]> jfr.im git - yt-dlp.git/blame - youtube_dl/extractor/youtube.py
[prosiebensat1] extract all formats
[yt-dlp.git] / youtube_dl / extractor / youtube.py
CommitLineData
c5e8d7af 1# coding: utf-8
c5e8d7af 2
78caa52a
PH
3from __future__ import unicode_literals
4
5
0ca96d48 6import itertools
c5e8d7af 7import json
c4417ddb 8import os.path
d77ab8e2 9import random
c5e8d7af 10import re
42939b61 11import time
e0df6211 12import traceback
c5e8d7af 13
b05654f0 14from .common import InfoExtractor, SearchInfoExtractor
2b25cb5d 15from ..jsinterp import JSInterpreter
54256267 16from ..swfinterp import SWFInterpreter
4bb4a188 17from ..compat import (
edf3e38e 18 compat_chr,
c5e8d7af 19 compat_parse_qs,
7fd002c0
S
20 compat_urllib_parse_unquote,
21 compat_urllib_parse_unquote_plus,
15707c7e 22 compat_urllib_parse_urlencode,
7c80519c 23 compat_urllib_parse_urlparse,
7c61bd36 24 compat_urlparse,
c5e8d7af 25 compat_str,
4bb4a188
PH
26)
27from ..utils import (
c5e8d7af 28 clean_html,
9b9c5355 29 error_to_compat_str,
c5e8d7af 30 ExtractorError,
2d30521a 31 float_or_none,
4bb4a188
PH
32 get_element_by_attribute,
33 get_element_by_id,
dd27fd17 34 int_or_none,
94278f72 35 mimetype2ext,
4bb4a188 36 orderedSet,
7c80519c 37 parse_duration,
0cb58b02 38 remove_quotes,
041bc3ad 39 remove_start,
5c2266df 40 sanitized_Request,
cf7e015f 41 smuggle_url,
c93d53f5 42 str_to_int,
c5e8d7af
PH
43 unescapeHTML,
44 unified_strdate,
cf7e015f 45 unsmuggle_url,
81c2f20b 46 uppercase_escape,
6e6bc8da 47 urlencode_postdata,
af214c3a 48 ISO3166Utils,
c5e8d7af
PH
49)
50
5f6a1245 51
de7f3446 52class YoutubeBaseInfoExtractor(InfoExtractor):
b2e8bc1b
JMF
53 """Provide base functions for Youtube extractors"""
54 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
9303ce3e 55 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
b2e8bc1b
JMF
56 _NETRC_MACHINE = 'youtube'
57 # If True it will raise an error if no login info is provided
58 _LOGIN_REQUIRED = False
59
b2e8bc1b 60 def _set_language(self):
810fb84d
PH
61 self._set_cookie(
62 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
42939b61 63 # YouTube sets the expire time to about two months
810fb84d 64 expire_time=time.time() + 2 * 30 * 24 * 3600)
b2e8bc1b 65
25f14e9f
S
66 def _ids_to_results(self, ids):
67 return [
68 self.url_result(vid_id, 'Youtube', video_id=vid_id)
69 for vid_id in ids]
70
b2e8bc1b 71 def _login(self):
83317f69 72 """
73 Attempt to log in to YouTube.
74 True is returned if successful or skipped.
75 False is returned if login failed.
76
77 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
78 """
b2e8bc1b
JMF
79 (username, password) = self._get_login_info()
80 # No authentication to be performed
81 if username is None:
82 if self._LOGIN_REQUIRED:
69ea8ca4 83 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
83317f69 84 return True
b2e8bc1b 85
7cc3570e
PH
86 login_page = self._download_webpage(
87 self._LOGIN_URL, None,
69ea8ca4
PH
88 note='Downloading login page',
89 errnote='unable to fetch login page', fatal=False)
7cc3570e
PH
90 if login_page is False:
91 return
b2e8bc1b 92
795f28f8 93 galx = self._search_regex(r'(?s)<input.+?name="GALX".+?value="(.+?)"',
78caa52a 94 login_page, 'Login GALX parameter')
c5e8d7af 95
b2e8bc1b
JMF
96 # Log in
97 login_form_strs = {
8bcc8756
JW
98 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1',
99 'Email': username,
100 'GALX': galx,
101 'Passwd': password,
102
103 'PersistentCookie': 'yes',
104 '_utf8': '霱',
105 'bgresponse': 'js_disabled',
106 'checkConnection': '',
107 'checkedDomains': 'youtube',
108 'dnConn': '',
109 'pstMsg': '0',
110 'rmShown': '1',
111 'secTok': '',
112 'signIn': 'Sign in',
113 'timeStmp': '',
114 'service': 'youtube',
115 'uilel': '3',
116 'hl': 'en_US',
b2e8bc1b 117 }
83317f69 118
6e6bc8da 119 login_data = urlencode_postdata(login_form_strs)
7cc3570e 120
5c2266df 121 req = sanitized_Request(self._LOGIN_URL, login_data)
7cc3570e
PH
122 login_results = self._download_webpage(
123 req, None,
69ea8ca4 124 note='Logging in', errnote='unable to log in', fatal=False)
7cc3570e
PH
125 if login_results is False:
126 return False
83317f69 127
494ab6db
S
128 error_msg = self._html_search_regex(
129 r'<[^>]+id="errormsg_0_Passwd"[^>]*>([^<]+)<',
130 login_results, 'error message', default=None)
131 if error_msg:
132 raise ExtractorError('Unable to login: %s' % error_msg, expected=True)
133
83317f69 134 if re.search(r'id="errormsg_0_Passwd"', login_results) is not None:
69ea8ca4 135 raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True)
83317f69 136
137 # Two-Factor
138 # TODO add SMS and phone call support - these require making a request and then prompting the user
139
9303ce3e 140 if re.search(r'(?i)<form[^>]* id="challenge"', login_results) is not None:
041bc3ad 141 tfa_code = self._get_tfa_info('2-step verification code')
83317f69 142
041bc3ad
S
143 if not tfa_code:
144 self._downloader.report_warning(
145 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
146 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
83317f69 147 return False
148
041bc3ad
S
149 tfa_code = remove_start(tfa_code, 'G-')
150
151 tfa_form_strs = self._form_hidden_inputs('challenge', login_results)
152
153 tfa_form_strs.update({
9303ce3e 154 'Pin': tfa_code,
155 'TrustDevice': 'on',
041bc3ad
S
156 })
157
6e6bc8da 158 tfa_data = urlencode_postdata(tfa_form_strs)
83317f69 159
5c2266df 160 tfa_req = sanitized_Request(self._TWOFACTOR_URL, tfa_data)
83317f69 161 tfa_results = self._download_webpage(
162 tfa_req, None,
69ea8ca4 163 note='Submitting TFA code', errnote='unable to submit tfa', fatal=False)
83317f69 164
165 if tfa_results is False:
166 return False
167
9303ce3e 168 if re.search(r'(?i)<form[^>]* id="challenge"', tfa_results) is not None:
041bc3ad 169 self._downloader.report_warning('Two-factor code expired or invalid. Please try again, or use a one-use backup code instead.')
83317f69 170 return False
171 if re.search(r'(?i)<form[^>]* id="gaia_loginform"', tfa_results) is not None:
69ea8ca4 172 self._downloader.report_warning('unable to log in - did the page structure change?')
83317f69 173 return False
174 if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None:
69ea8ca4 175 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 176 return False
177
7cc3570e 178 if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None:
69ea8ca4 179 self._downloader.report_warning('unable to log in: bad username or password')
b2e8bc1b
JMF
180 return False
181 return True
182
b2e8bc1b
JMF
183 def _real_initialize(self):
184 if self._downloader is None:
185 return
42939b61 186 self._set_language()
b2e8bc1b
JMF
187 if not self._login():
188 return
c5e8d7af 189
8377574c 190
8e7aad20 191class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
061a75ed 192 # Extract entries from page with "Load more" button
648e6a1f
S
193 def _entries(self, page, playlist_id):
194 more_widget_html = content_html = page
195 for page_num in itertools.count(1):
061a75ed
S
196 for entry in self._process_page(content_html):
197 yield entry
648e6a1f
S
198
199 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
200 if not mobj:
201 break
202
203 more = self._download_json(
204 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
205 'Downloading page #%s' % page_num,
206 transform_source=uppercase_escape)
207 content_html = more['content_html']
208 if not content_html.strip():
209 # Some webpages show a "Load more" button but they don't
210 # have more videos
211 break
212 more_widget_html = more['load_more_widget_html']
213
061a75ed
S
214
215class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
216 def _process_page(self, content):
217 for video_id, video_title in self.extract_videos_from_page(content):
218 yield self.url_result(video_id, 'Youtube', video_id, video_title)
219
648e6a1f
S
220 def extract_videos_from_page(self, page):
221 ids_in_page = []
222 titles_in_page = []
223 for mobj in re.finditer(self._VIDEO_RE, page):
224 # The link with index 0 is not the first video of the playlist (not sure if still actual)
225 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
226 continue
227 video_id = mobj.group('id')
228 video_title = unescapeHTML(mobj.group('title'))
229 if video_title:
230 video_title = video_title.strip()
231 try:
232 idx = ids_in_page.index(video_id)
233 if video_title and not titles_in_page[idx]:
234 titles_in_page[idx] = video_title
235 except ValueError:
236 ids_in_page.append(video_id)
237 titles_in_page.append(video_title)
238 return zip(ids_in_page, titles_in_page)
239
240
061a75ed
S
241class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
242 def _process_page(self, content):
6dee688e
S
243 for playlist_id in orderedSet(re.findall(
244 r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
245 content)):
061a75ed
S
246 yield self.url_result(
247 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
248
0c148415
S
249 def _real_extract(self, url):
250 playlist_id = self._match_id(url)
251 webpage = self._download_webpage(url, playlist_id)
0c148415 252 title = self._og_search_title(webpage, fatal=False)
061a75ed 253 return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
0c148415
S
254
255
360e1ca5 256class YoutubeIE(YoutubeBaseInfoExtractor):
78caa52a 257 IE_DESC = 'YouTube.com'
cb7dfeea 258 _VALID_URL = r"""(?x)^
c5e8d7af 259 (
edb53e2d 260 (?:https?://|//) # http(s):// or protocol-independent URL
cb7dfeea 261 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
484aaeb2 262 (?:www\.)?deturl\.com/www\.youtube\.com/|
e70dc1d1 263 (?:www\.)?pwnyoutube\.com/|
f7000f3a 264 (?:www\.)?yourepeat\.com/|
e69ae5b9
JMF
265 tube\.majestyc\.net/|
266 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
c5e8d7af
PH
267 (?:.*?\#/)? # handle anchor (#/) redirect urls
268 (?: # the various things that can precede the ID:
ac7553d0 269 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
c5e8d7af 270 |(?: # or the v= param in all its forms
f7000f3a 271 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
c5e8d7af 272 (?:\?|\#!?) # the params delimiter ? or # or #!
