]>
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 JMF |
51 | |
52 | def _login(self): | |
83317f69 | 53 | """ |
54 | Attempt to log in to YouTube. | |
55 | True is returned if successful or skipped. | |
56 | False is returned if login failed. | |
57 | ||
58 | If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised. | |
59 | """ | |
b2e8bc1b JMF |
60 | (username, password) = self._get_login_info() |
61 | # No authentication to be performed | |
62 | if username is None: | |
63 | if self._LOGIN_REQUIRED: | |
69ea8ca4 | 64 | raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True) |
83317f69 | 65 | return True |
b2e8bc1b | 66 | |
7cc3570e PH |
67 | login_page = self._download_webpage( |
68 | self._LOGIN_URL, None, | |
69ea8ca4 PH |
69 | note='Downloading login page', |
70 | errnote='unable to fetch login page', fatal=False) | |
7cc3570e PH |
71 | if login_page is False: |
72 | return | |
b2e8bc1b | 73 | |
795f28f8 | 74 | galx = self._search_regex(r'(?s)<input.+?name="GALX".+?value="(.+?)"', |
78caa52a | 75 | login_page, 'Login GALX parameter') |
c5e8d7af | 76 | |
b2e8bc1b JMF |
77 | # Log in |
78 | login_form_strs = { | |
8bcc8756 JW |
79 | 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', |
80 | 'Email': username, | |
81 | 'GALX': galx, | |
82 | 'Passwd': password, | |
83 | ||
84 | 'PersistentCookie': 'yes', | |
85 | '_utf8': '霱', | |
86 | 'bgresponse': 'js_disabled', | |
87 | 'checkConnection': '', | |
88 | 'checkedDomains': 'youtube', | |
89 | 'dnConn': '', | |
90 | 'pstMsg': '0', | |
91 | 'rmShown': '1', | |
92 | 'secTok': '', | |
93 | 'signIn': 'Sign in', | |
94 | 'timeStmp': '', | |
95 | 'service': 'youtube', | |
96 | 'uilel': '3', | |
97 | 'hl': 'en_US', | |
b2e8bc1b | 98 | } |
83317f69 | 99 | |
b2e8bc1b JMF |
100 | # Convert to UTF-8 *before* urlencode because Python 2.x's urlencode |
101 | # chokes on unicode | |
5f6a1245 | 102 | login_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in login_form_strs.items()) |
b2e8bc1b | 103 | login_data = compat_urllib_parse.urlencode(login_form).encode('ascii') |
7cc3570e PH |
104 | |
105 | req = compat_urllib_request.Request(self._LOGIN_URL, login_data) | |
106 | login_results = self._download_webpage( | |
107 | req, None, | |
69ea8ca4 | 108 | note='Logging in', errnote='unable to log in', fatal=False) |
7cc3570e PH |
109 | if login_results is False: |
110 | return False | |
83317f69 | 111 | |
112 | if re.search(r'id="errormsg_0_Passwd"', login_results) is not None: | |
69ea8ca4 | 113 | raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True) |
83317f69 | 114 | |
115 | # Two-Factor | |
116 | # TODO add SMS and phone call support - these require making a request and then prompting the user | |
117 | ||
118 | if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', login_results) is not None: | |
119 | tfa_code = self._get_tfa_info() | |
120 | ||
121 | if tfa_code is None: | |
69ea8ca4 PH |
122 | self._downloader.report_warning('Two-factor authentication required. Provide it with --twofactor <code>') |
123 | self._downloader.report_warning('(Note that only TOTP (Google Authenticator App) codes work at this time.)') | |
83317f69 | 124 | return False |
125 | ||
126 | # Unlike the first login form, secTok and timeStmp are both required for the TFA form | |
127 | ||
128 | match = re.search(r'id="secTok"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) | |
129 | if match is None: | |
69ea8ca4 | 130 | self._downloader.report_warning('Failed to get secTok - did the page structure change?') |
83317f69 | 131 | secTok = match.group(1) |
132 | match = re.search(r'id="timeStmp"\n\s+value=\'(.+)\'/>', login_results, re.M | re.U) | |
133 | if match is None: | |
69ea8ca4 | 134 | self._downloader.report_warning('Failed to get timeStmp - did the page structure change?') |
83317f69 | 135 | timeStmp = match.group(1) |
136 | ||
137 | tfa_form_strs = { | |
78caa52a PH |
138 | 'continue': 'https://www.youtube.com/signin?action_handle_signin=true&feature=sign_in_button&hl=en_US&nomobiletemp=1', |
139 | 'smsToken': '', | |
140 | 'smsUserPin': tfa_code, | |
141 | 'smsVerifyPin': 'Verify', | |
142 | ||
143 | 'PersistentCookie': 'yes', | |
144 | 'checkConnection': '', | |
145 | 'checkedDomains': 'youtube', | |
146 | 'pstMsg': '1', | |
147 | 'secTok': secTok, | |
148 | 'timeStmp': timeStmp, | |
149 | 'service': 'youtube', | |
150 | 'hl': 'en_US', | |
83317f69 | 151 | } |
5f6a1245 | 152 | tfa_form = dict((k.encode('utf-8'), v.encode('utf-8')) for k, v in tfa_form_strs.items()) |
83317f69 | 153 | tfa_data = compat_urllib_parse.urlencode(tfa_form).encode('ascii') |
154 | ||
155 | tfa_req = compat_urllib_request.Request(self._TWOFACTOR_URL, tfa_data) | |
156 | tfa_results = self._download_webpage( | |
157 | tfa_req, None, | |
69ea8ca4 | 158 | note='Submitting TFA code', errnote='unable to submit tfa', fatal=False) |
83317f69 | 159 | |
160 | if tfa_results is False: | |
161 | return False | |
162 | ||
163 | if re.search(r'(?i)<form[^>]* id="gaia_secondfactorform"', tfa_results) is not None: | |
69ea8ca4 | 164 | self._downloader.report_warning('Two-factor code expired. Please try again, or use a one-use backup code instead.') |
83317f69 | 165 | return False |
166 | if re.search(r'(?i)<form[^>]* id="gaia_loginform"', tfa_results) is not None: | |
69ea8ca4 | 167 | self._downloader.report_warning('unable to log in - did the page structure change?') |
83317f69 | 168 | return False |
169 | if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None: | |
69ea8ca4 | 170 | 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 | 171 | return False |
172 | ||
7cc3570e | 173 | if re.search(r'(?i)<form[^>]* id="gaia_loginform"', login_results) is not None: |
69ea8ca4 | 174 | self._downloader.report_warning('unable to log in: bad username or password') |
b2e8bc1b JMF |
175 | return False |
176 | return True | |
177 | ||
b2e8bc1b JMF |
178 | def _real_initialize(self): |
179 | if self._downloader is None: | |
180 | return | |
42939b61 | 181 | self._set_language() |
b2e8bc1b JMF |
182 | if not self._login(): |
183 | return | |
c5e8d7af | 184 | |
8377574c | 185 | |
360e1ca5 | 186 | class YoutubeIE(YoutubeBaseInfoExtractor): |
78caa52a | 187 | IE_DESC = 'YouTube.com' |
cb7dfeea | 188 | _VALID_URL = r"""(?x)^ |
c5e8d7af | 189 | ( |
edb53e2d | 190 | (?:https?://|//) # http(s):// or protocol-independent URL |
cb7dfeea | 191 | (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/| |
484aaeb2 | 192 | (?:www\.)?deturl\.com/www\.youtube\.com/| |
e70dc1d1 | 193 | (?:www\.)?pwnyoutube\.com/| |
f7000f3a | 194 | (?:www\.)?yourepeat\.com/| |
e69ae5b9 JMF |
195 | tube\.majestyc\.net/| |
196 | youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains | |
c5e8d7af PH |
197 | (?:.*?\#/)? # handle anchor (#/) redirect urls |
198 | (?: # the various things that can precede the ID: | |
ac7553d0 | 199 | (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/ |
c5e8d7af | 200 | |(?: # or the v= param in all its forms |
f7000f3a | 201 | (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx) |
c5e8d7af PH |
202 | (?:\?|\#!?) # the params delimiter ? or # or #! |
203 | (?:.*?&)? # any other preceding param (like /?s=tuff&v=xxxx) | |
204 | v= | |
205 | ) | |
f4b05232 JMF |
206 | )) |
207 | |youtu\.be/ # just youtu.be/xxxx | |
edb53e2d | 208 | |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId= |
f4b05232 | 209 | ) |
c5e8d7af | 210 | )? # all until now is optional -> you can pass the naked ID |
8963d9c2 | 211 | ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID |
9291475f | 212 | (?!.*?&list=) # combined list/video URLs are handled by the playlist IE |
c5e8d7af PH |
213 | (?(1).+)? # if we found the ID, everything can follow |
214 | $""" | |
c5e8d7af | 215 | _NEXT_URL_RE = r'[\?&]next_url=([^&]+)' |
2c62dc26 PH |
216 | _formats = { |
217 | '5': {'ext': 'flv', 'width': 400, 'height': 240}, | |
218 | '6': {'ext': 'flv', 'width': 450, 'height': 270}, | |
219 | '13': {'ext': '3gp'}, | |
220 | '17': {'ext': '3gp', 'width': 176, 'height': 144}, | |
221 | '18': {'ext': 'mp4', 'width': 640, 'height': 360}, | |
222 | '22': {'ext': 'mp4', 'width': 1280, 'height': 720}, | |
223 | '34': {'ext': 'flv', 'width': 640, 'height': 360}, | |
224 | '35': {'ext': 'flv', 'width': 854, 'height': 480}, | |
225 | '36': {'ext': '3gp', 'width': 320, 'height': 240}, | |
226 | '37': {'ext': 'mp4', 'width': 1920, 'height': 1080}, | |
227 | '38': {'ext': 'mp4', 'width': 4096, 'height': 3072}, | |
228 | '43': {'ext': 'webm', 'width': 640, 'height': 360}, | |
229 | '44': {'ext': 'webm', 'width': 854, 'height': 480}, | |
230 | '45': {'ext': 'webm', 'width': 1280, 'height': 720}, | |
231 | '46': {'ext': 'webm', 'width': 1920, 'height': 1080}, | |
232 | ||
1d043b93 | 233 | |
86fe61c8 | 234 | # 3d videos |
43b81eb9 PH |
235 | '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'preference': -20}, |
236 | '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'preference': -20}, | |
237 | '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'preference': -20}, | |
238 | '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'preference': -20}, | |
239 | '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'preference': -20}, | |
240 | '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'preference': -20}, | |
241 | '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'preference': -20}, | |
836a086c | 242 | |
96fb5605 | 243 | # Apple HTTP Live Streaming |
43b81eb9 PH |
244 | '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'preference': -10}, |
245 | '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'preference': -10}, | |
246 | '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'preference': -10}, | |
247 | '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'preference': -10}, | |
248 | '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'preference': -10}, | |
