yt_dlp/extractor/vimeo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import base64
   5 import functools
   6 import re
   7 import itertools
   8
   9 from .common import InfoExtractor
  10 from ..compat import (
  11     compat_kwargs,
  12     compat_HTTPError,
  13     compat_str,
  14     compat_urlparse,
  15 )
  16 from ..utils import (
  17     clean_html,
  18     determine_ext,
  19     ExtractorError,
  20     get_element_by_class,
  21     HEADRequest,
  22     js_to_json,
  23     int_or_none,
  24     merge_dicts,
  25     OnDemandPagedList,
  26     parse_filesize,
  27     parse_iso8601,
  28     parse_qs,
  29     sanitized_Request,
  30     smuggle_url,
  31     std_headers,
  32     str_or_none,
  33     try_get,
  34     unified_timestamp,
  35     unsmuggle_url,
  36     urlencode_postdata,
  37     urljoin,
  38     unescapeHTML,
  39     urlhandle_detect_ext,
  40 )
  41
  42
  43 class VimeoBaseInfoExtractor(InfoExtractor):
  44     _NETRC_MACHINE = 'vimeo'
  45     _LOGIN_REQUIRED = False
  46     _LOGIN_URL = 'https://vimeo.com/log_in'
  47
  48     def _login(self):
  49         username, password = self._get_login_info()
  50         if username is None:
  51             if self._LOGIN_REQUIRED:
  52                 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
  53             return
  54         webpage = self._download_webpage(
  55             self._LOGIN_URL, None, 'Downloading login page')
  56         token, vuid = self._extract_xsrft_and_vuid(webpage)
  57         data = {
  58             'action': 'login',
  59             'email': username,
  60             'password': password,
  61             'service': 'vimeo',
  62             'token': token,
  63         }
  64         self._set_vimeo_cookie('vuid', vuid)
  65         try:
  66             self._download_webpage(
  67                 self._LOGIN_URL, None, 'Logging in',
  68                 data=urlencode_postdata(data), headers={
  69                     'Content-Type': 'application/x-www-form-urlencoded',
  70                     'Referer': self._LOGIN_URL,
  71                 })
  72         except ExtractorError as e:
  73             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418:
  74                 raise ExtractorError(
  75                     'Unable to log in: bad username or password',
  76                     expected=True)
  77             raise ExtractorError('Unable to log in')
  78
  79     def _get_video_password(self):
  80         password = self.get_param('videopassword')
  81         if password is None:
  82             raise ExtractorError(
  83                 'This video is protected by a password, use the --video-password option',
  84                 expected=True)
  85         return password
  86
  87     def _verify_video_password(self, url, video_id, password, token, vuid):
  88         if url.startswith('http://'):
  89             # vimeo only supports https now, but the user can give an http url
  90             url = url.replace('http://', 'https://')
  91         self._set_vimeo_cookie('vuid', vuid)
  92         return self._download_webpage(
  93             url + '/password', video_id, 'Verifying the password',
  94             'Wrong password', data=urlencode_postdata({
  95                 'password': password,
  96                 'token': token,
  97             }), headers={
  98                 'Content-Type': 'application/x-www-form-urlencoded',
  99                 'Referer': url,
 100             })
 101
 102     def _extract_xsrft_and_vuid(self, webpage):
 103         xsrft = self._search_regex(
 104             r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
 105             webpage, 'login token', group='xsrft')
 106         vuid = self._search_regex(
 107             r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
 108             webpage, 'vuid', group='vuid')
 109         return xsrft, vuid
 110
 111     def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
 112         vimeo_config = self._search_regex(
 113             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
 114             webpage, 'vimeo config', *args, **compat_kwargs(kwargs))
 115         if vimeo_config:
 116             return self._parse_json(vimeo_config, video_id)
 117
 118     def _set_vimeo_cookie(self, name, value):
 119         self._set_cookie('vimeo.com', name, value)
 120
 121     def _vimeo_sort_formats(self, formats):
 122         # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
 123         # at the same time without actual units specified. This lead to wrong sorting.
