]>
Commit | Line | Data |
---|---|---|
1 | # coding: utf-8 | |
2 | ||
3 | from __future__ import unicode_literals | |
4 | ||
5 | ||
6 | import itertools | |
7 | import json | |
8 | import os.path | |
9 | import random | |
10 | import re | |
11 | import time | |
12 | import traceback | |
13 | ||
14 | from .common import InfoExtractor, SearchInfoExtractor | |
15 | from ..jsinterp import JSInterpreter | |
16 | from ..swfinterp import SWFInterpreter | |
17 | from ..compat import ( | |
18 | compat_chr, | |
19 | compat_kwargs, | |
20 | compat_parse_qs, | |
21 | compat_urllib_parse_unquote, | |
22 | compat_urllib_parse_unquote_plus, | |
23 | compat_urllib_parse_urlencode, | |
24 | compat_urllib_parse_urlparse, | |
25 | compat_urlparse, | |
26 | compat_str, | |
27 | ) | |
28 | from ..utils import ( | |
29 | clean_html, | |
30 | error_to_compat_str, | |
31 | ExtractorError, | |
32 | float_or_none, | |
33 | get_element_by_attribute, | |
34 | get_element_by_id, | |
35 | int_or_none, | |
36 | mimetype2ext, | |
37 | orderedSet, | |
38 | parse_codecs, | |
39 | parse_duration, | |
40 | qualities, | |
41 | remove_quotes, | |
42 | remove_start, | |
43 | smuggle_url, | |
44 | str_or_none, | |
45 | str_to_int, | |
46 | try_get, | |
47 | unescapeHTML, | |
48 | unified_strdate, | |
49 | unsmuggle_url, | |
50 | uppercase_escape, | |
51 | urlencode_postdata, | |
52 | ) | |
53 | ||
54 | ||
55 | class YoutubeBaseInfoExtractor(InfoExtractor): | |
56 | """Provide base functions for Youtube extractors""" | |
57 | _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' | |
58 | _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge' | |
59 | ||
60 | _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup' | |
61 | _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge' | |
62 | _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}' | |
63 | ||
64 | _NETRC_MACHINE = 'youtube' | |
65 | # If True it will raise an error if no login info is provided | |
66 | _LOGIN_REQUIRED = False | |
67 | ||
68 | _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)[0-9A-Za-z-_]{10,}' | |
69 | ||
70 | def _set_language(self): | |
71 | self._set_cookie( | |
72 | '.youtube.com', 'PREF', 'f1=50000000&hl=en', | |
73 | # YouTube sets the expire time to about two months | |
74 | expire_time=time.time() + 2 * 30 * 24 * 3600) | |
75 | ||
76 | def _ids_to_results(self, ids): | |
77 | return [ | |
78 | self.url_result(vid_id, 'Youtube', video_id=vid_id) | |
79 | for vid_id in ids] | |
80 | ||
81 | def _login(self): | |
82 | """ | |
83 | Attempt to log in to YouTube. | |
84 | True is returned if successful or skipped. | |
85 | False is returned if login failed. | |
86 | ||
87 | If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. | |
88 | """ | |
89 | username, password = self._get_login_info() | |
90 | # No authentication to be performed | |
91 | if username is None: | |
92 | if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None: | |
93 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) | |
94 | return True | |
95 | ||
96 | login_page = self._download_webpage( | |
97 | self._LOGIN_URL, None, | |
98 | note='Downloading login page', | |
99 | errnote='unable to fetch login page', fatal=False) | |
100 | if login_page is False: | |
101 | return | |
102 | ||
103 | login_form = self._hidden_inputs(login_page) | |
104 | ||
105 | def req(url, f_req, note, errnote): | |
106 | data = login_form.copy() | |
107 | data.update({ | |
108 | 'pstMsg': 1, | |
109 | 'checkConnection': 'youtube', | |
110 | 'checkedDomains': 'youtube', | |
111 | 'hl': 'en', | |
112 | 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]', | |
113 | 'f.req': json.dumps(f_req), | |
114 | 'flowName': 'GlifWebSignIn', | |
115 | 'flowEntry': 'ServiceLogin', | |
116 | }) | |
117 | return self._download_json( | |
118 | url, None, note=note, errnote=errnote, | |
119 | transform_source=lambda s: re.sub(r'^[^[]*', '', s), | |
120 | fatal=False, | |
121 | data=urlencode_postdata(data), headers={ | |
122 | 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8', | |
123 | 'Google-Accounts-XSRF': 1, | |
124 | }) | |
125 | ||
126 | def warn(message): | |
127 | self._downloader.report_warning(message) | |
128 | ||
129 | lookup_req = [ | |
130 | username, | |
131 | None, [], None, 'US', None, None, 2, False, True, | |
132 | [ | |
133 | None, None, | |
134 | [2, 1, None, 1, | |
135 | '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', | |
136 | None, [], 4], | |
137 | 1, [None, None, []], None, None, None, True | |
138 | ], | |
139 | username, | |
140 | ] | |
141 | ||
142 | lookup_results = req( | |
143 | self._LOOKUP_URL, lookup_req, | |
144 | 'Looking up account info', 'Unable to look up account info') | |
145 | ||
146 | if lookup_results is False: | |
147 | return False | |
148 | ||
149 | user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str) | |
150 | if not user_hash: | |
151 | warn('Unable to extract user hash') | |
152 | return False | |
153 | ||
154 | challenge_req = [ | |
155 | user_hash, | |
156 | None, 1, None, [1, None, None, None, [password, None, True]], | |
157 | [ | |
158 | 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], | |
159 | 1, [None, None, []], None, None, None, True | |
160 | ]] | |
161 | ||
162 | challenge_results = req( | |
163 | self._CHALLENGE_URL, challenge_req, | |
164 | 'Logging in', 'Unable to log in') | |
165 | ||
166 | if challenge_results is False: | |
167 | return | |
168 | ||
169 | login_res = try_get(challenge_results, lambda x: x[0][5], list) | |
170 | if login_res: | |
171 | login_msg = try_get(login_res, lambda x: x[5], compat_str) | |
172 | warn( | |
173 | 'Unable to login: %s' % 'Invalid password' | |
174 | if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg) | |
175 | return False | |
176 | ||
177 | res = try_get(challenge_results, lambda x: x[0][-1], list) | |
178 | if not res: | |
179 | warn('Unable to extract result entry') | |
180 | return False | |
181 | ||
182 | login_challenge = try_get(res, lambda x: x[0][0], list) | |
183 | if login_challenge: | |
184 | challenge_str = try_get(login_challenge, lambda x: x[2], compat_str) | |
185 | if challenge_str == 'TWO_STEP_VERIFICATION': | |
186 | # SEND_SUCCESS - TFA code has been successfully sent to phone | |
187 | # QUOTA_EXCEEDED - reached the limit of TFA codes | |
188 | status = try_get(login_challenge, lambda x: x[5], compat_str) | |
189 | if status == 'QUOTA_EXCEEDED': | |
190 | warn('Exceeded the limit of TFA codes, try later') | |
191 | return False | |
192 | ||
193 | tl = try_get(challenge_results, lambda x: x[1][2], compat_str) | |
194 | if not tl: | |
195 | warn('Unable to extract TL') | |
196 | return False | |
197 | ||
198 | tfa_code = self._get_tfa_info('2-step verification code') | |
199 | ||
200 | if not tfa_code: | |
201 | warn( | |
202 | 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>' | |
203 | '(Note that only TOTP (Google Authenticator App) codes work at this time.)') | |
204 | return False | |
205 | ||
206 | tfa_code = remove_start(tfa_code, 'G-') | |
207 | ||
208 | tfa_req = [ | |
209 | user_hash, None, 2, None, | |
210 | [ | |
211 | 9, None, None, None, None, None, None, None, | |
212 | [None, tfa_code, True, 2] | |
213 | ]] | |
214 | ||
215 | tfa_results = req( | |
216 | self._TFA_URL.format(tl), tfa_req, | |
217 | 'Submitting TFA code', 'Unable to submit TFA code') | |
218 | ||
219 | if tfa_results is False: | |
220 | return False | |
221 | ||
222 | tfa_res = try_get(tfa_results, lambda x: x[0][5], list) | |
223 | if tfa_res: | |
224 | tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str) | |
225 | warn( | |
226 | 'Unable to finish TFA: %s' % 'Invalid TFA code' | |
227 | if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg) | |
228 | return False | |
229 | ||
230 | check_cookie_url = try_get( | |
231 | tfa_results, lambda x: x[0][-1][2], compat_str) | |
232 | else: | |
233 | CHALLENGES = { | |
234 | 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.", | |
235 | 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.', | |
236 | 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.", | |
237 | } | |
238 | challenge = CHALLENGES.get( | |
239 | challenge_str, | |
240 | '%s returned error %s.' % (self.IE_NAME, challenge_str)) | |
241 | warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge) | |
242 | return False | |
243 | else: | |
244 | check_cookie_url = try_get(res, lambda x: x[2], compat_str) | |
245 | ||
246 | if not check_cookie_url: | |
247 | warn('Unable to extract CheckCookie URL') | |
248 | return False | |
249 | ||
250 | check_cookie_results = self._download_webpage( | |
251 | check_cookie_url, None, 'Checking cookie', fatal=False) | |
252 | ||
253 | if check_cookie_results is False: | |
254 | return False | |
255 | ||
256 | if 'https://myaccount.google.com/' not in check_cookie_results: | |
257 | warn('Unable to log in') | |
258 | return False | |
259 | ||
260 | return True | |
261 | ||
262 | def _download_webpage_handle(self, *args, **kwargs): | |
263 | query = kwargs.get('query', {}).copy() | |
264 | query['disable_polymer'] = 'true' | |
265 | kwargs['query'] = query | |
266 | return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle( | |
267 | *args, **compat_kwargs(kwargs)) | |
268 | ||
269 | def _real_initialize(self): | |
270 | if self._downloader is None: | |
271 | return | |
272 | self._set_language() | |
273 | if not self._login(): | |
274 | return | |
275 | ||
276 | ||
277 | class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor): | |
278 | # Extract entries from page with "Load more" button | |
279 | def _entries(self, page, playlist_id): | |
280 | more_widget_html = content_html = page | |
281 | for page_num in itertools.count(1): | |
282 | for entry in self._process_page(content_html): | |
283 | yield entry | |
284 | ||
285 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) | |
286 | if not mobj: | |
287 | break | |
288 | ||
289 | more = self._download_json( | |
290 | 'https://youtube.com/%s' % mobj.group('more'), playlist_id, | |
291 | 'Downloading page #%s' % page_num, | |
292 | transform_source=uppercase_escape) | |
293 | content_html = more['content_html'] | |
294 | if not content_html.strip(): | |
295 | # Some webpages show a "Load more" button but they don't | |
296 | # have more videos | |
297 | break | |
298 | more_widget_html = more['load_more_widget_html'] | |
299 | ||
300 | ||
301 | class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): | |
302 | def _process_page(self, content): | |
303 | for video_id, video_title in self.extract_videos_from_page(content): | |
304 | yield self.url_result(video_id, 'Youtube', video_id, video_title) | |
305 | ||
306 | def extract_videos_from_page(self, page): | |
307 | ids_in_page = [] | |
308 | titles_in_page = [] | |
309 | for mobj in re.finditer(self._VIDEO_RE, page): | |
310 | # The link with index 0 is not the first video of the playlist (not sure if still actual) | |
311 | if 'index' in mobj.groupdict() and mobj.group('id') == '0': | |
312 | continue | |
313 | video_id = mobj.group('id') | |
314 | video_title = unescapeHTML(mobj.group('title')) | |
315 | if video_title: | |
316 | video_title = video_title.strip() | |
317 | try: | |
318 | idx = ids_in_page.index(video_id) | |
319 | if video_title and not titles_in_page[idx]: | |
320 | titles_in_page[idx] = video_title | |
321 | except ValueError: | |
322 | ids_in_page.append(video_id) | |
323 | titles_in_page.append(video_title) | |
324 | return zip(ids_in_page, titles_in_page) | |
325 | ||
326 | ||
327 | class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): | |
328 | def _process_page(self, content): | |
329 | for playlist_id in orderedSet(re.findall( | |
330 | r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"', | |
331 | content)): | |
332 | yield self.url_result( | |
333 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist') | |
334 | ||
335 | def _real_extract(self, url): | |
336 | playlist_id = self._match_id(url) | |
337 | webpage = self._download_webpage(url, playlist_id) | |
338 | title = self._og_search_title(webpage, fatal=False) | |
339 | return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title) | |
340 | ||
341 | ||
342 | class YoutubeIE(YoutubeBaseInfoExtractor): | |
343 | IE_DESC = 'YouTube.com' | |
344 | _VALID_URL = r"""(?x)^ | |
345 | ( | |
346 | (?:https?://|//) # http(s):// or protocol-independent URL | |
347 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/| | |
348 | (?:www\.)?deturl\.com/www\.youtube\.com/| | |
349 | (?:www\.)?pwnyoutube\.com/| | |
350 | (?:www\.)?hooktube\.com/| | |
351 | (?:www\.)?yourepeat\.com/| | |
352 | tube\.majestyc\.net/| | |
353 | (?:www\.)?invidio\.us/| | |
354 | youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains | |
355 | (?:.*?\#/)? # handle anchor (#/) redirect urls | |
356 | (?: # the various things that can precede the ID: | |
357 | (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/ | |
358 | |(?: # or the v= param in all its forms | |
359 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) | |
360 | (?:\?|\#!?) # the params delimiter ? or # or #! | |
361 | (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY) | |
362 | v= | |
363 | ) | |
364 | )) | |
365 | |(?: | |
366 | youtu\.be| # just youtu.be/xxxx | |
367 | vid\.plus| # or vid.plus/xxxx | |
368 | zwearz\.com/watch| # or zwearz.com/watch/xxxx | |
369 | )/ | |
370 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= | |
371 | ) | |
372 | )? # all until now is optional -> you can pass the naked ID | |
373 | ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID | |
374 | (?!.*?\blist= | |
375 | (?: | |
376 | %(playlist_id)s| # combined list/video URLs are handled by the playlist IE | |
377 | WL # WL are handled by the watch later IE | |
378 | ) | |
379 | ) | |
380 | (?(1).+)? # if we found the ID, everything can follow | |
381 | $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} | |
382 | _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' | |
383 | _formats = { | |
384 | '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
385 | '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
386 | '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
387 | '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}, | |
388 | '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}, | |
389 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
390 | '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
391 | '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
392 | # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well | |
393 | '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
394 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
395 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
396 | '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
397 | '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
398 | '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
