Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/vimeo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import base64
   5 import functools
   6 import json
   7 import re
   8 import itertools
   9
  10 from .common import InfoExtractor
  11 from ..compat import (
  12     compat_kwargs,
  13     compat_HTTPError,
  14     compat_str,
  15     compat_urlparse,
  16 )
  17 from ..utils import (
  18     clean_html,
  19     determine_ext,
  20     dict_get,
  21     ExtractorError,
  22     js_to_json,
  23     int_or_none,
  24     merge_dicts,
  25     OnDemandPagedList,
  26     parse_filesize,
  27     RegexNotFoundError,
  28     sanitized_Request,
  29     smuggle_url,
  30     std_headers,
  31     str_or_none,
  32     try_get,
  33     unified_timestamp,
  34     unsmuggle_url,
  35     urlencode_postdata,
  36     urljoin,
  37     unescapeHTML,
  38 )
  39
  40
  41 class VimeoBaseInfoExtractor(InfoExtractor):
  42     _NETRC_MACHINE = 'vimeo'
  43     _LOGIN_REQUIRED = False
  44     _LOGIN_URL = 'https://vimeo.com/log_in'
  45
  46     def _login(self):
  47         username, password = self._get_login_info()
  48         if username is None:
  49             if self._LOGIN_REQUIRED:
  50                 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
  51             return
  52         webpage = self._download_webpage(
  53             self._LOGIN_URL, None, 'Downloading login page')
  54         token, vuid = self._extract_xsrft_and_vuid(webpage)
  55         data = {
  56             'action': 'login',
  57             'email': username,
  58             'password': password,
  59             'service': 'vimeo',
  60             'token': token,
  61         }
  62         self._set_vimeo_cookie('vuid', vuid)
  63         try:
  64             self._download_webpage(
  65                 self._LOGIN_URL, None, 'Logging in',
  66                 data=urlencode_postdata(data), headers={
  67                     'Content-Type': 'application/x-www-form-urlencoded',
  68                     'Referer': self._LOGIN_URL,
  69                 })
  70         except ExtractorError as e:
  71             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418:
  72                 raise ExtractorError(
  73                     'Unable to log in: bad username or password',
  74                     expected=True)
  75             raise ExtractorError('Unable to log in')
  76
  77     def _verify_video_password(self, url, video_id, webpage):
  78         password = self._downloader.params.get('videopassword')
  79         if password is None:
  80             raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
  81         token, vuid = self._extract_xsrft_and_vuid(webpage)
  82         data = urlencode_postdata({
  83             'password': password,
  84             'token': token,
  85         })
  86         if url.startswith('http://'):
  87             # vimeo only supports https now, but the user can give an http url
  88             url = url.replace('http://', 'https://')
  89         password_request = sanitized_Request(url + '/password', data)
  90         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  91         password_request.add_header('Referer', url)
  92         self._set_vimeo_cookie('vuid', vuid)
  93         return self._download_webpage(
  94             password_request, video_id,
  95             'Verifying the password', 'Wrong password')
  96
  97     def _extract_xsrft_and_vuid(self, webpage):
  98         xsrft = self._search_regex(
  99             r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
 100             webpage, 'login token', group='xsrft')
 101         vuid = self._search_regex(
 102             r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
 103             webpage, 'vuid', group='vuid')
 104         return xsrft, vuid
 105
 106     def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
 107         vimeo_config = self._search_regex(
 108             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
 109             webpage, 'vimeo config', *args, **compat_kwargs(kwargs))
 110         if vimeo_config:
 111             return self._parse_json(vimeo_config, video_id)
 112
 113     def _set_vimeo_cookie(self, name, value):
 114         self._set_cookie('vimeo.com', name, value)
 115
 116     def _vimeo_sort_formats(self, formats):
 117         # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
 118         # at the same time without actual units specified. This lead to wrong sorting.