249 | '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'preference': -10}, | |
250 | '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'preference': -10}, | |
2c62dc26 PH |
251 | |
252 | # DASH mp4 video | |
43b81eb9 PH |
253 | '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
254 | '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
255 | '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
256 | '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
257 | '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
e65566a9 | 258 | '138': {'ext': 'mp4', 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559) |
43b81eb9 PH |
259 | '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
260 | '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
0d2c1418 PH |
261 | '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'}, |
262 | '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'h264'}, | |
263 | '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'h264'}, | |
836a086c | 264 | |
f6f1fc92 | 265 | # Dash mp4 audio |
62cd676c PH |
266 | '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'}, |
267 | '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'}, | |
268 | '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'vcodec': 'none', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'}, | |
836a086c AZ |
269 | |
270 | # Dash webm | |
e75cafe9 A |
271 | '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, |
272 | '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
273 | '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
274 | '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
275 | '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
276 | '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'acodec': 'none', 'container': 'webm', 'vcodec': 'VP8', 'preference': -40}, | |
1cc887cb | 277 | '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'container': 'webm', 'vcodec': 'VP9'}, |
e75cafe9 A |
278 | '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
279 | '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
280 | '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
281 | '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
282 | '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
283 | '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
284 | '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, | |
3c80377b | 285 | '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
18061bba | 286 | '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40}, |
a51d3aa0 PH |
287 | '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, |
288 | '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, | |
76b3c610 | 289 | '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, |
10a404c3 | 290 | '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'vcodec': 'VP9'}, |
76b3c610 | 291 | '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'acodec': 'none', 'preference': -40, 'fps': 60, 'vcodec': 'VP9'}, |
2c62dc26 PH |
292 | |
293 | # Dash webm audio | |
55db73ef | 294 | '171': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50}, |
e75cafe9 | 295 | '172': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50}, |
ce6b9a2d | 296 | |
0857baad PH |
297 | # Dash webm audio with opus inside |
298 | '249': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50}, | |
299 | '250': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50}, | |
300 | '251': {'ext': 'webm', 'vcodec': 'none', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50}, | |
301 | ||
ce6b9a2d PH |
302 | # RTMP (unnamed) |
303 | '_rtmp': {'protocol': 'rtmp'}, | |
c5e8d7af | 304 | } |
836a086c | 305 | |
78caa52a | 306 | IE_NAME = 'youtube' |
2eb88d95 PH |
307 | _TESTS = [ |
308 | { | |
4bc3a23e PH |
309 | 'url': 'http://www.youtube.com/watch?v=BaW_jenozKc', |
310 | 'info_dict': { | |
311 | 'id': 'BaW_jenozKc', | |
312 | 'ext': 'mp4', | |
313 | 'title': 'youtube-dl test video "\'/\\ä↭𝕐', | |
314 | 'uploader': 'Philipp Hagemeister', | |
315 | 'uploader_id': 'phihag', | |
316 | 'upload_date': '20121002', | |
317 | '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 .', | |
318 | 'categories': ['Science & Technology'], | |
3e7c1224 PH |
319 | 'like_count': int, |
320 | 'dislike_count': int, | |
2eb88d95 | 321 | } |
0e853ca4 | 322 | }, |
0e853ca4 | 323 | { |
4bc3a23e PH |
324 | 'url': 'http://www.youtube.com/watch?v=UxxajLWwzqY', |
325 | 'note': 'Test generic use_cipher_signature video (#897)', | |
326 | 'info_dict': { | |
327 | 'id': 'UxxajLWwzqY', | |
328 | 'ext': 'mp4', | |
329 | 'upload_date': '20120506', | |
330 | 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]', | |
331 | 'description': 'md5:fea86fda2d5a5784273df5c7cc994d9f', | |
332 | 'uploader': 'Icona Pop', | |
333 | 'uploader_id': 'IconaPop', | |
2eb88d95 | 334 | } |
c108eb73 JMF |
335 | }, |
336 | { | |
4bc3a23e PH |
337 | 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ', |
338 | 'note': 'Test VEVO video with age protection (#956)', | |
339 | 'info_dict': { | |
340 | 'id': '07FYdnEawAQ', | |
341 | 'ext': 'mp4', | |
342 | 'upload_date': '20130703', | |
343 | 'title': 'Justin Timberlake - Tunnel Vision (Explicit)', | |
344 | 'description': 'md5:64249768eec3bc4276236606ea996373', | |
345 | 'uploader': 'justintimberlakeVEVO', | |
346 | 'uploader_id': 'justintimberlakeVEVO', | |
c108eb73 JMF |
347 | } |
348 | }, | |
fccd3771 | 349 | { |
4bc3a23e PH |
350 | 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ', |
351 | 'note': 'Embed-only video (#1746)', | |
352 | 'info_dict': { | |
353 | 'id': 'yZIXLfi8CZQ', | |
354 | 'ext': 'mp4', | |
355 | 'upload_date': '20120608', | |
356 | 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012', | |
357 | 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7', | |
358 | 'uploader': 'SET India', | |
359 | 'uploader_id': 'setindia' | |
fccd3771 PH |
360 | } |
361 | }, | |
dd27fd17 | 362 | { |
4bc3a23e PH |
363 | 'url': 'http://www.youtube.com/watch?v=a9LDPn-MO4I', |
364 | 'note': '256k DASH audio (format 141) via DASH manifest', | |
365 | 'info_dict': { | |
366 | 'id': 'a9LDPn-MO4I', | |
367 | 'ext': 'm4a', | |
368 | 'upload_date': '20121002', | |
369 | 'uploader_id': '8KVIDEO', | |
370 | 'description': '', | |
371 | 'uploader': '8KVIDEO', | |
372 | 'title': 'UHDTV TEST 8K VIDEO.mp4' | |
4919603f | 373 | }, |
4bc3a23e PH |
374 | 'params': { |
375 | 'youtube_include_dash_manifest': True, | |
376 | 'format': '141', | |
4919603f | 377 | }, |
dd27fd17 | 378 | }, |
3489b7d2 JMF |
379 | # DASH manifest with encrypted signature |
380 | { | |
78caa52a PH |
381 | 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA', |
382 | 'info_dict': { | |
383 | 'id': 'IB3lcPjvWLA', | |
384 | 'ext': 'm4a', | |
b766eb27 JMF |
385 | 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson', |
386 | 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d', | |
78caa52a PH |
387 | 'uploader': 'AfrojackVEVO', |
388 | 'uploader_id': 'AfrojackVEVO', | |
389 | 'upload_date': '20131011', | |
3489b7d2 | 390 | }, |
4bc3a23e | 391 | 'params': { |
78caa52a PH |
392 | 'youtube_include_dash_manifest': True, |
393 | 'format': '141', | |
3489b7d2 JMF |
394 | }, |
395 | }, | |
aaeb86f6 S |
396 | # JS player signature function name containing $ |
397 | { | |
398 | 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM', | |
399 | 'info_dict': { | |
400 | 'id': 'nfWlot6h_JM', | |
401 | 'ext': 'm4a', | |
402 | 'title': 'Taylor Swift - Shake It Off', | |
403 | 'description': 'md5:2acfda1b285bdd478ccec22f9918199d', | |
404 | 'uploader': 'TaylorSwiftVEVO', | |
405 | 'uploader_id': 'TaylorSwiftVEVO', | |
406 | 'upload_date': '20140818', | |
407 | }, | |
408 | 'params': { | |
409 | 'youtube_include_dash_manifest': True, | |
410 | 'format': '141', | |
411 | }, | |
412 | }, | |
aa79ac0c PH |
413 | # Controversy video |
414 | { | |
415 | 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8', | |
416 | 'info_dict': { | |
417 | 'id': 'T4XJQO3qol8', | |
418 | 'ext': 'mp4', | |
419 | 'upload_date': '20100909', | |
420 | 'uploader': 'The Amazing Atheist', | |
421 | 'uploader_id': 'TheAmazingAtheist', | |
422 | 'title': 'Burning Everyone\'s Koran', | |
423 | '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', | |
424 | } | |
c522adb1 JMF |
425 | }, |
426 | # Normal age-gate video (No vevo, embed allowed) | |
427 | { | |
428 | 'url': 'http://youtube.com/watch?v=HtVdAasjOgU', | |
429 | 'info_dict': { | |
430 | 'id': 'HtVdAasjOgU', | |
431 | 'ext': 'mp4', | |
432 | 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer', | |
9ed99402 | 433 | 'description': 're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}', |
c522adb1 JMF |
434 | 'uploader': 'The Witcher', |
435 | 'uploader_id': 'WitcherGame', | |
436 | 'upload_date': '20140605', | |
437 | }, | |
438 | }, | |
fccae2b9 S |
439 | # Age-gate video with encrypted signature |
440 | { | |
441 | 'url': 'http://www.youtube.com/watch?v=6kLq3WMV1nU', | |
442 | 'info_dict': { | |
443 | 'id': '6kLq3WMV1nU', | |
444 | 'ext': 'mp4', | |
445 | 'title': 'Dedication To My Ex (Miss That) (Lyric Video)', | |
446 | 'description': 'md5:33765bb339e1b47e7e72b5490139bb41', | |
447 | 'uploader': 'LloydVEVO', | |
448 | 'uploader_id': 'LloydVEVO', | |
449 | 'upload_date': '20110629', | |
450 | }, | |
451 | }, | |
774e208f PH |
452 | # video_info is None (https://github.com/rg3/youtube-dl/issues/4421) |
453 | { | |
454 | 'url': '__2ABJjxzNo', | |
455 | 'info_dict': { | |
456 | 'id': '__2ABJjxzNo', | |
457 | 'ext': 'mp4', | |
458 | 'upload_date': '20100430', | |
459 | 'uploader_id': 'deadmau5', | |
460 | 'description': 'md5:12c56784b8032162bb936a5f76d55360', | |
461 | 'uploader': 'deadmau5', | |
462 | 'title': 'Deadmau5 - Some Chords (HD)', | |
463 | }, | |
464 | 'expected_warnings': [ | |
465 | 'DASH manifest missing', | |
466 | ] | |
e52a40ab PH |
467 | }, |
