]>
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 |
c5e8d7af | 9 | import re |
42939b61 | 10 | import time |
e0df6211 | 11 | import traceback |
c5e8d7af | 12 | |
b05654f0 | 13 | from .common import InfoExtractor, SearchInfoExtractor |
2b25cb5d | 14 | from ..jsinterp import JSInterpreter |
54256267 | 15 | from ..swfinterp import SWFInterpreter |
4bb4a188 | 16 | from ..compat import ( |
edf3e38e | 17 | compat_chr, |
c5e8d7af | 18 | compat_parse_qs, |
c5e8d7af | 19 | compat_urllib_parse, |
7fd002c0 S |
20 | compat_urllib_parse_unquote, |
21 | compat_urllib_parse_unquote_plus, | |
7c80519c | 22 | compat_urllib_parse_urlparse, |
7c61bd36 | 23 | compat_urlparse, |
c5e8d7af | 24 | compat_str, |
4bb4a188 PH |
25 | ) |
26 | from ..utils import ( | |
c5e8d7af | 27 | clean_html, |
515fc877 | 28 | encode_dict, |
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, |
4bb4a188 | 35 | orderedSet, |
7c80519c | 36 | parse_duration, |
0cb58b02 | 37 | remove_quotes, |
041bc3ad | 38 | remove_start, |
5c2266df | 39 | sanitized_Request, |
cf7e015f | 40 | smuggle_url, |
c93d53f5 | 41 | str_to_int, |
c5e8d7af PH |
42 | unescapeHTML, |
43 | unified_strdate, | |
cf7e015f | 44 | unsmuggle_url, |
81c2f20b | 45 | uppercase_escape, |
af214c3a | 46 | ISO3166Utils, |
c5e8d7af PH |
47 | ) |
48 | ||
5f6a1245 | 49 | |
de7f3446 | 50 | class YoutubeBaseInfoExtractor(InfoExtractor): |
b2e8bc1b JMF |
51 | """Provide base functions for Youtube extractors""" |
52 | _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' | |
9303ce3e | 53 | _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge' |
b2e8bc1b JMF |
54 | _NETRC_MACHINE = 'youtube' |
55 | # If True it will raise an error if no login info is provided | |
56 | _LOGIN_REQUIRED = False | |
57 | ||
b2e8bc1b | 58 | def _set_language(self): |
810fb84d PH |
59 | self._set_cookie( |
60 | '.youtube.com', 'PREF', 'f1=50000000&hl=en', | |
42939b61 | 61 | # YouTube sets the expire time to about two months |
810fb84d | 62 | expire_time=time.time() + 2 * 30 * 24 * 3600) |
b2e8bc1b | 63 | |
25f14e9f S |
64 | def _ids_to_results(self, ids): |
65 | return [ | |
66 | self.url_result(vid_id, 'Youtube', video_id=vid_id) | |
67 | for vid_id in ids] | |
68 | ||
b2e8bc1b | 69 | def _login(self): |
83317f69 | 70 | """ |
71 | Attempt to log in to YouTube. | |
72 | True is returned if successful or skipped. | |
73 | False is returned if login failed. | |
74 | ||
75 | If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. | |
76 | """ | |
b2e8bc1b JMF |
77 | (username, password) = self._get_login_info() |
78 | # No authentication to be performed | |
79 | if username is None: | |
80 | if self._LOGIN_REQUIRED: | |
69ea8ca4 | 81 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
83317f69 | 82 | return True |
b2e8bc1b | 83 | |
7cc3570e PH |
84 | login_page = self._download_webpage( |
85 | self._LOGIN_URL, None, | |
69ea8ca4 PH |
86 | note='Downloading login page', |
87 | errnote='unable to fetch login page', fatal=False) | |
7cc3570e PH |
88 | if login_page is False: |
89 | return | |
b2e8bc1b | 90 | |
795f28f8 | 91 | galx = self._search_regex(r'(?s)<input.+?name="GALX".+?value="(.+?)"', |
78caa52a | 92 | login_page, 'Login GALX parameter') |
c5e8d7af | 93 | |
b2e8bc1b JMF |
94 | # Log in |
95 | login_form_strs = { | |
8bcc8756 JW |
96 | 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', |
97 | 'Email': username, | |
98 | 'GALX': galx, | |
99 | 'Passwd': password, | |
100 | ||
101 | 'PersistentCookie': 'yes', | |
102 | '_utf8': '霱', | |
103 | 'bgresponse': 'js_disabled', | |
104 | 'checkConnection': '', | |
105 | 'checkedDomains': 'youtube', | |
106 | 'dnConn': '', | |
107 | 'pstMsg': '0', | |
108 | 'rmShown': '1', | |
109 | 'secTok': '', | |
110 | 'signIn': 'Sign in', | |
111 | 'timeStmp': '', | |
112 | 'service': 'youtube', | |
113 | 'uilel': '3', | |
114 | 'hl': 'en_US', | |
b2e8bc1b | 115 | } |
83317f69 | 116 | |
515fc877 | 117 | login_data = compat_urllib_parse.urlencode(encode_dict(login_form_strs)).encode('ascii') |
7cc3570e | 118 | |
5c2266df | 119 | req = sanitized_Request(self._LOGIN_URL, login_data) |
7cc3570e PH |
120 | login_results = self._download_webpage( |
121 | req, None, | |
69ea8ca4 | 122 | note='Logging in', errnote='unable to log in', fatal=False) |
7cc3570e PH |
123 | if login_results is False: |
124 | return False | |
83317f69 | 125 | |
126 | if re.search(r'id="errormsg_0_Passwd"', login_results) is not None: | |
69ea8ca4 | 127 | raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True) |
83317f69 | 128 | |
129 | # Two-Factor | |
130 | # TODO add SMS and phone call support - these require making a request and then prompting the user | |
131 | ||
9303ce3e | 132 | if re.search(r'(?i)<form[^>]* id="challenge"', login_results) is not None: |
041bc3ad | 133 | tfa_code = self._get_tfa_info('2-step verification code') |
83317f69 | 134 | |
041bc3ad S |
135 | if not tfa_code: |
136 | self._downloader.report_warning( | |
137 | 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>' | |
138 | '(Note that only TOTP (Google Authenticator App) codes work at this time.)') | |
83317f69 | 139 | return False |
140 | ||
041bc3ad S |
141 | tfa_code = remove_start(tfa_code, 'G-') |
142 | ||
143 | tfa_form_strs = self._form_hidden_inputs('challenge', login_results) | |
144 | ||
145 | tfa_form_strs.update({ | |
9303ce3e | 146 | 'Pin': tfa_code, |
147 | 'TrustDevice': 'on', | |
041bc3ad S |
148 | }) |
149 | ||
515fc877 | 150 | tfa_data = compat_urllib_parse.urlencode(encode_dict(tfa_form_strs)).encode('ascii') |
83317f69 | 151 | |
5c2266df | 152 | tfa_req = sanitized_Request(self._TWOFACTOR_URL, tfa_data) |
83317f69 | 153 | tfa_results = self._download_webpage( |
154 | tfa_req, None, | |
69ea8ca4 | 155 | note='Submitting TFA code', errnote='unable to submit tfa', fatal=False) |
83317f69 | 156 | |
157 | if tfa_results is False: | |
158 | return False | |
159 | ||
9303ce3e | 160 | if re.search(r'(?i)<form[^>]* id="challenge"', tfa_results) is not None: |
041bc3ad | 161 | self._downloader.report_warning('Two-factor code expired or invalid. Please try again, or use a one-use backup code instead.') |
83317f69 | 162 | return False |
163 | if re.search(r'(?i)<form[^>]* id="gaia_loginform"', tfa_results) is not None: | |
69ea8ca4 | 164 | self._downloader.report_warning('unable to log in - did the page structure change?') |
83317f69 | 165 | return False |
166 | if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None: | |
69ea8ca4 | 167 | self._downloader.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.') |
83317f69 | 168 | return False |
169 | ||
7cc3570e | 170 | if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None: |
69ea8ca4 | 171 | self._downloader.report_warning('unable to log in: bad username or password') |
b2e8bc1b JMF |
172 | return False |
173 | return True | |
174 | ||
b2e8bc1b JMF |
175 | def _real_initialize(self): |
176 | if self._downloader is None: | |
177 | return | |
42939b61 | 178 | self._set_language() |
b2e8bc1b JMF |
179 | if not self._login(): |
180 | return | |
c5e8d7af | 181 | |
8377574c | 182 | |
061a75ed S |
183 | class YoutubeEntryListBaseInfoExtractor(InfoExtractor): |
184 | # Extract entries from page with "Load more" button | |
648e6a1f S |
185 | def _entries(self, page, playlist_id): |
186 | more_widget_html = content_html = page | |
187 | for page_num in itertools.count(1): | |
061a75ed S |
188 | for entry in self._process_page(content_html): |
189 | yield entry | |
648e6a1f S |
190 | |
191 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) | |
192 | if not mobj: | |
193 | break | |
194 | ||
195 | more = self._download_json( | |
196 | 'https://youtube.com/%s' % mobj.group('more'), playlist_id, | |
197 | 'Downloading page #%s' % page_num, | |
198 | transform_source=uppercase_escape) | |
199 | content_html = more['content_html'] | |
200 | if not content_html.strip(): | |
201 | # Some webpages show a "Load more" button but they don't | |
202 | # have more videos | |
203 | break | |
204 | more_widget_html = more['load_more_widget_html'] | |
205 | ||
061a75ed S |
206 | |
207 | class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): | |
208 | def _process_page(self, content): | |
209 | for video_id, video_title in self.extract_videos_from_page(content): | |
210 | yield self.url_result(video_id, 'Youtube', video_id, video_title) | |
211 | ||
648e6a1f S |
212 | def extract_videos_from_page(self, page): |
213 | ids_in_page = [] | |
214 | titles_in_page = [] | |
215 | for mobj in re.finditer(self._VIDEO_RE, page): | |
216 | # The link with index 0 is not the first video of the playlist (not sure if still actual) | |
217 | if 'index' in mobj.groupdict() and mobj.group('id') == '0': | |
218 | continue | |
219 | video_id = mobj.group('id') | |
220 | video_title = unescapeHTML(mobj.group('title')) | |
221 | if video_title: | |
222 | video_title = video_title.strip() | |
223 | try: | |
224 | idx = ids_in_page.index(video_id) | |
225 | if video_title and not titles_in_page[idx]: | |
226 | titles_in_page[idx] = video_title | |
227 | except ValueError: | |
228 | ids_in_page.append(video_id) | |
229 | titles_in_page.append(video_title) | |
230 | return zip(ids_in_page, titles_in_page) | |
231 | ||
232 | ||
061a75ed S |
233 | class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor): |
234 | def _process_page(self, content): | |
235 | for playlist_id in re.findall(r'href="/?playlist\?list=(.+?)"', content): | |
236 | yield self.url_result( | |
237 | 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist') | |
238 | ||
0c148415 S |
239 | def _real_extract(self, url): |
240 | playlist_id = self._match_id(url) | |
241 | webpage = self._download_webpage(url, playlist_id) | |
0c148415 | 242 | title = self._og_search_title(webpage, fatal=False) |
061a75ed | 243 | return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title) |
0c148415 S |
244 | |
245 | ||
360e1ca5 | 246 | class YoutubeIE(YoutubeBaseInfoExtractor): |
78caa52a | 247 | IE_DESC = 'YouTube.com' |
cb7dfeea | 248 | _VALID_URL = r"""(?x)^ |
c5e8d7af | 249 | ( |
edb53e2d | 250 | (?:https?://|//) # http(s):// or protocol-independent URL |
cb7dfeea | 251 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/| |
484aaeb2 | 252 | (?:www\.)?deturl\.com/www\.youtube\.com/| |
e70dc1d1 | 253 | (?:www\.)?pwnyoutube\.com/| |
f7000f3a | 254 | (?:www\.)?yourepeat\.com/| |
e69ae5b9 JMF |
255 | tube\.majestyc\.net/| |
256 | youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains | |
c5e8d7af PH |
257 | (?:.*?\#/)? # handle anchor (#/) redirect urls |
258 | (?: # the various things that can precede the ID: | |
ac7553d0 | 259 | (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/ |
c5e8d7af | 260 | |(?: # or the v= param in all its forms |
f7000f3a | 261 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) |
c5e8d7af | 262 | (?:\?|\#!?) # the params delimiter ? or # or #! |
040ac686 | 263 | (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY) |
c5e8d7af PH |
264 | v= |
265 | ) | |
f4b05232 | 266 | )) |
cbaed4bb S |
267 | |(?: |
268 | youtu\.be| # just youtu.be/xxxx | |
269 | vid\.plus # or vid.plus/xxxx | |
270 | )/ | |
edb53e2d | 271 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= |
f4b05232 | 272 | ) |
c5e8d7af | 273 | )? # all until now is optional -> you can pass the naked ID |
8963d9c2 | 274 | ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID |
9291475f | 275 | (?!.*?&list=) # combined list/video URLs are handled by the playlist IE |
c5e8d7af PH |
276 | (?(1).+)? # if we found the ID, everything can follow |
277 | $""" | |
c5e8d7af | 278 | _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' |
2c62dc26 PH |
279 | _formats = { |
280 | '5': {'ext': 'flv', 'width': 400, 'height': 240}, | |
281 | '6': {'ext': 'flv', 'width': 450, 'height': 270}, | |
282 | '13': {'ext': '3gp'}, | |
283 | '17': {'ext': '3gp', 'width': 176, 'height': 144}, | |
284 | '18': {'ext': 'mp4', 'width': 640, 'height': 360}, | |
285 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720}, | |
286 | '34': {'ext': 'flv', 'width': 640, 'height': 360}, | |
287 | '35': {'ext': 'flv', 'width': 854, 'height': 480}, | |
288 | '36': {'ext': '3gp', 'width': 320, 'height': 240}, | |
289 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080}, | |