399 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
400 | '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
401 | '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
402 | ||
403 | ||
404 | # 3D videos | |
405 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
406 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
407 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
408 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
409 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}, | |
410 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
411 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
412 | ||
413 | # Apple HTTP Live Streaming | |
414 | '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, | |
415 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, | |
416 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
417 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
418 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
419 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
420 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, | |
421 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}, | |
422 | ||
423 | # DASH mp4 video | |
424 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
425 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
426 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
427 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
428 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
429 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559) | |
430 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
431 | '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
432 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
433 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
434 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
435 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
436 | ||
437 | # Dash mp4 audio | |
438 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}, | |
439 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}, | |
440 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}, | |
441 | '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
442 | '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
443 | '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}, | |
444 | '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}, | |
445 | ||
446 | # Dash webm | |
447 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
448 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
449 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
450 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
451 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
452 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
453 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}, | |
454 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
455 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
456 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
457 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
458 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
459 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
460 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
461 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
462 | # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug) | |
463 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
464 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
465 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
466 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
467 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
468 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
469 | ||
470 | # Dash webm audio | |
471 | '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}, | |
472 | '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}, | |
473 | ||
474 | # Dash webm audio with opus inside | |
475 | '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}, | |
476 | '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}, | |
477 | '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}, | |
478 | ||
479 | # RTMP (unnamed) | |
480 | '_rtmp': {'protocol': 'rtmp'}, | |
481 | } | |
482 | _SUBTITLE_FORMATS = ('ttml', 'vtt') | |
483 | ||
484 | _GEO_BYPASS = False | |
485 | ||
486 | IE_NAME = 'youtube' | |
487 | _TESTS = [ | |
488 | { | |
489 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9', | |
490 | 'info_dict': { | |
491 | 'id': 'BaW_jenozKc', | |
492 | 'ext': 'mp4', | |
493 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
494 | 'uploader': 'Philipp Hagemeister', | |
495 | 'uploader_id': 'phihag', | |
496 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', | |
497 | 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q', | |
498 | 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q', | |
499 | 'upload_date': '20121002', | |
500 | 'license': 'Standard YouTube License', | |
501 | '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 .', | |
502 | 'categories': ['Science & Technology'], | |
503 | 'tags': ['youtube-dl'], | |
504 | 'duration': 10, | |
505 | 'view_count': int, | |
506 | 'like_count': int, | |
507 | 'dislike_count': int, | |
508 | 'start_time': 1, | |
509 | 'end_time': 9, | |
510 | } | |
511 | }, | |
512 | { | |
513 | 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY', | |
514 | 'note': 'Test generic use_cipher_signature video (#897)', | |
515 | 'info_dict': { | |
516 | 'id': 'UxxajLWwzqY', | |
517 | 'ext': 'mp4', | |
518 | 'upload_date': '20120506', | |
519 | 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', | |
520 | 'alt_title': 'I Love It (feat. Charli XCX)', | |
521 | 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8', | |
522 | 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli', | |
523 | 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop', | |
524 | 'iconic ep', 'iconic', 'love', 'it'], | |
525 | 'duration': 180, | |
526 | 'uploader': 'Icona Pop', | |
527 | 'uploader_id': 'IconaPop', | |
528 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop', | |
529 | 'license': 'Standard YouTube License', | |
530 | 'creator': 'Icona Pop', | |
531 | 'track': 'I Love It (feat. Charli XCX)', | |
532 | 'artist': 'Icona Pop', | |
533 | } | |
534 | }, | |
535 | { | |
536 | 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ', | |
537 | 'note': 'Test VEVO video with age protection (#956)', | |
538 | 'info_dict': { | |
539 | 'id': '07FYdnEawAQ', | |
540 | 'ext': 'mp4', | |
541 | 'upload_date': '20130703', | |
542 | 'title': 'Justin Timberlake - Tunnel Vision (Explicit)', | |
543 | 'alt_title': 'Tunnel Vision', | |
544 | 'description': 'md5:64249768eec3bc4276236606ea996373', | |
545 | 'duration': 419, | |
546 | 'uploader': 'justintimberlakeVEVO', | |
547 | 'uploader_id': 'justintimberlakeVEVO', | |
548 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO', | |
549 | 'license': 'Standard YouTube License', | |
550 | 'creator': 'Justin Timberlake', | |
551 | 'track': 'Tunnel Vision', | |
552 | 'artist': 'Justin Timberlake', | |
553 | 'age_limit': 18, | |
554 | } | |
555 | }, | |
556 | { | |
557 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', | |
558 | 'note': 'Embed-only video (#1746)', | |
559 | 'info_dict': { | |
560 | 'id': 'yZIXLfi8CZQ', | |
561 | 'ext': 'mp4', | |
562 | 'upload_date': '20120608', | |
563 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
564 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
565 | 'uploader': 'SET India', | |
566 | 'uploader_id': 'setindia', | |
567 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia', | |
568 | 'license': 'Standard YouTube License', | |
569 | 'age_limit': 18, | |
570 | } | |
571 | }, | |
572 | { | |
573 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY', | |
574 | 'note': 'Use the first video ID in the URL', | |
575 | 'info_dict': { | |
576 | 'id': 'BaW_jenozKc', | |
577 | 'ext': 'mp4', | |
578 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
579 | 'uploader': 'Philipp Hagemeister', | |
580 | 'uploader_id': 'phihag', | |
581 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', | |
582 | 'upload_date': '20121002', | |
583 | 'license': 'Standard YouTube License', | |
584 | '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 .', | |
585 | 'categories': ['Science & Technology'], | |
586 | 'tags': ['youtube-dl'], | |
587 | 'duration': 10, | |
588 | 'view_count': int, | |
589 | 'like_count': int, | |
590 | 'dislike_count': int, | |
591 | }, | |
592 | 'params': { | |
593 | 'skip_download': True, | |
594 | }, | |
595 | }, | |
596 | { | |
597 | 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I', | |
598 | 'note': '256k DASH audio (format 141) via DASH manifest', | |
599 | 'info_dict': { | |
600 | 'id': 'a9LDPn-MO4I', | |
601 | 'ext': 'm4a', | |
602 | 'upload_date': '20121002', | |
603 | 'uploader_id': '8KVIDEO', | |
604 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO', | |
605 | 'description': '', | |
606 | 'uploader': '8KVIDEO', | |
607 | 'license': 'Standard YouTube License', | |
608 | 'title': 'UHDTV TEST 8K VIDEO.mp4' | |
609 | }, | |
610 | 'params': { | |
611 | 'youtube_include_dash_manifest': True, | |
612 | 'format': '141', | |
613 | }, | |
614 | 'skip': 'format 141 not served anymore', | |
615 | }, | |
616 | # DASH manifest with encrypted signature | |
617 | { | |
618 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', | |
619 | 'info_dict': { | |
620 | 'id': 'IB3lcPjvWLA', | |
621 | 'ext': 'm4a', | |
622 | 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson', | |
623 | 'description': 'md5:1900ed86ee514927b9e00fbead6969a5', | |
624 | 'duration': 244, | |
625 | 'uploader': 'AfrojackVEVO', | |
626 | 'uploader_id': 'AfrojackVEVO', | |
627 | 'upload_date': '20131011', | |
628 | 'license': 'Standard YouTube License', | |
629 | }, | |
630 | 'params': { | |
631 | 'youtube_include_dash_manifest': True, | |
632 | 'format': '141/bestaudio[ext=m4a]', | |
633 | }, | |
634 | }, | |
635 | # JS player signature function name containing $ | |
636 | { | |
637 | 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM', | |
638 | 'info_dict': { | |
639 | 'id': 'nfWlot6h_JM', | |
640 | 'ext': 'm4a', | |
641 | 'title': 'Taylor Swift - Shake It Off', | |
642 | 'alt_title': 'Shake It Off', | |
643 | 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3', | |
644 | 'duration': 242, | |
645 | 'uploader': 'TaylorSwiftVEVO', | |
646 | 'uploader_id': 'TaylorSwiftVEVO', | |
647 | 'upload_date': '20140818', | |
648 | 'license': 'Standard YouTube License', | |
649 | 'creator': 'Taylor Swift', | |
650 | }, | |
651 | 'params': { | |
652 | 'youtube_include_dash_manifest': True, | |
653 | 'format': '141/bestaudio[ext=m4a]', | |
654 | }, | |
655 | }, | |
656 | # Controversy video | |
657 | { | |
658 | 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8', | |
659 | 'info_dict': { | |
660 | 'id': 'T4XJQO3qol8', | |
661 | 'ext': 'mp4', | |
662 | 'duration': 219, | |
663 | 'upload_date': '20100909', | |
664 | 'uploader': 'TJ Kirk', | |
665 | 'uploader_id': 'TheAmazingAtheist', | |
666 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist', | |
667 | 'license': 'Standard YouTube License', | |
668 | 'title': 'Burning Everyone\'s Koran', | |
669 | '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', | |
670 | } | |
671 | }, | |
672 | # Normal age-gate video (No vevo, embed allowed) | |
673 | { | |
674 | 'url': 'https://youtube.com/watch?v=HtVdAasjOgU', | |
675 | 'info_dict': { | |
676 | 'id': 'HtVdAasjOgU', | |
677 | 'ext': 'mp4', | |
678 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
679 | 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', | |
680 | 'duration': 142, | |
681 | 'uploader': 'The Witcher', | |
682 | 'uploader_id': 'WitcherGame', | |
683 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame', | |
684 | 'upload_date': '20140605', | |
685 | 'license': 'Standard YouTube License', | |
686 | 'age_limit': 18, | |
687 | }, | |
688 | }, | |
689 | # Age-gate video with encrypted signature | |
690 | { | |
691 | 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU', | |
692 | 'info_dict': { | |
693 | 'id': '6kLq3WMV1nU', | |
694 | 'ext': 'webm', | |
695 | 'title': 'Dedication To My Ex (Miss That) (Lyric Video)', | |
696 | 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', | |
697 | 'duration': 246, | |
698 | 'uploader': 'LloydVEVO', | |
699 | 'uploader_id': 'LloydVEVO', | |
700 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO', | |
701 | 'upload_date': '20110629', | |
702 | 'license': 'Standard YouTube License', | |
703 | 'age_limit': 18, | |
704 | }, | |
705 | }, | |
706 | # video_info is None (https://github.com/rg3/youtube-dl/issues/4421) | |
707 | # YouTube Red ad is not captured for creator | |
708 | { | |
709 | 'url': '__2ABJjxzNo', | |
710 | 'info_dict': { | |
711 | 'id': '__2ABJjxzNo', | |
712 | 'ext': 'mp4', | |
713 | 'duration': 266, | |
714 | 'upload_date': '20100430', | |
715 | 'uploader_id': 'deadmau5', | |
716 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5', | |
717 | 'creator': 'deadmau5', | |
718 | 'description': 'md5:12c56784b8032162bb936a5f76d55360', | |
719 | 'uploader': 'deadmau5', | |
720 | 'license': 'Standard YouTube License', | |
721 | 'title': 'Deadmau5 - Some Chords (HD)', | |
722 | 'alt_title': 'Some Chords', | |
723 | }, | |
724 | 'expected_warnings': [ | |
725 | 'DASH manifest missing', | |
726 | ] | |
727 | }, | |
728 | # Olympics (https://github.com/rg3/youtube-dl/issues/4431) | |
729 | { | |
730 | 'url': 'lqQg6PlCWgI', | |
731 | 'info_dict': { | |
732 | 'id': 'lqQg6PlCWgI', | |
733 | 'ext': 'mp4', | |
734 | 'duration': 6085, | |
735 | 'upload_date': '20150827', | |
736 | 'uploader_id': 'olympic', | |
737 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic', | |
738 | 'license': 'Standard YouTube License', | |
739 | 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', | |
740 | 'uploader': 'Olympic', | |
741 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', | |
742 | }, | |
743 | 'params': { | |
744 | 'skip_download': 'requires avconv', | |
745 | } | |
746 | }, | |
747 | # Non-square pixels | |
748 | { | |
749 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
750 | 'info_dict': { | |
751 | 'id': '_b-2C3KPAM0', | |
752 | 'ext': 'mp4', | |
753 | 'stretched_ratio': 16 / 9., | |
754 | 'duration': 85, | |
755 | 'upload_date': '20110310', | |
756 | 'uploader_id': 'AllenMeow', | |
757 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow', | |
758 | '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', | |
759 | 'uploader': '孫ᄋᄅ', | |
760 | 'license': 'Standard YouTube License', | |
761 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', | |
762 | }, | |
763 | }, | |
764 | # url_encoded_fmt_stream_map is empty string | |
765 | { | |
766 | 'url': 'qEJwOuvDf7I', | |
767 | 'info_dict': { | |
768 | 'id': 'qEJwOuvDf7I', | |
769 | 'ext': 'webm', | |