 124         # But since yt-dlp prefers 'res,fps' anyway, 'field_preference' is not needed
 125         self._sort_formats(formats)
 126
 127     def _parse_config(self, config, video_id):
 128         video_data = config['video']
 129         video_title = video_data['title']
 130         live_event = video_data.get('live_event') or {}
 131         is_live = live_event.get('status') == 'started'
 132         request = config.get('request') or {}
 133
 134         formats = []
 135         config_files = video_data.get('files') or request.get('files') or {}
 136         for f in (config_files.get('progressive') or []):
 137             video_url = f.get('url')
 138             if not video_url:
 139                 continue
 140             formats.append({
 141                 'url': video_url,
 142                 'format_id': 'http-%s' % f.get('quality'),
 143                 'width': int_or_none(f.get('width')),
 144                 'height': int_or_none(f.get('height')),
 145                 'fps': int_or_none(f.get('fps')),
 146                 'tbr': int_or_none(f.get('bitrate')),
 147             })
 148
 149         # TODO: fix handling of 308 status code returned for live archive manifest requests
 150         sep_pattern = r'/sep/video/'
 151         for files_type in ('hls', 'dash'):
 152             for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items():
 153                 manifest_url = cdn_data.get('url')
 154                 if not manifest_url:
 155                     continue
 156                 format_id = '%s-%s' % (files_type, cdn_name)
 157                 sep_manifest_urls = []
 158                 if re.search(sep_pattern, manifest_url):
 159                     for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
 160                         sep_manifest_urls.append((format_id + suffix, re.sub(
 161                             sep_pattern, '/%s/' % repl, manifest_url)))
 162                 else:
 163                     sep_manifest_urls = [(format_id, manifest_url)]
 164                 for f_id, m_url in sep_manifest_urls:
 165                     if files_type == 'hls':
 166                         formats.extend(self._extract_m3u8_formats(
 167                             m_url, video_id, 'mp4',
 168                             'm3u8' if is_live else 'm3u8_native', m3u8_id=f_id,
 169                             note='Downloading %s m3u8 information' % cdn_name,
 170                             fatal=False))
 171                     elif files_type == 'dash':
 172                         if 'json=1' in m_url:
 173                             real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
 174                             if real_m_url:
 175                                 m_url = real_m_url
 176                         mpd_formats = self._extract_mpd_formats(
 177                             m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
 178                             'Downloading %s MPD information' % cdn_name,
 179                             fatal=False)
 180                         formats.extend(mpd_formats)
 181
 182         live_archive = live_event.get('archive') or {}
 183         live_archive_source_url = live_archive.get('source_url')
 184         if live_archive_source_url and live_archive.get('status') == 'done':
 185             formats.append({
 186                 'format_id': 'live-archive-source',
 187                 'url': live_archive_source_url,
 188                 'quality': 10,
 189             })
 190
 191         subtitles = {}
 192         for tt in (request.get('text_tracks') or []):
 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') or {}).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, unlisted_hash=None):
 229         query = {'action': 'load_download_config'}
 230         if unlisted_hash:
 231             query['unlisted_hash'] = unlisted_hash
 232         download_data = self._download_json(
 233             url, video_id, fatal=False, query=query,
 234             headers={'X-Requested-With': 'XMLHttpRequest'},
 235             expected_status=(403, 404)) or {}
 236         source_file = download_data.get('source_file')
 237         download_url = try_get(source_file, lambda x: x['download_url'])
 238         if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 239             source_name = source_file.get('public_name', 'Original')
 240             if self._is_valid_url(download_url, video_id, '%s video' % source_name):
 241                 ext = (try_get(
 242                     source_file, lambda x: x['extension'],
 243                     compat_str) or determine_ext(
 244                     download_url, None) or 'mp4').lower()
 245                 return {
 246                     'url': download_url,
 247                     'ext': ext,
 248                     'width': int_or_none(source_file.get('width')),
 249                     'height': int_or_none(source_file.get('height')),
 250                     'filesize': parse_filesize(source_file.get('size')),
 251                     'format_id': source_name,
 252                     'quality': 1,
 253                 }
 254
 255         jwt_response = self._download_json(
 256             'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {}
 257         if not jwt_response.get('jwt'):
 258             return
 259         headers = {'Authorization': 'jwt %s' % jwt_response['jwt']}
 260         original_response = self._download_json(
 261             f'https://api.vimeo.com/videos/{video_id}', video_id,
 262             headers=headers, fatal=False, expected_status=(403, 404)) or {}
 263         for download_data in original_response.get('download') or []:
 264             download_url = download_data.get('link')
 265             if not download_url or download_data.get('quality') != 'source':
 266                 continue
 267             ext = determine_ext(parse_qs(download_url).get('filename', [''])[0].lower(), default_ext=None)
 268             if not ext:
 269                 urlh = self._request_webpage(
 270                     HEADRequest(download_url), video_id, fatal=False, note='Determining source extension')
 271                 ext = urlh and urlhandle_detect_ext(urlh)
 272             return {
 273                 'url': download_url,
 274                 'ext': ext or 'unknown_video',
 275                 'format_id': download_data.get('public_name', 'Original'),
 276                 'width': int_or_none(download_data.get('width')),
 277                 'height': int_or_none(download_data.get('height')),
 278                 'fps': int_or_none(download_data.get('fps')),
 279                 'filesize': int_or_none(download_data.get('size')),
 280                 'quality': 1,
 281             }
 282
 283
 284 class VimeoIE(VimeoBaseInfoExtractor):
 285     """Information extractor for vimeo.com."""
 286
 287     # _VALID_URL matches Vimeo URLs
 288     _VALID_URL = r'''(?x)
 289                     https?://
 290                         (?:
 291                             (?:
 292                                 www|
 293                                 player
 294                             )
 295                             \.
 296                         )?
 297                         vimeo(?:pro)?\.com/
 298                         (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
 299                         (?:[^/]+/)*?
 300                         (?:
 301                             (?:
 302                                 play_redirect_hls|
 303                                 moogaloop\.swf)\?clip_id=
 304                             )?
 305                         (?:videos?/)?
 306                         (?P<id>[0-9]+)
 307                         (?:/(?P<unlisted_hash>[\da-f]{10}))?