468 | # Olympics (https://github.com/rg3/youtube-dl/issues/4431) | |
469 | { | |
470 | 'url': 'lqQg6PlCWgI', | |
471 | 'info_dict': { | |
472 | 'id': 'lqQg6PlCWgI', | |
473 | 'ext': 'mp4', | |
cbe2bd91 PH |
474 | 'upload_date': '20120731', |
475 | 'uploader_id': 'olympic', | |
476 | 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games', | |
477 | 'uploader': 'Olympics', | |
478 | 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games', | |
479 | }, | |
480 | 'params': { | |
481 | 'skip_download': 'requires avconv', | |
e52a40ab | 482 | } |
cbe2bd91 | 483 | }, |
6271f1ca PH |
484 | # Non-square pixels |
485 | { | |
486 | 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0', | |
487 | 'info_dict': { | |
488 | 'id': '_b-2C3KPAM0', | |
489 | 'ext': 'mp4', | |
490 | 'stretched_ratio': 16 / 9., | |
491 | 'upload_date': '20110310', | |
492 | 'uploader_id': 'AllenMeow', | |
493 | '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', | |
494 | 'uploader': '孫艾倫', | |
495 | 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人', | |
496 | }, | |
06b491eb S |
497 | }, |
498 | # url_encoded_fmt_stream_map is empty string | |
499 | { | |
500 | 'url': 'qEJwOuvDf7I', | |
501 | 'info_dict': { | |
502 | 'id': 'qEJwOuvDf7I', | |
503 | 'ext': 'mp4', | |
504 | 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге', | |
505 | 'description': '', | |
506 | 'upload_date': '20150404', | |
507 | 'uploader_id': 'spbelect', | |
508 | 'uploader': 'Наблюдатели Петербурга', | |
509 | }, | |
510 | 'params': { | |
511 | 'skip_download': 'requires avconv', | |
512 | } | |
513 | }, | |
2eb88d95 PH |
514 | ] |
515 | ||
e0df6211 PH |
516 | def __init__(self, *args, **kwargs): |
517 | super(YoutubeIE, self).__init__(*args, **kwargs) | |
83799698 | 518 | self._player_cache = {} |
e0df6211 | 519 | |
c5e8d7af PH |
520 | def report_video_info_webpage_download(self, video_id): |
521 | """Report attempt to download video info webpage.""" | |
69ea8ca4 | 522 | self.to_screen('%s: Downloading video info webpage' % video_id) |
c5e8d7af | 523 | |
c5e8d7af PH |
524 | def report_information_extraction(self, video_id): |
525 | """Report attempt to extract video information.""" | |
69ea8ca4 | 526 | self.to_screen('%s: Extracting video information' % video_id) |
c5e8d7af PH |
527 | |
528 | def report_unavailable_format(self, video_id, format): | |
529 | """Report extracted video URL.""" | |
69ea8ca4 | 530 | self.to_screen('%s: Format %s not available' % (video_id, format)) |
c5e8d7af PH |
531 | |
532 | def report_rtmp_download(self): | |
533 | """Indicate the download will use the RTMP protocol.""" | |
69ea8ca4 | 534 | self.to_screen('RTMP download detected') |
c5e8d7af | 535 | |
60064c53 PH |
536 | def _signature_cache_id(self, example_sig): |
537 | """ Return a string representation of a signature """ | |
78caa52a | 538 | return '.'.join(compat_str(len(part)) for part in example_sig.split('.')) |
60064c53 PH |
539 | |
540 | def _extract_signature_function(self, video_id, player_url, example_sig): | |
cf010131 | 541 | id_m = re.match( |
60620368 | 542 | r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player)?\.(?P<ext>[a-z]+)$', |
cf010131 | 543 | player_url) |
c081b35c PH |
544 | if not id_m: |
545 | raise ExtractorError('Cannot identify player %r' % player_url) | |
e0df6211 PH |
546 | player_type = id_m.group('ext') |
547 | player_id = id_m.group('id') | |
548 | ||
c4417ddb | 549 | # Read from filesystem cache |
60064c53 PH |
550 | func_id = '%s_%s_%s' % ( |
551 | player_type, player_id, self._signature_cache_id(example_sig)) | |
c4417ddb | 552 | assert os.path.basename(func_id) == func_id |
a0e07d31 | 553 | |
69ea8ca4 | 554 | cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id) |
a0e07d31 | 555 | if cache_spec is not None: |
78caa52a | 556 | return lambda s: ''.join(s[i] for i in cache_spec) |
83799698 | 557 | |
6d1a55a5 PH |
558 | download_note = ( |
559 | 'Downloading player %s' % player_url | |
560 | if self._downloader.params.get('verbose') else | |
561 | 'Downloading %s player %s' % (player_type, player_id) | |
562 | ) | |
e0df6211 PH |
563 | if player_type == 'js': |
564 | code = self._download_webpage( | |
565 | player_url, video_id, | |
6d1a55a5 | 566 | note=download_note, |
69ea8ca4 | 567 | errnote='Download of %s failed' % player_url) |
83799698 | 568 | res = self._parse_sig_js(code) |
c4417ddb | 569 | elif player_type == 'swf': |
e0df6211 PH |
570 | urlh = self._request_webpage( |
571 | player_url, video_id, | |
6d1a55a5 | 572 | note=download_note, |
69ea8ca4 | 573 | errnote='Download of %s failed' % player_url) |
e0df6211 | 574 | code = urlh.read() |
83799698 | 575 | res = self._parse_sig_swf(code) |
e0df6211 PH |
576 | else: |
577 | assert False, 'Invalid player type %r' % player_type | |
578 | ||
785521bf PH |
579 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
580 | cache_res = res(test_string) | |
581 | cache_spec = [ord(c) for c in cache_res] | |
83799698 | 582 | |
69ea8ca4 | 583 | self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec) |
83799698 PH |
584 | return res |
585 | ||
60064c53 | 586 | def _print_sig_code(self, func, example_sig): |
edf3e38e PH |
587 | def gen_sig_code(idxs): |
588 | def _genslice(start, end, step): | |
78caa52a | 589 | starts = '' if start == 0 else str(start) |
8bcc8756 | 590 | ends = (':%d' % (end + step)) if end + step >= 0 else ':' |
69ea8ca4 | 591 | steps = '' if step == 1 else (':%d' % step) |
78caa52a | 592 | return 's[%s%s%s]' % (starts, ends, steps) |
edf3e38e PH |
593 | |
594 | step = None | |
7af808a5 PH |
595 | # Quelch pyflakes warnings - start will be set when step is set |
596 | start = '(Never used)' | |
edf3e38e PH |
597 | for i, prev in zip(idxs[1:], idxs[:-1]): |
598 | if step is not None: | |
599 | if i - prev == step: | |
600 | continue | |
601 | yield _genslice(start, prev, step) | |
602 | step = None | |
603 | continue | |
604 | if i - prev in [-1, 1]: | |
605 | step = i - prev | |
606 | start = prev | |
607 | continue | |
608 | else: | |
78caa52a | 609 | yield 's[%d]' % prev |
edf3e38e | 610 | if step is None: |
78caa52a | 611 | yield 's[%d]' % i |
edf3e38e PH |
612 | else: |
613 | yield _genslice(start, i, step) | |
614 | ||
78caa52a | 615 | test_string = ''.join(map(compat_chr, range(len(example_sig)))) |
c705320f | 616 | cache_res = func(test_string) |
edf3e38e | 617 | cache_spec = [ord(c) for c in cache_res] |
78caa52a | 618 | expr_code = ' + '.join(gen_sig_code(cache_spec)) |
60064c53 PH |
619 | signature_id_tuple = '(%s)' % ( |
620 | ', '.join(compat_str(len(p)) for p in example_sig.split('.'))) | |
69ea8ca4 | 621 | code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n' |
78caa52a | 622 | ' return %s\n') % (signature_id_tuple, expr_code) |
69ea8ca4 | 623 | self.to_screen('Extracted signature function:\n' + code) |
edf3e38e | 624 | |
e0df6211 PH |
625 | def _parse_sig_js(self, jscode): |
626 | funcname = self._search_regex( | |
aaeb86f6 | 627 | r'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode, |
8bcc8756 | 628 | 'Initial JS player signature function name') |
2b25cb5d PH |
629 | |
630 | jsi = JSInterpreter(jscode) | |
631 | initial_function = jsi.extract_function(funcname) | |
e0df6211 PH |
632 | return lambda s: initial_function([s]) |
633 | ||
634 | def _parse_sig_swf(self, file_contents): | |
54256267 | 635 | swfi = SWFInterpreter(file_contents) |
78caa52a | 636 | TARGET_CLASSNAME = 'SignatureDecipher' |
54256267 | 637 | searched_class = swfi.extract_class(TARGET_CLASSNAME) |
78caa52a | 638 | initial_function = swfi.extract_function(searched_class, 'decipher') |
e0df6211 PH |
639 | return lambda s: initial_function([s]) |
640 | ||
83799698 | 641 | def _decrypt_signature(self, s, video_id, player_url, age_gate=False): |
257a2501 | 642 | """Turn the encrypted s field into a working signature""" |
6b37f0be | 643 | |
c8bf86d5 | 644 | if player_url is None: |
69ea8ca4 | 645 | raise ExtractorError('Cannot decrypt signature without player_url') |
920de7a2 | 646 | |
69ea8ca4 | 647 | if player_url.startswith('//'): |
78caa52a | 648 | player_url = 'https:' + player_url |
c8bf86d5 | 649 | try: |
62af3a0e | 650 | player_id = (player_url, self._signature_cache_id(s)) |
c8bf86d5 PH |
651 | if player_id not in self._player_cache: |
652 | func = self._extract_signature_function( | |
60064c53 | 653 | video_id, player_url, s |
c8bf86d5 PH |
654 | ) |
655 | self._player_cache[player_id] = func | |
656 | func = self._player_cache[player_id] | |
657 | if self._downloader.params.get('youtube_print_sig_code'): | |
60064c53 | 658 | self._print_sig_code(func, s) |
c8bf86d5 PH |
659 | return func(s) |
660 | except Exception as e: | |
661 | tb = traceback.format_exc() | |
662 | raise ExtractorError( | |
78caa52a | 663 | 'Signature extraction failed: ' + tb, cause=e) |
e0df6211 | 664 | |
360e1ca5 | 665 | def _get_subtitles(self, video_id, webpage): |
de7f3446 | 666 | try: |
60e47a26 | 667 | subs_doc = self._download_xml( |
38c2e5b8 | 668 | 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id, |
7fad1c63 JMF |
669 | video_id, note=False) |
670 | except ExtractorError as err: | |
69ea8ca4 | 671 | self._downloader.report_warning('unable to download video subtitles: %s' % compat_str(err)) |
de7f3446 | 672 | return {} |
de7f3446 JMF |
673 | |
674 | sub_lang_list = {} | |
60e47a26 JMF |
675 | for track in subs_doc.findall('track'): |
676 | lang = track.attrib['lang_code'] | |
7e660ac1 LD |
677 | if lang in sub_lang_list: |
678 | continue | |
360e1ca5 JMF |
679 | sub_formats = [] |
680 | for ext in ['sbv', 'vtt', 'srt']: | |
681 | params = compat_urllib_parse.urlencode({ | |
682 | 'lang': lang, | |
683 | 'v': video_id, | |
684 | 'fmt': ext, | |
685 | 'name': track.attrib['name'].encode('utf-8'), | |
686 | }) | |
687 | sub_formats.append({ | |
688 | 'url': 'https://www.youtube.com/api/timedtext?' + params, | |
689 | 'ext': ext, | |
690 | }) | |