 119         self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'tbr', 'format_id'))
 120
 121     def _parse_config(self, config, video_id):
 122         video_data = config['video']
 123         video_title = video_data['title']
 124         live_event = video_data.get('live_event') or {}
 125         is_live = live_event.get('status') == 'started'
 126
 127         formats = []
 128         config_files = video_data.get('files') or config['request'].get('files', {})
 129         for f in config_files.get('progressive', []):
 130             video_url = f.get('url')
 131             if not video_url:
 132                 continue
 133             formats.append({
 134                 'url': video_url,
 135                 'format_id': 'http-%s' % f.get('quality'),
 136                 'width': int_or_none(f.get('width')),
 137                 'height': int_or_none(f.get('height')),
 138                 'fps': int_or_none(f.get('fps')),
 139                 'tbr': int_or_none(f.get('bitrate')),
 140             })
 141
 142         # TODO: fix handling of 308 status code returned for live archive manifest requests
 143         for files_type in ('hls', 'dash'):
 144             for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items():
 145                 manifest_url = cdn_data.get('url')
 146                 if not manifest_url:
 147                     continue
 148                 format_id = '%s-%s' % (files_type, cdn_name)
 149                 if files_type == 'hls':
 150                     formats.extend(self._extract_m3u8_formats(
 151                         manifest_url, video_id, 'mp4',
 152                         'm3u8' if is_live else 'm3u8_native', m3u8_id=format_id,
 153                         note='Downloading %s m3u8 information' % cdn_name,
 154                         fatal=False))
 155                 elif files_type == 'dash':
 156                     mpd_pattern = r'/%s/(?:sep/)?video/' % video_id
 157                     mpd_manifest_urls = []
 158                     if re.search(mpd_pattern, manifest_url):
 159                         for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
 160                             mpd_manifest_urls.append((format_id + suffix, re.sub(
 161                                 mpd_pattern, '/%s/%s/' % (video_id, repl), manifest_url)))
 162                     else:
 163                         mpd_manifest_urls = [(format_id, manifest_url)]
 164                     for f_id, m_url in mpd_manifest_urls:
 165                         if 'json=1' in m_url:
 166                             real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
 167                             if real_m_url:
 168                                 m_url = real_m_url
 169                         mpd_formats = self._extract_mpd_formats(
 170                             m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
 171                             'Downloading %s MPD information' % cdn_name,
 172                             fatal=False)
 173                         for f in mpd_formats:
 174                             if f.get('vcodec') == 'none':
 175                                 f['preference'] = -50
 176                             elif f.get('acodec') == 'none':
 177                                 f['preference'] = -40
 178                         formats.extend(mpd_formats)
 179
 180         live_archive = live_event.get('archive') or {}
 181         live_archive_source_url = live_archive.get('source_url')
 182         if live_archive_source_url and live_archive.get('status') == 'done':
 183             formats.append({
 184                 'format_id': 'live-archive-source',
 185                 'url': live_archive_source_url,
 186                 'preference': 1,
 187             })
 188
 189         subtitles = {}
 190         text_tracks = config['request'].get('text_tracks')
 191         if text_tracks:
 192             for tt in text_tracks:
 193                 subtitles[tt['lang']] = [{
 194                     'ext': 'vtt',
 195                     'url': urljoin('https://vimeo.com', tt['url']),
 196                 }]
 197
 198         thumbnails = []
 199         if not is_live:
 200             for key, thumb in video_data.get('thumbs', {}).items():
 201                 thumbnails.append({
 202                     'id': key,
 203                     'width': int_or_none(key),
 204                     'url': thumb,
 205                 })
 206             thumbnail = video_data.get('thumbnail')
 207             if thumbnail:
 208                 thumbnails.append({
 209                     'url': thumbnail,
 210                 })
 211
 212         owner = video_data.get('owner') or {}
 213         video_uploader_url = owner.get('url')
 214
 215         return {
 216             'id': str_or_none(video_data.get('id')) or video_id,
 217             'title': self._live_title(video_title) if is_live else video_title,
 218             'uploader': owner.get('name'),
 219             'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
 220             'uploader_url': video_uploader_url,
 221             'thumbnails': thumbnails,
 222             'duration': int_or_none(video_data.get('duration')),
 223             'formats': formats,
 224             'subtitles': subtitles,
 225             'is_live': is_live,
 226         }
 227
 228     def _extract_original_format(self, url, video_id):
 229         download_data = self._download_json(
 230             url, video_id, fatal=False,
 231             query={'action': 'load_download_config'},
 232             headers={'X-Requested-With': 'XMLHttpRequest'})
 233         if download_data:
 234             source_file = download_data.get('source_file')
 235             if isinstance(source_file, dict):
 236                 download_url = source_file.get('download_url')
 237                 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 238                     source_name = source_file.get('public_name', 'Original')
 239                     if self._is_valid_url(download_url, video_id, '%s video' % source_name):
 240                         ext = (try_get(
 241                             source_file, lambda x: x['extension'],
 242                             compat_str) or determine_ext(
 243                             download_url, None) or 'mp4').lower()
 244                         return {
 245                             'url': download_url,
 246                             'ext': ext,
 247                             'width': int_or_none(source_file.get('width')),
 248                             'height': int_or_none(source_file.get('height')),
 249                             'filesize': parse_filesize(source_file.get('size')),
 250                             'format_id': source_name,
 251                             'preference': 1,
 252                         }
 253
 254
 255 class VimeoIE(VimeoBaseInfoExtractor):
 256     """Information extractor for vimeo.com."""
 257
 258     # _VALID_URL matches Vimeo URLs
 259     _VALID_URL = r'''(?x)
 260                     https?://
 261                         (?:
 262                             (?:
 263                                 www|
 264                                 player
 265                             )
 266                             \.
 267                         )?
 268                         vimeo(?:pro)?\.com/
 269                         (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
 270                         (?:.*?/)?
 271                         (?:
 272                             (?:
 273                                 play_redirect_hls|
 274                                 moogaloop\.swf)\?clip_id=
 275                             )?