040ac686 273 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&amp;v=V36LpHqtcDY)
c5e8d7af
PH
274 v=
275 )
f4b05232 276 ))
cbaed4bb
S
277 |(?:
278 youtu\.be| # just youtu.be/xxxx
6d4fc66b
S
279 vid\.plus| # or vid.plus/xxxx
280 zwearz\.com/watch| # or zwearz.com/watch/xxxx
cbaed4bb 281 )/
edb53e2d 282 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
f4b05232 283 )
c5e8d7af 284 )? # all until now is optional -> you can pass the naked ID
8963d9c2 285 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
9291475f 286 (?!.*?&list=) # combined list/video URLs are handled by the playlist IE
c5e8d7af
PH
287 (?(1).+)? # if we found the ID, everything can follow
288 $"""
c5e8d7af 289 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
2c62dc26 290 _formats = {
c2d3cb4c 291 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
292 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
293 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
294 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
295 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
296 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
297 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
298 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
3834d3e3 299 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
c2d3cb4c 300 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
301 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
302 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
303 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
304 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
305 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
e1a0bfdf 306 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
c2d3cb4c 307 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
308 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
e1a0bfdf 309
310
311 # 3D videos
c2d3cb4c 312 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
313 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
314 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
315 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
e1a0bfdf 316 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
317 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
318 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
836a086c 319
96fb5605 320 # Apple HTTP Live Streaming
11f12195 321 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
c2d3cb4c 322 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
323 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
324 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
325 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
326 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
e1a0bfdf 327 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
328 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
2c62dc26
PH
329
330 # DASH mp4 video
c2d3cb4c 331 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
332 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
333 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
334 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
335 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
336 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
337 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
a6c2c244
YCH
338 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
339 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
340 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
341 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
836a086c 342
f6f1fc92 343 # Dash mp4 audio
c2d3cb4c 344 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'},
345 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'},
346 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
2c347352
S
347 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
348 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
836a086c
AZ
349
350 # Dash webm
a6c2c244
YCH
351 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
352 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
353 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
354 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
355 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
356 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
357 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9', 'preference': -40},
358 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
359 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
360 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
361 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
362 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
363 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
364 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
365 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
4c6b4764 366 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
a6c2c244
YCH
367 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
368 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
369 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
370 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
371 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
372 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
2c62dc26
PH
373
374 # Dash webm audio
a6c2c244
YCH
375 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
376 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50},
ce6b9a2d 377
0857baad 378 # Dash webm audio with opus inside
a6c2c244
YCH
379 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50},
380 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50},
381 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50},
0857baad 382
ce6b9a2d
PH
383 # RTMP (unnamed)
384 '_rtmp': {'protocol': 'rtmp'},
c5e8d7af 385 }
23d17e4b 386 _SUBTITLE_FORMATS = ('ttml', 'vtt')
836a086c 387
78caa52a 388 IE_NAME = 'youtube'
2eb88d95
PH
389 _TESTS = [
390 {
b67d6314 391 'url': 'http://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
4bc3a23e
PH
392 'info_dict': {
393 'id': 'BaW_jenozKc',
394 'ext': 'mp4',
395 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
396 'uploader': 'Philipp Hagemeister',
397 'uploader_id': 'phihag',
fd050249 398 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/phihag',
4bc3a23e 399 'upload_date': '20121002',
7caf9830 400 'license': 'Standard YouTube License',
4bc3a23e
PH
401 '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 .',
402 'categories': ['Science & Technology'],
000b6b5a 403 'tags': ['youtube-dl'],
3e7c1224
PH
404 'like_count': int,
405 'dislike_count': int,
7c80519c 406 'start_time': 1,
297a564b 407 'end_time': 9,
2eb88d95 408 }
0e853ca4 409 },
0e853ca4 410 {
4bc3a23e
PH
411 'url': 'http://www.youtube.com/watch?v=UxxajLWwzqY',
412 'note': 'Test generic use_cipher_signature video (#897)',
413 'info_dict': {
414 'id': 'UxxajLWwzqY',
415 'ext': 'mp4',
416 'upload_date': '20120506',
417 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
0cb58b02 418 'alt_title': 'I Love It (feat. Charli XCX)',
7caf9830 419 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
000b6b5a
S
420 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
421 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
422 'iconic ep', 'iconic', 'love', 'it'],
4bc3a23e
PH
423 'uploader': 'Icona Pop',
424 'uploader_id': 'IconaPop',
fd050249 425 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/IconaPop',
7caf9830 426 'license': 'Standard YouTube License',
0cb58b02 427 'creator': 'Icona Pop',
2eb88d95 428 }
c108eb73
JMF
429 },
430 {
4bc3a23e
PH
431 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
432 'note': 'Test VEVO video with age protection (#956)',
433 'info_dict': {
434 'id': '07FYdnEawAQ',
435 'ext': 'mp4',
436 'upload_date': '20130703',
437 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
0cb58b02 438 'alt_title': 'Tunnel Vision',
4bc3a23e
PH
439 'description': 'md5:64249768eec3bc4276236606ea996373',
440 'uploader': 'justintimberlakeVEVO',
441 'uploader_id': 'justintimberlakeVEVO',
fd050249 442 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
7caf9830 443 'license': 'Standard YouTube License',
0cb58b02 444 'creator': 'Justin Timberlake',
34952f09 445 'age_limit': 18,
c108eb73
JMF
446 }
447 },
fccd3771 448 {
4bc3a23e
PH
449 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
450 'note': 'Embed-only video (#1746)',
451 'info_dict': {
452 'id': 'yZIXLfi8CZQ',
453 'ext': 'mp4',
454 'upload_date': '20120608',
455 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
456 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
457 'uploader': 'SET India',
94bfcd23 458 'uploader_id': 'setindia',
fd050249 459 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/setindia',
7caf9830 460 'license': 'Standard YouTube License',
94bfcd23 461 'age_limit': 18,
fccd3771
PH
462 }
463 },
11b56058 464 {
b67d6314 465 'url': 'http://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
11b56058
PM
466 'note': 'Use the first video ID in the URL',
467 'info_dict': {
468 'id': 'BaW_jenozKc',
469 'ext': 'mp4',
470 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
471 'uploader': 'Philipp Hagemeister',
472 'uploader_id': 'phihag',
fd050249 473 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/phihag',
11b56058 474 'upload_date': '20121002',
7caf9830 475 'license': 'Standard YouTube License',
11b56058
PM
476 '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 .',
477 'categories': ['Science & Technology'],
478 'tags': ['youtube-dl'],
479 'like_count': int,
480 'dislike_count': int,
34a7de29
S
481 },
482 'params': {
483 'skip_download': True,
484 },
11b56058 485 },
dd27fd17 486 {
4bc3a23e
PH
487 'url': 'http://www.youtube.com/watch?v=a9LDPn-MO4I',
488 'note': '256k DASH audio (format 141) via DASH manifest',
489 'info_dict': {
490 'id': 'a9LDPn-MO4I',
491 'ext': 'm4a',
492 'upload_date': '20121002',
493 'uploader_id': '8KVIDEO',
fd050249 494 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
4bc3a23e
PH
495 'description': '',
496 'uploader': '8KVIDEO',
7caf9830 497 'license': 'Standard YouTube License',
4bc3a23e 498 'title': 'UHDTV TEST 8K VIDEO.mp4'
4919603f 499 },
4bc3a23e
PH
500 'params': {
501 'youtube_include_dash_manifest': True,
502 'format': '141',
4919603f 503 },
de3c7fe0 504 'skip': 'format 141 not served anymore',
dd27fd17 505 },
3489b7d2
JMF
506 # DASH manifest with encrypted signature
507 {
78caa52a
PH
508 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
509 'info_dict': {
510 'id': 'IB3lcPjvWLA',
511 'ext': 'm4a',
b766eb27
JMF
512 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
513 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
78caa52a
PH
514 'uploader': 'AfrojackVEVO',
515 'uploader_id': 'AfrojackVEVO',
516 'upload_date': '20131011',
7caf9830 517 'license': 'Standard YouTube License',
3489b7d2 518 },
4bc3a23e 519 'params': {
78caa52a 520 'youtube_include_dash_manifest': True,
de3c7fe0 521 'format': '141/bestaudio[ext=m4a]',
3489b7d2
JMF
522 },
523 },
aaeb86f6
S
524 # JS player signature function name containing $
525 {
526 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
527 'info_dict': {
528 'id': 'nfWlot6h_JM',
529 'ext': 'm4a',
530 'title': 'Taylor Swift - Shake It Off',
0cb58b02 531 'alt_title': 'Shake It Off',
f57b7835 532 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
aaeb86f6
S
533 'uploader': 'TaylorSwiftVEVO',
534 'uploader_id': 'TaylorSwiftVEVO',
535 'upload_date': '20140818',
7caf9830 536 'license': 'Standard YouTube License',
0cb58b02 537 'creator': 'Taylor Swift',
aaeb86f6
S
538 },
539 'params': {
540 'youtube_include_dash_manifest': True,
de3c7fe0 541 'format': '141/bestaudio[ext=m4a]',
aaeb86f6
S
542 },
543 },
aa79ac0c
PH
544 # Controversy video
545 {
546 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
547 'info_dict': {
548 'id': 'T4XJQO3qol8',
549 'ext': 'mp4',
550 'upload_date': '20100909',
551 'uploader': 'The Amazing Atheist',
552 'uploader_id': 'TheAmazingAtheist',
fd050249 553 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
7caf9830 554 'license': 'Standard YouTube License',
aa79ac0c
PH
555 'title': 'Burning Everyone\'s Koran',
556 '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',
557 }
c522adb1
JMF
558 },
559 # Normal age-gate video (No vevo, embed allowed)
560 {
561 'url': 'http://youtube.com/watch?v=HtVdAasjOgU',
562 'info_dict': {
563 'id': 'HtVdAasjOgU',
564 'ext': 'mp4',
565 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
9ed99402 566 'description': 're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
c522adb1
JMF
567 'uploader': 'The Witcher',
568 'uploader_id': 'WitcherGame',
fd050249 569 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
c522adb1 570 'upload_date': '20140605',
7caf9830 571 'license': 'Standard YouTube License',
34952f09 572 'age_limit': 18,
c522adb1
JMF
573 },
574 },
fccae2b9
S
575 # Age-gate video with encrypted signature
576 {
577 'url': 'http://www.youtube.com/watch?v=6kLq3WMV1nU',
578 'info_dict': {
579 'id': '6kLq3WMV1nU',
580 'ext': 'mp4',
581 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
582 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
583 'uploader': 'LloydVEVO',
584 'uploader_id': 'LloydVEVO',
fd050249 585 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
fccae2b9 586 'upload_date': '20110629',
7caf9830 587 'license': 'Standard YouTube License',
