]>
Commit | Line | Data |
---|---|---|
c5e8d7af | 1 | # coding: utf-8 |
c5e8d7af | 2 | |
78caa52a PH |
3 | from __future__ import unicode_literals |
4 | ||
5 | ||
0ca96d48 | 6 | import itertools |
c5e8d7af | 7 | import json |
c4417ddb | 8 | import os.path |
c5e8d7af | 9 | import re |
42939b61 | 10 | import time |
e0df6211 | 11 | import traceback |
c5e8d7af | 12 | |
b05654f0 | 13 | from .common import InfoExtractor, SearchInfoExtractor |
2b25cb5d | 14 | from ..jsinterp import JSInterpreter |
54256267 | 15 | from ..swfinterp import SWFInterpreter |
4bb4a188 | 16 | from ..compat import ( |
edf3e38e | 17 | compat_chr, |
c5e8d7af | 18 | compat_parse_qs, |
c5e8d7af PH |
19 | compat_urllib_parse, |
20 | compat_urllib_request, | |
7c61bd36 | 21 | compat_urlparse, |
c5e8d7af | 22 | compat_str, |
4bb4a188 PH |
23 | ) |
24 | from ..utils import ( | |
c5e8d7af | 25 | clean_html, |
c5e8d7af | 26 | ExtractorError, |
2d30521a | 27 | float_or_none, |
4bb4a188 PH |
28 | get_element_by_attribute, |
29 | get_element_by_id, | |
dd27fd17 | 30 | int_or_none, |
4bb4a188 | 31 | orderedSet, |
c5e8d7af PH |
32 | unescapeHTML, |
33 | unified_strdate, | |
81c2f20b | 34 | uppercase_escape, |
c5e8d7af PH |
35 | ) |
36 | ||
5f6a1245 | 37 | |
de7f3446 | 38 | class YoutubeBaseInfoExtractor(InfoExtractor): |
b2e8bc1b JMF |
39 | """Provide base functions for Youtube extractors""" |
40 | _LOGIN_URL = 'https://accounts.google.com/ServiceLogin' | |
83317f69 | 41 | _TWOFACTOR_URL = 'https://accounts.google.com/SecondFactor' |
b2e8bc1b JMF |
42 | _NETRC_MACHINE = 'youtube' |
43 | # If True it will raise an error if no login info is provided | |
44 | _LOGIN_REQUIRED = False | |
45 | ||
b2e8bc1b | 46 | def _set_language(self): |
810fb84d PH |
47 | self._set_cookie( |
48 | '.youtube.com', 'PREF', 'f1=50000000&hl=en', | |
42939b61 | 49 | # YouTube sets the expire time to about two months |
810fb84d | 50 | expire_time=time.time() + 2 * 30 * 24 * 3600) |
b2e8bc1b | 51 | |
25f14e9f S |
52 | def _ids_to_results(self, ids): |
53 | return [ | |
54 | self.url_result(vid_id, 'Youtube', video_id=vid_id) | |
55 | for vid_id in ids] | |
56 | ||
b2e8bc1b | 57 | def _login(self): |
83317f69 | 58 | """ |
59 | Attempt to log in to YouTube. | |
60 | True is returned if successful or skipped. | |
61 | False is returned if login failed. | |
62 | ||
63 | If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. | |
64 | """ | |
b2e8bc1b JMF |
65 | (username, password) = self._get_login_info() |
66 | # No authentication to be performed | |
67 | if username is None: | |
68 | if self._LOGIN_REQUIRED: | |
69ea8ca4 | 69 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
83317f69 | 70 | return True |
b2e8bc1b | 71 | |
7cc3570e PH |
72 | login_page = self._download_webpage( |
73 | self._LOGIN_URL, None, | |
69ea8ca4 PH |
74 | note='Downloading login page', |
75 | errnote='unable to fetch login page', fatal=False) | |
7cc3570e PH |
76 | if login_page is False: |
77 | return | |
b2e8bc1b | 78 | |
795f28f8 | 79 | galx = self._search_regex(r'(?s)<input.+?name="GALX".+?value="(.+?)"', |
78caa52a | 80 | login_page, 'Login GALX parameter') |
c5e8d7af | 81 | |
b2e8bc1b JMF |
82 | # Log in |
83 | login_form_strs = { | |
8bcc8756 JW |
84 | 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', |
85 | 'Email': username, | |
86 | 'GALX': galx, | |
87 | 'Passwd': password, | |
88 | ||
89 | 'PersistentCookie': 'yes', | |
90 | '_utf8': '霱', | |
91 | 'bgresponse': 'js_disabled', | |
92 | 'checkConnection': '', | |
93 | 'checkedDomains': 'youtube', | |
94 | 'dnConn': '', | |
95 | 'pstMsg': '0', | |
96 | 'rmShown': '1', | |
97 | 'secTok': '', | |
98 | 'signIn': 'Sign in', | |
99 | 'timeStmp': '', | |
100 | 'service': 'youtube', | |
101 | 'uilel': '3', | |
102 | 'hl': 'en_US', | |
b2e8bc1b | 103 | } |
83317f69 | 104 | |
b2e8bc1b JMF |
105 | # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode |
106 | # chokes on unicode | |
5f6a1245 | 107 | login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items()) |
b2e8bc1b | 108 | login_data = compat_urllib_parse.urlencode(login_form).encode('ascii') |
7cc3570e PH |
109 | |
110 | req = compat_urllib_request.Request(self._LOGIN_URL, login_data) | |
111 | login_results = self._download_webpage( | |
112 | req, None, | |
69ea8ca4 | 113 | note='Logging in', errnote='unable to log in', fatal=False) |
7cc3570e PH |
114 | if login_results is False: |
115 | return False | |
83317f69 | 116 | |
117 | if re.search(r'id="errormsg_0_Passwd"', login_results) is not None: | |
69ea8ca4 | 118 | raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True) |
83317f69 | 119 | |
120 | # Two-Factor | |
121 | # TODO add SMS and phone call support - these require making a request and then prompting the user | |
122 | ||
123 | if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', login_results) is not None: | |
124 | tfa_code = self._get_tfa_info() | |
125 | ||
126 | if tfa_code is None: | |
69ea8ca4 PH |
127 | self._downloader.report_warning('Two-factor authentication required. Provide it with --twofactor <code>') |
128 | self._downloader.report_warning('(Note that only TOTP (Google Authenticator App) codes work at this time.)') | |
83317f69 | 129 | return False |
130 | ||
131 | # Unlike the first login form, secTok and timeStmp are both required for the TFA form | |
132 | ||
133 | match = re.search(r'id="secTok"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) | |
134 | if match is None: | |
69ea8ca4 | 135 | self._downloader.report_warning('Failed to get secTok - did the page structure change?') |
83317f69 | 136 | secTok = match.group(1) |
137 | match = re.search(r'id="timeStmp"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) | |
138 | if match is None: | |
69ea8ca4 | 139 | self._downloader.report_warning('Failed to get timeStmp - did the page structure change?') |
83317f69 | 140 | timeStmp = match.group(1) |
141 | ||
142 | tfa_form_strs = { | |
78caa52a PH |
143 | 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', |
144 | 'smsToken': '', | |
145 | 'smsUserPin': tfa_code, | |
146 | 'smsVerifyPin': 'Verify', | |
147 | ||
148 | 'PersistentCookie': 'yes', | |
149 | 'checkConnection': '', | |
150 | 'checkedDomains': 'youtube', | |
151 | 'pstMsg': '1', | |
152 | 'secTok': secTok, | |
153 | 'timeStmp': timeStmp, | |
154 | 'service': 'youtube', | |
155 | 'hl': 'en_US', | |
83317f69 | 156 | } |
5f6a1245 | 157 | tfa_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in tfa_form_strs.items()) |
83317f69 | 158 | tfa_data = compat_urllib_parse.urlencode(tfa_form).encode('ascii') |
159 | ||
160 | tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data) | |
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 | ||
168 | if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', tfa_results) is not None: | |
69ea8ca4 | 169 | self._downloader.report_warning('Two-factor code expired. 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 | |
360e1ca5 | 191 | class YoutubeIE(YoutubeBaseInfoExtractor): |
78caa52a | 192 | IE_DESC = 'YouTube.com' |
cb7dfeea | 193 | _VALID_URL = r"""(?x)^ |
c5e8d7af | 194 | ( |
edb53e2d | 195 | (?:https?://|//) # http(s):// or protocol-independent URL |
cb7dfeea | 196 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/| |
484aaeb2 | 197 | (?:www\.)?deturl\.com/www\.youtube\.com/| |
e70dc1d1 | 198 | (?:www\.)?pwnyoutube\.com/| |
f7000f3a | 199 | (?:www\.)?yourepeat\.com/| |
e69ae5b9 JMF |
200 | tube\.majestyc\.net/| |
201 | youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains | |
c5e8d7af PH |
202 | (?:.*?\#/)? # handle anchor (#/) redirect urls |
203 | (?: # the various things that can precede the ID: | |
ac7553d0 | 204 | (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/ |
c5e8d7af | 205 | |(?: # or the v= param in all its forms |
f7000f3a | 206 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) |
c5e8d7af PH |
207 | (?:\?|\#!?) # the params delimiter ? or # or #! |
208 | (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx) | |
209 | v= | |
210 | ) | |
f4b05232 JMF |
211 | )) |
212 | |youtu\.be/ # just youtu.be/xxxx | |
edb53e2d | 213 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= |
f4b05232 | 214 | ) |
c5e8d7af | 215 | )? # all until now is optional -> you can pass the naked ID |
8963d9c2 | 216 | ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID |
9291475f | 217 | (?!.*?&list=) # combined list/video URLs are handled by the playlist IE |
c5e8d7af PH |
218 | (?(1).+)? # if we found the ID, everything can follow |
219 | $""" | |
c5e8d7af | 220 | _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' |
2c62dc26 PH |
221 | _formats = { |
222 | '5': {'ext': 'flv', 'width': 400, 'height': 240}, | |
223 | '6': {'ext': 'flv', 'width': 450, 'height': 270}, | |
224 | '13': {'ext': '3gp'}, | |
225 | '17': {'ext': '3gp', 'width': 176, 'height': 144}, | |
226 | '18': {'ext': 'mp4', 'width': 640, 'height': 360}, | |
227 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720}, | |
228 | '34': {'ext': 'flv', 'width': 640, 'height': 360}, | |
229 | '35': {'ext': 'flv', 'width': 854, 'height': 480}, | |
230 | '36': {'ext': '3gp', 'width': 320, 'height': 240}, | |
231 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080}, | |
232 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072}, | |
233 | '43': {'ext': 'webm', 'width': 640, 'height': 360}, | |
234 | '44': {'ext': 'webm', 'width': 854, 'height': 480}, | |
235 | '45': {'ext': 'webm', 'width': 1280, 'height': 720}, | |
236 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080}, | |
c9bebed2 S |
237 | '59': {'ext': 'mp4', 'width': 854, 'height': 480}, |
238 | '78': {'ext': 'mp4', 'width': 854, 'height': 480}, | |
2c62dc26 | 239 | |
1d043b93 | 240 | |
86fe61c8 | 241 | # 3d videos |
43b81eb9 PH |
242 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'preference': -20}, |
243 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'preference': -20}, | |