 276                         (?:videos?/)?
 277                         (?P<id>[0-9]+)
 278                         (?:/[\da-f]+)?
 279                         /?(?:[?&].*)?(?:[#].*)?$
 280                     '''
 281     IE_NAME = 'vimeo'
 282     _TESTS = [
 283         {
 284             'url': 'http://vimeo.com/56015672#at=0',
 285             'md5': '8879b6cc097e987f02484baf890129e5',
 286             'info_dict': {
 287                 'id': '56015672',
 288                 'ext': 'mp4',
 289                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
 290                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
 291                 'timestamp': 1355990239,
 292                 'upload_date': '20121220',
 293                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
 294                 'uploader_id': 'user7108434',
 295                 'uploader': 'Filippo Valsorda',
 296                 'duration': 10,
 297                 'license': 'by-sa',
 298             },
 299             'params': {
 300                 'format': 'best[protocol=https]',
 301             },
 302         },
 303         {
 304             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
 305             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
 306             'note': 'Vimeo Pro video (#1197)',
 307             'info_dict': {
 308                 'id': '68093876',
 309                 'ext': 'mp4',
 310                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
 311                 'uploader_id': 'openstreetmapus',
 312                 'uploader': 'OpenStreetMap US',
 313                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 314                 'description': 'md5:2c362968038d4499f4d79f88458590c1',
 315                 'duration': 1595,
 316                 'upload_date': '20130610',
 317                 'timestamp': 1370893156,
 318             },
 319             'params': {
 320                 'format': 'best[protocol=https]',
 321             },
 322         },
 323         {
 324             'url': 'http://player.vimeo.com/video/54469442',
 325             'md5': '619b811a4417aa4abe78dc653becf511',
 326             'note': 'Videos that embed the url in the player page',
 327             'info_dict': {
 328                 'id': '54469442',
 329                 'ext': 'mp4',
 330                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 331                 'uploader': 'The BLN & Business of Software',
 332                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
 333                 'uploader_id': 'theblnbusinessofsoftware',
 334                 'duration': 3610,
 335                 'description': None,
 336             },
 337             'params': {
 338                 'format': 'best[protocol=https]',
 339             },
 340             'expected_warnings': ['Unable to download JSON metadata'],
 341         },
 342         {
 343             'url': 'http://vimeo.com/68375962',
 344             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 345             'note': 'Video protected with password',
 346             'info_dict': {
 347                 'id': '68375962',
 348                 'ext': 'mp4',
 349                 'title': 'youtube-dl password protected test video',
 350                 'timestamp': 1371200155,
 351                 'upload_date': '20130614',
 352                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 353                 'uploader_id': 'user18948128',
 354                 'uploader': 'Jaime Marquínez Ferrándiz',
 355                 'duration': 10,
 356                 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
 357             },
 358             'params': {
 359                 'format': 'best[protocol=https]',
 360                 'videopassword': 'youtube-dl',
 361             },
 362         },
 363         {
 364             'url': 'http://vimeo.com/channels/keypeele/75629013',
 365             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 366             'info_dict': {
 367                 'id': '75629013',
 368                 'ext': 'mp4',
 369                 'title': 'Key & Peele: Terrorist Interrogation',
 370                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 371                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
 372                 'uploader_id': 'atencio',
 373                 'uploader': 'Peter Atencio',
 374                 'channel_id': 'keypeele',
 375                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
 376                 'timestamp': 1380339469,
 377                 'upload_date': '20130928',
 378                 'duration': 187,
 379             },
 380             'expected_warnings': ['Unable to download JSON metadata'],
 381         },
 382         {
 383             'url': 'http://vimeo.com/76979871',
 384             'note': 'Video with subtitles',
 385             'info_dict': {
 386                 'id': '76979871',
 387                 'ext': 'mp4',
 388                 'title': 'The New Vimeo Player (You Know, For Videos)',
 389                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 390                 'timestamp': 1381846109,
 391                 'upload_date': '20131015',
 392                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
 393                 'uploader_id': 'staff',
 394                 'uploader': 'Vimeo Staff',
 395                 'duration': 62,
 396             }
 397         },
 398         {
 399             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 400             'url': 'https://player.vimeo.com/video/98044508',
 401             'note': 'The js code contains assignments to the same variable as the config',
 402             'info_dict': {
 403                 'id': '98044508',
 404                 'ext': 'mp4',
 405                 'title': 'Pier Solar OUYA Official Trailer',
 406                 'uploader': 'Tulio Gonçalves',
 407                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
 408                 'uploader_id': 'user28849593',
 409             },
 410         },
 411         {
 412             # contains original format
 413             'url': 'https://vimeo.com/33951933',
 414             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 415             'info_dict': {
 416                 'id': '33951933',
 417                 'ext': 'mp4',
 418                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 419                 'uploader': 'The DMCI',
 420                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
 421                 'uploader_id': 'dmci',
 422                 'timestamp': 1324343742,
 423                 'upload_date': '20111220',
 424                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 425             },
 426         },
 427         {
 428             # only available via https://vimeo.com/channels/tributes/6213729 and
 429             # not via https://vimeo.com/6213729
 430             'url': 'https://vimeo.com/channels/tributes/6213729',
 431             'info_dict': {
 432                 'id': '6213729',
 433                 'ext': 'mp4',
 434                 'title': 'Vimeo Tribute: The Shining',
 435                 'uploader': 'Casey Donahue',
 436                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
 437                 'uploader_id': 'caseydonahue',
 438                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
