yt_dlp/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     parse_iso8601,
  28     parse_qs,
  29     RegexNotFoundError,
  30     sanitized_Request,
  31     smuggle_url,
  32     std_headers,
  33     str_or_none,
  34     try_get,
  35     unified_timestamp,
  36     unsmuggle_url,
  37     urlencode_postdata,
  38     urljoin,
  39     unescapeHTML,
  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
 133         formats = []
 134         config_files = video_data.get('files') or config['request'].get('files', {})
 135         for f in config_files.get('progressive', []):
 136             video_url = f.get('url')
 137             if not video_url:
 138                 continue
 139             formats.append({
 140                 'url': video_url,
 141                 'format_id': 'http-%s' % f.get('quality'),
 142                 'width': int_or_none(f.get('width')),
 143                 'height': int_or_none(f.get('height')),
 144                 'fps': int_or_none(f.get('fps')),
 145                 'tbr': int_or_none(f.get('bitrate')),
 146             })
 147
 148         # TODO: fix handling of 308 status code returned for live archive manifest requests
 149         sep_pattern = r'/sep/video/'
 150         for files_type in ('hls', 'dash'):
 151             for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items():
 152                 manifest_url = cdn_data.get('url')
 153                 if not manifest_url:
 154                     continue
 155                 format_id = '%s-%s' % (files_type, cdn_name)
 156                 sep_manifest_urls = []
 157                 if re.search(sep_pattern, manifest_url):
 158                     for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
 159                         sep_manifest_urls.append((format_id + suffix, re.sub(
 160                             sep_pattern, '/%s/' % repl, manifest_url)))
 161                 else:
 162                     sep_manifest_urls = [(format_id, manifest_url)]
 163                 for f_id, m_url in sep_manifest_urls:
 164                     if files_type == 'hls':
 165                         formats.extend(self._extract_m3u8_formats(
 166                             m_url, video_id, 'mp4',
 167                             'm3u8' if is_live else 'm3u8_native', m3u8_id=f_id,
 168                             note='Downloading %s m3u8 information' % cdn_name,
 169                             fatal=False))
 170                     elif files_type == 'dash':
 171                         if 'json=1' in m_url:
 172                             real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
 173                             if real_m_url:
 174                                 m_url = real_m_url
 175                         mpd_formats = self._extract_mpd_formats(
 176                             m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
 177                             'Downloading %s MPD information' % cdn_name,
 178                             fatal=False)
 179                         formats.extend(mpd_formats)
 180
 181         live_archive = live_event.get('archive') or {}
 182         live_archive_source_url = live_archive.get('source_url')
 183         if live_archive_source_url and live_archive.get('status') == 'done':
 184             formats.append({
 185                 'format_id': 'live-archive-source',
 186                 'url': live_archive_source_url,
 187                 'quality': 10,
 188             })
 189
 190         subtitles = {}
 191         text_tracks = config['request'].get('text_tracks')
 192         if text_tracks:
 193             for tt in text_tracks:
 194                 subtitles[tt['lang']] = [{
 195                     'ext': 'vtt',
 196                     'url': urljoin('https://vimeo.com', tt['url']),
 197                 }]
 198
 199         thumbnails = []
 200         if not is_live:
 201             for key, thumb in video_data.get('thumbs', {}).items():
 202                 thumbnails.append({
 203                     'id': key,
 204                     'width': int_or_none(key),
 205                     'url': thumb,
 206                 })
 207             thumbnail = video_data.get('thumbnail')
 208             if thumbnail:
 209                 thumbnails.append({
 210                     'url': thumbnail,
 211                 })
 212
 213         owner = video_data.get('owner') or {}
 214         video_uploader_url = owner.get('url')
 215
 216         return {