244 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'preference': -20}, | |
245 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'preference': -20}, | |
246 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'preference': -20}, | |
247 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'preference': -20}, | |
248 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'preference': -20}, | |
836a086c | 249 | |
96fb5605 | 250 | # Apple HTTP Live Streaming |
43b81eb9 PH |
251 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'preference': -10}, |
252 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'preference': -10}, | |
253 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'preference': -10}, | |
254 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'preference': -10}, | |
255 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'preference': -10}, | |
256 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'preference': -10}, | |
257 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'preference': -10}, | |
2c62dc26 PH |
258 | |
259 | # DASH mp4 video | |
43b81eb9 PH |
260 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
261 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
262 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
263 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
264 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
e65566a9 | 265 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559) |
43b81eb9 PH |
266 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
267 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
0d2c1418 PH |
268 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'}, |
269 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'}, | |
270 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'h264'}, | |
836a086c | 271 | |
f6f1fc92 | 272 | # Dash mp4 audio |
62cd676c PH |
273 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'}, |
274 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'}, | |
275 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'}, | |
836a086c AZ |
276 | |
277 | # Dash webm | |
e75cafe9 A |
278 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, |
279 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
280 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
281 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
282 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
283 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
1cc887cb | 284 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'container': 'webm', 'vcodec': 'VP9'}, |
e75cafe9 A |
285 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
286 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
287 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
288 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
289 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
290 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
291 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
3c80377b | 292 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
18061bba | 293 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
a51d3aa0 PH |
294 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, |
295 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, | |
76b3c610 | 296 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, |
10a404c3 | 297 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'VP9'}, |
76b3c610 | 298 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, |
2c62dc26 PH |
299 | |
300 | # Dash webm audio | |
55db73ef | 301 | '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50}, |
e75cafe9 | 302 | '172': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50}, |
ce6b9a2d | 303 | |
0857baad PH |
304 | # Dash webm audio with opus inside |
305 | '249': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50}, | |
306 | '250': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50}, | |
307 | '251': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50}, | |
308 | ||
ce6b9a2d PH |
309 | # RTMP (unnamed) |
310 | '_rtmp': {'protocol': 'rtmp'}, | |
c5e8d7af | 311 | } |
836a086c | 312 | |
78caa52a | 313 | IE_NAME = 'youtube' |
2eb88d95 PH |
314 | _TESTS = [ |
315 | { | |
4bc3a23e PH |
316 | 'url': 'http://www.youtube.com/watch?v=BaW_jenozKc', |
317 | 'info_dict': { | |
318 | 'id': 'BaW_jenozKc', | |
319 | 'ext': 'mp4', | |
320 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
321 | 'uploader': 'Philipp Hagemeister', | |
322 | 'uploader_id': 'phihag', | |
323 | 'upload_date': '20121002', | |
324 | '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 .', | |
325 | 'categories': ['Science & Technology'], | |
3e7c1224 PH |
326 | 'like_count': int, |
327 | 'dislike_count': int, | |
2eb88d95 | 328 | } |
0e853ca4 | 329 | }, |
0e853ca4 | 330 | { |
4bc3a23e PH |
331 | 'url': 'http://www.youtube.com/watch?v=UxxajLWwzqY', |
332 | 'note': 'Test generic use_cipher_signature video (#897)', | |
333 | 'info_dict': { | |
334 | 'id': 'UxxajLWwzqY', | |
335 | 'ext': 'mp4', | |
336 | 'upload_date': '20120506', | |
337 | 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', | |
338 | 'description': 'md5:fea86fda2d5a5784273df5c7cc994d9f', | |
339 | 'uploader': 'Icona Pop', | |
340 | 'uploader_id': 'IconaPop', | |
2eb88d95 | 341 | } |
c108eb73 JMF |
342 | }, |
343 | { | |
4bc3a23e PH |
344 | 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ', |
345 | 'note': 'Test VEVO video with age protection (#956)', | |
346 | 'info_dict': { | |
347 | 'id': '07FYdnEawAQ', | |
348 | 'ext': 'mp4', | |
349 | 'upload_date': '20130703', | |
350 | 'title': 'Justin Timberlake - Tunnel Vision (Explicit)', | |
351 | 'description': 'md5:64249768eec3bc4276236606ea996373', | |
352 | 'uploader': 'justintimberlakeVEVO', | |
353 | 'uploader_id': 'justintimberlakeVEVO', | |
c108eb73 JMF |
354 | } |
355 | }, | |
fccd3771 | 356 | { |
4bc3a23e PH |
357 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', |
358 | 'note': 'Embed-only video (#1746)', | |
359 | 'info_dict': { | |
360 | 'id': 'yZIXLfi8CZQ', | |
361 | 'ext': 'mp4', | |
362 | 'upload_date': '20120608', | |
363 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
364 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
365 | 'uploader': 'SET India', | |
366 | 'uploader_id': 'setindia' | |
fccd3771 PH |
367 | } |
368 | }, | |
dd27fd17 | 369 | { |
4bc3a23e PH |
370 | 'url': 'http://www.youtube.com/watch?v=a9LDPn-MO4I', |
371 | 'note': '256k DASH audio (format 141) via DASH manifest', | |
372 | 'info_dict': { | |
373 | 'id': 'a9LDPn-MO4I', | |
374 | 'ext': 'm4a', | |
375 | 'upload_date': '20121002', | |
376 | 'uploader_id': '8KVIDEO', | |
377 | 'description': '', | |
378 | 'uploader': '8KVIDEO', | |
379 | 'title': 'UHDTV TEST 8K VIDEO.mp4' | |
4919603f | 380 | }, |
4bc3a23e PH |
381 | 'params': { |
382 | 'youtube_include_dash_manifest': True, | |
383 | 'format': '141', | |
4919603f | 384 | }, |
dd27fd17 | 385 | }, |
3489b7d2 JMF |
386 | # DASH manifest with encrypted signature |
387 | { | |
78caa52a PH |
388 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', |
389 | 'info_dict': { | |
390 | 'id': 'IB3lcPjvWLA', | |
391 | 'ext': 'm4a', | |
b766eb27 JMF |
392 | 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson', |
393 | 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d', | |
78caa52a PH |
394 | 'uploader': 'AfrojackVEVO', |
395 | 'uploader_id': 'AfrojackVEVO', | |
396 | 'upload_date': '20131011', | |
3489b7d2 | 397 | }, |
4bc3a23e | 398 | 'params': { |
78caa52a PH |
399 | 'youtube_include_dash_manifest': True, |
400 | 'format': '141', | |
3489b7d2 JMF |
401 | }, |
402 | }, | |
aaeb86f6 S |
403 | # JS player signature function name containing $ |
404 | { | |
405 | 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM', | |
406 | 'info_dict': { | |
407 | 'id': 'nfWlot6h_JM', | |
408 | 'ext': 'm4a', | |
409 | 'title': 'Taylor Swift - Shake It Off', | |
410 | 'description': 'md5:2acfda1b285bdd478ccec22f9918199d', | |
411 | 'uploader': 'TaylorSwiftVEVO', | |
412 | 'uploader_id': 'TaylorSwiftVEVO', | |
413 | 'upload_date': '20140818', | |
414 | }, | |
415 | 'params': { | |
416 | 'youtube_include_dash_manifest': True, | |
417 | 'format': '141', | |
418 | }, | |
419 | }, | |
aa79ac0c PH |
420 | # Controversy video |
421 | { | |
422 | 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8', | |
423 | 'info_dict': { | |
424 | 'id': 'T4XJQO3qol8', | |
425 | 'ext': 'mp4', | |
426 | 'upload_date': '20100909', | |
427 | 'uploader': 'The Amazing Atheist', | |
428 | 'uploader_id': 'TheAmazingAtheist', | |
429 | 'title': 'Burning Everyone\'s Koran', | |
430 | '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', | |
431 | } | |
c522adb1 JMF |
432 | }, |
433 | # Normal age-gate video (No vevo, embed allowed) | |
434 | { | |
435 | 'url': 'http://youtube.com/watch?v=HtVdAasjOgU', | |
436 | 'info_dict': { | |
437 | 'id': 'HtVdAasjOgU', | |
438 | 'ext': 'mp4', | |
439 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
9ed99402 | 440 | 'description': 're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', |
c522adb1 JMF |
441 | 'uploader': 'The Witcher', |
442 | 'uploader_id': 'WitcherGame', | |
443 | 'upload_date': '20140605', | |
444 | }, | |
445 | }, | |
fccae2b9 S |
446 | # Age-gate video with encrypted signature |
447 | { | |
448 | 'url': 'http://www.youtube.com/watch?v=6kLq3WMV1nU', | |
449 | 'info_dict': { | |
450 | 'id': '6kLq3WMV1nU', | |
451 | 'ext': 'mp4', | |
452 | 'title': 'Dedication To My Ex (Miss That) (Lyric Video)', | |
453 | 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', | |
454 | 'uploader': 'LloydVEVO', | |
455 | 'uploader_id': 'LloydVEVO', | |
456 | 'upload_date': '20110629', | |
457 | }, | |
458 | }, | |
774e208f PH |
459 | # video_info is None (https://github.com/rg3/youtube-dl/issues/4421) |
460 | { | |
461 | 'url': '__2ABJjxzNo', | |
462 | 'info_dict': { | |
463 | 'id': '__2ABJjxzNo', | |
464 | 'ext': 'mp4', | |