34952f09 588 'age_limit': 18,
fccae2b9
S
589 },
590 },
774e208f
PH
591 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
592 {
593 'url': '__2ABJjxzNo',
594 'info_dict': {
595 'id': '__2ABJjxzNo',
596 'ext': 'mp4',
597 'upload_date': '20100430',
598 'uploader_id': 'deadmau5',
fd050249 599 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/deadmau5',
0cb58b02 600 'creator': 'deadmau5',
774e208f
PH
601 'description': 'md5:12c56784b8032162bb936a5f76d55360',
602 'uploader': 'deadmau5',
7caf9830 603 'license': 'Standard YouTube License',
774e208f 604 'title': 'Deadmau5 - Some Chords (HD)',
0cb58b02 605 'alt_title': 'Some Chords',
774e208f
PH
606 },
607 'expected_warnings': [
608 'DASH manifest missing',
609 ]
e52a40ab
PH
610 },
611 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
612 {
613 'url': 'lqQg6PlCWgI',
614 'info_dict': {
615 'id': 'lqQg6PlCWgI',
616 'ext': 'mp4',
90227264 617 'upload_date': '20150827',
cbe2bd91 618 'uploader_id': 'olympic',
fd050249 619 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/olympic',
7caf9830 620 'license': 'Standard YouTube License',
cbe2bd91 621 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
be49068d 622 'uploader': 'Olympic',
cbe2bd91
PH
623 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
624 },
625 'params': {
626 'skip_download': 'requires avconv',
e52a40ab 627 }
cbe2bd91 628 },
6271f1ca
PH
629 # Non-square pixels
630 {
631 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
632 'info_dict': {
633 'id': '_b-2C3KPAM0',
634 'ext': 'mp4',
635 'stretched_ratio': 16 / 9.,
636 'upload_date': '20110310',
637 'uploader_id': 'AllenMeow',
fd050249 638 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
6271f1ca
PH
639 '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',
640 'uploader': '孫艾倫',
7caf9830 641 'license': 'Standard YouTube License',
6271f1ca
PH
642 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
643 },
06b491eb
S
644 },
645 # url_encoded_fmt_stream_map is empty string
646 {
647 'url': 'qEJwOuvDf7I',
648 'info_dict': {
649 'id': 'qEJwOuvDf7I',
f57b7835 650 'ext': 'webm',
06b491eb
S
651 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
652 'description': '',
653 'upload_date': '20150404',
654 'uploader_id': 'spbelect',
655 'uploader': 'Наблюдатели Петербурга',
656 },
657 'params': {
658 'skip_download': 'requires avconv',
e323cf3f
S
659 },
660 'skip': 'This live event has ended.',
06b491eb 661 },
da77d856
S
662 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
663 {
664 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
665 'info_dict': {
666 'id': 'FIl7x6_3R5Y',
667 'ext': 'mp4',
668 'title': 'md5:7b81415841e02ecd4313668cde88737a',
669 'description': 'md5:116377fd2963b81ec4ce64b542173306',
670 'upload_date': '20150625',
671 'uploader_id': 'dorappi2000',
fd050249 672 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
da77d856 673 'uploader': 'dorappi2000',
7caf9830 674 'license': 'Standard YouTube License',
be49068d 675 'formats': 'mincount:32',
da77d856 676 },
2ee8f5d8 677 },
8a1a26ce
YCH
678 # DASH manifest with segment_list
679 {
680 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
681 'md5': '8ce563a1d667b599d21064e982ab9e31',
682 'info_dict': {
683 'id': 'CsmdDsKjzN8',
684 'ext': 'mp4',
17ee98e1 685 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
8a1a26ce
YCH
686 'uploader': 'Airtek',
687 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
688 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
7caf9830 689 'license': 'Standard YouTube License',
8a1a26ce
YCH
690 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
691 },
692 'params': {
693 'youtube_include_dash_manifest': True,
694 'format': '135', # bestvideo
be49068d
S
695 },
696 'skip': 'This live event has ended.',
2ee8f5d8 697 },
cf7e015f
S
698 {
699 # Multifeed videos (multiple cameras), URL is for Main Camera
700 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
701 'info_dict': {
702 'id': 'jqWvoWXjCVs',
703 'title': 'teamPGP: Rocket League Noob Stream',
704 'description': 'md5:dc7872fb300e143831327f1bae3af010',
705 },
706 'playlist': [{
707 'info_dict': {
708 'id': 'jqWvoWXjCVs',
709 'ext': 'mp4',
710 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
711 'description': 'md5:dc7872fb300e143831327f1bae3af010',
712 'upload_date': '20150721',
713 'uploader': 'Beer Games Beer',
714 'uploader_id': 'beergamesbeer',
fd050249 715 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 716 'license': 'Standard YouTube License',
cf7e015f
S
717 },
718 }, {
719 'info_dict': {
720 'id': '6h8e8xoXJzg',
721 'ext': 'mp4',
722 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
723 'description': 'md5:dc7872fb300e143831327f1bae3af010',
724 'upload_date': '20150721',
725 'uploader': 'Beer Games Beer',
726 'uploader_id': 'beergamesbeer',
fd050249 727 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 728 'license': 'Standard YouTube License',
cf7e015f
S
729 },
730 }, {
731 'info_dict': {
732 'id': 'PUOgX5z9xZw',
733 'ext': 'mp4',
734 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
735 'description': 'md5:dc7872fb300e143831327f1bae3af010',
736 'upload_date': '20150721',
737 'uploader': 'Beer Games Beer',
738 'uploader_id': 'beergamesbeer',
fd050249 739 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 740 'license': 'Standard YouTube License',
cf7e015f
S
741 },
742 }, {
743 'info_dict': {
744 'id': 'teuwxikvS5k',
745 'ext': 'mp4',
746 'title': 'teamPGP: Rocket League Noob Stream (zim)',
747 'description': 'md5:dc7872fb300e143831327f1bae3af010',
748 'upload_date': '20150721',
749 'uploader': 'Beer Games Beer',
750 'uploader_id': 'beergamesbeer',
fd050249 751 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
7caf9830 752 'license': 'Standard YouTube License',
cf7e015f
S
753 },
754 }],
755 'params': {
756 'skip_download': True,
757 },
cbaed4bb 758 },
f9f49d87
S
759 {
760 # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
761 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
762 'info_dict': {
763 'id': 'gVfLd0zydlo',
764 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
765 },
766 'playlist_count': 2,
be49068d 767 'skip': 'Not multifeed anymore',
f9f49d87 768 },
cbaed4bb
S
769 {
770 'url': 'http://vid.plus/FlRa-iH7PGw',
771 'only_matching': True,
0e49d9a6 772 },
6d4fc66b
S
773 {
774 'url': 'http://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
775 'only_matching': True,
776 },
0e49d9a6 777 {
61f92af1 778 # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
a8776b10
S
779 # Also tests cut-off URL expansion in video description (see
780 # https://github.com/rg3/youtube-dl/issues/1892,
781 # https://github.com/rg3/youtube-dl/issues/8164)
0e49d9a6
LL
782 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
783 'info_dict': {
784 'id': 'lsguqyKfVQg',
785 'ext': 'mp4',
786 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
0cb58b02 787 'alt_title': 'Dark Walk',
0e49d9a6
LL
788 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
789 'upload_date': '20151119',
790 'uploader_id': 'IronSoulElf',
fd050249 791 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
0e49d9a6 792 'uploader': 'IronSoulElf',
7caf9830 793 'license': 'Standard YouTube License',
0cb58b02 794 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
0e49d9a6
LL
795 },
796 'params': {
797 'skip_download': True,
798 },
799 },
61f92af1
S
800 {
801 # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
802 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
803 'only_matching': True,
804 },
313dfc45
LL
805 {
806 # Video with yt:stretch=17:0
807 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
808 'info_dict': {
809 'id': 'Q39EVAstoRM',
810 'ext': 'mp4',
811 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
812 'description': 'md5:ee18a25c350637c8faff806845bddee9',
813 'upload_date': '20151107',
814 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
815 'uploader': 'CH GAMER DROID',
816 },
817 'params': {
818 'skip_download': True,
819 },
be49068d 820 'skip': 'This video does not exist.',
313dfc45 821 },
7caf9830
S
822 {
823 # Video licensed under Creative Commons
824 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
825 'info_dict': {
826 'id': 'M4gD1WSo5mA',
827 'ext': 'mp4',
828 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
829 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
830 'upload_date': '20150127',
831 'uploader_id': 'BerkmanCenter',
fd050249 832 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
7caf9830
S
833 'uploader': 'BerkmanCenter',
834 'license': 'Creative Commons Attribution license (reuse allowed)',
835 },
836 'params': {
837 'skip_download': True,
838 },
839 },
fd050249
S
840 {
841 # Channel-like uploader_url
842 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
843 'info_dict': {
844 'id': 'eQcmzGIKrzg',
845 'ext': 'mp4',
846 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
847 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
848 'upload_date': '20151119',
849 'uploader': 'Bernie 2016',
850 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
851 'uploader_url': 're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
852 'license': 'Creative Commons Attribution license (reuse allowed)',
853 },
854 'params': {
855 'skip_download': True,
856 },
857 },
040ac686
S
858 {
859 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;amp;v=V36LpHqtcDY',
860 'only_matching': True,
861 }
2eb88d95
PH
862 ]
863
e0df6211
PH
864 def __init__(self, *args, **kwargs):
865 super(YoutubeIE, self).__init__(*args, **kwargs)
83799698 866 self._player_cache = {}
e0df6211 867
c5e8d7af
PH
868 def report_video_info_webpage_download(self, video_id):
869 """Report attempt to download video info webpage."""
69ea8ca4 870 self.to_screen('%s: Downloading video info webpage' % video_id)
c5e8d7af 871
c5e8d7af
PH
872 def report_information_extraction(self, video_id):
873 """Report attempt to extract video information."""
69ea8ca4 874 self.to_screen('%s: Extracting video information' % video_id)
c5e8d7af
PH
875
876 def report_unavailable_format(self, video_id, format):
877 """Report extracted video URL."""
69ea8ca4 878 self.to_screen('%s: Format %s not available' % (video_id, format))
c5e8d7af
PH
879
880 def report_rtmp_download(self):
881 """Indicate the download will use the RTMP protocol."""
69ea8ca4 882 self.to_screen('RTMP download detected')
c5e8d7af 883
60064c53
PH
884 def _signature_cache_id(self, example_sig):
885 """ Return a string representation of a signature """
78caa52a 886 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
60064c53
PH
887
888 def _extract_signature_function(self, video_id, player_url, example_sig):
cf010131 889 id_m = re.match(
50f84a9a 890 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$',
cf010131 891 player_url)
c081b35c
PH
892 if not id_m:
893 raise ExtractorError('Cannot identify player %r' % player_url)
e0df6211
PH
894 player_type = id_m.group('ext')
895 player_id = id_m.group('id')
896
c4417ddb 897 # Read from filesystem cache
60064c53
PH
898 func_id = '%s_%s_%s' % (
899 player_type, player_id, self._signature_cache_id(example_sig))
c4417ddb 900 assert os.path.basename(func_id) == func_id
a0e07d31 901
69ea8ca4 902 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
a0e07d31 903 if cache_spec is not None:
78caa52a 904 return lambda s: ''.join(s[i] for i in cache_spec)
83799698 905
6d1a55a5
PH
906 download_note = (
907 'Downloading player %s' % player_url
908 if self._downloader.params.get('verbose') else
909 'Downloading %s player %s' % (player_type, player_id)
910 )
e0df6211
PH
911 if player_type == 'js':
912 code = self._download_webpage(
913 player_url, video_id,
6d1a55a5 914 note=download_note,
69ea8ca4 915 errnote='Download of %s failed' % player_url)
83799698 916 res = self._parse_sig_js(code)
c4417ddb 917 elif player_type == 'swf':
e0df6211
PH
918 urlh = self._request_webpage(
919 player_url, video_id,
6d1a55a5 920 note=download_note,
69ea8ca4 921 errnote='Download of %s failed' % player_url)
e0df6211 922 code = urlh.read()
83799698 923 res = self._parse_sig_swf(code)
e0df6211
PH
924 else:
925 assert False, 'Invalid player type %r' % player_type
926
785521bf
PH
927 test_string = ''.join(map(compat_chr, range(len(example_sig))))
928 cache_res = res(test_string)
929 cache_spec = [ord(c) for c in cache_res]
83799698 930
69ea8ca4 931 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
83799698
PH
932 return res
933
60064c53 934 def _print_sig_code(self, func, example_sig):
edf3e38e
PH
935 def gen_sig_code(idxs):
936 def _genslice(start, end, step):
78caa52a 937 starts = '' if start == 0 else str(start)
8bcc8756 938 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
69ea8ca4 939 steps = '' if step == 1 else (':%d' % step)
78caa52a 940 return 's[%s%s%s]' % (starts, ends, steps)
edf3e38e
PH
941
942 step = None
7af808a5
PH
943 # Quelch pyflakes warnings - start will be set when step is set
944 start = '(Never used)'
edf3e38e
PH
945 for i, prev in zip(idxs[1:], idxs[:-1]):
946 if step is not None:
947 if i - prev == step:
948 continue
949 yield _genslice(start, prev, step)
950 step = None
951 continue
952 if i - prev in [-1, 1]:
953 step = i - prev
954 start = prev
955 continue
956 else:
78caa52a 957 yield 's[%d]' % prev
edf3e38e 958 if step is None:
78caa52a 959 yield 's[%d]' % i
edf3e38e
PH
960 else:
961 yield _genslice(start, i, step)