 439                 'channel_id': 'tributes',
 440                 'timestamp': 1250886430,
 441                 'upload_date': '20090821',
 442                 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
 443             },
 444             'params': {
 445                 'skip_download': True,
 446             },
 447             'expected_warnings': ['Unable to download JSON metadata'],
 448         },
 449         {
 450             # redirects to ondemand extractor and should be passed through it
 451             # for successful extraction
 452             'url': 'https://vimeo.com/73445910',
 453             'info_dict': {
 454                 'id': '73445910',
 455                 'ext': 'mp4',
 456                 'title': 'The Reluctant Revolutionary',
 457                 'uploader': '10Ft Films',
 458                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
 459                 'uploader_id': 'tenfootfilms',
 460                 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
 461                 'upload_date': '20130830',
 462                 'timestamp': 1377853339,
 463             },
 464             'params': {
 465                 'skip_download': True,
 466             },
 467             'expected_warnings': ['Unable to download JSON metadata'],
 468         },
 469         {
 470             'url': 'http://player.vimeo.com/video/68375962',
 471             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 472             'info_dict': {
 473                 'id': '68375962',
 474                 'ext': 'mp4',
 475                 'title': 'youtube-dl password protected test video',
 476                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 477                 'uploader_id': 'user18948128',
 478                 'uploader': 'Jaime Marquínez Ferrándiz',
 479                 'duration': 10,
 480             },
 481             'params': {
 482                 'format': 'best[protocol=https]',
 483                 'videopassword': 'youtube-dl',
 484             },
 485         },
 486         {
 487             'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
 488             'only_matching': True,
 489         },
 490         {
 491             'url': 'https://vimeo.com/109815029',
 492             'note': 'Video not completely processed, "failed" seed status',
 493             'only_matching': True,
 494         },
 495         {
 496             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 497             'only_matching': True,
 498         },
 499         {
 500             'url': 'https://vimeo.com/album/2632481/video/79010983',
 501             'only_matching': True,
 502         },
 503         {
 504             # source file returns 403: Forbidden
 505             'url': 'https://vimeo.com/7809605',
 506             'only_matching': True,
 507         },
 508         {
 509             'url': 'https://vimeo.com/160743502/abd0e13fb4',
 510             'only_matching': True,
 511         }
 512         # https://gettingthingsdone.com/workflowmap/
 513         # vimeo embed with check-password page protected by Referer header
 514     ]
 515
 516     @staticmethod
 517     def _smuggle_referrer(url, referrer_url):
 518         return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
 519
 520     @staticmethod
 521     def _extract_urls(url, webpage):
 522         urls = []
 523         # Look for embedded (iframe) Vimeo player
 524         for mobj in re.finditer(
 525                 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
 526                 webpage):
 527             urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
 528         PLAIN_EMBED_RE = (
 529             # Look for embedded (swf embed) Vimeo player
 530             r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
 531             # Look more for non-standard embedded Vimeo player
 532             r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
 533         )
 534         for embed_re in PLAIN_EMBED_RE:
 535             for mobj in re.finditer(embed_re, webpage):
 536                 urls.append(mobj.group('url'))
 537         return urls
 538
 539     @staticmethod
 540     def _extract_url(url, webpage):
 541         urls = VimeoIE._extract_urls(url, webpage)
 542         return urls[0] if urls else None
 543
 544     def _verify_player_video_password(self, url, video_id, headers):
 545         password = self._downloader.params.get('videopassword')
 546         if password is None:
 547             raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
 548         data = urlencode_postdata({
 549             'password': base64.b64encode(password.encode()),
 550         })
 551         headers = merge_dicts(headers, {
 552             'Content-Type': 'application/x-www-form-urlencoded',
 553         })
 554         checked = self._download_json(
 555             url + '/check-password', video_id,
 556             'Verifying the password', data=data, headers=headers)
 557         if checked is False:
 558             raise ExtractorError('Wrong video password', expected=True)
 559         return checked
 560
 561     def _real_initialize(self):
 562         self._login()
 563
 564     def _real_extract(self, url):
 565         url, data = unsmuggle_url(url, {})
 566         headers = std_headers.copy()
 567         if 'http_headers' in data:
 568             headers.update(data['http_headers'])
 569         if 'Referer' not in headers:
 570             headers['Referer'] = url
 571
 572         channel_id = self._search_regex(
 573             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
 574
 575         # Extract ID from URL
 576         video_id = self._match_id(url)
 577         orig_url = url
 578         is_pro = 'vimeopro.com/' in url
 579         is_player = '://player.vimeo.com/video/' in url
 580         if is_pro:
 581             # some videos require portfolio_id to be present in player url
 582             # https://github.com/ytdl-org/youtube-dl/issues/20070
 583             url = self._extract_url(url, self._download_webpage(url, video_id))
 584             if not url:
 585                 url = 'https://vimeo.com/' + video_id
 586         elif is_player:
 587             url = 'https://player.vimeo.com/video/' + video_id
 588         elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
 589             url = 'https://vimeo.com/' + video_id
 590
 591         try:
 592             # Retrieve video webpage to extract further information
 593             webpage, urlh = self._download_webpage_handle(
 594                 url, video_id, headers=headers)
 595             redirect_url = urlh.geturl()
 596         except ExtractorError as ee:
 597             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 598                 errmsg = ee.cause.read()
 599                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 600                     raise ExtractorError(
 601                         'Cannot download embed-only video without embedding '
 602                         'URL. Please call youtube-dl with the URL of the page '
 603                         'that embeds this video.',
 604                         expected=True)
 605             raise
 606
 607         # Now we begin extracting as much information as we can from what we
 608         # retrieved. First we extract the information common to all extractors,
 609         # and latter we extract those that are Vimeo specific.