465 | 'upload_date': '20100430', | |
466 | 'uploader_id': 'deadmau5', | |
467 | 'description': 'md5:12c56784b8032162bb936a5f76d55360', | |
468 | 'uploader': 'deadmau5', | |
469 | 'title': 'Deadmau5 - Some Chords (HD)', | |
470 | }, | |
471 | 'expected_warnings': [ | |
472 | 'DASH manifest missing', | |
473 | ] | |
e52a40ab PH |
474 | }, |
475 | # Olympics (https://github.com/rg3/youtube-dl/issues/4431) | |
476 | { | |
477 | 'url': 'lqQg6PlCWgI', | |
478 | 'info_dict': { | |
479 | 'id': 'lqQg6PlCWgI', | |
480 | 'ext': 'mp4', | |
cbe2bd91 PH |
481 | 'upload_date': '20120731', |
482 | 'uploader_id': 'olympic', | |
483 | 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', | |
484 | 'uploader': 'Olympics', | |
485 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', | |
486 | }, | |
487 | 'params': { | |
488 | 'skip_download': 'requires avconv', | |
e52a40ab | 489 | } |
cbe2bd91 | 490 | }, |
6271f1ca PH |
491 | # Non-square pixels |
492 | { | |
493 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
494 | 'info_dict': { | |
495 | 'id': '_b-2C3KPAM0', | |
496 | 'ext': 'mp4', | |
497 | 'stretched_ratio': 16 / 9., | |
498 | 'upload_date': '20110310', | |
499 | 'uploader_id': 'AllenMeow', | |
500 | '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', | |
501 | 'uploader': '孫艾倫', | |
502 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', | |
503 | }, | |
06b491eb S |
504 | }, |
505 | # url_encoded_fmt_stream_map is empty string | |
506 | { | |
507 | 'url': 'qEJwOuvDf7I', | |
508 | 'info_dict': { | |
509 | 'id': 'qEJwOuvDf7I', | |
510 | 'ext': 'mp4', | |
511 | 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', | |
512 | 'description': '', | |
513 | 'upload_date': '20150404', | |
514 | 'uploader_id': 'spbelect', | |
515 | 'uploader': 'Наблюдатели Петербурга', | |
516 | }, | |
517 | 'params': { | |
518 | 'skip_download': 'requires avconv', | |
519 | } | |
520 | }, | |
2eb88d95 PH |
521 | ] |
522 | ||
e0df6211 PH |
523 | def __init__(self, *args, **kwargs): |
524 | super(YoutubeIE, self).__init__(*args, **kwargs) | |
83799698 | 525 | self._player_cache = {} |
e0df6211 | 526 | |
c5e8d7af PH |
527 | def report_video_info_webpage_download(self, video_id): |
528 | """Report attempt to download video info webpage.""" | |
69ea8ca4 | 529 | self.to_screen('%s: Downloading video info webpage' % video_id) |
c5e8d7af | 530 | |
c5e8d7af PH |
531 | def report_information_extraction(self, video_id): |
532 | """Report attempt to extract video information.""" | |
69ea8ca4 | 533 | self.to_screen('%s: Extracting video information' % video_id) |
c5e8d7af PH |
534 | |
535 | def report_unavailable_format(self, video_id, format): | |
536 | """Report extracted video URL.""" | |
69ea8ca4 | 537 | self.to_screen('%s: Format %s not available' % (video_id, format)) |
c5e8d7af PH |
538 | |
539 | def report_rtmp_download(self): | |
540 | """Indicate the download will use the RTMP protocol.""" | |
69ea8ca4 | 541 | self.to_screen('RTMP download detected') |
c5e8d7af | 542 | |
60064c53 PH |
543 | def _signature_cache_id(self, example_sig): |
544 | """ Return a string representation of a signature """ | |
78caa52a | 545 | return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) |
60064c53 PH |
546 | |
547 | def _extract_signature_function(self, video_id, player_url, example_sig): | |
cf010131 | 548 | id_m = re.match( |
60620368 | 549 | r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.(?P<ext>[a-z]+)$', |
cf010131 | 550 | player_url) |
c081b35c PH |
551 | if not id_m: |
552 | raise ExtractorError('Cannot identify player %r' % player_url) | |
e0df6211 PH |
553 | player_type = id_m.group('ext') |
554 | player_id = id_m.group('id') | |
555 | ||
c4417ddb | 556 | # Read from filesystem cache |
60064c53 PH |
557 | func_id = '%s_%s_%s' % ( |
558 | player_type, player_id, self._signature_cache_id(example_sig)) | |
c4417ddb | 559 | assert os.path.basename(func_id) == func_id |
a0e07d31 | 560 | |
69ea8ca4 | 561 | cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) |
a0e07d31 | 562 | if cache_spec is not None: |
78caa52a | 563 | return lambda s: ''.join(s[i] for i in cache_spec) |
83799698 | 564 | |
6d1a55a5 PH |
565 | download_note = ( |
566 | 'Downloading player %s' % player_url | |
567 | if self._downloader.params.get('verbose') else | |
568 | 'Downloading %s player %s' % (player_type, player_id) | |
569 | ) | |
e0df6211 PH |
570 | if player_type == 'js': |
571 | code = self._download_webpage( | |
572 | player_url, video_id, | |
6d1a55a5 | 573 | note=download_note, |
69ea8ca4 | 574 | errnote='Download of %s failed' % player_url) |
83799698 | 575 | res = self._parse_sig_js(code) |
c4417ddb | 576 | elif player_type == 'swf': |
e0df6211 PH |
577 | urlh = self._request_webpage( |
578 | player_url, video_id, | |
6d1a55a5 | 579 | note=download_note, |
69ea8ca4 | 580 | errnote='Download of %s failed' % player_url) |
e0df6211 | 581 | code = urlh.read() |
83799698 | 582 | res = self._parse_sig_swf(code) |
e0df6211 PH |
583 | else: |
584 | assert False, 'Invalid player type %r' % player_type | |
585 | ||
785521bf PH |
586 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
587 | cache_res = res(test_string) | |
588 | cache_spec = [ord(c) for c in cache_res] | |
83799698 | 589 | |
69ea8ca4 | 590 | self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) |
83799698 PH |
591 | return res |
592 | ||
60064c53 | 593 | def _print_sig_code(self, func, example_sig): |
edf3e38e PH |
594 | def gen_sig_code(idxs): |
595 | def _genslice(start, end, step): | |
78caa52a | 596 | starts = '' if start == 0 else str(start) |
8bcc8756 | 597 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' |
69ea8ca4 | 598 | steps = '' if step == 1 else (':%d' % step) |
78caa52a | 599 | return 's[%s%s%s]' % (starts, ends, steps) |
edf3e38e PH |
600 | |
601 | step = None | |
7af808a5 PH |
602 | # Quelch pyflakes warnings - start will be set when step is set |
603 | start = '(Never used)' | |
edf3e38e PH |
604 | for i, prev in zip(idxs[1:], idxs[:-1]): |
605 | if step is not None: | |
606 | if i - prev == step: | |
607 | continue | |
608 | yield _genslice(start, prev, step) | |
609 | step = None | |
610 | continue | |
611 | if i - prev in [-1, 1]: | |
612 | step = i - prev | |
613 | start = prev | |
614 | continue | |
615 | else: | |
78caa52a | 616 | yield 's[%d]' % prev |
edf3e38e | 617 | if step is None: |
78caa52a | 618 | yield 's[%d]' % i |
edf3e38e PH |
619 | else: |
620 | yield _genslice(start, i, step) | |
621 | ||
78caa52a | 622 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
c705320f | 623 | cache_res = func(test_string) |
edf3e38e | 624 | cache_spec = [ord(c) for c in cache_res] |
78caa52a | 625 | expr_code = ' + '.join(gen_sig_code(cache_spec)) |
60064c53 PH |
626 | signature_id_tuple = '(%s)' % ( |
627 | ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) | |
69ea8ca4 | 628 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' |
78caa52a | 629 | ' return %s\n') % (signature_id_tuple, expr_code) |
69ea8ca4 | 630 | self.to_screen('Extracted signature function:\n' + code) |
edf3e38e | 631 | |
e0df6211 PH |
632 | def _parse_sig_js(self, jscode): |
633 | funcname = self._search_regex( | |
aaeb86f6 | 634 | r'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode, |
8bcc8756 | 635 | 'Initial JS player signature function name') |
2b25cb5d PH |
636 | |
637 | jsi = JSInterpreter(jscode) | |
638 | initial_function = jsi.extract_function(funcname) | |
e0df6211 PH |
639 | return lambda s: initial_function([s]) |
640 | ||
641 | def _parse_sig_swf(self, file_contents): | |
54256267 | 642 | swfi = SWFInterpreter(file_contents) |
78caa52a | 643 | TARGET_CLASSNAME = 'SignatureDecipher' |
54256267 | 644 | searched_class = swfi.extract_class(TARGET_CLASSNAME) |
78caa52a | 645 | initial_function = swfi.extract_function(searched_class, 'decipher') |
e0df6211 PH |
646 | return lambda s: initial_function([s]) |
647 | ||
83799698 | 648 | def _decrypt_signature(self, s, video_id, player_url, age_gate=False): |
257a2501 | 649 | """Turn the encrypted s field into a working signature""" |
6b37f0be | 650 | |
c8bf86d5 | 651 | if player_url is None: |
69ea8ca4 | 652 | raise ExtractorError('Cannot decrypt signature without player_url') |
920de7a2 | 653 | |
69ea8ca4 | 654 | if player_url.startswith('//'): |
78caa52a | 655 | player_url = 'https:' + player_url |
c8bf86d5 | 656 | try: |
62af3a0e | 657 | player_id = (player_url, self._signature_cache_id(s)) |
c8bf86d5 PH |
658 | if player_id not in self._player_cache: |
659 | func = self._extract_signature_function( | |
60064c53 | 660 | video_id, player_url, s |
c8bf86d5 PH |
661 | ) |
662 | self._player_cache[player_id] = func | |
663 | func = self._player_cache[player_id] | |
664 | if self._downloader.params.get('youtube_print_sig_code'): | |
60064c53 | 665 | self._print_sig_code(func, s) |
c8bf86d5 PH |
666 | return func(s) |
667 | except Exception as e: | |
668 | tb = traceback.format_exc() | |
669 | raise ExtractorError( | |
78caa52a | 670 | 'Signature extraction failed: ' + tb, cause=e) |
e0df6211 | 671 | |
360e1ca5 | 672 | def _get_subtitles(self, video_id, webpage): |
de7f3446 | 673 | try: |
60e47a26 | 674 | subs_doc = self._download_xml( |
38c2e5b8 | 675 | 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, |
7fad1c63 JMF |
676 | video_id, note=False) |
677 | except ExtractorError as err: | |
69ea8ca4 | 678 | self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err)) |
de7f3446 | 679 | return {} |
de7f3446 JMF |
680 | |
681 | sub_lang_list = {} | |
60e47a26 JMF |
682 | for track in subs_doc.findall('track'): |
683 | lang = track.attrib['lang_code'] | |
7e660ac1 LD |
684 | if lang in sub_lang_list: |
685 | continue | |
360e1ca5 JMF |
686 | sub_formats = [] |
687 | for ext in ['sbv', 'vtt', 'srt']: | |
688 | params = compat_urllib_parse.urlencode({ | |
689 | 'lang': lang, | |
690 | 'v': video_id, | |
691 | 'fmt': ext, | |