962
78caa52a 963 test_string = ''.join(map(compat_chr, range(len(example_sig))))
c705320f 964 cache_res = func(test_string)
edf3e38e 965 cache_spec = [ord(c) for c in cache_res]
78caa52a 966 expr_code = ' + '.join(gen_sig_code(cache_spec))
60064c53
PH
967 signature_id_tuple = '(%s)' % (
968 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
69ea8ca4 969 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
78caa52a 970 ' return %s\n') % (signature_id_tuple, expr_code)
69ea8ca4 971 self.to_screen('Extracted signature function:\n' + code)
edf3e38e 972
e0df6211
PH
973 def _parse_sig_js(self, jscode):
974 funcname = self._search_regex(
aaeb86f6 975 r'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode,
8bcc8756 976 'Initial JS player signature function name')
2b25cb5d
PH
977
978 jsi = JSInterpreter(jscode)
979 initial_function = jsi.extract_function(funcname)
e0df6211
PH
980 return lambda s: initial_function([s])
981
982 def _parse_sig_swf(self, file_contents):
54256267 983 swfi = SWFInterpreter(file_contents)
78caa52a 984 TARGET_CLASSNAME = 'SignatureDecipher'
54256267 985 searched_class = swfi.extract_class(TARGET_CLASSNAME)
78caa52a 986 initial_function = swfi.extract_function(searched_class, 'decipher')
e0df6211
PH
987 return lambda s: initial_function([s])
988
83799698 989 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
257a2501 990 """Turn the encrypted s field into a working signature"""
6b37f0be 991
c8bf86d5 992 if player_url is None:
69ea8ca4 993 raise ExtractorError('Cannot decrypt signature without player_url')
920de7a2 994
69ea8ca4 995 if player_url.startswith('//'):
78caa52a 996 player_url = 'https:' + player_url
c8bf86d5 997 try:
62af3a0e 998 player_id = (player_url, self._signature_cache_id(s))
c8bf86d5
PH
999 if player_id not in self._player_cache:
1000 func = self._extract_signature_function(
60064c53 1001 video_id, player_url, s
c8bf86d5
PH
1002 )
1003 self._player_cache[player_id] = func
1004 func = self._player_cache[player_id]
1005 if self._downloader.params.get('youtube_print_sig_code'):
60064c53 1006 self._print_sig_code(func, s)
c8bf86d5
PH
1007 return func(s)
1008 except Exception as e:
1009 tb = traceback.format_exc()
1010 raise ExtractorError(
78caa52a 1011 'Signature extraction failed: ' + tb, cause=e)
e0df6211 1012
360e1ca5 1013 def _get_subtitles(self, video_id, webpage):
de7f3446 1014 try:
60e47a26 1015 subs_doc = self._download_xml(
38c2e5b8 1016 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
7fad1c63
JMF
1017 video_id, note=False)
1018 except ExtractorError as err:
9b9c5355 1019 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
de7f3446 1020 return {}
de7f3446
JMF
1021
1022 sub_lang_list = {}
60e47a26
JMF
1023 for track in subs_doc.findall('track'):
1024 lang = track.attrib['lang_code']
7e660ac1
LD
1025 if lang in sub_lang_list:
1026 continue
360e1ca5 1027 sub_formats = []
23d17e4b 1028 for ext in self._SUBTITLE_FORMATS:
15707c7e 1029 params = compat_urllib_parse_urlencode({
360e1ca5
JMF
1030 'lang': lang,
1031 'v': video_id,
1032 'fmt': ext,
1033 'name': track.attrib['name'].encode('utf-8'),
1034 })
1035 sub_formats.append({
1036 'url': 'https://www.youtube.com/api/timedtext?' + params,
1037 'ext': ext,
1038 })
1039 sub_lang_list[lang] = sub_formats
de7f3446 1040 if not sub_lang_list:
69ea8ca4 1041 self._downloader.report_warning('video doesn\'t have subtitles')
de7f3446
JMF
1042 return {}
1043 return sub_lang_list
1044
a72778d3
S
1045 def _get_ytplayer_config(self, video_id, webpage):
1046 patterns = (
526b3b07
S
1047 # User data may contain arbitrary character sequences that may affect
1048 # JSON extraction with regex, e.g. when '};' is contained the second
1049 # regex won't capture the whole JSON. Yet working around by trying more
1050 # concrete regex first keeping in mind proper quoted string handling
1051 # to be implemented in future that will replace this workaround (see
1052 # https://github.com/rg3/youtube-dl/issues/7468,
1053 # https://github.com/rg3/youtube-dl/pull/7599)
a72778d3
S
1054 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1055 r';ytplayer\.config\s*=\s*({.+?});',
1056 )
1057 config = self._search_regex(
1058 patterns, webpage, 'ytplayer.config', default=None)
1059 if config:
1060 return self._parse_json(
1061 uppercase_escape(config), video_id, fatal=False)
0e49d9a6 1062
360e1ca5 1063 def _get_automatic_captions(self, video_id, webpage):
de7f3446
JMF
1064 """We need the webpage for getting the captions url, pass it as an
1065 argument to speed up the process."""
69ea8ca4 1066 self.to_screen('%s: Looking for automatic captions' % video_id)
a72778d3 1067 player_config = self._get_ytplayer_config(video_id, webpage)
78caa52a 1068 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
a72778d3 1069 if not player_config:
de7f3446
JMF
1070 self._downloader.report_warning(err_msg)
1071 return {}
de7f3446 1072 try:
0792d563 1073 args = player_config['args']
b78b292f
S
1074 caption_url = args.get('ttsurl')
1075 if caption_url:
1076 timestamp = args['timestamp']
1077 # We get the available subtitles
15707c7e 1078 list_params = compat_urllib_parse_urlencode({
b78b292f
S
1079 'type': 'list',
1080 'tlangs': 1,
1081 'asrs': 1,
1082 })
1083 list_url = caption_url + '&' + list_params
1084 caption_list = self._download_xml(list_url, video_id)
1085 original_lang_node = caption_list.find('track')
1086 if original_lang_node is None:
1087 self._downloader.report_warning('Video doesn\'t have automatic captions')
1088 return {}
1089 original_lang = original_lang_node.attrib['lang_code']
1090 caption_kind = original_lang_node.attrib.get('kind', '')
1091
1092 sub_lang_list = {}
1093 for lang_node in caption_list.findall('target'):
1094 sub_lang = lang_node.attrib['lang_code']
1095 sub_formats = []
1096 for ext in self._SUBTITLE_FORMATS:
15707c7e 1097 params = compat_urllib_parse_urlencode({
b78b292f
S
1098 'lang': original_lang,
1099 'tlang': sub_lang,
1100 'fmt': ext,
1101 'ts': timestamp,
1102 'kind': caption_kind,
1103 })
1104 sub_formats.append({
1105 'url': caption_url + '&' + params,
1106 'ext': ext,
1107 })
1108 sub_lang_list[sub_lang] = sub_formats
1109 return sub_lang_list
1110
1111 # Some videos don't provide ttsurl but rather caption_tracks and
1112 # caption_translation_languages (e.g. 20LmZk1hakA)
1113 caption_tracks = args['caption_tracks']
1114 caption_translation_languages = args['caption_translation_languages']
1115 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
15707c7e 1116 parsed_caption_url = compat_urllib_parse_urlparse(caption_url)
b78b292f 1117 caption_qs = compat_parse_qs(parsed_caption_url.query)
055e6f36
JMF
1118
1119 sub_lang_list = {}
b78b292f
S
1120 for lang in caption_translation_languages.split(','):
1121 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1122 sub_lang = lang_qs.get('lc', [None])[0]
1123 if not sub_lang:
1124 continue
360e1ca5 1125 sub_formats = []
23d17e4b 1126 for ext in self._SUBTITLE_FORMATS:
b78b292f
S
1127 caption_qs.update({
1128 'tlang': [sub_lang],
1129 'fmt': [ext],
360e1ca5 1130 })
b78b292f 1131 sub_url = compat_urlparse.urlunparse(parsed_caption_url._replace(
15707c7e 1132 query=compat_urllib_parse_urlencode(caption_qs, True)))
360e1ca5 1133 sub_formats.append({
b78b292f 1134 'url': sub_url,
360e1ca5
JMF
1135 'ext': ext,
1136 })
1137 sub_lang_list[sub_lang] = sub_formats
055e6f36 1138 return sub_lang_list
de7f3446
JMF
1139 # An extractor error can be raise by the download process if there are
1140 # no automatic captions but there are subtitles
1141 except (KeyError, ExtractorError):
1142 self._downloader.report_warning(err_msg)
1143 return {}
1144
d77ab8e2
S
1145 def _mark_watched(self, video_id, video_info):
1146 playback_url = video_info.get('videostats_playback_base_url', [None])[0]
1147 if not playback_url:
1148 return
1149 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1150 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1151
1152 # cpn generation algorithm is reverse engineered from base.js.
1153 # In fact it works even with dummy cpn.
1154 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1155 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1156
1157 qs.update({
1158 'ver': ['2'],
1159 'cpn': [cpn],
1160 })
1161 playback_url = compat_urlparse.urlunparse(
15707c7e 1162 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
d77ab8e2
S
1163
1164 self._download_webpage(
1165 playback_url, video_id, 'Marking watched',
1166 'Unable to mark watched', fatal=False)
1167
97665381
PH
1168 @classmethod
1169 def extract_id(cls, url):
1170 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
c5e8d7af 1171 if mobj is None:
69ea8ca4 1172 raise ExtractorError('Invalid URL: %s' % url)
c5e8d7af
PH
1173 video_id = mobj.group(2)
1174 return video_id
1175
1d043b93
JMF
1176 def _extract_from_m3u8(self, manifest_url, video_id):
1177 url_map = {}
5f6a1245 1178
1d043b93
JMF
1179 def _get_urls(_manifest):
1180 lines = _manifest.split('\n')
1181 urls = filter(lambda l: l and not l.startswith('#'),
8bcc8756 1182 lines)
1d043b93 1183 return urls
78caa52a 1184 manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest')
1d043b93
JMF
1185 formats_urls = _get_urls(manifest)
1186 for format_url in formats_urls:
890f62e8 1187 itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag')
1d043b93
JMF
1188 url_map[itag] = format_url
1189 return url_map
1190
1fb07d10
JG
1191 def _extract_annotations(self, video_id):
1192 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
69ea8ca4 1193 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
1fb07d10 1194
c5e8d7af 1195 def _real_extract(self, url):
cf7e015f
S
1196 url, smuggled_data = unsmuggle_url(url, {})
1197
7e8c0af0 1198 proto = (
78caa52a
PH
1199 'http' if self._downloader.params.get('prefer_insecure', False)
1200 else 'https')
7e8c0af0 1201
7c80519c 1202 start_time = None
297a564b 1203 end_time = None
7c80519c
JMF
1204 parsed_url = compat_urllib_parse_urlparse(url)
1205 for component in [parsed_url.fragment, parsed_url.query]:
1206 query = compat_parse_qs(component)
297a564b 1207 if start_time is None and 't' in query:
7c80519c 1208 start_time = parse_duration(query['t'][0])
2929fa0e
JMF
1209 if start_time is None and 'start' in query:
1210 start_time = parse_duration(query['start'][0])
297a564b
JMF
1211 if end_time is None and 'end' in query:
1212 end_time = parse_duration(query['end'][0])
7c80519c 1213
c5e8d7af
PH
1214 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1215 mobj = re.search(self._NEXT_URL_RE, url)
1216 if mobj:
7fd002c0 1217 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
97665381 1218 video_id = self.extract_id(url)
c5e8d7af
PH
1219
1220 # Get video webpage
aa79ac0c 1221 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
a1f934b1 1222 video_webpage = self._download_webpage(url, video_id)
c5e8d7af
PH
1223
1224 # Attempt to extract SWF player URL
e0df6211 1225 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
c5e8d7af
PH
1226 if mobj is not None:
1227 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1228 else:
1229 player_url = None
1230
d8d24a92
S
1231 dash_mpds = []
1232
1233 def add_dash_mpd(video_info):
1234 dash_mpd = video_info.get('dashmpd')
1235 if dash_mpd and dash_mpd[0] not in dash_mpds:
1236 dash_mpds.append(dash_mpd[0])
1237
c5e8d7af 1238 # Get video info
6449cd80 1239 embed_webpage = None
2fe1ff85 1240 is_live = None
c108eb73 1241 if re.search(r'player-age-gate-content">', video_webpage) is not None:
c108eb73
JMF
1242 age_gate = True
1243 # We simulate the access to the video from www.youtube.com/v/{video_id}
1244 # this can be viewed without login into Youtube
beb95e77
CL
1245 url = proto + '://www.youtube.com/embed/%s' % video_id
1246 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
15707c7e 1247 data = compat_urllib_parse_urlencode({
2c57c7fa
JMF
1248 'video_id': video_id,
1249 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
c084c934 1250 'sts': self._search_regex(
beb95e77 1251 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
2c57c7fa 1252 })
7e8c0af0 1253 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
94bd3613
PH
1254 video_info_webpage = self._download_webpage(
1255 video_info_url, video_id,
20436c30 1256 note='Refetching age-gated info webpage',
94bd3613 1257 errnote='unable to download video info webpage')
c5e8d7af 1258 video_info = compat_parse_qs(video_info_webpage)
d8d24a92 1259 add_dash_mpd(video_info)
c108eb73
JMF
1260 else:
1261 age_gate = False
bc93bdb5 1262 video_info = None
d8d24a92 1263 # Try looking directly into the video webpage
a72778d3
S
1264 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1265 if ytplayer_config:
4e62ebe2 1266 args = ytplayer_config['args']
d8d24a92
S
1267 if args.get('url_encoded_fmt_stream_map'):
1268 # Convert to the same format returned by compat_parse_qs
1269 video_info = dict((k, [v]) for k, v in args.items())
1270 add_dash_mpd(video_info)
2fe1ff85
JMF
1271 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1272 is_live = True
0a3cf9ad
S
1273 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1274 # We also try looking in get_video_info since it may contain different dashmpd
1275 # URL that points to a DASH manifest with possibly different itag set (some itags
1276 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1277 # manifest pointed by get_video_info's dashmpd).