 217             'id': str_or_none(video_data.get('id')) or video_id,
 218             'title': self._live_title(video_title) if is_live else video_title,
 219             'uploader': owner.get('name'),
 220             'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
 221             'uploader_url': video_uploader_url,
 222             'thumbnails': thumbnails,
 223             'duration': int_or_none(video_data.get('duration')),
 224             'formats': formats,
 225             'subtitles': subtitles,
 226             'is_live': is_live,
 227         }
 228
 229     def _extract_original_format(self, url, video_id, unlisted_hash=None):
 230         query = {'action': 'load_download_config'}
 231         if unlisted_hash:
 232             query['unlisted_hash'] = unlisted_hash
 233         download_data = self._download_json(
 234             url, video_id, fatal=False, query=query,
 235             headers={'X-Requested-With': 'XMLHttpRequest'})
 236         if download_data:
 237             source_file = download_data.get('source_file')
 238             if isinstance(source_file, dict):
 239                 download_url = source_file.get('download_url')
 240                 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 241                     source_name = source_file.get('public_name', 'Original')
 242                     if self._is_valid_url(download_url, video_id, '%s video' % source_name):
 243                         ext = (try_get(
 244                             source_file, lambda x: x['extension'],
 245                             compat_str) or determine_ext(
 246                             download_url, None) or 'mp4').lower()
 247                         return {
 248                             'url': download_url,
 249                             'ext': ext,
 250                             'width': int_or_none(source_file.get('width')),
 251                             'height': int_or_none(source_file.get('height')),
 252                             'filesize': parse_filesize(source_file.get('size')),
 253                             'format_id': source_name,
 254                             'quality': 1,
 255                         }
 256
 257         jwt_response = self._download_json(
 258             'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {}
 259         if not jwt_response.get('jwt'):
 260             return
 261         headers = {'Authorization': 'jwt %s' % jwt_response['jwt']}
 262         original_response = self._download_json(
 263             f'https://api.vimeo.com/videos/{video_id}', video_id,
 264             headers=headers, fatal=False) or {}
 265         for download_data in original_response.get('download') or {}:
 266             download_url = download_data.get('link')
 267             if not download_url or download_data.get('quality') != 'source':
 268                 continue
 269             query = parse_qs(download_url)
 270             return {
 271                 'url': download_url,
 272                 'ext': determine_ext(query.get('filename', [''])[0].lower()),
 273                 'format_id': download_data.get('public_name', 'Original'),
 274                 'width': int_or_none(download_data.get('width')),
 275                 'height': int_or_none(download_data.get('height')),
 276                 'fps': int_or_none(download_data.get('fps')),
 277                 'filesize': int_or_none(download_data.get('size')),
 278                 'quality': 1,
 279             }
 280
 281
 282 class VimeoIE(VimeoBaseInfoExtractor):
 283     """Information extractor for vimeo.com."""
 284
 285     # _VALID_URL matches Vimeo URLs
 286     _VALID_URL = r'''(?x)
 287                     https?://
 288                         (?:
 289                             (?:
 290                                 www|
 291                                 player
 292                             )
 293                             \.
 294                         )?
 295                         vimeo(?:pro)?\.com/
 296                         (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
 297                         (?:.*?/)?
 298                         (?:
 299                             (?:
 300                                 play_redirect_hls|
 301                                 moogaloop\.swf)\?clip_id=
 302                             )?
 303                         (?:videos?/)?
 304                         (?P<id>[0-9]+)
 305                         (?:/(?P<unlisted_hash>[\da-f]{10}))?
