]>
Commit | Line | Data |
---|---|---|
c5e8d7af | 1 | # coding: utf-8 |
c5e8d7af | 2 | |
78caa52a PH |
3 | from __future__ import unicode_literals |
4 | ||
5 | ||
0ca96d48 | 6 | import itertools |
c5e8d7af | 7 | import json |
c4417ddb | 8 | import os.path |
d77ab8e2 | 9 | import random |
c5e8d7af | 10 | import re |
42939b61 | 11 | import time |
e0df6211 | 12 | import traceback |
c5e8d7af | 13 | |
b05654f0 | 14 | from .common import InfoExtractor, SearchInfoExtractor |
2b25cb5d | 15 | from ..jsinterp import JSInterpreter |
54256267 | 16 | from ..swfinterp import SWFInterpreter |
4bb4a188 | 17 | from ..compat import ( |
edf3e38e | 18 | compat_chr, |
c5e8d7af | 19 | compat_parse_qs, |
7fd002c0 S |
20 | compat_urllib_parse_unquote, |
21 | compat_urllib_parse_unquote_plus, | |
15707c7e | 22 | compat_urllib_parse_urlencode, |
7c80519c | 23 | compat_urllib_parse_urlparse, |
7c61bd36 | 24 | compat_urlparse, |
c5e8d7af | 25 | compat_str, |
4bb4a188 PH |
26 | ) |
27 | from ..utils import ( | |
c5e8d7af | 28 | clean_html, |
9b9c5355 | 29 | error_to_compat_str, |
c5e8d7af | 30 | ExtractorError, |
2d30521a | 31 | float_or_none, |
4bb4a188 PH |
32 | get_element_by_attribute, |
33 | get_element_by_id, | |
dd27fd17 | 34 | int_or_none, |
94278f72 | 35 | mimetype2ext, |
4bb4a188 | 36 | orderedSet, |
6310acf5 | 37 | parse_codecs, |
7c80519c | 38 | parse_duration, |
0cb58b02 | 39 | remove_quotes, |
e00eb564 | 40 | # remove_start, |
cf7e015f | 41 | smuggle_url, |
c93d53f5 | 42 | str_to_int, |
556dbe7f | 43 | try_get, |
c5e8d7af PH |
44 | unescapeHTML, |
45 | unified_strdate, | |
cf7e015f | 46 | unsmuggle_url, |
81c2f20b | 47 | uppercase_escape, |
6e6bc8da | 48 | urlencode_postdata, |
c5e8d7af PH |
49 | ) |
50 | ||
5f6a1245 | 51 | |
de7f3446 | 52 | class YoutubeBaseInfoExtractor(InfoExtractor): |
b2e8bc1b JMF |
53 | """Provide base functions for Youtube extractors""" |
54 | _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' | |
9303ce3e | 55 | _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge' |
e00eb564 S |
56 | |
57 | _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup' | |
58 | _LOOKUP_REQ_TEMPLATE = '["{0}",null,[],null,"US",null,null,2,false,true,[null,null,[2,1,null,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",null,[],4],1,[null,null,[]],null,null,null,true],"{0}"]' | |
59 | ||
60 | _PASSWORD_CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge' | |
61 | _PASSWORD_CHALLENGE_REQ_TEMPLATE = '["{0}",null,1,null,[1,null,null,null,["{1}",null,true]],[null,null,[2,1,null,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",null,[],4],1,[null,null,[]],null,null,null,true]]' | |
62 | ||
63 | _TFA_URL = 'https://accounts.google.com/_/signin/challenge' | |
64 | _TFA_REQ_TEMPLATE = '["{0}",null,2,null,[9,null,null,null,null,null,null,null,[null,"{1}",false,2]]]' | |
65 | ||
b2e8bc1b JMF |
66 | _NETRC_MACHINE = 'youtube' |
67 | # If True it will raise an error if no login info is provided | |
68 | _LOGIN_REQUIRED = False | |
69 | ||
d0ba5587 S |
70 | _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,}' |
71 | ||
b2e8bc1b | 72 | def _set_language(self): |
810fb84d PH |
73 | self._set_cookie( |
74 | '.youtube.com', 'PREF', 'f1=50000000&hl=en', | |
42939b61 | 75 | # YouTube sets the expire time to about two months |
810fb84d | 76 | expire_time=time.time() + 2 * 30 * 24 * 3600) |
b2e8bc1b | 77 | |
25f14e9f S |
78 | def _ids_to_results(self, ids): |
79 | return [ | |
80 | self.url_result(vid_id, 'Youtube', video_id=vid_id) | |
81 | for vid_id in ids] | |
82 | ||
b2e8bc1b | 83 | def _login(self): |
83317f69 | 84 | """ |
85 | Attempt to log in to YouTube. | |
86 | True is returned if successful or skipped. | |
87 | False is returned if login failed. | |
88 | ||
89 | If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. | |
90 | """ | |
b2e8bc1b JMF |
91 | (username, password) = self._get_login_info() |
92 | # No authentication to be performed | |
93 | if username is None: | |
94 | if self._LOGIN_REQUIRED: | |
69ea8ca4 | 95 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
83317f69 | 96 | return True |
b2e8bc1b | 97 | |
7cc3570e PH |
98 | login_page = self._download_webpage( |
99 | self._LOGIN_URL, None, | |
69ea8ca4 PH |
100 | note='Downloading login page', |
101 | errnote='unable to fetch login page', fatal=False) | |
7cc3570e PH |
102 | if login_page is False: |
103 | return | |
b2e8bc1b | 104 | |
1212e997 | 105 | login_form = self._hidden_inputs(login_page) |
c5e8d7af | 106 | |
e00eb564 S |
107 | def req(url, f_req, note, errnote): |
108 | data = login_form.copy() | |
109 | data.update({ | |
110 | 'pstMsg': 1, | |
111 | 'checkConnection': 'youtube', | |
112 | 'checkedDomains': 'youtube', | |
113 | 'hl': 'en', | |
114 | 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]', | |
115 | 'f.req': f_req, | |
116 | 'flowName': 'GlifWebSignIn', | |
117 | 'flowEntry': 'ServiceLogin', | |
041bc3ad | 118 | }) |
e00eb564 S |
119 | return self._download_json( |
120 | url, None, note=note, errnote=errnote, | |
121 | transform_source=lambda s: re.sub(r'^[^[]*', '', s), | |
122 | fatal=False, | |
123 | data=urlencode_postdata(data), headers={ | |
124 | 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8', | |
125 | 'Google-Accounts-XSRF': 1, | |
126 | }) | |
127 | ||
128 | lookup_results = req( | |
129 | self._LOOKUP_URL, self._LOOKUP_REQ_TEMPLATE.format(username), | |
130 | 'Looking up account info', 'Unable to look up account info') | |
131 | ||
132 | if lookup_results is False: | |
133 | return False | |
041bc3ad | 134 | |
e00eb564 | 135 | user_hash = lookup_results[0][2] |
83317f69 | 136 | |
e00eb564 S |
137 | password_challenge_results = req( |
138 | self._PASSWORD_CHALLENGE_URL, | |
139 | self._PASSWORD_CHALLENGE_REQ_TEMPLATE.format(user_hash, password), | |
140 | 'Logging in', 'Unable to log in')[0] | |
83317f69 | 141 | |
e00eb564 S |
142 | if password_challenge_results is False: |
143 | return | |
83317f69 | 144 | |
e00eb564 S |
145 | msg = password_challenge_results[5] |
146 | if msg is not None and isinstance(msg, list): | |
147 | raise ExtractorError('Unable to login: %s' % msg[5], expected=True) | |
148 | ||
149 | password_challenge_results = password_challenge_results[-1] | |
150 | ||
151 | # tfa = password_challenge_results[0] | |
152 | # if isinstance(tfa, list) and tfa[0][2] == 'TWO_STEP_VERIFICATION': | |
153 | # tfa_code = self._get_tfa_info('2-step verification code') | |
154 | # | |
155 | # if not tfa_code: | |
156 | # self._downloader.report_warning( | |
157 | # 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>' | |
158 | # '(Note that only TOTP (Google Authenticator App) codes work at this time.)') | |
159 | # return False | |
160 | # | |
161 | # tfa_code = remove_start(tfa_code, 'G-') | |
162 | # print('tfa', tfa_code) | |
163 | # tfa_results = req( | |
164 | # self._TFA_URL, | |
165 | # self._TFA_REQ_TEMPLATE.format(user_hash, tfa_code), | |
166 | # 'Submitting TFA code', 'Unable to submit TFA code') | |
167 | # | |
168 | # TODO | |
169 | ||
170 | check_cookie_results = self._download_webpage( | |
171 | password_challenge_results[2], None, 'Checking cookie') | |
172 | ||
173 | if '>Sign out<' not in check_cookie_results: | |
174 | self._downloader.report_warning('Unable to log in') | |
b2e8bc1b | 175 | return False |
e00eb564 | 176 | |
b2e8bc1b JMF |
177 | return True |
178 | ||
b2e8bc1b JMF |
179 | def _real_initialize(self): |
180 | if self._downloader is None: | |
181 | return | |
42939b61 | 182 | self._set_language() |
b2e8bc1b JMF |
183 | if not self._login(): |
184 | return | |
c5e8d7af | 185 | |
8377574c | 186 | |
8e7aad20 | 187 | class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor): |
061a75ed | 188 | # Extract entries from page with "Load more" button |
648e6a1f S |
189 | def _entries(self, page, playlist_id): |
190 | more_widget_html = content_html = page | |
191 | for page_num in itertools.count(1): | |
061a75ed S |
192 | for entry in self._process_page(content_html): |
193 | yield entry | |
648e6a1f S |
194 | |
195 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) | |
196 | if not mobj: | |
197 | break | |
198 | ||
199 | more = self._download_json( | |
200 | 'https://youtube.com/%s' % mobj.group('more'), playlist_id, | |
201 | 'Downloading page #%s' % page_num, | |
202 | transform_source=uppercase_escape) | |
203 | content_html = more['content_html'] | |
204 | if not content_html.strip(): | |
205 | # Some webpages show a "Load more" button but they don't | |
206 | # have more videos | |
207 | break | |
208 | more_widget_html = more['load_more_widget_html'] | |
209 | ||
061a75ed S |
210 | |
211 | class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): | |
212 | def _process_page(self, content): | |
213 | for video_id, video_title in self.extract_videos_from_page(content): | |
214 | yield self.url_result(video_id, 'Youtube', video_id, video_title) | |
215 | ||
648e6a1f S |
216 | def extract_videos_from_page(self, page): |
217 | ids_in_page = [] | |
218 | titles_in_page = [] | |
219 | for mobj in re.finditer(self._VIDEO_RE, page): | |
220 | # The link with index 0 is not the first video of the playlist (not sure if still actual) | |
221 | if 'index' in mobj.groupdict() and mobj.group('id') == '0': | |
222 | continue | |
223 | video_id = mobj.group('id') | |
224 | video_title = unescapeHTML(mobj.group('title')) | |
225 | if video_title: | |
226 | video_title = video_title.strip() | |
227 | try: | |
228 | idx = ids_in_page.index(video_id) | |
229 | if video_title and not titles_in_page[idx]: | |
230 | titles_in_page[idx] = video_title | |
231 | except ValueError: | |
232 | ids_in_page.append(video_id) | |
233 | titles_in_page.append(video_title) | |
234 | return zip(ids_in_page, titles_in_page) | |
235 | ||
236 | ||
061a75ed S |
237 | class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): |
238 | def _process_page(self, content): | |
6dee688e S |
239 | for playlist_id in orderedSet(re.findall( |
240 | r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"', | |
241 | content)): | |
061a75ed S |
242 | yield self.url_result( |
243 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist') | |
244 | ||
0c148415 S |
245 | def _real_extract(self, url): |
246 | playlist_id = self._match_id(url) | |
247 | webpage = self._download_webpage(url, playlist_id) | |
0c148415 | 248 | title = self._og_search_title(webpage, fatal=False) |
061a75ed | 249 | return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title) |
0c148415 S |
250 | |
251 | ||
360e1ca5 | 252 | class YoutubeIE(YoutubeBaseInfoExtractor): |
78caa52a | 253 | IE_DESC = 'YouTube.com' |
cb7dfeea | 254 | _VALID_URL = r"""(?x)^ |
c5e8d7af | 255 | ( |
edb53e2d | 256 | (?:https?://|//) # http(s):// or protocol-independent URL |
cb7dfeea | 257 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/| |
484aaeb2 | 258 | (?:www\.)?deturl\.com/www\.youtube\.com/| |
e70dc1d1 | 259 | (?:www\.)?pwnyoutube\.com/| |
f7000f3a | 260 | (?:www\.)?yourepeat\.com/| |
e69ae5b9 JMF |
261 | tube\.majestyc\.net/| |
262 | youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains | |
c5e8d7af PH |
263 | (?:.*?\#/)? # handle anchor (#/) redirect urls |
264 | (?: # the various things that can precede the ID: | |
ac7553d0 | 265 | (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/ |
c5e8d7af | 266 | |(?: # or the v= param in all its forms |
f7000f3a | 267 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) |
c5e8d7af | 268 | (?:\?|\#!?) # the params delimiter ? or # or #! |
040ac686 | 269 | (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY) |
c5e8d7af PH |
270 | v= |
271 | ) | |
f4b05232 | 272 | )) |
cbaed4bb S |
273 | |(?: |
274 | youtu\.be| # just youtu.be/xxxx | |
6d4fc66b S |
275 | vid\.plus| # or vid.plus/xxxx |
276 | zwearz\.com/watch| # or zwearz.com/watch/xxxx | |
cbaed4bb | 277 | )/ |
edb53e2d | 278 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= |
f4b05232 | 279 | ) |
c5e8d7af | 280 | )? # all until now is optional -> you can pass the naked ID |
8963d9c2 | 281 | ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID |
d0ba5587 S |
282 | (?!.*?\blist= |
283 | (?: | |
284 | %(playlist_id)s| # combined list/video URLs are handled by the playlist IE | |
285 | WL # WL are handled by the watch later IE | |
286 | ) | |
287 | ) | |
c5e8d7af | 288 | (?(1).+)? # if we found the ID, everything can follow |
d0ba5587 | 289 | $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} |
c5e8d7af | 290 | _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' |
2c62dc26 | 291 | _formats = { |
c2d3cb4c | 292 | '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, |
293 | '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}, | |
294 | '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}, | |
295 | '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}, | |
296 | '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}, | |
297 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
298 | '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
299 | '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
3834d3e3 | 300 | # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well |
c2d3cb4c | 301 | '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}, |
302 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
303 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}, | |
304 | '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
305 | '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}, | |
306 | '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, | |
e1a0bfdf | 307 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}, |
c2d3cb4c | 308 | '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, |
309 | '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}, | |
e1a0bfdf | 310 | |
311 | ||
312 | # 3D videos | |
c2d3cb4c | 313 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, |
314 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}, | |
315 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
316 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}, | |
e1a0bfdf | 317 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}, |
318 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
319 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}, | |
836a086c | 320 | |
96fb5605 | 321 | # Apple HTTP Live Streaming |
11f12195 | 322 | '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
c2d3cb4c | 323 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
324 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
325 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}, | |
326 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
327 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}, | |
e1a0bfdf | 328 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}, |
329 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}, | |
2c62dc26 PH |
330 | |
331 | # DASH mp4 video | |
d23028a8 S |
332 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}, |