1278 # The general idea is to take a union of itags of both DASH manifests (for example
1279 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
4e62ebe2 1280 self.report_video_info_webpage_download(video_id)
0a3cf9ad 1281 for el_type in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
810fb84d
PH
1282 video_info_url = (
1283 '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
1284 % (proto, video_id, el_type))
1285 video_info_webpage = self._download_webpage(
1286 video_info_url,
4e62ebe2
JMF
1287 video_id, note=False,
1288 errnote='unable to download video info webpage')
0a3cf9ad 1289 get_video_info = compat_parse_qs(video_info_webpage)
87dc4511
JMF
1290 if get_video_info.get('use_cipher_signature') != ['True']:
1291 add_dash_mpd(get_video_info)
0a3cf9ad
S
1292 if not video_info:
1293 video_info = get_video_info
1294 if 'token' in get_video_info:
89ea063e
S
1295 # Different get_video_info requests may report different results, e.g.
1296 # some may report video unavailability, but some may serve it without
1297 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1298 # the original webpage as well as el=info and el=embedded get_video_info
1299 # requests report video unavailability due to geo restriction while
1300 # el=detailpage succeeds and returns valid data). This is probably
1301 # due to YouTube measures against IP ranges of hosting providers.
1302 # Working around by preferring the first succeeded video_info containing
1303 # the token if no such video_info yet was found.
44b2264f
S
1304 if 'token' not in video_info:
1305 video_info = get_video_info
4e62ebe2 1306 break
c5e8d7af
PH
1307 if 'token' not in video_info:
1308 if 'reason' in video_info:
af214c3a
YCH
1309 if 'The uploader has not made this video available in your country.' in video_info['reason']:
1310 regions_allowed = self._html_search_meta('regionsAllowed', video_webpage, default=None)
678e436f 1311 if regions_allowed:
af214c3a
YCH
1312 raise ExtractorError('YouTube said: This video is available in %s only' % (
1313 ', '.join(map(ISO3166Utils.short2full, regions_allowed.split(',')))),
1314 expected=True)
d11271dd 1315 raise ExtractorError(
78caa52a 1316 'YouTube said: %s' % video_info['reason'][0],
d11271dd 1317 expected=True, video_id=video_id)
c5e8d7af 1318 else:
d11271dd 1319 raise ExtractorError(
78caa52a 1320 '"token" parameter not in video info for unknown reason',
d11271dd 1321 video_id=video_id)
c5e8d7af 1322
cf7e015f
S
1323 # title
1324 if 'title' in video_info:
1325 video_title = video_info['title'][0]
1326 else:
1327 self._downloader.report_warning('Unable to extract video title')
1328 video_title = '_'
1329
1330 # description
1331 video_description = get_element_by_id("eow-description", video_webpage)
1332 if video_description:
1333 video_description = re.sub(r'''(?x)
1334 <a\s+
25cb7a0e 1335 (?:[a-zA-Z-]+="[^"]*"\s+)*?
23f13e97 1336 (?:title|href)="([^"]+)"\s+
25cb7a0e 1337 (?:[a-zA-Z-]+="[^"]*"\s+)*?
525cedb9 1338 class="[^"]*"[^>]*>
23f13e97 1339 [^<]+\.{3}\s*
cf7e015f
S
1340 </a>
1341 ''', r'\1', video_description)
1342 video_description = clean_html(video_description)
1343 else:
1344 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1345 if fd_mobj:
1346 video_description = unescapeHTML(fd_mobj.group(1))
1347 else:
1348 video_description = ''
1349
5e1eddb9
S
1350 if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False):
1351 if not self._downloader.params.get('noplaylist'):
1352 entries = []
1353 feed_ids = []
6863631c 1354 multifeed_metadata_list = video_info['multifeed_metadata_list'][0]
5e1eddb9 1355 for feed in multifeed_metadata_list.split(','):
6863631c
S
1356 # Unquote should take place before split on comma (,) since textual
1357 # fields may contain comma as well (see
1358 # https://github.com/rg3/youtube-dl/issues/8536)
1359 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
5e1eddb9
S
1360 entries.append({
1361 '_type': 'url_transparent',
1362 'ie_key': 'Youtube',
1363 'url': smuggle_url(
1364 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1365 {'force_singlefeed': True}),
1366 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1367 })
1368 feed_ids.append(feed_data['id'][0])
1369 self.to_screen(
1370 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1371 % (', '.join(feed_ids), video_id))
1372 return self.playlist_result(entries, video_id, video_title, video_description)
1373 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
cf7e015f 1374
1d699755
PH
1375 if 'view_count' in video_info:
1376 view_count = int(video_info['view_count'][0])
1377 else:
1378 view_count = None
1379
c5e8d7af
PH
1380 # Check for "rental" videos
1381 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
69ea8ca4 1382 raise ExtractorError('"rental" videos not supported')
c5e8d7af
PH
1383
1384 # Start extracting information
1385 self.report_information_extraction(video_id)
1386
1387 # uploader
1388 if 'author' not in video_info:
69ea8ca4 1389 raise ExtractorError('Unable to extract uploader name')
7fd002c0 1390 video_uploader = compat_urllib_parse_unquote_plus(video_info['author'][0])
c5e8d7af
PH
1391
1392 # uploader_id
1393 video_uploader_id = None
fd050249
S
1394 video_uploader_url = None
1395 mobj = re.search(
1396 r'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1397 video_webpage)
c5e8d7af 1398 if mobj is not None:
fd050249
S
1399 video_uploader_id = mobj.group('uploader_id')
1400 video_uploader_url = mobj.group('uploader_url')
c5e8d7af 1401 else:
69ea8ca4 1402 self._downloader.report_warning('unable to extract uploader nickname')
c5e8d7af 1403
c5e8d7af 1404 # thumbnail image
7763b04e
JMF
1405 # We try first to get a high quality image:
1406 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
1407 video_webpage, re.DOTALL)
1408 if m_thumb is not None:
1409 video_thumbnail = m_thumb.group(1)
1410 elif 'thumbnail_url' not in video_info:
69ea8ca4 1411 self._downloader.report_warning('unable to extract video thumbnail')
f490e77e 1412 video_thumbnail = None
c5e8d7af 1413 else: # don't panic if we can't find it
7fd002c0 1414 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
c5e8d7af
PH
1415
1416 # upload date
9d0b581f
S
1417 upload_date = self._html_search_meta(
1418 'datePublished', video_webpage, 'upload date', default=None)
1419 if not upload_date:
1420 upload_date = self._search_regex(
1421 [r'(?s)id="eow-date.*?>(.*?)</span>',
1422 r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
1423 video_webpage, 'upload date', default=None)
1424 if upload_date:
1425 upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
1426 upload_date = unified_strdate(upload_date)
c5e8d7af 1427
7caf9830
S
1428 video_license = self._html_search_regex(
1429 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
1430 video_webpage, 'license', default=None)
1431
0cb58b02
S
1432 m_music = re.search(
1433 r'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li',
1434 video_webpage)
1435 if m_music:
1436 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
1437 video_creator = clean_html(m_music.group('creator'))
1438 else:
1439 video_alt_title = video_creator = None
1440
55f7bd2d
PH
1441 m_cat_container = self._search_regex(
1442 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
624dcebf 1443 video_webpage, 'categories', default=None)
ec8deefc 1444 if m_cat_container:
ad3bc6ac 1445 category = self._html_search_regex(
01ed5c9b 1446 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
ad3bc6ac
PH
1447 default=None)
1448 video_categories = None if category is None else [category]
1449 else:
1450 video_categories = None
ec8deefc 1451
000b6b5a
S
1452 video_tags = [
1453 unescapeHTML(m.group('content'))
1454 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
1455
f30a38be 1456 def _extract_count(count_name):
c93d53f5
S
1457 return str_to_int(self._search_regex(
1458 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
1459 % re.escape(count_name),
1460 video_webpage, count_name, default=None))
1461
69ea8ca4
PH
1462 like_count = _extract_count('like')
1463 dislike_count = _extract_count('dislike')
336c3a69 1464
c5e8d7af 1465 # subtitles
d82134c3 1466 video_subtitles = self.extract_subtitles(video_id, video_webpage)
360e1ca5 1467 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
c5e8d7af
PH
1468
1469 if 'length_seconds' not in video_info:
69ea8ca4 1470 self._downloader.report_warning('unable to extract video duration')
b466b702 1471 video_duration = None
c5e8d7af 1472 else:
7fd002c0 1473 video_duration = int(compat_urllib_parse_unquote_plus(video_info['length_seconds'][0]))
c5e8d7af 1474
1fb07d10
JG
1475 # annotations
1476 video_annotations = None
1477 if self._downloader.params.get('writeannotations', False):
5f6a1245 1478 video_annotations = self._extract_annotations(video_id)
1fb07d10 1479
dd27fd17
PH
1480 def _map_to_format_list(urlmap):
1481 formats = []
1482 for itag, video_real_url in urlmap.items():
1483 dct = {
1484 'format_id': itag,
1485 'url': video_real_url,
1486 'player_url': player_url,
1487 }
0b65e5d4
PH
1488 if itag in self._formats:
1489 dct.update(self._formats[itag])
dd27fd17
PH
1490 formats.append(dct)
1491 return formats
1492
c5e8d7af
PH
1493 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1494 self.report_rtmp_download()
dd27fd17
PH
1495 formats = [{
1496 'format_id': '_rtmp',
1497 'protocol': 'rtmp',
1498 'url': video_info['conn'][0],
1499 'player_url': player_url,
1500 }]
24270b03 1501 elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1:
5f6a1245 1502 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
00fe14fc 1503 if 'rtmpe%3Dyes' in encoded_url_map:
a7055eb9 1504 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
3318832e 1505 formats_spec = {}
82156fdb 1506 fmt_list = video_info.get('fmt_list', [''])[0]
1507 if fmt_list:
1508 for fmt in fmt_list.split(','):
1509 spec = fmt.split('/')
3318832e 1510 if len(spec) > 1:
1511 width_height = spec[1].split('x')
1512 if len(width_height) == 2:
1513 formats_spec[spec[0]] = {
1514 'resolution': spec[1],
1515 'width': int_or_none(width_height[0]),
1516 'height': int_or_none(width_height[1]),