770 | 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', | |
771 | 'description': '', | |
772 | 'upload_date': '20150404', | |
773 | 'uploader_id': 'spbelect', | |
774 | 'uploader': 'Наблюдатели Петербурга', | |
775 | }, | |
776 | 'params': { | |
777 | 'skip_download': 'requires avconv', | |
778 | }, | |
779 | 'skip': 'This live event has ended.', | |
780 | }, | |
781 | # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097) | |
782 | { | |
783 | 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y', | |
784 | 'info_dict': { | |
785 | 'id': 'FIl7x6_3R5Y', | |
786 | 'ext': 'webm', | |
787 | 'title': 'md5:7b81415841e02ecd4313668cde88737a', | |
788 | 'description': 'md5:116377fd2963b81ec4ce64b542173306', | |
789 | 'duration': 220, | |
790 | 'upload_date': '20150625', | |
791 | 'uploader_id': 'dorappi2000', | |
792 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000', | |
793 | 'uploader': 'dorappi2000', | |
794 | 'license': 'Standard YouTube License', | |
795 | 'formats': 'mincount:31', | |
796 | }, | |
797 | 'skip': 'not actual anymore', | |
798 | }, | |
799 | # DASH manifest with segment_list | |
800 | { | |
801 | 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8', | |
802 | 'md5': '8ce563a1d667b599d21064e982ab9e31', | |
803 | 'info_dict': { | |
804 | 'id': 'CsmdDsKjzN8', | |
805 | 'ext': 'mp4', | |
806 | 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510 | |
807 | 'uploader': 'Airtek', | |
808 | 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', | |
809 | 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ', | |
810 | 'license': 'Standard YouTube License', | |
811 | 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', | |
812 | }, | |
813 | 'params': { | |
814 | 'youtube_include_dash_manifest': True, | |
815 | 'format': '135', # bestvideo | |
816 | }, | |
817 | 'skip': 'This live event has ended.', | |
818 | }, | |
819 | { | |
820 | # Multifeed videos (multiple cameras), URL is for Main Camera | |
821 | 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs', | |
822 | 'info_dict': { | |
823 | 'id': 'jqWvoWXjCVs', | |
824 | 'title': 'teamPGP: Rocket League Noob Stream', | |
825 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
826 | }, | |
827 | 'playlist': [{ | |
828 | 'info_dict': { | |
829 | 'id': 'jqWvoWXjCVs', | |
830 | 'ext': 'mp4', | |
831 | 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)', | |
832 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
833 | 'duration': 7335, | |
834 | 'upload_date': '20150721', | |
835 | 'uploader': 'Beer Games Beer', | |
836 | 'uploader_id': 'beergamesbeer', | |
837 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', | |
838 | 'license': 'Standard YouTube License', | |
839 | }, | |
840 | }, { | |
841 | 'info_dict': { | |
842 | 'id': '6h8e8xoXJzg', | |
843 | 'ext': 'mp4', | |
844 | 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)', | |
845 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
846 | 'duration': 7337, | |
847 | 'upload_date': '20150721', | |
848 | 'uploader': 'Beer Games Beer', | |
849 | 'uploader_id': 'beergamesbeer', | |
850 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', | |
851 | 'license': 'Standard YouTube License', | |
852 | }, | |
853 | }, { | |
854 | 'info_dict': { | |
855 | 'id': 'PUOgX5z9xZw', | |
856 | 'ext': 'mp4', | |
857 | 'title': 'teamPGP: Rocket League Noob Stream (grizzle)', | |
858 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
859 | 'duration': 7337, | |
860 | 'upload_date': '20150721', | |
861 | 'uploader': 'Beer Games Beer', | |
862 | 'uploader_id': 'beergamesbeer', | |
863 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', | |
864 | 'license': 'Standard YouTube License', | |
865 | }, | |
866 | }, { | |
867 | 'info_dict': { | |
868 | 'id': 'teuwxikvS5k', | |
869 | 'ext': 'mp4', | |
870 | 'title': 'teamPGP: Rocket League Noob Stream (zim)', | |
871 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
872 | 'duration': 7334, | |
873 | 'upload_date': '20150721', | |
874 | 'uploader': 'Beer Games Beer', | |
875 | 'uploader_id': 'beergamesbeer', | |
876 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', | |
877 | 'license': 'Standard YouTube License', | |
878 | }, | |
879 | }], | |
880 | 'params': { | |
881 | 'skip_download': True, | |
882 | }, | |
883 | }, | |
884 | { | |
885 | # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536) | |
886 | 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo', | |
887 | 'info_dict': { | |
888 | 'id': 'gVfLd0zydlo', | |
889 | 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30', | |
890 | }, | |
891 | 'playlist_count': 2, | |
892 | 'skip': 'Not multifeed anymore', | |
893 | }, | |
894 | { | |
895 | 'url': 'https://vid.plus/FlRa-iH7PGw', | |
896 | 'only_matching': True, | |
897 | }, | |
898 | { | |
899 | 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html', | |
900 | 'only_matching': True, | |
901 | }, | |
902 | { | |
903 | # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468) | |
904 | # Also tests cut-off URL expansion in video description (see | |
905 | # https://github.com/rg3/youtube-dl/issues/1892, | |
906 | # https://github.com/rg3/youtube-dl/issues/8164) | |
907 | 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg', | |
908 | 'info_dict': { | |
909 | 'id': 'lsguqyKfVQg', | |
910 | 'ext': 'mp4', | |
911 | 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21', | |
912 | 'alt_title': 'Dark Walk - Position Music', | |
913 | 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a', | |
914 | 'duration': 133, | |
915 | 'upload_date': '20151119', | |
916 | 'uploader_id': 'IronSoulElf', | |
917 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf', | |
918 | 'uploader': 'IronSoulElf', | |
919 | 'license': 'Standard YouTube License', | |
920 | 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', | |
921 | 'track': 'Dark Walk - Position Music', | |
922 | 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan', | |
923 | }, | |
924 | 'params': { | |
925 | 'skip_download': True, | |
926 | }, | |
927 | }, | |
928 | { | |
929 | # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468) | |
930 | 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8', | |
931 | 'only_matching': True, | |
932 | }, | |
933 | { | |
934 | # Video with yt:stretch=17:0 | |
935 | 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM', | |
936 | 'info_dict': { | |
937 | 'id': 'Q39EVAstoRM', | |
938 | 'ext': 'mp4', | |
939 | 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4', | |
940 | 'description': 'md5:ee18a25c350637c8faff806845bddee9', | |
941 | 'upload_date': '20151107', | |
942 | 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA', | |
943 | 'uploader': 'CH GAMER DROID', | |
944 | }, | |
945 | 'params': { | |
946 | 'skip_download': True, | |
947 | }, | |
948 | 'skip': 'This video does not exist.', | |
949 | }, | |
950 | { | |
951 | # Video licensed under Creative Commons | |
952 | 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA', | |
953 | 'info_dict': { | |
954 | 'id': 'M4gD1WSo5mA', | |
955 | 'ext': 'mp4', | |
956 | 'title': 'md5:e41008789470fc2533a3252216f1c1d1', | |
957 | 'description': 'md5:a677553cf0840649b731a3024aeff4cc', | |
958 | 'duration': 721, | |
959 | 'upload_date': '20150127', | |
960 | 'uploader_id': 'BerkmanCenter', | |
961 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter', | |
962 | 'uploader': 'The Berkman Klein Center for Internet & Society', | |
963 | 'license': 'Creative Commons Attribution license (reuse allowed)', | |
964 | }, | |
965 | 'params': { | |
966 | 'skip_download': True, | |
967 | }, | |
968 | }, | |
969 | { | |
970 | # Channel-like uploader_url | |
971 | 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg', | |
972 | 'info_dict': { | |
973 | 'id': 'eQcmzGIKrzg', | |
974 | 'ext': 'mp4', | |
975 | 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders', | |
976 | 'description': 'md5:dda0d780d5a6e120758d1711d062a867', | |
977 | 'duration': 4060, | |
978 | 'upload_date': '20151119', | |
979 | 'uploader': 'Bernie Sanders', | |
980 | 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg', | |
981 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg', | |
982 | 'license': 'Creative Commons Attribution license (reuse allowed)', | |
983 | }, | |
984 | 'params': { | |
985 | 'skip_download': True, | |
986 | }, | |
987 | }, | |
988 | { | |
989 | 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY', | |
990 | 'only_matching': True, | |
991 | }, | |
992 | { | |
993 | # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059) | |
994 | 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo', | |
995 | 'only_matching': True, | |
996 | }, | |
997 | { | |
998 | # Rental video preview | |
999 | 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg', | |
1000 | 'info_dict': { | |
1001 | 'id': 'uGpuVWrhIzE', | |
1002 | 'ext': 'mp4', | |
1003 | 'title': 'Piku - Trailer', | |
1004 | 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb', | |
1005 | 'upload_date': '20150811', | |
1006 | 'uploader': 'FlixMatrix', | |
1007 | 'uploader_id': 'FlixMatrixKaravan', | |
1008 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan', | |
1009 | 'license': 'Standard YouTube License', | |
1010 | }, | |
1011 | 'params': { | |
1012 | 'skip_download': True, | |
1013 | }, | |
1014 | 'skip': 'This video is not available.', | |
1015 | }, | |
1016 | { | |
1017 | # YouTube Red video with episode data | |
1018 | 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4', | |
1019 | 'info_dict': { | |
1020 | 'id': 'iqKdEhx-dD4', | |
1021 | 'ext': 'mp4', | |
1022 | 'title': 'Isolation - Mind Field (Ep 1)', | |
1023 | 'description': 'md5:25b78d2f64ae81719f5c96319889b736', | |
1024 | 'duration': 2085, | |
1025 | 'upload_date': '20170118', | |
1026 | 'uploader': 'Vsauce', | |
1027 | 'uploader_id': 'Vsauce', | |
1028 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce', | |
1029 | 'license': 'Standard YouTube License', | |
1030 | 'series': 'Mind Field', | |
1031 | 'season_number': 1, | |
1032 | 'episode_number': 1, | |
1033 | }, | |
1034 | 'params': { | |
1035 | 'skip_download': True, | |
1036 | }, | |
1037 | 'expected_warnings': [ | |
1038 | 'Skipping DASH manifest', | |
1039 | ], | |
1040 | }, | |
1041 | { | |
1042 | # The following content has been identified by the YouTube community | |
1043 | # as inappropriate or offensive to some audiences. | |
1044 | 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI', | |
1045 | 'info_dict': { | |
1046 | 'id': '6SJNVb0GnPI', | |
1047 | 'ext': 'mp4', | |
1048 | 'title': 'Race Differences in Intelligence', | |
1049 | 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1', | |
1050 | 'duration': 965, | |
1051 | 'upload_date': '20140124', | |
1052 | 'uploader': 'New Century Foundation', | |
1053 | 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg', | |
1054 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg', | |
1055 | 'license': 'Standard YouTube License', | |
1056 | }, | |
1057 | 'params': { | |
1058 | 'skip_download': True, | |
1059 | }, | |
1060 | }, | |
1061 | { | |
1062 | # itag 212 | |
1063 | 'url': '1t24XAntNCY', | |
1064 | 'only_matching': True, | |
1065 | }, | |
1066 | { | |
1067 | # geo restricted to JP | |
1068 | 'url': 'sJL6WA-aGkQ', | |
1069 | 'only_matching': True, | |
1070 | }, | |
1071 | { | |
1072 | 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', | |
1073 | 'only_matching': True, | |
1074 | }, | |
1075 | { | |
1076 | 'url': 'https://invidio.us/watch?v=BaW_jenozKc', | |
1077 | 'only_matching': True, | |
1078 | }, | |
1079 | ] | |
1080 | ||
1081 | def __init__(self, *args, **kwargs): | |
1082 | super(YoutubeIE, self).__init__(*args, **kwargs) | |
1083 | self._player_cache = {} | |
1084 | ||
1085 | def report_video_info_webpage_download(self, video_id): | |
1086 | """Report attempt to download video info webpage.""" | |
1087 | self.to_screen('%s: Downloading video info webpage' % video_id) | |
1088 | ||
1089 | def report_information_extraction(self, video_id): | |
1090 | """Report attempt to extract video information.""" | |
1091 | self.to_screen('%s: Extracting video information' % video_id) | |
1092 | ||
1093 | def report_unavailable_format(self, video_id, format): | |
1094 | """Report extracted video URL.""" | |
1095 | self.to_screen('%s: Format %s not available' % (video_id, format)) | |
1096 | ||
1097 | def report_rtmp_download(self): | |
1098 | """Indicate the download will use the RTMP protocol.""" | |
1099 | self.to_screen('RTMP download detected') | |
1100 | ||
1101 | def _signature_cache_id(self, example_sig): | |
1102 | """ Return a string representation of a signature """ | |
1103 | return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) | |
1104 | ||
1105 | def _extract_signature_function(self, video_id, player_url, example_sig): | |
1106 | id_m = re.match( | |
1107 | r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$', | |
1108 | player_url) | |
1109 | if not id_m: | |
1110 | raise ExtractorError('Cannot identify player %r' % player_url) | |
1111 | player_type = id_m.group('ext') | |
1112 | player_id = id_m.group('id') | |
1113 | ||
1114 | # Read from filesystem cache | |
1115 | func_id = '%s_%s_%s' % ( | |
1116 | player_type, player_id, self._signature_cache_id(example_sig)) | |
1117 | assert os.path.basename(func_id) == func_id | |
1118 | ||
1119 | cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) | |
1120 | if cache_spec is not None: | |
1121 | return lambda s: ''.join(s[i] for i in cache_spec) | |
1122 | ||
1123 | download_note = ( | |
1124 | 'Downloading player %s' % player_url | |
1125 | if self._downloader.params.get('verbose') else | |
1126 | 'Downloading %s player %s' % (player_type, player_id) | |
1127 | ) | |
1128 | if player_type == 'js': | |
1129 | code = self._download_webpage( | |
1130 | player_url, video_id, | |
1131 | note=download_note, | |
1132 | errnote='Download of %s failed' % player_url) | |
1133 | res = self._parse_sig_js(code) | |
1134 | elif player_type == 'swf': | |
1135 | urlh = self._request_webpage( | |
1136 | player_url, video_id, | |
1137 | note=download_note, | |
1138 | errnote='Download of %s failed' % player_url) | |
1139 | code = urlh.read() | |
1140 | res = self._parse_sig_swf(code) | |
1141 | else: | |
1142 | assert False, 'Invalid player type %r' % player_type | |
1143 | ||
1144 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) | |
1145 | cache_res = res(test_string) | |
1146 | cache_spec = [ord(c) for c in cache_res] | |
1147 | ||
1148 | self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) | |
1149 | return res | |
1150 | ||
1151 | def _print_sig_code(self, func, example_sig): | |
1152 | def gen_sig_code(idxs): | |
1153 | def _genslice(start, end, step): | |
1154 | starts = '' if start == 0 else str(start) | |
1155 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' | |
1156 | steps = '' if step == 1 else (':%d' % step) | |
1157 | return 's[%s%s%s]' % (starts, ends, steps) | |
1158 | ||