333 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
334 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
335 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
336 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
337 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559) | |
338 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
339 | '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
340 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
341 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
342 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}, | |
343 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}, | |
836a086c | 344 | |
f6f1fc92 | 345 | # Dash mp4 audio |
d23028a8 S |
346 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}, |
347 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}, | |
348 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}, | |
349 | '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
350 | '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}, | |
351 | '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}, | |
352 | '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}, | |
836a086c AZ |
353 | |
354 | # Dash webm | |
d23028a8 S |
355 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, |
356 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
357 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
358 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
359 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
360 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}, | |
361 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}, | |
362 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
363 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
364 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
365 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
366 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
367 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
368 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
369 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
4c6b4764 | 370 | # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug) |
d23028a8 S |
371 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, |
372 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
373 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
374 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
375 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}, | |
376 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}, | |
2c62dc26 PH |
377 | |
378 | # Dash webm audio | |
d23028a8 S |
379 | '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}, |
380 | '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}, | |
ce6b9a2d | 381 | |
0857baad | 382 | # Dash webm audio with opus inside |
d23028a8 S |
383 | '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}, |
384 | '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}, | |
385 | '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}, | |
0857baad | 386 | |
ce6b9a2d PH |
387 | # RTMP (unnamed) |
388 | '_rtmp': {'protocol': 'rtmp'}, | |
c5e8d7af | 389 | } |
23d17e4b | 390 | _SUBTITLE_FORMATS = ('ttml', 'vtt') |
836a086c | 391 | |
fd5c4aab S |
392 | _GEO_BYPASS = False |
393 | ||
78caa52a | 394 | IE_NAME = 'youtube' |
2eb88d95 PH |
395 | _TESTS = [ |
396 | { | |
2d3d2997 | 397 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9', |
4bc3a23e PH |
398 | 'info_dict': { |
399 | 'id': 'BaW_jenozKc', | |
400 | 'ext': 'mp4', | |
401 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
402 | 'uploader': 'Philipp Hagemeister', | |
403 | 'uploader_id': 'phihag', | |
ec85ded8 | 404 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', |
4bc3a23e | 405 | 'upload_date': '20121002', |
7caf9830 | 406 | 'license': 'Standard YouTube License', |
4bc3a23e PH |
407 | '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 .', |
408 | 'categories': ['Science & Technology'], | |
000b6b5a | 409 | 'tags': ['youtube-dl'], |
556dbe7f | 410 | 'duration': 10, |
3e7c1224 PH |
411 | 'like_count': int, |
412 | 'dislike_count': int, | |
7c80519c | 413 | 'start_time': 1, |
297a564b | 414 | 'end_time': 9, |
2eb88d95 | 415 | } |
0e853ca4 | 416 | }, |
0e853ca4 | 417 | { |
2d3d2997 | 418 | 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY', |
4bc3a23e PH |
419 | 'note': 'Test generic use_cipher_signature video (#897)', |
420 | 'info_dict': { | |
421 | 'id': 'UxxajLWwzqY', | |
422 | 'ext': 'mp4', | |
423 | 'upload_date': '20120506', | |
424 | 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', | |
0cb58b02 | 425 | 'alt_title': 'I Love It (feat. Charli XCX)', |
7caf9830 | 426 | 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8', |
000b6b5a S |
427 | 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli', |
428 | 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop', | |
429 | 'iconic ep', 'iconic', 'love', 'it'], | |
556dbe7f | 430 | 'duration': 180, |
4bc3a23e PH |
431 | 'uploader': 'Icona Pop', |
432 | 'uploader_id': 'IconaPop', | |
ec85ded8 | 433 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop', |
7caf9830 | 434 | 'license': 'Standard YouTube License', |
0cb58b02 | 435 | 'creator': 'Icona Pop', |
2eb88d95 | 436 | } |
c108eb73 JMF |
437 | }, |
438 | { | |
4bc3a23e PH |
439 | 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ', |
440 | 'note': 'Test VEVO video with age protection (#956)', | |
441 | 'info_dict': { | |
442 | 'id': '07FYdnEawAQ', | |
443 | 'ext': 'mp4', | |
444 | 'upload_date': '20130703', | |
445 | 'title': 'Justin Timberlake - Tunnel Vision (Explicit)', | |
0cb58b02 | 446 | 'alt_title': 'Tunnel Vision', |
4bc3a23e | 447 | 'description': 'md5:64249768eec3bc4276236606ea996373', |
556dbe7f | 448 | 'duration': 419, |
4bc3a23e PH |
449 | 'uploader': 'justintimberlakeVEVO', |
450 | 'uploader_id': 'justintimberlakeVEVO', | |
ec85ded8 | 451 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO', |
7caf9830 | 452 | 'license': 'Standard YouTube License', |
0cb58b02 | 453 | 'creator': 'Justin Timberlake', |
34952f09 | 454 | 'age_limit': 18, |
c108eb73 JMF |
455 | } |
456 | }, | |
fccd3771 | 457 | { |
4bc3a23e PH |
458 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', |
459 | 'note': 'Embed-only video (#1746)', | |
460 | 'info_dict': { | |
461 | 'id': 'yZIXLfi8CZQ', | |
462 | 'ext': 'mp4', | |
463 | 'upload_date': '20120608', | |
464 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
465 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
466 | 'uploader': 'SET India', | |
94bfcd23 | 467 | 'uploader_id': 'setindia', |
ec85ded8 | 468 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia', |
7caf9830 | 469 | 'license': 'Standard YouTube License', |
94bfcd23 | 470 | 'age_limit': 18, |
fccd3771 PH |
471 | } |
472 | }, | |
11b56058 | 473 | { |
2d3d2997 | 474 | 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY', |
11b56058 PM |
475 | 'note': 'Use the first video ID in the URL', |
476 | 'info_dict': { | |
477 | 'id': 'BaW_jenozKc', | |
478 | 'ext': 'mp4', | |
479 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
480 | 'uploader': 'Philipp Hagemeister', | |
481 | 'uploader_id': 'phihag', | |
ec85ded8 | 482 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag', |
11b56058 | 483 | 'upload_date': '20121002', |
7caf9830 | 484 | 'license': 'Standard YouTube License', |
11b56058 PM |
485 | '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 .', |
486 | 'categories': ['Science & Technology'], | |
487 | 'tags': ['youtube-dl'], | |
556dbe7f | 488 | 'duration': 10, |
11b56058 PM |
489 | 'like_count': int, |
490 | 'dislike_count': int, | |
34a7de29 S |
491 | }, |
492 | 'params': { | |
493 | 'skip_download': True, | |
494 | }, | |
11b56058 | 495 | }, |
dd27fd17 | 496 | { |
2d3d2997 | 497 | 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I', |
4bc3a23e PH |
498 | 'note': '256k DASH audio (format 141) via DASH manifest', |
499 | 'info_dict': { | |
500 | 'id': 'a9LDPn-MO4I', | |
501 | 'ext': 'm4a', | |
502 | 'upload_date': '20121002', | |
503 | 'uploader_id': '8KVIDEO', | |
ec85ded8 | 504 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO', |
4bc3a23e PH |
505 | 'description': '', |
506 | 'uploader': '8KVIDEO', | |
7caf9830 | 507 | 'license': 'Standard YouTube License', |
4bc3a23e | 508 | 'title': 'UHDTV TEST 8K VIDEO.mp4' |
4919603f | 509 | }, |
4bc3a23e PH |
510 | 'params': { |
511 | 'youtube_include_dash_manifest': True, | |
512 | 'format': '141', | |
4919603f | 513 | }, |
de3c7fe0 | 514 | 'skip': 'format 141 not served anymore', |
dd27fd17 | 515 | }, |
3489b7d2 JMF |
516 | # DASH manifest with encrypted signature |
517 | { | |
78caa52a PH |
518 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', |
519 | 'info_dict': { | |
520 | 'id': 'IB3lcPjvWLA', | |
521 | 'ext': 'm4a', | |
b766eb27 JMF |
522 | 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson', |
523 | 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d', | |
556dbe7f | 524 | 'duration': 244, |
78caa52a PH |
525 | 'uploader': 'AfrojackVEVO', |
526 | 'uploader_id': 'AfrojackVEVO', | |
527 | 'upload_date': '20131011', | |
7caf9830 | 528 | 'license': 'Standard YouTube License', |
3489b7d2 | 529 | }, |
4bc3a23e | 530 | 'params': { |
78caa52a | 531 | 'youtube_include_dash_manifest': True, |
de3c7fe0 | 532 | 'format': '141/bestaudio[ext=m4a]', |
3489b7d2 JMF |
533 | }, |
534 | }, | |
aaeb86f6 S |
535 | # JS player signature function name containing $ |
536 | { | |
537 | 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM', | |
538 | 'info_dict': { | |
539 | 'id': 'nfWlot6h_JM', | |
540 | 'ext': 'm4a', | |
541 | 'title': 'Taylor Swift - Shake It Off', | |
0cb58b02 | 542 | 'alt_title': 'Shake It Off', |
f57b7835 | 543 | 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3', |
556dbe7f | 544 | 'duration': 242, |
aaeb86f6 S |
545 | 'uploader': 'TaylorSwiftVEVO', |
546 | 'uploader_id': 'TaylorSwiftVEVO', | |
547 | 'upload_date': '20140818', | |
7caf9830 | 548 | 'license': 'Standard YouTube License', |
0cb58b02 | 549 | 'creator': 'Taylor Swift', |
aaeb86f6 S |
550 | }, |
551 | 'params': { | |
552 | 'youtube_include_dash_manifest': True, | |
de3c7fe0 | 553 | 'format': '141/bestaudio[ext=m4a]', |
aaeb86f6 S |
554 | }, |
555 | }, | |
aa79ac0c PH |
556 | # Controversy video |
557 | { | |
558 | 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8', | |
559 | 'info_dict': { | |
560 | 'id': 'T4XJQO3qol8', | |
561 | 'ext': 'mp4', | |
556dbe7f | 562 | 'duration': 219, |
aa79ac0c PH |
563 | 'upload_date': '20100909', |
564 | 'uploader': 'The Amazing Atheist', | |
565 | 'uploader_id': 'TheAmazingAtheist', | |
ec85ded8 | 566 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist', |
7caf9830 | 567 | 'license': 'Standard YouTube License', |
aa79ac0c PH |
568 | 'title': 'Burning Everyone\'s Koran', |
569 | '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', | |
570 | } | |
c522adb1 JMF |
571 | }, |
572 | # Normal age-gate video (No vevo, embed allowed) | |
573 | { | |
2d3d2997 | 574 | 'url': 'https://youtube.com/watch?v=HtVdAasjOgU', |
c522adb1 JMF |
575 | 'info_dict': { |
576 | 'id': 'HtVdAasjOgU', | |
577 | 'ext': 'mp4', | |
578 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
ec85ded8 | 579 | 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', |
556dbe7f | 580 | 'duration': 142, |
c522adb1 JMF |
581 | 'uploader': 'The Witcher', |
582 | 'uploader_id': 'WitcherGame', | |
ec85ded8 | 583 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame', |
c522adb1 | 584 | 'upload_date': '20140605', |
7caf9830 | 585 | 'license': 'Standard YouTube License', |
34952f09 | 586 | 'age_limit': 18, |
c522adb1 JMF |
587 | }, |
588 | }, | |
fccae2b9 S |
589 | # Age-gate video with encrypted signature |
590 | { | |
2d3d2997 | 591 | 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU', |
fccae2b9 S |
592 | 'info_dict': { |
593 | 'id': '6kLq3WMV1nU', | |
594 | 'ext': 'mp4', | |
595 | 'title': 'Dedication To My Ex (Miss That) (Lyric Video)', | |
596 | 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', | |
556dbe7f | 597 | 'duration': 247, |
fccae2b9 S |
598 | 'uploader': 'LloydVEVO', |
599 | 'uploader_id': 'LloydVEVO', | |
ec85ded8 | 600 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO', |
fccae2b9 | 601 | 'upload_date': '20110629', |
7caf9830 | 602 | 'license': 'Standard YouTube License', |
34952f09 | 603 | 'age_limit': 18, |
fccae2b9 S |
604 | }, |
605 | }, | |
774e208f PH |
606 | # video_info is None (https://github.com/rg3/youtube-dl/issues/4421) |
607 | { | |
608 | 'url': '__2ABJjxzNo', | |
609 | 'info_dict': { | |
610 | 'id': '__2ABJjxzNo', | |
611 | 'ext': 'mp4', | |
556dbe7f | 612 | 'duration': 266, |
774e208f PH |
613 | 'upload_date': '20100430', |
614 | 'uploader_id': 'deadmau5', | |
ec85ded8 | 615 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5', |
0cb58b02 | 616 | 'creator': 'deadmau5', |
774e208f PH |
617 | 'description': 'md5:12c56784b8032162bb936a5f76d55360', |
618 | 'uploader': 'deadmau5', | |
7caf9830 | 619 | 'license': 'Standard YouTube License', |
774e208f | 620 | 'title': 'Deadmau5 - Some Chords (HD)', |
0cb58b02 | 621 | 'alt_title': 'Some Chords', |
774e208f PH |
622 | }, |
623 | 'expected_warnings': [ | |
624 | 'DASH manifest missing', | |
625 | ] | |
e52a40ab PH |
626 | }, |
627 | # Olympics (https://github.com/rg3/youtube-dl/issues/4431) | |
628 | { | |
629 | 'url': 'lqQg6PlCWgI', | |
630 | 'info_dict': { | |
631 | 'id': 'lqQg6PlCWgI', | |
632 | 'ext': 'mp4', | |
556dbe7f | 633 | 'duration': 6085, |
90227264 | 634 | 'upload_date': '20150827', |
cbe2bd91 | 635 | 'uploader_id': 'olympic', |
ec85ded8 | 636 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic', |
7caf9830 | 637 | 'license': 'Standard YouTube License', |
cbe2bd91 | 638 | 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', |
be49068d | 639 | 'uploader': 'Olympic', |
cbe2bd91 PH |
640 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', |
641 | }, | |
642 | 'params': { | |
643 | 'skip_download': 'requires avconv', | |
e52a40ab | 644 | } |
cbe2bd91 | 645 | }, |
6271f1ca PH |
646 | # Non-square pixels |
647 | { | |
648 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
649 | 'info_dict': { | |
650 | 'id': '_b-2C3KPAM0', | |
651 | 'ext': 'mp4', | |
652 | 'stretched_ratio': 16 / 9., | |
556dbe7f | 653 | 'duration': 85, |
6271f1ca PH |
654 | 'upload_date': '20110310', |
655 | 'uploader_id': 'AllenMeow', | |
ec85ded8 | 656 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow', |
6271f1ca PH |
657 | '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', |
658 | 'uploader': '孫艾倫', | |
7caf9830 | 659 | 'license': 'Standard YouTube License', |
6271f1ca PH |
660 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', |
661 | }, | |
06b491eb S |
662 | }, |
663 | # url_encoded_fmt_stream_map is empty string | |
664 | { | |
665 | 'url': 'qEJwOuvDf7I', | |
666 | 'info_dict': { | |
667 | 'id': 'qEJwOuvDf7I', | |
f57b7835 | 668 | 'ext': 'webm', |
06b491eb S |