290 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072}, | |
291 | '43': {'ext': 'webm', 'width': 640, 'height': 360}, | |
292 | '44': {'ext': 'webm', 'width': 854, 'height': 480}, | |
293 | '45': {'ext': 'webm', 'width': 1280, 'height': 720}, | |
294 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080}, | |
c9bebed2 S |
295 | '59': {'ext': 'mp4', 'width': 854, 'height': 480}, |
296 | '78': {'ext': 'mp4', 'width': 854, 'height': 480}, | |
2c62dc26 | 297 | |
1d043b93 | 298 | |
86fe61c8 | 299 | # 3d videos |
43b81eb9 PH |
300 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'preference': -20}, |
301 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'preference': -20}, | |
302 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'preference': -20}, | |
303 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'preference': -20}, | |
304 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'preference': -20}, | |
305 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'preference': -20}, | |
306 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'preference': -20}, | |
836a086c | 307 | |
96fb5605 | 308 | # Apple HTTP Live Streaming |
43b81eb9 PH |
309 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'preference': -10}, |
310 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'preference': -10}, | |
311 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'preference': -10}, | |
312 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'preference': -10}, | |
313 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'preference': -10}, | |
314 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'preference': -10}, | |
315 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'preference': -10}, | |
2c62dc26 PH |
316 | |
317 | # DASH mp4 video | |
43b81eb9 PH |
318 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
319 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
320 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
321 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
322 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
e65566a9 | 323 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559) |
43b81eb9 PH |
324 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
325 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
0d2c1418 PH |
326 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'}, |
327 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'}, | |
328 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'h264'}, | |
836a086c | 329 | |
f6f1fc92 | 330 | # Dash mp4 audio |
62cd676c PH |
331 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'}, |
332 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'}, | |
333 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'}, | |
836a086c AZ |
334 | |
335 | # Dash webm | |
4c6bd5b5 JMF |
336 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}, |
337 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}, | |
338 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}, | |
339 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}, | |
340 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}, | |
341 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40}, | |
342 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'container': 'webm', 'vcodec': 'vp9'}, | |
e75cafe9 A |
343 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
344 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
345 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
346 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
347 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
348 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
349 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
3c80377b | 350 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
4c6b4764 | 351 | # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug) |
18061bba | 352 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
4c6bd5b5 JMF |
353 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'}, |
354 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'}, | |
355 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'}, | |
356 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'vp9'}, | |
357 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'vp9'}, | |
2c62dc26 PH |
358 | |
359 | # Dash webm audio | |
55db73ef | 360 | '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50}, |
e75cafe9 | 361 | '172': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50}, |
ce6b9a2d | 362 | |
0857baad PH |
363 | # Dash webm audio with opus inside |
364 | '249': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50}, | |
365 | '250': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50}, | |
366 | '251': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50}, | |
367 | ||
ce6b9a2d PH |
368 | # RTMP (unnamed) |
369 | '_rtmp': {'protocol': 'rtmp'}, | |
c5e8d7af | 370 | } |
836a086c | 371 | |
78caa52a | 372 | IE_NAME = 'youtube' |
2eb88d95 PH |
373 | _TESTS = [ |
374 | { | |
297a564b | 375 | 'url': 'http://www.youtube.com/watch?v=BaW_jenozKcj&t=1s&end=9', |
4bc3a23e PH |
376 | 'info_dict': { |
377 | 'id': 'BaW_jenozKc', | |
378 | 'ext': 'mp4', | |
379 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
380 | 'uploader': 'Philipp Hagemeister', | |
381 | 'uploader_id': 'phihag', | |
382 | 'upload_date': '20121002', | |
383 | '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 .', | |
384 | 'categories': ['Science & Technology'], | |
000b6b5a | 385 | 'tags': ['youtube-dl'], |
3e7c1224 PH |
386 | 'like_count': int, |
387 | 'dislike_count': int, | |
7c80519c | 388 | 'start_time': 1, |
297a564b | 389 | 'end_time': 9, |
2eb88d95 | 390 | } |
0e853ca4 | 391 | }, |
0e853ca4 | 392 | { |
4bc3a23e PH |
393 | 'url': 'http://www.youtube.com/watch?v=UxxajLWwzqY', |
394 | 'note': 'Test generic use_cipher_signature video (#897)', | |
395 | 'info_dict': { | |
396 | 'id': 'UxxajLWwzqY', | |
397 | 'ext': 'mp4', | |
398 | 'upload_date': '20120506', | |
399 | 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', | |
0cb58b02 | 400 | 'alt_title': 'I Love It (feat. Charli XCX)', |
000b6b5a S |
401 | 'description': 'md5:782e8651347686cba06e58f71ab51773', |
402 | 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli', | |
403 | 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop', | |
404 | 'iconic ep', 'iconic', 'love', 'it'], | |
4bc3a23e PH |
405 | 'uploader': 'Icona Pop', |
406 | 'uploader_id': 'IconaPop', | |
0cb58b02 | 407 | 'creator': 'Icona Pop', |
2eb88d95 | 408 | } |
c108eb73 JMF |
409 | }, |
410 | { | |
4bc3a23e PH |
411 | 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ', |
412 | 'note': 'Test VEVO video with age protection (#956)', | |
413 | 'info_dict': { | |
414 | 'id': '07FYdnEawAQ', | |
415 | 'ext': 'mp4', | |
416 | 'upload_date': '20130703', | |
417 | 'title': 'Justin Timberlake - Tunnel Vision (Explicit)', | |
0cb58b02 | 418 | 'alt_title': 'Tunnel Vision', |
4bc3a23e PH |
419 | 'description': 'md5:64249768eec3bc4276236606ea996373', |
420 | 'uploader': 'justintimberlakeVEVO', | |
421 | 'uploader_id': 'justintimberlakeVEVO', | |
0cb58b02 | 422 | 'creator': 'Justin Timberlake', |
34952f09 | 423 | 'age_limit': 18, |
c108eb73 JMF |
424 | } |
425 | }, | |
fccd3771 | 426 | { |
4bc3a23e PH |
427 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', |
428 | 'note': 'Embed-only video (#1746)', | |
429 | 'info_dict': { | |
430 | 'id': 'yZIXLfi8CZQ', | |
431 | 'ext': 'mp4', | |
432 | 'upload_date': '20120608', | |
433 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
434 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
435 | 'uploader': 'SET India', | |
94bfcd23 S |
436 | 'uploader_id': 'setindia', |
437 | 'age_limit': 18, | |
fccd3771 PH |
438 | } |
439 | }, | |
11b56058 PM |
440 | { |
441 | 'url': 'http://www.youtube.com/watch?v=BaW_jenozKcj&v=UxxajLWwzqY', | |
442 | 'note': 'Use the first video ID in the URL', | |
443 | 'info_dict': { | |
444 | 'id': 'BaW_jenozKc', | |
445 | 'ext': 'mp4', | |
446 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
447 | 'uploader': 'Philipp Hagemeister', | |
448 | 'uploader_id': 'phihag', | |
449 | 'upload_date': '20121002', | |
450 | '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 .', | |
451 | 'categories': ['Science & Technology'], | |
452 | 'tags': ['youtube-dl'], | |
453 | 'like_count': int, | |
454 | 'dislike_count': int, | |
34a7de29 S |
455 | }, |
456 | 'params': { | |
457 | 'skip_download': True, | |
458 | }, | |
11b56058 | 459 | }, |
dd27fd17 | 460 | { |
4bc3a23e PH |
461 | 'url': 'http://www.youtube.com/watch?v=a9LDPn-MO4I', |
462 | 'note': '256k DASH audio (format 141) via DASH manifest', | |
463 | 'info_dict': { | |
464 | 'id': 'a9LDPn-MO4I', | |
465 | 'ext': 'm4a', | |
466 | 'upload_date': '20121002', | |
467 | 'uploader_id': '8KVIDEO', | |
468 | 'description': '', | |
469 | 'uploader': '8KVIDEO', | |
470 | 'title': 'UHDTV TEST 8K VIDEO.mp4' | |
4919603f | 471 | }, |
4bc3a23e PH |
472 | 'params': { |
473 | 'youtube_include_dash_manifest': True, | |
474 | 'format': '141', | |
4919603f | 475 | }, |
dd27fd17 | 476 | }, |
3489b7d2 JMF |
477 | # DASH manifest with encrypted signature |
478 | { | |
78caa52a PH |
479 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', |
480 | 'info_dict': { | |
481 | 'id': 'IB3lcPjvWLA', | |
482 | 'ext': 'm4a', | |
b766eb27 JMF |
483 | 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson', |
484 | 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d', | |
78caa52a PH |
485 | 'uploader': 'AfrojackVEVO', |
486 | 'uploader_id': 'AfrojackVEVO', | |
487 | 'upload_date': '20131011', | |
3489b7d2 | 488 | }, |
4bc3a23e | 489 | 'params': { |
78caa52a PH |
490 | 'youtube_include_dash_manifest': True, |
491 | 'format': '141', | |
3489b7d2 JMF |
492 | }, |
493 | }, | |
aaeb86f6 S |
494 | # JS player signature function name containing $ |
495 | { | |
496 | 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM', | |
497 | 'info_dict': { | |
498 | 'id': 'nfWlot6h_JM', | |
499 | 'ext': 'm4a', | |
500 | 'title': 'Taylor Swift - Shake It Off', | |
0cb58b02 | 501 | 'alt_title': 'Shake It Off', |
f57b7835 | 502 | 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3', |
aaeb86f6 S |
503 | 'uploader': 'TaylorSwiftVEVO', |
504 | 'uploader_id': 'TaylorSwiftVEVO', | |
505 | 'upload_date': '20140818', | |
0cb58b02 | 506 | 'creator': 'Taylor Swift', |
aaeb86f6 S |
507 | }, |
508 | 'params': { | |
509 | 'youtube_include_dash_manifest': True, | |
510 | 'format': '141', | |
511 | }, | |
512 | }, | |
aa79ac0c PH |
513 | # Controversy video |
514 | { | |
515 | 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8', | |
516 | 'info_dict': { | |
517 | 'id': 'T4XJQO3qol8', | |
518 | 'ext': 'mp4', | |
519 | 'upload_date': '20100909', | |
520 | 'uploader': 'The Amazing Atheist', | |
521 | 'uploader_id': 'TheAmazingAtheist', | |
522 | 'title': 'Burning Everyone\'s Koran', | |
523 | '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', | |
524 | } | |
c522adb1 JMF |
525 | }, |
526 | # Normal age-gate video (No vevo, embed allowed) | |
527 | { | |
528 | 'url': 'http://youtube.com/watch?v=HtVdAasjOgU', | |
529 | 'info_dict': { | |
530 | 'id': 'HtVdAasjOgU', | |
531 | 'ext': 'mp4', | |
532 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
9ed99402 | 533 | 'description': 're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', |
c522adb1 JMF |
534 | 'uploader': 'The Witcher', |
535 | 'uploader_id': 'WitcherGame', | |
536 | 'upload_date': '20140605', | |
34952f09 | 537 | 'age_limit': 18, |
c522adb1 JMF |
538 | }, |
539 | }, | |
fccae2b9 S |
540 | # Age-gate video with encrypted signature |
541 | { | |
542 | 'url': 'http://www.youtube.com/watch?v=6kLq3WMV1nU', | |
543 | 'info_dict': { | |
544 | 'id': '6kLq3WMV1nU', | |
545 | 'ext': 'mp4', | |
546 | 'title': 'Dedication To My Ex (Miss That) (Lyric Video)', | |
547 | 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', | |
548 | 'uploader': 'LloydVEVO', | |
549 | 'uploader_id': 'LloydVEVO', | |
550 | 'upload_date': '20110629', | |
34952f09 | 551 | 'age_limit': 18, |
fccae2b9 S |
552 | }, |
553 | }, | |
774e208f PH |
554 | # video_info is None (https://github.com/rg3/youtube-dl/issues/4421) |
555 | { | |