691 | sub_lang_list[lang] = sub_formats | |
de7f3446 | 692 | if not sub_lang_list: |
69ea8ca4 | 693 | self._downloader.report_warning('video doesn\'t have subtitles') |
de7f3446 JMF |
694 | return {} |
695 | return sub_lang_list | |
696 | ||
360e1ca5 | 697 | def _get_automatic_captions(self, video_id, webpage): |
de7f3446 JMF |
698 | """We need the webpage for getting the captions url, pass it as an |
699 | argument to speed up the process.""" | |
69ea8ca4 | 700 | self.to_screen('%s: Looking for automatic captions' % video_id) |
de7f3446 | 701 | mobj = re.search(r';ytplayer.config = ({.*?});', webpage) |
78caa52a | 702 | err_msg = 'Couldn\'t find automatic captions for %s' % video_id |
de7f3446 JMF |
703 | if mobj is None: |
704 | self._downloader.report_warning(err_msg) | |
705 | return {} | |
706 | player_config = json.loads(mobj.group(1)) | |
707 | try: | |
0792d563 PH |
708 | args = player_config['args'] |
709 | caption_url = args['ttsurl'] | |
710 | timestamp = args['timestamp'] | |
055e6f36 JMF |
711 | # We get the available subtitles |
712 | list_params = compat_urllib_parse.urlencode({ | |
713 | 'type': 'list', | |
714 | 'tlangs': 1, | |
715 | 'asrs': 1, | |
de7f3446 | 716 | }) |
055e6f36 | 717 | list_url = caption_url + '&' + list_params |
e26f8712 | 718 | caption_list = self._download_xml(list_url, video_id) |
e3dc22ca | 719 | original_lang_node = caption_list.find('track') |
7d900ef1 | 720 | if original_lang_node is None: |
69ea8ca4 | 721 | self._downloader.report_warning('Video doesn\'t have automatic captions') |
e3dc22ca JMF |
722 | return {} |
723 | original_lang = original_lang_node.attrib['lang_code'] | |
7d900ef1 | 724 | caption_kind = original_lang_node.attrib.get('kind', '') |
055e6f36 JMF |
725 | |
726 | sub_lang_list = {} | |
727 | for lang_node in caption_list.findall('target'): | |
728 | sub_lang = lang_node.attrib['lang_code'] | |
360e1ca5 JMF |
729 | sub_formats = [] |
730 | for ext in ['sbv', 'vtt', 'srt']: | |
731 | params = compat_urllib_parse.urlencode({ | |
732 | 'lang': original_lang, | |
733 | 'tlang': sub_lang, | |
734 | 'fmt': ext, | |
735 | 'ts': timestamp, | |
736 | 'kind': caption_kind, | |
737 | }) | |
738 | sub_formats.append({ | |
739 | 'url': caption_url + '&' + params, | |
740 | 'ext': ext, | |
741 | }) | |
742 | sub_lang_list[sub_lang] = sub_formats | |
055e6f36 | 743 | return sub_lang_list |
de7f3446 JMF |
744 | # An extractor error can be raise by the download process if there are |
745 | # no automatic captions but there are subtitles | |
746 | except (KeyError, ExtractorError): | |
747 | self._downloader.report_warning(err_msg) | |
748 | return {} | |
749 | ||
97665381 PH |
750 | @classmethod |
751 | def extract_id(cls, url): | |
752 | mobj = re.match(cls._VALID_URL, url, re.VERBOSE) | |
c5e8d7af | 753 | if mobj is None: |
69ea8ca4 | 754 | raise ExtractorError('Invalid URL: %s' % url) |
c5e8d7af PH |
755 | video_id = mobj.group(2) |
756 | return video_id | |
757 | ||
1d043b93 JMF |
758 | def _extract_from_m3u8(self, manifest_url, video_id): |
759 | url_map = {} | |
5f6a1245 | 760 | |
1d043b93 JMF |
761 | def _get_urls(_manifest): |
762 | lines = _manifest.split('\n') | |
763 | urls = filter(lambda l: l and not l.startswith('#'), | |
8bcc8756 | 764 | lines) |
1d043b93 | 765 | return urls |
78caa52a | 766 | manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest') |
1d043b93 JMF |
767 | formats_urls = _get_urls(manifest) |
768 | for format_url in formats_urls: | |
890f62e8 | 769 | itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag') |
1d043b93 JMF |
770 | url_map[itag] = format_url |
771 | return url_map | |
772 | ||
1fb07d10 JG |
773 | def _extract_annotations(self, video_id): |
774 | url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id | |
69ea8ca4 | 775 | return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.') |
1fb07d10 | 776 | |
da276600 PH |
777 | def _parse_dash_manifest( |
778 | self, video_id, dash_manifest_url, player_url, age_gate): | |
774e208f PH |
779 | def decrypt_sig(mobj): |
780 | s = mobj.group(1) | |
781 | dec_s = self._decrypt_signature(s, video_id, player_url, age_gate) | |
782 | return '/signature/%s' % dec_s | |
783 | dash_manifest_url = re.sub(r'/s/([\w\.]+)', decrypt_sig, dash_manifest_url) | |
784 | dash_doc = self._download_xml( | |
785 | dash_manifest_url, video_id, | |
786 | note='Downloading DASH manifest', | |
787 | errnote='Could not download DASH manifest') | |
788 | ||
789 | formats = [] | |
de5c5456 YCH |
790 | for a in dash_doc.findall('.//{urn:mpeg:DASH:schema:MPD:2011}AdaptationSet'): |
791 | mime_type = a.attrib.get('mimeType') | |
792 | for r in a.findall('{urn:mpeg:DASH:schema:MPD:2011}Representation'): | |
793 | url_el = r.find('{urn:mpeg:DASH:schema:MPD:2011}BaseURL') | |
794 | if url_el is None: | |
795 | continue | |
796 | if mime_type == 'text/vtt': | |
797 | # TODO implement WebVTT downloading | |
798 | pass | |
799 | elif mime_type.startswith('audio/') or mime_type.startswith('video/'): | |
800 | format_id = r.attrib['id'] | |
801 | video_url = url_el.text | |
802 | filesize = int_or_none(url_el.attrib.get('{http://youtube.com/yt/2012/10/10}contentLength')) | |
803 | f = { | |
804 | 'format_id': format_id, | |
805 | 'url': video_url, | |
806 | 'width': int_or_none(r.attrib.get('width')), | |
807 | 'height': int_or_none(r.attrib.get('height')), | |
808 | 'tbr': int_or_none(r.attrib.get('bandwidth'), 1000), | |
809 | 'asr': int_or_none(r.attrib.get('audioSamplingRate')), | |
810 | 'filesize': filesize, | |
811 | 'fps': int_or_none(r.attrib.get('frameRate')), | |
812 | } | |
813 | try: | |
814 | existing_format = next( | |
815 | fo for fo in formats | |
816 | if fo['format_id'] == format_id) | |
817 | except StopIteration: | |
818 | full_info = self._formats.get(format_id, {}).copy() | |
819 | full_info.update(f) | |
820 | formats.append(full_info) | |
821 | else: | |
822 | existing_format.update(f) | |
823 | else: | |
824 | self.report_warning('Unknown MIME type %s in DASH manifest' % mime_type) | |
774e208f PH |
825 | return formats |
826 | ||
c5e8d7af | 827 | def _real_extract(self, url): |
7e8c0af0 | 828 | proto = ( |
78caa52a PH |
829 | 'http' if self._downloader.params.get('prefer_insecure', False) |
830 | else 'https') | |
7e8c0af0 | 831 | |
c5e8d7af PH |
832 | # Extract original video URL from URL with redirection, like age verification, using next_url parameter |
833 | mobj = re.search(self._NEXT_URL_RE, url) | |
834 | if mobj: | |
7e8c0af0 | 835 | url = proto + '://www.youtube.com/' + compat_urllib_parse.unquote(mobj.group(1)).lstrip('/') |
97665381 | 836 | video_id = self.extract_id(url) |
c5e8d7af PH |
837 | |
838 | # Get video webpage | |
aa79ac0c | 839 | url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id |
a1f934b1 | 840 | video_webpage = self._download_webpage(url, video_id) |
c5e8d7af PH |
841 | |
842 | # Attempt to extract SWF player URL | |
e0df6211 | 843 | mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage) |
c5e8d7af PH |
844 | if mobj is not None: |
845 | player_url = re.sub(r'\\(.)', r'\1', mobj.group(1)) | |
846 | else: | |
847 | player_url = None | |
848 | ||
849 | # Get video info | |
6449cd80 | 850 | embed_webpage = None |
c108eb73 | 851 | if re.search(r'player-age-gate-content">', video_webpage) is not None: |
c108eb73 JMF |
852 | age_gate = True |
853 | # We simulate the access to the video from www.youtube.com/v/{video_id} | |
854 | # this can be viewed without login into Youtube | |
beb95e77 CL |
855 | url = proto + '://www.youtube.com/embed/%s' % video_id |
856 | embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage') | |
2c57c7fa JMF |
857 | data = compat_urllib_parse.urlencode({ |
858 | 'video_id': video_id, | |
859 | 'eurl': 'https://youtube.googleapis.com/v/' + video_id, | |
c084c934 | 860 | 'sts': self._search_regex( |
beb95e77 | 861 | r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''), |
2c57c7fa | 862 | }) |
7e8c0af0 | 863 | video_info_url = proto + '://www.youtube.com/get_video_info?' + data |
94bd3613 PH |
864 | video_info_webpage = self._download_webpage( |
865 | video_info_url, video_id, | |
20436c30 | 866 | note='Refetching age-gated info webpage', |
94bd3613 | 867 | errnote='unable to download video info webpage') |
c5e8d7af | 868 | video_info = compat_parse_qs(video_info_webpage) |
c108eb73 JMF |
869 | else: |
870 | age_gate = False | |
4e62ebe2 JMF |
871 | try: |
872 | # Try looking directly into the video webpage | |
873 | mobj = re.search(r';ytplayer\.config\s*=\s*({.*?});', video_webpage) | |
874 | if not mobj: | |
875 | raise ValueError('Could not find ytplayer.config') # caught below | |
876 | json_code = uppercase_escape(mobj.group(1)) | |
877 | ytplayer_config = json.loads(json_code) | |
878 | args = ytplayer_config['args'] | |
879 | # Convert to the same format returned by compat_parse_qs | |
880 | video_info = dict((k, [v]) for k, v in args.items()) | |
e40bd5f0 | 881 | if not args.get('url_encoded_fmt_stream_map'): |
4e62ebe2 JMF |
882 | raise ValueError('No stream_map present') # caught below |
883 | except ValueError: | |
884 | # We fallback to the get_video_info pages (used by the embed page) | |
885 | self.report_video_info_webpage_download(video_id) | |
886 | for el_type in ['&el=embedded', '&el=detailpage', '&el=vevo', '']: | |
810fb84d PH |
887 | video_info_url = ( |
888 | '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en' | |
889 | % (proto, video_id, el_type)) | |
890 | video_info_webpage = self._download_webpage( | |
891 | video_info_url, | |
4e62ebe2 JMF |
892 | video_id, note=False, |
893 | errnote='unable to download video info webpage') | |
894 | video_info = compat_parse_qs(video_info_webpage) | |
895 | if 'token' in video_info: | |
896 | break | |
c5e8d7af PH |
897 | if 'token' not in video_info: |
898 | if 'reason' in video_info: | |
d11271dd | 899 | raise ExtractorError( |