669 | 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', |
670 | 'description': '', | |
671 | 'upload_date': '20150404', | |
672 | 'uploader_id': 'spbelect', | |
673 | 'uploader': 'Наблюдатели Петербурга', | |
674 | }, | |
675 | 'params': { | |
676 | 'skip_download': 'requires avconv', | |
e323cf3f S |
677 | }, |
678 | 'skip': 'This live event has ended.', | |
06b491eb | 679 | }, |
da77d856 S |
680 | # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097) |
681 | { | |
682 | 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y', | |
683 | 'info_dict': { | |
684 | 'id': 'FIl7x6_3R5Y', | |
685 | 'ext': 'mp4', | |
686 | 'title': 'md5:7b81415841e02ecd4313668cde88737a', | |
687 | 'description': 'md5:116377fd2963b81ec4ce64b542173306', | |
556dbe7f | 688 | 'duration': 220, |
da77d856 S |
689 | 'upload_date': '20150625', |
690 | 'uploader_id': 'dorappi2000', | |
ec85ded8 | 691 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000', |
da77d856 | 692 | 'uploader': 'dorappi2000', |
7caf9830 | 693 | 'license': 'Standard YouTube License', |
be49068d | 694 | 'formats': 'mincount:32', |
da77d856 | 695 | }, |
2ee8f5d8 | 696 | }, |
8a1a26ce YCH |
697 | # DASH manifest with segment_list |
698 | { | |
699 | 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8', | |
700 | 'md5': '8ce563a1d667b599d21064e982ab9e31', | |
701 | 'info_dict': { | |
702 | 'id': 'CsmdDsKjzN8', | |
703 | 'ext': 'mp4', | |
17ee98e1 | 704 | 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510 |
8a1a26ce YCH |
705 | 'uploader': 'Airtek', |
706 | 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', | |
707 | 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ', | |
7caf9830 | 708 | 'license': 'Standard YouTube License', |
8a1a26ce YCH |
709 | 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', |
710 | }, | |
711 | 'params': { | |
712 | 'youtube_include_dash_manifest': True, | |
713 | 'format': '135', # bestvideo | |
be49068d S |
714 | }, |
715 | 'skip': 'This live event has ended.', | |
2ee8f5d8 | 716 | }, |
cf7e015f S |
717 | { |
718 | # Multifeed videos (multiple cameras), URL is for Main Camera | |
719 | 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs', | |
720 | 'info_dict': { | |
721 | 'id': 'jqWvoWXjCVs', | |
722 | 'title': 'teamPGP: Rocket League Noob Stream', | |
723 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
724 | }, | |
725 | 'playlist': [{ | |
726 | 'info_dict': { | |
727 | 'id': 'jqWvoWXjCVs', | |
728 | 'ext': 'mp4', | |
729 | 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)', | |
730 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 731 | 'duration': 7335, |
cf7e015f S |
732 | 'upload_date': '20150721', |
733 | 'uploader': 'Beer Games Beer', | |
734 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 735 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 736 | 'license': 'Standard YouTube License', |
cf7e015f S |
737 | }, |
738 | }, { | |
739 | 'info_dict': { | |
740 | 'id': '6h8e8xoXJzg', | |
741 | 'ext': 'mp4', | |
742 | 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)', | |
743 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 744 | 'duration': 7337, |
cf7e015f S |
745 | 'upload_date': '20150721', |
746 | 'uploader': 'Beer Games Beer', | |
747 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 748 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 749 | 'license': 'Standard YouTube License', |
cf7e015f S |
750 | }, |
751 | }, { | |
752 | 'info_dict': { | |
753 | 'id': 'PUOgX5z9xZw', | |
754 | 'ext': 'mp4', | |
755 | 'title': 'teamPGP: Rocket League Noob Stream (grizzle)', | |
756 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 757 | 'duration': 7337, |
cf7e015f S |
758 | 'upload_date': '20150721', |
759 | 'uploader': 'Beer Games Beer', | |
760 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 761 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 762 | 'license': 'Standard YouTube License', |
cf7e015f S |
763 | }, |
764 | }, { | |
765 | 'info_dict': { | |
766 | 'id': 'teuwxikvS5k', | |
767 | 'ext': 'mp4', | |
768 | 'title': 'teamPGP: Rocket League Noob Stream (zim)', | |
769 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
556dbe7f | 770 | 'duration': 7334, |
cf7e015f S |
771 | 'upload_date': '20150721', |
772 | 'uploader': 'Beer Games Beer', | |
773 | 'uploader_id': 'beergamesbeer', | |
ec85ded8 | 774 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer', |
7caf9830 | 775 | 'license': 'Standard YouTube License', |
cf7e015f S |
776 | }, |
777 | }], | |
778 | 'params': { | |
779 | 'skip_download': True, | |
780 | }, | |
cbaed4bb | 781 | }, |
f9f49d87 S |
782 | { |
783 | # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536) | |
784 | 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo', | |
785 | 'info_dict': { | |
786 | 'id': 'gVfLd0zydlo', | |
787 | 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30', | |
788 | }, | |
789 | 'playlist_count': 2, | |
be49068d | 790 | 'skip': 'Not multifeed anymore', |
f9f49d87 | 791 | }, |
cbaed4bb | 792 | { |
2d3d2997 | 793 | 'url': 'https://vid.plus/FlRa-iH7PGw', |
cbaed4bb | 794 | 'only_matching': True, |
0e49d9a6 | 795 | }, |
6d4fc66b | 796 | { |
2d3d2997 | 797 | 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html', |
6d4fc66b S |
798 | 'only_matching': True, |
799 | }, | |
0e49d9a6 | 800 | { |
61f92af1 | 801 | # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468) |
a8776b10 S |
802 | # Also tests cut-off URL expansion in video description (see |
803 | # https://github.com/rg3/youtube-dl/issues/1892, | |
804 | # https://github.com/rg3/youtube-dl/issues/8164) | |
0e49d9a6 LL |
805 | 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg', |
806 | 'info_dict': { | |
807 | 'id': 'lsguqyKfVQg', | |
808 | 'ext': 'mp4', | |
809 | 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21', | |
0cb58b02 | 810 | 'alt_title': 'Dark Walk', |
0e49d9a6 | 811 | 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a', |
556dbe7f | 812 | 'duration': 133, |
0e49d9a6 LL |
813 | 'upload_date': '20151119', |
814 | 'uploader_id': 'IronSoulElf', | |
ec85ded8 | 815 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf', |
0e49d9a6 | 816 | 'uploader': 'IronSoulElf', |
7caf9830 | 817 | 'license': 'Standard YouTube License', |
0cb58b02 | 818 | 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan', |
0e49d9a6 LL |
819 | }, |
820 | 'params': { | |
821 | 'skip_download': True, | |
822 | }, | |
823 | }, | |
61f92af1 S |
824 | { |
825 | # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468) | |
826 | 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8', | |
827 | 'only_matching': True, | |
828 | }, | |
313dfc45 LL |
829 | { |
830 | # Video with yt:stretch=17:0 | |
831 | 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM', | |
832 | 'info_dict': { | |
833 | 'id': 'Q39EVAstoRM', | |
834 | 'ext': 'mp4', | |
835 | 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4', | |
836 | 'description': 'md5:ee18a25c350637c8faff806845bddee9', | |
837 | 'upload_date': '20151107', | |
838 | 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA', | |
839 | 'uploader': 'CH GAMER DROID', | |
840 | }, | |
841 | 'params': { | |
842 | 'skip_download': True, | |
843 | }, | |
be49068d | 844 | 'skip': 'This video does not exist.', |
313dfc45 | 845 | }, |
7caf9830 S |
846 | { |
847 | # Video licensed under Creative Commons | |
848 | 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA', | |
849 | 'info_dict': { | |
850 | 'id': 'M4gD1WSo5mA', | |
851 | 'ext': 'mp4', | |
852 | 'title': 'md5:e41008789470fc2533a3252216f1c1d1', | |
853 | 'description': 'md5:a677553cf0840649b731a3024aeff4cc', | |
556dbe7f | 854 | 'duration': 721, |
7caf9830 S |
855 | 'upload_date': '20150127', |
856 | 'uploader_id': 'BerkmanCenter', | |
ec85ded8 | 857 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter', |
556dbe7f | 858 | 'uploader': 'The Berkman Klein Center for Internet & Society', |
7caf9830 S |
859 | 'license': 'Creative Commons Attribution license (reuse allowed)', |
860 | }, | |
861 | 'params': { | |
862 | 'skip_download': True, | |
863 | }, | |
864 | }, | |
fd050249 S |
865 | { |
866 | # Channel-like uploader_url | |
867 | 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg', | |
868 | 'info_dict': { | |
869 | 'id': 'eQcmzGIKrzg', | |
870 | 'ext': 'mp4', | |
871 | 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders', | |
872 | 'description': 'md5:dda0d780d5a6e120758d1711d062a867', | |
556dbe7f | 873 | 'duration': 4060, |
fd050249 S |
874 | 'upload_date': '20151119', |
875 | 'uploader': 'Bernie 2016', | |
876 | 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg', | |
ec85ded8 | 877 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg', |
fd050249 S |
878 | 'license': 'Creative Commons Attribution license (reuse allowed)', |
879 | }, | |
880 | 'params': { | |
881 | 'skip_download': True, | |
882 | }, | |
883 | }, | |
040ac686 S |
884 | { |
885 | 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY', | |
886 | 'only_matching': True, | |
7f29cf54 S |
887 | }, |
888 | { | |
889 | # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059) | |
890 | 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo', | |
891 | 'only_matching': True, | |
6496ccb4 S |
892 | }, |
893 | { | |
894 | # Rental video preview | |
895 | 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg', | |
896 | 'info_dict': { | |
897 | 'id': 'uGpuVWrhIzE', | |
898 | 'ext': 'mp4', | |
899 | 'title': 'Piku - Trailer', | |
900 | 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb', | |
901 | 'upload_date': '20150811', | |
902 | 'uploader': 'FlixMatrix', | |
903 | 'uploader_id': 'FlixMatrixKaravan', | |
ec85ded8 | 904 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan', |
6496ccb4 S |
905 | 'license': 'Standard YouTube License', |
906 | }, | |
907 | 'params': { | |
908 | 'skip_download': True, | |
909 | }, | |
022a5d66 | 910 | }, |
12afdc2a S |
911 | { |
912 | # YouTube Red video with episode data | |
913 | 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4', | |
914 | 'info_dict': { | |
915 | 'id': 'iqKdEhx-dD4', | |
916 | 'ext': 'mp4', | |
917 | 'title': 'Isolation - Mind Field (Ep 1)', | |
556dbe7f S |
918 | 'description': 'md5:8013b7ddea787342608f63a13ddc9492', |
919 | 'duration': 2085, | |
12afdc2a S |
920 | 'upload_date': '20170118', |
921 | 'uploader': 'Vsauce', | |
922 | 'uploader_id': 'Vsauce', | |
923 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce', | |
924 | 'license': 'Standard YouTube License', | |
925 | 'series': 'Mind Field', | |
926 | 'season_number': 1, | |
927 | 'episode_number': 1, | |
928 | }, | |
929 | 'params': { | |
930 | 'skip_download': True, | |
931 | }, | |
932 | 'expected_warnings': [ | |
933 | 'Skipping DASH manifest', | |
934 | ], | |
935 | }, | |
022a5d66 S |
936 | { |
937 | # itag 212 | |
938 | 'url': '1t24XAntNCY', | |
939 | 'only_matching': True, | |
fd5c4aab S |
940 | }, |
941 | { | |
942 | # geo restricted to JP | |
943 | 'url': 'sJL6WA-aGkQ', | |
944 | 'only_matching': True, | |
945 | }, | |
d0ba5587 S |
946 | { |
947 | 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM', | |
948 | 'only_matching': True, | |
949 | }, | |
2eb88d95 PH |
950 | ] |
951 | ||
e0df6211 PH |
952 | def __init__(self, *args, **kwargs): |
953 | super(YoutubeIE, self).__init__(*args, **kwargs) | |
83799698 | 954 | self._player_cache = {} |
e0df6211 | 955 | |
c5e8d7af PH |
956 | def report_video_info_webpage_download(self, video_id): |
957 | """Report attempt to download video info webpage.""" | |
69ea8ca4 | 958 | self.to_screen('%s: Downloading video info webpage' % video_id) |
c5e8d7af | 959 | |
c5e8d7af PH |
960 | def report_information_extraction(self, video_id): |
961 | """Report attempt to extract video information.""" | |
69ea8ca4 | 962 | self.to_screen('%s: Extracting video information' % video_id) |
c5e8d7af PH |
963 | |
964 | def report_unavailable_format(self, video_id, format): | |
965 | """Report extracted video URL.""" | |
69ea8ca4 | 966 | self.to_screen('%s: Format %s not available' % (video_id, format)) |
c5e8d7af PH |
967 | |
968 | def report_rtmp_download(self): | |
969 | """Indicate the download will use the RTMP protocol.""" | |
69ea8ca4 | 970 | self.to_screen('RTMP download detected') |
c5e8d7af | 971 | |
60064c53 PH |
972 | def _signature_cache_id(self, example_sig): |
973 | """ Return a string representation of a signature """ | |
78caa52a | 974 | return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) |
60064c53 PH |
975 | |
976 | def _extract_signature_function(self, video_id, player_url, example_sig): | |
cf010131 | 977 | id_m = re.match( |
e31fed95 | 978 | r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$', |
cf010131 | 979 | player_url) |
c081b35c PH |
980 | if not id_m: |
981 | raise ExtractorError('Cannot identify player %r' % player_url) | |
e0df6211 PH |
982 | player_type = id_m.group('ext') |
983 | player_id = id_m.group('id') | |
984 | ||
c4417ddb | 985 | # Read from filesystem cache |
60064c53 PH |
986 | func_id = '%s_%s_%s' % ( |
987 | player_type, player_id, self._signature_cache_id(example_sig)) | |
c4417ddb | 988 | assert os.path.basename(func_id) == func_id |
a0e07d31 | 989 | |
69ea8ca4 | 990 | cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) |
a0e07d31 | 991 | if cache_spec is not None: |
78caa52a | 992 | return lambda s: ''.join(s[i] for i in cache_spec) |
83799698 | 993 | |
6d1a55a5 PH |
994 | download_note = ( |
995 | 'Downloading player %s' % player_url | |
996 | if self._downloader.params.get('verbose') else | |
997 | 'Downloading %s player %s' % (player_type, player_id) | |
998 | ) | |
e0df6211 PH |
999 | if player_type == 'js': |
1000 | code = self._download_webpage( | |
1001 | player_url, video_id, | |
6d1a55a5 | 1002 | note=download_note, |
69ea8ca4 | 1003 | errnote='Download of %s failed' % player_url) |
83799698 | 1004 | res = self._parse_sig_js(code) |
c4417ddb | 1005 | elif player_type == 'swf': |
e0df6211 PH |
1006 | urlh = self._request_webpage( |
1007 | player_url, video_id, | |
6d1a55a5 | 1008 | note=download_note, |
69ea8ca4 | 1009 | errnote='Download of %s failed' % player_url) |
e0df6211 | 1010 | code = urlh.read() |
83799698 | 1011 | res = self._parse_sig_swf(code) |
e0df6211 PH |
1012 | else: |
1013 | assert False, 'Invalid player type %r' % player_type | |
1014 | ||
785521bf PH |
1015 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
1016 | cache_res = res(test_string) | |
1017 | cache_spec = [ord(c) for c in cache_res] | |
83799698 | 1018 | |
69ea8ca4 | 1019 | self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) |
83799698 PH |
1020 | return res |
1021 | ||
60064c53 | 1022 | def _print_sig_code(self, func, example_sig): |
edf3e38e PH |
1023 | def gen_sig_code(idxs): |
1024 | def _genslice(start, end, step): | |
78caa52a | 1025 | starts = '' if start == 0 else str(start) |
8bcc8756 | 1026 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' |
69ea8ca4 | 1027 | steps = '' if step == 1 else (':%d' % step) |