 308                         /?(?:[?&].*)?(?:[#].*)?$
 309                     '''
 310     IE_NAME = 'vimeo'
 311     _TESTS = [
 312         {
 313             'url': 'http://vimeo.com/56015672#at=0',
 314             'md5': '8879b6cc097e987f02484baf890129e5',
 315             'info_dict': {
 316                 'id': '56015672',
 317                 'ext': 'mp4',
 318                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
 319                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
 320                 'timestamp': 1355990239,
 321                 'upload_date': '20121220',
 322                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
 323                 'uploader_id': 'user7108434',
 324                 'uploader': 'Filippo Valsorda',
 325                 'duration': 10,
 326                 'license': 'by-sa',
 327             },
 328             'params': {
 329                 'format': 'best[protocol=https]',
 330             },
 331         },
 332         {
 333             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
 334             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
 335             'note': 'Vimeo Pro video (#1197)',
 336             'info_dict': {
 337                 'id': '68093876',
 338                 'ext': 'mp4',
 339                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
 340                 'uploader_id': 'openstreetmapus',
 341                 'uploader': 'OpenStreetMap US',
 342                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 343                 'description': 'md5:2c362968038d4499f4d79f88458590c1',
 344                 'duration': 1595,
 345                 'upload_date': '20130610',
 346                 'timestamp': 1370893156,
 347                 'license': 'by',
 348             },
 349             'params': {
 350                 'format': 'best[protocol=https]',
 351             },
 352         },
 353         {
 354             'url': 'http://player.vimeo.com/video/54469442',
 355             'md5': '619b811a4417aa4abe78dc653becf511',
 356             'note': 'Videos that embed the url in the player page',
 357             'info_dict': {
 358                 'id': '54469442',
 359                 'ext': 'mp4',
 360                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 361                 'uploader': 'Business of Software',
 362                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
 363                 'uploader_id': 'businessofsoftware',
 364                 'duration': 3610,
 365                 'description': None,
 366             },
 367             'params': {
 368                 'format': 'best[protocol=https]',
 369             },
 370         },
 371         {
 372             'url': 'http://vimeo.com/68375962',
 373             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 374             'note': 'Video protected with password',
 375             'info_dict': {
 376                 'id': '68375962',
 377                 'ext': 'mp4',
 378                 'title': 'youtube-dl password protected test video',
 379                 'timestamp': 1371200155,
 380                 'upload_date': '20130614',
 381                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 382                 'uploader_id': 'user18948128',
 383                 'uploader': 'Jaime Marquínez Ferrándiz',
 384                 'duration': 10,
 385                 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
 386             },
 387             'params': {
 388                 'format': 'best[protocol=https]',
 389                 'videopassword': 'youtube-dl',
 390             },
 391         },
 392         {
 393             'url': 'http://vimeo.com/channels/keypeele/75629013',
 394             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 395             'info_dict': {
 396                 'id': '75629013',
 397                 'ext': 'mp4',
 398                 'title': 'Key & Peele: Terrorist Interrogation',
 399                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 400                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
 401                 'uploader_id': 'atencio',
 402                 'uploader': 'Peter Atencio',
 403                 'channel_id': 'keypeele',
 404                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
 405                 'timestamp': 1380339469,
 406                 'upload_date': '20130928',
 407                 'duration': 187,
 408             },
 409             'params': {'format': 'http-1080p'},
 410         },
 411         {
 412             'url': 'http://vimeo.com/76979871',
 413             'note': 'Video with subtitles',
 414             'info_dict': {
 415                 'id': '76979871',
 416                 'ext': 'mp4',
 417                 'title': 'The New Vimeo Player (You Know, For Videos)',
 418                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 419                 'timestamp': 1381846109,
 420                 'upload_date': '20131015',
 421                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
 422                 'uploader_id': 'staff',
 423                 'uploader': 'Vimeo Staff',
 424                 'duration': 62,
 425                 'subtitles': {
 426                     'de': [{'ext': 'vtt'}],
 427                     'en': [{'ext': 'vtt'}],
 428                     'es': [{'ext': 'vtt'}],
 429                     'fr': [{'ext': 'vtt'}],
 430                 },
 431             },
 432             'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
 433         },
 434         {
 435             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 436             'url': 'https://player.vimeo.com/video/98044508',
 437             'note': 'The js code contains assignments to the same variable as the config',
 438             'info_dict': {
 439                 'id': '98044508',
 440                 'ext': 'mp4',
 441                 'title': 'Pier Solar OUYA Official Trailer',
 442                 'uploader': 'Tulio Gonçalves',
 443                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
 444                 'uploader_id': 'user28849593',
 445             },
 446         },
 447         {
 448             # contains original format
 449             'url': 'https://vimeo.com/33951933',
 450             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 451             'info_dict': {
 452                 'id': '33951933',
 453                 'ext': 'mp4',
 454                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 455                 'uploader': 'The DMCI',
 456                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
 457                 'uploader_id': 'dmci',
 458                 'timestamp': 1324343742,
 459                 'upload_date': '20111220',
 460                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 461             },
 462         },
 463         {
 464             'note': 'Contains original format not accessible in webpage',
 465             'url': 'https://vimeo.com/393756517',
 466             'md5': 'c464af248b592190a5ffbb5d33f382b0',
 467             'info_dict': {
 468                 'id': '393756517',