 610         self.report_extraction(video_id)
 611
 612         vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
 613         if vimeo_config:
 614             seed_status = vimeo_config.get('seed_status', {})
 615             if seed_status.get('state') == 'failed':
 616                 raise ExtractorError(
 617                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 618                     expected=True)
 619
 620         cc_license = None
 621         timestamp = None
 622         video_description = None
 623
 624         # Extract the config JSON
 625         try:
 626             try:
 627                 config_url = self._html_search_regex(
 628                     r' data-config-url="(.+?)"', webpage,
 629                     'config URL', default=None)
 630                 if not config_url:
 631                     # Sometimes new react-based page is served instead of old one that require
 632                     # different config URL extraction approach (see
 633                     # https://github.com/ytdl-org/youtube-dl/pull/7209)
 634                     page_config = self._parse_json(self._search_regex(
 635                         r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
 636                         webpage, 'page config'), video_id)
 637                     config_url = page_config['player']['config_url']
 638                     cc_license = page_config.get('cc_license')
 639                     timestamp = try_get(
 640                         page_config, lambda x: x['clip']['uploaded_on'],
 641                         compat_str)
 642                     video_description = clean_html(dict_get(
 643                         page_config, ('description', 'description_html_escaped')))
 644                 config = self._download_json(config_url, video_id)
 645             except RegexNotFoundError:
 646                 # For pro videos or player.vimeo.com urls
 647                 # We try to find out to which variable is assigned the config dic
 648                 m_variable_name = re.search(r'(\w)\.video\.id', webpage)
 649                 if m_variable_name is not None:
 650                     config_re = [r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))]
 651                 else:
 652                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
 653                 config_re.append(r'\bvar\s+r\s*=\s*({.+?})\s*;')
 654                 config_re.append(r'\bconfig\s*=\s*({.+?})\s*;')
 655                 config = self._search_regex(config_re, webpage, 'info section',
 656                                             flags=re.DOTALL)
 657                 config = json.loads(config)
 658         except Exception as e:
 659             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
 660                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 661
 662             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
 663                 if '_video_password_verified' in data:
 664                     raise ExtractorError('video password verification failed!')