78caa52a | 900 | 'YouTube said: %s' % video_info['reason'][0], |
d11271dd | 901 | expected=True, video_id=video_id) |
c5e8d7af | 902 | else: |
d11271dd | 903 | raise ExtractorError( |
78caa52a | 904 | '"token" parameter not in video info for unknown reason', |
d11271dd | 905 | video_id=video_id) |
c5e8d7af | 906 | |
1d699755 PH |
907 | if 'view_count' in video_info: |
908 | view_count = int(video_info['view_count'][0]) | |
909 | else: | |
910 | view_count = None | |
911 | ||
c5e8d7af PH |
912 | # Check for "rental" videos |
913 | if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info: | |
69ea8ca4 | 914 | raise ExtractorError('"rental" videos not supported') |
c5e8d7af PH |
915 | |
916 | # Start extracting information | |
917 | self.report_information_extraction(video_id) | |
918 | ||
919 | # uploader | |
920 | if 'author' not in video_info: | |
69ea8ca4 | 921 | raise ExtractorError('Unable to extract uploader name') |
c5e8d7af PH |
922 | video_uploader = compat_urllib_parse.unquote_plus(video_info['author'][0]) |
923 | ||
924 | # uploader_id | |
925 | video_uploader_id = None | |
926 | mobj = re.search(r'<link itemprop="url" href="http://www.youtube.com/(?:user|channel)/([^"]+)">', video_webpage) | |
927 | if mobj is not None: | |
928 | video_uploader_id = mobj.group(1) | |
929 | else: | |
69ea8ca4 | 930 | self._downloader.report_warning('unable to extract uploader nickname') |
c5e8d7af PH |
931 | |
932 | # title | |
a8c6b241 | 933 | if 'title' in video_info: |
aa92f063 | 934 | video_title = video_info['title'][0] |
a8c6b241 | 935 | else: |
69ea8ca4 | 936 | self._downloader.report_warning('Unable to extract video title') |
78caa52a | 937 | video_title = '_' |
c5e8d7af PH |
938 | |
939 | # thumbnail image | |
7763b04e JMF |
940 | # We try first to get a high quality image: |
941 | m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">', | |
942 | video_webpage, re.DOTALL) | |
943 | if m_thumb is not None: | |
944 | video_thumbnail = m_thumb.group(1) | |
945 | elif 'thumbnail_url' not in video_info: | |
69ea8ca4 | 946 | self._downloader.report_warning('unable to extract video thumbnail') |
f490e77e | 947 | video_thumbnail = None |
c5e8d7af PH |
948 | else: # don't panic if we can't find it |
949 | video_thumbnail = compat_urllib_parse.unquote_plus(video_info['thumbnail_url'][0]) | |
950 | ||
951 | # upload date | |
952 | upload_date = None | |
ad3bc6ac | 953 | mobj = re.search(r'(?s)id="eow-date.*?>(.*?)</span>', video_webpage) |
beee53de PH |
954 | if mobj is None: |
955 | mobj = re.search( | |
263bd4ec | 956 | r'(?s)id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live) on (.*?)</strong>', |
beee53de | 957 | video_webpage) |
c5e8d7af PH |
958 | if mobj is not None: |
959 | upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split()) | |
960 | upload_date = unified_strdate(upload_date) | |
961 | ||
55f7bd2d PH |
962 | m_cat_container = self._search_regex( |
963 | r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>', | |
624dcebf | 964 | video_webpage, 'categories', default=None) |
ec8deefc | 965 | if m_cat_container: |
ad3bc6ac | 966 | category = self._html_search_regex( |
01ed5c9b | 967 | r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category', |
ad3bc6ac PH |
968 | default=None) |
969 | video_categories = None if category is None else [category] | |
970 | else: | |
971 | video_categories = None | |
ec8deefc | 972 | |
c5e8d7af PH |
973 | # description |
974 | video_description = get_element_by_id("eow-description", video_webpage) | |
975 | if video_description: | |
27dcce19 PH |
976 | video_description = re.sub(r'''(?x) |
977 | <a\s+ | |
978 | (?:[a-zA-Z-]+="[^"]+"\s+)*? | |
979 | title="([^"]+)"\s+ | |
980 | (?:[a-zA-Z-]+="[^"]+"\s+)*? | |
981 | class="yt-uix-redirect-link"\s*> | |
982 | [^<]+ | |
983 | </a> | |
984 | ''', r'\1', video_description) | |
c5e8d7af PH |
985 | video_description = clean_html(video_description) |
986 | else: | |
987 | fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage) | |
988 | if fd_mobj: | |
989 | video_description = unescapeHTML(fd_mobj.group(1)) | |
990 | else: | |
78caa52a | 991 | video_description = '' |
c5e8d7af | 992 | |
f30a38be | 993 | def _extract_count(count_name): |
46374a56 | 994 | count = self._search_regex( |
f30a38be JMF |
995 | r'id="watch-%s"[^>]*>.*?([\d,]+)\s*</span>' % re.escape(count_name), |
996 | video_webpage, count_name, default=None) | |
336c3a69 JMF |
997 | if count is not None: |
998 | return int(count.replace(',', '')) | |
999 | return None | |
69ea8ca4 PH |
1000 | like_count = _extract_count('like') |
1001 | dislike_count = _extract_count('dislike') | |
336c3a69 | 1002 | |
c5e8d7af | 1003 | # subtitles |
d82134c3 | 1004 | video_subtitles = self.extract_subtitles(video_id, video_webpage) |
360e1ca5 | 1005 | automatic_captions = self.extract_automatic_captions(video_id, video_webpage) |
c5e8d7af PH |
1006 | |
1007 | if 'length_seconds' not in video_info: | |
69ea8ca4 | 1008 | self._downloader.report_warning('unable to extract video duration') |
b466b702 | 1009 | video_duration = None |
c5e8d7af | 1010 | else: |
b466b702 | 1011 | video_duration = int(compat_urllib_parse.unquote_plus(video_info['length_seconds'][0])) |
c5e8d7af | 1012 | |
1fb07d10 JG |
1013 | # annotations |
1014 | video_annotations = None | |
1015 | if self._downloader.params.get('writeannotations', False): | |
5f6a1245 | 1016 | video_annotations = self._extract_annotations(video_id) |
1fb07d10 | 1017 | |
dd27fd17 PH |
1018 | def _map_to_format_list(urlmap): |
1019 | formats = [] | |
1020 | for itag, video_real_url in urlmap.items(): | |
1021 | dct = { | |
1022 | 'format_id': itag, | |
1023 | 'url': video_real_url, | |
1024 | 'player_url': player_url, | |
1025 | } | |
0b65e5d4 PH |
1026 | if itag in self._formats: |
1027 | dct.update(self._formats[itag]) | |
dd27fd17 PH |
1028 | formats.append(dct) |
1029 | return formats | |
1030 | ||
c5e8d7af PH |
1031 | if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'): |
1032 | self.report_rtmp_download() | |
dd27fd17 PH |
1033 | formats = [{ |
1034 | 'format_id': '_rtmp', | |
1035 | 'protocol': 'rtmp', | |
1036 | 'url': video_info['conn'][0], | |
1037 | 'player_url': player_url, | |
1038 | }] | |
24270b03 | 1039 | elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1: |
5f6a1245 | 1040 | encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0] |
00fe14fc | 1041 | if 'rtmpe%3Dyes' in encoded_url_map: |
a7055eb9 | 1042 | raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True) |
c5e8d7af | 1043 | url_map = {} |
00fe14fc | 1044 | for url_data_str in encoded_url_map.split(','): |
c5e8d7af | 1045 | url_data = compat_parse_qs(url_data_str) |
201e9eaa PH |
1046 | if 'itag' not in url_data or 'url' not in url_data: |
1047 | continue | |
1048 | format_id = url_data['itag'][0] | |
1049 | url = url_data['url'][0] | |
1050 | ||
1051 | if 'sig' in url_data: | |
1052 | url += '&signature=' + url_data['sig'][0] | |
1053 | elif 's' in url_data: | |
1054 | encrypted_sig = url_data['s'][0] | |
6449cd80 | 1055 | ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")' |
201e9eaa | 1056 | |
beb95e77 | 1057 | jsplayer_url_json = self._search_regex( |
6449cd80 PH |
1058 | ASSETS_RE, |
1059 | embed_webpage if age_gate else video_webpage, | |
1060 | 'JS player URL (1)', default=None) | |
1061 | if not jsplayer_url_json and not age_gate: | |
1062 | # We need the embed website after all | |
1063 | if embed_webpage is None: | |
1064 | embed_url = proto + '://www.youtube.com/embed/%s' % video_id | |
1065 | embed_webpage = self._download_webpage( | |
1066 | embed_url, video_id, 'Downloading embed webpage') | |
1067 | jsplayer_url_json = self._search_regex( | |
1068 | ASSETS_RE, embed_webpage, 'JS player URL') | |
1069 | ||
beb95e77 | 1070 | player_url = json.loads(jsplayer_url_json) |
201e9eaa PH |
1071 | if player_url is None: |
1072 | player_url_json = self._search_regex( | |
1073 | r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")', | |
78caa52a | 1074 | video_webpage, 'age gate player URL') |
201e9eaa PH |
1075 | player_url = json.loads(player_url_json) |
1076 | ||
1077 | if self._downloader.params.get('verbose'): | |
cf010131 | 1078 | if player_url is None: |
201e9eaa PH |
1079 | player_version = 'unknown' |
1080 | player_desc = 'unknown' | |
1081 | else: | |
1082 | if player_url.endswith('swf'): | |
1083 | player_version = self._search_regex( | |
1084 | r'-(.+?)(?:/watch_as3)?\.swf$', player_url, | |
78caa52a | 1085 | 'flash player', fatal=False) |
201e9eaa | 1086 | player_desc = 'flash player %s' % player_version |
cf010131 | 1087 | else: |
201e9eaa PH |
1088 | player_version = self._search_regex( |
1089 | r'html5player-([^/]+?)(?:/html5player)?\.js', | |
1090 | player_url, | |
1091 | 'html5 player', fatal=False) | |
78caa52a | 1092 | player_desc = 'html5 player %s' % player_version |
201e9eaa | 1093 | |
60064c53 | 1094 | parts_sizes = self._signature_cache_id(encrypted_sig) |
69ea8ca4 | 1095 | self.to_screen('{%s} signature length %s, %s' % |
9e1a5b84 | 1096 | (format_id, parts_sizes, player_desc)) |
201e9eaa PH |
1097 | |
1098 | signature = self._decrypt_signature( | |
1099 | encrypted_sig, video_id, player_url, age_gate) | |
1100 | url += '&signature=' + signature | |
1101 | if 'ratebypass' not in url: | |
1102 | url += '&ratebypass=yes' | |
1103 | url_map[format_id] = url | |
dd27fd17 | 1104 | formats = _map_to_format_list(url_map) |
1d043b93 JMF |
1105 | elif video_info.get('hlsvp'): |
1106 | manifest_url = video_info['hlsvp'][0] | |
1107 | url_map = self._extract_from_m3u8(manifest_url, video_id) | |
dd27fd17 | 1108 | formats = _map_to_format_list(url_map) |
c5e8d7af | 1109 | else: |
69ea8ca4 | 1110 | raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info') |
c5e8d7af | 1111 | |
dd27fd17 | 1112 | # Look for the DASH manifest |