 469                 'ext': 'mov',
 470                 'timestamp': 1582642091,
 471                 'uploader_id': 'frameworkla',
 472                 'title': 'Straight To Hell - Sabrina: Netflix',
 473                 'uploader': 'Framework Studio',
 474                 'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
 475                 'upload_date': '20200225',
 476             },
 477         },
 478         {
 479             # only available via https://vimeo.com/channels/tributes/6213729 and
 480             # not via https://vimeo.com/6213729
 481             'url': 'https://vimeo.com/channels/tributes/6213729',
 482             'info_dict': {
 483                 'id': '6213729',
 484                 'ext': 'mp4',
 485                 'title': 'Vimeo Tribute: The Shining',
 486                 'uploader': 'Casey Donahue',
 487                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
 488                 'uploader_id': 'caseydonahue',
 489                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
 490                 'channel_id': 'tributes',
 491                 'timestamp': 1250886430,
 492                 'upload_date': '20090821',
 493                 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
 494             },
 495             'params': {
 496                 'skip_download': True,
 497             },
 498         },
 499         {
 500             # redirects to ondemand extractor and should be passed through it
 501             # for successful extraction
 502             'url': 'https://vimeo.com/73445910',
 503             'info_dict': {
 504                 'id': '73445910',
 505                 'ext': 'mp4',
 506                 'title': 'The Reluctant Revolutionary',
 507                 'uploader': '10Ft Films',
 508                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
 509                 'uploader_id': 'tenfootfilms',
 510                 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
 511                 'upload_date': '20130830',
 512                 'timestamp': 1377853339,
 513             },
 514             'params': {
 515                 'skip_download': True,
 516             },
 517             'skip': 'this page is no longer available.',
 518         },
 519         {
 520             'url': 'http://player.vimeo.com/video/68375962',
 521             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 522             'info_dict': {
 523                 'id': '68375962',
 524                 'ext': 'mp4',
 525                 'title': 'youtube-dl password protected test video',
 526                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 527                 'uploader_id': 'user18948128',
 528                 'uploader': 'Jaime Marquínez Ferrándiz',
 529                 'duration': 10,
 530             },
 531             'params': {
 532                 'format': 'best[protocol=https]',
 533                 'videopassword': 'youtube-dl',
 534             },
 535         },
 536         {
 537             'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
 538             'only_matching': True,
 539         },
 540         {
 541             'url': 'https://vimeo.com/109815029',
 542             'note': 'Video not completely processed, "failed" seed status',
 543             'only_matching': True,
 544         },
 545         {
 546             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 547             'only_matching': True,
 548         },
 549         {
 550             'url': 'https://vimeo.com/album/2632481/video/79010983',
 551             'only_matching': True,
 552         },
 553         {
 554             'url': 'https://vimeo.com/showcase/3253534/video/119195465',
 555             'note': 'A video in a password protected album (showcase)',
 556             'info_dict': {
 557                 'id': '119195465',
 558                 'ext': 'mp4',
 559                 'title': 'youtube-dl test video \'ä"BaW_jenozKc',
 560                 'uploader': 'Philipp Hagemeister',
 561                 'uploader_id': 'user20132939',
 562                 'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
 563                 'upload_date': '20150209',
 564                 'timestamp': 1423518307,
 565             },
 566             'params': {
 567                 'format': 'best[protocol=https]',
 568                 'videopassword': 'youtube-dl',
 569             },
 570         },
 571         {
 572             # source file returns 403: Forbidden
 573             'url': 'https://vimeo.com/7809605',
 574             'only_matching': True,
 575         },
 576         {
 577             'note': 'Direct URL with hash',
 578             'url': 'https://vimeo.com/160743502/abd0e13fb4',
 579             'info_dict': {
 580                 'id': '160743502',
 581                 'ext': 'mp4',
 582                 'uploader': 'Julian Tryba',
 583                 'uploader_id': 'aliniamedia',
 584                 'title': 'Harrisville New Hampshire',
 585                 'timestamp': 1459259666,
 586                 'upload_date': '20160329',
 587             },
 588             'params': {'skip_download': True},
 589         },
 590         {
 591             'url': 'https://vimeo.com/138909882',
 592             'info_dict': {
 593                 'id': '138909882',
 594                 'ext': 'mp4',
 595                 'title': 'Eastnor Castle 2015 Firework Champions - The Promo!',
 596                 'description': 'md5:5967e090768a831488f6e74b7821b3c1',
 597                 'uploader_id': 'fireworkchampions',
 598                 'uploader': 'Firework Champions',
 599                 'upload_date': '20150910',
 600                 'timestamp': 1441901895,
 601             },
 602             'params': {
 603                 'skip_download': True,
 604                 'format': 'Original',
 605             },
 606         },
 607         {
 608             # requires passing unlisted_hash(a52724358e) to load_download_config request
 609             'url': 'https://vimeo.com/392479337/a52724358e',
 610             'only_matching': True,
 611         },
 612         # https://gettingthingsdone.com/workflowmap/
 613         # vimeo embed with check-password page protected by Referer header
 614     ]
 615
 616     @staticmethod
 617     def _smuggle_referrer(url, referrer_url):
 618         return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
 619
 620     @staticmethod
 621     def _extract_urls(url, webpage):
 622         urls = []
 623         # Look for embedded (iframe) Vimeo player
 624         for mobj in re.finditer(
 625                 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
 626                 webpage):
 627             urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
 628         PLAIN_EMBED_RE = (
 629             # Look for embedded (swf embed) Vimeo player
 630             r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
 631             # Look more for non-standard embedded Vimeo player
 632             r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
 633         )
 634         for embed_re in PLAIN_EMBED_RE:
 635             for mobj in re.finditer(embed_re, webpage):
 636                 urls.append(mobj.group('url'))
