | 3047 | data = self._download_json( |
69ea8ca4 | 3048 | result_url, video_id='query "%s"' % query, |
b4c08069 | 3049 | note='Downloading page %s' % pagenum, |
a22b2fd1 YCH |
3050 | errnote='Unable to download API page', |
3051 | query={'spf': 'navigate'}) | |
b4c08069 | 3052 | html_content = data[1]['body']['content'] |
7cc3570e | 3053 | |
b4c08069 | 3054 | if 'class="search-message' in html_content: |
07ad22b8 | 3055 | raise ExtractorError( |
78caa52a | 3056 | '[youtube] No video results', expected=True) |
b05654f0 | 3057 | |
870f3bfc | 3058 | new_videos = list(self._process_page(html_content)) |
b4c08069 JMF |
3059 | videos += new_videos |
3060 | if not new_videos or len(videos) > limit: | |
3061 | break | |
a22b2fd1 YCH |
3062 | next_link = self._html_search_regex( |
3063 | r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next', | |
3064 | html_content, 'next link', default=None) | |
3065 | if next_link is None: | |
3066 | break | |
3067 | result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link) | |
b05654f0 | 3068 | |
b4c08069 JMF |
3069 | if len(videos) > n: |
3070 | videos = videos[:n] | |
b05654f0 | 3071 | return self.playlist_result(videos, query) |
75dff0ee | 3072 | |
c9ae7b95 | 3073 | |
a3dd9248 | 3074 | class YoutubeSearchDateIE(YoutubeSearchIE): |
cb7fb546 | 3075 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' |
a3dd9248 | 3076 | _SEARCH_KEY = 'ytsearchdate' |
78caa52a | 3077 | IE_DESC = 'YouTube.com searches, newest videos first' |
b4c08069 | 3078 | _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'} |
75dff0ee | 3079 | |
c9ae7b95 | 3080 | |
870f3bfc | 3081 | class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor): |
78caa52a PH |
3082 | IE_DESC = 'YouTube.com search URLs' |
3083 | IE_NAME = 'youtube:search_url' | |
d2c1f79f | 3084 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)' |
cdc628a4 PH |
3085 | _TESTS = [{ |
3086 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
3087 | 'playlist_mincount': 5, | |
3088 | 'info_dict': { | |
3089 | 'title': 'youtube-dl test video', | |
3090 | } | |
d2c1f79f S |
3091 | }, { |
3092 | 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB', | |
3093 | 'only_matching': True, | |
cdc628a4 | 3094 | }] |
c9ae7b95 PH |
3095 | |
3096 | def _real_extract(self, url): | |
3097 | mobj = re.match(self._VALID_URL, url) | |
7fd002c0 | 3098 | query = compat_urllib_parse_unquote_plus(mobj.group('query')) |
c9ae7b95 | 3099 | webpage = self._download_webpage(url, query) |
175c2e9e | 3100 | return self.playlist_result(self._process_page(webpage), playlist_title=query) |
c9ae7b95 PH |
3101 | |
3102 | ||
136dadde | 3103 | class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor): |
78caa52a | 3104 | IE_DESC = 'YouTube.com (multi-season) shows' |
92519402 | 3105 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)' |
78caa52a | 3106 | IE_NAME = 'youtube:show' |
cdc628a4 | 3107 | _TESTS = [{ |
4003bd82 | 3108 | 'url': 'https://www.youtube.com/show/airdisasters', |
8801255d | 3109 | 'playlist_mincount': 5, |
cdc628a4 PH |
3110 | 'info_dict': { |
3111 | 'id': 'airdisasters', | |
3112 | 'title': 'Air Disasters', | |
3113 | } | |
3114 | }] | |
75dff0ee JMF |
3115 | |
3116 | def _real_extract(self, url): | |
136dadde S |
3117 | playlist_id = self._match_id(url) |
3118 | return super(YoutubeShowIE, self)._real_extract( | |
3119 | 'https://www.youtube.com/show/%s/playlists' % playlist_id) | |
04cc9617 JMF |
3120 | |
3121 | ||
b2e8bc1b | 3122 | class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): |
d7ae0639 | 3123 | """ |
25f14e9f | 3124 | Base class for feed extractors |