1159 | step = None | |
1160 | # Quelch pyflakes warnings - start will be set when step is set | |
1161 | start = '(Never used)' | |
1162 | for i, prev in zip(idxs[1:], idxs[:-1]): | |
1163 | if step is not None: | |
1164 | if i - prev == step: | |
1165 | continue | |
1166 | yield _genslice(start, prev, step) | |
1167 | step = None | |
1168 | continue | |
1169 | if i - prev in [-1, 1]: | |
1170 | step = i - prev | |
1171 | start = prev | |
1172 | continue | |
1173 | else: | |
1174 | yield 's[%d]' % prev | |
1175 | if step is None: | |
1176 | yield 's[%d]' % i | |
1177 | else: | |
1178 | yield _genslice(start, i, step) | |
1179 | ||
1180 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) | |
1181 | cache_res = func(test_string) | |
1182 | cache_spec = [ord(c) for c in cache_res] | |
1183 | expr_code = ' + '.join(gen_sig_code(cache_spec)) | |
1184 | signature_id_tuple = '(%s)' % ( | |
1185 | ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) | |
1186 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' | |
1187 | ' return %s\n') % (signature_id_tuple, expr_code) | |
1188 | self.to_screen('Extracted signature function:\n' + code) | |
1189 | ||
1190 | def _parse_sig_js(self, jscode): | |
1191 | funcname = self._search_regex( | |
1192 | (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1193 | r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(', | |
1194 | r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', | |
1195 | r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\('), | |
1196 | jscode, 'Initial JS player signature function name', group='sig') | |
1197 | ||
1198 | jsi = JSInterpreter(jscode) | |
1199 | initial_function = jsi.extract_function(funcname) | |
1200 | return lambda s: initial_function([s]) | |
1201 | ||
1202 | def _parse_sig_swf(self, file_contents): | |
1203 | swfi = SWFInterpreter(file_contents) | |
1204 | TARGET_CLASSNAME = 'SignatureDecipher' | |
1205 | searched_class = swfi.extract_class(TARGET_CLASSNAME) | |
1206 | initial_function = swfi.extract_function(searched_class, 'decipher') | |
1207 | return lambda s: initial_function([s]) | |
1208 | ||
1209 | def _decrypt_signature(self, s, video_id, player_url, age_gate=False): | |
1210 | """Turn the encrypted s field into a working signature""" | |
1211 | ||
1212 | if player_url is None: | |
1213 | raise ExtractorError('Cannot decrypt signature without player_url') | |
1214 | ||
1215 | if player_url.startswith('//'): | |
1216 | player_url = 'https:' + player_url | |
1217 | elif not re.match(r'https?://', player_url): | |
1218 | player_url = compat_urlparse.urljoin( | |
1219 | 'https://www.youtube.com', player_url) | |
1220 | try: | |
1221 | player_id = (player_url, self._signature_cache_id(s)) | |
1222 | if player_id not in self._player_cache: | |
1223 | func = self._extract_signature_function( | |
1224 | video_id, player_url, s | |
1225 | ) | |
1226 | self._player_cache[player_id] = func | |
1227 | func = self._player_cache[player_id] | |
1228 | if self._downloader.params.get('youtube_print_sig_code'): | |
1229 | self._print_sig_code(func, s) | |
1230 | return func(s) | |
1231 | except Exception as e: | |
1232 | tb = traceback.format_exc() | |
1233 | raise ExtractorError( | |
1234 | 'Signature extraction failed: ' + tb, cause=e) | |
1235 | ||
1236 | def _get_subtitles(self, video_id, webpage): | |
1237 | try: | |
1238 | subs_doc = self._download_xml( | |
1239 | 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, | |
1240 | video_id, note=False) | |
1241 | except ExtractorError as err: | |
1242 | self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err)) | |
1243 | return {} | |
1244 | ||
1245 | sub_lang_list = {} | |
1246 | for track in subs_doc.findall('track'): | |
1247 | lang = track.attrib['lang_code'] | |
1248 | if lang in sub_lang_list: | |
1249 | continue | |
1250 | sub_formats = [] | |
1251 | for ext in self._SUBTITLE_FORMATS: | |
1252 | params = compat_urllib_parse_urlencode({ | |
1253 | 'lang': lang, | |
1254 | 'v': video_id, | |
1255 | 'fmt': ext, | |
1256 | 'name': track.attrib['name'].encode('utf-8'), | |
1257 | }) | |
1258 | sub_formats.append({ | |
1259 | 'url': 'https://www.youtube.com/api/timedtext?' + params, | |
1260 | 'ext': ext, | |
1261 | }) | |
1262 | sub_lang_list[lang] = sub_formats | |
1263 | if not sub_lang_list: | |
1264 | self._downloader.report_warning('video doesn\'t have subtitles') | |
1265 | return {} | |
1266 | return sub_lang_list | |
1267 | ||
1268 | def _get_ytplayer_config(self, video_id, webpage): | |
1269 | patterns = ( | |
1270 | # User data may contain arbitrary character sequences that may affect | |
1271 | # JSON extraction with regex, e.g. when '};' is contained the second | |
1272 | # regex won't capture the whole JSON. Yet working around by trying more | |
1273 | # concrete regex first keeping in mind proper quoted string handling | |
1274 | # to be implemented in future that will replace this workaround (see | |
1275 | # https://github.com/rg3/youtube-dl/issues/7468, | |
1276 | # https://github.com/rg3/youtube-dl/pull/7599) | |
1277 | r';ytplayer\.config\s*=\s*({.+?});ytplayer', | |
1278 | r';ytplayer\.config\s*=\s*({.+?});', | |
1279 | ) | |
1280 | config = self._search_regex( | |
1281 | patterns, webpage, 'ytplayer.config', default=None) | |
1282 | if config: | |
1283 | return self._parse_json( | |
1284 | uppercase_escape(config), video_id, fatal=False) | |
1285 | ||
1286 | def _get_automatic_captions(self, video_id, webpage): | |
1287 | """We need the webpage for getting the captions url, pass it as an | |
1288 | argument to speed up the process.""" | |
1289 | self.to_screen('%s: Looking for automatic captions' % video_id) | |
1290 | player_config = self._get_ytplayer_config(video_id, webpage) | |
1291 | err_msg = 'Couldn\'t find automatic captions for %s' % video_id | |
1292 | if not player_config: | |
1293 | self._downloader.report_warning(err_msg) | |
1294 | return {} | |
1295 | try: | |
1296 | args = player_config['args'] | |
1297 | caption_url = args.get('ttsurl') | |
1298 | if caption_url: | |
1299 | timestamp = args['timestamp'] | |
1300 | # We get the available subtitles | |
1301 | list_params = compat_urllib_parse_urlencode({ | |
1302 | 'type': 'list', | |
1303 | 'tlangs': 1, | |
1304 | 'asrs': 1, | |
1305 | }) | |
1306 | list_url = caption_url + '&' + list_params | |
1307 | caption_list = self._download_xml(list_url, video_id) | |
1308 | original_lang_node = caption_list.find('track') | |
1309 | if original_lang_node is None: | |
1310 | self._downloader.report_warning('Video doesn\'t have automatic captions') | |
1311 | return {} | |
1312 | original_lang = original_lang_node.attrib['lang_code'] | |
1313 | caption_kind = original_lang_node.attrib.get('kind', '') | |
1314 | ||
1315 | sub_lang_list = {} | |
1316 | for lang_node in caption_list.findall('target'): | |
1317 | sub_lang = lang_node.attrib['lang_code'] | |
1318 | sub_formats = [] | |
1319 | for ext in self._SUBTITLE_FORMATS: | |
1320 | params = compat_urllib_parse_urlencode({ | |
1321 | 'lang': original_lang, | |
1322 | 'tlang': sub_lang, | |
1323 | 'fmt': ext, | |
1324 | 'ts': timestamp, | |
1325 | 'kind': caption_kind, | |
1326 | }) | |
1327 | sub_formats.append({ | |
1328 | 'url': caption_url + '&' + params, | |
1329 | 'ext': ext, | |
1330 | }) | |
1331 | sub_lang_list[sub_lang] = sub_formats | |
1332 | return sub_lang_list | |
1333 | ||
1334 | def make_captions(sub_url, sub_langs): | |
1335 | parsed_sub_url = compat_urllib_parse_urlparse(sub_url) | |
1336 | caption_qs = compat_parse_qs(parsed_sub_url.query) | |
1337 | captions = {} | |
1338 | for sub_lang in sub_langs: | |
1339 | sub_formats = [] | |
1340 | for ext in self._SUBTITLE_FORMATS: | |
1341 | caption_qs.update({ | |
1342 | 'tlang': [sub_lang], | |
1343 | 'fmt': [ext], | |
1344 | }) | |
1345 | sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace( | |
1346 | query=compat_urllib_parse_urlencode(caption_qs, True))) | |
1347 | sub_formats.append({ | |
1348 | 'url': sub_url, | |
1349 | 'ext': ext, | |
1350 | }) | |
1351 | captions[sub_lang] = sub_formats | |
1352 | return captions | |
1353 | ||
1354 | # New captions format as of 22.06.2017 | |
1355 | player_response = args.get('player_response') | |
1356 | if player_response and isinstance(player_response, compat_str): | |
1357 | player_response = self._parse_json( | |
1358 | player_response, video_id, fatal=False) | |
1359 | if player_response: | |
1360 | renderer = player_response['captions']['playerCaptionsTracklistRenderer'] | |
1361 | base_url = renderer['captionTracks'][0]['baseUrl'] | |
1362 | sub_lang_list = [] | |
1363 | for lang in renderer['translationLanguages']: | |
1364 | lang_code = lang.get('languageCode') | |
1365 | if lang_code: | |
1366 | sub_lang_list.append(lang_code) | |
1367 | return make_captions(base_url, sub_lang_list) | |
1368 | ||
1369 | # Some videos don't provide ttsurl but rather caption_tracks and | |
1370 | # caption_translation_languages (e.g. 20LmZk1hakA) | |
1371 | # Does not used anymore as of 22.06.2017 | |
1372 | caption_tracks = args['caption_tracks'] | |
1373 | caption_translation_languages = args['caption_translation_languages'] | |
1374 | caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0] | |
1375 | sub_lang_list = [] | |
1376 | for lang in caption_translation_languages.split(','): | |
1377 | lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang)) | |
1378 | sub_lang = lang_qs.get('lc', [None])[0] | |
1379 | if sub_lang: | |
1380 | sub_lang_list.append(sub_lang) | |
1381 | return make_captions(caption_url, sub_lang_list) | |
1382 | # An extractor error can be raise by the download process if there are | |
1383 | # no automatic captions but there are subtitles | |
1384 | except (KeyError, IndexError, ExtractorError): | |
1385 | self._downloader.report_warning(err_msg) | |
1386 | return {} | |
1387 | ||
1388 | def _mark_watched(self, video_id, video_info): | |
1389 | playback_url = video_info.get('videostats_playback_base_url', [None])[0] | |
1390 | if not playback_url: | |
1391 | return | |
1392 | parsed_playback_url = compat_urlparse.urlparse(playback_url) | |
1393 | qs = compat_urlparse.parse_qs(parsed_playback_url.query) | |
1394 | ||
1395 | # cpn generation algorithm is reverse engineered from base.js. | |
1396 | # In fact it works even with dummy cpn. | |
1397 | CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_' | |
1398 | cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))) | |
1399 | ||
1400 | qs.update({ | |
1401 | 'ver': ['2'], | |
1402 | 'cpn': [cpn], | |
1403 | }) | |
1404 | playback_url = compat_urlparse.urlunparse( | |
1405 | parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True))) | |
1406 | ||
1407 | self._download_webpage( | |
1408 | playback_url, video_id, 'Marking watched', | |
1409 | 'Unable to mark watched', fatal=False) | |
1410 | ||
1411 | @staticmethod | |
1412 | def _extract_urls(webpage): | |
1413 | # Embedded YouTube player | |
1414 | entries = [ | |
1415 | unescapeHTML(mobj.group('url')) | |
1416 | for mobj in re.finditer(r'''(?x) | |
1417 | (?: | |
1418 | <iframe[^>]+?src=| | |
1419 | data-video-url=| | |
1420 | <embed[^>]+?src=| | |
1421 | embedSWF\(?:\s*| | |
1422 | <object[^>]+data=| | |
1423 | new\s+SWFObject\( | |
1424 | ) | |
1425 | (["\']) | |
1426 | (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/ | |
1427 | (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?) | |
1428 | \1''', webpage)] | |
1429 | ||
1430 | # lazyYT YouTube embed | |
1431 | entries.extend(list(map( | |
1432 | unescapeHTML, | |
1433 | re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage)))) | |
1434 | ||
1435 | # Wordpress "YouTube Video Importer" plugin | |
1436 | matches = re.findall(r'''(?x)<div[^>]+ | |
1437 | class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+ | |
1438 | data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage) | |
1439 | entries.extend(m[-1] for m in matches) | |
1440 | ||
1441 | return entries | |
1442 | ||
1443 | @staticmethod | |
1444 | def _extract_url(webpage): | |
1445 | urls = YoutubeIE._extract_urls(webpage) | |
1446 | return urls[0] if urls else None | |
1447 | ||
1448 | @classmethod | |
1449 | def extract_id(cls, url): | |
1450 | mobj = re.match(cls._VALID_URL, url, re.VERBOSE) | |
1451 | if mobj is None: | |
1452 | raise ExtractorError('Invalid URL: %s' % url) | |
1453 | video_id = mobj.group(2) | |
1454 | return video_id | |
1455 | ||
1456 | def _extract_annotations(self, video_id): | |
1457 | url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id | |
1458 | return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.') | |
1459 | ||
1460 | @staticmethod | |
1461 | def _extract_chapters(description, duration): | |
1462 | if not description: | |
1463 | return None | |
1464 | chapter_lines = re.findall( | |
1465 | r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)', | |
1466 | description) | |
1467 | if not chapter_lines: | |
1468 | return None | |
1469 | chapters = [] | |
1470 | for next_num, (chapter_line, time_point) in enumerate( | |
1471 | chapter_lines, start=1): | |
1472 | start_time = parse_duration(time_point) | |
1473 | if start_time is None: | |
1474 | continue | |
1475 | if start_time > duration: | |
1476 | break | |
1477 | end_time = (duration if next_num == len(chapter_lines) | |
1478 | else parse_duration(chapter_lines[next_num][1])) | |
1479 | if end_time is None: | |
1480 | continue | |
1481 | if end_time > duration: | |
1482 | end_time = duration | |
1483 | if start_time > end_time: | |
1484 | break | |
1485 | chapter_title = re.sub( | |
1486 | r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-') | |
1487 | chapter_title = re.sub(r'\s+', ' ', chapter_title) | |
1488 | chapters.append({ | |
1489 | 'start_time': start_time, | |
1490 | 'end_time': end_time, | |
1491 | 'title': chapter_title, | |
1492 | }) | |
1493 | return chapters | |
1494 | ||
1495 | def _real_extract(self, url): | |
1496 | url, smuggled_data = unsmuggle_url(url, {}) | |
1497 | ||
1498 | proto = ( | |
1499 | 'http' if self._downloader.params.get('prefer_insecure', False) | |
1500 | else 'https') | |
1501 | ||
1502 | start_time = None | |
1503 | end_time = None | |
1504 | parsed_url = compat_urllib_parse_urlparse(url) | |
1505 | for component in [parsed_url.fragment, parsed_url.query]: | |
1506 | query = compat_parse_qs(component) | |
1507 | if start_time is None and 't' in query: | |
1508 | start_time = parse_duration(query['t'][0]) | |
1509 | if start_time is None and 'start' in query: | |
1510 | start_time = parse_duration(query['start'][0]) | |
1511 | if end_time is None and 'end' in query: | |
1512 | end_time = parse_duration(query['end'][0]) | |
1513 | ||
1514 | # Extract original video URL from URL with redirection, like age verification, using next_url parameter | |
1515 | mobj = re.search(self._NEXT_URL_RE, url) | |
1516 | if mobj: | |
1517 | url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/') | |