 637         return urls
 638
 639     @staticmethod
 640     def _extract_url(url, webpage):
 641         urls = VimeoIE._extract_urls(url, webpage)
 642         return urls[0] if urls else None
 643
 644     def _verify_player_video_password(self, url, video_id, headers):
 645         password = self._get_video_password()
 646         data = urlencode_postdata({
 647             'password': base64.b64encode(password.encode()),
 648         })
 649         headers = merge_dicts(headers, {
 650             'Content-Type': 'application/x-www-form-urlencoded',
 651         })
 652         checked = self._download_json(
 653             url + '/check-password', video_id,
 654             'Verifying the password', data=data, headers=headers)
 655         if checked is False:
 656             raise ExtractorError('Wrong video password', expected=True)
 657         return checked
 658
 659     def _real_initialize(self):
 660         self._login()
 661
 662     def _extract_from_api(self, video_id, unlisted_hash=None):
 663         token = self._download_json(
 664             'https://vimeo.com/_rv/jwt', video_id, headers={
 665                 'X-Requested-With': 'XMLHttpRequest'
 666             })['token']
 667         api_url = 'https://api.vimeo.com/videos/' + video_id
 668         if unlisted_hash:
 669             api_url += ':' + unlisted_hash
 670         video = self._download_json(
 671             api_url, video_id, headers={
 672                 'Authorization': 'jwt ' + token,
 673             }, query={
 674                 'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
 675             })
 676         info = self._parse_config(self._download_json(
 677             video['config_url'], video_id), video_id)
 678         self._vimeo_sort_formats(info['formats'])
 679         get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
 680         info.update({
 681             'description': video.get('description'),
 682             'license': video.get('license'),
 683             'release_timestamp': get_timestamp('release'),
 684             'timestamp': get_timestamp('created'),
 685             'view_count': int_or_none(try_get(video, lambda x: x['stats']['plays'])),
 686         })
 687         connections = try_get(
 688             video, lambda x: x['metadata']['connections'], dict) or {}
 689         for k in ('comment', 'like'):
 690             info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total']))
 691         return info
 692
 693     def _try_album_password(self, url):
 694         album_id = self._search_regex(
 695             r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None)
 696         if not album_id:
 697             return
 698         viewer = self._download_json(
 699             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
 700         if not viewer:
 701             webpage = self._download_webpage(url, album_id)
 702             viewer = self._parse_json(self._search_regex(
 703                 r'bootstrap_data\s*=\s*({.+?})</script>',
 704                 webpage, 'bootstrap data'), album_id)['viewer']
 705         jwt = viewer['jwt']
 706         album = self._download_json(
 707             'https://api.vimeo.com/albums/' + album_id,
 708             album_id, headers={'Authorization': 'jwt ' + jwt},
 709             query={'fields': 'description,name,privacy'})
 710         if try_get(album, lambda x: x['privacy']['view']) == 'password':
 711             password = self.get_param('videopassword')
 712             if not password:
 713                 raise ExtractorError(
 714                     'This album is protected by a password, use the --video-password option',
 715                     expected=True)
 716             self._set_vimeo_cookie('vuid', viewer['vuid'])
 717             try:
 718                 self._download_json(
 719                     'https://vimeo.com/showcase/%s/auth' % album_id,
 720                     album_id, 'Verifying the password', data=urlencode_postdata({
 721                         'password': password,
 722                         'token': viewer['xsrft'],
 723                     }), headers={
 724                         'X-Requested-With': 'XMLHttpRequest',
 725                     })
 726             except ExtractorError as e:
 727                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
 728                     raise ExtractorError('Wrong password', expected=True)
 729                 raise
 730
 731     def _real_extract(self, url):
 732         url, data = unsmuggle_url(url, {})
 733         headers = std_headers.copy()
 734         if 'http_headers' in data:
 735             headers.update(data['http_headers'])
 736         if 'Referer' not in headers:
 737             headers['Referer'] = url
 738
 739         # Extract ID from URL
 740         mobj = self._match_valid_url(url).groupdict()
 741         video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash')
 742         if unlisted_hash:
 743             return self._extract_from_api(video_id, unlisted_hash)
 744
 745         orig_url = url
 746         is_pro = 'vimeopro.com/' in url
 747         if is_pro:
 748             # some videos require portfolio_id to be present in player url
 749             # https://github.com/ytdl-org/youtube-dl/issues/20070
 750             url = self._extract_url(url, self._download_webpage(url, video_id))
 751             if not url:
 752                 url = 'https://vimeo.com/' + video_id
 753         elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
 754             url = 'https://vimeo.com/' + video_id
 755
 756         self._try_album_password(url)
 757         try:
 758             # Retrieve video webpage to extract further information
 759             webpage, urlh = self._download_webpage_handle(
 760                 url, video_id, headers=headers)
 761             redirect_url = urlh.geturl()
 762         except ExtractorError as ee:
 763             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 764                 errmsg = ee.cause.read()
 765                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 766                     raise ExtractorError(
 767                         'Cannot download embed-only video without embedding '
 768                         'URL. Please call yt-dlp with the URL of the page '
 769                         'that embeds this video.',
 770                         expected=True)
 771             raise
 772
 773         if '://player.vimeo.com/video/' in url:
 774             config = self._parse_json(self._search_regex(
 775                 r'\bconfig\s*=\s*({.+?})\s*;', webpage, 'info section'), video_id)
 776             if config.get('view') == 4:
 777                 config = self._verify_player_video_password(
 778                     redirect_url, video_id, headers)
 779             info = self._parse_config(config, video_id)
 780             self._vimeo_sort_formats(info['formats'])
 781             return info
 782
 783         if re.search(r'<form[^>]+?id="pw_form"', webpage):
 784             video_password = self._get_video_password()
 785             token, vuid = self._extract_xsrft_and_vuid(webpage)
 786             webpage = self._verify_video_password(
 787                 redirect_url, video_id, video_password, token, vuid)