 306                         /?(?:[?&].*)?(?:[#].*)?$
 307                     '''
 308     IE_NAME = 'vimeo'
 309     _TESTS = [
 310         {
 311             'url': 'http://vimeo.com/56015672#at=0',
 312             'md5': '8879b6cc097e987f02484baf890129e5',
 313             'info_dict': {
 314                 'id': '56015672',
 315                 'ext': 'mp4',
 316                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
 317                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
 318                 'timestamp': 1355990239,
 319                 'upload_date': '20121220',
 320                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
 321                 'uploader_id': 'user7108434',
 322                 'uploader': 'Filippo Valsorda',
 323                 'duration': 10,
 324                 'license': 'by-sa',
 325             },
 326             'params': {
 327                 'format': 'best[protocol=https]',
 328             },
 329         },
 330         {
 331             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
 332             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
 333             'note': 'Vimeo Pro video (#1197)',
 334             'info_dict': {
 335                 'id': '68093876',
 336                 'ext': 'mp4',
 337                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
 338                 'uploader_id': 'openstreetmapus',
 339                 'uploader': 'OpenStreetMap US',
 340                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 341                 'description': 'md5:2c362968038d4499f4d79f88458590c1',
 342                 'duration': 1595,
 343                 'upload_date': '20130610',
 344                 'timestamp': 1370893156,
 345             },
 346             'params': {
 347                 'format': 'best[protocol=https]',
 348             },
 349         },
 350         {
 351             'url': 'http://player.vimeo.com/video/54469442',
 352             'md5': '619b811a4417aa4abe78dc653becf511',
 353             'note': 'Videos that embed the url in the player page',
 354             'info_dict': {
 355                 'id': '54469442',
 356                 'ext': 'mp4',
 357                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 358                 'uploader': 'Business of Software',
 359                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
 360                 'uploader_id': 'businessofsoftware',
 361                 'duration': 3610,
 362                 'description': None,
 363             },
 364             'params': {
 365                 'format': 'best[protocol=https]',
 366             },
 367             'expected_warnings': ['Unable to download JSON metadata'],
 368         },
 369         {
 370             'url': 'http://vimeo.com/68375962',
 371             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 372             'note': 'Video protected with password',
 373             'info_dict': {
 374                 'id': '68375962',
 375                 'ext': 'mp4',
 376                 'title': 'youtube-dl password protected test video',
 377                 'timestamp': 1371200155,
 378                 'upload_date': '20130614',
 379                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 380                 'uploader_id': 'user18948128',
 381                 'uploader': 'Jaime Marquínez Ferrándiz',
 382                 'duration': 10,
 383                 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
 384             },
 385             'params': {
 386                 'format': 'best[protocol=https]',
 387                 'videopassword': 'youtube-dl',
 388             },
 389         },
 390         {
 391             'url': 'http://vimeo.com/channels/keypeele/75629013',
 392             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 393             'info_dict': {
 394                 'id': '75629013',
 395                 'ext': 'mp4',
 396                 'title': 'Key & Peele: Terrorist Interrogation',
 397                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 398                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
 399                 'uploader_id': 'atencio',
 400                 'uploader': 'Peter Atencio',
 401                 'channel_id': 'keypeele',
 402                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
 403                 'timestamp': 1380339469,
 404                 'upload_date': '20130928',
 405                 'duration': 187,
 406             },
 407             'expected_warnings': ['Unable to download JSON metadata'],
 408         },
 409         {
 410             'url': 'http://vimeo.com/76979871',
 411             'note': 'Video with subtitles',
 412             'info_dict': {
 413                 'id': '76979871',
 414                 'ext': 'mp4',
 415                 'title': 'The New Vimeo Player (You Know, For Videos)',
 416                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 417                 'timestamp': 1381846109,
 418                 'upload_date': '20131015',
 419                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
 420                 'uploader_id': 'staff',
 421                 'uploader': 'Vimeo Staff',
 422                 'duration': 62,
 423             }