692 | 'name': track.attrib['name'].encode('utf-8'), | |
693 | }) | |
694 | sub_formats.append({ | |
695 | 'url': 'https://www.youtube.com/api/timedtext?' + params, | |
696 | 'ext': ext, | |
697 | }) | |
698 | sub_lang_list[lang] = sub_formats | |
de7f3446 | 699 | if not sub_lang_list: |
69ea8ca4 | 700 | self._downloader.report_warning('video doesn\'t have subtitles') |
de7f3446 JMF |
701 | return {} |
702 | return sub_lang_list | |
703 | ||
360e1ca5 | 704 | def _get_automatic_captions(self, video_id, webpage): |
de7f3446 JMF |
705 | """We need the webpage for getting the captions url, pass it as an |
706 | argument to speed up the process.""" | |
69ea8ca4 | 707 | self.to_screen('%s: Looking for automatic captions' % video_id) |
de7f3446 | 708 | mobj = re.search(r';ytplayer.config = ({.*?});', webpage) |
78caa52a | 709 | err_msg = 'Couldn\'t find automatic captions for %s' % video_id |
de7f3446 JMF |
710 | if mobj is None: |
711 | self._downloader.report_warning(err_msg) | |
712 | return {} | |
713 | player_config = json.loads(mobj.group(1)) | |
714 | try: | |
0792d563 PH |
715 | args = player_config['args'] |
716 | caption_url = args['ttsurl'] | |
717 | timestamp = args['timestamp'] | |
055e6f36 JMF |
718 | # We get the available subtitles |
719 | list_params = compat_urllib_parse.urlencode({ | |
720 | 'type': 'list', | |
721 | 'tlangs': 1, | |
722 | 'asrs': 1, | |
de7f3446 | 723 | }) |
055e6f36 | 724 | list_url = caption_url + '&' + list_params |
e26f8712 | 725 | caption_list = self._download_xml(list_url, video_id) |
e3dc22ca | 726 | original_lang_node = caption_list.find('track') |
7d900ef1 | 727 | if original_lang_node is None: |
69ea8ca4 | 728 | self._downloader.report_warning('Video doesn\'t have automatic captions') |
e3dc22ca JMF |
729 | return {} |
730 | original_lang = original_lang_node.attrib['lang_code'] | |
7d900ef1 | 731 | caption_kind = original_lang_node.attrib.get('kind', '') |
055e6f36 JMF |
732 | |
733 | sub_lang_list = {} | |
734 | for lang_node in caption_list.findall('target'): | |
735 | sub_lang = lang_node.attrib['lang_code'] | |
360e1ca5 JMF |
736 | sub_formats = [] |
737 | for ext in ['sbv', 'vtt', 'srt']: | |
738 | params = compat_urllib_parse.urlencode({ | |
739 | 'lang': original_lang, | |
740 | 'tlang': sub_lang, | |
741 | 'fmt': ext, | |
742 | 'ts': timestamp, | |
743 | 'kind': caption_kind, | |
744 | }) | |
745 | sub_formats.append({ | |
746 | 'url': caption_url + '&' + params, | |
747 | 'ext': ext, | |
748 | }) | |
749 | sub_lang_list[sub_lang] = sub_formats | |
055e6f36 | 750 | return sub_lang_list |
de7f3446 JMF |
751 | # An extractor error can be raise by the download process if there are |
752 | # no automatic captions but there are subtitles | |
753 | except (KeyError, ExtractorError): | |
754 | self._downloader.report_warning(err_msg) | |
755 | return {} | |
756 | ||
97665381 PH |
757 | @classmethod |
758 | def extract_id(cls, url): | |
759 | mobj = re.match(cls._VALID_URL, url, re.VERBOSE) | |
c5e8d7af | 760 | if mobj is None: |
69ea8ca4 | 761 | raise ExtractorError('Invalid URL: %s' % url) |
c5e8d7af PH |
762 | video_id = mobj.group(2) |
763 | return video_id | |
764 | ||
1d043b93 JMF |
765 | def _extract_from_m3u8(self, manifest_url, video_id): |
766 | url_map = {} | |
5f6a1245 | 767 | |
1d043b93 JMF |
768 | def _get_urls(_manifest): |
769 | lines = _manifest.split('\n') | |
770 | urls = filter(lambda l: l and not l.startswith('#'), | |
8bcc8756 | 771 | lines) |
1d043b93 | 772 | return urls |
78caa52a | 773 | manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest') |
1d043b93 JMF |
774 | formats_urls = _get_urls(manifest) |
775 | for format_url in formats_urls: | |
890f62e8 | 776 | itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag') |
1d043b93 JMF |
777 | url_map[itag] = format_url |
778 | return url_map | |
779 | ||
1fb07d10 JG |
780 | def _extract_annotations(self, video_id): |
781 | url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id | |
69ea8ca4 | 782 | return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.') |
1fb07d10 | 783 | |
da276600 PH |
784 | def _parse_dash_manifest( |
785 | self, video_id, dash_manifest_url, player_url, age_gate): | |
774e208f PH |
786 | def decrypt_sig(mobj): |
787 | s = mobj.group(1) | |
788 | dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) | |
789 | return '/signature/%s' % dec_s | |
e1b9322b | 790 | dash_manifest_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, dash_manifest_url) |
774e208f PH |
791 | dash_doc = self._download_xml( |
792 | dash_manifest_url, video_id, | |
793 | note='Downloading DASH manifest', | |
794 | errnote='Could not download DASH manifest') | |
795 | ||
796 | formats = [] | |
de5c5456 YCH |
797 | for a in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}AdaptationSet'): |
798 | mime_type = a.attrib.get('mimeType') | |
799 | for r in a.findall('{urn:mpeg:DASH:schema:MPD:2011}Representation'): | |
800 | url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL') | |
801 | if url_el is None: | |
802 | continue | |
803 | if mime_type == 'text/vtt': | |
804 | # TODO implement WebVTT downloading | |
805 | pass | |
806 | elif mime_type.startswith('audio/') or mime_type.startswith('video/'): | |
807 | format_id = r.attrib['id'] | |
808 | video_url = url_el.text | |
809 | filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength')) | |
810 | f = { | |
811 | 'format_id': format_id, | |
812 | 'url': video_url, | |
813 | 'width': int_or_none(r.attrib.get('width')), | |
814 | 'height': int_or_none(r.attrib.get('height')), | |
815 | 'tbr': int_or_none(r.attrib.get('bandwidth'), 1000), | |
816 | 'asr': int_or_none(r.attrib.get('audioSamplingRate')), | |
817 | 'filesize': filesize, | |
818 | 'fps': int_or_none(r.attrib.get('frameRate')), | |
819 | } | |
820 | try: | |
821 | existing_format = next( | |
822 | fo for fo in formats | |
823 | if fo['format_id'] == format_id) | |
824 | except StopIteration: | |
825 | full_info = self._formats.get(format_id, {}).copy() | |
826 | full_info.update(f) | |
827 | formats.append(full_info) | |
828 | else: | |
829 | existing_format.update(f) | |
830 | else: | |
831 | self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type) | |
774e208f PH |
832 | return formats |
833 | ||
c5e8d7af | 834 | def _real_extract(self, url): |
7e8c0af0 | 835 | proto = ( |
78caa52a PH |
836 | 'http' if self._downloader.params.get('prefer_insecure', False) |
837 | else 'https') | |
7e8c0af0 | 838 | |
c5e8d7af PH |
839 | # Extract original video URL from URL with redirection, like age verification, using next_url parameter |
840 | mobj = re.search(self._NEXT_URL_RE, url) | |
841 | if mobj: | |
7e8c0af0 | 842 | url = proto + '://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/') |
97665381 | 843 | video_id = self.extract_id(url) |
c5e8d7af PH |
844 | |
845 | # Get video webpage | |
aa79ac0c | 846 | url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id |
a1f934b1 | 847 | video_webpage = self._download_webpage(url, video_id) |
c5e8d7af PH |
848 | |
849 | # Attempt to extract SWF player URL | |
e0df6211 | 850 | mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) |
c5e8d7af PH |
851 | if mobj is not None: |
852 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) | |
853 | else: | |
854 | player_url = None | |
855 | ||
d8d24a92 S |
856 | dash_mpds = [] |
857 | ||
858 | def add_dash_mpd(video_info): | |
859 | dash_mpd = video_info.get('dashmpd') | |
860 | if dash_mpd and dash_mpd[0] not in dash_mpds: | |
861 | dash_mpds.append(dash_mpd[0]) | |
862 | ||
c5e8d7af | 863 | # Get video info |
6449cd80 | 864 | embed_webpage = None |
c108eb73 | 865 | if re.search(r'player-age-gate-content">', video_webpage) is not None: |
c108eb73 JMF |
866 | age_gate = True |
867 | # We simulate the access to the video from www.youtube.com/v/{video_id} | |
868 | # this can be viewed without login into Youtube | |
beb95e77 CL |
869 | url = proto + '://www.youtube.com/embed/%s' % video_id |
870 | embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage') | |
2c57c7fa JMF |
871 | data = compat_urllib_parse.urlencode({ |
872 | 'video_id': video_id, | |
873 | 'eurl': 'https://youtube.googleapis.com/v/' + video_id, | |
c084c934 | 874 | 'sts': self._search_regex( |
beb95e77 | 875 | r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''), |
2c57c7fa | 876 | }) |
7e8c0af0 | 877 | video_info_url = proto + '://www.youtube.com/get_video_info?' + data |
94bd3613 PH |
878 | video_info_webpage = self._download_webpage( |
879 | video_info_url, video_id, | |
20436c30 | 880 | note='Refetching age-gated info webpage', |
94bd3613 | 881 | errnote='unable to download video info webpage') |
c5e8d7af | 882 | video_info = compat_parse_qs(video_info_webpage) |
d8d24a92 | 883 | add_dash_mpd(video_info) |
c108eb73 JMF |
884 | else: |
885 | age_gate = False | |
bc93bdb5 | 886 | video_info = None |
d8d24a92 S |
887 | # Try looking directly into the video webpage |
888 | mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage) | |
889 | if mobj: | |
4e62ebe2 JMF |
890 | json_code = uppercase_escape(mobj.group(1)) |
891 | ytplayer_config = json.loads(json_code) | |
892 | args = ytplayer_config['args'] | |
d8d24a92 S |
893 | if args.get('url_encoded_fmt_stream_map'): |
894 | # Convert to the same format returned by compat_parse_qs | |
895 | video_info = dict((k, [v]) for k, v in args.items()) | |
896 | add_dash_mpd(video_info) | |
0a3cf9ad S |
897 | if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True): |
898 | # We also try looking in get_video_info since it may contain different dashmpd | |
899 | # URL that points to a DASH manifest with possibly different itag set (some itags | |
900 | # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH | |
901 | # manifest pointed by get_video_info's dashmpd). | |
902 | # The general idea is to take a union of itags of both DASH manifests (for example | |
903 | # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093) | |