 665                 self._verify_video_password(redirect_url, video_id, webpage)
 666                 return self._real_extract(
 667                     smuggle_url(redirect_url, {'_video_password_verified': 'verified'}))
 668             else:
 669                 raise ExtractorError('Unable to extract info section',
 670                                      cause=e)
 671         else:
 672             if config.get('view') == 4:
 673                 config = self._verify_player_video_password(redirect_url, video_id, headers)
 674
 675         vod = config.get('video', {}).get('vod', {})
 676
 677         def is_rented():
 678             if '>You rented this title.<' in webpage:
 679                 return True
 680             if config.get('user', {}).get('purchased'):
 681                 return True
 682             for purchase_option in vod.get('purchase_options', []):
 683                 if purchase_option.get('purchased'):
 684                     return True
 685                 label = purchase_option.get('label_string')
 686                 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
 687                     return True
 688             return False
 689
 690         if is_rented() and vod.get('is_trailer'):
 691             feature_id = vod.get('feature_id')
 692             if feature_id and not data.get('force_feature_id', False):
 693                 return self.url_result(smuggle_url(
 694                     'https://player.vimeo.com/player/%s' % feature_id,
 695                     {'force_feature_id': True}), 'Vimeo')
 696
 697         # Extract video description
 698         if not video_description:
 699             video_description = self._html_search_regex(
 700                 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 701                 webpage, 'description', default=None)
 702         if not video_description:
 703             video_description = self._html_search_meta(
 704                 'description', webpage, default=None)
 705         if not video_description and is_pro:
 706             orig_webpage = self._download_webpage(
 707                 orig_url, video_id,
 708                 note='Downloading webpage for description',
 709                 fatal=False)
 710             if orig_webpage:
 711                 video_description = self._html_search_meta(
 712                     'description', orig_webpage, default=None)
 713         if not video_description and not is_player:
 714             self._downloader.report_warning('Cannot find video description')
 715
 716         # Extract upload date
 717         if not timestamp:
 718             timestamp = self._search_regex(
 719                 r'<time[^>]+datetime="([^"]+)"', webpage,
 720                 'timestamp', default=None)
 721
 722         try:
 723             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
 724             like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
 725             comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
 726         except RegexNotFoundError:
 727             # This info is only available in vimeo.com/{id} urls
 728             view_count = None
 729             like_count = None
 730             comment_count = None
 731
 732         formats = []
 733
 734         source_format = self._extract_original_format(
 735             'https://vimeo.com/' + video_id, video_id)
 736         if source_format:
 737             formats.append(source_format)
 738
 739         info_dict_config = self._parse_config(config, video_id)
 740         formats.extend(info_dict_config['formats'])
 741         self._vimeo_sort_formats(formats)
 742
 743         json_ld = self._search_json_ld(webpage, video_id, default={})
 744
 745         if not cc_license:
 746             cc_license = self._search_regex(
 747                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
 748                 webpage, 'license', default=None, group='license')
 749
 750         channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
 751
 752         info_dict = {
 753             'formats': formats,
 754             'timestamp': unified_timestamp(timestamp),
 755             'description': video_description,
 756             'webpage_url': url,
 757             'view_count': view_count,
 758             'like_count': like_count,
 759             'comment_count': comment_count,
 760             'license': cc_license,
 761             'channel_id': channel_id,
 762             'channel_url': channel_url,
 763         }
 764
 765         info_dict = merge_dicts(info_dict, info_dict_config, json_ld)
 766
 767         return info_dict
 768
 769
 770 class VimeoOndemandIE(VimeoIE):
 771     IE_NAME = 'vimeo:ondemand'
 772     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/([^/]+/)?(?P<id>[^/?#&]+)'
 773     _TESTS = [{
 774         # ondemand video not available via https://vimeo.com/id
 775         'url': 'https://vimeo.com/ondemand/20704',
 776         'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
 777         'info_dict': {
 778             'id': '105442900',
 779             'ext': 'mp4',
 780             'title': 'המעבדה - במאי יותם פלדמן',
 781             'uploader': 'גם סרטים',
 782             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
 783             'uploader_id': 'gumfilms',
 784             'description': 'md5:4c027c965e439de4baab621e48b60791',
 785             'upload_date': '20140906',
 786             'timestamp': 1410032453,
 787         },
 788         'params': {
 789             'format': 'best[protocol=https]',
 790         },
 791         'expected_warnings': ['Unable to download JSON metadata'],
 792     }, {
 793         # requires Referer to be passed along with og:video:url
 794         'url': 'https://vimeo.com/ondemand/36938/126682985',
 795         'info_dict': {
 796             'id': '126584684',
 797             'ext': 'mp4',
 798             'title': 'Rävlock, rätt läte på rätt plats',
 799             'uploader': 'Lindroth & Norin',
 800             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
 801             'uploader_id': 'lindrothnorin',
 802             'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
 803             'upload_date': '20150502',
 804             'timestamp': 1430586422,
 805         },
 806         'params': {
 807             'skip_download': True,
 808         },
 809         'expected_warnings': ['Unable to download JSON metadata'],
 810     }, {
 811         'url': 'https://vimeo.com/ondemand/nazmaalik',