556 | 'url': '__2ABJjxzNo', | |
557 | 'info_dict': { | |
558 | 'id': '__2ABJjxzNo', | |
559 | 'ext': 'mp4', | |
560 | 'upload_date': '20100430', | |
561 | 'uploader_id': 'deadmau5', | |
0cb58b02 | 562 | 'creator': 'deadmau5', |
774e208f PH |
563 | 'description': 'md5:12c56784b8032162bb936a5f76d55360', |
564 | 'uploader': 'deadmau5', | |
565 | 'title': 'Deadmau5 - Some Chords (HD)', | |
0cb58b02 | 566 | 'alt_title': 'Some Chords', |
774e208f PH |
567 | }, |
568 | 'expected_warnings': [ | |
569 | 'DASH manifest missing', | |
570 | ] | |
e52a40ab PH |
571 | }, |
572 | # Olympics (https://github.com/rg3/youtube-dl/issues/4431) | |
573 | { | |
574 | 'url': 'lqQg6PlCWgI', | |
575 | 'info_dict': { | |
576 | 'id': 'lqQg6PlCWgI', | |
577 | 'ext': 'mp4', | |
90227264 | 578 | 'upload_date': '20150827', |
cbe2bd91 PH |
579 | 'uploader_id': 'olympic', |
580 | 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', | |
581 | 'uploader': 'Olympics', | |
582 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', | |
583 | }, | |
584 | 'params': { | |
585 | 'skip_download': 'requires avconv', | |
e52a40ab | 586 | } |
cbe2bd91 | 587 | }, |
6271f1ca PH |
588 | # Non-square pixels |
589 | { | |
590 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
591 | 'info_dict': { | |
592 | 'id': '_b-2C3KPAM0', | |
593 | 'ext': 'mp4', | |
594 | 'stretched_ratio': 16 / 9., | |
595 | 'upload_date': '20110310', | |
596 | 'uploader_id': 'AllenMeow', | |
597 | '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', | |
598 | 'uploader': '孫艾倫', | |
599 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', | |
600 | }, | |
06b491eb S |
601 | }, |
602 | # url_encoded_fmt_stream_map is empty string | |
603 | { | |
604 | 'url': 'qEJwOuvDf7I', | |
605 | 'info_dict': { | |
606 | 'id': 'qEJwOuvDf7I', | |
f57b7835 | 607 | 'ext': 'webm', |
06b491eb S |
608 | 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', |
609 | 'description': '', | |
610 | 'upload_date': '20150404', | |
611 | 'uploader_id': 'spbelect', | |
612 | 'uploader': 'Наблюдатели Петербурга', | |
613 | }, | |
614 | 'params': { | |
615 | 'skip_download': 'requires avconv', | |
e323cf3f S |
616 | }, |
617 | 'skip': 'This live event has ended.', | |
06b491eb | 618 | }, |
da77d856 S |
619 | # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097) |
620 | { | |
621 | 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y', | |
622 | 'info_dict': { | |
623 | 'id': 'FIl7x6_3R5Y', | |
624 | 'ext': 'mp4', | |
625 | 'title': 'md5:7b81415841e02ecd4313668cde88737a', | |
626 | 'description': 'md5:116377fd2963b81ec4ce64b542173306', | |
627 | 'upload_date': '20150625', | |
628 | 'uploader_id': 'dorappi2000', | |
629 | 'uploader': 'dorappi2000', | |
630 | 'formats': 'mincount:33', | |
631 | }, | |
2ee8f5d8 | 632 | }, |
8a1a26ce YCH |
633 | # DASH manifest with segment_list |
634 | { | |
635 | 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8', | |
636 | 'md5': '8ce563a1d667b599d21064e982ab9e31', | |
637 | 'info_dict': { | |
638 | 'id': 'CsmdDsKjzN8', | |
639 | 'ext': 'mp4', | |
17ee98e1 | 640 | 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510 |
8a1a26ce YCH |
641 | 'uploader': 'Airtek', |
642 | 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.', | |
643 | 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ', | |
644 | 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015', | |
645 | }, | |
646 | 'params': { | |
647 | 'youtube_include_dash_manifest': True, | |
648 | 'format': '135', # bestvideo | |
649 | } | |
2ee8f5d8 | 650 | }, |
cf7e015f S |
651 | { |
652 | # Multifeed videos (multiple cameras), URL is for Main Camera | |
653 | 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs', | |
654 | 'info_dict': { | |
655 | 'id': 'jqWvoWXjCVs', | |
656 | 'title': 'teamPGP: Rocket League Noob Stream', | |
657 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
658 | }, | |
659 | 'playlist': [{ | |
660 | 'info_dict': { | |
661 | 'id': 'jqWvoWXjCVs', | |
662 | 'ext': 'mp4', | |
663 | 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)', | |
664 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
665 | 'upload_date': '20150721', | |
666 | 'uploader': 'Beer Games Beer', | |
667 | 'uploader_id': 'beergamesbeer', | |
668 | }, | |
669 | }, { | |
670 | 'info_dict': { | |
671 | 'id': '6h8e8xoXJzg', | |
672 | 'ext': 'mp4', | |
673 | 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)', | |
674 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
675 | 'upload_date': '20150721', | |
676 | 'uploader': 'Beer Games Beer', | |
677 | 'uploader_id': 'beergamesbeer', | |
678 | }, | |
679 | }, { | |
680 | 'info_dict': { | |
681 | 'id': 'PUOgX5z9xZw', | |
682 | 'ext': 'mp4', | |
683 | 'title': 'teamPGP: Rocket League Noob Stream (grizzle)', | |
684 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
685 | 'upload_date': '20150721', | |
686 | 'uploader': 'Beer Games Beer', | |
687 | 'uploader_id': 'beergamesbeer', | |
688 | }, | |
689 | }, { | |
690 | 'info_dict': { | |
691 | 'id': 'teuwxikvS5k', | |
692 | 'ext': 'mp4', | |
693 | 'title': 'teamPGP: Rocket League Noob Stream (zim)', | |
694 | 'description': 'md5:dc7872fb300e143831327f1bae3af010', | |
695 | 'upload_date': '20150721', | |
696 | 'uploader': 'Beer Games Beer', | |
697 | 'uploader_id': 'beergamesbeer', | |
698 | }, | |
699 | }], | |
700 | 'params': { | |
701 | 'skip_download': True, | |
702 | }, | |
cbaed4bb S |
703 | }, |
704 | { | |
705 | 'url': 'http://vid.plus/FlRa-iH7PGw', | |
706 | 'only_matching': True, | |
0e49d9a6 LL |
707 | }, |
708 | { | |
61f92af1 | 709 | # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468) |
a8776b10 S |
710 | # Also tests cut-off URL expansion in video description (see |
711 | # https://github.com/rg3/youtube-dl/issues/1892, | |
712 | # https://github.com/rg3/youtube-dl/issues/8164) | |
0e49d9a6 LL |
713 | 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg', |
714 | 'info_dict': { | |
715 | 'id': 'lsguqyKfVQg', | |
716 | 'ext': 'mp4', | |
717 | 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21', | |
0cb58b02 | 718 | 'alt_title': 'Dark Walk', |
0e49d9a6 LL |
719 | 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a', |
720 | 'upload_date': '20151119', | |
721 | 'uploader_id': 'IronSoulElf', | |
722 | 'uploader': 'IronSoulElf', | |
0cb58b02 | 723 | 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan', |
0e49d9a6 LL |
724 | }, |
725 | 'params': { | |
726 | 'skip_download': True, | |
727 | }, | |
728 | }, | |
61f92af1 S |
729 | { |
730 | # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468) | |
731 | 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8', | |
732 | 'only_matching': True, | |
733 | }, | |
313dfc45 LL |
734 | { |
735 | # Video with yt:stretch=17:0 | |
736 | 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM', | |
737 | 'info_dict': { | |
738 | 'id': 'Q39EVAstoRM', | |
739 | 'ext': 'mp4', | |
740 | 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4', | |
741 | 'description': 'md5:ee18a25c350637c8faff806845bddee9', | |
742 | 'upload_date': '20151107', | |
743 | 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA', | |
744 | 'uploader': 'CH GAMER DROID', | |
745 | }, | |
746 | 'params': { | |
747 | 'skip_download': True, | |
748 | }, | |
749 | }, | |
040ac686 S |
750 | { |
751 | 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY', | |
752 | 'only_matching': True, | |
753 | } | |
2eb88d95 PH |
754 | ] |
755 | ||
e0df6211 PH |
756 | def __init__(self, *args, **kwargs): |
757 | super(YoutubeIE, self).__init__(*args, **kwargs) | |
83799698 | 758 | self._player_cache = {} |
e0df6211 | 759 | |
c5e8d7af PH |
760 | def report_video_info_webpage_download(self, video_id): |
761 | """Report attempt to download video info webpage.""" | |
69ea8ca4 | 762 | self.to_screen('%s: Downloading video info webpage' % video_id) |
c5e8d7af | 763 | |
c5e8d7af PH |
764 | def report_information_extraction(self, video_id): |
765 | """Report attempt to extract video information.""" | |
69ea8ca4 | 766 | self.to_screen('%s: Extracting video information' % video_id) |
c5e8d7af PH |
767 | |
768 | def report_unavailable_format(self, video_id, format): | |
769 | """Report extracted video URL.""" | |
69ea8ca4 | 770 | self.to_screen('%s: Format %s not available' % (video_id, format)) |
c5e8d7af PH |
771 | |
772 | def report_rtmp_download(self): | |
773 | """Indicate the download will use the RTMP protocol.""" | |
69ea8ca4 | 774 | self.to_screen('RTMP download detected') |
c5e8d7af | 775 | |
60064c53 PH |
776 | def _signature_cache_id(self, example_sig): |
777 | """ Return a string representation of a signature """ | |
78caa52a | 778 | return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) |
60064c53 PH |
779 | |
780 | def _extract_signature_function(self, video_id, player_url, example_sig): | |
cf010131 | 781 | id_m = re.match( |
50f84a9a | 782 | r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$', |
cf010131 | 783 | player_url) |
c081b35c PH |
784 | if not id_m: |
785 | raise ExtractorError('Cannot identify player %r' % player_url) | |
e0df6211 PH |
786 | player_type = id_m.group('ext') |
787 | player_id = id_m.group('id') | |
788 | ||
c4417ddb | 789 | # Read from filesystem cache |
60064c53 PH |
790 | func_id = '%s_%s_%s' % ( |
791 | player_type, player_id, self._signature_cache_id(example_sig)) | |
c4417ddb | 792 | assert os.path.basename(func_id) == func_id |
a0e07d31 | 793 | |
69ea8ca4 | 794 | cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) |
a0e07d31 | 795 | if cache_spec is not None: |
78caa52a | 796 | return lambda s: ''.join(s[i] for i in cache_spec) |
83799698 | 797 | |
6d1a55a5 PH |
798 | download_note = ( |
799 | 'Downloading player %s' % player_url | |
800 | if self._downloader.params.get('verbose') else | |
801 | 'Downloading %s player %s' % (player_type, player_id) | |
802 | ) | |
e0df6211 PH |
803 | if player_type == 'js': |
804 | code = self._download_webpage( | |
805 | player_url, video_id, | |
6d1a55a5 | 806 | note=download_note, |
69ea8ca4 | 807 | errnote='Download of %s failed' % player_url) |
83799698 | 808 | res = self._parse_sig_js(code) |
c4417ddb | 809 | elif player_type == 'swf': |
e0df6211 PH |
810 | urlh = self._request_webpage( |
811 | player_url, video_id, | |
6d1a55a5 | 812 | note=download_note, |
69ea8ca4 | 813 | errnote='Download of %s failed' % player_url) |
e0df6211 | 814 | code = urlh.read() |
83799698 | 815 | res = self._parse_sig_swf(code) |
e0df6211 PH |
816 | else: |
817 | assert False, 'Invalid player type %r' % player_type | |
818 | ||
785521bf PH |
819 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
820 | cache_res = res(test_string) | |
821 | cache_spec = [ord(c) for c in cache_res] | |
83799698 | 822 | |
69ea8ca4 | 823 | self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) |
83799698 PH |
824 | return res |
825 | ||
60064c53 | 826 | def _print_sig_code(self, func, example_sig): |
edf3e38e PH |
827 | def gen_sig_code(idxs): |
828 | def _genslice(start, end, step): | |
78caa52a | 829 | starts = '' if start == 0 else str(start) |
8bcc8756 | 830 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' |
69ea8ca4 | 831 | steps = '' if step == 1 else (':%d' % step) |
78caa52a | 832 | return 's[%s%s%s]' % (starts, ends, steps) |
edf3e38e PH |
833 | |
834 | step = None | |
7af808a5 PH |
835 | # Quelch pyflakes warnings - start will be set when step is set |
836 | start = '(Never used)' | |
edf3e38e PH |
837 | for i, prev in zip(idxs[1:], idxs[:-1]): |
838 | if step is not None: | |
839 | if i - prev == step: | |
840 | continue | |
841 | yield _genslice(start, prev, step) | |
842 | step = None | |
843 | continue | |
844 | if i - prev in [-1, 1]: | |
845 | step = i - prev | |
846 | start = prev | |
847 | continue | |
848 | else: | |
78caa52a | 849 | yield 's[%d]' % prev |
edf3e38e | 850 | if step is None: |
78caa52a | 851 | yield 's[%d]' % i |
edf3e38e PH |
852 | else: |
853 | yield _genslice(start, i, step) | |
854 | ||
78caa52a | 855 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
c705320f | 856 | cache_res = func(test_string) |
edf3e38e | 857 | cache_spec = [ord(c) for c in cache_res] |
78caa52a | 858 | expr_code = ' + '.join(gen_sig_code(cache_spec)) |
60064c53 PH |
859 | signature_id_tuple = '(%s)' % ( |