1517 }
c9afb51c 1518 formats = []
00fe14fc 1519 for url_data_str in encoded_url_map.split(','):
c5e8d7af 1520 url_data = compat_parse_qs(url_data_str)
201e9eaa
PH
1521 if 'itag' not in url_data or 'url' not in url_data:
1522 continue
1523 format_id = url_data['itag'][0]
1524 url = url_data['url'][0]
1525
1526 if 'sig' in url_data:
1527 url += '&signature=' + url_data['sig'][0]
1528 elif 's' in url_data:
1529 encrypted_sig = url_data['s'][0]
6449cd80 1530 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
201e9eaa 1531
beb95e77 1532 jsplayer_url_json = self._search_regex(
6449cd80
PH
1533 ASSETS_RE,
1534 embed_webpage if age_gate else video_webpage,
1535 'JS player URL (1)', default=None)
1536 if not jsplayer_url_json and not age_gate:
1537 # We need the embed website after all
1538 if embed_webpage is None:
1539 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1540 embed_webpage = self._download_webpage(
1541 embed_url, video_id, 'Downloading embed webpage')
1542 jsplayer_url_json = self._search_regex(
1543 ASSETS_RE, embed_webpage, 'JS player URL')
1544
beb95e77 1545 player_url = json.loads(jsplayer_url_json)
201e9eaa
PH
1546 if player_url is None:
1547 player_url_json = self._search_regex(
1548 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
78caa52a 1549 video_webpage, 'age gate player URL')
201e9eaa
PH
1550 player_url = json.loads(player_url_json)
1551
1552 if self._downloader.params.get('verbose'):
cf010131 1553 if player_url is None:
201e9eaa
PH
1554 player_version = 'unknown'
1555 player_desc = 'unknown'
1556 else:
1557 if player_url.endswith('swf'):
1558 player_version = self._search_regex(
1559 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
78caa52a 1560 'flash player', fatal=False)
201e9eaa 1561 player_desc = 'flash player %s' % player_version
cf010131 1562 else:
201e9eaa 1563 player_version = self._search_regex(
50f84a9a 1564 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r'(?:www|player)-([^/]+)/base\.js'],
201e9eaa
PH
1565 player_url,
1566 'html5 player', fatal=False)
78caa52a 1567 player_desc = 'html5 player %s' % player_version
201e9eaa 1568
60064c53 1569 parts_sizes = self._signature_cache_id(encrypted_sig)
69ea8ca4 1570 self.to_screen('{%s} signature length %s, %s' %
9e1a5b84 1571 (format_id, parts_sizes, player_desc))
201e9eaa
PH
1572
1573 signature = self._decrypt_signature(
1574 encrypted_sig, video_id, player_url, age_gate)
1575 url += '&signature=' + signature
1576 if 'ratebypass' not in url:
1577 url += '&ratebypass=yes'
c9afb51c 1578
94278f72
YCH
1579 dct = {
1580 'format_id': format_id,
1581 'url': url,
1582 'player_url': player_url,
1583 }
1584 if format_id in self._formats:
1585 dct.update(self._formats[format_id])
3318832e 1586 if format_id in formats_spec:
1587 dct.update(formats_spec[format_id])
94278f72 1588
aabc2be6
S
1589 # Some itags are not included in DASH manifest thus corresponding formats will
1590 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1591 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1592 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
1593 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
94278f72
YCH
1594
1595 more_fields = {
c9afb51c 1596 'filesize': int_or_none(url_data.get('clen', [None])[0]),
aabc2be6 1597 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
c9afb51c
AH
1598 'width': width,
1599 'height': height,
1600 'fps': int_or_none(url_data.get('fps', [None])[0]),
aabc2be6 1601 'format_note': url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0],
c9afb51c 1602 }
94278f72
YCH
1603 for key, value in more_fields.items():
1604 if value:
1605 dct[key] = value
aabc2be6
S
1606 type_ = url_data.get('type', [None])[0]
1607 if type_:
1608 type_split = type_.split(';')
1609 kind_ext = type_split[0].split('/')
1610 if len(kind_ext) == 2:
94278f72
YCH
1611 kind, _ = kind_ext
1612 dct['ext'] = mimetype2ext(type_split[0])
aabc2be6
S
1613 if kind in ('audio', 'video'):
1614 codecs = None
1615 for mobj in re.finditer(
1616 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
1617 if mobj.group('key') == 'codecs':
1618 codecs = mobj.group('val')
1619 break
1620 if codecs:
1621 codecs = codecs.split(',')
1622 if len(codecs) == 2:
cc28492d 1623 acodec, vcodec = codecs[1], codecs[0]
aabc2be6
S
1624 else:
1625 acodec, vcodec = (codecs[0], 'none') if kind == 'audio' else ('none', codecs[0])
1626 dct.update({
1627 'acodec': acodec,
1628 'vcodec': vcodec,
1629 })
aabc2be6 1630 formats.append(dct)
1d043b93
JMF
1631 elif video_info.get('hlsvp'):
1632 manifest_url = video_info['hlsvp'][0]
1633 url_map = self._extract_from_m3u8(manifest_url, video_id)
dd27fd17 1634 formats = _map_to_format_list(url_map)
ac5a69af
YCH
1635 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
1636 for a_format in formats:
049d71d8 1637 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
c5e8d7af 1638 else:
8ceabd4d
S
1639 unavailable_message = self._html_search_regex(
1640 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1641 video_webpage, 'unavailable message', default=None)
1642 if unavailable_message:
1643 raise ExtractorError(unavailable_message, expected=True)
69ea8ca4 1644 raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
c5e8d7af 1645
dd27fd17 1646 # Look for the DASH manifest
203fb43f 1647 if self._downloader.params.get('youtube_include_dash_manifest', True):
77c6fb5b 1648 dash_mpd_fatal = True
8ff648e4 1649 for mpd_url in dash_mpds:
d8d24a92 1650 dash_formats = {}
774e208f 1651 try:
05d0d131
YCH
1652 def decrypt_sig(mobj):
1653 s = mobj.group(1)
1654 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
1655 return '/signature/%s' % dec_s
1656
8ff648e4 1657 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2d2fa82d 1658
8ff648e4 1659 for df in self._extract_mpd_formats(
1660 mpd_url, video_id, fatal=dash_mpd_fatal,
1661 formats_dict=self._formats):
d8d24a92
S
1662 # Do not overwrite DASH format found in some previous DASH manifest
1663 if df['format_id'] not in dash_formats:
1664 dash_formats[df['format_id']] = df
77c6fb5b
S
1665 # Additional DASH manifests may end up in HTTP Error 403 therefore
1666 # allow them to fail without bug report message if we already have
1667 # some DASH manifest succeeded. This is temporary workaround to reduce
1668 # burst of bug reports until we figure out the reason and whether it
1669 # can be fixed at all.
1670 dash_mpd_fatal = False
774e208f
PH
1671 except (ExtractorError, KeyError) as e:
1672 self.report_warning(
1673 'Skipping DASH manifest: %r' % e, video_id)
d8d24a92 1674 if dash_formats:
04b3b3df
JMF
1675 # Remove the formats we found through non-DASH, they
1676 # contain less info and it can be wrong, because we use
1677 # fixed values (for example the resolution). See
1678 # https://github.com/rg3/youtube-dl/issues/5774 for an
1679 # example.
d80265cc 1680 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
d8d24a92 1681 formats.extend(dash_formats.values())
d80044c2 1682
6271f1ca
PH
1683 # Check for malformed aspect ratio
1684 stretched_m = re.search(
1685 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
1686 video_webpage)
1687 if stretched_m:
313dfc45
LL
1688 w = float(stretched_m.group('w'))
1689 h = float(stretched_m.group('h'))
5faf9fed
S
1690 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
1691 # We will only process correct ratios.
313dfc45 1692 if w > 0 and h > 0:
41f24c32 1693 ratio = w / h
313dfc45
LL
1694 for f in formats:
1695 if f.get('vcodec') != 'none':
1696 f['stretched_ratio'] = ratio
6271f1ca 1697
4bcc7bd1 1698 self._sort_formats(formats)
4ea3be0a 1699
d77ab8e2
S
1700 self.mark_watched(video_id, video_info)
1701
4ea3be0a 1702 return {
8bcc8756
JW
1703 'id': video_id,
1704 'uploader': video_uploader,
1705 'uploader_id': video_uploader_id,
fd050249 1706 'uploader_url': video_uploader_url,
8bcc8756 1707 'upload_date': upload_date,
7caf9830 1708 'license': video_license,
0cb58b02 1709 'creator': video_creator,
8bcc8756 1710 'title': video_title,
0cb58b02 1711 'alt_title': video_alt_title,
8bcc8756
JW
1712 'thumbnail': video_thumbnail,
1713 'description': video_description,
1714 'categories': video_categories,
000b6b5a 1715 'tags': video_tags,
8bcc8756 1716 'subtitles': video_subtitles,
360e1ca5 1717 'automatic_captions': automatic_captions,
8bcc8756
JW
1718 'duration': video_duration,
1719 'age_limit': 18 if age_gate else 0,
1720 'annotations': video_annotations,
7e8c0af0 1721 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
8bcc8756 1722 'view_count': view_count,
4ea3be0a 1723 'like_count': like_count,
1724 'dislike_count': dislike_count,
2d30521a 1725 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
8bcc8756 1726 'formats': formats,
2fe1ff85 1727 'is_live': is_live,
7c80519c 1728 'start_time': start_time,
297a564b 1729 'end_time': end_time,
4ea3be0a 1730 }
c5e8d7af 1731
5f6a1245 1732
40805306
YCH
1733class YoutubeSharedVideoIE(InfoExtractor):
1734 _VALID_URL = r'(?:https?:)?//(?:www\.)?youtube\.com/shared\?ci=(?P<id>[0-9A-Za-z_-]{11})'
1735 IE_NAME = 'youtube:shared'
1736
1737 _TEST = {
1738 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1739 'info_dict': {
1740 'id': 'uPDB5I9wfp8',
1741 'ext': 'webm',
1742 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1743 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1744 'upload_date': '20160219',
1745 'uploader': 'Pocoyo - Português (BR)',
1746 'uploader_id': 'PocoyoBrazil',
1747 },
1748 'add_ie': ['Youtube'],
1749 'params': {
1750 # There are already too many Youtube downloads
1751 'skip_download': True,
1752 },
1753 }
1754
1755 def _real_extract(self, url):
1756 video_id = self._match_id(url)
1757
1758 webpage = self._download_webpage(url, video_id)
1759
1760 real_video_id = self._html_search_meta(
1761 'videoId', webpage, 'YouTube video id', fatal=True)
1762
1763 return self.url_result(real_video_id, YoutubeIE.ie_key())
1764
1765
8e7aad20 1766class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
78caa52a 1767 IE_DESC = 'YouTube.com playlists'
d67cc9fa 1768 _VALID_URL = r"""(?x)(?:
c5e8d7af
PH
1769 (?:https?://)?
1770 (?:\w+\.)?