 812         'only_matching': True,
 813     }, {
 814         'url': 'https://vimeo.com/ondemand/141692381',
 815         'only_matching': True,
 816     }, {
 817         'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
 818         'only_matching': True,
 819     }]
 820
 821
 822 class VimeoChannelIE(VimeoBaseInfoExtractor):
 823     IE_NAME = 'vimeo:channel'
 824     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 825     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 826     _TITLE = None
 827     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 828     _TESTS = [{
 829         'url': 'https://vimeo.com/channels/tributes',
 830         'info_dict': {
 831             'id': 'tributes',
 832             'title': 'Vimeo Tributes',
 833         },
 834         'playlist_mincount': 25,
 835     }]
 836     _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
 837
 838     def _page_url(self, base_url, pagenum):
 839         return '%s/videos/page:%d/' % (base_url, pagenum)
 840
 841     def _extract_list_title(self, webpage):
 842         return self._TITLE or self._html_search_regex(
 843             self._TITLE_RE, webpage, 'list title', fatal=False)
 844
 845     def _title_and_entries(self, list_id, base_url):
 846         for pagenum in itertools.count(1):
 847             page_url = self._page_url(base_url, pagenum)
 848             webpage = self._download_webpage(
 849                 page_url, list_id,
 850                 'Downloading page %s' % pagenum)
 851
 852             if pagenum == 1:
 853                 yield self._extract_list_title(webpage)
 854
 855             # Try extracting href first since not all videos are available via
 856             # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
 857             clips = re.findall(
 858                 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
 859             if clips:
 860                 for video_id, video_url, video_title in clips:
 861                     yield self.url_result(
 862                         compat_urlparse.urljoin(base_url, video_url),
 863                         VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
 864             # More relaxed fallback
 865             else:
 866                 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
 867                     yield self.url_result(
 868                         'https://vimeo.com/%s' % video_id,
 869                         VimeoIE.ie_key(), video_id=video_id)
 870
 871             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
 872                 break
 873
 874     def _extract_videos(self, list_id, base_url):
 875         title_and_entries = self._title_and_entries(list_id, base_url)
 876         list_title = next(title_and_entries)
 877         return self.playlist_result(title_and_entries, list_id, list_title)
 878
 879     def _real_extract(self, url):
 880         channel_id = self._match_id(url)
 881         return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
 882
 883
 884 class VimeoUserIE(VimeoChannelIE):
 885     IE_NAME = 'vimeo:user'
 886     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
 887     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
 888     _TESTS = [{
 889         'url': 'https://vimeo.com/nkistudio/videos',
 890         'info_dict': {
 891             'title': 'Nki',
 892             'id': 'nkistudio',
 893         },
 894         'playlist_mincount': 66,
 895     }]
 896     _BASE_URL_TEMPL = 'https://vimeo.com/%s'
 897
 898
 899 class VimeoAlbumIE(VimeoBaseInfoExtractor):
 900     IE_NAME = 'vimeo:album'
 901     _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
 902     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
 903     _TESTS = [{
 904         'url': 'https://vimeo.com/album/2632481',
 905         'info_dict': {
 906             'id': '2632481',
 907             'title': 'Staff Favorites: November 2013',
 908         },
 909         'playlist_mincount': 13,
 910     }, {
 911         'note': 'Password-protected album',
 912         'url': 'https://vimeo.com/album/3253534',
 913         'info_dict': {
 914             'title': 'test',
 915             'id': '3253534',
 916         },
 917         'playlist_count': 1,
 918         'params': {
 919             'videopassword': 'youtube-dl',
 920         }
 921     }]
 922     _PAGE_SIZE = 100
 923
 924     def _fetch_page(self, album_id, authorizaion, hashed_pass, page):
 925         api_page = page + 1
 926         query = {
 927             'fields': 'link,uri',
 928             'page': api_page,
 929             'per_page': self._PAGE_SIZE,
 930         }
 931         if hashed_pass:
 932             query['_hashed_pass'] = hashed_pass
 933         videos = self._download_json(
 934             'https://api.vimeo.com/albums/%s/videos' % album_id,
 935             album_id, 'Downloading page %d' % api_page, query=query, headers={
 936                 'Authorization': 'jwt ' + authorizaion,
 937             })['data']
 938         for video in videos:
 939             link = video.get('link')
 940             if not link:
 941                 continue
 942             uri = video.get('uri')
 943             video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
 944             yield self.url_result(link, VimeoIE.ie_key(), video_id)
 945
 946     def _real_extract(self, url):
 947         album_id = self._match_id(url)
 948         webpage = self._download_webpage(url, album_id)
 949         viewer = self._parse_json(self._search_regex(
 950             r'bootstrap_data\s*=\s*({.+?})</script>',
 951             webpage, 'bootstrap data'), album_id)['viewer']
 952         jwt = viewer['jwt']
 953         album = self._download_json(
 954             'https://api.vimeo.com/albums/' + album_id,
 955             album_id, headers={'Authorization': 'jwt ' + jwt},
 956             query={'fields': 'description,name,privacy'})
 957         hashed_pass = None
 958         if try_get(album, lambda x: x['privacy']['view']) == 'password':
 959             password = self._downloader.params.get('videopassword')
 960             if not password:
 961                 raise ExtractorError(
 962                     'This album is protected by a password, use the --video-password option',
 963                     expected=True)
 964             self._set_vimeo_cookie('vuid', viewer['vuid'])
 965             try:
 966                 hashed_pass = self._download_json(