904 | self.report_video_info_webpage_download(video_id) | |
905 | for el_type in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']: | |
906 | video_info_url = ( | |
907 | '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' | |
908 | % (proto, video_id, el_type)) | |
909 | video_info_webpage = self._download_webpage( | |
910 | video_info_url, | |
911 | video_id, note=False, | |
912 | errnote='unable to download video info webpage') | |
913 | get_video_info = compat_parse_qs(video_info_webpage) | |
914 | add_dash_mpd(get_video_info) | |
915 | if not video_info: | |
916 | video_info = get_video_info | |
917 | if 'token' in get_video_info: | |
918 | break | |
c5e8d7af PH |
919 | if 'token' not in video_info: |
920 | if 'reason' in video_info: | |
d11271dd | 921 | raise ExtractorError( |
78caa52a | 922 | 'YouTube said: %s' % video_info['reason'][0], |
d11271dd | 923 | expected=True, video_id=video_id) |
c5e8d7af | 924 | else: |
d11271dd | 925 | raise ExtractorError( |
78caa52a | 926 | '"token" parameter not in video info for unknown reason', |
d11271dd | 927 | video_id=video_id) |
c5e8d7af | 928 | |
1d699755 PH |
929 | if 'view_count' in video_info: |
930 | view_count = int(video_info['view_count'][0]) | |
931 | else: | |
932 | view_count = None | |
933 | ||
c5e8d7af PH |
934 | # Check for "rental" videos |
935 | if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: | |
69ea8ca4 | 936 | raise ExtractorError('"rental" videos not supported') |
c5e8d7af PH |
937 | |
938 | # Start extracting information | |
939 | self.report_information_extraction(video_id) | |
940 | ||
941 | # uploader | |
942 | if 'author' not in video_info: | |
69ea8ca4 | 943 | raise ExtractorError('Unable to extract uploader name') |
c5e8d7af PH |
944 | video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0]) |
945 | ||
946 | # uploader_id | |
947 | video_uploader_id = None | |
948 | mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage) | |
949 | if mobj is not None: | |
950 | video_uploader_id = mobj.group(1) | |
951 | else: | |
69ea8ca4 | 952 | self._downloader.report_warning('unable to extract uploader nickname') |
c5e8d7af PH |
953 | |
954 | # title | |
a8c6b241 | 955 | if 'title' in video_info: |
aa92f063 | 956 | video_title = video_info['title'][0] |
a8c6b241 | 957 | else: |
69ea8ca4 | 958 | self._downloader.report_warning('Unable to extract video title') |
78caa52a | 959 | video_title = '_' |
c5e8d7af PH |
960 | |
961 | # thumbnail image | |
7763b04e JMF |
962 | # We try first to get a high quality image: |
963 | m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">', | |
964 | video_webpage, re.DOTALL) | |
965 | if m_thumb is not None: | |
966 | video_thumbnail = m_thumb.group(1) | |
967 | elif 'thumbnail_url' not in video_info: | |
69ea8ca4 | 968 | self._downloader.report_warning('unable to extract video thumbnail') |
f490e77e | 969 | video_thumbnail = None |
c5e8d7af PH |
970 | else: # don't panic if we can't find it |
971 | video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0]) | |
972 | ||
973 | # upload date | |
974 | upload_date = None | |
ad3bc6ac | 975 | mobj = re.search(r'(?s)id="eow-date.*?>(.*?)</span>', video_webpage) |
beee53de PH |
976 | if mobj is None: |
977 | mobj = re.search( | |
263bd4ec | 978 | r'(?s)id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live) on (.*?)</strong>', |
beee53de | 979 | video_webpage) |
c5e8d7af PH |
980 | if mobj is not None: |
981 | upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) | |
982 | upload_date = unified_strdate(upload_date) | |
983 | ||
55f7bd2d PH |
984 | m_cat_container = self._search_regex( |
985 | r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', | |
624dcebf | 986 | video_webpage, 'categories', default=None) |
ec8deefc | 987 | if m_cat_container: |
ad3bc6ac | 988 | category = self._html_search_regex( |
01ed5c9b | 989 | r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', |
ad3bc6ac PH |
990 | default=None) |
991 | video_categories = None if category is None else [category] | |
992 | else: | |
993 | video_categories = None | |
ec8deefc | 994 | |
c5e8d7af PH |
995 | # description |
996 | video_description = get_element_by_id("eow-description", video_webpage) | |
997 | if video_description: | |
27dcce19 PH |
998 | video_description = re.sub(r'''(?x) |
999 | <a\s+ | |
1000 | (?:[a-zA-Z-]+="[^"]+"\s+)*? | |
1001 | title="([^"]+)"\s+ | |
1002 | (?:[a-zA-Z-]+="[^"]+"\s+)*? | |
1003 | class="yt-uix-redirect-link"\s*> | |
1004 | [^<]+ | |
1005 | </a> | |
1006 | ''', r'\1', video_description) | |
c5e8d7af PH |
1007 | video_description = clean_html(video_description) |
1008 | else: | |
1009 | fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage) | |
1010 | if fd_mobj: | |
1011 | video_description = unescapeHTML(fd_mobj.group(1)) | |
1012 | else: | |
78caa52a | 1013 | video_description = '' |
c5e8d7af | 1014 | |
f30a38be | 1015 | def _extract_count(count_name): |
46374a56 | 1016 | count = self._search_regex( |
f30a38be JMF |
1017 | r'id="watch-%s"[^>]*>.*?([\d,]+)\s*</span>' % re.escape(count_name), |
1018 | video_webpage, count_name, default=None) | |
336c3a69 JMF |
1019 | if count is not None: |
1020 | return int(count.replace(',', '')) | |
1021 | return None | |
69ea8ca4 PH |
1022 | like_count = _extract_count('like') |
1023 | dislike_count = _extract_count('dislike') | |
336c3a69 | 1024 | |
c5e8d7af | 1025 | # subtitles |
d82134c3 | 1026 | video_subtitles = self.extract_subtitles(video_id, video_webpage) |
360e1ca5 | 1027 | automatic_captions = self.extract_automatic_captions(video_id, video_webpage) |
c5e8d7af PH |
1028 | |
1029 | if 'length_seconds' not in video_info: | |
69ea8ca4 | 1030 | self._downloader.report_warning('unable to extract video duration') |
b466b702 | 1031 | video_duration = None |
c5e8d7af | 1032 | else: |
b466b702 | 1033 | video_duration = int(compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])) |
c5e8d7af | 1034 | |
1fb07d10 JG |
1035 | # annotations |
1036 | video_annotations = None | |
1037 | if self._downloader.params.get('writeannotations', False): | |
5f6a1245 | 1038 | video_annotations = self._extract_annotations(video_id) |
1fb07d10 | 1039 | |
dd27fd17 PH |
1040 | def _map_to_format_list(urlmap): |
1041 | formats = [] | |
1042 | for itag, video_real_url in urlmap.items(): | |
1043 | dct = { | |
1044 | 'format_id': itag, | |
1045 | 'url': video_real_url, | |
1046 | 'player_url': player_url, | |
1047 | } | |
0b65e5d4 PH |
1048 | if itag in self._formats: |
1049 | dct.update(self._formats[itag]) | |
dd27fd17 PH |
1050 | formats.append(dct) |
1051 | return formats | |
1052 | ||
c5e8d7af PH |
1053 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): |
1054 | self.report_rtmp_download() | |
dd27fd17 PH |
1055 | formats = [{ |
1056 | 'format_id': '_rtmp', | |
1057 | 'protocol': 'rtmp', | |
1058 | 'url': video_info['conn'][0], | |
1059 | 'player_url': player_url, | |
1060 | }] | |
24270b03 | 1061 | elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1: |
5f6a1245 | 1062 | encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] |
00fe14fc | 1063 | if 'rtmpe%3Dyes' in encoded_url_map: |
a7055eb9 | 1064 | raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True) |
c5e8d7af | 1065 | url_map = {} |
00fe14fc | 1066 | for url_data_str in encoded_url_map.split(','): |
c5e8d7af | 1067 | url_data = compat_parse_qs(url_data_str) |
201e9eaa PH |
1068 | if 'itag' not in url_data or 'url' not in url_data: |
1069 | continue | |
1070 | format_id = url_data['itag'][0] | |
1071 | url = url_data['url'][0] | |
1072 | ||
1073 | if 'sig' in url_data: | |
1074 | url += '&signature=' + url_data['sig'][0] | |
1075 | elif 's' in url_data: | |
1076 | encrypted_sig = url_data['s'][0] | |
6449cd80 | 1077 | ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' |
201e9eaa | 1078 | |
beb95e77 | 1079 | jsplayer_url_json = self._search_regex( |
6449cd80 PH |
1080 | ASSETS_RE, |
1081 | embed_webpage if age_gate else video_webpage, | |
1082 | 'JS player URL (1)', default=None) | |
1083 | if not jsplayer_url_json and not age_gate: | |
1084 | # We need the embed website after all | |
1085 | if embed_webpage is None: | |
1086 | embed_url = proto + '://www.youtube.com/embed/%s' % video_id | |
1087 | embed_webpage = self._download_webpage( | |
1088 | embed_url, video_id, 'Downloading embed webpage') | |
1089 | jsplayer_url_json = self._search_regex( | |
1090 | ASSETS_RE, embed_webpage, 'JS player URL') | |
1091 | ||
beb95e77 | 1092 | player_url = json.loads(jsplayer_url_json) |
201e9eaa PH |
1093 | if player_url is None: |
1094 | player_url_json = self._search_regex( | |
1095 | r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', | |
78caa52a | 1096 | video_webpage, 'age gate player URL') |
201e9eaa PH |
1097 | player_url = json.loads(player_url_json) |
1098 | ||
1099 | if self._downloader.params.get('verbose'): | |
cf010131 | 1100 | if player_url is None: |
201e9eaa PH |
1101 | player_version = 'unknown' |
1102 | player_desc = 'unknown' | |
1103 | else: | |
1104 | if player_url.endswith('swf'): | |
1105 | player_version = self._search_regex( | |
1106 | r'-(.+?)(?:/watch_as3)?\.swf$', player_url, | |
78caa52a | 1107 | 'flash player', fatal=False) |
201e9eaa | 1108 | player_desc = 'flash player %s' % player_version |
cf010131 | 1109 | else: |
201e9eaa PH |
1110 | player_version = self._search_regex( |
1111 | r'html5player-([^/]+?)(?:/html5player)?\.js', | |
1112 | player_url, | |
1113 | 'html5 player', fatal=False) | |
78caa52a | 1114 | player_desc = 'html5 player %s' % player_version |
201e9eaa | 1115 | |
60064c53 | 1116 | parts_sizes = self._signature_cache_id(encrypted_sig) |
69ea8ca4 | 1117 | self.to_screen('{%s} signature length %s, %s' % |
9e1a5b84 | 1118 | (format_id, parts_sizes, player_desc)) |
201e9eaa PH |
1119 | |
1120 | signature = self._decrypt_signature( | |
1121 | encrypted_sig, video_id, player_url, age_gate) | |