1771 youtube\.com/
1772 (?:
ac7553d0 1773 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
2e1b9285 1774 \? (?:.*?[&;])*? (?:p|a|list)=
c5e8d7af
PH
1775 | p/
1776 )
d67cc9fa 1777 (
99209c29 1778 (?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,}
5f6a1245 1779 # Top tracks, they can also include dots
d67cc9fa
JMF
1780 |(?:MC)[\w\.]*
1781 )
c5e8d7af
PH
1782 .*
1783 |
99209c29 1784 ((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,})
c5e8d7af 1785 )"""
dbb94fb0 1786 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
648e6a1f 1787 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
78caa52a 1788 IE_NAME = 'youtube:playlist'
81127aa5
PH
1789 _TESTS = [{
1790 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
1791 'info_dict': {
1792 'title': 'ytdl test PL',
a1cf99d0 1793 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
81127aa5
PH
1794 },
1795 'playlist_count': 3,
9291475f
PH
1796 }, {
1797 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
1798 'info_dict': {
acf757f4 1799 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
9291475f
PH
1800 'title': 'YDL_Empty_List',
1801 },
1802 'playlist_count': 0,
1803 }, {
1804 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
1805 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1806 'info_dict': {
1807 'title': '29C3: Not my department',
acf757f4 1808 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
9291475f
PH
1809 },
1810 'playlist_count': 95,
1811 }, {
1812 'note': 'issue #673',
1813 'url': 'PLBB231211A4F62143',
1814 'info_dict': {
f46a8702 1815 'title': '[OLD]Team Fortress 2 (Class-based LP)',
acf757f4 1816 'id': 'PLBB231211A4F62143',
9291475f
PH
1817 },
1818 'playlist_mincount': 26,
1819 }, {
1820 'note': 'Large playlist',
1821 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
1822 'info_dict': {
1823 'title': 'Uploads from Cauchemar',
acf757f4 1824 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
9291475f
PH
1825 },
1826 'playlist_mincount': 799,
1827 }, {
1828 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1829 'info_dict': {
1830 'title': 'YDL_safe_search',
acf757f4 1831 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
9291475f
PH
1832 },
1833 'playlist_count': 2,
ac7553d0
PH
1834 }, {
1835 'note': 'embedded',
1836 'url': 'http://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1837 'playlist_count': 4,
1838 'info_dict': {
1839 'title': 'JODA15',
acf757f4 1840 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
ac7553d0 1841 }
6b08cdf6
PH
1842 }, {
1843 'note': 'Embedded SWF player',
1844 'url': 'http://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
1845 'playlist_count': 4,
1846 'info_dict': {
1847 'title': 'JODA7',
acf757f4 1848 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
6b08cdf6 1849 }
4b7df0d3
JMF
1850 }, {
1851 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
1852 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
1853 'info_dict': {
acf757f4
PH
1854 'title': 'Uploads from Interstellar Movie',
1855 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4b7df0d3
JMF
1856 },
1857 'playlist_mincout': 21,
81127aa5 1858 }]
c5e8d7af 1859
880e1c52
JMF
1860 def _real_initialize(self):
1861 self._login()
1862
652cdaa2 1863 def _extract_mix(self, playlist_id):
99209c29 1864 # The mixes are generated from a single video
652cdaa2 1865 # the id of the playlist is just 'RD' + video_id
1b6182d8
JMF
1866 ids = []
1867 last_id = playlist_id[-11:]
1868 for n in itertools.count(1):
1869 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
1870 webpage = self._download_webpage(
1871 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
1872 new_ids = orderedSet(re.findall(
1873 r'''(?xs)data-video-username=".*?".*?
1874 href="/watch\?v=([0-9A-Za-z_-]{11})&amp;[^"]*?list=%s''' % re.escape(playlist_id),
1875 webpage))
1876 # Fetch new pages until all the videos are repeated, it seems that
1877 # there are always 51 unique videos.
1878 new_ids = [_id for _id in new_ids if _id not in ids]
1879 if not new_ids:
1880 break
1881 ids.extend(new_ids)
1882 last_id = ids[-1]
1883
1884 url_results = self._ids_to_results(ids)
1885
bc2f773b 1886 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
c9cc0bf5
PH
1887 title_span = (
1888 search_title('playlist-title') or
1889 search_title('title long-title') or
1890 search_title('title'))
76d1700b 1891 title = clean_html(title_span)
652cdaa2
JMF
1892
1893 return self.playlist_result(url_results, playlist_id, title)
1894
448830ce 1895 def _extract_playlist(self, playlist_id):
dbb94fb0
S
1896 url = self._TEMPLATE_URL % playlist_id
1897 page = self._download_webpage(url, playlist_id)
dbb94fb0 1898
39b62db1
YCH
1899 for match in re.findall(r'<div class="yt-alert-message">([^<]+)</div>', page):
1900 match = match.strip()
1901 # Check if the playlist exists or is private
1902 if re.match(r'[^<]*(The|This) playlist (does not exist|is private)[^<]*', match):
1903 raise ExtractorError(
1904 'The playlist doesn\'t exist or is private, use --username or '
1905 '--netrc to access it.',
1906 expected=True)
1907 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
1908 raise ExtractorError(
1909 'Invalid parameters. Maybe URL is incorrect.',
1910 expected=True)
1911 elif re.match(r'[^<]*Choose your language[^<]*', match):
1912 continue
1913 else:
1914 self.report_warning('Youtube gives an alert message: ' + match)
10c0e2d8 1915
dbb94fb0 1916 playlist_title = self._html_search_regex(
63b4295d 1917 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
78caa52a 1918 page, 'title')
c5e8d7af 1919
648e6a1f 1920 return self.playlist_result(self._entries(page, playlist_id), playlist_id, playlist_title)
c5e8d7af 1921
ebf1b291 1922 def _check_download_just_video(self, url, playlist_id):
448830ce
S
1923 # Check if it's a video-specific URL
1924 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
1925 if 'v' in query_dict:
1926 video_id = query_dict['v'][0]
1927 if self._downloader.params.get('noplaylist'):
1928 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1929 return self.url_result(video_id, 'Youtube', video_id=video_id)
1930 else:
1931 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
1932
ebf1b291
S
1933 def _real_extract(self, url):
1934 # Extract playlist id
1935 mobj = re.match(self._VALID_URL, url)
1936 if mobj is None:
1937 raise ExtractorError('Invalid URL: %s' % url)
1938 playlist_id = mobj.group(1) or mobj.group(2)
1939
1940 video = self._check_download_just_video(url, playlist_id)
1941 if video:
1942 return video
1943
466a6145 1944 if playlist_id.startswith(('RD', 'UL', 'PU')):
448830ce
S
1945 # Mixes require a custom extraction process
1946 return self._extract_mix(playlist_id)
1947
1948 return self._extract_playlist(playlist_id)
1949
c5e8d7af 1950
648e6a1f 1951class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
78caa52a 1952 IE_DESC = 'YouTube.com channels'
9ff67727 1953 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
eb0f3e7e 1954 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
648e6a1f 1955 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
78caa52a 1956 IE_NAME = 'youtube:channel'
cdc628a4
PH
1957 _TESTS = [{
1958 'note': 'paginated channel',
1959 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
1960 'playlist_mincount': 91,
acf757f4 1961 'info_dict': {
9170ca5b
JMF
1962 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
1963 'title': 'Uploads from lex will',
acf757f4 1964 }
5c43afd4
JMF
1965 }, {
1966 'note': 'Age restricted channel',
1967 # from https://www.youtube.com/user/DeusExOfficial
1968 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
1969 'playlist_mincount': 64,
1970 'info_dict': {
1971 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
1972 'title': 'Uploads from Deus Ex',
1973 },
cdc628a4 1974 }]
c5e8d7af 1975
e462474e
S
1976 @classmethod
1977 def suitable(cls, url):
f07e276a
S
1978 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
1979 else super(YoutubeChannelIE, cls).suitable(url))
e462474e 1980
c5e8d7af 1981 def _real_extract(self, url):
9ff67727 1982 channel_id = self._match_id(url)
c5e8d7af 1983
eb0f3e7e 1984 url = self._TEMPLATE_URL % channel_id
386bdfa6
S
1985
1986 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
1987 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
1988 # otherwise fallback on channel by page extraction
1989 channel_page = self._download_webpage(
1990 url + '?view=57', channel_id,
1991 'Downloading channel page', fatal=False)
2b3c2546
PH
1992 if channel_page is False:
1993 channel_playlist_id = False
1994 else:
1995 channel_playlist_id = self._html_search_meta(
1996 'channelId', channel_page, 'channel id', default=None)
1997 if not channel_playlist_id:
1998 channel_playlist_id = self._search_regex(
5c43afd4 1999 r'data-(?:channel-external-|yt)id="([^"]+)"',
2b3c2546 2000 channel_page, 'channel id', default=None)
386bdfa6
S
2001 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2002 playlist_id = 'UU' + channel_playlist_id[2:]
d2a9de78
IK
2003 return self.url_result(
2004 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
386bdfa6 2005
60bf45c8 2006 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
31812a9e
PH
2007 autogenerated = re.search(r'''(?x)
2008 class="[^"]*?(?:
2009 channel-header-autogenerated-label|
2010 yt-channel-title-autogenerated
2011 )[^"]*"''', channel_page) is not None
c5e8d7af 2012
b9643eed
JMF
2013 if autogenerated:
2014 # The videos are contained in a single page
2015 # the ajax pages can't be used, they are empty
b82f815f 2016 entries = [
fb69240c
S
2017 self.url_result(
2018 video_id, 'Youtube', video_id=video_id,
2019 video_title=video_title)
8f02ad4f 2020 for video_id, video_title in self.extract_videos_from_page(channel_page)]
b82f815f
PH
2021 return self.playlist_result(entries, channel_id)
2022
648e6a1f 2023 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
c5e8d7af
PH
2024
2025
eb0f3e7e 2026class YoutubeUserIE(YoutubeChannelIE):
78caa52a 2027 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
daa0df9e 2028 _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:user/|c/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
eb0f3e7e 2029 _TEMPLATE_URL = 'https://www.youtube.com/user/%s/videos'
78caa52a 2030 IE_NAME = 'youtube:user'
c5e8d7af 2031
cdc628a4
PH
2032 _TESTS = [{
2033 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2034 'playlist_mincount': 320,
2035 'info_dict': {
2036 'title': 'TheLinuxFoundation',
2037 }
2038 }, {
2039 'url': 'ytuser:phihag',
2040 'only_matching': True,
daa0df9e
YCH
2041 }, {
2042 'url': 'https://www.youtube.com/c/gametrailers',
2043 'only_matching': True,
cdc628a4
PH
2044 }]
2045
e3ea4790 2046 @classmethod
f4b05232 2047 def suitable(cls, url):
e3ea4790
JMF
2048 # Don't return True if the url can be extracted with other youtube
2049 # extractor, the regex would is too permissive and it would match.