d7ae0639 JMF |
3125 | Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties. |
3126 | """ | |
b2e8bc1b | 3127 | _LOGIN_REQUIRED = True |
d7ae0639 JMF |
3128 | |
3129 | @property | |
3130 | def IE_NAME(self): | |
78caa52a | 3131 | return 'youtube:%s' % self._FEED_NAME |
04cc9617 | 3132 | |
81f0259b | 3133 | def _real_initialize(self): |
b2e8bc1b | 3134 | self._login() |
81f0259b | 3135 | |
3853309f | 3136 | def _entries(self, page): |
2bc43303 JMF |
3137 | # The extraction process is the same as for playlists, but the regex |
3138 | # for the video ids doesn't contain an index | |
3139 | ids = [] | |
3140 | more_widget_html = content_html = page | |
2bc43303 JMF |
3141 | for page_num in itertools.count(1): |
3142 | matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html) | |
62c95fd5 S |
3143 | |
3144 | # 'recommended' feed has infinite 'load more' and each new portion spins | |
3145 | # the same videos in (sometimes) slightly different order, so we'll check | |
3146 | # for unicity and break when portion has no new videos | |
3853309f | 3147 | new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches))) |
62c95fd5 S |
3148 | if not new_ids: |
3149 | break | |
3150 | ||
2bc43303 JMF |
3151 | ids.extend(new_ids) |
3152 | ||
3853309f S |
3153 | for entry in self._ids_to_results(new_ids): |
3154 | yield entry | |
3155 | ||
2bc43303 JMF |
3156 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) |
3157 | if not mobj: | |
3158 | break | |
3159 | ||
3160 | more = self._download_json( | |
25f14e9f | 3161 | 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE, |
2bc43303 JMF |
3162 | 'Downloading page #%s' % page_num, |
3163 | transform_source=uppercase_escape) | |
3164 | content_html = more['content_html'] | |
3165 | more_widget_html = more['load_more_widget_html'] | |
3166 | ||
3853309f S |
3167 | def _real_extract(self, url): |
3168 | page = self._download_webpage( | |
3169 | 'https://www.youtube.com/feed/%s' % self._FEED_NAME, | |
3170 | self._PLAYLIST_TITLE) | |
25f14e9f | 3171 | return self.playlist_result( |
3853309f | 3172 | self._entries(page), playlist_title=self._PLAYLIST_TITLE) |
25f14e9f S |
3173 | |
3174 | ||
3175 | class YoutubeWatchLaterIE(YoutubePlaylistIE): | |
3176 | IE_NAME = 'youtube:watchlater' | |
3177 | IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' | |
92519402 | 3178 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater' |
25f14e9f | 3179 | |
bc7a9cd8 S |
3180 | _TESTS = [{ |
3181 | 'url': 'https://www.youtube.com/playlist?list=WL', | |
3182 | 'only_matching': True, | |
3183 | }, { | |
3184 | 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL', | |
3185 | 'only_matching': True, | |
3186 | }] | |
25f14e9f S |
3187 | |
3188 | def _real_extract(self, url): | |
7e5dc339 | 3189 | _, video = self._check_download_just_video(url, 'WL') |
ebf1b291 S |
3190 | if video: |
3191 | return video | |
dacb3a86 S |
3192 | _, playlist = self._extract_playlist('WL') |
3193 | return playlist | |
f459d170 | 3194 | |
5f6a1245 | 3195 | |
c626a3d9 | 3196 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): |
78caa52a | 3197 | IE_NAME = 'youtube:favorites' |
f3a34072 | 3198 | IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)' |
92519402 | 3199 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?' |
c626a3d9 JMF |
3200 | _LOGIN_REQUIRED = True |
3201 | ||
3202 | def _real_extract(self, url): | |
3203 | webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos') | |
78caa52a | 3204 | playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id') |
c626a3d9 | 3205 | return self.url_result(playlist_id, 'YoutubePlaylist') |