1122 | url += '&signature=' + signature | |
1123 | if 'ratebypass' not in url: | |
1124 | url += '&ratebypass=yes' | |
1125 | url_map[format_id] = url | |
dd27fd17 | 1126 | formats = _map_to_format_list(url_map) |
1d043b93 JMF |
1127 | elif video_info.get('hlsvp'): |
1128 | manifest_url = video_info['hlsvp'][0] | |
1129 | url_map = self._extract_from_m3u8(manifest_url, video_id) | |
dd27fd17 | 1130 | formats = _map_to_format_list(url_map) |
c5e8d7af | 1131 | else: |
69ea8ca4 | 1132 | raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') |
c5e8d7af | 1133 | |
dd27fd17 | 1134 | # Look for the DASH manifest |
203fb43f | 1135 | if self._downloader.params.get('youtube_include_dash_manifest', True): |
d8d24a92 S |
1136 | for dash_manifest_url in dash_mpds: |
1137 | dash_formats = {} | |
774e208f | 1138 | try: |
d8d24a92 S |
1139 | for df in self._parse_dash_manifest( |
1140 | video_id, dash_manifest_url, player_url, age_gate): | |
1141 | # Do not overwrite DASH format found in some previous DASH manifest | |
1142 | if df['format_id'] not in dash_formats: | |
1143 | dash_formats[df['format_id']] = df | |
774e208f PH |
1144 | except (ExtractorError, KeyError) as e: |
1145 | self.report_warning( | |
1146 | 'Skipping DASH manifest: %r' % e, video_id) | |
d8d24a92 | 1147 | if dash_formats: |
04b3b3df JMF |
1148 | # Remove the formats we found through non-DASH, they |
1149 | # contain less info and it can be wrong, because we use | |
1150 | # fixed values (for example the resolution). See | |
1151 | # https://github.com/rg3/youtube-dl/issues/5774 for an | |
1152 | # example. | |
d80265cc | 1153 | formats = [f for f in formats if f['format_id'] not in dash_formats.keys()] |
d8d24a92 | 1154 | formats.extend(dash_formats.values()) |
d80044c2 | 1155 | |
6271f1ca PH |
1156 | # Check for malformed aspect ratio |
1157 | stretched_m = re.search( | |
1158 | r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">', | |
1159 | video_webpage) | |
1160 | if stretched_m: | |
1161 | ratio = float(stretched_m.group('w')) / float(stretched_m.group('h')) | |
1162 | for f in formats: | |
1163 | if f.get('vcodec') != 'none': | |
1164 | f['stretched_ratio'] = ratio | |
1165 | ||
4bcc7bd1 | 1166 | self._sort_formats(formats) |
4ea3be0a | 1167 | |
1168 | return { | |
8bcc8756 JW |
1169 | 'id': video_id, |
1170 | 'uploader': video_uploader, | |
1171 | 'uploader_id': video_uploader_id, | |
1172 | 'upload_date': upload_date, | |
1173 | 'title': video_title, | |
1174 | 'thumbnail': video_thumbnail, | |
1175 | 'description': video_description, | |
1176 | 'categories': video_categories, | |
1177 | 'subtitles': video_subtitles, | |
360e1ca5 | 1178 | 'automatic_captions': automatic_captions, |
8bcc8756 JW |
1179 | 'duration': video_duration, |
1180 | 'age_limit': 18 if age_gate else 0, | |
1181 | 'annotations': video_annotations, | |
7e8c0af0 | 1182 | 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id, |
8bcc8756 | 1183 | 'view_count': view_count, |
4ea3be0a | 1184 | 'like_count': like_count, |
1185 | 'dislike_count': dislike_count, | |
2d30521a | 1186 | 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]), |
8bcc8756 | 1187 | 'formats': formats, |
4ea3be0a | 1188 | } |
c5e8d7af | 1189 | |
5f6a1245 | 1190 | |
880e1c52 | 1191 | class YoutubePlaylistIE(YoutubeBaseInfoExtractor): |
78caa52a | 1192 | IE_DESC = 'YouTube.com playlists' |
d67cc9fa | 1193 | _VALID_URL = r"""(?x)(?: |
c5e8d7af PH |
1194 | (?:https?://)? |
1195 | (?:\w+\.)? | |
1196 | youtube\.com/ | |
1197 | (?: | |
ac7553d0 | 1198 | (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries) |
c5e8d7af PH |
1199 | \? (?:.*?&)*? (?:p|a|list)= |
1200 | | p/ | |
1201 | ) | |
d67cc9fa | 1202 | ( |
99209c29 | 1203 | (?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,} |
5f6a1245 | 1204 | # Top tracks, they can also include dots |
d67cc9fa JMF |
1205 | |(?:MC)[\w\.]* |
1206 | ) | |
c5e8d7af PH |
1207 | .* |
1208 | | | |
99209c29 | 1209 | ((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,}) |
c5e8d7af | 1210 | )""" |
dbb94fb0 | 1211 | _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' |
dbb94fb0 | 1212 | _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)' |
78caa52a | 1213 | IE_NAME = 'youtube:playlist' |
81127aa5 PH |
1214 | _TESTS = [{ |
1215 | 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', | |
1216 | 'info_dict': { | |
1217 | 'title': 'ytdl test PL', | |
a1cf99d0 | 1218 | 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', |
81127aa5 PH |
1219 | }, |
1220 | 'playlist_count': 3, | |
9291475f PH |
1221 | }, { |
1222 | 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', | |
1223 | 'info_dict': { | |
acf757f4 | 1224 | 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', |
9291475f PH |
1225 | 'title': 'YDL_Empty_List', |
1226 | }, | |
1227 | 'playlist_count': 0, | |
1228 | }, { | |
1229 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
1230 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
1231 | 'info_dict': { | |
1232 | 'title': '29C3: Not my department', | |
acf757f4 | 1233 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', |
9291475f PH |
1234 | }, |
1235 | 'playlist_count': 95, | |
1236 | }, { | |
1237 | 'note': 'issue #673', | |
1238 | 'url': 'PLBB231211A4F62143', | |
1239 | 'info_dict': { | |
f46a8702 | 1240 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', |
acf757f4 | 1241 | 'id': 'PLBB231211A4F62143', |
9291475f PH |
1242 | }, |
1243 | 'playlist_mincount': 26, | |
1244 | }, { | |
1245 | 'note': 'Large playlist', | |
1246 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
1247 | 'info_dict': { | |
1248 | 'title': 'Uploads from Cauchemar', | |
acf757f4 | 1249 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', |
9291475f PH |
1250 | }, |
1251 | 'playlist_mincount': 799, | |
1252 | }, { | |
1253 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
1254 | 'info_dict': { | |
1255 | 'title': 'YDL_safe_search', | |
acf757f4 | 1256 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', |
9291475f PH |
1257 | }, |
1258 | 'playlist_count': 2, | |
ac7553d0 PH |
1259 | }, { |
1260 | 'note': 'embedded', | |
1261 | 'url': 'http://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
1262 | 'playlist_count': 4, | |
1263 | 'info_dict': { | |
1264 | 'title': 'JODA15', | |
acf757f4 | 1265 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', |
ac7553d0 | 1266 | } |
6b08cdf6 PH |
1267 | }, { |
1268 | 'note': 'Embedded SWF player', | |
1269 | 'url': 'http://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0', | |
1270 | 'playlist_count': 4, | |
1271 | 'info_dict': { | |
1272 | 'title': 'JODA7', | |
acf757f4 | 1273 | 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ', |
6b08cdf6 | 1274 | } |
4b7df0d3 JMF |
1275 | }, { |
1276 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
1277 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
1278 | 'info_dict': { | |
acf757f4 PH |
1279 | 'title': 'Uploads from Interstellar Movie', |
1280 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
4b7df0d3 JMF |
1281 | }, |
1282 | 'playlist_mincout': 21, | |
81127aa5 | 1283 | }] |
c5e8d7af | 1284 | |
880e1c52 JMF |
1285 | def _real_initialize(self): |
1286 | self._login() | |
1287 | ||
652cdaa2 | 1288 | def _extract_mix(self, playlist_id): |
99209c29 | 1289 | # The mixes are generated from a single video |
652cdaa2 | 1290 | # the id of the playlist is just 'RD' + video_id |
7d4afc55 | 1291 | url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id) |
c9cc0bf5 | 1292 | webpage = self._download_webpage( |
78caa52a | 1293 | url, playlist_id, 'Downloading Youtube mix') |
bc2f773b | 1294 | search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage) |
c9cc0bf5 PH |
1295 | title_span = ( |
1296 | search_title('playlist-title') or | |
1297 | search_title('title long-title') or | |
1298 | search_title('title')) | |
76d1700b | 1299 | title = clean_html(title_span) |
c9cc0bf5 PH |
1300 | ids = orderedSet(re.findall( |
1301 | r'''(?xs)data-video-username=".*?".*? | |
1302 | href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id), | |
1303 | webpage)) | |
652cdaa2 JMF |
1304 | url_results = self._ids_to_results(ids) |
1305 | ||
1306 | return self.playlist_result(url_results, playlist_id, title) | |
1307 | ||
448830ce | 1308 | def _extract_playlist(self, playlist_id): |
dbb94fb0 S |
1309 | url = self._TEMPLATE_URL % playlist_id |
1310 | page = self._download_webpage(url, playlist_id) | |
dbb94fb0 | 1311 | |
39b62db1 YCH |
1312 | for match in re.findall(r'<div class="yt-alert-message">([^<]+)</div>', page): |
1313 | match = match.strip() | |
1314 | # Check if the playlist exists or is private | |
1315 | if re.match(r'[^<]*(The|This) playlist (does not exist|is private)[^<]*', match): | |
1316 | raise ExtractorError( | |
1317 | 'The playlist doesn\'t exist or is private, use --username or ' | |
1318 | '--netrc to access it.', | |
1319 | expected=True) | |
1320 | elif re.match(r'[^<]*Invalid parameters[^<]*', match): | |
1321 | raise ExtractorError( | |
1322 | 'Invalid parameters. Maybe URL is incorrect.', | |
1323 | expected=True) | |
1324 | elif re.match(r'[^<]*Choose your language[^<]*', match): | |
1325 | continue | |
1326 | else: | |
1327 | self.report_warning('Youtube gives an alert message: ' + match) | |
10c0e2d8 | 1328 | |
dcbb4580 | 1329 | # Extract the video ids from the playlist pages |
70219b0f JMF |
1330 | def _entries(): |
1331 | more_widget_html = content_html = page | |
1332 | for page_num in itertools.count(1): | |
1333 | matches = re.finditer(self._VIDEO_RE, content_html) | |
1334 | # We remove the duplicates and the link with index 0 | |
1335 | # (it's not the first video of the playlist) | |
1336 | new_ids = orderedSet(m.group('id') for m in matches if m.group('index') != '0') | |
1337 | for vid_id in new_ids: | |
1338 | yield self.url_result(vid_id, 'Youtube', video_id=vid_id) | |
1339 | ||
1340 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) | |