78caa52a | 1028 | return 's[%s%s%s]' % (starts, ends, steps) |
edf3e38e PH |
1029 | |
1030 | step = None | |
7af808a5 PH |
1031 | # Quelch pyflakes warnings - start will be set when step is set |
1032 | start = '(Never used)' | |
edf3e38e PH |
1033 | for i, prev in zip(idxs[1:], idxs[:-1]): |
1034 | if step is not None: | |
1035 | if i - prev == step: | |
1036 | continue | |
1037 | yield _genslice(start, prev, step) | |
1038 | step = None | |
1039 | continue | |
1040 | if i - prev in [-1, 1]: | |
1041 | step = i - prev | |
1042 | start = prev | |
1043 | continue | |
1044 | else: | |
78caa52a | 1045 | yield 's[%d]' % prev |
edf3e38e | 1046 | if step is None: |
78caa52a | 1047 | yield 's[%d]' % i |
edf3e38e PH |
1048 | else: |
1049 | yield _genslice(start, i, step) | |
1050 | ||
78caa52a | 1051 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
c705320f | 1052 | cache_res = func(test_string) |
edf3e38e | 1053 | cache_spec = [ord(c) for c in cache_res] |
78caa52a | 1054 | expr_code = ' + '.join(gen_sig_code(cache_spec)) |
60064c53 PH |
1055 | signature_id_tuple = '(%s)' % ( |
1056 | ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) | |
69ea8ca4 | 1057 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' |
78caa52a | 1058 | ' return %s\n') % (signature_id_tuple, expr_code) |
69ea8ca4 | 1059 | self.to_screen('Extracted signature function:\n' + code) |
edf3e38e | 1060 | |
e0df6211 PH |
1061 | def _parse_sig_js(self, jscode): |
1062 | funcname = self._search_regex( | |
3c90cc8b S |
1063 | (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(', |
1064 | r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\('), | |
1065 | jscode, 'Initial JS player signature function name', group='sig') | |
2b25cb5d PH |
1066 | |
1067 | jsi = JSInterpreter(jscode) | |
1068 | initial_function = jsi.extract_function(funcname) | |
e0df6211 PH |
1069 | return lambda s: initial_function([s]) |
1070 | ||
1071 | def _parse_sig_swf(self, file_contents): | |
54256267 | 1072 | swfi = SWFInterpreter(file_contents) |
78caa52a | 1073 | TARGET_CLASSNAME = 'SignatureDecipher' |
54256267 | 1074 | searched_class = swfi.extract_class(TARGET_CLASSNAME) |
78caa52a | 1075 | initial_function = swfi.extract_function(searched_class, 'decipher') |
e0df6211 PH |
1076 | return lambda s: initial_function([s]) |
1077 | ||
83799698 | 1078 | def _decrypt_signature(self, s, video_id, player_url, age_gate=False): |
257a2501 | 1079 | """Turn the encrypted s field into a working signature""" |
6b37f0be | 1080 | |
c8bf86d5 | 1081 | if player_url is None: |
69ea8ca4 | 1082 | raise ExtractorError('Cannot decrypt signature without player_url') |
920de7a2 | 1083 | |
69ea8ca4 | 1084 | if player_url.startswith('//'): |
78caa52a | 1085 | player_url = 'https:' + player_url |
3c90cc8b S |
1086 | elif not re.match(r'https?://', player_url): |
1087 | player_url = compat_urlparse.urljoin( | |
1088 | 'https://www.youtube.com', player_url) | |
c8bf86d5 | 1089 | try: |
62af3a0e | 1090 | player_id = (player_url, self._signature_cache_id(s)) |
c8bf86d5 PH |
1091 | if player_id not in self._player_cache: |
1092 | func = self._extract_signature_function( | |
60064c53 | 1093 | video_id, player_url, s |
c8bf86d5 PH |
1094 | ) |
1095 | self._player_cache[player_id] = func | |
1096 | func = self._player_cache[player_id] | |
1097 | if self._downloader.params.get('youtube_print_sig_code'): | |
60064c53 | 1098 | self._print_sig_code(func, s) |
c8bf86d5 PH |
1099 | return func(s) |
1100 | except Exception as e: | |
1101 | tb = traceback.format_exc() | |
1102 | raise ExtractorError( | |
78caa52a | 1103 | 'Signature extraction failed: ' + tb, cause=e) |
e0df6211 | 1104 | |
360e1ca5 | 1105 | def _get_subtitles(self, video_id, webpage): |
de7f3446 | 1106 | try: |
60e47a26 | 1107 | subs_doc = self._download_xml( |
38c2e5b8 | 1108 | 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, |
7fad1c63 JMF |
1109 | video_id, note=False) |
1110 | except ExtractorError as err: | |
9b9c5355 | 1111 | self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err)) |
de7f3446 | 1112 | return {} |
de7f3446 JMF |
1113 | |
1114 | sub_lang_list = {} | |
60e47a26 JMF |
1115 | for track in subs_doc.findall('track'): |
1116 | lang = track.attrib['lang_code'] | |
7e660ac1 LD |
1117 | if lang in sub_lang_list: |
1118 | continue | |
360e1ca5 | 1119 | sub_formats = [] |
23d17e4b | 1120 | for ext in self._SUBTITLE_FORMATS: |
15707c7e | 1121 | params = compat_urllib_parse_urlencode({ |
360e1ca5 JMF |
1122 | 'lang': lang, |
1123 | 'v': video_id, | |
1124 | 'fmt': ext, | |
1125 | 'name': track.attrib['name'].encode('utf-8'), | |
1126 | }) | |
1127 | sub_formats.append({ | |
1128 | 'url': 'https://www.youtube.com/api/timedtext?' + params, | |
1129 | 'ext': ext, | |
1130 | }) | |
1131 | sub_lang_list[lang] = sub_formats | |
de7f3446 | 1132 | if not sub_lang_list: |
69ea8ca4 | 1133 | self._downloader.report_warning('video doesn\'t have subtitles') |
de7f3446 JMF |
1134 | return {} |
1135 | return sub_lang_list | |
1136 | ||
a72778d3 S |
1137 | def _get_ytplayer_config(self, video_id, webpage): |
1138 | patterns = ( | |
526b3b07 S |
1139 | # User data may contain arbitrary character sequences that may affect |
1140 | # JSON extraction with regex, e.g. when '};' is contained the second | |
1141 | # regex won't capture the whole JSON. Yet working around by trying more | |
1142 | # concrete regex first keeping in mind proper quoted string handling | |
1143 | # to be implemented in future that will replace this workaround (see | |
1144 | # https://github.com/rg3/youtube-dl/issues/7468, | |
1145 | # https://github.com/rg3/youtube-dl/pull/7599) | |
a72778d3 S |
1146 | r';ytplayer\.config\s*=\s*({.+?});ytplayer', |
1147 | r';ytplayer\.config\s*=\s*({.+?});', | |
1148 | ) | |
1149 | config = self._search_regex( | |
1150 | patterns, webpage, 'ytplayer.config', default=None) | |
1151 | if config: | |
1152 | return self._parse_json( | |
1153 | uppercase_escape(config), video_id, fatal=False) | |
0e49d9a6 | 1154 | |
360e1ca5 | 1155 | def _get_automatic_captions(self, video_id, webpage): |
de7f3446 JMF |
1156 | """We need the webpage for getting the captions url, pass it as an |
1157 | argument to speed up the process.""" | |
69ea8ca4 | 1158 | self.to_screen('%s: Looking for automatic captions' % video_id) |
a72778d3 | 1159 | player_config = self._get_ytplayer_config(video_id, webpage) |
78caa52a | 1160 | err_msg = 'Couldn\'t find automatic captions for %s' % video_id |
a72778d3 | 1161 | if not player_config: |
de7f3446 JMF |
1162 | self._downloader.report_warning(err_msg) |
1163 | return {} | |
de7f3446 | 1164 | try: |
0792d563 | 1165 | args = player_config['args'] |
b78b292f S |
1166 | caption_url = args.get('ttsurl') |
1167 | if caption_url: | |
1168 | timestamp = args['timestamp'] | |
1169 | # We get the available subtitles | |
15707c7e | 1170 | list_params = compat_urllib_parse_urlencode({ |
b78b292f S |
1171 | 'type': 'list', |
1172 | 'tlangs': 1, | |
1173 | 'asrs': 1, | |
1174 | }) | |
1175 | list_url = caption_url + '&' + list_params | |
1176 | caption_list = self._download_xml(list_url, video_id) | |
1177 | original_lang_node = caption_list.find('track') | |
1178 | if original_lang_node is None: | |
1179 | self._downloader.report_warning('Video doesn\'t have automatic captions') | |
1180 | return {} | |
1181 | original_lang = original_lang_node.attrib['lang_code'] | |
1182 | caption_kind = original_lang_node.attrib.get('kind', '') | |
1183 | ||
1184 | sub_lang_list = {} | |
1185 | for lang_node in caption_list.findall('target'): | |
1186 | sub_lang = lang_node.attrib['lang_code'] | |
1187 | sub_formats = [] | |
1188 | for ext in self._SUBTITLE_FORMATS: | |
15707c7e | 1189 | params = compat_urllib_parse_urlencode({ |
b78b292f S |
1190 | 'lang': original_lang, |
1191 | 'tlang': sub_lang, | |
1192 | 'fmt': ext, | |
1193 | 'ts': timestamp, | |
1194 | 'kind': caption_kind, | |
1195 | }) | |
1196 | sub_formats.append({ | |
1197 | 'url': caption_url + '&' + params, | |
1198 | 'ext': ext, | |
1199 | }) | |
1200 | sub_lang_list[sub_lang] = sub_formats | |
1201 | return sub_lang_list | |
1202 | ||
1203 | # Some videos don't provide ttsurl but rather caption_tracks and | |
1204 | # caption_translation_languages (e.g. 20LmZk1hakA) | |
1205 | caption_tracks = args['caption_tracks'] | |
1206 | caption_translation_languages = args['caption_translation_languages'] | |
1207 | caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0] | |
15707c7e | 1208 | parsed_caption_url = compat_urllib_parse_urlparse(caption_url) |
b78b292f | 1209 | caption_qs = compat_parse_qs(parsed_caption_url.query) |
055e6f36 JMF |
1210 | |
1211 | sub_lang_list = {} | |
b78b292f S |
1212 | for lang in caption_translation_languages.split(','): |
1213 | lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang)) | |
1214 | sub_lang = lang_qs.get('lc', [None])[0] | |
1215 | if not sub_lang: | |
1216 | continue | |
360e1ca5 | 1217 | sub_formats = [] |
23d17e4b | 1218 | for ext in self._SUBTITLE_FORMATS: |
b78b292f S |
1219 | caption_qs.update({ |
1220 | 'tlang': [sub_lang], | |
1221 | 'fmt': [ext], | |
360e1ca5 | 1222 | }) |
b78b292f | 1223 | sub_url = compat_urlparse.urlunparse(parsed_caption_url._replace( |
15707c7e | 1224 | query=compat_urllib_parse_urlencode(caption_qs, True))) |
360e1ca5 | 1225 | sub_formats.append({ |
b78b292f | 1226 | 'url': sub_url, |
360e1ca5 JMF |
1227 | 'ext': ext, |
1228 | }) | |
1229 | sub_lang_list[sub_lang] = sub_formats | |
055e6f36 | 1230 | return sub_lang_list |
de7f3446 JMF |
1231 | # An extractor error can be raise by the download process if there are |
1232 | # no automatic captions but there are subtitles | |
1233 | except (KeyError, ExtractorError): | |
1234 | self._downloader.report_warning(err_msg) | |
1235 | return {} | |
1236 | ||
d77ab8e2 S |
1237 | def _mark_watched(self, video_id, video_info): |
1238 | playback_url = video_info.get('videostats_playback_base_url', [None])[0] | |
1239 | if not playback_url: | |
1240 | return | |
1241 | parsed_playback_url = compat_urlparse.urlparse(playback_url) | |
1242 | qs = compat_urlparse.parse_qs(parsed_playback_url.query) | |
1243 | ||
1244 | # cpn generation algorithm is reverse engineered from base.js. | |
1245 | # In fact it works even with dummy cpn. | |
1246 | CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_' | |
1247 | cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))) | |
1248 | ||
1249 | qs.update({ | |
1250 | 'ver': ['2'], | |
1251 | 'cpn': [cpn], | |
1252 | }) | |
1253 | playback_url = compat_urlparse.urlunparse( | |
15707c7e | 1254 | parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True))) |
d77ab8e2 S |
1255 | |
1256 | self._download_webpage( | |
1257 | playback_url, video_id, 'Marking watched', | |
1258 | 'Unable to mark watched', fatal=False) | |
1259 | ||
97665381 PH |
1260 | @classmethod |
1261 | def extract_id(cls, url): | |
1262 | mobj = re.match(cls._VALID_URL, url, re.VERBOSE) | |
c5e8d7af | 1263 | if mobj is None: |
69ea8ca4 | 1264 | raise ExtractorError('Invalid URL: %s' % url) |
c5e8d7af PH |
1265 | video_id = mobj.group(2) |
1266 | return video_id | |
1267 | ||
1fb07d10 JG |
1268 | def _extract_annotations(self, video_id): |
1269 | url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id | |
69ea8ca4 | 1270 | return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.') |
1fb07d10 | 1271 | |
9cafc3fd S |
1272 | @staticmethod |
1273 | def _extract_chapters(description, duration): | |
1274 | if not description: | |
1275 | return None | |
1276 | chapter_lines = re.findall( | |
1277 | r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)', | |
1278 | description) | |
1279 | if not chapter_lines: | |
1280 | return None | |
1281 | chapters = [] | |
1282 | for next_num, (chapter_line, time_point) in enumerate( | |
1283 | chapter_lines, start=1): | |
1284 | start_time = parse_duration(time_point) | |
1285 | if start_time is None: | |
1286 | continue | |
1287 | end_time = (duration if next_num == len(chapter_lines) | |
1288 | else parse_duration(chapter_lines[next_num][1])) | |
1289 | if end_time is None: | |
1290 | continue | |
1291 | chapter_title = re.sub( | |
1292 | r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-') | |
1293 | chapter_title = re.sub(r'\s+', ' ', chapter_title) | |
1294 | chapters.append({ | |
1295 | 'start_time': start_time, | |
1296 | 'end_time': end_time, | |
1297 | 'title': chapter_title, | |
1298 | }) | |
1299 | return chapters | |
1300 | ||
c5e8d7af | 1301 | def _real_extract(self, url): |
cf7e015f S |
1302 | url, smuggled_data = unsmuggle_url(url, {}) |
1303 | ||
7e8c0af0 | 1304 | proto = ( |
78caa52a PH |
1305 | 'http' if self._downloader.params.get('prefer_insecure', False) |
1306 | else 'https') | |
7e8c0af0 | 1307 | |
7c80519c | 1308 | start_time = None |
297a564b | 1309 | end_time = None |
7c80519c JMF |
1310 | parsed_url = compat_urllib_parse_urlparse(url) |
1311 | for component in [parsed_url.fragment, parsed_url.query]: | |
1312 | query = compat_parse_qs(component) | |
297a564b | 1313 | if start_time is None and 't' in query: |
7c80519c | 1314 | start_time = parse_duration(query['t'][0]) |
2929fa0e JMF |
1315 | if start_time is None and 'start' in query: |
1316 | start_time = parse_duration(query['start'][0]) | |
297a564b JMF |
1317 | if end_time is None and 'end' in query: |
1318 | end_time = parse_duration(query['end'][0]) | |
7c80519c | 1319 | |
c5e8d7af PH |
1320 | # Extract original video URL from URL with redirection, like age verification, using next_url parameter |
1321 | mobj = re.search(self._NEXT_URL_RE, url) | |
1322 | if mobj: | |
7fd002c0 | 1323 | url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/') |
97665381 | 1324 | video_id = self.extract_id(url) |
c5e8d7af PH |
1325 | |
1326 | # Get video webpage | |
aa79ac0c | 1327 | url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id |
a1f934b1 | 1328 | video_webpage = self._download_webpage(url, video_id) |
c5e8d7af PH |
1329 | |
1330 | # Attempt to extract SWF player URL | |
e0df6211 | 1331 | mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) |
c5e8d7af PH |
1332 | if mobj is not None: |
1333 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) | |
1334 | else: | |
1335 | player_url = None | |
1336 | ||
d8d24a92 S |
1337 | dash_mpds = [] |
1338 | ||
1339 | def add_dash_mpd(video_info): | |
1340 | dash_mpd = video_info.get('dashmpd') | |
1341 | if dash_mpd and dash_mpd[0] not in dash_mpds: | |
1342 | dash_mpds.append(dash_mpd[0]) | |
1343 | ||
c5e8d7af | 1344 | # Get video info |
6449cd80 | 1345 | embed_webpage = None |
2fe1ff85 | 1346 | is_live = None |
c108eb73 | 1347 | if re.search(r'player-age-gate-content">', video_webpage) is not None: |
c108eb73 JMF |
1348 | age_gate = True |
1349 | # We simulate the access to the video from www.youtube.com/v/{video_id} | |
1350 | # this can be viewed without login into Youtube | |
beb95e77 CL |
1351 | url = proto + '://www.youtube.com/embed/%s' % video_id |