860 | ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) | |
69ea8ca4 | 861 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' |
78caa52a | 862 | ' return %s\n') % (signature_id_tuple, expr_code) |
69ea8ca4 | 863 | self.to_screen('Extracted signature function:\n' + code) |
edf3e38e | 864 | |
e0df6211 PH |
865 | def _parse_sig_js(self, jscode): |
866 | funcname = self._search_regex( | |
aaeb86f6 | 867 | r'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode, |
8bcc8756 | 868 | 'Initial JS player signature function name') |
2b25cb5d PH |
869 | |
870 | jsi = JSInterpreter(jscode) | |
871 | initial_function = jsi.extract_function(funcname) | |
e0df6211 PH |
872 | return lambda s: initial_function([s]) |
873 | ||
874 | def _parse_sig_swf(self, file_contents): | |
54256267 | 875 | swfi = SWFInterpreter(file_contents) |
78caa52a | 876 | TARGET_CLASSNAME = 'SignatureDecipher' |
54256267 | 877 | searched_class = swfi.extract_class(TARGET_CLASSNAME) |
78caa52a | 878 | initial_function = swfi.extract_function(searched_class, 'decipher') |
e0df6211 PH |
879 | return lambda s: initial_function([s]) |
880 | ||
83799698 | 881 | def _decrypt_signature(self, s, video_id, player_url, age_gate=False): |
257a2501 | 882 | """Turn the encrypted s field into a working signature""" |
6b37f0be | 883 | |
c8bf86d5 | 884 | if player_url is None: |
69ea8ca4 | 885 | raise ExtractorError('Cannot decrypt signature without player_url') |
920de7a2 | 886 | |
69ea8ca4 | 887 | if player_url.startswith('//'): |
78caa52a | 888 | player_url = 'https:' + player_url |
c8bf86d5 | 889 | try: |
62af3a0e | 890 | player_id = (player_url, self._signature_cache_id(s)) |
c8bf86d5 PH |
891 | if player_id not in self._player_cache: |
892 | func = self._extract_signature_function( | |
60064c53 | 893 | video_id, player_url, s |
c8bf86d5 PH |
894 | ) |
895 | self._player_cache[player_id] = func | |
896 | func = self._player_cache[player_id] | |
897 | if self._downloader.params.get('youtube_print_sig_code'): | |
60064c53 | 898 | self._print_sig_code(func, s) |
c8bf86d5 PH |
899 | return func(s) |
900 | except Exception as e: | |
901 | tb = traceback.format_exc() | |
902 | raise ExtractorError( | |
78caa52a | 903 | 'Signature extraction failed: ' + tb, cause=e) |
e0df6211 | 904 | |
360e1ca5 | 905 | def _get_subtitles(self, video_id, webpage): |
de7f3446 | 906 | try: |
60e47a26 | 907 | subs_doc = self._download_xml( |
38c2e5b8 | 908 | 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, |
7fad1c63 JMF |
909 | video_id, note=False) |
910 | except ExtractorError as err: | |
9b9c5355 | 911 | self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err)) |
de7f3446 | 912 | return {} |
de7f3446 JMF |
913 | |
914 | sub_lang_list = {} | |
60e47a26 JMF |
915 | for track in subs_doc.findall('track'): |
916 | lang = track.attrib['lang_code'] | |
7e660ac1 LD |
917 | if lang in sub_lang_list: |
918 | continue | |
360e1ca5 JMF |
919 | sub_formats = [] |
920 | for ext in ['sbv', 'vtt', 'srt']: | |
921 | params = compat_urllib_parse.urlencode({ | |
922 | 'lang': lang, | |
923 | 'v': video_id, | |
924 | 'fmt': ext, | |
925 | 'name': track.attrib['name'].encode('utf-8'), | |
926 | }) | |
927 | sub_formats.append({ | |
928 | 'url': 'https://www.youtube.com/api/timedtext?' + params, | |
929 | 'ext': ext, | |
930 | }) | |
931 | sub_lang_list[lang] = sub_formats | |
de7f3446 | 932 | if not sub_lang_list: |
69ea8ca4 | 933 | self._downloader.report_warning('video doesn\'t have subtitles') |
de7f3446 JMF |
934 | return {} |
935 | return sub_lang_list | |
936 | ||
a72778d3 S |
937 | def _get_ytplayer_config(self, video_id, webpage): |
938 | patterns = ( | |
526b3b07 S |
939 | # User data may contain arbitrary character sequences that may affect |
940 | # JSON extraction with regex, e.g. when '};' is contained the second | |
941 | # regex won't capture the whole JSON. Yet working around by trying more | |
942 | # concrete regex first keeping in mind proper quoted string handling | |
943 | # to be implemented in future that will replace this workaround (see | |
944 | # https://github.com/rg3/youtube-dl/issues/7468, | |
945 | # https://github.com/rg3/youtube-dl/pull/7599) | |
a72778d3 S |
946 | r';ytplayer\.config\s*=\s*({.+?});ytplayer', |
947 | r';ytplayer\.config\s*=\s*({.+?});', | |
948 | ) | |
949 | config = self._search_regex( | |
950 | patterns, webpage, 'ytplayer.config', default=None) | |
951 | if config: | |
952 | return self._parse_json( | |
953 | uppercase_escape(config), video_id, fatal=False) | |
0e49d9a6 | 954 | |
360e1ca5 | 955 | def _get_automatic_captions(self, video_id, webpage): |
de7f3446 JMF |
956 | """We need the webpage for getting the captions url, pass it as an |
957 | argument to speed up the process.""" | |
69ea8ca4 | 958 | self.to_screen('%s: Looking for automatic captions' % video_id) |
a72778d3 | 959 | player_config = self._get_ytplayer_config(video_id, webpage) |
78caa52a | 960 | err_msg = 'Couldn\'t find automatic captions for %s' % video_id |
a72778d3 | 961 | if not player_config: |
de7f3446 JMF |
962 | self._downloader.report_warning(err_msg) |
963 | return {} | |
de7f3446 | 964 | try: |
0792d563 PH |
965 | args = player_config['args'] |
966 | caption_url = args['ttsurl'] | |
51290d84 S |
967 | if not caption_url: |
968 | self._downloader.report_warning(err_msg) | |
582f4f83 | 969 | return {} |
0792d563 | 970 | timestamp = args['timestamp'] |
055e6f36 JMF |
971 | # We get the available subtitles |
972 | list_params = compat_urllib_parse.urlencode({ | |
973 | 'type': 'list', | |
974 | 'tlangs': 1, | |
975 | 'asrs': 1, | |
de7f3446 | 976 | }) |
055e6f36 | 977 | list_url = caption_url + '&' + list_params |
e26f8712 | 978 | caption_list = self._download_xml(list_url, video_id) |
e3dc22ca | 979 | original_lang_node = caption_list.find('track') |
7d900ef1 | 980 | if original_lang_node is None: |
69ea8ca4 | 981 | self._downloader.report_warning('Video doesn\'t have automatic captions') |
e3dc22ca JMF |
982 | return {} |
983 | original_lang = original_lang_node.attrib['lang_code'] | |
7d900ef1 | 984 | caption_kind = original_lang_node.attrib.get('kind', '') |
055e6f36 JMF |
985 | |
986 | sub_lang_list = {} | |
987 | for lang_node in caption_list.findall('target'): | |
988 | sub_lang = lang_node.attrib['lang_code'] | |
360e1ca5 JMF |
989 | sub_formats = [] |
990 | for ext in ['sbv', 'vtt', 'srt']: | |
991 | params = compat_urllib_parse.urlencode({ | |
992 | 'lang': original_lang, | |
993 | 'tlang': sub_lang, | |
994 | 'fmt': ext, | |
995 | 'ts': timestamp, | |
996 | 'kind': caption_kind, | |
997 | }) | |
998 | sub_formats.append({ | |
999 | 'url': caption_url + '&' + params, | |
1000 | 'ext': ext, | |
1001 | }) | |
1002 | sub_lang_list[sub_lang] = sub_formats | |
055e6f36 | 1003 | return sub_lang_list |
de7f3446 JMF |
1004 | # An extractor error can be raise by the download process if there are |
1005 | # no automatic captions but there are subtitles | |
1006 | except (KeyError, ExtractorError): | |
1007 | self._downloader.report_warning(err_msg) | |
1008 | return {} | |
1009 | ||
97665381 PH |
1010 | @classmethod |
1011 | def extract_id(cls, url): | |
1012 | mobj = re.match(cls._VALID_URL, url, re.VERBOSE) | |
c5e8d7af | 1013 | if mobj is None: |
69ea8ca4 | 1014 | raise ExtractorError('Invalid URL: %s' % url) |
c5e8d7af PH |
1015 | video_id = mobj.group(2) |
1016 | return video_id | |
1017 | ||
1d043b93 JMF |
1018 | def _extract_from_m3u8(self, manifest_url, video_id): |
1019 | url_map = {} | |
5f6a1245 | 1020 | |
1d043b93 JMF |
1021 | def _get_urls(_manifest): |
1022 | lines = _manifest.split('\n') | |
1023 | urls = filter(lambda l: l and not l.startswith('#'), | |
8bcc8756 | 1024 | lines) |
1d043b93 | 1025 | return urls |
78caa52a | 1026 | manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest') |
1d043b93 JMF |
1027 | formats_urls = _get_urls(manifest) |
1028 | for format_url in formats_urls: | |
890f62e8 | 1029 | itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag') |
1d043b93 JMF |
1030 | url_map[itag] = format_url |
1031 | return url_map | |
1032 | ||
1fb07d10 JG |
1033 | def _extract_annotations(self, video_id): |
1034 | url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id | |
69ea8ca4 | 1035 | return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.') |
1fb07d10 | 1036 | |
da276600 | 1037 | def _parse_dash_manifest( |
77c6fb5b | 1038 | self, video_id, dash_manifest_url, player_url, age_gate, fatal=True): |
774e208f PH |
1039 | def decrypt_sig(mobj): |
1040 | s = mobj.group(1) | |
1041 | dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) | |
1042 | return '/signature/%s' % dec_s | |
e1b9322b | 1043 | dash_manifest_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, dash_manifest_url) |
774e208f PH |
1044 | dash_doc = self._download_xml( |
1045 | dash_manifest_url, video_id, | |
1046 | note='Downloading DASH manifest', | |
77c6fb5b S |
1047 | errnote='Could not download DASH manifest', |
1048 | fatal=fatal) | |
1049 | ||
1050 | if dash_doc is False: | |
1051 | return [] | |
774e208f PH |
1052 | |
1053 | formats = [] | |
de5c5456 YCH |
1054 | for a in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}AdaptationSet'): |
1055 | mime_type = a.attrib.get('mimeType') | |
1056 | for r in a.findall('{urn:mpeg:DASH:schema:MPD:2011}Representation'): | |
1057 | url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL') | |
1058 | if url_el is None: | |
1059 | continue | |
1060 | if mime_type == 'text/vtt': | |
1061 | # TODO implement WebVTT downloading | |
1062 | pass | |
1063 | elif mime_type.startswith('audio/') or mime_type.startswith('video/'): | |
6800d337 | 1064 | segment_list = r.find('{urn:mpeg:DASH:schema:MPD:2011}SegmentList') |
de5c5456 YCH |
1065 | format_id = r.attrib['id'] |
1066 | video_url = url_el.text | |
1067 | filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength')) | |
1068 | f = { | |
1069 | 'format_id': format_id, | |
1070 | 'url': video_url, | |
1071 | 'width': int_or_none(r.attrib.get('width')), | |
1072 | 'height': int_or_none(r.attrib.get('height')), | |
1073 | 'tbr': int_or_none(r.attrib.get('bandwidth'), 1000), | |
1074 | 'asr': int_or_none(r.attrib.get('audioSamplingRate')), | |
1075 | 'filesize': filesize, | |
1076 | 'fps': int_or_none(r.attrib.get('frameRate')), | |
1077 | } | |
0c8662d2 | 1078 | if segment_list is not None: |
6800d337 YCH |
1079 | f.update({ |
1080 | 'initialization_url': segment_list.find('{urn:mpeg:DASH:schema:MPD:2011}Initialization').attrib['sourceURL'], | |
b9258c61 | 1081 | 'segment_urls': [segment.attrib.get('media') for segment in segment_list.findall('{urn:mpeg:DASH:schema:MPD:2011}SegmentURL')], |
423d2be5 | 1082 | 'protocol': 'http_dash_segments', |
6800d337 | 1083 | }) |
de5c5456 YCH |
1084 | try: |
1085 | existing_format = next( | |
1086 | fo for fo in formats | |
1087 | if fo['format_id'] == format_id) | |
1088 | except StopIteration: | |
1089 | full_info = self._formats.get(format_id, {}).copy() | |
1090 | full_info.update(f) | |
1b5a1ae2 S |
1091 | codecs = r.attrib.get('codecs') |
1092 | if codecs: | |
1093 | if full_info.get('acodec') == 'none' and 'vcodec' not in full_info: | |
1094 | full_info['vcodec'] = codecs | |
1095 | elif full_info.get('vcodec') == 'none' and 'acodec' not in full_info: | |
1096 | full_info['acodec'] = codecs | |
de5c5456 YCH |
1097 | formats.append(full_info) |
1098 | else: | |
1099 | existing_format.update(f) | |
1100 | else: | |
1101 | self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type) | |
774e208f PH |
1102 | return formats |
1103 | ||
c5e8d7af | 1104 | def _real_extract(self, url): |
cf7e015f S |
1105 | url, smuggled_data = unsmuggle_url(url, {}) |
1106 | ||
7e8c0af0 | 1107 | proto = ( |
78caa52a PH |
1108 | 'http' if self._downloader.params.get('prefer_insecure', False) |
1109 | else 'https') | |
7e8c0af0 | 1110 | |
7c80519c | 1111 | start_time = None |
297a564b | 1112 | end_time = None |
7c80519c JMF |
1113 | parsed_url = compat_urllib_parse_urlparse(url) |
1114 | for component in [parsed_url.fragment, parsed_url.query]: | |
1115 | query = compat_parse_qs(component) | |
297a564b | 1116 | if start_time is None and 't' in query: |
7c80519c | 1117 | start_time = parse_duration(query['t'][0]) |
2929fa0e JMF |