1518 | video_id = self.extract_id(url) | |
1519 | ||
1520 | # Get video webpage | |
1521 | url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id | |
1522 | video_webpage = self._download_webpage(url, video_id) | |
1523 | ||
1524 | # Attempt to extract SWF player URL | |
1525 | mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) | |
1526 | if mobj is not None: | |
1527 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) | |
1528 | else: | |
1529 | player_url = None | |
1530 | ||
1531 | dash_mpds = [] | |
1532 | ||
1533 | def add_dash_mpd(video_info): | |
1534 | dash_mpd = video_info.get('dashmpd') | |
1535 | if dash_mpd and dash_mpd[0] not in dash_mpds: | |
1536 | dash_mpds.append(dash_mpd[0]) | |
1537 | ||
1538 | is_live = None | |
1539 | view_count = None | |
1540 | ||
1541 | def extract_view_count(v_info): | |
1542 | return int_or_none(try_get(v_info, lambda x: x['view_count'][0])) | |
1543 | ||
1544 | player_response = {} | |
1545 | ||
1546 | # Get video info | |
1547 | embed_webpage = None | |
1548 | if re.search(r'player-age-gate-content">', video_webpage) is not None: | |
1549 | age_gate = True | |
1550 | # We simulate the access to the video from www.youtube.com/v/{video_id} | |
1551 | # this can be viewed without login into Youtube | |
1552 | url = proto + '://www.youtube.com/embed/%s' % video_id | |
1553 | embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage') | |
1554 | data = compat_urllib_parse_urlencode({ | |
1555 | 'video_id': video_id, | |
1556 | 'eurl': 'https://youtube.googleapis.com/v/' + video_id, | |
1557 | 'sts': self._search_regex( | |
1558 | r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''), | |
1559 | }) | |
1560 | video_info_url = proto + '://www.youtube.com/get_video_info?' + data | |
1561 | video_info_webpage = self._download_webpage( | |
1562 | video_info_url, video_id, | |
1563 | note='Refetching age-gated info webpage', | |
1564 | errnote='unable to download video info webpage') | |
1565 | video_info = compat_parse_qs(video_info_webpage) | |
1566 | add_dash_mpd(video_info) | |
1567 | else: | |
1568 | age_gate = False | |
1569 | video_info = None | |
1570 | sts = None | |
1571 | # Try looking directly into the video webpage | |
1572 | ytplayer_config = self._get_ytplayer_config(video_id, video_webpage) | |
1573 | if ytplayer_config: | |
1574 | args = ytplayer_config['args'] | |
1575 | if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'): | |
1576 | # Convert to the same format returned by compat_parse_qs | |
1577 | video_info = dict((k, [v]) for k, v in args.items()) | |
1578 | add_dash_mpd(video_info) | |
1579 | # Rental video is not rented but preview is available (e.g. | |
1580 | # https://www.youtube.com/watch?v=yYr8q0y5Jfg, | |
1581 | # https://github.com/rg3/youtube-dl/issues/10532) | |
1582 | if not video_info and args.get('ypc_vid'): | |
1583 | return self.url_result( | |
1584 | args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid']) | |
1585 | if args.get('livestream') == '1' or args.get('live_playback') == 1: | |
1586 | is_live = True | |
1587 | sts = ytplayer_config.get('sts') | |
1588 | if not player_response: | |
1589 | pl_response = str_or_none(args.get('player_response')) | |
1590 | if pl_response: | |
1591 | pl_response = self._parse_json(pl_response, video_id, fatal=False) | |
1592 | if isinstance(pl_response, dict): | |
1593 | player_response = pl_response | |
1594 | if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): | |
1595 | # We also try looking in get_video_info since it may contain different dashmpd | |
1596 | # URL that points to a DASH manifest with possibly different itag set (some itags | |
1597 | # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH | |
1598 | # manifest pointed by get_video_info's dashmpd). | |
1599 | # The general idea is to take a union of itags of both DASH manifests (for example | |
1600 | # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093) | |
1601 | self.report_video_info_webpage_download(video_id) | |
1602 | for el in ('info', 'embedded', 'detailpage', 'vevo', ''): | |
1603 | query = { | |
1604 | 'video_id': video_id, | |
1605 | 'ps': 'default', | |
1606 | 'eurl': '', | |
1607 | 'gl': 'US', | |
1608 | 'hl': 'en', | |
1609 | } | |
1610 | if el: | |
1611 | query['el'] = el | |
1612 | if sts: | |
1613 | query['sts'] = sts | |
1614 | video_info_webpage = self._download_webpage( | |
1615 | '%s://www.youtube.com/get_video_info' % proto, | |
1616 | video_id, note=False, | |
1617 | errnote='unable to download video info webpage', | |
1618 | fatal=False, query=query) | |
1619 | if not video_info_webpage: | |
1620 | continue | |
1621 | get_video_info = compat_parse_qs(video_info_webpage) | |
1622 | if not player_response: | |
1623 | pl_response = get_video_info.get('player_response', [None])[0] | |
1624 | if isinstance(pl_response, dict): | |
1625 | player_response = pl_response | |
1626 | add_dash_mpd(get_video_info) | |
1627 | if view_count is None: | |
1628 | view_count = extract_view_count(get_video_info) | |
1629 | if not video_info: | |
1630 | video_info = get_video_info | |
1631 | if 'token' in get_video_info: | |
1632 | # Different get_video_info requests may report different results, e.g. | |
1633 | # some may report video unavailability, but some may serve it without | |
1634 | # any complaint (see https://github.com/rg3/youtube-dl/issues/7362, | |
1635 | # the original webpage as well as el=info and el=embedded get_video_info | |
1636 | # requests report video unavailability due to geo restriction while | |
1637 | # el=detailpage succeeds and returns valid data). This is probably | |
1638 | # due to YouTube measures against IP ranges of hosting providers. | |
1639 | # Working around by preferring the first succeeded video_info containing | |
1640 | # the token if no such video_info yet was found. | |
1641 | if 'token' not in video_info: | |
1642 | video_info = get_video_info | |
1643 | break | |
1644 | ||
1645 | def extract_unavailable_message(): | |
1646 | return self._html_search_regex( | |
1647 | r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>', | |
1648 | video_webpage, 'unavailable message', default=None) | |
1649 | ||
1650 | if 'token' not in video_info: | |
1651 | if 'reason' in video_info: | |
1652 | if 'The uploader has not made this video available in your country.' in video_info['reason']: | |
1653 | regions_allowed = self._html_search_meta( | |
1654 | 'regionsAllowed', video_webpage, default=None) | |
1655 | countries = regions_allowed.split(',') if regions_allowed else None | |
1656 | self.raise_geo_restricted( | |
1657 | msg=video_info['reason'][0], countries=countries) | |
1658 | reason = video_info['reason'][0] | |
1659 | if 'Invalid parameters' in reason: | |
1660 | unavailable_message = extract_unavailable_message() | |
1661 | if unavailable_message: | |
1662 | reason = unavailable_message | |
1663 | raise ExtractorError( | |
1664 | 'YouTube said: %s' % reason, | |
1665 | expected=True, video_id=video_id) | |
1666 | else: | |
1667 | raise ExtractorError( | |
1668 | '"token" parameter not in video info for unknown reason', | |
1669 | video_id=video_id) | |
1670 | ||
1671 | video_details = try_get( | |
1672 | player_response, lambda x: x['videoDetails'], dict) or {} | |
1673 | ||
1674 | # title | |
1675 | if 'title' in video_info: | |
1676 | video_title = video_info['title'][0] | |
1677 | elif 'title' in player_response: | |
1678 | video_title = video_details['title'] | |
1679 | else: | |
1680 | self._downloader.report_warning('Unable to extract video title') | |
1681 | video_title = '_' | |
1682 | ||
1683 | # description | |
1684 | description_original = video_description = get_element_by_id("eow-description", video_webpage) | |
1685 | if video_description: | |
1686 | ||
1687 | def replace_url(m): | |
1688 | redir_url = compat_urlparse.urljoin(url, m.group(1)) | |
1689 | parsed_redir_url = compat_urllib_parse_urlparse(redir_url) | |
1690 | if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect': | |
1691 | qs = compat_parse_qs(parsed_redir_url.query) | |
1692 | q = qs.get('q') | |
1693 | if q and q[0]: | |
1694 | return q[0] | |
1695 | return redir_url | |
1696 | ||
1697 | description_original = video_description = re.sub(r'''(?x) | |
1698 | <a\s+ | |
1699 | (?:[a-zA-Z-]+="[^"]*"\s+)*? | |
1700 | (?:title|href)="([^"]+)"\s+ | |
1701 | (?:[a-zA-Z-]+="[^"]*"\s+)*? | |
1702 | class="[^"]*"[^>]*> | |
1703 | [^<]+\.{3}\s* | |
1704 | </a> | |
1705 | ''', replace_url, video_description) | |
1706 | video_description = clean_html(video_description) | |
1707 | else: | |
1708 | fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage) | |
1709 | if fd_mobj: | |
1710 | video_description = unescapeHTML(fd_mobj.group(1)) | |
1711 | else: | |
1712 | video_description = '' | |
1713 | ||
1714 | if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False): | |
1715 | if not self._downloader.params.get('noplaylist'): | |
1716 | entries = [] | |
1717 | feed_ids = [] | |
1718 | multifeed_metadata_list = video_info['multifeed_metadata_list'][0] | |
1719 | for feed in multifeed_metadata_list.split(','): | |
1720 | # Unquote should take place before split on comma (,) since textual | |
1721 | # fields may contain comma as well (see | |
1722 | # https://github.com/rg3/youtube-dl/issues/8536) | |
1723 | feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed)) | |
1724 | entries.append({ | |
1725 | '_type': 'url_transparent', | |
1726 | 'ie_key': 'Youtube', | |
1727 | 'url': smuggle_url( | |
1728 | '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]), | |
1729 | {'force_singlefeed': True}), | |
1730 | 'title': '%s (%s)' % (video_title, feed_data['title'][0]), | |
1731 | }) | |
1732 | feed_ids.append(feed_data['id'][0]) | |
1733 | self.to_screen( | |
1734 | 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' | |
1735 | % (', '.join(feed_ids), video_id)) | |
1736 | return self.playlist_result(entries, video_id, video_title, video_description) | |
1737 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
1738 | ||
1739 | if view_count is None: | |
1740 | view_count = extract_view_count(video_info) | |
1741 | if view_count is None and video_details: | |
1742 | view_count = int_or_none(video_details.get('viewCount')) | |
1743 | ||
1744 | # Check for "rental" videos | |
1745 | if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: | |
1746 | raise ExtractorError('"rental" videos not supported. See https://github.com/rg3/youtube-dl/issues/359 for more information.', expected=True) | |
1747 | ||
1748 | def _extract_filesize(media_url): | |
1749 | return int_or_none(self._search_regex( | |
1750 | r'\bclen[=/](\d+)', media_url, 'filesize', default=None)) | |
1751 | ||
1752 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): | |
1753 | self.report_rtmp_download() | |
1754 | formats = [{ | |
1755 | 'format_id': '_rtmp', | |
1756 | 'protocol': 'rtmp', | |
1757 | 'url': video_info['conn'][0], | |
1758 | 'player_url': player_url, | |
1759 | }] | |
1760 | 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): | |
1761 | encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] | |
1762 | if 'rtmpe%3Dyes' in encoded_url_map: | |
1763 | raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True) | |
1764 | formats_spec = {} | |
1765 | fmt_list = video_info.get('fmt_list', [''])[0] | |
1766 | if fmt_list: | |
1767 | for fmt in fmt_list.split(','): | |
1768 | spec = fmt.split('/') | |
1769 | if len(spec) > 1: | |
1770 | width_height = spec[1].split('x') | |
1771 | if len(width_height) == 2: | |
1772 | formats_spec[spec[0]] = { | |
1773 | 'resolution': spec[1], | |
1774 | 'width': int_or_none(width_height[0]), | |
1775 | 'height': int_or_none(width_height[1]), | |
1776 | } | |
1777 | q = qualities(['small', 'medium', 'hd720']) | |
1778 | formats = [] | |
1779 | for url_data_str in encoded_url_map.split(','): | |
1780 | url_data = compat_parse_qs(url_data_str) | |
1781 | if 'itag' not in url_data or 'url' not in url_data: | |
1782 | continue | |
1783 | format_id = url_data['itag'][0] | |
1784 | url = url_data['url'][0] | |
1785 | ||
1786 | if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True): | |
1787 | ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' | |
1788 | jsplayer_url_json = self._search_regex( | |
1789 | ASSETS_RE, | |
1790 | embed_webpage if age_gate else video_webpage, | |
1791 | 'JS player URL (1)', default=None) | |
1792 | if not jsplayer_url_json and not age_gate: | |
1793 | # We need the embed website after all | |
1794 | if embed_webpage is None: | |
1795 | embed_url = proto + '://www.youtube.com/embed/%s' % video_id | |
1796 | embed_webpage = self._download_webpage( | |
1797 | embed_url, video_id, 'Downloading embed webpage') | |
1798 | jsplayer_url_json = self._search_regex( | |
1799 | ASSETS_RE, embed_webpage, 'JS player URL') | |
1800 | ||
1801 | player_url = json.loads(jsplayer_url_json) | |
1802 | if player_url is None: | |
1803 | player_url_json = self._search_regex( | |
1804 | r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', | |
1805 | video_webpage, 'age gate player URL') | |
1806 | player_url = json.loads(player_url_json) | |
1807 | ||
1808 | if 'sig' in url_data: | |
1809 | url += '&signature=' + url_data['sig'][0] | |
1810 | elif 's' in url_data: | |
1811 | encrypted_sig = url_data['s'][0] | |
1812 | ||
1813 | if self._downloader.params.get('verbose'): | |
1814 | if player_url is None: | |
1815 | player_version = 'unknown' | |
1816 | player_desc = 'unknown' | |
1817 | else: | |
1818 | if player_url.endswith('swf'): | |
1819 | player_version = self._search_regex( | |
1820 | r'-(.+?)(?:/watch_as3)?\.swf$', player_url, | |
1821 | 'flash player', fatal=False) | |
1822 | player_desc = 'flash player %s' % player_version | |
1823 | else: | |
1824 | player_version = self._search_regex( | |
1825 | [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', | |
1826 | r'(?:www|player)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'], | |
1827 | player_url, | |
1828 | 'html5 player', fatal=False) | |
1829 | player_desc = 'html5 player %s' % player_version | |
1830 | ||
1831 | parts_sizes = self._signature_cache_id(encrypted_sig) | |
1832 | self.to_screen('{%s} signature length %s, %s' % | |
1833 | (format_id, parts_sizes, player_desc)) | |
1834 | ||
1835 | signature = self._decrypt_signature( | |
1836 | encrypted_sig, video_id, player_url, age_gate) | |
1837 | url += '&signature=' + signature | |
1838 | if 'ratebypass' not in url: | |
1839 | url += '&ratebypass=yes' | |
1840 | ||
1841 | dct = { | |
1842 | 'format_id': format_id, | |
1843 | 'url': url, | |
1844 | 'player_url': player_url, | |
1845 | } | |
1846 | if format_id in self._formats: | |
1847 | dct.update(self._formats[format_id]) | |
1848 | if format_id in formats_spec: | |
1849 | dct.update(formats_spec[format_id]) | |
1850 | ||
1851 | # Some itags are not included in DASH manifest thus corresponding formats will | |