 788
 789         vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
 790         if vimeo_config:
 791             seed_status = vimeo_config.get('seed_status') or {}
 792             if seed_status.get('state') == 'failed':
 793                 raise ExtractorError(
 794                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 795                     expected=True)
 796
 797         cc_license = None
 798         timestamp = None
 799         video_description = None
 800         info_dict = {}
 801
 802         channel_id = self._search_regex(
 803             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
 804         if channel_id:
 805             config_url = self._html_search_regex(
 806                 r'\bdata-config-url="([^"]+)"', webpage, 'config URL')
 807             video_description = clean_html(get_element_by_class('description', webpage))
 808             info_dict.update({
 809                 'channel_id': channel_id,
 810                 'channel_url': 'https://vimeo.com/channels/' + channel_id,
 811             })
 812         else:
 813             page_config = self._parse_json(self._search_regex(
 814                 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
 815                 webpage, 'page config', default='{}'), video_id, fatal=False)
 816             if not page_config:
 817                 return self._extract_from_api(video_id)
 818             config_url = page_config['player']['config_url']
 819             cc_license = page_config.get('cc_license')
 820             clip = page_config.get('clip') or {}
 821             timestamp = clip.get('uploaded_on')
 822             video_description = clean_html(
 823                 clip.get('description') or page_config.get('description_html_escaped'))
 824         config = self._download_json(config_url, video_id)
 825         video = config.get('video') or {}
 826         vod = video.get('vod') or {}
 827
 828         def is_rented():
 829             if '>You rented this title.<' in webpage:
 830                 return True
 831             if try_get(config, lambda x: x['user']['purchased']):
 832                 return True
 833             for purchase_option in (vod.get('purchase_options') or []):
 834                 if purchase_option.get('purchased'):
 835                     return True
 836                 label = purchase_option.get('label_string')
 837                 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
 838                     return True
 839             return False
 840
 841         if is_rented() and vod.get('is_trailer'):
 842             feature_id = vod.get('feature_id')
 843             if feature_id and not data.get('force_feature_id', False):
 844                 return self.url_result(smuggle_url(
 845                     'https://player.vimeo.com/player/%s' % feature_id,
 846                     {'force_feature_id': True}), 'Vimeo')
 847
 848         if not video_description:
 849             video_description = self._html_search_regex(
 850                 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 851                 webpage, 'description', default=None)
 852         if not video_description:
 853             video_description = self._html_search_meta(
 854                 ['description', 'og:description', 'twitter:description'],
 855                 webpage, default=None)
 856         if not video_description and is_pro:
 857             orig_webpage = self._download_webpage(
 858                 orig_url, video_id,
 859                 note='Downloading webpage for description',
 860                 fatal=False)
 861             if orig_webpage:
 862                 video_description = self._html_search_meta(
 863                     'description', orig_webpage, default=None)
 864         if not video_description:
 865             self.report_warning('Cannot find video description')
 866
 867         if not timestamp:
 868             timestamp = self._search_regex(
 869                 r'<time[^>]+datetime="([^"]+)"', webpage,
 870                 'timestamp', default=None)
 871
 872         view_count = int_or_none(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count', default=None))
 873         like_count = int_or_none(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count', default=None))
 874         comment_count = int_or_none(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count', default=None))
 875
 876         formats = []
 877
 878         source_format = self._extract_original_format(
 879             'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
 880         if source_format:
 881             formats.append(source_format)
 882
 883         info_dict_config = self._parse_config(config, video_id)
 884         formats.extend(info_dict_config['formats'])
 885         self._vimeo_sort_formats(formats)
 886
 887         json_ld = self._search_json_ld(webpage, video_id, default={})
 888
 889         if not cc_license:
 890             cc_license = self._search_regex(
 891                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
 892                 webpage, 'license', default=None, group='license')
 893
 894         info_dict.update({
 895             'formats': formats,
 896             'timestamp': unified_timestamp(timestamp),
 897             'description': video_description,
 898             'webpage_url': url,
 899             'view_count': view_count,
 900             'like_count': like_count,
 901             'comment_count': comment_count,
 902             'license': cc_license,
 903         })
 904
 905         return merge_dicts(info_dict, info_dict_config, json_ld)
 906
 907
 908 class VimeoOndemandIE(VimeoIE):
 909     IE_NAME = 'vimeo:ondemand'
 910     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)'
 911     _TESTS = [{
 912         # ondemand video not available via https://vimeo.com/id
 913         'url': 'https://vimeo.com/ondemand/20704',
 914         'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
 915         'info_dict': {
 916             'id': '105442900',
 917             'ext': 'mp4',
 918             'title': 'המעבדה - במאי יותם פלדמן',
 919             'uploader': 'גם סרטים',
 920             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
 921             'uploader_id': 'gumfilms',
 922             'description': 'md5:4c027c965e439de4baab621e48b60791',
 923             'upload_date': '20140906',
 924             'timestamp': 1410032453,
 925         },
 926         'params': {
 927             'format': 'best[protocol=https]',
 928         },
 929         'expected_warnings': ['Unable to download JSON metadata'],
 930     }, {
 931         # requires Referer to be passed along with og:video:url
 932         'url': 'https://vimeo.com/ondemand/36938/126682985',
 933         'info_dict': {
 934             'id': '126584684',
 935             'ext': 'mp4',
 936             'title': 'Rävlock, rätt läte på rätt plats',
 937             'uploader': 'Lindroth & Norin',
 938             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
 939             'uploader_id': 'lindrothnorin',
 940             'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
 941             'upload_date': '20150502',