1352 | embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage') | |
15707c7e | 1353 | data = compat_urllib_parse_urlencode({ |
2c57c7fa JMF |
1354 | 'video_id': video_id, |
1355 | 'eurl': 'https://youtube.googleapis.com/v/' + video_id, | |
c084c934 | 1356 | 'sts': self._search_regex( |
beb95e77 | 1357 | r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''), |
2c57c7fa | 1358 | }) |
7e8c0af0 | 1359 | video_info_url = proto + '://www.youtube.com/get_video_info?' + data |
94bd3613 PH |
1360 | video_info_webpage = self._download_webpage( |
1361 | video_info_url, video_id, | |
20436c30 | 1362 | note='Refetching age-gated info webpage', |
94bd3613 | 1363 | errnote='unable to download video info webpage') |
c5e8d7af | 1364 | video_info = compat_parse_qs(video_info_webpage) |
d8d24a92 | 1365 | add_dash_mpd(video_info) |
c108eb73 JMF |
1366 | else: |
1367 | age_gate = False | |
bc93bdb5 | 1368 | video_info = None |
d8d24a92 | 1369 | # Try looking directly into the video webpage |
a72778d3 S |
1370 | ytplayer_config = self._get_ytplayer_config(video_id, video_webpage) |
1371 | if ytplayer_config: | |
4e62ebe2 | 1372 | args = ytplayer_config['args'] |
d8d24a92 S |
1373 | if args.get('url_encoded_fmt_stream_map'): |
1374 | # Convert to the same format returned by compat_parse_qs | |
1375 | video_info = dict((k, [v]) for k, v in args.items()) | |
1376 | add_dash_mpd(video_info) | |
6496ccb4 S |
1377 | # Rental video is not rented but preview is available (e.g. |
1378 | # https://www.youtube.com/watch?v=yYr8q0y5Jfg, | |
1379 | # https://github.com/rg3/youtube-dl/issues/10532) | |
1380 | if not video_info and args.get('ypc_vid'): | |
1381 | return self.url_result( | |
1382 | args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid']) | |
2fe1ff85 JMF |
1383 | if args.get('livestream') == '1' or args.get('live_playback') == 1: |
1384 | is_live = True | |
0a3cf9ad S |
1385 | if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): |
1386 | # We also try looking in get_video_info since it may contain different dashmpd | |
1387 | # URL that points to a DASH manifest with possibly different itag set (some itags | |
1388 | # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH | |
1389 | # manifest pointed by get_video_info's dashmpd). | |
1390 | # The general idea is to take a union of itags of both DASH manifests (for example | |
1391 | # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093) | |
4e62ebe2 | 1392 | self.report_video_info_webpage_download(video_id) |
0a3cf9ad | 1393 | for el_type in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']: |
810fb84d PH |
1394 | video_info_url = ( |
1395 | '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' | |
1396 | % (proto, video_id, el_type)) | |
1397 | video_info_webpage = self._download_webpage( | |
1398 | video_info_url, | |
4e62ebe2 JMF |
1399 | video_id, note=False, |
1400 | errnote='unable to download video info webpage') | |
0a3cf9ad | 1401 | get_video_info = compat_parse_qs(video_info_webpage) |
87dc4511 JMF |
1402 | if get_video_info.get('use_cipher_signature') != ['True']: |
1403 | add_dash_mpd(get_video_info) | |
0a3cf9ad S |
1404 | if not video_info: |
1405 | video_info = get_video_info | |
1406 | if 'token' in get_video_info: | |
89ea063e S |
1407 | # Different get_video_info requests may report different results, e.g. |
1408 | # some may report video unavailability, but some may serve it without | |
1409 | # any complaint (see https://github.com/rg3/youtube-dl/issues/7362, | |
1410 | # the original webpage as well as el=info and el=embedded get_video_info | |
1411 | # requests report video unavailability due to geo restriction while | |
1412 | # el=detailpage succeeds and returns valid data). This is probably | |
1413 | # due to YouTube measures against IP ranges of hosting providers. | |
1414 | # Working around by preferring the first succeeded video_info containing | |
1415 | # the token if no such video_info yet was found. | |
44b2264f S |
1416 | if 'token' not in video_info: |
1417 | video_info = get_video_info | |
4e62ebe2 | 1418 | break |
c5e8d7af PH |
1419 | if 'token' not in video_info: |
1420 | if 'reason' in video_info: | |
af214c3a | 1421 | if 'The uploader has not made this video available in your country.' in video_info['reason']: |
fd5c4aab S |
1422 | regions_allowed = self._html_search_meta( |
1423 | 'regionsAllowed', video_webpage, default=None) | |
1424 | countries = regions_allowed.split(',') if regions_allowed else None | |
1425 | self.raise_geo_restricted( | |
1426 | msg=video_info['reason'][0], countries=countries) | |
d11271dd | 1427 | raise ExtractorError( |
78caa52a | 1428 | 'YouTube said: %s' % video_info['reason'][0], |
d11271dd | 1429 | expected=True, video_id=video_id) |
c5e8d7af | 1430 | else: |
d11271dd | 1431 | raise ExtractorError( |
78caa52a | 1432 | '"token" parameter not in video info for unknown reason', |
d11271dd | 1433 | video_id=video_id) |
c5e8d7af | 1434 | |
cf7e015f S |
1435 | # title |
1436 | if 'title' in video_info: | |
1437 | video_title = video_info['title'][0] | |
1438 | else: | |
1439 | self._downloader.report_warning('Unable to extract video title') | |
1440 | video_title = '_' | |
1441 | ||
1442 | # description | |
9cafc3fd | 1443 | description_original = video_description = get_element_by_id("eow-description", video_webpage) |
cf7e015f | 1444 | if video_description: |
9cafc3fd | 1445 | description_original = video_description = re.sub(r'''(?x) |
cf7e015f | 1446 | <a\s+ |
25cb7a0e | 1447 | (?:[a-zA-Z-]+="[^"]*"\s+)*? |
23f13e97 | 1448 | (?:title|href)="([^"]+)"\s+ |
25cb7a0e | 1449 | (?:[a-zA-Z-]+="[^"]*"\s+)*? |
525cedb9 | 1450 | class="[^"]*"[^>]*> |
23f13e97 | 1451 | [^<]+\.{3}\s* |
cf7e015f S |
1452 | </a> |
1453 | ''', r'\1', video_description) | |
1454 | video_description = clean_html(video_description) | |
1455 | else: | |
1456 | fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage) | |
1457 | if fd_mobj: | |
1458 | video_description = unescapeHTML(fd_mobj.group(1)) | |
1459 | else: | |
1460 | video_description = '' | |
1461 | ||
5e1eddb9 S |
1462 | if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False): |
1463 | if not self._downloader.params.get('noplaylist'): | |
1464 | entries = [] | |
1465 | feed_ids = [] | |
6863631c | 1466 | multifeed_metadata_list = video_info['multifeed_metadata_list'][0] |
5e1eddb9 | 1467 | for feed in multifeed_metadata_list.split(','): |
6863631c S |
1468 | # Unquote should take place before split on comma (,) since textual |
1469 | # fields may contain comma as well (see | |
1470 | # https://github.com/rg3/youtube-dl/issues/8536) | |
1471 | feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed)) | |
5e1eddb9 S |
1472 | entries.append({ |
1473 | '_type': 'url_transparent', | |
1474 | 'ie_key': 'Youtube', | |
1475 | 'url': smuggle_url( | |
1476 | '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]), | |
1477 | {'force_singlefeed': True}), | |
1478 | 'title': '%s (%s)' % (video_title, feed_data['title'][0]), | |
1479 | }) | |
1480 | feed_ids.append(feed_data['id'][0]) | |
1481 | self.to_screen( | |
1482 | 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' | |
1483 | % (', '.join(feed_ids), video_id)) | |
1484 | return self.playlist_result(entries, video_id, video_title, video_description) | |
1485 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
cf7e015f | 1486 | |
1d699755 PH |
1487 | if 'view_count' in video_info: |
1488 | view_count = int(video_info['view_count'][0]) | |
1489 | else: | |
1490 | view_count = None | |
1491 | ||
c5e8d7af PH |
1492 | # Check for "rental" videos |
1493 | if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: | |
c9612c04 | 1494 | raise ExtractorError('"rental" videos not supported. See https://github.com/rg3/youtube-dl/issues/359 for more information.', expected=True) |
c5e8d7af PH |
1495 | |
1496 | # Start extracting information | |
1497 | self.report_information_extraction(video_id) | |
1498 | ||
1499 | # uploader | |
1500 | if 'author' not in video_info: | |
69ea8ca4 | 1501 | raise ExtractorError('Unable to extract uploader name') |
7fd002c0 | 1502 | video_uploader = compat_urllib_parse_unquote_plus(video_info['author'][0]) |
c5e8d7af PH |
1503 | |
1504 | # uploader_id | |
1505 | video_uploader_id = None | |
fd050249 S |
1506 | video_uploader_url = None |
1507 | mobj = re.search( | |
1508 | r'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">', | |
1509 | video_webpage) | |
c5e8d7af | 1510 | if mobj is not None: |
fd050249 S |
1511 | video_uploader_id = mobj.group('uploader_id') |
1512 | video_uploader_url = mobj.group('uploader_url') | |
c5e8d7af | 1513 | else: |
69ea8ca4 | 1514 | self._downloader.report_warning('unable to extract uploader nickname') |
c5e8d7af | 1515 | |
c5e8d7af | 1516 | # thumbnail image |
7763b04e JMF |
1517 | # We try first to get a high quality image: |
1518 | m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">', | |
1519 | video_webpage, re.DOTALL) | |
1520 | if m_thumb is not None: | |
1521 | video_thumbnail = m_thumb.group(1) | |
1522 | elif 'thumbnail_url' not in video_info: | |
69ea8ca4 | 1523 | self._downloader.report_warning('unable to extract video thumbnail') |
f490e77e | 1524 | video_thumbnail = None |
c5e8d7af | 1525 | else: # don't panic if we can't find it |
7fd002c0 | 1526 | video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0]) |
c5e8d7af PH |
1527 | |
1528 | # upload date | |
9d0b581f S |
1529 | upload_date = self._html_search_meta( |
1530 | 'datePublished', video_webpage, 'upload date', default=None) | |
1531 | if not upload_date: | |
1532 | upload_date = self._search_regex( | |
1533 | [r'(?s)id="eow-date.*?>(.*?)</span>', | |
1534 | r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'], | |
1535 | video_webpage, 'upload date', default=None) | |
1536 | if upload_date: | |
1537 | upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) | |
1538 | upload_date = unified_strdate(upload_date) | |
c5e8d7af | 1539 | |
7caf9830 S |
1540 | video_license = self._html_search_regex( |
1541 | r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li', | |
1542 | video_webpage, 'license', default=None) | |
1543 | ||
0cb58b02 S |
1544 | m_music = re.search( |
1545 | r'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li', | |
1546 | video_webpage) | |
1547 | if m_music: | |
1548 | video_alt_title = remove_quotes(unescapeHTML(m_music.group('title'))) | |
1549 | video_creator = clean_html(m_music.group('creator')) | |
1550 | else: | |
1551 | video_alt_title = video_creator = None | |
1552 | ||
12afdc2a S |
1553 | m_episode = re.search( |
1554 | r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>', | |
1555 | video_webpage) | |
1556 | if m_episode: | |
1557 | series = m_episode.group('series') | |
1558 | season_number = int(m_episode.group('season')) | |
1559 | episode_number = int(m_episode.group('episode')) | |
1560 | else: | |
1561 | series = season_number = episode_number = None | |
1562 | ||
55f7bd2d PH |
1563 | m_cat_container = self._search_regex( |
1564 | r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', | |
624dcebf | 1565 | video_webpage, 'categories', default=None) |
ec8deefc | 1566 | if m_cat_container: |
ad3bc6ac | 1567 | category = self._html_search_regex( |
01ed5c9b | 1568 | r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', |
ad3bc6ac PH |
1569 | default=None) |
1570 | video_categories = None if category is None else [category] | |
1571 | else: | |
1572 | video_categories = None | |
ec8deefc | 1573 | |
000b6b5a S |
1574 | video_tags = [ |
1575 | unescapeHTML(m.group('content')) | |
1576 | for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)] | |
1577 | ||
f30a38be | 1578 | def _extract_count(count_name): |
c93d53f5 S |
1579 | return str_to_int(self._search_regex( |
1580 | r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>' | |
1581 | % re.escape(count_name), | |
1582 | video_webpage, count_name, default=None)) | |
1583 | ||
69ea8ca4 PH |
1584 | like_count = _extract_count('like') |
1585 | dislike_count = _extract_count('dislike') | |
336c3a69 | 1586 | |
c5e8d7af | 1587 | # subtitles |
d82134c3 | 1588 | video_subtitles = self.extract_subtitles(video_id, video_webpage) |
360e1ca5 | 1589 | automatic_captions = self.extract_automatic_captions(video_id, video_webpage) |
c5e8d7af | 1590 | |
556dbe7f S |
1591 | video_duration = try_get( |
1592 | video_info, lambda x: int_or_none(x['length_seconds'][0])) | |
1593 | if not video_duration: | |
1594 | video_duration = parse_duration(self._html_search_meta( | |
1595 | 'duration', video_webpage, 'video duration')) | |
c5e8d7af | 1596 | |
1fb07d10 JG |
1597 | # annotations |
1598 | video_annotations = None | |
1599 | if self._downloader.params.get('writeannotations', False): | |
5f6a1245 | 1600 | video_annotations = self._extract_annotations(video_id) |
1fb07d10 | 1601 | |
9cafc3fd S |
1602 | chapters = self._extract_chapters(description_original, video_duration) |
1603 | ||
c5e8d7af PH |
1604 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): |
1605 | self.report_rtmp_download() | |
dd27fd17 PH |
1606 | formats = [{ |
1607 | 'format_id': '_rtmp', | |
1608 | 'protocol': 'rtmp', | |
1609 | 'url': video_info['conn'][0], | |
1610 | 'player_url': player_url, | |
1611 | }] | |
24270b03 | 1612 | elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1: |
5f6a1245 | 1613 | encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] |
00fe14fc | 1614 | if 'rtmpe%3Dyes' in encoded_url_map: |
a7055eb9 | 1615 | raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True) |
3318832e | 1616 | formats_spec = {} |
82156fdb | 1617 | fmt_list = video_info.get('fmt_list', [''])[0] |
1618 | if fmt_list: | |
1619 | for fmt in fmt_list.split(','): | |
1620 | spec = fmt.split('/') | |
3318832e | 1621 | if len(spec) > 1: |
1622 | width_height = spec[1].split('x') | |
1623 | if len(width_height) == 2: | |
1624 | formats_spec[spec[0]] = { | |
1625 | 'resolution': spec[1], | |
1626 | 'width': int_or_none(width_height[0]), | |
1627 | 'height': int_or_none(width_height[1]), | |
1628 | } | |
c9afb51c | 1629 | formats = [] |
00fe14fc | 1630 | for url_data_str in encoded_url_map.split(','): |
c5e8d7af | 1631 | url_data = compat_parse_qs(url_data_str) |
201e9eaa PH |
1632 | if 'itag' not in url_data or 'url' not in url_data: |
1633 | continue | |
1634 | format_id = url_data['itag'][0] | |
1635 | url = url_data['url'][0] | |
1636 | ||
1637 | if 'sig' in url_data: | |
1638 | url += '&signature=' + url_data['sig'][0] | |
1639 | elif 's' in url_data: | |
1640 | encrypted_sig = url_data['s'][0] | |
6449cd80 | 1641 | ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' |
201e9eaa | 1642 | |
beb95e77 | 1643 | jsplayer_url_json = self._search_regex( |
6449cd80 PH |
1644 | ASSETS_RE, |
1645 | embed_webpage if age_gate else video_webpage, | |
1646 | 'JS player URL (1)', default=None) | |
1647 | if not jsplayer_url_json and not age_gate: | |
1648 | # We need the embed website after all | |
1649 | if embed_webpage is None: | |