1852 | # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993). | |
1853 | # Trying to extract metadata from url_encoded_fmt_stream_map entry. | |
1854 | mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0]) | |
1855 | width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None) | |
1856 | ||
1857 | filesize = int_or_none(url_data.get( | |
1858 | 'clen', [None])[0]) or _extract_filesize(url) | |
1859 | ||
1860 | quality = url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0] | |
1861 | ||
1862 | more_fields = { | |
1863 | 'filesize': filesize, | |
1864 | 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000), | |
1865 | 'width': width, | |
1866 | 'height': height, | |
1867 | 'fps': int_or_none(url_data.get('fps', [None])[0]), | |
1868 | 'format_note': quality, | |
1869 | 'quality': q(quality), | |
1870 | } | |
1871 | for key, value in more_fields.items(): | |
1872 | if value: | |
1873 | dct[key] = value | |
1874 | type_ = url_data.get('type', [None])[0] | |
1875 | if type_: | |
1876 | type_split = type_.split(';') | |
1877 | kind_ext = type_split[0].split('/') | |
1878 | if len(kind_ext) == 2: | |
1879 | kind, _ = kind_ext | |
1880 | dct['ext'] = mimetype2ext(type_split[0]) | |
1881 | if kind in ('audio', 'video'): | |
1882 | codecs = None | |
1883 | for mobj in re.finditer( | |
1884 | r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_): | |
1885 | if mobj.group('key') == 'codecs': | |
1886 | codecs = mobj.group('val') | |
1887 | break | |
1888 | if codecs: | |
1889 | dct.update(parse_codecs(codecs)) | |
1890 | if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none': | |
1891 | dct['downloader_options'] = { | |
1892 | # Youtube throttles chunks >~10M | |
1893 | 'http_chunk_size': 10485760, | |
1894 | } | |
1895 | formats.append(dct) | |
1896 | elif video_info.get('hlsvp'): | |
1897 | manifest_url = video_info['hlsvp'][0] | |
1898 | formats = [] | |
1899 | m3u8_formats = self._extract_m3u8_formats( | |
1900 | manifest_url, video_id, 'mp4', fatal=False) | |
1901 | for a_format in m3u8_formats: | |
1902 | itag = self._search_regex( | |
1903 | r'/itag/(\d+)/', a_format['url'], 'itag', default=None) | |
1904 | if itag: | |
1905 | a_format['format_id'] = itag | |
1906 | if itag in self._formats: | |
1907 | dct = self._formats[itag].copy() | |
1908 | dct.update(a_format) | |
1909 | a_format = dct | |
1910 | a_format['player_url'] = player_url | |
1911 | # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming | |
1912 | a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True' | |
1913 | formats.append(a_format) | |
1914 | else: | |
1915 | error_message = clean_html(video_info.get('reason', [None])[0]) | |
1916 | if not error_message: | |
1917 | error_message = extract_unavailable_message() | |
1918 | if error_message: | |
1919 | raise ExtractorError(error_message, expected=True) | |
1920 | raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') | |
1921 | ||
1922 | # uploader | |
1923 | video_uploader = try_get( | |
1924 | video_info, lambda x: x['author'][0], | |
1925 | compat_str) or str_or_none(video_details.get('author')) | |
1926 | if video_uploader: | |
1927 | video_uploader = compat_urllib_parse_unquote_plus(video_uploader) | |
1928 | else: | |
1929 | self._downloader.report_warning('unable to extract uploader name') | |
1930 | ||
1931 | # uploader_id | |
1932 | video_uploader_id = None | |
1933 | video_uploader_url = None | |
1934 | mobj = re.search( | |
1935 | r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">', | |
1936 | video_webpage) | |
1937 | if mobj is not None: | |
1938 | video_uploader_id = mobj.group('uploader_id') | |
1939 | video_uploader_url = mobj.group('uploader_url') | |
1940 | else: | |
1941 | self._downloader.report_warning('unable to extract uploader nickname') | |
1942 | ||
1943 | channel_id = self._html_search_meta( | |
1944 | 'channelId', video_webpage, 'channel id') | |
1945 | channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None | |
1946 | ||
1947 | # thumbnail image | |
1948 | # We try first to get a high quality image: | |
1949 | m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">', | |
1950 | video_webpage, re.DOTALL) | |
1951 | if m_thumb is not None: | |
1952 | video_thumbnail = m_thumb.group(1) | |
1953 | elif 'thumbnail_url' not in video_info: | |
1954 | self._downloader.report_warning('unable to extract video thumbnail') | |
1955 | video_thumbnail = None | |
1956 | else: # don't panic if we can't find it | |
1957 | video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0]) | |
1958 | ||
1959 | # upload date | |
1960 | upload_date = self._html_search_meta( | |
1961 | 'datePublished', video_webpage, 'upload date', default=None) | |
1962 | if not upload_date: | |
1963 | upload_date = self._search_regex( | |
1964 | [r'(?s)id="eow-date.*?>(.*?)</span>', | |
1965 | r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'], | |
1966 | video_webpage, 'upload date', default=None) | |
1967 | upload_date = unified_strdate(upload_date) | |
1968 | ||
1969 | video_license = self._html_search_regex( | |
1970 | r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li', | |
1971 | video_webpage, 'license', default=None) | |
1972 | ||
1973 | m_music = re.search( | |
1974 | r'''(?x) | |
1975 | <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s* | |
1976 | <ul[^>]*>\s* | |
1977 | <li>(?P<title>.+?) | |
1978 | by (?P<creator>.+?) | |
1979 | (?: | |
1980 | \(.+?\)| | |
1981 | <a[^>]* | |
1982 | (?: | |
1983 | \bhref=["\']/red[^>]*>| # drop possible | |
1984 | >\s*Listen ad-free with YouTube Red # YouTube Red ad | |
1985 | ) | |
1986 | .*? | |
1987 | )?</li | |
1988 | ''', | |
1989 | video_webpage) | |
1990 | if m_music: | |
1991 | video_alt_title = remove_quotes(unescapeHTML(m_music.group('title'))) | |
1992 | video_creator = clean_html(m_music.group('creator')) | |
1993 | else: | |
1994 | video_alt_title = video_creator = None | |
1995 | ||
1996 | def extract_meta(field): | |
1997 | return self._html_search_regex( | |
1998 | r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field, | |
1999 | video_webpage, field, default=None) | |
2000 | ||
2001 | track = extract_meta('Song') | |
2002 | artist = extract_meta('Artist') | |
2003 | ||
2004 | m_episode = re.search( | |
2005 | r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>', | |
2006 | video_webpage) | |
2007 | if m_episode: | |
2008 | series = m_episode.group('series') | |
2009 | season_number = int(m_episode.group('season')) | |
2010 | episode_number = int(m_episode.group('episode')) | |
2011 | else: | |
2012 | series = season_number = episode_number = None | |
2013 | ||
2014 | m_cat_container = self._search_regex( | |
2015 | r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', | |
2016 | video_webpage, 'categories', default=None) | |
2017 | if m_cat_container: | |
2018 | category = self._html_search_regex( | |
2019 | r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', | |
2020 | default=None) | |
2021 | video_categories = None if category is None else [category] | |
2022 | else: | |
2023 | video_categories = None | |
2024 | ||
2025 | video_tags = [ | |
2026 | unescapeHTML(m.group('content')) | |
2027 | for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)] | |
2028 | ||
2029 | def _extract_count(count_name): | |
2030 | return str_to_int(self._search_regex( | |
2031 | r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>' | |
2032 | % re.escape(count_name), | |
2033 | video_webpage, count_name, default=None)) | |
2034 | ||
2035 | like_count = _extract_count('like') | |
2036 | dislike_count = _extract_count('dislike') | |
2037 | ||
2038 | if view_count is None: | |
2039 | view_count = str_to_int(self._search_regex( | |
2040 | r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage, | |
2041 | 'view count', default=None)) | |
2042 | ||
2043 | # subtitles | |
2044 | video_subtitles = self.extract_subtitles(video_id, video_webpage) | |
2045 | automatic_captions = self.extract_automatic_captions(video_id, video_webpage) | |
2046 | ||
2047 | video_duration = try_get( | |
2048 | video_info, lambda x: int_or_none(x['length_seconds'][0])) | |
2049 | if not video_duration: | |
2050 | video_duration = int_or_none(video_details.get('lengthSeconds')) | |
2051 | if not video_duration: | |
2052 | video_duration = parse_duration(self._html_search_meta( | |
2053 | 'duration', video_webpage, 'video duration')) | |
2054 | ||
2055 | # annotations | |
2056 | video_annotations = None | |
2057 | if self._downloader.params.get('writeannotations', False): | |
2058 | video_annotations = self._extract_annotations(video_id) | |
2059 | ||
2060 | chapters = self._extract_chapters(description_original, video_duration) | |
2061 | ||
2062 | # Look for the DASH manifest | |
2063 | if self._downloader.params.get('youtube_include_dash_manifest', True): | |
2064 | dash_mpd_fatal = True | |
2065 | for mpd_url in dash_mpds: | |
2066 | dash_formats = {} | |
2067 | try: | |
2068 | def decrypt_sig(mobj): | |
2069 | s = mobj.group(1) | |
2070 | dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) | |
2071 | return '/signature/%s' % dec_s | |
2072 | ||
2073 | mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url) | |
2074 | ||
2075 | for df in self._extract_mpd_formats( | |
2076 | mpd_url, video_id, fatal=dash_mpd_fatal, | |
2077 | formats_dict=self._formats): | |
2078 | if not df.get('filesize'): | |
2079 | df['filesize'] = _extract_filesize(df['url']) | |
2080 | # Do not overwrite DASH format found in some previous DASH manifest | |
2081 | if df['format_id'] not in dash_formats: | |
2082 | dash_formats[df['format_id']] = df | |
2083 | # Additional DASH manifests may end up in HTTP Error 403 therefore | |
2084 | # allow them to fail without bug report message if we already have | |
2085 | # some DASH manifest succeeded. This is temporary workaround to reduce | |
2086 | # burst of bug reports until we figure out the reason and whether it | |
2087 | # can be fixed at all. | |
2088 | dash_mpd_fatal = False | |
2089 | except (ExtractorError, KeyError) as e: | |
2090 | self.report_warning( | |
2091 | 'Skipping DASH manifest: %r' % e, video_id) | |
2092 | if dash_formats: | |
2093 | # Remove the formats we found through non-DASH, they | |
2094 | # contain less info and it can be wrong, because we use | |
2095 | # fixed values (for example the resolution). See | |
2096 | # https://github.com/rg3/youtube-dl/issues/5774 for an | |
2097 | # example. | |
2098 | formats = [f for f in formats if f['format_id'] not in dash_formats.keys()] | |
2099 | formats.extend(dash_formats.values()) | |
2100 | ||
2101 | # Check for malformed aspect ratio | |
2102 | stretched_m = re.search( | |
2103 | r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">', | |
2104 | video_webpage) | |
2105 | if stretched_m: | |
2106 | w = float(stretched_m.group('w')) | |
2107 | h = float(stretched_m.group('h')) | |
2108 | # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0). | |
2109 | # We will only process correct ratios. | |
2110 | if w > 0 and h > 0: | |
2111 | ratio = w / h | |
2112 | for f in formats: | |
2113 | if f.get('vcodec') != 'none': | |
2114 | f['stretched_ratio'] = ratio | |
2115 | ||
2116 | self._sort_formats(formats) | |
2117 | ||
2118 | self.mark_watched(video_id, video_info) | |
2119 | ||
2120 | return { | |
2121 | 'id': video_id, | |
2122 | 'uploader': video_uploader, | |
2123 | 'uploader_id': video_uploader_id, | |
2124 | 'uploader_url': video_uploader_url, | |
2125 | 'channel_id': channel_id, | |
2126 | 'channel_url': channel_url, | |
2127 | 'upload_date': upload_date, | |
2128 | 'license': video_license, | |
2129 | 'creator': video_creator or artist, | |
2130 | 'title': video_title, | |
2131 | 'alt_title': video_alt_title or track, | |
2132 | 'thumbnail': video_thumbnail, | |
2133 | 'description': video_description, | |
2134 | 'categories': video_categories, | |
2135 | 'tags': video_tags, | |
2136 | 'subtitles': video_subtitles, | |
2137 | 'automatic_captions': automatic_captions, | |
2138 | 'duration': video_duration, | |
2139 | 'age_limit': 18 if age_gate else 0, | |
2140 | 'annotations': video_annotations, | |
2141 | 'chapters': chapters, | |
2142 | 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id, | |
2143 | 'view_count': view_count, | |
2144 | 'like_count': like_count, | |
2145 | 'dislike_count': dislike_count, | |
2146 | 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]), | |
2147 | 'formats': formats, | |
2148 | 'is_live': is_live, | |
2149 | 'start_time': start_time, | |
2150 | 'end_time': end_time, | |
2151 | 'series': series, | |
2152 | 'season_number': season_number, | |
2153 | 'episode_number': episode_number, | |
2154 | 'track': track, | |
2155 | 'artist': artist, | |
2156 | } | |
2157 | ||
2158 | ||
2159 | class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): | |
2160 | IE_DESC = 'YouTube.com playlists' | |
2161 | _VALID_URL = r"""(?x)(?: | |
2162 | (?:https?://)? | |
2163 | (?:\w+\.)? | |
2164 | (?: | |
2165 | (?: | |
2166 | youtube\.com| | |
2167 | invidio\.us | |
2168 | ) | |
2169 | / | |
2170 | (?: | |
2171 | (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11})) | |
2172 | \? (?:.*?[&;])*? (?:p|a|list)= | |
2173 | | p/ | |
2174 | )| | |
2175 | youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist= | |
2176 | ) | |
2177 | ( | |
2178 | (?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)?[0-9A-Za-z-_]{10,} | |
2179 | # Top tracks, they can also include dots | |
2180 | |(?:MC)[\w\.]* | |
2181 | ) | |
2182 | .* | |
2183 | | | |
2184 | (%(playlist_id)s) | |
2185 | )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} | |
2186 | _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' | |
2187 | _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?' | |
2188 | IE_NAME = 'youtube:playlist' | |
2189 | _TESTS = [{ | |
2190 | 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', | |
2191 | 'info_dict': { | |
2192 | 'title': 'ytdl test PL', | |
2193 | 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', | |
2194 | }, | |
2195 | 'playlist_count': 3, | |
2196 | }, { | |
2197 | 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', | |
2198 | 'info_dict': { | |
2199 | 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', | |
2200 | 'title': 'YDL_Empty_List', | |
2201 | }, | |
2202 | 'playlist_count': 0, | |
2203 | 'skip': 'This playlist is private', | |
2204 | }, { | |
2205 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
2206 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
2207 | 'info_dict': { | |
2208 | 'title': '29C3: Not my department', | |
2209 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
2210 | }, | |
2211 | 'playlist_count': 95, | |
2212 | }, { | |
2213 | 'note': 'issue #673', | |
2214 | 'url': 'PLBB231211A4F62143', | |
2215 | 'info_dict': { | |
2216 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', | |
2217 | 'id': 'PLBB231211A4F62143', | |
2218 | }, | |