 942             'timestamp': 1430586422,
 943         },
 944         'params': {
 945             'skip_download': True,
 946         },
 947         'expected_warnings': ['Unable to download JSON metadata'],
 948     }, {
 949         'url': 'https://vimeo.com/ondemand/nazmaalik',
 950         'only_matching': True,
 951     }, {
 952         'url': 'https://vimeo.com/ondemand/141692381',
 953         'only_matching': True,
 954     }, {
 955         'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
 956         'only_matching': True,
 957     }]
 958
 959
 960 class VimeoChannelIE(VimeoBaseInfoExtractor):
 961     IE_NAME = 'vimeo:channel'
 962     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 963     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 964     _TITLE = None
 965     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 966     _TESTS = [{
 967         'url': 'https://vimeo.com/channels/tributes',
 968         'info_dict': {
 969             'id': 'tributes',
 970             'title': 'Vimeo Tributes',
 971         },
 972         'playlist_mincount': 25,
 973     }]
 974     _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
 975
 976     def _page_url(self, base_url, pagenum):
 977         return '%s/videos/page:%d/' % (base_url, pagenum)
 978
 979     def _extract_list_title(self, webpage):
 980         return self._TITLE or self._html_search_regex(
 981             self._TITLE_RE, webpage, 'list title', fatal=False)
 982
 983     def _title_and_entries(self, list_id, base_url):
 984         for pagenum in itertools.count(1):
 985             page_url = self._page_url(base_url, pagenum)
 986             webpage = self._download_webpage(
 987                 page_url, list_id,
 988                 'Downloading page %s' % pagenum)
 989
 990             if pagenum == 1:
 991                 yield self._extract_list_title(webpage)
 992
 993             # Try extracting href first since not all videos are available via
 994             # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
 995             clips = re.findall(
 996                 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
 997             if clips:
 998                 for video_id, video_url, video_title in clips:
 999                     yield self.url_result(
1000                         compat_urlparse.urljoin(base_url, video_url),
1001                         VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
1002             # More relaxed fallback
1003             else:
1004                 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
1005                     yield self.url_result(
1006                         'https://vimeo.com/%s' % video_id,
1007                         VimeoIE.ie_key(), video_id=video_id)
1008
1009             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
1010                 break
1011
1012     def _extract_videos(self, list_id, base_url):
1013         title_and_entries = self._title_and_entries(list_id, base_url)
1014         list_title = next(title_and_entries)
1015         return self.playlist_result(title_and_entries, list_id, list_title)
1016
1017     def _real_extract(self, url):
1018         channel_id = self._match_id(url)
1019         return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
1020
1021
1022 class VimeoUserIE(VimeoChannelIE):
1023     IE_NAME = 'vimeo:user'
1024     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
1025     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
1026     _TESTS = [{
1027         'url': 'https://vimeo.com/nkistudio/videos',
1028         'info_dict': {
1029             'title': 'Nki',
1030             'id': 'nkistudio',
1031         },
1032         'playlist_mincount': 66,
1033     }]
1034     _BASE_URL_TEMPL = 'https://vimeo.com/%s'
1035
1036
1037 class VimeoAlbumIE(VimeoBaseInfoExtractor):
1038     IE_NAME = 'vimeo:album'
1039     _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
1040     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
1041     _TESTS = [{
1042         'url': 'https://vimeo.com/album/2632481',
1043         'info_dict': {
1044             'id': '2632481',
1045             'title': 'Staff Favorites: November 2013',
1046         },
1047         'playlist_mincount': 13,
1048     }, {
1049         'note': 'Password-protected album',
1050         'url': 'https://vimeo.com/album/3253534',
1051         'info_dict': {
1052             'title': 'test',
1053             'id': '3253534',
1054         },
1055         'playlist_count': 1,
1056         'params': {
1057             'videopassword': 'youtube-dl',
1058         }
1059     }]
1060     _PAGE_SIZE = 100
1061
1062     def _fetch_page(self, album_id, authorization, hashed_pass, page):
1063         api_page = page + 1
1064         query = {
1065             'fields': 'link,uri',
1066             'page': api_page,
1067             'per_page': self._PAGE_SIZE,
1068         }
1069         if hashed_pass:
1070             query['_hashed_pass'] = hashed_pass
1071         try:
1072             videos = self._download_json(
1073                 'https://api.vimeo.com/albums/%s/videos' % album_id,
1074                 album_id, 'Downloading page %d' % api_page, query=query, headers={
1075                     'Authorization': 'jwt ' + authorization,
1076                 })['data']
1077         except ExtractorError as e:
1078             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
1079                 return
1080         for video in videos:
1081             link = video.get('link')
1082             if not link:
1083                 continue
1084             uri = video.get('uri')
1085             video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
1086             yield self.url_result(link, VimeoIE.ie_key(), video_id)
1087
1088     def _real_extract(self, url):
1089         album_id = self._match_id(url)
1090         viewer = self._download_json(
1091             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
1092         if not viewer:
1093             webpage = self._download_webpage(url, album_id)
1094             viewer = self._parse_json(self._search_regex(
1095                 r'bootstrap_data\s*=\s*({.+?})</script>',
1096                 webpage, 'bootstrap data'), album_id)['viewer']
1097         jwt = viewer['jwt']
1098         album = self._download_json(
1099             'https://api.vimeo.com/albums/' + album_id,
1100             album_id, headers={'Authorization': 'jwt ' + jwt},
1101             query={'fields': 'description,name,privacy'})
1102         hashed_pass = None
1103         if try_get(album, lambda x: x['privacy']['view']) == 'password':
1104             password = self.get_param('videopassword')
1105             if not password:
1106                 raise ExtractorError(
1107                     'This album is protected by a password, use the --video-password option',
1108                     expected=True)
1109             self._set_vimeo_cookie('vuid', viewer['vuid'])
1110             try:
1111                 hashed_pass = self._download_json(
1112                     'https://vimeo.com/showcase/%s/auth' % album_id,
1113                     album_id, 'Verifying the password', data=urlencode_postdata({
1114                         'password': password,