 424         },
 425         {
 426             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 427             'url': 'https://player.vimeo.com/video/98044508',
 428             'note': 'The js code contains assignments to the same variable as the config',
 429             'info_dict': {
 430                 'id': '98044508',
 431                 'ext': 'mp4',
 432                 'title': 'Pier Solar OUYA Official Trailer',
 433                 'uploader': 'Tulio Gonçalves',
 434                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
 435                 'uploader_id': 'user28849593',
 436             },
 437         },
 438         {
 439             # contains original format
 440             'url': 'https://vimeo.com/33951933',
 441             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 442             'info_dict': {
 443                 'id': '33951933',
 444                 'ext': 'mp4',
 445                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 446                 'uploader': 'The DMCI',
 447                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
 448                 'uploader_id': 'dmci',
 449                 'timestamp': 1324343742,
 450                 'upload_date': '20111220',
 451                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 452             },
 453         },
 454         {
 455             'note': 'Contains original format not accessible in webpage',
 456             'url': 'https://vimeo.com/393756517',
 457             'md5': 'c464af248b592190a5ffbb5d33f382b0',
 458             'info_dict': {
 459                 'id': '393756517',
 460                 'ext': 'mov',
 461                 'timestamp': 1582642091,
 462                 'uploader_id': 'frameworkla',
 463                 'title': 'Straight To Hell - Sabrina: Netflix',
 464                 'uploader': 'Framework Studio',
 465                 'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
 466                 'upload_date': '20200225',
 467             },
 468             'expected_warnings': ['Unable to download JSON metadata'],
 469         },
 470         {
 471             # only available via https://vimeo.com/channels/tributes/6213729 and
 472             # not via https://vimeo.com/6213729
 473             'url': 'https://vimeo.com/channels/tributes/6213729',
 474             'info_dict': {
 475                 'id': '6213729',
 476                 'ext': 'mp4',
 477                 'title': 'Vimeo Tribute: The Shining',
 478                 'uploader': 'Casey Donahue',
 479                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
 480                 'uploader_id': 'caseydonahue',
 481                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
 482                 'channel_id': 'tributes',
 483                 'timestamp': 1250886430,
 484                 'upload_date': '20090821',
 485                 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
 486             },
 487             'params': {
 488                 'skip_download': True,
 489             },
 490             'expected_warnings': ['Unable to download JSON metadata'],
 491         },
 492         {
 493             # redirects to ondemand extractor and should be passed through it
 494             # for successful extraction
 495             'url': 'https://vimeo.com/73445910',
 496             'info_dict': {
 497                 'id': '73445910',
 498                 'ext': 'mp4',
 499                 'title': 'The Reluctant Revolutionary',
 500                 'uploader': '10Ft Films',
 501                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
 502                 'uploader_id': 'tenfootfilms',
 503                 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
 504                 'upload_date': '20130830',
 505                 'timestamp': 1377853339,
 506             },
 507             'params': {
 508                 'skip_download': True,
 509             },
 510             'expected_warnings': ['Unable to download JSON metadata'],
 511             'skip': 'this page is no longer available.',
 512         },
 513         {
 514             'url': 'http://player.vimeo.com/video/68375962',
 515             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 516             'info_dict': {
 517                 'id': '68375962',
 518                 'ext': 'mp4',
 519                 'title': 'youtube-dl password protected test video',
 520                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 521                 'uploader_id': 'user18948128',
 522                 'uploader': 'Jaime Marquínez Ferrándiz',
 523                 'duration': 10,
 524             },
 525             'params': {
 526                 'format': 'best[protocol=https]',
 527                 'videopassword': 'youtube-dl',
 528             },
 529         },
 530         {
 531             'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
 532             'only_matching': True,
 533         },
 534         {
 535             'url': 'https://vimeo.com/109815029',
 536             'note': 'Video not completely processed, "failed" seed status',
 537             'only_matching': True,
 538         },
 539         {
 540             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 541             'only_matching': True,