1650 | embed_url = proto + '://www.youtube.com/embed/%s' % video_id | |
1651 | embed_webpage = self._download_webpage( | |
1652 | embed_url, video_id, 'Downloading embed webpage') | |
1653 | jsplayer_url_json = self._search_regex( | |
1654 | ASSETS_RE, embed_webpage, 'JS player URL') | |
1655 | ||
beb95e77 | 1656 | player_url = json.loads(jsplayer_url_json) |
201e9eaa PH |
1657 | if player_url is None: |
1658 | player_url_json = self._search_regex( | |
1659 | r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', | |
78caa52a | 1660 | video_webpage, 'age gate player URL') |
201e9eaa PH |
1661 | player_url = json.loads(player_url_json) |
1662 | ||
1663 | if self._downloader.params.get('verbose'): | |
cf010131 | 1664 | if player_url is None: |
201e9eaa PH |
1665 | player_version = 'unknown' |
1666 | player_desc = 'unknown' | |
1667 | else: | |
1668 | if player_url.endswith('swf'): | |
1669 | player_version = self._search_regex( | |
1670 | r'-(.+?)(?:/watch_as3)?\.swf$', player_url, | |
78caa52a | 1671 | 'flash player', fatal=False) |
201e9eaa | 1672 | player_desc = 'flash player %s' % player_version |
cf010131 | 1673 | else: |
201e9eaa | 1674 | player_version = self._search_regex( |
b62985a9 YCH |
1675 | [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', |
1676 | r'(?:www|player)-([^/]+)(?:/[a-z]{2}_[A-Z]{2})?/base\.js'], | |
201e9eaa PH |
1677 | player_url, |
1678 | 'html5 player', fatal=False) | |
78caa52a | 1679 | player_desc = 'html5 player %s' % player_version |
201e9eaa | 1680 | |
60064c53 | 1681 | parts_sizes = self._signature_cache_id(encrypted_sig) |
69ea8ca4 | 1682 | self.to_screen('{%s} signature length %s, %s' % |
9e1a5b84 | 1683 | (format_id, parts_sizes, player_desc)) |
201e9eaa PH |
1684 | |
1685 | signature = self._decrypt_signature( | |
1686 | encrypted_sig, video_id, player_url, age_gate) | |
1687 | url += '&signature=' + signature | |
1688 | if 'ratebypass' not in url: | |
1689 | url += '&ratebypass=yes' | |
c9afb51c | 1690 | |
94278f72 YCH |
1691 | dct = { |
1692 | 'format_id': format_id, | |
1693 | 'url': url, | |
1694 | 'player_url': player_url, | |
1695 | } | |
1696 | if format_id in self._formats: | |
1697 | dct.update(self._formats[format_id]) | |
3318832e | 1698 | if format_id in formats_spec: |
1699 | dct.update(formats_spec[format_id]) | |
94278f72 | 1700 | |
aabc2be6 S |
1701 | # Some itags are not included in DASH manifest thus corresponding formats will |
1702 | # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993). | |
1703 | # Trying to extract metadata from url_encoded_fmt_stream_map entry. | |
1704 | mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0]) | |
1705 | width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None) | |
94278f72 YCH |
1706 | |
1707 | more_fields = { | |
c9afb51c | 1708 | 'filesize': int_or_none(url_data.get('clen', [None])[0]), |
aabc2be6 | 1709 | 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000), |
c9afb51c AH |
1710 | 'width': width, |
1711 | 'height': height, | |
1712 | 'fps': int_or_none(url_data.get('fps', [None])[0]), | |
aabc2be6 | 1713 | 'format_note': url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0], |
c9afb51c | 1714 | } |
94278f72 YCH |
1715 | for key, value in more_fields.items(): |
1716 | if value: | |
1717 | dct[key] = value | |
aabc2be6 S |
1718 | type_ = url_data.get('type', [None])[0] |
1719 | if type_: | |
1720 | type_split = type_.split(';') | |
1721 | kind_ext = type_split[0].split('/') | |
1722 | if len(kind_ext) == 2: | |
94278f72 YCH |
1723 | kind, _ = kind_ext |
1724 | dct['ext'] = mimetype2ext(type_split[0]) | |
aabc2be6 S |
1725 | if kind in ('audio', 'video'): |
1726 | codecs = None | |
1727 | for mobj in re.finditer( | |
1728 | r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_): | |
1729 | if mobj.group('key') == 'codecs': | |
1730 | codecs = mobj.group('val') | |
1731 | break | |
1732 | if codecs: | |
6310acf5 | 1733 | dct.update(parse_codecs(codecs)) |
aabc2be6 | 1734 | formats.append(dct) |
1d043b93 JMF |
1735 | elif video_info.get('hlsvp'): |
1736 | manifest_url = video_info['hlsvp'][0] | |
89beedd3 RA |
1737 | formats = [] |
1738 | m3u8_formats = self._extract_m3u8_formats( | |
1739 | manifest_url, video_id, 'mp4', fatal=False) | |
1740 | for a_format in m3u8_formats: | |
1741 | itag = self._search_regex( | |
1742 | r'/itag/(\d+)/', a_format['url'], 'itag', default=None) | |
1743 | if itag: | |
1744 | a_format['format_id'] = itag | |
1745 | if itag in self._formats: | |
1746 | dct = self._formats[itag].copy() | |
1747 | dct.update(a_format) | |
1748 | a_format = dct | |
1749 | a_format['player_url'] = player_url | |
1750 | # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming | |
049d71d8 | 1751 | a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True' |
89beedd3 | 1752 | formats.append(a_format) |
c5e8d7af | 1753 | else: |
8ceabd4d S |
1754 | unavailable_message = self._html_search_regex( |
1755 | r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>', | |
1756 | video_webpage, 'unavailable message', default=None) | |
1757 | if unavailable_message: | |
1758 | raise ExtractorError(unavailable_message, expected=True) | |
69ea8ca4 | 1759 | raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') |
c5e8d7af | 1760 | |
dd27fd17 | 1761 | # Look for the DASH manifest |
203fb43f | 1762 | if self._downloader.params.get('youtube_include_dash_manifest', True): |
77c6fb5b | 1763 | dash_mpd_fatal = True |
8ff648e4 | 1764 | for mpd_url in dash_mpds: |
d8d24a92 | 1765 | dash_formats = {} |
774e208f | 1766 | try: |
05d0d131 YCH |
1767 | def decrypt_sig(mobj): |
1768 | s = mobj.group(1) | |
1769 | dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) | |
1770 | return '/signature/%s' % dec_s | |
1771 | ||
8ff648e4 | 1772 | mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url) |
2d2fa82d | 1773 | |
8ff648e4 | 1774 | for df in self._extract_mpd_formats( |
1775 | mpd_url, video_id, fatal=dash_mpd_fatal, | |
1776 | formats_dict=self._formats): | |
d8d24a92 S |
1777 | # Do not overwrite DASH format found in some previous DASH manifest |
1778 | if df['format_id'] not in dash_formats: | |
1779 | dash_formats[df['format_id']] = df | |
77c6fb5b S |
1780 | # Additional DASH manifests may end up in HTTP Error 403 therefore |
1781 | # allow them to fail without bug report message if we already have | |
1782 | # some DASH manifest succeeded. This is temporary workaround to reduce | |
1783 | # burst of bug reports until we figure out the reason and whether it | |
1784 | # can be fixed at all. | |
1785 | dash_mpd_fatal = False | |
774e208f PH |
1786 | except (ExtractorError, KeyError) as e: |
1787 | self.report_warning( | |
1788 | 'Skipping DASH manifest: %r' % e, video_id) | |
d8d24a92 | 1789 | if dash_formats: |
04b3b3df JMF |
1790 | # Remove the formats we found through non-DASH, they |
1791 | # contain less info and it can be wrong, because we use | |
1792 | # fixed values (for example the resolution). See | |
1793 | # https://github.com/rg3/youtube-dl/issues/5774 for an | |
1794 | # example. | |
d80265cc | 1795 | formats = [f for f in formats if f['format_id'] not in dash_formats.keys()] |
d8d24a92 | 1796 | formats.extend(dash_formats.values()) |
d80044c2 | 1797 | |
6271f1ca PH |
1798 | # Check for malformed aspect ratio |
1799 | stretched_m = re.search( | |
1800 | r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">', | |
1801 | video_webpage) | |
1802 | if stretched_m: | |
313dfc45 LL |
1803 | w = float(stretched_m.group('w')) |
1804 | h = float(stretched_m.group('h')) | |
5faf9fed S |
1805 | # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0). |
1806 | # We will only process correct ratios. | |
313dfc45 | 1807 | if w > 0 and h > 0: |
41f24c32 | 1808 | ratio = w / h |
313dfc45 LL |
1809 | for f in formats: |
1810 | if f.get('vcodec') != 'none': | |
1811 | f['stretched_ratio'] = ratio | |
6271f1ca | 1812 | |
4bcc7bd1 | 1813 | self._sort_formats(formats) |
4ea3be0a | 1814 | |
d77ab8e2 S |
1815 | self.mark_watched(video_id, video_info) |
1816 | ||
4ea3be0a | 1817 | return { |
8bcc8756 JW |
1818 | 'id': video_id, |
1819 | 'uploader': video_uploader, | |
1820 | 'uploader_id': video_uploader_id, | |
fd050249 | 1821 | 'uploader_url': video_uploader_url, |
8bcc8756 | 1822 | 'upload_date': upload_date, |
7caf9830 | 1823 | 'license': video_license, |
0cb58b02 | 1824 | 'creator': video_creator, |
8bcc8756 | 1825 | 'title': video_title, |
0cb58b02 | 1826 | 'alt_title': video_alt_title, |
8bcc8756 JW |
1827 | 'thumbnail': video_thumbnail, |
1828 | 'description': video_description, | |
1829 | 'categories': video_categories, | |
000b6b5a | 1830 | 'tags': video_tags, |
8bcc8756 | 1831 | 'subtitles': video_subtitles, |
360e1ca5 | 1832 | 'automatic_captions': automatic_captions, |
8bcc8756 JW |
1833 | 'duration': video_duration, |
1834 | 'age_limit': 18 if age_gate else 0, | |
1835 | 'annotations': video_annotations, | |
9cafc3fd | 1836 | 'chapters': chapters, |
7e8c0af0 | 1837 | 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id, |
8bcc8756 | 1838 | 'view_count': view_count, |
4ea3be0a | 1839 | 'like_count': like_count, |
1840 | 'dislike_count': dislike_count, | |
2d30521a | 1841 | 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]), |
8bcc8756 | 1842 | 'formats': formats, |
2fe1ff85 | 1843 | 'is_live': is_live, |
7c80519c | 1844 | 'start_time': start_time, |
297a564b | 1845 | 'end_time': end_time, |
12afdc2a S |
1846 | 'series': series, |
1847 | 'season_number': season_number, | |
1848 | 'episode_number': episode_number, | |
4ea3be0a | 1849 | } |
c5e8d7af | 1850 | |
5f6a1245 | 1851 | |
40805306 | 1852 | class YoutubeSharedVideoIE(InfoExtractor): |
fd8c8c7d | 1853 | _VALID_URL = r'(?:https?:)?//(?:www\.)?youtube\.com/shared\?.*\bci=(?P<id>[0-9A-Za-z_-]{11})' |
40805306 YCH |
1854 | IE_NAME = 'youtube:shared' |
1855 | ||
1856 | _TEST = { | |
1857 | 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU', | |
1858 | 'info_dict': { | |
1859 | 'id': 'uPDB5I9wfp8', | |
1860 | 'ext': 'webm', | |
1861 | 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3', | |
1862 | 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d', | |
1863 | 'upload_date': '20160219', | |
1864 | 'uploader': 'Pocoyo - Português (BR)', | |
1865 | 'uploader_id': 'PocoyoBrazil', | |
1866 | }, | |
1867 | 'add_ie': ['Youtube'], | |
1868 | 'params': { | |
1869 | # There are already too many Youtube downloads | |
1870 | 'skip_download': True, | |
1871 | }, | |
1872 | } | |
1873 | ||
1874 | def _real_extract(self, url): | |
1875 | video_id = self._match_id(url) | |
1876 | ||
1877 | webpage = self._download_webpage(url, video_id) | |
1878 | ||
1879 | real_video_id = self._html_search_meta( | |
1880 | 'videoId', webpage, 'YouTube video id', fatal=True) | |
1881 | ||
1882 | return self.url_result(real_video_id, YoutubeIE.ie_key()) | |
1883 | ||
1884 | ||
8e7aad20 | 1885 | class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor): |
78caa52a | 1886 | IE_DESC = 'YouTube.com playlists' |
d67cc9fa | 1887 | _VALID_URL = r"""(?x)(?: |
c5e8d7af PH |
1888 | (?:https?://)? |
1889 | (?:\w+\.)? | |
c5e8d7af | 1890 | (?: |
feaa5ad7 S |
1891 | youtube\.com/ |
1892 | (?: | |
87dadd45 | 1893 | (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11})) |
feaa5ad7 S |
1894 | \? (?:.*?[&;])*? (?:p|a|list)= |
1895 | | p/ | |
1896 | )| | |
1897 | youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist= | |
c5e8d7af | 1898 | ) |
d67cc9fa | 1899 | ( |
a6857510 | 1900 | (?:PL|LL|EC|UU|FL|RD|UL|TL)?[0-9A-Za-z-_]{10,} |
5f6a1245 | 1901 | # Top tracks, they can also include dots |
d67cc9fa JMF |
1902 | |(?:MC)[\w\.]* |
1903 | ) | |
c5e8d7af PH |
1904 | .* |
1905 | | | |
d0ba5587 S |
1906 | (%(playlist_id)s) |
1907 | )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE} | |
c867adc6 | 1908 | _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true' |
648e6a1f | 1909 | _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?' |
78caa52a | 1910 | IE_NAME = 'youtube:playlist' |
81127aa5 PH |
1911 | _TESTS = [{ |
1912 | 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', | |
1913 | 'info_dict': { | |
1914 | 'title': 'ytdl test PL', | |
a1cf99d0 | 1915 | 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', |
81127aa5 PH |
1916 | }, |
1917 | 'playlist_count': 3, | |
9291475f PH |
1918 | }, { |
1919 | 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', | |
1920 | 'info_dict': { | |
acf757f4 | 1921 | 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', |
9291475f PH |
1922 | 'title': 'YDL_Empty_List', |
1923 | }, | |
1924 | 'playlist_count': 0, | |
4201ba13 | 1925 | 'skip': 'This playlist is private', |
9291475f PH |
1926 | }, { |
1927 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
1928 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
1929 | 'info_dict': { | |
1930 | 'title': '29C3: Not my department', | |
acf757f4 | 1931 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', |
9291475f PH |
1932 | }, |
1933 | 'playlist_count': 95, | |
1934 | }, { | |
1935 | 'note': 'issue #673', | |
1936 | 'url': 'PLBB231211A4F62143', | |
1937 | 'info_dict': { | |
f46a8702 | 1938 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', |
acf757f4 | 1939 | 'id': 'PLBB231211A4F62143', |
9291475f PH |
1940 | }, |
1941 | 'playlist_mincount': 26, | |
1942 | }, { | |
1943 | 'note': 'Large playlist', | |
1944 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
1945 | 'info_dict': { | |
1946 | 'title': 'Uploads from Cauchemar', | |
acf757f4 | 1947 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', |
9291475f PH |
1948 | }, |
1949 | 'playlist_mincount': 799, | |
1950 | }, { | |
1951 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
1952 | 'info_dict': { | |
1953 | 'title': 'YDL_safe_search', | |
acf757f4 | 1954 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', |
9291475f PH |
1955 | }, |
1956 | 'playlist_count': 2, | |
4201ba13 | 1957 | 'skip': 'This playlist is private', |
ac7553d0 PH |
1958 | }, { |
1959 | 'note': 'embedded', | |
2d3d2997 | 1960 | 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', |
ac7553d0 PH |
1961 | 'playlist_count': 4, |
1962 | 'info_dict': { | |
1963 | 'title': 'JODA15', | |
acf757f4 | 1964 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', |
ac7553d0 | 1965 | } |
87dadd45 S |
1966 | }, { |
1967 | 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
1968 | 'playlist_mincount': 485, | |
1969 | 'info_dict': { | |
1970 | 'title': '2017 華語最新單曲 (2/24更新)', | |
1971 | 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl', | |
1972 | } | |
6b08cdf6 PH |
1973 | }, { |
1974 | 'note': 'Embedded SWF player', | |
2d3d2997 | 1975 | 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0', |
6b08cdf6 PH |
1976 | 'playlist_count': 4, |
1977 | 'info_dict': { | |
1978 | 'title': 'JODA7', | |
acf757f4 | 1979 | 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ', |
6b08cdf6 | 1980 | } |
4b7df0d3 JMF |
1981 | }, { |
1982 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