 967                     'https://vimeo.com/showcase/%s/auth' % album_id,
 968                     album_id, 'Verifying the password', data=urlencode_postdata({
 969                         'password': password,
 970                         'token': viewer['xsrft'],
 971                     }), headers={
 972                         'X-Requested-With': 'XMLHttpRequest',
 973                     })['hashed_pass']
 974             except ExtractorError as e:
 975                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
 976                     raise ExtractorError('Wrong password', expected=True)
 977                 raise
 978         entries = OnDemandPagedList(functools.partial(
 979             self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
 980         return self.playlist_result(
 981             entries, album_id, album.get('name'), album.get('description'))
 982
 983
 984 class VimeoGroupsIE(VimeoChannelIE):
 985     IE_NAME = 'vimeo:group'
 986     _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
 987     _TESTS = [{
 988         'url': 'https://vimeo.com/groups/kattykay',
 989         'info_dict': {
 990             'id': 'kattykay',
 991             'title': 'Katty Kay',
 992         },
 993         'playlist_mincount': 27,
 994     }]
 995     _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
 996
 997
 998 class VimeoReviewIE(VimeoBaseInfoExtractor):
 999     IE_NAME = 'vimeo:review'
1000     IE_DESC = 'Review pages on vimeo'
1001     _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
1002     _TESTS = [{
1003         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1004         'md5': 'c507a72f780cacc12b2248bb4006d253',
1005         'info_dict': {
1006             'id': '75524534',
1007             'ext': 'mp4',
1008             'title': "DICK HARDWICK 'Comedian'",
1009             'uploader': 'Richard Hardwick',
1010             'uploader_id': 'user21297594',
1011             'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1012         },
1013         'expected_warnings': ['Unable to download JSON metadata'],
1014     }, {
1015         'note': 'video player needs Referer',
1016         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1017         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1018         'info_dict': {
1019             'id': '91613211',
1020             'ext': 'mp4',
1021             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1022             'uploader': 'DevWeek Events',
1023             'duration': 2773,
1024             'thumbnail': r're:^https?://.*\.jpg$',
1025             'uploader_id': 'user22258446',
1026         },
1027         'skip': 'video gone',
1028     }, {
1029         'note': 'Password protected',
1030         'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1031         'info_dict': {
1032             'id': '138823582',
1033             'ext': 'mp4',
1034             'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1035             'uploader': 'TMB',
1036             'uploader_id': 'user37284429',
1037         },
1038         'params': {
1039             'videopassword': 'holygrail',
1040         },
1041         'skip': 'video gone',
1042     }]
1043
1044     def _real_initialize(self):
1045         self._login()
1046
1047     def _real_extract(self, url):
1048         page_url, video_id = re.match(self._VALID_URL, url).groups()
1049         clip_data = self._download_json(
1050             page_url.replace('/review/', '/review/data/'),
1051             video_id)['clipData']
1052         config_url = clip_data['configUrl']
1053         config = self._download_json(config_url, video_id)
1054         info_dict = self._parse_config(config, video_id)
1055         source_format = self._extract_original_format(
1056             page_url + '/action', video_id)
1057         if source_format:
1058             info_dict['formats'].append(source_format)
1059         self._vimeo_sort_formats(info_dict['formats'])
1060         info_dict['description'] = clean_html(clip_data.get('description'))
1061         return info_dict
1062
1063
1064 class VimeoWatchLaterIE(VimeoChannelIE):
1065     IE_NAME = 'vimeo:watchlater'
1066     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
1067     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1068     _TITLE = 'Watch Later'
1069     _LOGIN_REQUIRED = True
1070     _TESTS = [{
1071         'url': 'https://vimeo.com/watchlater',
1072         'only_matching': True,
1073     }]
1074
1075     def _real_initialize(self):
1076         self._login()
1077
1078     def _page_url(self, base_url, pagenum):
1079         url = '%s/page:%d/' % (base_url, pagenum)
1080         request = sanitized_Request(url)
1081         # Set the header to get a partial html page with the ids,
1082         # the normal page doesn't contain them.
1083         request.add_header('X-Requested-With', 'XMLHttpRequest')
1084         return request
1085
1086     def _real_extract(self, url):
1087         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1088
1089
1090 class VimeoLikesIE(VimeoChannelIE):
1091     _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1092     IE_NAME = 'vimeo:likes'
1093     IE_DESC = 'Vimeo user likes'
1094     _TESTS = [{
1095         'url': 'https://vimeo.com/user755559/likes/',
1096         'playlist_mincount': 293,
1097         'info_dict': {
1098             'id': 'user755559',
1099             'title': 'urza’s Likes',
1100         },
1101     }, {
1102         'url': 'https://vimeo.com/stormlapse/likes',
1103         'only_matching': True,
1104     }]
1105
1106     def _page_url(self, base_url, pagenum):
1107         return '%s/page:%d/' % (base_url, pagenum)
1108
1109     def _real_extract(self, url):
1110         user_id = self._match_id(url)
1111         return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
1112
1113
1114 class VHXEmbedIE(VimeoBaseInfoExtractor):
1115     IE_NAME = 'vhx:embed'
1116     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1117
1118     def _real_extract(self, url):
1119         video_id = self._match_id(url)
1120         webpage = self._download_webpage(url, video_id)
1121         config_url = self._parse_json(self._search_regex(
1122             r'window\.OTTData\s*=\s*({.+})', webpage,
1123             'ott data'), video_id, js_to_json)['config_url']
1124         config = self._download_json(config_url, video_id)
1125         info = self._parse_config(config, video_id)
1126         self._vimeo_sort_formats(info['formats'])
1127         return info