203fb43f | 1113 | if self._downloader.params.get('youtube_include_dash_manifest', True): |
774e208f | 1114 | dash_mpd = video_info.get('dashmpd') |
75111274 | 1115 | if dash_mpd: |
774e208f PH |
1116 | dash_manifest_url = dash_mpd[0] |
1117 | try: | |
1118 | dash_formats = self._parse_dash_manifest( | |
da276600 | 1119 | video_id, dash_manifest_url, player_url, age_gate) |
774e208f PH |
1120 | except (ExtractorError, KeyError) as e: |
1121 | self.report_warning( | |
1122 | 'Skipping DASH manifest: %r' % e, video_id) | |
1123 | else: | |
e65566a9 PH |
1124 | # Hide the formats we found through non-DASH |
1125 | dash_keys = set(df['format_id'] for df in dash_formats) | |
1126 | for f in formats: | |
1127 | if f['format_id'] in dash_keys: | |
1128 | f['format_id'] = 'nondash-%s' % f['format_id'] | |
ee61f6f3 | 1129 | f['preference'] = f.get('preference', 0) - 10000 |
774e208f | 1130 | formats.extend(dash_formats) |
d80044c2 | 1131 | |
6271f1ca PH |
1132 | # Check for malformed aspect ratio |
1133 | stretched_m = re.search( | |
1134 | r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">', | |
1135 | video_webpage) | |
1136 | if stretched_m: | |
1137 | ratio = float(stretched_m.group('w')) / float(stretched_m.group('h')) | |
1138 | for f in formats: | |
1139 | if f.get('vcodec') != 'none': | |
1140 | f['stretched_ratio'] = ratio | |
1141 | ||
4bcc7bd1 | 1142 | self._sort_formats(formats) |
4ea3be0a | 1143 | |
1144 | return { | |
8bcc8756 JW |
1145 | 'id': video_id, |
1146 | 'uploader': video_uploader, | |
1147 | 'uploader_id': video_uploader_id, | |
1148 | 'upload_date': upload_date, | |
1149 | 'title': video_title, | |
1150 | 'thumbnail': video_thumbnail, | |
1151 | 'description': video_description, | |
1152 | 'categories': video_categories, | |
1153 | 'subtitles': video_subtitles, | |
360e1ca5 | 1154 | 'automatic_captions': automatic_captions, |
8bcc8756 JW |
1155 | 'duration': video_duration, |
1156 | 'age_limit': 18 if age_gate else 0, | |
1157 | 'annotations': video_annotations, | |
7e8c0af0 | 1158 | 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id, |
8bcc8756 | 1159 | 'view_count': view_count, |
4ea3be0a | 1160 | 'like_count': like_count, |
1161 | 'dislike_count': dislike_count, | |
2d30521a | 1162 | 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]), |
8bcc8756 | 1163 | 'formats': formats, |
4ea3be0a | 1164 | } |
c5e8d7af | 1165 | |
5f6a1245 | 1166 | |
880e1c52 | 1167 | class YoutubePlaylistIE(YoutubeBaseInfoExtractor): |
78caa52a | 1168 | IE_DESC = 'YouTube.com playlists' |
d67cc9fa | 1169 | _VALID_URL = r"""(?x)(?: |
c5e8d7af PH |
1170 | (?:https?://)? |
1171 | (?:\w+\.)? | |
1172 | youtube\.com/ | |
1173 | (?: | |
ac7553d0 | 1174 | (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries) |
c5e8d7af PH |
1175 | \? (?:.*?&)*? (?:p|a|list)= |
1176 | | p/ | |
1177 | ) | |
d67cc9fa | 1178 | ( |
99209c29 | 1179 | (?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,} |
5f6a1245 | 1180 | # Top tracks, they can also include dots |
d67cc9fa JMF |
1181 | |(?:MC)[\w\.]* |
1182 | ) | |
c5e8d7af PH |
1183 | .* |
1184 | | | |
99209c29 | 1185 | ((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,}) |
c5e8d7af | 1186 | )""" |
dbb94fb0 | 1187 | _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s' |
dbb94fb0 | 1188 | _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)' |
78caa52a | 1189 | IE_NAME = 'youtube:playlist' |
81127aa5 PH |
1190 | _TESTS = [{ |
1191 | 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', | |
1192 | 'info_dict': { | |
1193 | 'title': 'ytdl test PL', | |
a1cf99d0 | 1194 | 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re', |
81127aa5 PH |
1195 | }, |
1196 | 'playlist_count': 3, | |
9291475f PH |
1197 | }, { |
1198 | 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', | |
1199 | 'info_dict': { | |
acf757f4 | 1200 | 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx', |
9291475f PH |
1201 | 'title': 'YDL_Empty_List', |
1202 | }, | |
1203 | 'playlist_count': 0, | |
1204 | }, { | |
1205 | 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.', | |
1206 | 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', | |
1207 | 'info_dict': { | |
1208 | 'title': '29C3: Not my department', | |
acf757f4 | 1209 | 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC', |
9291475f PH |
1210 | }, |
1211 | 'playlist_count': 95, | |
1212 | }, { | |
1213 | 'note': 'issue #673', | |
1214 | 'url': 'PLBB231211A4F62143', | |
1215 | 'info_dict': { | |
f46a8702 | 1216 | 'title': '[OLD]Team Fortress 2 (Class-based LP)', |
acf757f4 | 1217 | 'id': 'PLBB231211A4F62143', |
9291475f PH |
1218 | }, |
1219 | 'playlist_mincount': 26, | |
1220 | }, { | |
1221 | 'note': 'Large playlist', | |
1222 | 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q', | |
1223 | 'info_dict': { | |
1224 | 'title': 'Uploads from Cauchemar', | |
acf757f4 | 1225 | 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q', |
9291475f PH |
1226 | }, |
1227 | 'playlist_mincount': 799, | |
1228 | }, { | |
1229 | 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', | |
1230 | 'info_dict': { | |
1231 | 'title': 'YDL_safe_search', | |
acf757f4 | 1232 | 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl', |
9291475f PH |
1233 | }, |
1234 | 'playlist_count': 2, | |
ac7553d0 PH |
1235 | }, { |
1236 | 'note': 'embedded', | |
1237 | 'url': 'http://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', | |
1238 | 'playlist_count': 4, | |
1239 | 'info_dict': { | |
1240 | 'title': 'JODA15', | |
acf757f4 | 1241 | 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu', |
ac7553d0 | 1242 | } |
6b08cdf6 PH |
1243 | }, { |
1244 | 'note': 'Embedded SWF player', | |
1245 | 'url': 'http://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0', | |
1246 | 'playlist_count': 4, | |
1247 | 'info_dict': { | |
1248 | 'title': 'JODA7', | |
acf757f4 | 1249 | 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ', |
6b08cdf6 | 1250 | } |
4b7df0d3 JMF |
1251 | }, { |
1252 | 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos', | |
1253 | 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA', | |
1254 | 'info_dict': { | |
acf757f4 PH |
1255 | 'title': 'Uploads from Interstellar Movie', |
1256 | 'id': 'UUXw-G3eDE9trcvY2sBMM_aA', | |
4b7df0d3 JMF |
1257 | }, |
1258 | 'playlist_mincout': 21, | |
81127aa5 | 1259 | }] |
c5e8d7af | 1260 | |
880e1c52 JMF |
1261 | def _real_initialize(self): |
1262 | self._login() | |
1263 | ||
652cdaa2 | 1264 | def _ids_to_results(self, ids): |
c9cc0bf5 PH |
1265 | return [ |
1266 | self.url_result(vid_id, 'Youtube', video_id=vid_id) | |
1267 | for vid_id in ids] | |
652cdaa2 JMF |
1268 | |
1269 | def _extract_mix(self, playlist_id): | |
99209c29 | 1270 | # The mixes are generated from a single video |
652cdaa2 | 1271 | # the id of the playlist is just 'RD' + video_id |
7d4afc55 | 1272 | url = 'https://youtube.com/watch?v=%s&list=%s' % (playlist_id[-11:], playlist_id) |
c9cc0bf5 | 1273 | webpage = self._download_webpage( |
78caa52a | 1274 | url, playlist_id, 'Downloading Youtube mix') |
bc2f773b | 1275 | search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage) |
c9cc0bf5 PH |
1276 | title_span = ( |
1277 | search_title('playlist-title') or | |
1278 | search_title('title long-title') or | |
1279 | search_title('title')) | |
76d1700b | 1280 | title = clean_html(title_span) |
c9cc0bf5 PH |
1281 | ids = orderedSet(re.findall( |
1282 | r'''(?xs)data-video-username=".*?".*? | |
1283 | href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id), | |
1284 | webpage)) | |
652cdaa2 JMF |
1285 | url_results = self._ids_to_results(ids) |
1286 | ||
1287 | return self.playlist_result(url_results, playlist_id, title) | |
1288 | ||
448830ce | 1289 | def _extract_playlist(self, playlist_id): |
dbb94fb0 S |
1290 | url = self._TEMPLATE_URL % playlist_id |
1291 | page = self._download_webpage(url, playlist_id) | |
1292 | more_widget_html = content_html = page | |
1293 | ||
10c0e2d8 | 1294 | # Check if the playlist exists or is private |
e399853d | 1295 | if re.search(r'<div class="yt-alert-message">[^<]*?(The|This) playlist (does not exist|is private)[^<]*?</div>', page) is not None: |
10c0e2d8 | 1296 | raise ExtractorError( |
78caa52a | 1297 | 'The playlist doesn\'t exist or is private, use --username or ' |
10c0e2d8 JMF |
1298 | '--netrc to access it.', |
1299 | expected=True) | |
1300 | ||
dcbb4580 JMF |
1301 | # Extract the video ids from the playlist pages |
1302 | ids = [] | |
c5e8d7af | 1303 | |
755eb032 | 1304 | for page_num in itertools.count(1): |
dbb94fb0 | 1305 | matches = re.finditer(self._VIDEO_RE, content_html) |
6e47b51e JMF |
1306 | # We remove the duplicates and the link with index 0 |
1307 | # (it's not the first video of the playlist) | |
1308 | new_ids = orderedSet(m.group('id') for m in matches if m.group('index') != '0') | |
dcbb4580 | 1309 | ids.extend(new_ids) |
c5e8d7af | 1310 | |
dbb94fb0 S |
1311 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) |
1312 | if not mobj: | |
c5e8d7af PH |
1313 | break |
1314 | ||
dbb94fb0 | 1315 | more = self._download_json( |
5912c639 PH |
1316 | 'https://youtube.com/%s' % mobj.group('more'), playlist_id, |
1317 | 'Downloading page #%s' % page_num, | |
1318 | transform_source=uppercase_escape) | |
dbb94fb0 | 1319 | content_html = more['content_html'] |
4b7df0d3 JMF |
1320 | if not content_html.strip(): |
1321 | # Some webpages show a "Load more" button but they don't | |
1322 | # have more videos | |
1323 | break | |
dbb94fb0 S |
1324 | more_widget_html = more['load_more_widget_html'] |
1325 | ||
1326 | playlist_title = self._html_search_regex( | |
68eb8e90 | 1327 | r'(?s)<h1 class="pl-header-title[^"]*">\s*(.*?)\s*</h1>', |
78caa52a | 1328 | page, 'title') |
c5e8d7af | 1329 | |
652cdaa2 | 1330 | url_results = self._ids_to_results(ids) |
dcbb4580 | 1331 | return self.playlist_result(url_results, playlist_id, playlist_title) |