1983 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
1984 | 'info_dict': { | |
acf757f4 PH |
1985 | 'title': 'Uploads from Interstellar Movie', |
1986 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
4b7df0d3 | 1987 | }, |
481cc733 | 1988 | 'playlist_mincount': 21, |
dacb3a86 S |
1989 | }, { |
1990 | # Playlist URL that does not actually serve a playlist | |
1991 | 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4', | |
1992 | 'info_dict': { | |
1993 | 'id': 'FqZTN594JQw', | |
1994 | 'ext': 'webm', | |
1995 | 'title': "Smiley's People 01 detective, Adventure Series, Action", | |
1996 | 'uploader': 'STREEM', | |
1997 | 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng', | |
ec85ded8 | 1998 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng', |
dacb3a86 S |
1999 | 'upload_date': '20150526', |
2000 | 'license': 'Standard YouTube License', | |
2001 | 'description': 'md5:507cdcb5a49ac0da37a920ece610be80', | |
2002 | 'categories': ['People & Blogs'], | |
2003 | 'tags': list, | |
2004 | 'like_count': int, | |
2005 | 'dislike_count': int, | |
2006 | }, | |
2007 | 'params': { | |
2008 | 'skip_download': True, | |
2009 | }, | |
2010 | 'add_ie': [YoutubeIE.ie_key()], | |
481cc733 S |
2011 | }, { |
2012 | 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5', | |
2013 | 'info_dict': { | |
2014 | 'id': 'yeWKywCrFtk', | |
2015 | 'ext': 'mp4', | |
2016 | 'title': 'Small Scale Baler and Braiding Rugs', | |
2017 | 'uploader': 'Backus-Page House Museum', | |
2018 | 'uploader_id': 'backuspagemuseum', | |
ec85ded8 | 2019 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum', |
481cc733 S |
2020 | 'upload_date': '20161008', |
2021 | 'license': 'Standard YouTube License', | |
2022 | 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a', | |
2023 | 'categories': ['Nonprofits & Activism'], | |
2024 | 'tags': list, | |
2025 | 'like_count': int, | |
2026 | 'dislike_count': int, | |
2027 | }, | |
2028 | 'params': { | |
2029 | 'noplaylist': True, | |
2030 | 'skip_download': True, | |
2031 | }, | |
feaa5ad7 S |
2032 | }, { |
2033 | 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21', | |
2034 | 'only_matching': True, | |
a6857510 S |
2035 | }, { |
2036 | 'url': 'TLGGrESM50VT6acwMjAyMjAxNw', | |
2037 | 'only_matching': True, | |
81127aa5 | 2038 | }] |
c5e8d7af | 2039 | |
880e1c52 JMF |
2040 | def _real_initialize(self): |
2041 | self._login() | |
2042 | ||
652cdaa2 | 2043 | def _extract_mix(self, playlist_id): |
99209c29 | 2044 | # The mixes are generated from a single video |
652cdaa2 | 2045 | # the id of the playlist is just 'RD' + video_id |
1b6182d8 JMF |
2046 | ids = [] |
2047 | last_id = playlist_id[-11:] | |
2048 | for n in itertools.count(1): | |
2049 | url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id) | |
2050 | webpage = self._download_webpage( | |
2051 | url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n)) | |
2052 | new_ids = orderedSet(re.findall( | |
2053 | r'''(?xs)data-video-username=".*?".*? | |
2054 | href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id), | |
2055 | webpage)) | |
2056 | # Fetch new pages until all the videos are repeated, it seems that | |
2057 | # there are always 51 unique videos. | |
2058 | new_ids = [_id for _id in new_ids if _id not in ids] | |
2059 | if not new_ids: | |
2060 | break | |
2061 | ids.extend(new_ids) | |
2062 | last_id = ids[-1] | |
2063 | ||
2064 | url_results = self._ids_to_results(ids) | |
2065 | ||
bc2f773b | 2066 | search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage) |
c9cc0bf5 PH |
2067 | title_span = ( |
2068 | search_title('playlist-title') or | |
2069 | search_title('title long-title') or | |
2070 | search_title('title')) | |
76d1700b | 2071 | title = clean_html(title_span) |
652cdaa2 JMF |
2072 | |
2073 | return self.playlist_result(url_results, playlist_id, title) | |
2074 | ||
448830ce | 2075 | def _extract_playlist(self, playlist_id): |
dbb94fb0 S |
2076 | url = self._TEMPLATE_URL % playlist_id |
2077 | page = self._download_webpage(url, playlist_id) | |
dbb94fb0 | 2078 | |
8bc0800d G |
2079 | # the yt-alert-message now has tabindex attribute (see https://github.com/rg3/youtube-dl/issues/11604) |
2080 | for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page): | |
39b62db1 YCH |
2081 | match = match.strip() |
2082 | # Check if the playlist exists or is private | |
4201ba13 S |
2083 | mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match) |
2084 | if mobj: | |
2085 | reason = mobj.group('reason') | |
2086 | message = 'This playlist %s' % reason | |
2087 | if 'private' in reason: | |
2088 | message += ', use --username or --netrc to access it' | |
2089 | message += '.' | |
2090 | raise ExtractorError(message, expected=True) | |
39b62db1 YCH |
2091 | elif re.match(r'[^<]*Invalid parameters[^<]*', match): |
2092 | raise ExtractorError( | |
2093 | 'Invalid parameters. Maybe URL is incorrect.', | |
2094 | expected=True) | |
2095 | elif re.match(r'[^<]*Choose your language[^<]*', match): | |
2096 | continue | |
2097 | else: | |
2098 | self.report_warning('Youtube gives an alert message: ' + match) | |
10c0e2d8 | 2099 | |
dbb94fb0 | 2100 | playlist_title = self._html_search_regex( |
63b4295d | 2101 | r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>', |
dacb3a86 | 2102 | page, 'title', default=None) |
c5e8d7af | 2103 | |
dacb3a86 S |
2104 | has_videos = True |
2105 | ||
2106 | if not playlist_title: | |
2107 | try: | |
2108 | # Some playlist URLs don't actually serve a playlist (e.g. | |
2109 | # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4) | |
2110 | next(self._entries(page, playlist_id)) | |
2111 | except StopIteration: | |
2112 | has_videos = False | |
2113 | ||
2114 | return has_videos, self.playlist_result( | |
2115 | self._entries(page, playlist_id), playlist_id, playlist_title) | |
c5e8d7af | 2116 | |
ebf1b291 | 2117 | def _check_download_just_video(self, url, playlist_id): |
448830ce S |
2118 | # Check if it's a video-specific URL |
2119 | query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) | |
481cc733 | 2120 | video_id = query_dict.get('v', [None])[0] or self._search_regex( |
87dadd45 | 2121 | r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url, |
481cc733 S |
2122 | 'video id', default=None) |
2123 | if video_id: | |
448830ce S |
2124 | if self._downloader.params.get('noplaylist'): |
2125 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
dacb3a86 | 2126 | return video_id, self.url_result(video_id, 'Youtube', video_id=video_id) |
448830ce S |
2127 | else: |
2128 | self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) | |
dacb3a86 S |
2129 | return video_id, None |
2130 | return None, None | |
448830ce | 2131 | |
ebf1b291 S |
2132 | def _real_extract(self, url): |
2133 | # Extract playlist id | |
2134 | mobj = re.match(self._VALID_URL, url) | |
2135 | if mobj is None: | |
2136 | raise ExtractorError('Invalid URL: %s' % url) | |
2137 | playlist_id = mobj.group(1) or mobj.group(2) | |
2138 | ||
dacb3a86 | 2139 | video_id, video = self._check_download_just_video(url, playlist_id) |
ebf1b291 S |
2140 | if video: |
2141 | return video | |
2142 | ||
466a6145 | 2143 | if playlist_id.startswith(('RD', 'UL', 'PU')): |
448830ce S |
2144 | # Mixes require a custom extraction process |
2145 | return self._extract_mix(playlist_id) | |
2146 | ||
dacb3a86 S |
2147 | has_videos, playlist = self._extract_playlist(playlist_id) |
2148 | if has_videos or not video_id: | |
2149 | return playlist | |
2150 | ||
2151 | # Some playlist URLs don't actually serve a playlist (see | |
2152 | # https://github.com/rg3/youtube-dl/issues/10537). | |
2153 | # Fallback to plain video extraction if there is a video id | |
2154 | # along with playlist id. | |
2155 | return self.url_result(video_id, 'Youtube', video_id=video_id) | |
448830ce | 2156 | |
c5e8d7af | 2157 | |
648e6a1f | 2158 | class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): |
78caa52a | 2159 | IE_DESC = 'YouTube.com channels' |
9ff67727 | 2160 | _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)' |
eb0f3e7e | 2161 | _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos' |
648e6a1f | 2162 | _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?' |
78caa52a | 2163 | IE_NAME = 'youtube:channel' |
cdc628a4 PH |
2164 | _TESTS = [{ |
2165 | 'note': 'paginated channel', | |
2166 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
2167 | 'playlist_mincount': 91, | |
acf757f4 | 2168 | 'info_dict': { |
9170ca5b JMF |
2169 | 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w', |
2170 | 'title': 'Uploads from lex will', | |
acf757f4 | 2171 | } |
5c43afd4 JMF |
2172 | }, { |
2173 | 'note': 'Age restricted channel', | |
2174 | # from https://www.youtube.com/user/DeusExOfficial | |
2175 | 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w', | |
2176 | 'playlist_mincount': 64, | |
2177 | 'info_dict': { | |
2178 | 'id': 'UUs0ifCMCm1icqRbqhUINa0w', | |
2179 | 'title': 'Uploads from Deus Ex', | |
2180 | }, | |
cdc628a4 | 2181 | }] |
c5e8d7af | 2182 | |
e462474e S |
2183 | @classmethod |
2184 | def suitable(cls, url): | |
f07e276a S |
2185 | return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url) |
2186 | else super(YoutubeChannelIE, cls).suitable(url)) | |
e462474e | 2187 | |
9558dcec S |
2188 | def _build_template_url(self, url, channel_id): |
2189 | return self._TEMPLATE_URL % channel_id | |
2190 | ||
c5e8d7af | 2191 | def _real_extract(self, url): |
9ff67727 | 2192 | channel_id = self._match_id(url) |
c5e8d7af | 2193 | |
9558dcec | 2194 | url = self._build_template_url(url, channel_id) |
386bdfa6 S |
2195 | |
2196 | # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778) | |
2197 | # Workaround by extracting as a playlist if managed to obtain channel playlist URL | |
2198 | # otherwise fallback on channel by page extraction | |
2199 | channel_page = self._download_webpage( | |
2200 | url + '?view=57', channel_id, | |
2201 | 'Downloading channel page', fatal=False) | |
2b3c2546 PH |
2202 | if channel_page is False: |
2203 | channel_playlist_id = False | |
2204 | else: | |
2205 | channel_playlist_id = self._html_search_meta( | |
2206 | 'channelId', channel_page, 'channel id', default=None) | |
2207 | if not channel_playlist_id: | |
73c4ac2c S |
2208 | channel_url = self._html_search_meta( |
2209 | ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'), | |
2210 | channel_page, 'channel url', default=None) | |
2211 | if channel_url: | |
2212 | channel_playlist_id = self._search_regex( | |
2213 | r'vnd\.youtube://user/([0-9A-Za-z_-]+)', | |
2214 | channel_url, 'channel id', default=None) | |
386bdfa6 S |
2215 | if channel_playlist_id and channel_playlist_id.startswith('UC'): |
2216 | playlist_id = 'UU' + channel_playlist_id[2:] | |
d2a9de78 IK |
2217 | return self.url_result( |
2218 | compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist') | |
386bdfa6 | 2219 | |
60bf45c8 | 2220 | channel_page = self._download_webpage(url, channel_id, 'Downloading page #1') |
31812a9e PH |
2221 | autogenerated = re.search(r'''(?x) |
2222 | class="[^"]*?(?: | |
2223 | channel-header-autogenerated-label| | |
2224 | yt-channel-title-autogenerated | |
2225 | )[^"]*"''', channel_page) is not None | |
c5e8d7af | 2226 | |
b9643eed JMF |
2227 | if autogenerated: |
2228 | # The videos are contained in a single page | |
2229 | # the ajax pages can't be used, they are empty | |
b82f815f | 2230 | entries = [ |
fb69240c S |
2231 | self.url_result( |
2232 | video_id, 'Youtube', video_id=video_id, | |
2233 | video_title=video_title) | |
8f02ad4f | 2234 | for video_id, video_title in self.extract_videos_from_page(channel_page)] |
b82f815f PH |
2235 | return self.playlist_result(entries, channel_id) |
2236 | ||
73c4ac2c S |
2237 | try: |
2238 | next(self._entries(channel_page, channel_id)) | |
2239 | except StopIteration: | |
2240 | alert_message = self._html_search_regex( | |
2241 | r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>', | |
2242 | channel_page, 'alert', default=None, group='alert') | |
2243 | if alert_message: | |
2244 | raise ExtractorError('Youtube said: %s' % alert_message, expected=True) | |
2245 | ||
648e6a1f | 2246 | return self.playlist_result(self._entries(channel_page, channel_id), channel_id) |
c5e8d7af PH |
2247 | |
2248 | ||
eb0f3e7e | 2249 | class YoutubeUserIE(YoutubeChannelIE): |
78caa52a | 2250 | IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)' |
9558dcec S |
2251 | _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)' |
2252 | _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos' | |
78caa52a | 2253 | IE_NAME = 'youtube:user' |
c5e8d7af | 2254 | |
cdc628a4 PH |
2255 | _TESTS = [{ |
2256 | 'url': 'https://www.youtube.com/user/TheLinuxFoundation', | |
2257 | 'playlist_mincount': 320, | |
2258 | 'info_dict': { | |
73c4ac2c S |
2259 | 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ', |
2260 | 'title': 'Uploads from The Linux Foundation', | |
cdc628a4 | 2261 | } |
9558dcec S |
2262 | }, { |
2263 | # Only available via https://www.youtube.com/c/12minuteathlete/videos | |
2264 | # but not https://www.youtube.com/user/12minuteathlete/videos | |
2265 | 'url': 'https://www.youtube.com/c/12minuteathlete/videos', | |
2266 | 'playlist_mincount': 249, | |
2267 | 'info_dict': { | |
2268 | 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ', | |
2269 | 'title': 'Uploads from 12 Minute Athlete', | |
2270 | } | |
cdc628a4 PH |
2271 | }, { |
2272 | 'url': 'ytuser:phihag', | |
2273 | 'only_matching': True, | |
daa0df9e YCH |
2274 | }, { |
2275 | 'url': 'https://www.youtube.com/c/gametrailers', | |
2276 | 'only_matching': True, | |
9558dcec S |
2277 | }, { |
2278 | 'url': 'https://www.youtube.com/gametrailers', | |
2279 | 'only_matching': True, | |
73c4ac2c | 2280 | }, { |
0e879f43 | 2281 | # This channel is not available, geo restricted to JP |
73c4ac2c S |
2282 | 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos', |
2283 | 'only_matching': True, | |
cdc628a4 PH |
2284 | }] |
2285 | ||
e3ea4790 | 2286 | @classmethod |
f4b05232 | 2287 | def suitable(cls, url): |
e3ea4790 JMF |
2288 | # Don't return True if the url can be extracted with other youtube |
2289 | # extractor, the regex would is too permissive and it would match. | |
f3a58d46 | 2290 | other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls) |
2291 | if any(ie.suitable(url) for ie in other_yt_ies): | |
5f6a1245 JW |
2292 | return False |
2293 | else: | |
2294 | return super(YoutubeUserIE, cls).suitable(url) | |
f4b05232 | 2295 | |
9558dcec S |
2296 | def _build_template_url(self, url, channel_id): |
2297 | mobj = re.match(self._VALID_URL, url) | |
2298 | return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id')) | |
2299 | ||
b05654f0 | 2300 | |
f07e276a S |
2301 | class YoutubeLiveIE(YoutubeBaseInfoExtractor): |
2302 | IE_DESC = 'YouTube.com live streams' | |
073d5bf5 | 2303 | _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live' |
f07e276a S |
2304 | IE_NAME = 'youtube:live' |