1341 | if not mobj: | |
1342 | break | |
1343 | ||
1344 | more = self._download_json( | |
1345 | 'https://youtube.com/%s' % mobj.group('more'), playlist_id, | |
1346 | 'Downloading page #%s' % page_num, | |
1347 | transform_source=uppercase_escape) | |
1348 | content_html = more['content_html'] | |
1349 | if not content_html.strip(): | |
1350 | # Some webpages show a "Load more" button but they don't | |
1351 | # have more videos | |
1352 | break | |
1353 | more_widget_html = more['load_more_widget_html'] | |
dbb94fb0 S |
1354 | |
1355 | playlist_title = self._html_search_regex( | |
68eb8e90 | 1356 | r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>', |
78caa52a | 1357 | page, 'title') |
c5e8d7af | 1358 | |
70219b0f | 1359 | return self.playlist_result(_entries(), playlist_id, playlist_title) |
c5e8d7af | 1360 | |
448830ce S |
1361 | def _real_extract(self, url): |
1362 | # Extract playlist id | |
1363 | mobj = re.match(self._VALID_URL, url) | |
1364 | if mobj is None: | |
1365 | raise ExtractorError('Invalid URL: %s' % url) | |
1366 | playlist_id = mobj.group(1) or mobj.group(2) | |
1367 | ||
1368 | # Check if it's a video-specific URL | |
1369 | query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) | |
1370 | if 'v' in query_dict: | |
1371 | video_id = query_dict['v'][0] | |
1372 | if self._downloader.params.get('noplaylist'): | |
1373 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
1374 | return self.url_result(video_id, 'Youtube', video_id=video_id) | |
1375 | else: | |
1376 | self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) | |
1377 | ||
1378 | if playlist_id.startswith('RD') or playlist_id.startswith('UL'): | |
1379 | # Mixes require a custom extraction process | |
1380 | return self._extract_mix(playlist_id) | |
1381 | ||
1382 | return self._extract_playlist(playlist_id) | |
1383 | ||
c5e8d7af PH |
1384 | |
1385 | class YoutubeChannelIE(InfoExtractor): | |
78caa52a | 1386 | IE_DESC = 'YouTube.com channels' |
9ff67727 | 1387 | _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)' |
eb0f3e7e | 1388 | _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos' |
78caa52a | 1389 | IE_NAME = 'youtube:channel' |
cdc628a4 PH |
1390 | _TESTS = [{ |
1391 | 'note': 'paginated channel', | |
1392 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
1393 | 'playlist_mincount': 91, | |
acf757f4 PH |
1394 | 'info_dict': { |
1395 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
1396 | } | |
cdc628a4 | 1397 | }] |
c5e8d7af | 1398 | |
6de5dbaf S |
1399 | @staticmethod |
1400 | def extract_videos_from_page(page): | |
c5e8d7af | 1401 | ids_in_page = [] |
fb69240c S |
1402 | titles_in_page = [] |
1403 | for mobj in re.finditer(r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?', page): | |
1404 | video_id = mobj.group('id') | |
1405 | video_title = unescapeHTML(mobj.group('title')) | |
1406 | try: | |
1407 | idx = ids_in_page.index(video_id) | |
1408 | if video_title and not titles_in_page[idx]: | |
1409 | titles_in_page[idx] = video_title | |
1410 | except ValueError: | |
1411 | ids_in_page.append(video_id) | |
1412 | titles_in_page.append(video_title) | |
1413 | return zip(ids_in_page, titles_in_page) | |
c5e8d7af PH |
1414 | |
1415 | def _real_extract(self, url): | |
9ff67727 | 1416 | channel_id = self._match_id(url) |
c5e8d7af | 1417 | |
eb0f3e7e | 1418 | url = self._TEMPLATE_URL % channel_id |
386bdfa6 S |
1419 | |
1420 | # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778) | |
1421 | # Workaround by extracting as a playlist if managed to obtain channel playlist URL | |
1422 | # otherwise fallback on channel by page extraction | |
1423 | channel_page = self._download_webpage( | |
1424 | url + '?view=57', channel_id, | |
1425 | 'Downloading channel page', fatal=False) | |
3d8e9573 S |
1426 | channel_playlist_id = self._html_search_meta( |
1427 | 'channelId', channel_page, 'channel id', default=None) | |
1428 | if not channel_playlist_id: | |
1429 | channel_playlist_id = self._search_regex( | |
1430 | r'data-channel-external-id="([^"]+)"', | |
1431 | channel_page, 'channel id', default=None) | |
386bdfa6 S |
1432 | if channel_playlist_id and channel_playlist_id.startswith('UC'): |
1433 | playlist_id = 'UU' + channel_playlist_id[2:] | |
d2a9de78 IK |
1434 | return self.url_result( |
1435 | compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist') | |
386bdfa6 | 1436 | |
60bf45c8 | 1437 | channel_page = self._download_webpage(url, channel_id, 'Downloading page #1') |
31812a9e PH |
1438 | autogenerated = re.search(r'''(?x) |
1439 | class="[^"]*?(?: | |
1440 | channel-header-autogenerated-label| | |
1441 | yt-channel-title-autogenerated | |
1442 | )[^"]*"''', channel_page) is not None | |
c5e8d7af | 1443 | |
b9643eed JMF |
1444 | if autogenerated: |
1445 | # The videos are contained in a single page | |
1446 | # the ajax pages can't be used, they are empty | |
b82f815f | 1447 | entries = [ |
fb69240c S |
1448 | self.url_result( |
1449 | video_id, 'Youtube', video_id=video_id, | |
1450 | video_title=video_title) | |
8f02ad4f | 1451 | for video_id, video_title in self.extract_videos_from_page(channel_page)] |
b82f815f PH |
1452 | return self.playlist_result(entries, channel_id) |
1453 | ||
1454 | def _entries(): | |
23d3608c | 1455 | more_widget_html = content_html = channel_page |
b9643eed | 1456 | for pagenum in itertools.count(1): |
81c2f20b | 1457 | |
8f02ad4f | 1458 | for video_id, video_title in self.extract_videos_from_page(content_html): |
b82f815f | 1459 | yield self.url_result( |
fb69240c S |
1460 | video_id, 'Youtube', video_id=video_id, |
1461 | video_title=video_title) | |
5f6a1245 | 1462 | |
23d3608c JMF |
1463 | mobj = re.search( |
1464 | r'data-uix-load-more-href="/?(?P<more>[^"]+)"', | |
1465 | more_widget_html) | |
1466 | if not mobj: | |
b9643eed | 1467 | break |
c5e8d7af | 1468 | |
23d3608c JMF |
1469 | more = self._download_json( |
1470 | 'https://youtube.com/%s' % mobj.group('more'), channel_id, | |
1471 | 'Downloading page #%s' % (pagenum + 1), | |
1472 | transform_source=uppercase_escape) | |
1473 | content_html = more['content_html'] | |
1474 | more_widget_html = more['load_more_widget_html'] | |
1475 | ||
b82f815f | 1476 | return self.playlist_result(_entries(), channel_id) |
c5e8d7af PH |
1477 | |
1478 | ||
eb0f3e7e | 1479 | class YoutubeUserIE(YoutubeChannelIE): |
78caa52a | 1480 | IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)' |
9ff67727 | 1481 | _VALID_URL = r'(?:(?:(?:https?://)?(?:\w+\.)?youtube\.com/(?:user/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)' |
eb0f3e7e | 1482 | _TEMPLATE_URL = 'https://www.youtube.com/user/%s/videos' |
78caa52a | 1483 | IE_NAME = 'youtube:user' |
c5e8d7af | 1484 | |
cdc628a4 PH |
1485 | _TESTS = [{ |
1486 | 'url': 'https://www.youtube.com/user/TheLinuxFoundation', | |
1487 | 'playlist_mincount': 320, | |
1488 | 'info_dict': { | |
1489 | 'title': 'TheLinuxFoundation', | |
1490 | } | |
1491 | }, { | |
1492 | 'url': 'ytuser:phihag', | |
1493 | 'only_matching': True, | |
1494 | }] | |
1495 | ||
e3ea4790 | 1496 | @classmethod |
f4b05232 | 1497 | def suitable(cls, url): |
e3ea4790 JMF |
1498 | # Don't return True if the url can be extracted with other youtube |
1499 | # extractor, the regex would is too permissive and it would match. | |
1500 | other_ies = iter(klass for (name, klass) in globals().items() if name.endswith('IE') and klass is not cls) | |
5f6a1245 JW |
1501 | if any(ie.suitable(url) for ie in other_ies): |
1502 | return False | |
1503 | else: | |
1504 | return super(YoutubeUserIE, cls).suitable(url) | |
f4b05232 | 1505 | |
b05654f0 | 1506 | |
b4c08069 | 1507 | class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE): |
78caa52a | 1508 | IE_DESC = 'YouTube.com searches' |
b4c08069 JMF |
1509 | # there doesn't appear to be a real limit, for example if you search for |
1510 | # 'python' you get more than 8.000.000 results | |
1511 | _MAX_RESULTS = float('inf') | |
78caa52a | 1512 | IE_NAME = 'youtube:search' |
b05654f0 | 1513 | _SEARCH_KEY = 'ytsearch' |
b4c08069 | 1514 | _EXTRA_QUERY_ARGS = {} |
9dd8e46a | 1515 | _TESTS = [] |
b05654f0 | 1516 | |
b05654f0 PH |
1517 | def _get_n_results(self, query, n): |
1518 | """Get a specified number of results for a query""" | |
1519 | ||
b4c08069 | 1520 | videos = [] |
b05654f0 PH |
1521 | limit = n |
1522 | ||
b4c08069 JMF |
1523 | for pagenum in itertools.count(1): |
1524 | url_query = { | |
02175a79 | 1525 | 'search_query': query.encode('utf-8'), |
b4c08069 JMF |
1526 | 'page': pagenum, |
1527 | 'spf': 'navigate', | |
1528 | } | |
1529 | url_query.update(self._EXTRA_QUERY_ARGS) | |
1530 | result_url = 'https://www.youtube.com/results?' + compat_urllib_parse.urlencode(url_query) | |
1531 | data = self._download_json( | |
69ea8ca4 | 1532 | result_url, video_id='query "%s"' % query, |
b4c08069 | 1533 | note='Downloading page %s' % pagenum, |
69ea8ca4 | 1534 | errnote='Unable to download API page') |
b4c08069 | 1535 | html_content = data[1]['body']['content'] |
7cc3570e | 1536 | |
b4c08069 | 1537 | if 'class="search-message' in html_content: |
07ad22b8 | 1538 | raise ExtractorError( |
78caa52a | 1539 | '[youtube] No video results', expected=True) |
b05654f0 | 1540 | |
b4c08069 JMF |
1541 | new_videos = self._ids_to_results(orderedSet(re.findall( |
1542 | r'href="/watch\?v=(.{11})', html_content))) | |
1543 | videos += new_videos | |
1544 | if not new_videos or len(videos) > limit: | |
1545 | break | |
b05654f0 | 1546 | |
b4c08069 JMF |
1547 | if len(videos) > n: |
1548 | videos = videos[:n] | |
b05654f0 | 1549 | return self.playlist_result(videos, query) |
75dff0ee | 1550 | |
c9ae7b95 | 1551 | |
a3dd9248 | 1552 | class YoutubeSearchDateIE(YoutubeSearchIE): |
cb7fb546 | 1553 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' |
a3dd9248 | 1554 | _SEARCH_KEY = 'ytsearchdate' |
78caa52a | 1555 | IE_DESC = 'YouTube.com searches, newest videos first' |