f3a58d46 2050 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2051 if any(ie.suitable(url) for ie in other_yt_ies):
5f6a1245
JW
2052 return False
2053 else:
2054 return super(YoutubeUserIE, cls).suitable(url)
f4b05232 2055
b05654f0 2056
f07e276a
S
2057class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2058 IE_DESC = 'YouTube.com live streams'
2059 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+))/live'
2060 IE_NAME = 'youtube:live'
2061
2062 _TESTS = [{
2063 'url': 'http://www.youtube.com/user/TheYoungTurks/live',
2064 'info_dict': {
2065 'id': 'a48o2S1cPoo',
2066 'ext': 'mp4',
2067 'title': 'The Young Turks - Live Main Show',
2068 'uploader': 'The Young Turks',
2069 'uploader_id': 'TheYoungTurks',
2070 'uploader_url': 're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2071 'upload_date': '20150715',
2072 'license': 'Standard YouTube License',
2073 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2074 'categories': ['News & Politics'],
2075 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2076 'like_count': int,
2077 'dislike_count': int,
2078 },
2079 'params': {
2080 'skip_download': True,
2081 },
2082 }, {
2083 'url': 'http://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2084 'only_matching': True,
2085 }]
2086
2087 def _real_extract(self, url):
2088 mobj = re.match(self._VALID_URL, url)
2089 channel_id = mobj.group('id')
2090 base_url = mobj.group('base_url')
2091 webpage = self._download_webpage(url, channel_id, fatal=False)
2092 if webpage:
2093 page_type = self._og_search_property(
2094 'type', webpage, 'page type', default=None)
2095 video_id = self._html_search_meta(
2096 'videoId', webpage, 'video id', default=None)
2097 if page_type == 'video' and video_id and re.match(r'^[0-9A-Za-z_-]{11}$', video_id):
2098 return self.url_result(video_id, YoutubeIE.ie_key())
2099 return self.url_result(base_url)
2100
2101
e462474e
S
2102class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2103 IE_DESC = 'YouTube.com user/channel playlists'
2104 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2105 IE_NAME = 'youtube:playlists'
0c148415 2106
e568c223 2107 _TESTS = [{
0c148415
S
2108 'url': 'http://www.youtube.com/user/ThirstForScience/playlists',
2109 'playlist_mincount': 4,
2110 'info_dict': {
2111 'id': 'ThirstForScience',
2112 'title': 'Thirst for Science',
2113 },
e568c223
S
2114 }, {
2115 # with "Load more" button
2116 'url': 'http://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2117 'playlist_mincount': 70,
2118 'info_dict': {
2119 'id': 'igorkle1',
2120 'title': 'Игорь Клейнер',
2121 },
e462474e
S
2122 }, {
2123 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2124 'playlist_mincount': 17,
2125 'info_dict': {
2126 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2127 'title': 'Chem Player',
2128 },
e568c223 2129 }]
0c148415
S
2130
2131
b4c08069 2132class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
78caa52a 2133 IE_DESC = 'YouTube.com searches'
b4c08069
JMF
2134 # there doesn't appear to be a real limit, for example if you search for
2135 # 'python' you get more than 8.000.000 results
2136 _MAX_RESULTS = float('inf')
78caa52a 2137 IE_NAME = 'youtube:search'
b05654f0 2138 _SEARCH_KEY = 'ytsearch'
b4c08069 2139 _EXTRA_QUERY_ARGS = {}
9dd8e46a 2140 _TESTS = []
b05654f0 2141
b05654f0
PH
2142 def _get_n_results(self, query, n):
2143 """Get a specified number of results for a query"""
2144
b4c08069 2145 videos = []
b05654f0
PH
2146 limit = n
2147
b4c08069
JMF
2148 for pagenum in itertools.count(1):
2149 url_query = {
02175a79 2150 'search_query': query.encode('utf-8'),
b4c08069
JMF
2151 'page': pagenum,
2152 'spf': 'navigate',
2153 }
2154 url_query.update(self._EXTRA_QUERY_ARGS)
15707c7e 2155 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
b4c08069 2156 data = self._download_json(
69ea8ca4 2157 result_url, video_id='query "%s"' % query,
b4c08069 2158 note='Downloading page %s' % pagenum,
69ea8ca4 2159 errnote='Unable to download API page')
b4c08069 2160 html_content = data[1]['body']['content']
7cc3570e 2161
b4c08069 2162 if 'class="search-message' in html_content:
07ad22b8 2163 raise ExtractorError(
78caa52a 2164 '[youtube] No video results', expected=True)
b05654f0 2165
b4c08069
JMF
2166 new_videos = self._ids_to_results(orderedSet(re.findall(
2167 r'href="/watch\?v=(.{11})', html_content)))
2168 videos += new_videos
2169 if not new_videos or len(videos) > limit:
2170 break
b05654f0 2171
b4c08069
JMF
2172 if len(videos) > n:
2173 videos = videos[:n]
b05654f0 2174 return self.playlist_result(videos, query)
75dff0ee 2175
c9ae7b95 2176
a3dd9248 2177class YoutubeSearchDateIE(YoutubeSearchIE):
cb7fb546 2178 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
a3dd9248 2179 _SEARCH_KEY = 'ytsearchdate'
78caa52a 2180 IE_DESC = 'YouTube.com searches, newest videos first'
b4c08069 2181 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
75dff0ee 2182
c9ae7b95 2183
175c2e9e 2184class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor):
78caa52a
PH
2185 IE_DESC = 'YouTube.com search URLs'
2186 IE_NAME = 'youtube:search_url'
d2c1f79f 2187 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
175c2e9e 2188 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
cdc628a4
PH
2189 _TESTS = [{
2190 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2191 'playlist_mincount': 5,
2192 'info_dict': {
2193 'title': 'youtube-dl test video',
2194 }
d2c1f79f
S
2195 }, {
2196 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2197 'only_matching': True,
cdc628a4 2198 }]
c9ae7b95
PH
2199
2200 def _real_extract(self, url):
2201 mobj = re.match(self._VALID_URL, url)
7fd002c0 2202 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
c9ae7b95 2203 webpage = self._download_webpage(url, query)
175c2e9e 2204 return self.playlist_result(self._process_page(webpage), playlist_title=query)
c9ae7b95
PH
2205
2206
136dadde 2207class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
78caa52a 2208 IE_DESC = 'YouTube.com (multi-season) shows'
cdc628a4 2209 _VALID_URL = r'https?://www\.youtube\.com/show/(?P<id>[^?#]*)'
78caa52a 2210 IE_NAME = 'youtube:show'
cdc628a4 2211 _TESTS = [{
4003bd82 2212 'url': 'https://www.youtube.com/show/airdisasters',
8801255d 2213 'playlist_mincount': 5,
cdc628a4
PH
2214 'info_dict': {
2215 'id': 'airdisasters',
2216 'title': 'Air Disasters',
2217 }
2218 }]
75dff0ee
JMF
2219
2220 def _real_extract(self, url):
136dadde
S
2221 playlist_id = self._match_id(url)
2222 return super(YoutubeShowIE, self)._real_extract(
2223 'https://www.youtube.com/show/%s/playlists' % playlist_id)
04cc9617
JMF
2224
2225
b2e8bc1b 2226class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
d7ae0639 2227 """
25f14e9f 2228 Base class for feed extractors
d7ae0639
JMF
2229 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2230 """
b2e8bc1b 2231 _LOGIN_REQUIRED = True
d7ae0639
JMF
2232
2233 @property
2234 def IE_NAME(self):
78caa52a 2235 return 'youtube:%s' % self._FEED_NAME
04cc9617 2236
81f0259b 2237 def _real_initialize(self):
b2e8bc1b 2238 self._login()
81f0259b 2239
04cc9617 2240 def _real_extract(self, url):
25f14e9f
S
2241 page = self._download_webpage(
2242 'https://www.youtube.com/feed/%s' % self._FEED_NAME, self._PLAYLIST_TITLE)
2bc43303
JMF
2243
2244 # The extraction process is the same as for playlists, but the regex
2245 # for the video ids doesn't contain an index
2246 ids = []
2247 more_widget_html = content_html = page
2bc43303
JMF
2248 for page_num in itertools.count(1):
2249 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
62c95fd5
S
2250
2251 # 'recommended' feed has infinite 'load more' and each new portion spins
2252 # the same videos in (sometimes) slightly different order, so we'll check
2253 # for unicity and break when portion has no new videos
2254 new_ids = filter(lambda video_id: video_id not in ids, orderedSet(matches))
2255 if not new_ids:
2256 break
2257
2bc43303
JMF
2258 ids.extend(new_ids)
2259
2260 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
2261 if not mobj:
2262 break
2263
2264 more = self._download_json(
25f14e9f 2265 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
2bc43303
JMF
2266 'Downloading page #%s' % page_num,
2267 transform_source=uppercase_escape)
2268 content_html = more['content_html']
2269 more_widget_html = more['load_more_widget_html']
2270
25f14e9f
S
2271 return self.playlist_result(
2272 self._ids_to_results(ids), playlist_title=self._PLAYLIST_TITLE)
2273
2274
2275class YoutubeWatchLaterIE(YoutubePlaylistIE):
2276 IE_NAME = 'youtube:watchlater'
2277 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
bc7a9cd8 2278 _VALID_URL = r'https?://www\.youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
25f14e9f 2279
bc7a9cd8
S
2280 _TESTS = [{
2281 'url': 'https://www.youtube.com/playlist?list=WL',
2282 'only_matching': True,
2283 }, {
2284 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2285 'only_matching': True,
2286 }]
25f14e9f
S
2287
2288 def _real_extract(self, url):
ebf1b291
S
2289 video = self._check_download_just_video(url, 'WL')
2290 if video:
2291 return video
25f14e9f 2292 return self._extract_playlist('WL')
f459d170 2293
5f6a1245 2294
c626a3d9 2295class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
78caa52a 2296 IE_NAME = 'youtube:favorites'
f3a34072 2297 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
c7a7750d 2298 _VALID_URL = r'https?://www\.youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
c626a3d9
JMF
2299 _LOGIN_REQUIRED = True
2300
2301 def _real_extract(self, url):
2302 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
78caa52a 2303 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
c626a3d9 2304 return self.url_result(playlist_id, 'YoutubePlaylist')
15870e90
PH
2305
2306
25f14e9f
S
2307class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
2308 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
2309 _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?'
2310 _FEED_NAME = 'recommended'
2311 _PLAYLIST_TITLE = 'Youtube Recommended videos'
1ed5b5c9 2312
1ed5b5c9 2313
25f14e9f
S
2314class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
2315 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
2316 _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
2317 _FEED_NAME = 'subscriptions'
2318 _PLAYLIST_TITLE = 'Youtube Subscriptions'
1ed5b5c9 2319
1ed5b5c9 2320
25f14e9f
S
2321class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
2322 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
2323 _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory'
2324 _FEED_NAME = 'history'
2325 _PLAYLIST_TITLE = 'Youtube History'
1ed5b5c9
JMF
2326
2327
15870e90
PH
2328class YoutubeTruncatedURLIE(InfoExtractor):
2329 IE_NAME = 'youtube:truncated_url'
2330 IE_DESC = False # Do not list
975d35db 2331 _VALID_URL = r'''(?x)
b95aab84
PH
2332 (?:https?://)?
2333 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2334 (?:watch\?(?:
c4808c60 2335 feature=[a-z_]+|
b95aab84
PH
2336 annotation_id=annotation_[^&]+|
2337 x-yt-cl=[0-9]+|
c1708b89 2338 hl=[^&]*|
287be8c6 2339 t=[0-9]+
b95aab84
PH
2340 )?
2341 |
2342 attribution_link\?a=[^&]+
2343 )
2344 $
975d35db 2345 '''
15870e90 2346
c4808c60
PH
2347 _TESTS = [{
2348 'url': 'http://www.youtube.com/watch?annotation_id=annotation_3951667041',
2349 'only_matching': True,
dc2fc736
PH
2350 }, {
2351 'url': 'http://www.youtube.com/watch?',
2352 'only_matching': True,
b95aab84
PH
2353 }, {
2354 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2355 'only_matching': True,
2356 }, {
2357 'url': 'https://www.youtube.com/watch?feature=foo',
2358 'only_matching': True,
c1708b89
PH
2359 }, {
2360 'url': 'https://www.youtube.com/watch?hl=en-GB',
2361 'only_matching': True,
287be8c6
PH
2362 }, {
2363 'url': 'https://www.youtube.com/watch?t=2372',
2364 'only_matching': True,
c4808c60
PH
2365 }]
2366
15870e90
PH
2367 def _real_extract(self, url):
2368 raise ExtractorError(
78caa52a
PH
2369 'Did you forget to quote the URL? Remember that & is a meta '
2370 'character in most shells, so you want to put the URL in quotes, '
2371 'like youtube-dl '
2372 '"http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
2373 ' or simply youtube-dl BaW_jenozKc .',
15870e90 2374 expected=True)
772fd5cc
PH
2375
2376
2377class YoutubeTruncatedIDIE(InfoExtractor):
2378 IE_NAME = 'youtube:truncated_id'
2379 IE_DESC = False # Do not list
b95aab84 2380 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
772fd5cc
PH
2381
2382 _TESTS = [{
2383 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2384 'only_matching': True,
2385 }]
2386
2387 def _real_extract(self, url):
2388 video_id = self._match_id(url)
2389 raise ExtractorError(
2390 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
2391 expected=True)