1118 | if start_time is None and 'start' in query: |
1119 | start_time = parse_duration(query['start'][0]) | |
297a564b JMF |
1120 | if end_time is None and 'end' in query: |
1121 | end_time = parse_duration(query['end'][0]) | |
7c80519c | 1122 | |
c5e8d7af PH |
1123 | # Extract original video URL from URL with redirection, like age verification, using next_url parameter |
1124 | mobj = re.search(self._NEXT_URL_RE, url) | |
1125 | if mobj: | |
7fd002c0 | 1126 | url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/') |
97665381 | 1127 | video_id = self.extract_id(url) |
c5e8d7af PH |
1128 | |
1129 | # Get video webpage | |
aa79ac0c | 1130 | url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id |
a1f934b1 | 1131 | video_webpage = self._download_webpage(url, video_id) |
c5e8d7af PH |
1132 | |
1133 | # Attempt to extract SWF player URL | |
e0df6211 | 1134 | mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) |
c5e8d7af PH |
1135 | if mobj is not None: |
1136 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) | |
1137 | else: | |
1138 | player_url = None | |
1139 | ||
d8d24a92 S |
1140 | dash_mpds = [] |
1141 | ||
1142 | def add_dash_mpd(video_info): | |
1143 | dash_mpd = video_info.get('dashmpd') | |
1144 | if dash_mpd and dash_mpd[0] not in dash_mpds: | |
1145 | dash_mpds.append(dash_mpd[0]) | |
1146 | ||
c5e8d7af | 1147 | # Get video info |
6449cd80 | 1148 | embed_webpage = None |
2fe1ff85 | 1149 | is_live = None |
c108eb73 | 1150 | if re.search(r'player-age-gate-content">', video_webpage) is not None: |
c108eb73 JMF |
1151 | age_gate = True |
1152 | # We simulate the access to the video from www.youtube.com/v/{video_id} | |
1153 | # this can be viewed without login into Youtube | |
beb95e77 CL |
1154 | url = proto + '://www.youtube.com/embed/%s' % video_id |
1155 | embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage') | |
2c57c7fa JMF |
1156 | data = compat_urllib_parse.urlencode({ |
1157 | 'video_id': video_id, | |
1158 | 'eurl': 'https://youtube.googleapis.com/v/' + video_id, | |
c084c934 | 1159 | 'sts': self._search_regex( |
beb95e77 | 1160 | r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''), |
2c57c7fa | 1161 | }) |
7e8c0af0 | 1162 | video_info_url = proto + '://www.youtube.com/get_video_info?' + data |
94bd3613 PH |
1163 | video_info_webpage = self._download_webpage( |
1164 | video_info_url, video_id, | |
20436c30 | 1165 | note='Refetching age-gated info webpage', |
94bd3613 | 1166 | errnote='unable to download video info webpage') |
c5e8d7af | 1167 | video_info = compat_parse_qs(video_info_webpage) |
d8d24a92 | 1168 | add_dash_mpd(video_info) |
c108eb73 JMF |
1169 | else: |
1170 | age_gate = False | |
bc93bdb5 | 1171 | video_info = None |
d8d24a92 | 1172 | # Try looking directly into the video webpage |
a72778d3 S |
1173 | ytplayer_config = self._get_ytplayer_config(video_id, video_webpage) |
1174 | if ytplayer_config: | |
4e62ebe2 | 1175 | args = ytplayer_config['args'] |
d8d24a92 S |
1176 | if args.get('url_encoded_fmt_stream_map'): |
1177 | # Convert to the same format returned by compat_parse_qs | |
1178 | video_info = dict((k, [v]) for k, v in args.items()) | |
1179 | add_dash_mpd(video_info) | |
2fe1ff85 JMF |
1180 | if args.get('livestream') == '1' or args.get('live_playback') == 1: |
1181 | is_live = True | |
0a3cf9ad S |
1182 | if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): |
1183 | # We also try looking in get_video_info since it may contain different dashmpd | |
1184 | # URL that points to a DASH manifest with possibly different itag set (some itags | |
1185 | # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH | |
1186 | # manifest pointed by get_video_info's dashmpd). | |
1187 | # The general idea is to take a union of itags of both DASH manifests (for example | |
1188 | # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093) | |
4e62ebe2 | 1189 | self.report_video_info_webpage_download(video_id) |
0a3cf9ad | 1190 | for el_type in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']: |
810fb84d PH |
1191 | video_info_url = ( |
1192 | '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' | |
1193 | % (proto, video_id, el_type)) | |
1194 | video_info_webpage = self._download_webpage( | |
1195 | video_info_url, | |
4e62ebe2 JMF |
1196 | video_id, note=False, |
1197 | errnote='unable to download video info webpage') | |
0a3cf9ad | 1198 | get_video_info = compat_parse_qs(video_info_webpage) |
87dc4511 JMF |
1199 | if get_video_info.get('use_cipher_signature') != ['True']: |
1200 | add_dash_mpd(get_video_info) | |
0a3cf9ad S |
1201 | if not video_info: |
1202 | video_info = get_video_info | |
1203 | if 'token' in get_video_info: | |
89ea063e S |
1204 | # Different get_video_info requests may report different results, e.g. |
1205 | # some may report video unavailability, but some may serve it without | |
1206 | # any complaint (see https://github.com/rg3/youtube-dl/issues/7362, | |
1207 | # the original webpage as well as el=info and el=embedded get_video_info | |
1208 | # requests report video unavailability due to geo restriction while | |
1209 | # el=detailpage succeeds and returns valid data). This is probably | |
1210 | # due to YouTube measures against IP ranges of hosting providers. | |
1211 | # Working around by preferring the first succeeded video_info containing | |
1212 | # the token if no such video_info yet was found. | |
44b2264f S |
1213 | if 'token' not in video_info: |
1214 | video_info = get_video_info | |
4e62ebe2 | 1215 | break |
c5e8d7af PH |
1216 | if 'token' not in video_info: |
1217 | if 'reason' in video_info: | |
af214c3a YCH |
1218 | if 'The uploader has not made this video available in your country.' in video_info['reason']: |
1219 | regions_allowed = self._html_search_meta('regionsAllowed', video_webpage, default=None) | |
678e436f | 1220 | if regions_allowed: |
af214c3a YCH |
1221 | raise ExtractorError('YouTube said: This video is available in %s only' % ( |
1222 | ', '.join(map(ISO3166Utils.short2full, regions_allowed.split(',')))), | |
1223 | expected=True) | |
d11271dd | 1224 | raise ExtractorError( |
78caa52a | 1225 | 'YouTube said: %s' % video_info['reason'][0], |
d11271dd | 1226 | expected=True, video_id=video_id) |
c5e8d7af | 1227 | else: |
d11271dd | 1228 | raise ExtractorError( |
78caa52a | 1229 | '"token" parameter not in video info for unknown reason', |
d11271dd | 1230 | video_id=video_id) |
c5e8d7af | 1231 | |
cf7e015f S |
1232 | # title |
1233 | if 'title' in video_info: | |
1234 | video_title = video_info['title'][0] | |
1235 | else: | |
1236 | self._downloader.report_warning('Unable to extract video title') | |
1237 | video_title = '_' | |
1238 | ||
1239 | # description | |
1240 | video_description = get_element_by_id("eow-description", video_webpage) | |
1241 | if video_description: | |
1242 | video_description = re.sub(r'''(?x) | |
1243 | <a\s+ | |
1244 | (?:[a-zA-Z-]+="[^"]+"\s+)*? | |
23f13e97 | 1245 | (?:title|href)="([^"]+)"\s+ |
cf7e015f | 1246 | (?:[a-zA-Z-]+="[^"]+"\s+)*? |
096b5339 | 1247 | class="(?:yt-uix-redirect-link|yt-uix-sessionlink[^"]*)"[^>]*> |
23f13e97 | 1248 | [^<]+\.{3}\s* |
cf7e015f S |
1249 | </a> |
1250 | ''', r'\1', video_description) | |
1251 | video_description = clean_html(video_description) | |
1252 | else: | |
1253 | fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage) | |
1254 | if fd_mobj: | |
1255 | video_description = unescapeHTML(fd_mobj.group(1)) | |
1256 | else: | |
1257 | video_description = '' | |
1258 | ||
5e1eddb9 S |
1259 | if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False): |
1260 | if not self._downloader.params.get('noplaylist'): | |
1261 | entries = [] | |
1262 | feed_ids = [] | |
1263 | multifeed_metadata_list = compat_urllib_parse_unquote_plus(video_info['multifeed_metadata_list'][0]) | |
1264 | for feed in multifeed_metadata_list.split(','): | |
1265 | feed_data = compat_parse_qs(feed) | |
1266 | entries.append({ | |
1267 | '_type': 'url_transparent', | |
1268 | 'ie_key': 'Youtube', | |
1269 | 'url': smuggle_url( | |
1270 | '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]), | |
1271 | {'force_singlefeed': True}), | |
1272 | 'title': '%s (%s)' % (video_title, feed_data['title'][0]), | |
1273 | }) | |
1274 | feed_ids.append(feed_data['id'][0]) | |
1275 | self.to_screen( | |
1276 | 'Downloading multifeed video (%s) - add --no-playlist to just download video %s' | |
1277 | % (', '.join(feed_ids), video_id)) | |
1278 | return self.playlist_result(entries, video_id, video_title, video_description) | |
1279 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
cf7e015f | 1280 | |
1d699755 PH |
1281 | if 'view_count' in video_info: |
1282 | view_count = int(video_info['view_count'][0]) | |
1283 | else: | |
1284 | view_count = None | |
1285 | ||
c5e8d7af PH |
1286 | # Check for "rental" videos |
1287 | if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: | |
69ea8ca4 | 1288 | raise ExtractorError('"rental" videos not supported') |
c5e8d7af PH |
1289 | |
1290 | # Start extracting information | |
1291 | self.report_information_extraction(video_id) | |
1292 | ||
1293 | # uploader | |
1294 | if 'author' not in video_info: | |
69ea8ca4 | 1295 | raise ExtractorError('Unable to extract uploader name') |
7fd002c0 | 1296 | video_uploader = compat_urllib_parse_unquote_plus(video_info['author'][0]) |
c5e8d7af PH |
1297 | |
1298 | # uploader_id | |
1299 | video_uploader_id = None | |
1300 | mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage) | |
1301 | if mobj is not None: | |
1302 | video_uploader_id = mobj.group(1) | |
1303 | else: | |
69ea8ca4 | 1304 | self._downloader.report_warning('unable to extract uploader nickname') |
c5e8d7af | 1305 | |
c5e8d7af | 1306 | # thumbnail image |
7763b04e JMF |
1307 | # We try first to get a high quality image: |
1308 | m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">', | |
1309 | video_webpage, re.DOTALL) | |
1310 | if m_thumb is not None: | |
1311 | video_thumbnail = m_thumb.group(1) | |
1312 | elif 'thumbnail_url' not in video_info: | |
69ea8ca4 | 1313 | self._downloader.report_warning('unable to extract video thumbnail') |
f490e77e | 1314 | video_thumbnail = None |
c5e8d7af | 1315 | else: # don't panic if we can't find it |
7fd002c0 | 1316 | video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0]) |
c5e8d7af PH |
1317 | |
1318 | # upload date | |
9d0b581f S |
1319 | upload_date = self._html_search_meta( |
1320 | 'datePublished', video_webpage, 'upload date', default=None) | |
1321 | if not upload_date: | |
1322 | upload_date = self._search_regex( | |
1323 | [r'(?s)id="eow-date.*?>(.*?)</span>', | |
1324 | r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'], | |
1325 | video_webpage, 'upload date', default=None) | |
1326 | if upload_date: | |
1327 | upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) | |
1328 | upload_date = unified_strdate(upload_date) | |
c5e8d7af | 1329 | |
0cb58b02 S |
1330 | m_music = re.search( |
1331 | r'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li', | |
1332 | video_webpage) | |
1333 | if m_music: | |
1334 | video_alt_title = remove_quotes(unescapeHTML(m_music.group('title'))) | |
1335 | video_creator = clean_html(m_music.group('creator')) | |
1336 | else: | |
1337 | video_alt_title = video_creator = None | |
1338 | ||
55f7bd2d PH |
1339 | m_cat_container = self._search_regex( |
1340 | r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', | |
624dcebf | 1341 | video_webpage, 'categories', default=None) |
ec8deefc | 1342 | if m_cat_container: |
ad3bc6ac | 1343 | category = self._html_search_regex( |
01ed5c9b | 1344 | r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', |
ad3bc6ac PH |
1345 | default=None) |
1346 | video_categories = None if category is None else [category] | |
1347 | else: | |
1348 | video_categories = None | |
ec8deefc | 1349 | |
000b6b5a S |
1350 | video_tags = [ |
1351 | unescapeHTML(m.group('content')) | |
1352 | for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)] | |
1353 | ||
f30a38be | 1354 | def _extract_count(count_name): |
c93d53f5 S |
1355 | return str_to_int(self._search_regex( |
1356 | r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>' | |
1357 | % re.escape(count_name), | |