b4c08069 | 1556 | _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'} |
75dff0ee | 1557 | |
c9ae7b95 PH |
1558 | |
1559 | class YoutubeSearchURLIE(InfoExtractor): | |
78caa52a PH |
1560 | IE_DESC = 'YouTube.com search URLs' |
1561 | IE_NAME = 'youtube:search_url' | |
c9ae7b95 | 1562 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?search_query=(?P<query>[^&]+)(?:[&]|$)' |
cdc628a4 PH |
1563 | _TESTS = [{ |
1564 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
1565 | 'playlist_mincount': 5, | |
1566 | 'info_dict': { | |
1567 | 'title': 'youtube-dl test video', | |
1568 | } | |
1569 | }] | |
c9ae7b95 PH |
1570 | |
1571 | def _real_extract(self, url): | |
1572 | mobj = re.match(self._VALID_URL, url) | |
1573 | query = compat_urllib_parse.unquote_plus(mobj.group('query')) | |
1574 | ||
1575 | webpage = self._download_webpage(url, query) | |
1576 | result_code = self._search_regex( | |
98998cde | 1577 | r'(?s)<ol[^>]+class="item-section"(.*?)</ol>', webpage, 'result HTML') |
c9ae7b95 PH |
1578 | |
1579 | part_codes = re.findall( | |
1580 | r'(?s)<h3 class="yt-lockup-title">(.*?)</h3>', result_code) | |
1581 | entries = [] | |
1582 | for part_code in part_codes: | |
1583 | part_title = self._html_search_regex( | |
6feb2d5e | 1584 | [r'(?s)title="([^"]+)"', r'>([^<]+)</a>'], part_code, 'item title', fatal=False) |
c9ae7b95 PH |
1585 | part_url_snippet = self._html_search_regex( |
1586 | r'(?s)href="([^"]+)"', part_code, 'item URL') | |
1587 | part_url = compat_urlparse.urljoin( | |
1588 | 'https://www.youtube.com/', part_url_snippet) | |
1589 | entries.append({ | |
1590 | '_type': 'url', | |
1591 | 'url': part_url, | |
1592 | 'title': part_title, | |
1593 | }) | |
1594 | ||
1595 | return { | |
1596 | '_type': 'playlist', | |
1597 | 'entries': entries, | |
1598 | 'title': query, | |
1599 | } | |
1600 | ||
1601 | ||
75dff0ee | 1602 | class YoutubeShowIE(InfoExtractor): |
78caa52a | 1603 | IE_DESC = 'YouTube.com (multi-season) shows' |
cdc628a4 | 1604 | _VALID_URL = r'https?://www\.youtube\.com/show/(?P<id>[^?#]*)' |
78caa52a | 1605 | IE_NAME = 'youtube:show' |
cdc628a4 PH |
1606 | _TESTS = [{ |
1607 | 'url': 'http://www.youtube.com/show/airdisasters', | |
1608 | 'playlist_mincount': 3, | |
1609 | 'info_dict': { | |
1610 | 'id': 'airdisasters', | |
1611 | 'title': 'Air Disasters', | |
1612 | } | |
1613 | }] | |
75dff0ee JMF |
1614 | |
1615 | def _real_extract(self, url): | |
1616 | mobj = re.match(self._VALID_URL, url) | |
cdc628a4 PH |
1617 | playlist_id = mobj.group('id') |
1618 | webpage = self._download_webpage( | |
1619 | url, playlist_id, 'Downloading show webpage') | |
75dff0ee JMF |
1620 | # There's one playlist for each season of the show |
1621 | m_seasons = list(re.finditer(r'href="(/playlist\?list=.*?)"', webpage)) | |
cdc628a4 PH |
1622 | self.to_screen('%s: Found %s seasons' % (playlist_id, len(m_seasons))) |
1623 | entries = [ | |
1624 | self.url_result( | |
1625 | 'https://www.youtube.com' + season.group(1), 'YoutubePlaylist') | |
1626 | for season in m_seasons | |
1627 | ] | |
1628 | title = self._og_search_title(webpage, fatal=False) | |
1629 | ||
1630 | return { | |
1631 | '_type': 'playlist', | |
1632 | 'id': playlist_id, | |
1633 | 'title': title, | |
1634 | 'entries': entries, | |
1635 | } | |
04cc9617 JMF |
1636 | |
1637 | ||
b2e8bc1b | 1638 | class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): |
d7ae0639 | 1639 | """ |
25f14e9f | 1640 | Base class for feed extractors |
d7ae0639 JMF |
1641 | Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties. |
1642 | """ | |
b2e8bc1b | 1643 | _LOGIN_REQUIRED = True |
d7ae0639 JMF |
1644 | |
1645 | @property | |
1646 | def IE_NAME(self): | |
78caa52a | 1647 | return 'youtube:%s' % self._FEED_NAME |
04cc9617 | 1648 | |
81f0259b | 1649 | def _real_initialize(self): |
b2e8bc1b | 1650 | self._login() |
81f0259b | 1651 | |
04cc9617 | 1652 | def _real_extract(self, url): |
25f14e9f S |
1653 | page = self._download_webpage( |
1654 | 'https://www.youtube.com/feed/%s' % self._FEED_NAME, self._PLAYLIST_TITLE) | |
2bc43303 JMF |
1655 | |
1656 | # The extraction process is the same as for playlists, but the regex | |
1657 | # for the video ids doesn't contain an index | |
1658 | ids = [] | |
1659 | more_widget_html = content_html = page | |
2bc43303 JMF |
1660 | for page_num in itertools.count(1): |
1661 | matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html) | |
62c95fd5 S |
1662 | |
1663 | # 'recommended' feed has infinite 'load more' and each new portion spins | |
1664 | # the same videos in (sometimes) slightly different order, so we'll check | |
1665 | # for unicity and break when portion has no new videos | |
1666 | new_ids = filter(lambda video_id: video_id not in ids, orderedSet(matches)) | |
1667 | if not new_ids: | |
1668 | break | |
1669 | ||
2bc43303 JMF |
1670 | ids.extend(new_ids) |
1671 | ||
1672 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) | |
1673 | if not mobj: | |
1674 | break | |
1675 | ||
1676 | more = self._download_json( | |
25f14e9f | 1677 | 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE, |
2bc43303 JMF |
1678 | 'Downloading page #%s' % page_num, |
1679 | transform_source=uppercase_escape) | |
1680 | content_html = more['content_html'] | |
1681 | more_widget_html = more['load_more_widget_html'] | |
1682 | ||
25f14e9f S |
1683 | return self.playlist_result( |
1684 | self._ids_to_results(ids), playlist_title=self._PLAYLIST_TITLE) | |
1685 | ||
1686 | ||
1687 | class YoutubeWatchLaterIE(YoutubePlaylistIE): | |
1688 | IE_NAME = 'youtube:watchlater' | |
1689 | IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' | |
1690 | _VALID_URL = r'https?://www\.youtube\.com/(?:feed/watch_later|playlist\?list=WL)|:ytwatchlater' | |
1691 | ||
1692 | _TESTS = [] # override PlaylistIE tests | |
1693 | ||
1694 | def _real_extract(self, url): | |
1695 | return self._extract_playlist('WL') | |
f459d170 | 1696 | |
5f6a1245 | 1697 | |
c626a3d9 | 1698 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): |
78caa52a | 1699 | IE_NAME = 'youtube:favorites' |
f3a34072 | 1700 | IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)' |
c7a7750d | 1701 | _VALID_URL = r'https?://www\.youtube\.com/my_favorites|:ytfav(?:ou?rites)?' |
c626a3d9 JMF |
1702 | _LOGIN_REQUIRED = True |
1703 | ||
1704 | def _real_extract(self, url): | |
1705 | webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos') | |
78caa52a | 1706 | playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id') |
c626a3d9 | 1707 | return self.url_result(playlist_id, 'YoutubePlaylist') |
15870e90 PH |
1708 | |
1709 | ||
25f14e9f S |
1710 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): |
1711 | IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' | |
1712 | _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?' | |
1713 | _FEED_NAME = 'recommended' | |
1714 | _PLAYLIST_TITLE = 'Youtube Recommended videos' | |
1ed5b5c9 | 1715 | |
1ed5b5c9 | 1716 | |
25f14e9f S |
1717 | class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor): |
1718 | IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' | |
1719 | _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' | |
1720 | _FEED_NAME = 'subscriptions' | |
1721 | _PLAYLIST_TITLE = 'Youtube Subscriptions' | |
1ed5b5c9 | 1722 | |
1ed5b5c9 | 1723 | |
25f14e9f S |
1724 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): |
1725 | IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' | |
1726 | _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory' | |
1727 | _FEED_NAME = 'history' | |
1728 | _PLAYLIST_TITLE = 'Youtube History' | |
1ed5b5c9 JMF |
1729 | |
1730 | ||
15870e90 PH |
1731 | class YoutubeTruncatedURLIE(InfoExtractor): |
1732 | IE_NAME = 'youtube:truncated_url' | |
1733 | IE_DESC = False # Do not list | |
975d35db | 1734 | _VALID_URL = r'''(?x) |
b95aab84 PH |
1735 | (?:https?://)? |
1736 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
1737 | (?:watch\?(?: | |
c4808c60 | 1738 | feature=[a-z_]+| |
b95aab84 PH |
1739 | annotation_id=annotation_[^&]+| |
1740 | x-yt-cl=[0-9]+| | |
c1708b89 | 1741 | hl=[^&]*| |
b95aab84 PH |
1742 | )? |
1743 | | | |
1744 | attribution_link\?a=[^&]+ | |
1745 | ) | |
1746 | $ | |
975d35db | 1747 | ''' |
15870e90 | 1748 | |
c4808c60 PH |
1749 | _TESTS = [{ |
1750 | 'url': 'http://www.youtube.com/watch?annotation_id=annotation_3951667041', | |
1751 | 'only_matching': True, | |
dc2fc736 PH |
1752 | }, { |
1753 | 'url': 'http://www.youtube.com/watch?', | |
1754 | 'only_matching': True, | |
b95aab84 PH |
1755 | }, { |
1756 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
1757 | 'only_matching': True, | |
1758 | }, { | |
1759 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
1760 | 'only_matching': True, | |
c1708b89 PH |
1761 | }, { |
1762 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
1763 | 'only_matching': True, | |
c4808c60 PH |
1764 | }] |
1765 | ||
15870e90 PH |
1766 | def _real_extract(self, url): |
1767 | raise ExtractorError( | |
78caa52a PH |
1768 | 'Did you forget to quote the URL? Remember that & is a meta ' |
1769 | 'character in most shells, so you want to put the URL in quotes, ' | |
1770 | 'like youtube-dl ' | |
1771 | '"http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' | |
1772 | ' or simply youtube-dl BaW_jenozKc .', | |
15870e90 | 1773 | expected=True) |
772fd5cc PH |
1774 | |
1775 | ||
1776 | class YoutubeTruncatedIDIE(InfoExtractor): | |
1777 | IE_NAME = 'youtube:truncated_id' | |
1778 | IE_DESC = False # Do not list | |
b95aab84 | 1779 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' |
772fd5cc PH |
1780 | |
1781 | _TESTS = [{ | |
1782 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
1783 | 'only_matching': True, | |
1784 | }] | |
1785 | ||
1786 | def _real_extract(self, url): | |
1787 | video_id = self._match_id(url) | |
1788 | raise ExtractorError( | |
1789 | 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), | |
1790 | expected=True) |