1115                         'token': viewer['xsrft'],
1116                     }), headers={
1117                         'X-Requested-With': 'XMLHttpRequest',
1118                     })['hashed_pass']
1119             except ExtractorError as e:
1120                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
1121                     raise ExtractorError('Wrong password', expected=True)
1122                 raise
1123         entries = OnDemandPagedList(functools.partial(
1124             self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
1125         return self.playlist_result(
1126             entries, album_id, album.get('name'), album.get('description'))
1127
1128
1129 class VimeoGroupsIE(VimeoChannelIE):
1130     IE_NAME = 'vimeo:group'
1131     _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
1132     _TESTS = [{
1133         'url': 'https://vimeo.com/groups/meetup',
1134         'info_dict': {
1135             'id': 'meetup',
1136             'title': 'Vimeo Meetup!',
1137         },
1138         'playlist_mincount': 27,
1139     }]
1140     _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
1141
1142
1143 class VimeoReviewIE(VimeoBaseInfoExtractor):
1144     IE_NAME = 'vimeo:review'
1145     IE_DESC = 'Review pages on vimeo'
1146     _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
1147     _TESTS = [{
1148         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1149         'md5': 'c507a72f780cacc12b2248bb4006d253',
1150         'info_dict': {
1151             'id': '75524534',
1152             'ext': 'mp4',
1153             'title': "DICK HARDWICK 'Comedian'",
1154             'uploader': 'Richard Hardwick',
1155             'uploader_id': 'user21297594',
1156             'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1157         },
1158     }, {
1159         'note': 'video player needs Referer',
1160         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1161         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1162         'info_dict': {
1163             'id': '91613211',
1164             'ext': 'mp4',
1165             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1166             'uploader': 'DevWeek Events',
1167             'duration': 2773,
1168             'thumbnail': r're:^https?://.*\.jpg$',
1169             'uploader_id': 'user22258446',
1170         },
1171         'skip': 'video gone',
1172     }, {
1173         'note': 'Password protected',
1174         'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1175         'info_dict': {
1176             'id': '138823582',
1177             'ext': 'mp4',
1178             'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1179             'uploader': 'TMB',
1180             'uploader_id': 'user37284429',
1181         },
1182         'params': {
1183             'videopassword': 'holygrail',
1184         },
1185         'skip': 'video gone',
1186     }]
1187
1188     def _real_initialize(self):
1189         self._login()
1190
1191     def _real_extract(self, url):
1192         page_url, video_id = self._match_valid_url(url).groups()
1193         data = self._download_json(
1194             page_url.replace('/review/', '/review/data/'), video_id)
1195         if data.get('isLocked') is True:
1196             video_password = self._get_video_password()
1197             viewer = self._download_json(
1198                 'https://vimeo.com/_rv/viewer', video_id)
1199             webpage = self._verify_video_password(
1200                 'https://vimeo.com/' + video_id, video_id,
1201                 video_password, viewer['xsrft'], viewer['vuid'])
1202             clip_page_config = self._parse_json(self._search_regex(
1203                 r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
1204                 webpage, 'clip page config'), video_id)
1205             config_url = clip_page_config['player']['config_url']
1206             clip_data = clip_page_config.get('clip') or {}
1207         else:
1208             clip_data = data['clipData']
1209             config_url = clip_data['configUrl']
1210         config = self._download_json(config_url, video_id)
1211         info_dict = self._parse_config(config, video_id)
1212         source_format = self._extract_original_format(
1213             page_url + '/action', video_id)
1214         if source_format:
1215             info_dict['formats'].append(source_format)
1216         self._vimeo_sort_formats(info_dict['formats'])
1217         info_dict['description'] = clean_html(clip_data.get('description'))
1218         return info_dict
1219
1220
1221 class VimeoWatchLaterIE(VimeoChannelIE):
1222     IE_NAME = 'vimeo:watchlater'
1223     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
1224     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1225     _TITLE = 'Watch Later'
1226     _LOGIN_REQUIRED = True
1227     _TESTS = [{
1228         'url': 'https://vimeo.com/watchlater',
1229         'only_matching': True,
1230     }]
1231
1232     def _real_initialize(self):
1233         self._login()
1234
1235     def _page_url(self, base_url, pagenum):
1236         url = '%s/page:%d/' % (base_url, pagenum)
1237         request = sanitized_Request(url)
1238         # Set the header to get a partial html page with the ids,
1239         # the normal page doesn't contain them.
1240         request.add_header('X-Requested-With', 'XMLHttpRequest')
1241         return request
1242
1243     def _real_extract(self, url):
1244         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1245
1246
1247 class VimeoLikesIE(VimeoChannelIE):
1248     _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1249     IE_NAME = 'vimeo:likes'
1250     IE_DESC = 'Vimeo user likes'
1251     _TESTS = [{
1252         'url': 'https://vimeo.com/user755559/likes/',
1253         'playlist_mincount': 293,
1254         'info_dict': {
1255             'id': 'user755559',
1256             'title': 'urza’s Likes',
1257         },
1258     }, {
1259         'url': 'https://vimeo.com/stormlapse/likes',
1260         'only_matching': True,
1261     }]
1262
1263     def _page_url(self, base_url, pagenum):
1264         return '%s/page:%d/' % (base_url, pagenum)
1265
1266     def _real_extract(self, url):
1267         user_id = self._match_id(url)
1268         return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
1269
1270
1271 class VHXEmbedIE(VimeoBaseInfoExtractor):
1272     IE_NAME = 'vhx:embed'
1273     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1274
1275     @staticmethod
1276     def _extract_url(webpage):
1277         mobj = re.search(
1278             r'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage)
1279         return unescapeHTML(mobj.group(1)) if mobj else None
1280
1281     def _real_extract(self, url):
1282         video_id = self._match_id(url)
1283         webpage = self._download_webpage(url, video_id)
1284         config_url = self._parse_json(self._search_regex(
1285             r'window\.OTTData\s*=\s*({.+})', webpage,
1286             'ott data'), video_id, js_to_json)['config_url']
1287         config = self._download_json(config_url, video_id)
1288         info = self._parse_config(config, video_id)
1289         info['id'] = video_id
1290         self._vimeo_sort_formats(info['formats'])
1291         return info