1358 | video_webpage, count_name, default=None)) | |
1359 | ||
69ea8ca4 PH |
1360 | like_count = _extract_count('like') |
1361 | dislike_count = _extract_count('dislike') | |
336c3a69 | 1362 | |
c5e8d7af | 1363 | # subtitles |
d82134c3 | 1364 | video_subtitles = self.extract_subtitles(video_id, video_webpage) |
360e1ca5 | 1365 | automatic_captions = self.extract_automatic_captions(video_id, video_webpage) |
c5e8d7af PH |
1366 | |
1367 | if 'length_seconds' not in video_info: | |
69ea8ca4 | 1368 | self._downloader.report_warning('unable to extract video duration') |
b466b702 | 1369 | video_duration = None |
c5e8d7af | 1370 | else: |
7fd002c0 | 1371 | video_duration = int(compat_urllib_parse_unquote_plus(video_info['length_seconds'][0])) |
c5e8d7af | 1372 | |
1fb07d10 JG |
1373 | # annotations |
1374 | video_annotations = None | |
1375 | if self._downloader.params.get('writeannotations', False): | |
5f6a1245 | 1376 | video_annotations = self._extract_annotations(video_id) |
1fb07d10 | 1377 | |
dd27fd17 PH |
1378 | def _map_to_format_list(urlmap): |
1379 | formats = [] | |
1380 | for itag, video_real_url in urlmap.items(): | |
1381 | dct = { | |
1382 | 'format_id': itag, | |
1383 | 'url': video_real_url, | |
1384 | 'player_url': player_url, | |
1385 | } | |
0b65e5d4 PH |
1386 | if itag in self._formats: |
1387 | dct.update(self._formats[itag]) | |
dd27fd17 PH |
1388 | formats.append(dct) |
1389 | return formats | |
1390 | ||
c5e8d7af PH |
1391 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): |
1392 | self.report_rtmp_download() | |
dd27fd17 PH |
1393 | formats = [{ |
1394 | 'format_id': '_rtmp', | |
1395 | 'protocol': 'rtmp', | |
1396 | 'url': video_info['conn'][0], | |
1397 | 'player_url': player_url, | |
1398 | }] | |
24270b03 | 1399 | elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1: |
5f6a1245 | 1400 | encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] |
00fe14fc | 1401 | if 'rtmpe%3Dyes' in encoded_url_map: |
a7055eb9 | 1402 | raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True) |
c9afb51c | 1403 | formats = [] |
00fe14fc | 1404 | for url_data_str in encoded_url_map.split(','): |
c5e8d7af | 1405 | url_data = compat_parse_qs(url_data_str) |
201e9eaa PH |
1406 | if 'itag' not in url_data or 'url' not in url_data: |
1407 | continue | |
1408 | format_id = url_data['itag'][0] | |
1409 | url = url_data['url'][0] | |
1410 | ||
1411 | if 'sig' in url_data: | |
1412 | url += '&signature=' + url_data['sig'][0] | |
1413 | elif 's' in url_data: | |
1414 | encrypted_sig = url_data['s'][0] | |
6449cd80 | 1415 | ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' |
201e9eaa | 1416 | |
beb95e77 | 1417 | jsplayer_url_json = self._search_regex( |
6449cd80 PH |
1418 | ASSETS_RE, |
1419 | embed_webpage if age_gate else video_webpage, | |
1420 | 'JS player URL (1)', default=None) | |
1421 | if not jsplayer_url_json and not age_gate: | |
1422 | # We need the embed website after all | |
1423 | if embed_webpage is None: | |
1424 | embed_url = proto + '://www.youtube.com/embed/%s' % video_id | |
1425 | embed_webpage = self._download_webpage( | |
1426 | embed_url, video_id, 'Downloading embed webpage') | |
1427 | jsplayer_url_json = self._search_regex( | |
1428 | ASSETS_RE, embed_webpage, 'JS player URL') | |
1429 | ||
beb95e77 | 1430 | player_url = json.loads(jsplayer_url_json) |
201e9eaa PH |
1431 | if player_url is None: |
1432 | player_url_json = self._search_regex( | |
1433 | r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', | |
78caa52a | 1434 | video_webpage, 'age gate player URL') |
201e9eaa PH |
1435 | player_url = json.loads(player_url_json) |
1436 | ||
1437 | if self._downloader.params.get('verbose'): | |
cf010131 | 1438 | if player_url is None: |
201e9eaa PH |
1439 | player_version = 'unknown' |
1440 | player_desc = 'unknown' | |
1441 | else: | |
1442 | if player_url.endswith('swf'): | |
1443 | player_version = self._search_regex( | |
1444 | r'-(.+?)(?:/watch_as3)?\.swf$', player_url, | |
78caa52a | 1445 | 'flash player', fatal=False) |
201e9eaa | 1446 | player_desc = 'flash player %s' % player_version |
cf010131 | 1447 | else: |
201e9eaa | 1448 | player_version = self._search_regex( |
50f84a9a | 1449 | [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r'(?:www|player)-([^/]+)/base\.js'], |
201e9eaa PH |
1450 | player_url, |
1451 | 'html5 player', fatal=False) | |
78caa52a | 1452 | player_desc = 'html5 player %s' % player_version |
201e9eaa | 1453 | |
60064c53 | 1454 | parts_sizes = self._signature_cache_id(encrypted_sig) |
69ea8ca4 | 1455 | self.to_screen('{%s} signature length %s, %s' % |
9e1a5b84 | 1456 | (format_id, parts_sizes, player_desc)) |
201e9eaa PH |
1457 | |
1458 | signature = self._decrypt_signature( | |
1459 | encrypted_sig, video_id, player_url, age_gate) | |
1460 | url += '&signature=' + signature | |
1461 | if 'ratebypass' not in url: | |
1462 | url += '&ratebypass=yes' | |
c9afb51c | 1463 | |
aabc2be6 S |
1464 | # Some itags are not included in DASH manifest thus corresponding formats will |
1465 | # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993). | |
1466 | # Trying to extract metadata from url_encoded_fmt_stream_map entry. | |
1467 | mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0]) | |
1468 | width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None) | |
1469 | dct = { | |
c9afb51c AH |
1470 | 'format_id': format_id, |
1471 | 'url': url, | |
1472 | 'player_url': player_url, | |
c9afb51c | 1473 | 'filesize': int_or_none(url_data.get('clen', [None])[0]), |
aabc2be6 | 1474 | 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000), |
c9afb51c AH |
1475 | 'width': width, |
1476 | 'height': height, | |
1477 | 'fps': int_or_none(url_data.get('fps', [None])[0]), | |
aabc2be6 | 1478 | 'format_note': url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0], |
c9afb51c | 1479 | } |
aabc2be6 S |
1480 | type_ = url_data.get('type', [None])[0] |
1481 | if type_: | |
1482 | type_split = type_.split(';') | |
1483 | kind_ext = type_split[0].split('/') | |
1484 | if len(kind_ext) == 2: | |
1485 | kind, ext = kind_ext | |
1486 | dct['ext'] = ext | |
1487 | if kind in ('audio', 'video'): | |
1488 | codecs = None | |
1489 | for mobj in re.finditer( | |
1490 | r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_): | |
1491 | if mobj.group('key') == 'codecs': | |
1492 | codecs = mobj.group('val') | |
1493 | break | |
1494 | if codecs: | |
1495 | codecs = codecs.split(',') | |
1496 | if len(codecs) == 2: | |
cc28492d | 1497 | acodec, vcodec = codecs[1], codecs[0] |
aabc2be6 S |
1498 | else: |
1499 | acodec, vcodec = (codecs[0], 'none') if kind == 'audio' else ('none', codecs[0]) | |
1500 | dct.update({ | |
1501 | 'acodec': acodec, | |
1502 | 'vcodec': vcodec, | |
1503 | }) | |
1504 | if format_id in self._formats: | |
1505 | dct.update(self._formats[format_id]) | |
1506 | formats.append(dct) | |
1d043b93 JMF |
1507 | elif video_info.get('hlsvp'): |
1508 | manifest_url = video_info['hlsvp'][0] | |
1509 | url_map = self._extract_from_m3u8(manifest_url, video_id) | |
dd27fd17 | 1510 | formats = _map_to_format_list(url_map) |
ac5a69af YCH |
1511 | # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming |
1512 | for a_format in formats: | |
049d71d8 | 1513 | a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True' |
c5e8d7af | 1514 | else: |
8ceabd4d S |
1515 | unavailable_message = self._html_search_regex( |
1516 | r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>', | |
1517 | video_webpage, 'unavailable message', default=None) | |
1518 | if unavailable_message: | |
1519 | raise ExtractorError(unavailable_message, expected=True) | |
69ea8ca4 | 1520 | raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') |
c5e8d7af | 1521 | |
dd27fd17 | 1522 | # Look for the DASH manifest |
203fb43f | 1523 | if self._downloader.params.get('youtube_include_dash_manifest', True): |
77c6fb5b | 1524 | dash_mpd_fatal = True |
d8d24a92 S |
1525 | for dash_manifest_url in dash_mpds: |
1526 | dash_formats = {} | |
774e208f | 1527 | try: |
d8d24a92 | 1528 | for df in self._parse_dash_manifest( |
77c6fb5b | 1529 | video_id, dash_manifest_url, player_url, age_gate, dash_mpd_fatal): |
d8d24a92 S |
1530 | # Do not overwrite DASH format found in some previous DASH manifest |
1531 | if df['format_id'] not in dash_formats: | |
1532 | dash_formats[df['format_id']] = df | |
77c6fb5b S |
1533 | # Additional DASH manifests may end up in HTTP Error 403 therefore |
1534 | # allow them to fail without bug report message if we already have | |
1535 | # some DASH manifest succeeded. This is temporary workaround to reduce | |
1536 | # burst of bug reports until we figure out the reason and whether it | |
1537 | # can be fixed at all. | |
1538 | dash_mpd_fatal = False | |
774e208f PH |
1539 | except (ExtractorError, KeyError) as e: |
1540 | self.report_warning( | |
1541 | 'Skipping DASH manifest: %r' % e, video_id) | |
d8d24a92 | 1542 | if dash_formats: |
04b3b3df JMF |
1543 | # Remove the formats we found through non-DASH, they |
1544 | # contain less info and it can be wrong, because we use | |
1545 | # fixed values (for example the resolution). See | |
1546 | # https://github.com/rg3/youtube-dl/issues/5774 for an | |
1547 | # example. | |
d80265cc | 1548 | formats = [f for f in formats if f['format_id'] not in dash_formats.keys()] |
d8d24a92 | 1549 | formats.extend(dash_formats.values()) |
d80044c2 | 1550 | |
6271f1ca PH |
1551 | # Check for malformed aspect ratio |
1552 | stretched_m = re.search( | |
1553 | r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">', | |
1554 | video_webpage) | |
1555 | if stretched_m: | |
313dfc45 LL |
1556 | w = float(stretched_m.group('w')) |
1557 | h = float(stretched_m.group('h')) | |
5faf9fed S |
1558 | # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0). |
1559 | # We will only process correct ratios. | |
313dfc45 | 1560 | if w > 0 and h > 0: |
41f24c32 | 1561 | ratio = w / h |
313dfc45 LL |
1562 | for f in formats: |
1563 | if f.get('vcodec') != 'none': | |
1564 | f['stretched_ratio'] = ratio | |
6271f1ca | 1565 | |
4bcc7bd1 | 1566 | self._sort_formats(formats) |
4ea3be0a | 1567 | |
1568 | return { | |
8bcc8756 JW |
1569 | 'id': video_id, |
1570 | 'uploader': video_uploader, | |
1571 | 'uploader_id': video_uploader_id, | |
1572 | 'upload_date': upload_date, | |
0cb58b02 | 1573 | 'creator': video_creator, |
8bcc8756 | 1574 | 'title': video_title, |
0cb58b02 | 1575 | 'alt_title': video_alt_title, |
8bcc8756 JW |
1576 | 'thumbnail': video_thumbnail, |
1577 | 'description': video_description, | |
1578 | 'categories': video_categories, | |
000b6b5a | 1579 | 'tags': video_tags, |
8bcc8756 | 1580 | 'subtitles': video_subtitles, |
360e1ca5 | 1581 | 'automatic_captions': automatic_captions, |
8bcc8756 JW |
1582 | 'duration': video_duration, |
1583 | 'age_limit': 18 if age_gate else 0, | |
1584 | 'annotations': video_annotations, | |
7e8c0af0 | 1585 | 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id, |
8bcc8756 | 1586 | 'view_count': view_count, |
4ea3be0a | 1587 | 'like_count': like_count, |
1588 | 'dislike_count': dislike_count, | |
2d30521a | 1589 | 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]), |
8bcc8756 | 1590 | 'formats': formats, |
2fe1ff85 | 1591 | 'is_live': is_live, |
7c80519c | 1592 | 'start_time': start_time, |
297a564b | 1593 | 'end_time': end_time, |
4ea3be0a | 1594 | } |
c5e8d7af | 1595 | |
5f6a1245 | 1596 | |
648e6a1f | 1597 | class YoutubePlaylistIE(YoutubeBaseInfoExtractor, YoutubePlaylistBaseInfoExtractor): |
78caa52a | 1598 | IE_DESC = 'YouTube.com playlists' |
d67cc9fa | 1599 | _VALID_URL = r"""(?x)(?: |
c5e8d7af PH |
1600 | (?:https?://)? |
1601 | (?:\w+\.)? | |
1602 | youtube\.com/ | |
1603 | (?: | |
ac7553d0 | 1604 | (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries) |
2e1b9285 | 1605 | \? (?:.*?[&;])*? (?:p|a|list)= |
c5e8d7af PH |
1606 | | p/ |
1607 | ) | |
d67cc9fa | 1608 | ( |
99209c29 | 1609 | (?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,} |
5f6a1245 | 1610 | # Top tracks, they can also include dots |
d67cc9fa JMF |
1611 | |(?:MC)[\w\.]* |
1612 | ) | |
c5e8d7af PH |
1613 | .* |
1614 | | | |
99209c29 | 1615 | ((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,}) |
c5e8d7af | 1616 | )""" |