c5e8d7af | 1332 | |
448830ce S |
1333 | def _real_extract(self, url): |
1334 | # Extract playlist id | |
1335 | mobj = re.match(self._VALID_URL, url) | |
1336 | if mobj is None: | |
1337 | raise ExtractorError('Invalid URL: %s' % url) | |
1338 | playlist_id = mobj.group(1) or mobj.group(2) | |
1339 | ||
1340 | # Check if it's a video-specific URL | |
1341 | query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query) | |
1342 | if 'v' in query_dict: | |
1343 | video_id = query_dict['v'][0] | |
1344 | if self._downloader.params.get('noplaylist'): | |
1345 | self.to_screen('Downloading just video %s because of --no-playlist' % video_id) | |
1346 | return self.url_result(video_id, 'Youtube', video_id=video_id) | |
1347 | else: | |
1348 | self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id)) | |
1349 | ||
1350 | if playlist_id.startswith('RD') or playlist_id.startswith('UL'): | |
1351 | # Mixes require a custom extraction process | |
1352 | return self._extract_mix(playlist_id) | |
1353 | ||
1354 | return self._extract_playlist(playlist_id) | |
1355 | ||
c5e8d7af PH |
1356 | |
1357 | class YoutubeChannelIE(InfoExtractor): | |
78caa52a | 1358 | IE_DESC = 'YouTube.com channels' |
9ff67727 | 1359 | _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)' |
eb0f3e7e | 1360 | _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos' |
78caa52a | 1361 | IE_NAME = 'youtube:channel' |
cdc628a4 PH |
1362 | _TESTS = [{ |
1363 | 'note': 'paginated channel', | |
1364 | 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w', | |
1365 | 'playlist_mincount': 91, | |
acf757f4 PH |
1366 | 'info_dict': { |
1367 | 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w', | |
1368 | } | |
cdc628a4 | 1369 | }] |
c5e8d7af | 1370 | |
6de5dbaf S |
1371 | @staticmethod |
1372 | def extract_videos_from_page(page): | |
c5e8d7af | 1373 | ids_in_page = [] |
fb69240c S |
1374 | titles_in_page = [] |
1375 | for mobj in re.finditer(r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?', page): | |
1376 | video_id = mobj.group('id') | |
1377 | video_title = unescapeHTML(mobj.group('title')) | |
1378 | try: | |
1379 | idx = ids_in_page.index(video_id) | |
1380 | if video_title and not titles_in_page[idx]: | |
1381 | titles_in_page[idx] = video_title | |
1382 | except ValueError: | |
1383 | ids_in_page.append(video_id) | |
1384 | titles_in_page.append(video_title) | |
1385 | return zip(ids_in_page, titles_in_page) | |
c5e8d7af PH |
1386 | |
1387 | def _real_extract(self, url): | |
9ff67727 | 1388 | channel_id = self._match_id(url) |
c5e8d7af | 1389 | |
eb0f3e7e | 1390 | url = self._TEMPLATE_URL % channel_id |
60bf45c8 | 1391 | channel_page = self._download_webpage(url, channel_id, 'Downloading page #1') |
31812a9e PH |
1392 | autogenerated = re.search(r'''(?x) |
1393 | class="[^"]*?(?: | |
1394 | channel-header-autogenerated-label| | |
1395 | yt-channel-title-autogenerated | |
1396 | )[^"]*"''', channel_page) is not None | |
c5e8d7af | 1397 | |
b9643eed JMF |
1398 | if autogenerated: |
1399 | # The videos are contained in a single page | |
1400 | # the ajax pages can't be used, they are empty | |
b82f815f | 1401 | entries = [ |
fb69240c S |
1402 | self.url_result( |
1403 | video_id, 'Youtube', video_id=video_id, | |
1404 | video_title=video_title) | |
8f02ad4f | 1405 | for video_id, video_title in self.extract_videos_from_page(channel_page)] |
b82f815f PH |
1406 | return self.playlist_result(entries, channel_id) |
1407 | ||
1408 | def _entries(): | |
23d3608c | 1409 | more_widget_html = content_html = channel_page |
b9643eed | 1410 | for pagenum in itertools.count(1): |
81c2f20b | 1411 | |
8f02ad4f | 1412 | for video_id, video_title in self.extract_videos_from_page(content_html): |
b82f815f | 1413 | yield self.url_result( |
fb69240c S |
1414 | video_id, 'Youtube', video_id=video_id, |
1415 | video_title=video_title) | |
5f6a1245 | 1416 | |
23d3608c JMF |
1417 | mobj = re.search( |
1418 | r'data-uix-load-more-href="/?(?P<more>[^"]+)"', | |
1419 | more_widget_html) | |
1420 | if not mobj: | |
b9643eed | 1421 | break |
c5e8d7af | 1422 | |
23d3608c JMF |
1423 | more = self._download_json( |
1424 | 'https://youtube.com/%s' % mobj.group('more'), channel_id, | |
1425 | 'Downloading page #%s' % (pagenum + 1), | |
1426 | transform_source=uppercase_escape) | |
1427 | content_html = more['content_html'] | |
1428 | more_widget_html = more['load_more_widget_html'] | |
1429 | ||
b82f815f | 1430 | return self.playlist_result(_entries(), channel_id) |
c5e8d7af PH |
1431 | |
1432 | ||
eb0f3e7e | 1433 | class YoutubeUserIE(YoutubeChannelIE): |
78caa52a | 1434 | IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)' |
9ff67727 | 1435 | _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 | 1436 | _TEMPLATE_URL = 'https://www.youtube.com/user/%s/videos' |
78caa52a | 1437 | IE_NAME = 'youtube:user' |
c5e8d7af | 1438 | |
cdc628a4 PH |
1439 | _TESTS = [{ |
1440 | 'url': 'https://www.youtube.com/user/TheLinuxFoundation', | |
1441 | 'playlist_mincount': 320, | |
1442 | 'info_dict': { | |
1443 | 'title': 'TheLinuxFoundation', | |
1444 | } | |
1445 | }, { | |
1446 | 'url': 'ytuser:phihag', | |
1447 | 'only_matching': True, | |
1448 | }] | |
1449 | ||
e3ea4790 | 1450 | @classmethod |
f4b05232 | 1451 | def suitable(cls, url): |
e3ea4790 JMF |
1452 | # Don't return True if the url can be extracted with other youtube |
1453 | # extractor, the regex would is too permissive and it would match. | |
1454 | other_ies = iter(klass for (name, klass) in globals().items() if name.endswith('IE') and klass is not cls) | |
5f6a1245 JW |
1455 | if any(ie.suitable(url) for ie in other_ies): |
1456 | return False | |
1457 | else: | |
1458 | return super(YoutubeUserIE, cls).suitable(url) | |
f4b05232 | 1459 | |
b05654f0 | 1460 | |
b4c08069 | 1461 | class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE): |
78caa52a | 1462 | IE_DESC = 'YouTube.com searches' |
b4c08069 JMF |
1463 | # there doesn't appear to be a real limit, for example if you search for |
1464 | # 'python' you get more than 8.000.000 results | |
1465 | _MAX_RESULTS = float('inf') | |
78caa52a | 1466 | IE_NAME = 'youtube:search' |
b05654f0 | 1467 | _SEARCH_KEY = 'ytsearch' |
b4c08069 | 1468 | _EXTRA_QUERY_ARGS = {} |
9dd8e46a | 1469 | _TESTS = [] |
b05654f0 | 1470 | |
b05654f0 PH |
1471 | def _get_n_results(self, query, n): |
1472 | """Get a specified number of results for a query""" | |
1473 | ||
b4c08069 | 1474 | videos = [] |
b05654f0 PH |
1475 | limit = n |
1476 | ||
b4c08069 JMF |
1477 | for pagenum in itertools.count(1): |
1478 | url_query = { | |
1479 | 'search_query': query, | |
1480 | 'page': pagenum, | |
1481 | 'spf': 'navigate', | |
1482 | } | |
1483 | url_query.update(self._EXTRA_QUERY_ARGS) | |
1484 | result_url = 'https://www.youtube.com/results?' + compat_urllib_parse.urlencode(url_query) | |
1485 | data = self._download_json( | |
69ea8ca4 | 1486 | result_url, video_id='query "%s"' % query, |
b4c08069 | 1487 | note='Downloading page %s' % pagenum, |
69ea8ca4 | 1488 | errnote='Unable to download API page') |
b4c08069 | 1489 | html_content = data[1]['body']['content'] |
7cc3570e | 1490 | |
b4c08069 | 1491 | if 'class="search-message' in html_content: |
07ad22b8 | 1492 | raise ExtractorError( |
78caa52a | 1493 | '[youtube] No video results', expected=True) |
b05654f0 | 1494 | |
b4c08069 JMF |
1495 | new_videos = self._ids_to_results(orderedSet(re.findall( |
1496 | r'href="/watch\?v=(.{11})', html_content))) | |
1497 | videos += new_videos | |
1498 | if not new_videos or len(videos) > limit: | |
1499 | break | |
b05654f0 | 1500 | |
b4c08069 JMF |
1501 | if len(videos) > n: |
1502 | videos = videos[:n] | |
b05654f0 | 1503 | return self.playlist_result(videos, query) |
75dff0ee | 1504 | |
c9ae7b95 | 1505 | |
a3dd9248 | 1506 | class YoutubeSearchDateIE(YoutubeSearchIE): |
cb7fb546 | 1507 | IE_NAME = YoutubeSearchIE.IE_NAME + ':date' |
a3dd9248 | 1508 | _SEARCH_KEY = 'ytsearchdate' |
78caa52a | 1509 | IE_DESC = 'YouTube.com searches, newest videos first' |
b4c08069 | 1510 | _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'} |
75dff0ee | 1511 | |
c9ae7b95 PH |
1512 | |
1513 | class YoutubeSearchURLIE(InfoExtractor): | |
78caa52a PH |
1514 | IE_DESC = 'YouTube.com search URLs' |
1515 | IE_NAME = 'youtube:search_url' | |
c9ae7b95 | 1516 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?search_query=(?P<query>[^&]+)(?:[&]|$)' |
cdc628a4 PH |
1517 | _TESTS = [{ |
1518 | 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video', | |
1519 | 'playlist_mincount': 5, | |
1520 | 'info_dict': { | |
1521 | 'title': 'youtube-dl test video', | |
1522 | } | |
1523 | }] | |
c9ae7b95 PH |
1524 | |
1525 | def _real_extract(self, url): | |
1526 | mobj = re.match(self._VALID_URL, url) | |
1527 | query = compat_urllib_parse.unquote_plus(mobj.group('query')) | |
1528 | ||
1529 | webpage = self._download_webpage(url, query) | |
1530 | result_code = self._search_regex( | |
98998cde | 1531 | r'(?s)<ol[^>]+class="item-section"(.*?)</ol>', webpage, 'result HTML') |
c9ae7b95 PH |
1532 | |
1533 | part_codes = re.findall( | |
1534 | r'(?s)<h3 class="yt-lockup-title">(.*?)</h3>', result_code) | |
1535 | entries = [] | |
1536 | for part_code in part_codes: | |
1537 | part_title = self._html_search_regex( | |
6feb2d5e | 1538 | [r'(?s)title="([^"]+)"', r'>([^<]+)</a>'], part_code, 'item title', fatal=False) |
c9ae7b95 PH |
1539 | part_url_snippet = self._html_search_regex( |
1540 | r'(?s)href="([^"]+)"', part_code, 'item URL') | |
1541 | part_url = compat_urlparse.urljoin( | |
1542 | 'https://www.youtube.com/', part_url_snippet) | |
1543 | entries.append({ | |
1544 | '_type': 'url', | |
1545 | 'url': part_url, | |
1546 | 'title': part_title, | |
1547 | }) | |
1548 | ||
1549 | return { | |
1550 | '_type': 'playlist', | |
1551 | 'entries': entries, | |
1552 | 'title': query, | |