2219 | 'playlist_mincount': 26, | |
2220 | }, { | |
2221 | 'note': 'Large playlist', | |
2222 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
2223 | 'info_dict': { | |
2224 | 'title': 'Uploads from Cauchemar', | |
2225 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', | |
2226 | }, | |
2227 | 'playlist_mincount': 799, | |
2228 | }, { | |
2229 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
2230 | 'info_dict': { | |
2231 | 'title': 'YDL_safe_search', | |
2232 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
2233 | }, | |
2234 | 'playlist_count': 2, | |
2235 | 'skip': 'This playlist is private', | |
2236 | }, { | |
2237 | 'note': 'embedded', | |
2238 | 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
2239 | 'playlist_count': 4, | |
2240 | 'info_dict': { | |
2241 | 'title': 'JODA15', | |
2242 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
2243 | } | |
2244 | }, { | |
2245 | 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
2246 | 'playlist_mincount': 485, | |
2247 | 'info_dict': { | |
2248 | 'title': '2017 華語最新單曲 (2/24更新)', | |
2249 | 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
2250 | } | |
2251 | }, { | |
2252 | 'note': 'Embedded SWF player', | |
2253 | 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0', | |
2254 | 'playlist_count': 4, | |
2255 | 'info_dict': { | |
2256 | 'title': 'JODA7', | |
2257 | 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ', | |
2258 | } | |
2259 | }, { | |
2260 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
2261 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
2262 | 'info_dict': { | |
2263 | 'title': 'Uploads from Interstellar Movie', | |
2264 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
2265 | }, | |
2266 | 'playlist_mincount': 21, | |
2267 | }, { | |
2268 | # Playlist URL that does not actually serve a playlist | |
2269 | 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', | |
2270 | 'info_dict': { | |
2271 | 'id': 'FqZTN594JQw', | |
2272 | 'ext': 'webm', | |
2273 | 'title': "Smiley's People 01 detective, Adventure Series, Action", | |
2274 | 'uploader': 'STREEM', | |
2275 | 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng', | |
2276 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng', | |
2277 | 'upload_date': '20150526', | |
2278 | 'license': 'Standard YouTube License', | |
2279 | 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', | |
2280 | 'categories': ['People & Blogs'], | |
2281 | 'tags': list, | |
2282 | 'view_count': int, | |
2283 | 'like_count': int, | |
2284 | 'dislike_count': int, | |
2285 | }, | |
2286 | 'params': { | |
2287 | 'skip_download': True, | |
2288 | }, | |
2289 | 'add_ie': [YoutubeIE.ie_key()], | |
2290 | }, { | |
2291 | 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', | |
2292 | 'info_dict': { | |
2293 | 'id': 'yeWKywCrFtk', | |
2294 | 'ext': 'mp4', | |
2295 | 'title': 'Small Scale Baler and Braiding Rugs', | |
2296 | 'uploader': 'Backus-Page House Museum', | |
2297 | 'uploader_id': 'backuspagemuseum', | |
2298 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum', | |
2299 | 'upload_date': '20161008', | |
2300 | 'license': 'Standard YouTube License', | |
2301 | 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', | |
2302 | 'categories': ['Nonprofits & Activism'], | |
2303 | 'tags': list, | |
2304 | 'like_count': int, | |
2305 | 'dislike_count': int, | |
2306 | }, | |
2307 | 'params': { | |
2308 | 'noplaylist': True, | |
2309 | 'skip_download': True, | |
2310 | }, | |
2311 | }, { | |
2312 | 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', | |
2313 | 'only_matching': True, | |
2314 | }, { | |
2315 | 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', | |
2316 | 'only_matching': True, | |
2317 | }, { | |
2318 | # music album playlist | |
2319 | 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM', | |
2320 | 'only_matching': True, | |
2321 | }, { | |
2322 | 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU', | |
2323 | 'only_matching': True, | |
2324 | }] | |
2325 | ||
2326 | def _real_initialize(self): | |
2327 | self._login() | |
2328 | ||
2329 | def _extract_mix(self, playlist_id): | |
2330 | # The mixes are generated from a single video | |
2331 | # the id of the playlist is just 'RD' + video_id | |
2332 | ids = [] | |
2333 | last_id = playlist_id[-11:] | |
2334 | for n in itertools.count(1): | |
2335 | url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id) | |
2336 | webpage = self._download_webpage( | |
2337 | url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n)) | |
2338 | new_ids = orderedSet(re.findall( | |
2339 | r'''(?xs)data-video-username=".*?".*? | |
2340 | href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id), | |
2341 | webpage)) | |
2342 | # Fetch new pages until all the videos are repeated, it seems that | |
2343 | # there are always 51 unique videos. | |
2344 | new_ids = [_id for _id in new_ids if _id not in ids] | |
2345 | if not new_ids: | |
2346 | break | |
2347 | ids.extend(new_ids) | |
2348 | last_id = ids[-1] | |
2349 | ||
2350 | url_results = self._ids_to_results(ids) | |
2351 | ||
2352 | search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage) | |
2353 | title_span = ( | |
2354 | search_title('playlist-title') or | |
2355 | search_title('title long-title') or | |
2356 | search_title('title')) | |
2357 | title = clean_html(title_span) | |
2358 | ||
2359 | return self.playlist_result(url_results, playlist_id, title) | |
2360 | ||
2361 | def _extract_playlist(self, playlist_id): | |
2362 | url = self._TEMPLATE_URL % playlist_id | |
2363 | page = self._download_webpage(url, playlist_id) | |
2364 | ||
2365 | # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604) | |
2366 | for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page): | |
2367 | match = match.strip() | |
2368 | # Check if the playlist exists or is private | |
2369 | mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match) | |
2370 | if mobj: | |
2371 | reason = mobj.group('reason') | |
2372 | message = 'This playlist %s' % reason | |
2373 | if 'private' in reason: | |
2374 | message += ', use --username or --netrc to access it' | |
2375 | message += '.' | |
2376 | raise ExtractorError(message, expected=True) | |
2377 | elif re.match(r'[^<]*Invalid parameters[^<]*', match): | |
2378 | raise ExtractorError( | |
2379 | 'Invalid parameters. Maybe URL is incorrect.', | |
2380 | expected=True) | |
2381 | elif re.match(r'[^<]*Choose your language[^<]*', match): | |
2382 | continue | |
2383 | else: | |
2384 | self.report_warning('Youtube gives an alert message: ' + match) | |
2385 | ||
2386 | playlist_title = self._html_search_regex( | |
2387 | r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>', | |
2388 | page, 'title', default=None) | |
2389 | ||
2390 | _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref=' | |
2391 | uploader = self._search_regex( | |
2392 | r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE, | |
2393 | page, 'uploader', default=None) | |
2394 | mobj = re.search( | |
2395 | r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE, | |
2396 | page) | |
2397 | if mobj: | |
2398 | uploader_id = mobj.group('uploader_id') | |
2399 | uploader_url = compat_urlparse.urljoin(url, mobj.group('path')) | |
2400 | else: | |
2401 | uploader_id = uploader_url = None | |
2402 | ||
2403 | has_videos = True | |
2404 | ||
2405 | if not playlist_title: | |
2406 | try: | |
2407 | # Some playlist URLs don't actually serve a playlist (e.g. | |
2408 | # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4) | |
2409 | next(self._entries(page, playlist_id)) | |
2410 | except StopIteration: | |
2411 | has_videos = False | |
2412 | ||
2413 | playlist = self.playlist_result( | |
2414 | self._entries(page, playlist_id), playlist_id, playlist_title) | |
2415 | playlist.update({ | |
2416 | 'uploader': uploader, | |
2417 | 'uploader_id': uploader_id, | |
2418 | 'uploader_url': uploader_url, | |
2419 | }) | |
2420 | ||
2421 | return has_videos, playlist | |
2422 | ||
2423 | def _check_download_just_video(self, url, playlist_id): | |
2424 | # Check if it's a video-specific URL | |
2425 | query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) | |
2426 | video_id = query_dict.get('v', [None])[0] or self._search_regex( | |
2427 | r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url, | |
2428 | 'video id', default=None) | |
2429 | if video_id: | |
2430 | if self._downloader.params.get('noplaylist'): | |
2431 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
2432 | return video_id, self.url_result(video_id, 'Youtube', video_id=video_id) | |
2433 | else: | |
2434 | self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) | |
2435 | return video_id, None | |
2436 | return None, None | |
2437 | ||
2438 | def _real_extract(self, url): | |
2439 | # Extract playlist id | |
2440 | mobj = re.match(self._VALID_URL, url) | |
2441 | if mobj is None: | |
2442 | raise ExtractorError('Invalid URL: %s' % url) | |
2443 | playlist_id = mobj.group(1) or mobj.group(2) | |
2444 | ||
2445 | video_id, video = self._check_download_just_video(url, playlist_id) | |
2446 | if video: | |
2447 | return video | |
2448 | ||
2449 | if playlist_id.startswith(('RD', 'UL', 'PU')): | |
2450 | # Mixes require a custom extraction process | |
2451 | return self._extract_mix(playlist_id) | |
2452 | ||
2453 | has_videos, playlist = self._extract_playlist(playlist_id) | |
2454 | if has_videos or not video_id: | |
2455 | return playlist | |
2456 | ||
2457 | # Some playlist URLs don't actually serve a playlist (see | |
2458 | # https://github.com/rg3/youtube-dl/issues/10537). | |
2459 | # Fallback to plain video extraction if there is a video id | |
2460 | # along with playlist id. | |
2461 | return self.url_result(video_id, 'Youtube', video_id=video_id) | |
2462 | ||
2463 | ||
2464 | class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): | |
2465 | IE_DESC = 'YouTube.com channels' | |
2466 | _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)' | |
2467 | _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos' | |
2468 | _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?' | |
2469 | IE_NAME = 'youtube:channel' | |
2470 | _TESTS = [{ | |
2471 | 'note': 'paginated channel', | |
2472 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
2473 | 'playlist_mincount': 91, | |
2474 | 'info_dict': { | |
2475 | 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w', | |
2476 | 'title': 'Uploads from lex will', | |
2477 | } | |
2478 | }, { | |
2479 | 'note': 'Age restricted channel', | |
2480 | # from https://www.youtube.com/user/DeusExOfficial | |
2481 | 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w', | |
2482 | 'playlist_mincount': 64, | |
2483 | 'info_dict': { | |
2484 | 'id': 'UUs0ifCMCm1icqRbqhUINa0w', | |
2485 | 'title': 'Uploads from Deus Ex', | |
2486 | }, | |
2487 | }, { | |
2488 | 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA', | |
2489 | 'only_matching': True, | |
2490 | }] | |
2491 | ||
2492 | @classmethod | |
2493 | def suitable(cls, url): | |
2494 | return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url) | |
2495 | else super(YoutubeChannelIE, cls).suitable(url)) | |
2496 | ||
2497 | def _build_template_url(self, url, channel_id): | |
2498 | return self._TEMPLATE_URL % channel_id | |
2499 | ||
2500 | def _real_extract(self, url): | |
2501 | channel_id = self._match_id(url) | |
2502 | ||
2503 | url = self._build_template_url(url, channel_id) | |
2504 | ||
2505 | # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778) | |
2506 | # Workaround by extracting as a playlist if managed to obtain channel playlist URL | |
2507 | # otherwise fallback on channel by page extraction | |
2508 | channel_page = self._download_webpage( | |
2509 | url + '?view=57', channel_id, | |
2510 | 'Downloading channel page', fatal=False) | |
2511 | if channel_page is False: | |
2512 | channel_playlist_id = False | |
2513 | else: | |
2514 | channel_playlist_id = self._html_search_meta( | |
2515 | 'channelId', channel_page, 'channel id', default=None) | |
2516 | if not channel_playlist_id: | |
2517 | channel_url = self._html_search_meta( | |
2518 | ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'), | |
2519 | channel_page, 'channel url', default=None) | |
2520 | if channel_url: | |
2521 | channel_playlist_id = self._search_regex( | |
2522 | r'vnd\.youtube://user/([0-9A-Za-z_-]+)', | |
2523 | channel_url, 'channel id', default=None) | |
2524 | if channel_playlist_id and channel_playlist_id.startswith('UC'): | |
2525 | playlist_id = 'UU' + channel_playlist_id[2:] | |
2526 | return self.url_result( | |
2527 | compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist') | |
2528 | ||
2529 | channel_page = self._download_webpage(url, channel_id, 'Downloading page #1') | |
2530 | autogenerated = re.search(r'''(?x) | |
2531 | class="[^"]*?(?: | |
2532 | channel-header-autogenerated-label| | |
2533 | yt-channel-title-autogenerated | |
2534 | )[^"]*"''', channel_page) is not None | |
2535 | ||
2536 | if autogenerated: | |
2537 | # The videos are contained in a single page | |
2538 | # the ajax pages can't be used, they are empty | |
2539 | entries = [ | |
2540 | self.url_result( | |
2541 | video_id, 'Youtube', video_id=video_id, | |
2542 | video_title=video_title) | |
2543 | for video_id, video_title in self.extract_videos_from_page(channel_page)] | |
2544 | return self.playlist_result(entries, channel_id) | |
2545 | ||
2546 | try: | |
2547 | next(self._entries(channel_page, channel_id)) | |
2548 | except StopIteration: | |
2549 | alert_message = self._html_search_regex( | |
2550 | r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>', | |
2551 | channel_page, 'alert', default=None, group='alert') | |
2552 | if alert_message: | |
2553 | raise ExtractorError('Youtube said: %s' % alert_message, expected=True) | |
2554 | ||
2555 | return self.playlist_result(self._entries(channel_page, channel_id), channel_id) | |
2556 | ||
2557 | ||
2558 | class YoutubeUserIE(YoutubeChannelIE): | |
2559 | IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)' | |
2560 | _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_-]+)' | |
2561 | _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos' | |
2562 | IE_NAME = 'youtube:user' | |
2563 | ||
2564 | _TESTS = [{ | |
2565 | 'url': 'https://www.youtube.com/user/TheLinuxFoundation', | |
2566 | 'playlist_mincount': 320, | |
2567 | 'info_dict': { | |
2568 | 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ', | |
2569 | 'title': 'Uploads from The Linux Foundation', | |
2570 | } | |
2571 | }, { | |
2572 | # Only available via https://www.youtube.com/c/12minuteathlete/videos | |
2573 | # but not https://www.youtube.com/user/12minuteathlete/videos | |
2574 | 'url': 'https://www.youtube.com/c/12minuteathlete/videos', | |
2575 | 'playlist_mincount': 249, | |
2576 | 'info_dict': { | |
2577 | 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ', | |