dbb94fb0 | 1617 | _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' |
648e6a1f | 1618 | _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?' |
78caa52a | 1619 | IE_NAME = 'youtube:playlist' |
81127aa5 PH |
1620 | _TESTS = [{ |
1621 | 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', | |
1622 | 'info_dict': { | |
1623 | 'title': 'ytdl test PL', | |
a1cf99d0 | 1624 | 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', |
81127aa5 PH |
1625 | }, |
1626 | 'playlist_count': 3, | |
9291475f PH |
1627 | }, { |
1628 | 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', | |
1629 | 'info_dict': { | |
acf757f4 | 1630 | 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', |
9291475f PH |
1631 | 'title': 'YDL_Empty_List', |
1632 | }, | |
1633 | 'playlist_count': 0, | |
1634 | }, { | |
1635 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
1636 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
1637 | 'info_dict': { | |
1638 | 'title': '29C3: Not my department', | |
acf757f4 | 1639 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', |
9291475f PH |
1640 | }, |
1641 | 'playlist_count': 95, | |
1642 | }, { | |
1643 | 'note': 'issue #673', | |
1644 | 'url': 'PLBB231211A4F62143', | |
1645 | 'info_dict': { | |
f46a8702 | 1646 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', |
acf757f4 | 1647 | 'id': 'PLBB231211A4F62143', |
9291475f PH |
1648 | }, |
1649 | 'playlist_mincount': 26, | |
1650 | }, { | |
1651 | 'note': 'Large playlist', | |
1652 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
1653 | 'info_dict': { | |
1654 | 'title': 'Uploads from Cauchemar', | |
acf757f4 | 1655 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', |
9291475f PH |
1656 | }, |
1657 | 'playlist_mincount': 799, | |
1658 | }, { | |
1659 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
1660 | 'info_dict': { | |
1661 | 'title': 'YDL_safe_search', | |
acf757f4 | 1662 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', |
9291475f PH |
1663 | }, |
1664 | 'playlist_count': 2, | |
ac7553d0 PH |
1665 | }, { |
1666 | 'note': 'embedded', | |
1667 | 'url': 'http://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
1668 | 'playlist_count': 4, | |
1669 | 'info_dict': { | |
1670 | 'title': 'JODA15', | |
acf757f4 | 1671 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', |
ac7553d0 | 1672 | } |
6b08cdf6 PH |
1673 | }, { |
1674 | 'note': 'Embedded SWF player', | |
1675 | 'url': 'http://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0', | |
1676 | 'playlist_count': 4, | |
1677 | 'info_dict': { | |
1678 | 'title': 'JODA7', | |
acf757f4 | 1679 | 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ', |
6b08cdf6 | 1680 | } |
4b7df0d3 JMF |
1681 | }, { |
1682 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
1683 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
1684 | 'info_dict': { | |
acf757f4 PH |
1685 | 'title': 'Uploads from Interstellar Movie', |
1686 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
4b7df0d3 JMF |
1687 | }, |
1688 | 'playlist_mincout': 21, | |
81127aa5 | 1689 | }] |
c5e8d7af | 1690 | |
880e1c52 JMF |
1691 | def _real_initialize(self): |
1692 | self._login() | |
1693 | ||
652cdaa2 | 1694 | def _extract_mix(self, playlist_id): |
99209c29 | 1695 | # The mixes are generated from a single video |
652cdaa2 | 1696 | # the id of the playlist is just 'RD' + video_id |
7d4afc55 | 1697 | url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id) |
c9cc0bf5 | 1698 | webpage = self._download_webpage( |
78caa52a | 1699 | url, playlist_id, 'Downloading Youtube mix') |
bc2f773b | 1700 | search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage) |
c9cc0bf5 PH |
1701 | title_span = ( |
1702 | search_title('playlist-title') or | |
1703 | search_title('title long-title') or | |
1704 | search_title('title')) | |
76d1700b | 1705 | title = clean_html(title_span) |
c9cc0bf5 PH |
1706 | ids = orderedSet(re.findall( |
1707 | r'''(?xs)data-video-username=".*?".*? | |
1708 | href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id), | |
1709 | webpage)) | |
652cdaa2 JMF |
1710 | url_results = self._ids_to_results(ids) |
1711 | ||
1712 | return self.playlist_result(url_results, playlist_id, title) | |
1713 | ||
448830ce | 1714 | def _extract_playlist(self, playlist_id): |
dbb94fb0 S |
1715 | url = self._TEMPLATE_URL % playlist_id |
1716 | page = self._download_webpage(url, playlist_id) | |
dbb94fb0 | 1717 | |
39b62db1 YCH |
1718 | for match in re.findall(r'<div class="yt-alert-message">([^<]+)</div>', page): |
1719 | match = match.strip() | |
1720 | # Check if the playlist exists or is private | |
1721 | if re.match(r'[^<]*(The|This) playlist (does not exist|is private)[^<]*', match): | |
1722 | raise ExtractorError( | |
1723 | 'The playlist doesn\'t exist or is private, use --username or ' | |
1724 | '--netrc to access it.', | |
1725 | expected=True) | |
1726 | elif re.match(r'[^<]*Invalid parameters[^<]*', match): | |
1727 | raise ExtractorError( | |
1728 | 'Invalid parameters. Maybe URL is incorrect.', | |
1729 | expected=True) | |
1730 | elif re.match(r'[^<]*Choose your language[^<]*', match): | |
1731 | continue | |
1732 | else: | |
1733 | self.report_warning('Youtube gives an alert message: ' + match) | |
10c0e2d8 | 1734 | |
dbb94fb0 | 1735 | playlist_title = self._html_search_regex( |
63b4295d | 1736 | r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>', |
78caa52a | 1737 | page, 'title') |
c5e8d7af | 1738 | |
648e6a1f | 1739 | return self.playlist_result(self._entries(page, playlist_id), playlist_id, playlist_title) |
c5e8d7af | 1740 | |
448830ce S |
1741 | def _real_extract(self, url): |
1742 | # Extract playlist id | |
1743 | mobj = re.match(self._VALID_URL, url) | |
1744 | if mobj is None: | |
1745 | raise ExtractorError('Invalid URL: %s' % url) | |
1746 | playlist_id = mobj.group(1) or mobj.group(2) | |
1747 | ||
1748 | # Check if it's a video-specific URL | |
1749 | query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) | |
1750 | if 'v' in query_dict: | |
1751 | video_id = query_dict['v'][0] | |
1752 | if self._downloader.params.get('noplaylist'): | |
1753 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
1754 | return self.url_result(video_id, 'Youtube', video_id=video_id) | |
1755 | else: | |
1756 | self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) | |
1757 | ||
1758 | if playlist_id.startswith('RD') or playlist_id.startswith('UL'): | |
1759 | # Mixes require a custom extraction process | |
1760 | return self._extract_mix(playlist_id) | |
1761 | ||
1762 | return self._extract_playlist(playlist_id) | |
1763 | ||
c5e8d7af | 1764 | |
648e6a1f | 1765 | class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor): |
78caa52a | 1766 | IE_DESC = 'YouTube.com channels' |
9ff67727 | 1767 | _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)' |
eb0f3e7e | 1768 | _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos' |
648e6a1f | 1769 | _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?' |
78caa52a | 1770 | IE_NAME = 'youtube:channel' |
cdc628a4 PH |
1771 | _TESTS = [{ |
1772 | 'note': 'paginated channel', | |
1773 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
1774 | 'playlist_mincount': 91, | |
acf757f4 | 1775 | 'info_dict': { |
9170ca5b JMF |
1776 | 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w', |
1777 | 'title': 'Uploads from lex will', | |
acf757f4 | 1778 | } |
5c43afd4 JMF |
1779 | }, { |
1780 | 'note': 'Age restricted channel', | |
1781 | # from https://www.youtube.com/user/DeusExOfficial | |
1782 | 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w', | |
1783 | 'playlist_mincount': 64, | |
1784 | 'info_dict': { | |
1785 | 'id': 'UUs0ifCMCm1icqRbqhUINa0w', | |
1786 | 'title': 'Uploads from Deus Ex', | |
1787 | }, | |
cdc628a4 | 1788 | }] |
c5e8d7af | 1789 | |
e462474e S |
1790 | @classmethod |
1791 | def suitable(cls, url): | |
1792 | return False if YoutubePlaylistsIE.suitable(url) else super(YoutubeChannelIE, cls).suitable(url) | |
1793 | ||
c5e8d7af | 1794 | def _real_extract(self, url): |
9ff67727 | 1795 | channel_id = self._match_id(url) |
c5e8d7af | 1796 | |
eb0f3e7e | 1797 | url = self._TEMPLATE_URL % channel_id |
386bdfa6 S |
1798 | |
1799 | # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778) | |
1800 | # Workaround by extracting as a playlist if managed to obtain channel playlist URL | |
1801 | # otherwise fallback on channel by page extraction | |
1802 | channel_page = self._download_webpage( | |
1803 | url + '?view=57', channel_id, | |
1804 | 'Downloading channel page', fatal=False) | |
2b3c2546 PH |
1805 | if channel_page is False: |
1806 | channel_playlist_id = False | |
1807 | else: | |
1808 | channel_playlist_id = self._html_search_meta( | |
1809 | 'channelId', channel_page, 'channel id', default=None) | |
1810 | if not channel_playlist_id: | |
1811 | channel_playlist_id = self._search_regex( | |
5c43afd4 | 1812 | r'data-(?:channel-external-|yt)id="([^"]+)"', |
2b3c2546 | 1813 | channel_page, 'channel id', default=None) |
386bdfa6 S |
1814 | if channel_playlist_id and channel_playlist_id.startswith('UC'): |
1815 | playlist_id = 'UU' + channel_playlist_id[2:] | |
d2a9de78 IK |
1816 | return self.url_result( |
1817 | compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist') | |
386bdfa6 | 1818 | |
60bf45c8 | 1819 | channel_page = self._download_webpage(url, channel_id, 'Downloading page #1') |
31812a9e PH |
1820 | autogenerated = re.search(r'''(?x) |
1821 | class="[^"]*?(?: | |
1822 | channel-header-autogenerated-label| | |
1823 | yt-channel-title-autogenerated | |
1824 | )[^"]*"''', channel_page) is not None | |
c5e8d7af | 1825 | |
b9643eed JMF |
1826 | if autogenerated: |
1827 | # The videos are contained in a single page | |
1828 | # the ajax pages can't be used, they are empty | |
b82f815f | 1829 | entries = [ |
fb69240c S |
1830 | self.url_result( |
1831 | video_id, 'Youtube', video_id=video_id, | |
1832 | video_title=video_title) | |
8f02ad4f | 1833 | for video_id, video_title in self.extract_videos_from_page(channel_page)] |
b82f815f PH |
1834 | return self.playlist_result(entries, channel_id) |
1835 | ||
648e6a1f | 1836 | return self.playlist_result(self._entries(channel_page, channel_id), channel_id) |
c5e8d7af PH |
1837 | |
1838 | ||
eb0f3e7e | 1839 | class YoutubeUserIE(YoutubeChannelIE): |
78caa52a | 1840 | IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)' |
9ff67727 | 1841 | _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)' |
eb0f3e7e | 1842 | _TEMPLATE_URL = 'https://www.youtube.com/user/%s/videos' |
78caa52a | 1843 | IE_NAME = 'youtube:user' |
c5e8d7af | 1844 | |
cdc628a4 PH |
1845 | _TESTS = [{ |
1846 | 'url': 'https://www.youtube.com/user/TheLinuxFoundation', | |
1847 | 'playlist_mincount': 320, | |
1848 | 'info_dict': { | |
1849 | 'title': 'TheLinuxFoundation', | |
1850 | } | |
1851 | }, { | |
1852 | 'url': 'ytuser:phihag', | |
1853 | 'only_matching': True, | |
1854 | }] | |
1855 | ||
e3ea4790 | 1856 | @classmethod |
f4b05232 | 1857 | def suitable(cls, url): |
e3ea4790 JMF |
1858 | # Don't return True if the url can be extracted with other youtube |
1859 | # extractor, the regex would is too permissive and it would match. | |
1860 | other_ies = iter(klass for (name, klass) in globals().items() if name.endswith('IE') and klass is not cls) | |
5f6a1245 JW |
1861 | if any(ie.suitable(url) for ie in other_ies): |
1862 | return False | |
1863 | else: | |
1864 | return super(YoutubeUserIE, cls).suitable(url) | |
f4b05232 | 1865 | |
b05654f0 | 1866 | |
e462474e S |
1867 | class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor): |
1868 | IE_DESC = 'YouTube.com user/channel playlists' | |
1869 | _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists' | |
1870 | IE_NAME = 'youtube:playlists' | |
0c148415 | 1871 | |
e568c223 | 1872 | _TESTS = [{ |
0c148415 S |
1873 | 'url': 'http://www.youtube.com/user/ThirstForScience/playlists', |
1874 | 'playlist_mincount': 4, | |
1875 | 'info_dict': { | |
1876 | 'id': 'ThirstForScience', | |
1877 | 'title': 'Thirst for Science', | |
1878 | }, | |
e568c223 S |
1879 | }, { |
1880 | # with "Load more" button | |
1881 | 'url': 'http://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd', | |
1882 | 'playlist_mincount': 70, | |