2305 | ||
2306 | _TESTS = [{ | |
2d3d2997 | 2307 | 'url': 'https://www.youtube.com/user/TheYoungTurks/live', |
f07e276a S |
2308 | 'info_dict': { |
2309 | 'id': 'a48o2S1cPoo', | |
2310 | 'ext': 'mp4', | |
2311 | 'title': 'The Young Turks - Live Main Show', | |
2312 | 'uploader': 'The Young Turks', | |
2313 | 'uploader_id': 'TheYoungTurks', | |
ec85ded8 | 2314 | 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks', |
f07e276a S |
2315 | 'upload_date': '20150715', |
2316 | 'license': 'Standard YouTube License', | |
2317 | 'description': 'md5:438179573adcdff3c97ebb1ee632b891', | |
2318 | 'categories': ['News & Politics'], | |
2319 | 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'], | |
2320 | 'like_count': int, | |
2321 | 'dislike_count': int, | |
2322 | }, | |
2323 | 'params': { | |
2324 | 'skip_download': True, | |
2325 | }, | |
2326 | }, { | |
2d3d2997 | 2327 | 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live', |
f07e276a | 2328 | 'only_matching': True, |
c1b2a085 S |
2329 | }, { |
2330 | 'url': 'https://www.youtube.com/c/CommanderVideoHq/live', | |
2331 | 'only_matching': True, | |
073d5bf5 S |
2332 | }, { |
2333 | 'url': 'https://www.youtube.com/TheYoungTurks/live', | |
2334 | 'only_matching': True, | |
f07e276a S |
2335 | }] |
2336 | ||
2337 | def _real_extract(self, url): | |
2338 | mobj = re.match(self._VALID_URL, url) | |
2339 | channel_id = mobj.group('id') | |
2340 | base_url = mobj.group('base_url') | |
2341 | webpage = self._download_webpage(url, channel_id, fatal=False) | |
2342 | if webpage: | |
2343 | page_type = self._og_search_property( | |
2344 | 'type', webpage, 'page type', default=None) | |
2345 | video_id = self._html_search_meta( | |
2346 | 'videoId', webpage, 'video id', default=None) | |
2347 | if page_type == 'video' and video_id and re.match(r'^[0-9A-Za-z_-]{11}$', video_id): | |
2348 | return self.url_result(video_id, YoutubeIE.ie_key()) | |
2349 | return self.url_result(base_url) | |
2350 | ||
2351 | ||
e462474e S |
2352 | class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor): |
2353 | IE_DESC = 'YouTube.com user/channel playlists' | |
2354 | _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists' | |
2355 | IE_NAME = 'youtube:playlists' | |
0c148415 | 2356 | |
e568c223 | 2357 | _TESTS = [{ |
2d3d2997 | 2358 | 'url': 'https://www.youtube.com/user/ThirstForScience/playlists', |
0c148415 S |
2359 | 'playlist_mincount': 4, |
2360 | 'info_dict': { | |
2361 | 'id': 'ThirstForScience', | |
2362 | 'title': 'Thirst for Science', | |
2363 | }, | |
e568c223 S |
2364 | }, { |
2365 | # with "Load more" button | |
2d3d2997 | 2366 | 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', |
e568c223 S |
2367 | 'playlist_mincount': 70, |
2368 | 'info_dict': { | |
2369 | 'id': 'igorkle1', | |
2370 | 'title': 'Игорь Клейнер', | |
2371 | }, | |
e462474e S |
2372 | }, { |
2373 | 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists', | |
2374 | 'playlist_mincount': 17, | |
2375 | 'info_dict': { | |
2376 | 'id': 'UCiU1dHvZObB2iP6xkJ__Icw', | |
2377 | 'title': 'Chem Player', | |
2378 | }, | |
e568c223 | 2379 | }] |
0c148415 S |
2380 | |
2381 | ||
b4c08069 | 2382 | class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE): |
78caa52a | 2383 | IE_DESC = 'YouTube.com searches' |
b4c08069 JMF |
2384 | # there doesn't appear to be a real limit, for example if you search for |
2385 | # 'python' you get more than 8.000.000 results | |
2386 | _MAX_RESULTS = float('inf') | |
78caa52a | 2387 | IE_NAME = 'youtube:search' |
b05654f0 | 2388 | _SEARCH_KEY = 'ytsearch' |
b4c08069 | 2389 | _EXTRA_QUERY_ARGS = {} |
9dd8e46a | 2390 | _TESTS = [] |
b05654f0 | 2391 | |
b05654f0 PH |
2392 | def _get_n_results(self, query, n): |
2393 | """Get a specified number of results for a query""" | |
2394 | ||
b4c08069 | 2395 | videos = [] |
b05654f0 PH |
2396 | limit = n |
2397 | ||
a22b2fd1 YCH |
2398 | url_query = { |
2399 | 'search_query': query.encode('utf-8'), | |
2400 | } | |
2401 | url_query.update(self._EXTRA_QUERY_ARGS) | |
2402 | result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query) | |
2403 | ||
b4c08069 | 2404 | for pagenum in itertools.count(1): |
b4c08069 | 2405 | data = self._download_json( |
69ea8ca4 | 2406 | result_url, video_id='query "%s"' % query, |
b4c08069 | 2407 | note='Downloading page %s' % pagenum, |
a22b2fd1 YCH |
2408 | errnote='Unable to download API page', |
2409 | query={'spf': 'navigate'}) | |
b4c08069 | 2410 | html_content = data[1]['body']['content'] |
7cc3570e | 2411 | |
b4c08069 | 2412 | if 'class="search-message' in html_content: |
07ad22b8 | 2413 | raise ExtractorError( |
78caa52a | 2414 | '[youtube] No video results', expected=True) |
b05654f0 | 2415 | |
b4c08069 JMF |
2416 | new_videos = self._ids_to_results(orderedSet(re.findall( |
2417 | r'href="/watch\?v=(.{11})', html_content))) | |
2418 | videos += new_videos | |
2419 | if not new_videos or len(videos) > limit: | |
2420 | break | |
a22b2fd1 YCH |
2421 | next_link = self._html_search_regex( |
2422 | r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next', | |
2423 | html_content, 'next link', default=None) | |
2424 | if next_link is None: | |
2425 | break | |
2426 | result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link) | |
b05654f0 | 2427 | |
b4c08069 JMF |
2428 | if len(videos) > n: |
2429 | videos = videos[:n] | |
b05654f0 | 2430 | return self.playlist_result(videos, query) |
75dff0ee | 2431 | |
c9ae7b95 | 2432 | |
a3dd9248 | 2433 | class YoutubeSearchDateIE(YoutubeSearchIE): |
cb7fb546 | 2434 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' |
a3dd9248 | 2435 | _SEARCH_KEY = 'ytsearchdate' |
78caa52a | 2436 | IE_DESC = 'YouTube.com searches, newest videos first' |
b4c08069 | 2437 | _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'} |
75dff0ee | 2438 | |
c9ae7b95 | 2439 | |
175c2e9e | 2440 | class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor): |
78caa52a PH |
2441 | IE_DESC = 'YouTube.com search URLs' |
2442 | IE_NAME = 'youtube:search_url' | |
d2c1f79f | 2443 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)' |
175c2e9e | 2444 | _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?' |
cdc628a4 PH |
2445 | _TESTS = [{ |
2446 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
2447 | 'playlist_mincount': 5, | |
2448 | 'info_dict': { | |
2449 | 'title': 'youtube-dl test video', | |
2450 | } | |
d2c1f79f S |
2451 | }, { |
2452 | 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB', | |
2453 | 'only_matching': True, | |
cdc628a4 | 2454 | }] |
c9ae7b95 PH |
2455 | |
2456 | def _real_extract(self, url): | |
2457 | mobj = re.match(self._VALID_URL, url) | |
7fd002c0 | 2458 | query = compat_urllib_parse_unquote_plus(mobj.group('query')) |
c9ae7b95 | 2459 | webpage = self._download_webpage(url, query) |
175c2e9e | 2460 | return self.playlist_result(self._process_page(webpage), playlist_title=query) |
c9ae7b95 PH |
2461 | |
2462 | ||
136dadde | 2463 | class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor): |
78caa52a | 2464 | IE_DESC = 'YouTube.com (multi-season) shows' |
92519402 | 2465 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)' |
78caa52a | 2466 | IE_NAME = 'youtube:show' |
cdc628a4 | 2467 | _TESTS = [{ |
4003bd82 | 2468 | 'url': 'https://www.youtube.com/show/airdisasters', |
8801255d | 2469 | 'playlist_mincount': 5, |
cdc628a4 PH |
2470 | 'info_dict': { |
2471 | 'id': 'airdisasters', | |
2472 | 'title': 'Air Disasters', | |
2473 | } | |
2474 | }] | |
75dff0ee JMF |
2475 | |
2476 | def _real_extract(self, url): | |
136dadde S |
2477 | playlist_id = self._match_id(url) |
2478 | return super(YoutubeShowIE, self)._real_extract( | |
2479 | 'https://www.youtube.com/show/%s/playlists' % playlist_id) | |
04cc9617 JMF |
2480 | |
2481 | ||
b2e8bc1b | 2482 | class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): |
d7ae0639 | 2483 | """ |
25f14e9f | 2484 | Base class for feed extractors |
d7ae0639 JMF |
2485 | Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties. |
2486 | """ | |
b2e8bc1b | 2487 | _LOGIN_REQUIRED = True |
d7ae0639 JMF |
2488 | |
2489 | @property | |
2490 | def IE_NAME(self): | |
78caa52a | 2491 | return 'youtube:%s' % self._FEED_NAME |
04cc9617 | 2492 | |
81f0259b | 2493 | def _real_initialize(self): |
b2e8bc1b | 2494 | self._login() |
81f0259b | 2495 | |
04cc9617 | 2496 | def _real_extract(self, url): |
25f14e9f S |
2497 | page = self._download_webpage( |
2498 | 'https://www.youtube.com/feed/%s' % self._FEED_NAME, self._PLAYLIST_TITLE) | |
2bc43303 JMF |
2499 | |
2500 | # The extraction process is the same as for playlists, but the regex | |
2501 | # for the video ids doesn't contain an index | |
2502 | ids = [] | |
2503 | more_widget_html = content_html = page | |
2bc43303 JMF |
2504 | for page_num in itertools.count(1): |
2505 | matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html) | |
62c95fd5 S |
2506 | |
2507 | # 'recommended' feed has infinite 'load more' and each new portion spins | |
2508 | # the same videos in (sometimes) slightly different order, so we'll check | |
2509 | # for unicity and break when portion has no new videos | |
2510 | new_ids = filter(lambda video_id: video_id not in ids, orderedSet(matches)) | |
2511 | if not new_ids: | |
2512 | break | |
2513 | ||
2bc43303 JMF |
2514 | ids.extend(new_ids) |
2515 | ||
2516 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) | |
2517 | if not mobj: | |
2518 | break | |
2519 | ||
2520 | more = self._download_json( | |
25f14e9f | 2521 | 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE, |
2bc43303 JMF |
2522 | 'Downloading page #%s' % page_num, |
2523 | transform_source=uppercase_escape) | |
2524 | content_html = more['content_html'] | |
2525 | more_widget_html = more['load_more_widget_html'] | |
2526 | ||
25f14e9f S |
2527 | return self.playlist_result( |
2528 | self._ids_to_results(ids), playlist_title=self._PLAYLIST_TITLE) | |
2529 | ||
2530 | ||
2531 | class YoutubeWatchLaterIE(YoutubePlaylistIE): | |
2532 | IE_NAME = 'youtube:watchlater' | |
2533 | IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' | |
92519402 | 2534 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater' |
25f14e9f | 2535 | |
bc7a9cd8 S |
2536 | _TESTS = [{ |
2537 | 'url': 'https://www.youtube.com/playlist?list=WL', | |
2538 | 'only_matching': True, | |
2539 | }, { | |
2540 | 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL', | |
2541 | 'only_matching': True, | |
2542 | }] | |
25f14e9f S |
2543 | |
2544 | def _real_extract(self, url): | |
7e5dc339 | 2545 | _, video = self._check_download_just_video(url, 'WL') |
ebf1b291 S |
2546 | if video: |
2547 | return video | |
dacb3a86 S |
2548 | _, playlist = self._extract_playlist('WL') |
2549 | return playlist | |
f459d170 | 2550 | |
5f6a1245 | 2551 | |
c626a3d9 | 2552 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): |
78caa52a | 2553 | IE_NAME = 'youtube:favorites' |
f3a34072 | 2554 | IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)' |
92519402 | 2555 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?' |
c626a3d9 JMF |
2556 | _LOGIN_REQUIRED = True |
2557 | ||
2558 | def _real_extract(self, url): | |
2559 | webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos') | |
78caa52a | 2560 | playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id') |
c626a3d9 | 2561 | return self.url_result(playlist_id, 'YoutubePlaylist') |
15870e90 PH |
2562 | |
2563 | ||
25f14e9f S |
2564 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): |
2565 | IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' | |
92519402 | 2566 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?' |
25f14e9f S |
2567 | _FEED_NAME = 'recommended' |
2568 | _PLAYLIST_TITLE = 'Youtube Recommended videos' | |
1ed5b5c9 | 2569 | |
1ed5b5c9 | 2570 | |
25f14e9f S |
2571 | class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): |
2572 | IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' | |
92519402 | 2573 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' |
25f14e9f S |
2574 | _FEED_NAME = 'subscriptions' |
2575 | _PLAYLIST_TITLE = 'Youtube Subscriptions' | |
1ed5b5c9 | 2576 | |
1ed5b5c9 | 2577 | |
25f14e9f S |
2578 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): |
2579 | IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' | |
92519402 | 2580 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory' |
25f14e9f S |
2581 | _FEED_NAME = 'history' |
2582 | _PLAYLIST_TITLE = 'Youtube History' | |
1ed5b5c9 JMF |
2583 | |
2584 | ||
15870e90 PH |
2585 | class YoutubeTruncatedURLIE(InfoExtractor): |
2586 | IE_NAME = 'youtube:truncated_url' | |
2587 | IE_DESC = False # Do not list | |
975d35db | 2588 | _VALID_URL = r'''(?x) |
b95aab84 PH |
2589 | (?:https?://)? |
2590 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
2591 | (?:watch\?(?: | |
c4808c60 | 2592 | feature=[a-z_]+| |
b95aab84 PH |
2593 | annotation_id=annotation_[^&]+| |
2594 | x-yt-cl=[0-9]+| | |
c1708b89 | 2595 | hl=[^&]*| |
287be8c6 | 2596 | t=[0-9]+ |
b95aab84 PH |
2597 | )? |
2598 | | | |
2599 | attribution_link\?a=[^&]+ | |
2600 | ) | |
2601 | $ | |
975d35db | 2602 | ''' |
15870e90 | 2603 | |
c4808c60 | 2604 | _TESTS = [{ |
2d3d2997 | 2605 | 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041', |
c4808c60 | 2606 | 'only_matching': True, |
dc2fc736 | 2607 | }, { |
2d3d2997 | 2608 | 'url': 'https://www.youtube.com/watch?', |
dc2fc736 | 2609 | 'only_matching': True, |
b95aab84 PH |
2610 | }, { |
2611 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
2612 | 'only_matching': True, | |
2613 | }, { | |
2614 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
2615 | 'only_matching': True, | |
c1708b89 PH |
2616 | }, { |
2617 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
2618 | 'only_matching': True, | |
287be8c6 PH |
2619 | }, { |
2620 | 'url': 'https://www.youtube.com/watch?t=2372', | |
2621 | 'only_matching': True, | |
c4808c60 PH |
2622 | }] |
2623 | ||
15870e90 PH |
2624 | def _real_extract(self, url): |
2625 | raise ExtractorError( | |
78caa52a PH |
2626 | 'Did you forget to quote the URL? Remember that & is a meta ' |
2627 | 'character in most shells, so you want to put the URL in quotes, ' | |
2628 | 'like youtube-dl ' | |
2d3d2997 | 2629 | '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' |
78caa52a | 2630 | ' or simply youtube-dl BaW_jenozKc .', |
15870e90 | 2631 | expected=True) |
772fd5cc PH |
2632 | |
2633 | ||
2634 | class YoutubeTruncatedIDIE(InfoExtractor): | |
2635 | IE_NAME = 'youtube:truncated_id' | |
2636 | IE_DESC = False # Do not list | |
b95aab84 | 2637 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' |
772fd5cc PH |
2638 | |
2639 | _TESTS = [{ | |
2640 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
2641 | 'only_matching': True, | |
2642 | }] | |
2643 | ||
2644 | def _real_extract(self, url): | |
2645 | video_id = self._match_id(url) | |
2646 | raise ExtractorError( | |
2647 | 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), | |
2648 | expected=True) |