15870e90 PH |
3206 | |
3207 | ||
25f14e9f S |
3208 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): |
3209 | IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' | |
92519402 | 3210 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?' |
25f14e9f S |
3211 | _FEED_NAME = 'recommended' |
3212 | _PLAYLIST_TITLE = 'Youtube Recommended videos' | |
1ed5b5c9 | 3213 | |
1ed5b5c9 | 3214 | |
25f14e9f S |
3215 | class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): |
3216 | IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' | |
92519402 | 3217 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' |
25f14e9f S |
3218 | _FEED_NAME = 'subscriptions' |
3219 | _PLAYLIST_TITLE = 'Youtube Subscriptions' | |
1ed5b5c9 | 3220 | |
1ed5b5c9 | 3221 | |
25f14e9f S |
3222 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): |
3223 | IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' | |
92519402 | 3224 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory' |
25f14e9f S |
3225 | _FEED_NAME = 'history' |
3226 | _PLAYLIST_TITLE = 'Youtube History' | |
1ed5b5c9 JMF |
3227 | |
3228 | ||
15870e90 PH |
3229 | class YoutubeTruncatedURLIE(InfoExtractor): |
3230 | IE_NAME = 'youtube:truncated_url' | |
3231 | IE_DESC = False # Do not list | |
975d35db | 3232 | _VALID_URL = r'''(?x) |
b95aab84 PH |
3233 | (?:https?://)? |
3234 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
3235 | (?:watch\?(?: | |
c4808c60 | 3236 | feature=[a-z_]+| |
b95aab84 PH |
3237 | annotation_id=annotation_[^&]+| |
3238 | x-yt-cl=[0-9]+| | |
c1708b89 | 3239 | hl=[^&]*| |
287be8c6 | 3240 | t=[0-9]+ |
b95aab84 PH |
3241 | )? |
3242 | | | |
3243 | attribution_link\?a=[^&]+ | |
3244 | ) | |
3245 | $ | |
975d35db | 3246 | ''' |
15870e90 | 3247 | |
c4808c60 | 3248 | _TESTS = [{ |
2d3d2997 | 3249 | 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041', |
c4808c60 | 3250 | 'only_matching': True, |
dc2fc736 | 3251 | }, { |
2d3d2997 | 3252 | 'url': 'https://www.youtube.com/watch?', |
dc2fc736 | 3253 | 'only_matching': True, |
b95aab84 PH |
3254 | }, { |
3255 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
3256 | 'only_matching': True, | |
3257 | }, { | |
3258 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
3259 | 'only_matching': True, | |
c1708b89 PH |
3260 | }, { |
3261 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
3262 | 'only_matching': True, | |
287be8c6 PH |
3263 | }, { |
3264 | 'url': 'https://www.youtube.com/watch?t=2372', | |
3265 | 'only_matching': True, | |
c4808c60 PH |
3266 | }] |
3267 | ||
15870e90 PH |
3268 | def _real_extract(self, url): |
3269 | raise ExtractorError( | |
78caa52a PH |
3270 | 'Did you forget to quote the URL? Remember that & is a meta ' |
3271 | 'character in most shells, so you want to put the URL in quotes, ' | |
3272 | 'like youtube-dl ' | |
2d3d2997 | 3273 | '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' |
78caa52a | 3274 | ' or simply youtube-dl BaW_jenozKc .', |
15870e90 | 3275 | expected=True) |
772fd5cc PH |
3276 | |
3277 | ||
3278 | class YoutubeTruncatedIDIE(InfoExtractor): | |
3279 | IE_NAME = 'youtube:truncated_id' | |
3280 | IE_DESC = False # Do not list | |
b95aab84 | 3281 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' |
772fd5cc PH |
3282 | |
3283 | _TESTS = [{ | |
3284 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
3285 | 'only_matching': True, | |
3286 | }] | |
3287 | ||
3288 | def _real_extract(self, url): | |
3289 | video_id = self._match_id(url) | |
3290 | raise ExtractorError( | |
3291 | 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), | |
3292 | expected=True) |