1553 | } | |
1554 | ||
1555 | ||
75dff0ee | 1556 | class YoutubeShowIE(InfoExtractor): |
78caa52a | 1557 | IE_DESC = 'YouTube.com (multi-season) shows' |
cdc628a4 | 1558 | _VALID_URL = r'https?://www\.youtube\.com/show/(?P<id>[^?#]*)' |
78caa52a | 1559 | IE_NAME = 'youtube:show' |
cdc628a4 PH |
1560 | _TESTS = [{ |
1561 | 'url': 'http://www.youtube.com/show/airdisasters', | |
1562 | 'playlist_mincount': 3, | |
1563 | 'info_dict': { | |
1564 | 'id': 'airdisasters', | |
1565 | 'title': 'Air Disasters', | |
1566 | } | |
1567 | }] | |
75dff0ee JMF |
1568 | |
1569 | def _real_extract(self, url): | |
1570 | mobj = re.match(self._VALID_URL, url) | |
cdc628a4 PH |
1571 | playlist_id = mobj.group('id') |
1572 | webpage = self._download_webpage( | |
1573 | url, playlist_id, 'Downloading show webpage') | |
75dff0ee JMF |
1574 | # There's one playlist for each season of the show |
1575 | m_seasons = list(re.finditer(r'href="(/playlist\?list=.*?)"', webpage)) | |
cdc628a4 PH |
1576 | self.to_screen('%s: Found %s seasons' % (playlist_id, len(m_seasons))) |
1577 | entries = [ | |
1578 | self.url_result( | |
1579 | 'https://www.youtube.com' + season.group(1), 'YoutubePlaylist') | |
1580 | for season in m_seasons | |
1581 | ] | |
1582 | title = self._og_search_title(webpage, fatal=False) | |
1583 | ||
1584 | return { | |
1585 | '_type': 'playlist', | |
1586 | 'id': playlist_id, | |
1587 | 'title': title, | |
1588 | 'entries': entries, | |
1589 | } | |
04cc9617 JMF |
1590 | |
1591 | ||
b2e8bc1b | 1592 | class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor): |
d7ae0639 JMF |
1593 | """ |
1594 | Base class for extractors that fetch info from | |
1595 | http://www.youtube.com/feed_ajax | |
1596 | Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties. | |
1597 | """ | |
b2e8bc1b | 1598 | _LOGIN_REQUIRED = True |
43ba5456 JMF |
1599 | # use action_load_personal_feed instead of action_load_system_feed |
1600 | _PERSONAL_FEED = False | |
04cc9617 | 1601 | |
d7ae0639 JMF |
1602 | @property |
1603 | def _FEED_TEMPLATE(self): | |
43ba5456 JMF |
1604 | action = 'action_load_system_feed' |
1605 | if self._PERSONAL_FEED: | |
1606 | action = 'action_load_personal_feed' | |
38c2e5b8 | 1607 | return 'https://www.youtube.com/feed_ajax?%s=1&feed_name=%s&paging=%%s' % (action, self._FEED_NAME) |
d7ae0639 JMF |
1608 | |
1609 | @property | |
1610 | def IE_NAME(self): | |
78caa52a | 1611 | return 'youtube:%s' % self._FEED_NAME |
04cc9617 | 1612 | |
81f0259b | 1613 | def _real_initialize(self): |
b2e8bc1b | 1614 | self._login() |
81f0259b | 1615 | |
04cc9617 JMF |
1616 | def _real_extract(self, url): |
1617 | feed_entries = [] | |
0e44d838 JMF |
1618 | paging = 0 |
1619 | for i in itertools.count(1): | |
84d84211 PH |
1620 | info = self._download_json( |
1621 | self._FEED_TEMPLATE % paging, | |
1622 | '%s feed' % self._FEED_NAME, | |
1623 | 'Downloading page %s' % i, | |
1624 | transform_source=uppercase_escape) | |
f6177462 | 1625 | feed_html = info.get('feed_html') or info.get('content_html') |
1a9b9649 | 1626 | load_more_widget_html = info.get('load_more_widget_html') or feed_html |
43ba5456 | 1627 | m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html) |
04cc9617 | 1628 | ids = orderedSet(m.group(1) for m in m_ids) |
7012b23c PH |
1629 | feed_entries.extend( |
1630 | self.url_result(video_id, 'Youtube', video_id=video_id) | |
1631 | for video_id in ids) | |
05ee2b6d JMF |
1632 | mobj = re.search( |
1633 | r'data-uix-load-more-href="/?[^"]+paging=(?P<paging>\d+)', | |
1a9b9649 | 1634 | load_more_widget_html) |
05ee2b6d | 1635 | if mobj is None: |
04cc9617 | 1636 | break |
05ee2b6d | 1637 | paging = mobj.group('paging') |
d7ae0639 JMF |
1638 | return self.playlist_result(feed_entries, playlist_title=self._PLAYLIST_TITLE) |
1639 | ||
5f6a1245 | 1640 | |
d7ae0639 | 1641 | class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor): |
7e17ec8c | 1642 | IE_NAME = 'youtube:recommended' |
f3a34072 | 1643 | IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)' |
d7ae0639 JMF |
1644 | _VALID_URL = r'https?://www\.youtube\.com/feed/recommended|:ytrec(?:ommended)?' |
1645 | _FEED_NAME = 'recommended' | |
78caa52a | 1646 | _PLAYLIST_TITLE = 'Youtube Recommended videos' |
c626a3d9 | 1647 | |
5f6a1245 | 1648 | |
448830ce | 1649 | class YoutubeWatchLaterIE(YoutubePlaylistIE): |
7e17ec8c | 1650 | IE_NAME = 'youtube:watchlater' |
f3a34072 | 1651 | IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)' |
448830ce | 1652 | _VALID_URL = r'https?://www\.youtube\.com/(?:feed/watch_later|playlist\?list=WL)|:ytwatchlater' |
157e9e5a JMF |
1653 | |
1654 | _TESTS = [] # override PlaylistIE tests | |
c626a3d9 | 1655 | |
448830ce S |
1656 | def _real_extract(self, url): |
1657 | return self._extract_playlist('WL') | |
1658 | ||
5f6a1245 | 1659 | |
f459d170 | 1660 | class YoutubeHistoryIE(YoutubeFeedsInfoExtractor): |
7e17ec8c | 1661 | IE_NAME = 'youtube:history' |
f3a34072 | 1662 | IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)' |
78caa52a | 1663 | _VALID_URL = 'https?://www\.youtube\.com/feed/history|:ythistory' |
f459d170 JMF |
1664 | _FEED_NAME = 'history' |
1665 | _PERSONAL_FEED = True | |
78caa52a | 1666 | _PLAYLIST_TITLE = 'Youtube Watch History' |
f459d170 | 1667 | |
5f6a1245 | 1668 | |
c626a3d9 | 1669 | class YoutubeFavouritesIE(YoutubeBaseInfoExtractor): |
78caa52a | 1670 | IE_NAME = 'youtube:favorites' |
f3a34072 | 1671 | IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)' |
c7a7750d | 1672 | _VALID_URL = r'https?://www\.youtube\.com/my_favorites|:ytfav(?:ou?rites)?' |
c626a3d9 JMF |
1673 | _LOGIN_REQUIRED = True |
1674 | ||
1675 | def _real_extract(self, url): | |
1676 | webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos') | |
78caa52a | 1677 | playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id') |
c626a3d9 | 1678 | return self.url_result(playlist_id, 'YoutubePlaylist') |
15870e90 PH |
1679 | |
1680 | ||
1ed5b5c9 | 1681 | class YoutubeSubscriptionsIE(YoutubePlaylistIE): |
78caa52a PH |
1682 | IE_NAME = 'youtube:subscriptions' |
1683 | IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)' | |
1ed5b5c9 | 1684 | _VALID_URL = r'https?://www\.youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?' |
81127aa5 | 1685 | _TESTS = [] |
1ed5b5c9 JMF |
1686 | |
1687 | def _real_extract(self, url): | |
78caa52a | 1688 | title = 'Youtube Subscriptions' |
1ed5b5c9 JMF |
1689 | page = self._download_webpage('https://www.youtube.com/feed/subscriptions', title) |
1690 | ||
1691 | # The extraction process is the same as for playlists, but the regex | |
1692 | # for the video ids doesn't contain an index | |
1693 | ids = [] | |
1694 | more_widget_html = content_html = page | |
1695 | ||
1696 | for page_num in itertools.count(1): | |
1697 | matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html) | |
1698 | new_ids = orderedSet(matches) | |
1699 | ids.extend(new_ids) | |
1700 | ||
1701 | mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html) | |
1702 | if not mobj: | |
1703 | break | |
1704 | ||
1705 | more = self._download_json( | |
1706 | 'https://youtube.com/%s' % mobj.group('more'), title, | |
1707 | 'Downloading page #%s' % page_num, | |
1708 | transform_source=uppercase_escape) | |
1709 | content_html = more['content_html'] | |
1710 | more_widget_html = more['load_more_widget_html'] | |
1711 | ||
1712 | return { | |
1713 | '_type': 'playlist', | |
1714 | 'title': title, | |
1715 | 'entries': self._ids_to_results(ids), | |
1716 | } | |
1717 | ||
1718 | ||
15870e90 PH |
1719 | class YoutubeTruncatedURLIE(InfoExtractor): |
1720 | IE_NAME = 'youtube:truncated_url' | |
1721 | IE_DESC = False # Do not list | |
975d35db | 1722 | _VALID_URL = r'''(?x) |
b95aab84 PH |
1723 | (?:https?://)? |
1724 | (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/ | |
1725 | (?:watch\?(?: | |
c4808c60 | 1726 | feature=[a-z_]+| |
b95aab84 PH |
1727 | annotation_id=annotation_[^&]+| |
1728 | x-yt-cl=[0-9]+| | |
c1708b89 | 1729 | hl=[^&]*| |
b95aab84 PH |
1730 | )? |
1731 | | | |
1732 | attribution_link\?a=[^&]+ | |
1733 | ) | |
1734 | $ | |
975d35db | 1735 | ''' |
15870e90 | 1736 | |
c4808c60 PH |
1737 | _TESTS = [{ |
1738 | 'url': 'http://www.youtube.com/watch?annotation_id=annotation_3951667041', | |
1739 | 'only_matching': True, | |
dc2fc736 PH |
1740 | }, { |
1741 | 'url': 'http://www.youtube.com/watch?', | |
1742 | 'only_matching': True, | |
b95aab84 PH |
1743 | }, { |
1744 | 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534', | |
1745 | 'only_matching': True, | |
1746 | }, { | |
1747 | 'url': 'https://www.youtube.com/watch?feature=foo', | |
1748 | 'only_matching': True, | |
c1708b89 PH |
1749 | }, { |
1750 | 'url': 'https://www.youtube.com/watch?hl=en-GB', | |
1751 | 'only_matching': True, | |
c4808c60 PH |
1752 | }] |
1753 | ||
15870e90 PH |
1754 | def _real_extract(self, url): |
1755 | raise ExtractorError( | |
78caa52a PH |
1756 | 'Did you forget to quote the URL? Remember that & is a meta ' |
1757 | 'character in most shells, so you want to put the URL in quotes, ' | |
1758 | 'like youtube-dl ' | |
1759 | '"http://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" ' | |
1760 | ' or simply youtube-dl BaW_jenozKc .', | |
15870e90 | 1761 | expected=True) |
772fd5cc PH |
1762 | |
1763 | ||
1764 | class YoutubeTruncatedIDIE(InfoExtractor): | |
1765 | IE_NAME = 'youtube:truncated_id' | |
1766 | IE_DESC = False # Do not list | |
b95aab84 | 1767 | _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$' |
772fd5cc PH |
1768 | |
1769 | _TESTS = [{ | |
1770 | 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob', | |
1771 | 'only_matching': True, | |
1772 | }] | |
1773 | ||
1774 | def _real_extract(self, url): | |
1775 | video_id = self._match_id(url) | |
1776 | raise ExtractorError( | |
1777 | 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url), | |
1778 | expected=True) |