1883 | 'info_dict': { | |
1884 | 'id': 'igorkle1', | |
1885 | 'title': 'Игорь Клейнер', | |
1886 | }, | |
e462474e S |
1887 | }, { |
1888 | 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists', | |
1889 | 'playlist_mincount': 17, | |
1890 | 'info_dict': { | |
1891 | 'id': 'UCiU1dHvZObB2iP6xkJ__Icw', | |
1892 | 'title': 'Chem Player', | |
1893 | }, | |
e568c223 | 1894 | }] |
0c148415 S |
1895 | |
1896 | ||
b4c08069 | 1897 | class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE): |
78caa52a | 1898 | IE_DESC = 'YouTube.com searches' |
b4c08069 JMF |
1899 | # there doesn't appear to be a real limit, for example if you search for |
1900 | # 'python' you get more than 8.000.000 results | |
1901 | _MAX_RESULTS = float('inf') | |
78caa52a | 1902 | IE_NAME = 'youtube:search' |
b05654f0 | 1903 | _SEARCH_KEY = 'ytsearch' |
b4c08069 | 1904 | _EXTRA_QUERY_ARGS = {} |
9dd8e46a | 1905 | _TESTS = [] |
b05654f0 | 1906 | |
b05654f0 PH |
1907 | def _get_n_results(self, query, n): |
1908 | """Get a specified number of results for a query""" | |
1909 | ||
b4c08069 | 1910 | videos = [] |
b05654f0 PH |
1911 | limit = n |
1912 | ||
b4c08069 JMF |
1913 | for pagenum in itertools.count(1): |
1914 | url_query = { | |
02175a79 | 1915 | 'search_query': query.encode('utf-8'), |
b4c08069 JMF |
1916 | 'page': pagenum, |
1917 | 'spf': 'navigate', | |
1918 | } | |
1919 | url_query.update(self._EXTRA_QUERY_ARGS) | |
1920 | result_url = 'https://www.youtube.com/results?' + compat_urllib_parse.urlencode(url_query) | |
1921 | data = self._download_json( | |
69ea8ca4 | 1922 | result_url, video_id='query "%s"' % query, |
b4c08069 | 1923 | note='Downloading page %s' % pagenum, |
69ea8ca4 | 1924 | errnote='Unable to download API page') |
b4c08069 | 1925 | html_content = data[1]['body']['content'] |
7cc3570e | 1926 | |
b4c08069 | 1927 | if 'class="search-message' in html_content: |
07ad22b8 | 1928 | raise ExtractorError( |
78caa52a | 1929 | '[youtube] No video results', expected=True) |
b05654f0 | 1930 | |
b4c08069 JMF |
1931 | new_videos = self._ids_to_results(orderedSet(re.findall( |
1932 | r'href="/watch\?v=(.{11})', html_content))) | |
1933 | videos += new_videos | |
1934 | if not new_videos or len(videos) > limit: | |
1935 | break | |
b05654f0 | 1936 | |
b4c08069 JMF |
1937 | if len(videos) > n: |
1938 | videos = videos[:n] | |
b05654f0 | 1939 | return self.playlist_result(videos, query) |
75dff0ee | 1940 | |
c9ae7b95 | 1941 | |
a3dd9248 | 1942 | class YoutubeSearchDateIE(YoutubeSearchIE): |
cb7fb546 | 1943 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' |
a3dd9248 | 1944 | _SEARCH_KEY = 'ytsearchdate' |
78caa52a | 1945 | IE_DESC = 'YouTube.com searches, newest videos first' |
b4c08069 | 1946 | _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'} |
75dff0ee | 1947 | |
c9ae7b95 PH |
1948 | |
1949 | class YoutubeSearchURLIE(InfoExtractor): | |
78caa52a PH |
1950 | IE_DESC = 'YouTube.com search URLs' |
1951 | IE_NAME = 'youtube:search_url' | |
c9ae7b95 | 1952 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?search_query=(?P<query>[^&]+)(?:[&]|$)' |
cdc628a4 PH |
1953 | _TESTS = [{ |
1954 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
1955 | 'playlist_mincount': 5, | |
1956 | 'info_dict': { | |
1957 | 'title': 'youtube-dl test video', | |
1958 | } | |
1959 | }] | |
c9ae7b95 PH |
1960 | |
1961 | def _real_extract(self, url): | |
1962 | mobj = re.match(self._VALID_URL, url) | |
7fd002c0 | 1963 | query = compat_urllib_parse_unquote_plus(mobj.group('query')) |
c9ae7b95 PH |
1964 | |
1965 | webpage = self._download_webpage(url, query) | |
1966 | result_code = self._search_regex( | |
98998cde | 1967 | r'(?s)<ol[^>]+class="item-section"(.*?)</ol>', webpage, 'result HTML') |
c9ae7b95 PH |
1968 | |
1969 | part_codes = re.findall( | |
f74a7348 | 1970 | r'(?s)<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*>(.*?)</h3>', result_code) |
c9ae7b95 PH |
1971 | entries = [] |
1972 | for part_code in part_codes: | |
1973 | part_title = self._html_search_regex( | |
6feb2d5e | 1974 | [r'(?s)title="([^"]+)"', r'>([^<]+)</a>'], part_code, 'item title', fatal=False) |
c9ae7b95 PH |
1975 | part_url_snippet = self._html_search_regex( |
1976 | r'(?s)href="([^"]+)"', part_code, 'item URL') | |
1977 | part_url = compat_urlparse.urljoin( | |
1978 | 'https://www.youtube.com/', part_url_snippet) | |
1979 | entries.append({ | |
1980 | '_type': 'url', | |
1981 | 'url': part_url, | |
1982 | 'title': part_title, | |
1983 | }) | |
1984 | ||
1985 | return { | |
1986 | '_type': 'playlist', | |
1987 | 'entries': entries, | |
1988 | 'title': query, | |
1989 | } | |
1990 | ||
1991 | ||
136dadde | 1992 | class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor): |
78caa52a | 1993 | IE_DESC = 'YouTube.com (multi-season) shows' |
cdc628a4 | 1994 | _VALID_URL = r'https?://www\.youtube\.com/show/(?P<id>[^?#]*)' |
78caa52a | 1995 | IE_NAME = 'youtube:show' |
cdc628a4 | 1996 | _TESTS = [{ |
4003bd82 | 1997 | 'url': 'https://www.youtube.com/show/airdisasters', |
8801255d | 1998 | 'playlist_mincount': 5, |
cdc628a4 PH |
1999 | 'info_dict': { |
2000 | 'id': 'airdisasters', | |
2001 | 'title': 'Air Disasters', | |
2002 | } | |
2003 | }] | |
75dff0ee JMF |
2004 | |
2005 | def _real_extract(self, url): | |
136dadde S |
2006 | playlist_id = self._match_id(url) |
2007 | return super(YoutubeShowIE, self)._real_extract( | |
2008 | 'https://www.youtube.com/show/%s/playlists' % playlist_id) | |
04cc9617 JMF |
2009 | |
2010 | ||
b2e8bc1b | 2011 | class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): |
d7ae0639 | 2012 | """ |
25f14e9f | 2013 | Base class for feed extractors |
d7ae0639 JMF |
2014 | Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties. |
2015 | """ | |
b2e8bc1b | 2016 | _LOGIN_REQUIRED = True |
d7ae0639 JMF |
2017 | |
2018 | @property | |
2019 | def IE_NAME(self): | |
78caa52a | 2020 | return 'youtube:%s' % self._FEED_NAME |
04cc9617 | 2021 | |
81f0259b | 2022 | def _real_initialize(self): |
b2e8bc1b | 2023 | self._login() |
81f0259b | 2024 | |
04cc9617 | 2025 | def _real_extract(self, url): |
25f14e9f S |
2026 | page = self._download_webpage( |
2027 | 'https://www.youtube.com/feed/%s' % self._FEED_NAME, self._PLAYLIST_TITLE) | |
2bc43303 JMF |
2028 | |
2029 | # The extraction process is the same as for playlists, but the regex | |
2030 | # for the video ids doesn't contain an index | |
2031 | ids = [] | |
2032 | more_widget_html = content_html = page | |
2bc43303 JMF |
2033 | for page_num in itertools.count(1): |
2034 | matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html) | |
62c95fd5 S |
2035 | |
2036 | # 'recommended' feed has infinite 'load more' and each new portion spins | |
2037 | # the same videos in (sometimes) slightly different order, so we'll check | |
2038 | # for unicity and break when portion has no new videos | |
2039 | new_ids = filter(lambda video_id: video_id not in ids, orderedSet(matches)) | |
2040 | if not new_ids: | |
2041 | break | |
2042 | ||
2bc43303 JMF |
2043 | ids.extend(new_ids) |
2044 | ||
2045 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) | |
2046 | if not mobj: | |
2047 | break | |
2048 | ||
2049 | more = self._download_json( | |
25f14e9f | 2050 | 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE, |
2bc43303 JMF |
2051 | 'Downloading page #%s' % page_num, |
2052 | transform_source=uppercase_escape) | |
2053 | content_html = more['content_html'] | |
2054 | more_widget_html = more['load_more_widget_html'] | |
2055 | ||
25f14e9f S |
2056 | return self.playlist_result( |
2057 | self._ids_to_results(ids), playlist_title=self._PLAYLIST_TITLE) | |
2058 | ||
2059 | ||
2060 | class YoutubeWatchLaterIE(YoutubePlaylistIE): | |
2061 | IE_NAME = 'youtube:watchlater' | |
2062 | IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' | |
2063 | _VALID_URL = r'https?://www\.youtube\.com/(?:feed/watch_later|playlist\?list=WL)|:ytwatchlater' | |
2064 | ||
2065 | _TESTS = [] # override PlaylistIE tests | |
2066 | ||
2067 | def _real_extract(self, url): | |
2068 | return self._extract_playlist('WL') | |
f459d170 | 2069 | |
5f6a1245 | 2070 | |
c626a3d9 | 2071 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): |
78caa52a | 2072 | IE_NAME = 'youtube:favorites' |
f3a34072 | 2073 | IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)' |
c7a7750d | 2074 | _VALID_URL = r'https?://www\.youtube\.com/my_favorites|:ytfav(?:ou?rites)?' |
c626a3d9 JMF |
2075 | _LOGIN_REQUIRED = True |
2076 | ||
2077 | def _real_extract(self, url): | |
2078 | webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos') | |
78caa52a | 2079 | playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id') |
c626a3d9 | 2080 | return self.url_result(playlist_id, 'YoutubePlaylist') |
15870e90 PH |
2081 | |
2082 | ||
25f14e9f S |
2083 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): |
2084 | IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' | |
2085 | _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?' | |
2086 | _FEED_NAME = 'recommended' | |
2087 | _PLAYLIST_TITLE = 'Youtube Recommended videos' | |
1ed5b5c9 | 2088 | |
1ed5b5c9 | 2089 | |
25f14e9f S |
2090 | class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): |
2091 | IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' | |
2092 | _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' | |
2093 | _FEED_NAME = 'subscriptions' | |
2094 | _PLAYLIST_TITLE = 'Youtube Subscriptions' | |
1ed5b5c9 | 2095 | |
1ed5b5c9 | 2096 | |
25f14e9f S |
2097 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): |
2098 | IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' | |
2099 | _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory' | |
2100 | _FEED_NAME = 'history' | |
2101 | _PLAYLIST_TITLE = 'Youtube History' | |
1ed5b5c9 JMF |
2102 | |
2103 | ||
15870e90 PH |
2104 | class YoutubeTruncatedURLIE(InfoExtractor): |
2105 | IE_NAME = 'youtube:truncated_url' | |
2106 | IE_DESC = False # Do not list | |
975d35db | 2107 | _VALID_URL = r'''(?x) |
b95aab84 PH |
2108 | (?:https?://)? |
2109 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
2110 | (?:watch\?(?: | |
c4808c60 | 2111 | feature=[a-z_]+| |
b95aab84 PH |
2112 | annotation_id=annotation_[^&]+| |
2113 | x-yt-cl=[0-9]+| | |
c1708b89 | 2114 | hl=[^&]*| |
287be8c6 | 2115 | t=[0-9]+ |
b95aab84 PH |
2116 | )? |
2117 | | | |
2118 | attribution_link\?a=[^&]+ | |
2119 | ) | |
2120 | $ | |
975d35db | 2121 | ''' |
15870e90 | 2122 | |
c4808c60 PH |
2123 | _TESTS = [{ |
2124 | 'url': 'http://www.youtube.com/watch?annotation_id=annotation_3951667041', | |
2125 | 'only_matching': True, | |
dc2fc736 PH |
2126 | }, { |
2127 | 'url': 'http://www.youtube.com/watch?', | |
2128 | 'only_matching': True, | |
b95aab84 PH |
2129 | }, { |
2130 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
2131 | 'only_matching': True, | |
2132 | }, { | |
2133 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
2134 | 'only_matching': True, | |
c1708b89 PH |
2135 | }, { |
2136 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
2137 | 'only_matching': True, | |
287be8c6 PH |
2138 | }, { |
2139 | 'url': 'https://www.youtube.com/watch?t=2372', | |
2140 | 'only_matching': True, | |
c4808c60 PH |
2141 | }] |
2142 | ||
15870e90 PH |
2143 | def _real_extract(self, url): |
2144 | raise ExtractorError( | |
78caa52a PH |
2145 | 'Did you forget to quote the URL? Remember that & is a meta ' |
2146 | 'character in most shells, so you want to put the URL in quotes, ' | |
2147 | 'like youtube-dl ' | |
2148 | '"http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' | |
2149 | ' or simply youtube-dl BaW_jenozKc .', | |
15870e90 | 2150 | expected=True) |
772fd5cc PH |
2151 | |
2152 | ||
2153 | class YoutubeTruncatedIDIE(InfoExtractor): | |
2154 | IE_NAME = 'youtube:truncated_id' | |
2155 | IE_DESC = False # Do not list | |
b95aab84 | 2156 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' |
772fd5cc PH |
2157 | |
2158 | _TESTS = [{ | |
2159 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
2160 | 'only_matching': True, | |
2161 | }] | |
2162 | ||
2163 | def _real_extract(self, url): | |
2164 | video_id = self._match_id(url) | |
2165 | raise ExtractorError( | |
2166 | 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), | |
2167 | expected=True) |