2578 | 'title': 'Uploads from 12 Minute Athlete', | |
2579 | } | |
2580 | }, { | |
2581 | 'url': 'ytuser:phihag', | |
2582 | 'only_matching': True, | |
2583 | }, { | |
2584 | 'url': 'https://www.youtube.com/c/gametrailers', | |
2585 | 'only_matching': True, | |
2586 | }, { | |
2587 | 'url': 'https://www.youtube.com/gametrailers', | |
2588 | 'only_matching': True, | |
2589 | }, { | |
2590 | # This channel is not available, geo restricted to JP | |
2591 | 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos', | |
2592 | 'only_matching': True, | |
2593 | }] | |
2594 | ||
2595 | @classmethod | |
2596 | def suitable(cls, url): | |
2597 | # Don't return True if the url can be extracted with other youtube | |
2598 | # extractor, the regex would is too permissive and it would match. | |
2599 | other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls) | |
2600 | if any(ie.suitable(url) for ie in other_yt_ies): | |
2601 | return False | |
2602 | else: | |
2603 | return super(YoutubeUserIE, cls).suitable(url) | |
2604 | ||
2605 | def _build_template_url(self, url, channel_id): | |
2606 | mobj = re.match(self._VALID_URL, url) | |
2607 | return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id')) | |
2608 | ||
2609 | ||
2610 | class YoutubeLiveIE(YoutubeBaseInfoExtractor): | |
2611 | IE_DESC = 'YouTube.com live streams' | |
2612 | _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live' | |
2613 | IE_NAME = 'youtube:live' | |
2614 | ||
2615 | _TESTS = [{ | |
2616 | 'url': 'https://www.youtube.com/user/TheYoungTurks/live', | |
2617 | 'info_dict': { | |
2618 | 'id': 'a48o2S1cPoo', | |
2619 | 'ext': 'mp4', | |
2620 | 'title': 'The Young Turks - Live Main Show', | |
2621 | 'uploader': 'The Young Turks', | |
2622 | 'uploader_id': 'TheYoungTurks', | |
2623 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks', | |
2624 | 'upload_date': '20150715', | |
2625 | 'license': 'Standard YouTube License', | |
2626 | 'description': 'md5:438179573adcdff3c97ebb1ee632b891', | |
2627 | 'categories': ['News & Politics'], | |
2628 | 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], | |
2629 | 'like_count': int, | |
2630 | 'dislike_count': int, | |
2631 | }, | |
2632 | 'params': { | |
2633 | 'skip_download': True, | |
2634 | }, | |
2635 | }, { | |
2636 | 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', | |
2637 | 'only_matching': True, | |
2638 | }, { | |
2639 | 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', | |
2640 | 'only_matching': True, | |
2641 | }, { | |
2642 | 'url': 'https://www.youtube.com/TheYoungTurks/live', | |
2643 | 'only_matching': True, | |
2644 | }] | |
2645 | ||
2646 | def _real_extract(self, url): | |
2647 | mobj = re.match(self._VALID_URL, url) | |
2648 | channel_id = mobj.group('id') | |
2649 | base_url = mobj.group('base_url') | |
2650 | webpage = self._download_webpage(url, channel_id, fatal=False) | |
2651 | if webpage: | |
2652 | page_type = self._og_search_property( | |
2653 | 'type', webpage, 'page type', default='') | |
2654 | video_id = self._html_search_meta( | |
2655 | 'videoId', webpage, 'video id', default=None) | |
2656 | if page_type.startswith('video') and video_id and re.match( | |
2657 | r'^[0-9A-Za-z_-]{11}$', video_id): | |
2658 | return self.url_result(video_id, YoutubeIE.ie_key()) | |
2659 | return self.url_result(base_url) | |
2660 | ||
2661 | ||
2662 | class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor): | |
2663 | IE_DESC = 'YouTube.com user/channel playlists' | |
2664 | _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists' | |
2665 | IE_NAME = 'youtube:playlists' | |
2666 | ||
2667 | _TESTS = [{ | |
2668 | 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', | |
2669 | 'playlist_mincount': 4, | |
2670 | 'info_dict': { | |
2671 | 'id': 'ThirstForScience', | |
2672 | 'title': 'Thirst for Science', | |
2673 | }, | |
2674 | }, { | |
2675 | # with "Load more" button | |
2676 | 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', | |
2677 | 'playlist_mincount': 70, | |
2678 | 'info_dict': { | |
2679 | 'id': 'igorkle1', | |
2680 | 'title': 'Игорь Клейнер', | |
2681 | }, | |
2682 | }, { | |
2683 | 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists', | |
2684 | 'playlist_mincount': 17, | |
2685 | 'info_dict': { | |
2686 | 'id': 'UCiU1dHvZObB2iP6xkJ__Icw', | |
2687 | 'title': 'Chem Player', | |
2688 | }, | |
2689 | }] | |
2690 | ||
2691 | ||
2692 | class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor): | |
2693 | _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?' | |
2694 | ||
2695 | ||
2696 | class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor): | |
2697 | IE_DESC = 'YouTube.com searches' | |
2698 | # there doesn't appear to be a real limit, for example if you search for | |
2699 | # 'python' you get more than 8.000.000 results | |
2700 | _MAX_RESULTS = float('inf') | |
2701 | IE_NAME = 'youtube:search' | |
2702 | _SEARCH_KEY = 'ytsearch' | |
2703 | _EXTRA_QUERY_ARGS = {} | |
2704 | _TESTS = [] | |
2705 | ||
2706 | def _get_n_results(self, query, n): | |
2707 | """Get a specified number of results for a query""" | |
2708 | ||
2709 | videos = [] | |
2710 | limit = n | |
2711 | ||
2712 | url_query = { | |
2713 | 'search_query': query.encode('utf-8'), | |
2714 | } | |
2715 | url_query.update(self._EXTRA_QUERY_ARGS) | |
2716 | result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query) | |
2717 | ||
2718 | for pagenum in itertools.count(1): | |
2719 | data = self._download_json( | |
2720 | result_url, video_id='query "%s"' % query, | |
2721 | note='Downloading page %s' % pagenum, | |
2722 | errnote='Unable to download API page', | |
2723 | query={'spf': 'navigate'}) | |
2724 | html_content = data[1]['body']['content'] | |
2725 | ||
2726 | if 'class="search-message' in html_content: | |
2727 | raise ExtractorError( | |
2728 | '[youtube] No video results', expected=True) | |
2729 | ||
2730 | new_videos = list(self._process_page(html_content)) | |
2731 | videos += new_videos | |
2732 | if not new_videos or len(videos) > limit: | |
2733 | break | |
2734 | next_link = self._html_search_regex( | |
2735 | r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next', | |
2736 | html_content, 'next link', default=None) | |
2737 | if next_link is None: | |
2738 | break | |
2739 | result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link) | |
2740 | ||
2741 | if len(videos) > n: | |
2742 | videos = videos[:n] | |
2743 | return self.playlist_result(videos, query) | |
2744 | ||
2745 | ||
2746 | class YoutubeSearchDateIE(YoutubeSearchIE): | |
2747 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' | |
2748 | _SEARCH_KEY = 'ytsearchdate' | |
2749 | IE_DESC = 'YouTube.com searches, newest videos first' | |
2750 | _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'} | |
2751 | ||
2752 | ||
2753 | class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor): | |
2754 | IE_DESC = 'YouTube.com search URLs' | |
2755 | IE_NAME = 'youtube:search_url' | |
2756 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)' | |
2757 | _TESTS = [{ | |
2758 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
2759 | 'playlist_mincount': 5, | |
2760 | 'info_dict': { | |
2761 | 'title': 'youtube-dl test video', | |
2762 | } | |
2763 | }, { | |
2764 | 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB', | |
2765 | 'only_matching': True, | |
2766 | }] | |
2767 | ||
2768 | def _real_extract(self, url): | |
2769 | mobj = re.match(self._VALID_URL, url) | |
2770 | query = compat_urllib_parse_unquote_plus(mobj.group('query')) | |
2771 | webpage = self._download_webpage(url, query) | |
2772 | return self.playlist_result(self._process_page(webpage), playlist_title=query) | |
2773 | ||
2774 | ||
2775 | class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor): | |
2776 | IE_DESC = 'YouTube.com (multi-season) shows' | |
2777 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)' | |
2778 | IE_NAME = 'youtube:show' | |
2779 | _TESTS = [{ | |
2780 | 'url': 'https://www.youtube.com/show/airdisasters', | |
2781 | 'playlist_mincount': 5, | |
2782 | 'info_dict': { | |
2783 | 'id': 'airdisasters', | |
2784 | 'title': 'Air Disasters', | |
2785 | } | |
2786 | }] | |
2787 | ||
2788 | def _real_extract(self, url): | |
2789 | playlist_id = self._match_id(url) | |
2790 | return super(YoutubeShowIE, self)._real_extract( | |
2791 | 'https://www.youtube.com/show/%s/playlists' % playlist_id) | |
2792 | ||
2793 | ||
2794 | class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): | |
2795 | """ | |
2796 | Base class for feed extractors | |
2797 | Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties. | |
2798 | """ | |
2799 | _LOGIN_REQUIRED = True | |
2800 | ||
2801 | @property | |
2802 | def IE_NAME(self): | |
2803 | return 'youtube:%s' % self._FEED_NAME | |
2804 | ||
2805 | def _real_initialize(self): | |
2806 | self._login() | |
2807 | ||
2808 | def _entries(self, page): | |
2809 | # The extraction process is the same as for playlists, but the regex | |
2810 | # for the video ids doesn't contain an index | |
2811 | ids = [] | |
2812 | more_widget_html = content_html = page | |
2813 | for page_num in itertools.count(1): | |
2814 | matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html) | |
2815 | ||
2816 | # 'recommended' feed has infinite 'load more' and each new portion spins | |
2817 | # the same videos in (sometimes) slightly different order, so we'll check | |
2818 | # for unicity and break when portion has no new videos | |
2819 | new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches))) | |
2820 | if not new_ids: | |
2821 | break | |
2822 | ||
2823 | ids.extend(new_ids) | |
2824 | ||
2825 | for entry in self._ids_to_results(new_ids): | |
2826 | yield entry | |
2827 | ||
2828 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) | |
2829 | if not mobj: | |
2830 | break | |
2831 | ||
2832 | more = self._download_json( | |
2833 | 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE, | |
2834 | 'Downloading page #%s' % page_num, | |
2835 | transform_source=uppercase_escape) | |
2836 | content_html = more['content_html'] | |
2837 | more_widget_html = more['load_more_widget_html'] | |
2838 | ||
2839 | def _real_extract(self, url): | |
2840 | page = self._download_webpage( | |
2841 | 'https://www.youtube.com/feed/%s' % self._FEED_NAME, | |
2842 | self._PLAYLIST_TITLE) | |
2843 | return self.playlist_result( | |
2844 | self._entries(page), playlist_title=self._PLAYLIST_TITLE) | |
2845 | ||
2846 | ||
2847 | class YoutubeWatchLaterIE(YoutubePlaylistIE): | |
2848 | IE_NAME = 'youtube:watchlater' | |
2849 | IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' | |
2850 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater' | |
2851 | ||
2852 | _TESTS = [{ | |
2853 | 'url': 'https://www.youtube.com/playlist?list=WL', | |
2854 | 'only_matching': True, | |
2855 | }, { | |
2856 | 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL', | |
2857 | 'only_matching': True, | |
2858 | }] | |
2859 | ||
2860 | def _real_extract(self, url): | |
2861 | _, video = self._check_download_just_video(url, 'WL') | |
2862 | if video: | |
2863 | return video | |
2864 | _, playlist = self._extract_playlist('WL') | |
2865 | return playlist | |
2866 | ||
2867 | ||
2868 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): | |
2869 | IE_NAME = 'youtube:favorites' | |
2870 | IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)' | |
2871 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?' | |
2872 | _LOGIN_REQUIRED = True | |
2873 | ||
2874 | def _real_extract(self, url): | |
2875 | webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos') | |
2876 | playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id') | |
2877 | return self.url_result(playlist_id, 'YoutubePlaylist') | |
2878 | ||
2879 | ||
2880 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): | |
2881 | IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' | |
2882 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?' | |
2883 | _FEED_NAME = 'recommended' | |
2884 | _PLAYLIST_TITLE = 'Youtube Recommended videos' | |
2885 | ||
2886 | ||
2887 | class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): | |
2888 | IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' | |
2889 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' | |
2890 | _FEED_NAME = 'subscriptions' | |
2891 | _PLAYLIST_TITLE = 'Youtube Subscriptions' | |
2892 | ||
2893 | ||
2894 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): | |
2895 | IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' | |
2896 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory' | |
2897 | _FEED_NAME = 'history' | |
2898 | _PLAYLIST_TITLE = 'Youtube History' | |
2899 | ||
2900 | ||
2901 | class YoutubeTruncatedURLIE(InfoExtractor): | |
2902 | IE_NAME = 'youtube:truncated_url' | |
2903 | IE_DESC = False # Do not list | |
2904 | _VALID_URL = r'''(?x) | |
2905 | (?:https?://)? | |
2906 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
2907 | (?:watch\?(?: | |
2908 | feature=[a-z_]+| | |
2909 | annotation_id=annotation_[^&]+| | |
2910 | x-yt-cl=[0-9]+| | |
2911 | hl=[^&]*| | |
2912 | t=[0-9]+ | |
2913 | )? | |
2914 | | | |
2915 | attribution_link\?a=[^&]+ | |
2916 | ) | |
2917 | $ | |
2918 | ''' | |
2919 | ||
2920 | _TESTS = [{ | |
2921 | 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041', | |
2922 | 'only_matching': True, | |
2923 | }, { | |
2924 | 'url': 'https://www.youtube.com/watch?', | |
2925 | 'only_matching': True, | |
2926 | }, { | |
2927 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
2928 | 'only_matching': True, | |
2929 | }, { | |
2930 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
2931 | 'only_matching': True, | |
2932 | }, { | |
2933 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
2934 | 'only_matching': True, | |
2935 | }, { | |
2936 | 'url': 'https://www.youtube.com/watch?t=2372', | |
2937 | 'only_matching': True, | |
2938 | }] | |
2939 | ||
2940 | def _real_extract(self, url): | |
2941 | raise ExtractorError( | |
2942 | 'Did you forget to quote the URL? Remember that & is a meta ' | |
2943 | 'character in most shells, so you want to put the URL in quotes, ' | |
2944 | 'like youtube-dl ' | |
2945 | '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' | |
2946 | ' or simply youtube-dl BaW_jenozKc .', | |
2947 | expected=True) | |
2948 | ||
2949 | ||
2950 | class YoutubeTruncatedIDIE(InfoExtractor): | |
2951 | IE_NAME = 'youtube:truncated_id' | |
2952 | IE_DESC = False # Do not list | |
2953 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' | |
2954 | ||
2955 | _TESTS = [{ | |
2956 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
2957 | 'only_matching': True, | |
2958 | }] | |
2959 | ||
2960 | def _real_extract(self, url): | |
2961 | video_id = self._match_id(url) | |
2962 | raise ExtractorError( | |
2963 | 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), | |
2964 | expected=True) |