 542         },
 543         {
 544             'url': 'https://vimeo.com/album/2632481/video/79010983',
 545             'only_matching': True,
 546         },
 547         {
 548             'url': 'https://vimeo.com/showcase/3253534/video/119195465',
 549             'note': 'A video in a password protected album (showcase)',
 550             'info_dict': {
 551                 'id': '119195465',
 552                 'ext': 'mp4',
 553                 'title': 'youtube-dl test video \'ä"BaW_jenozKc',
 554                 'uploader': 'Philipp Hagemeister',
 555                 'uploader_id': 'user20132939',
 556                 'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
 557                 'upload_date': '20150209',
 558                 'timestamp': 1423518307,
 559             },
 560             'params': {
 561                 'format': 'best[protocol=https]',
 562                 'videopassword': 'youtube-dl',
 563             },
 564         },
 565         {
 566             # source file returns 403: Forbidden
 567             'url': 'https://vimeo.com/7809605',
 568             'only_matching': True,
 569         },
 570         {
 571             'url': 'https://vimeo.com/160743502/abd0e13fb4',
 572             'only_matching': True,
 573         },
 574         {
 575             # requires passing unlisted_hash(a52724358e) to load_download_config request
 576             'url': 'https://vimeo.com/392479337/a52724358e',
 577             'only_matching': True,
 578         }
 579         # https://gettingthingsdone.com/workflowmap/
 580         # vimeo embed with check-password page protected by Referer header
 581     ]
 582
 583     @staticmethod
 584     def _smuggle_referrer(url, referrer_url):
 585         return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
 586
 587     @staticmethod
 588     def _extract_urls(url, webpage):
 589         urls = []
 590         # Look for embedded (iframe) Vimeo player
 591         for mobj in re.finditer(
 592                 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
 593                 webpage):
 594             urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
 595         PLAIN_EMBED_RE = (
 596             # Look for embedded (swf embed) Vimeo player
 597             r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
 598             # Look more for non-standard embedded Vimeo player
 599             r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
 600         )
 601         for embed_re in PLAIN_EMBED_RE:
 602             for mobj in re.finditer(embed_re, webpage):
 603                 urls.append(mobj.group('url'))
 604         return urls
 605
 606     @staticmethod
 607     def _extract_url(url, webpage):
 608         urls = VimeoIE._extract_urls(url, webpage)
 609         return urls[0] if urls else None
 610
 611     def _verify_player_video_password(self, url, video_id, headers):
 612         password = self._get_video_password()
 613         data = urlencode_postdata({
 614             'password': base64.b64encode(password.encode()),
 615         })
 616         headers = merge_dicts(headers, {
 617             'Content-Type': 'application/x-www-form-urlencoded',
 618         })
 619         checked = self._download_json(
 620             url + '/check-password', video_id,
 621             'Verifying the password', data=data, headers=headers)
 622         if checked is False:
 623             raise ExtractorError('Wrong video password', expected=True)
 624         return checked
 625
 626     def _real_initialize(self):
 627         self._login()
 628
 629     def _try_album_password(self, url):
 630         album_id = self._search_regex(
 631             r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None)
 632         if not album_id:
 633             return
 634         viewer = self._download_json(
 635             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
 636         if not viewer:
 637             webpage = self._download_webpage(url, album_id)
 638             viewer = self._parse_json(self._search_regex(
 639                 r'bootstrap_data\s*=\s*({.+?})</script>',
 640                 webpage, 'bootstrap data'), album_id)['viewer']
 641         jwt = viewer['jwt']
 642         album = self._download_json(
 643             'https://api.vimeo.com/albums/' + album_id,
 644             album_id, headers={'Authorization': 'jwt ' + jwt},
 645             query={'fields': 'description,name,privacy'})
 646         if try_get(album, lambda x: x['privacy']['view']) == 'password':
 647             password = self.get_param('videopassword')
 648             if not password:
 649                 raise ExtractorError(
 650                     'This album is protected by a password, use the --video-password option',
 651                     expected=True)
 652             self._set_vimeo_cookie('vuid', viewer['vuid'])
 653             try:
 654                 self._download_json(
 655                     'https://vimeo.com/showcase/%s/auth' % album_id,
 656                     album_id, 'Verifying the password', data=urlencode_postdata({
 657                         'password': password,
 658                         'token': viewer['xsrft'],
 659                     }), headers={
 660                         'X-Requested-With': 'XMLHttpRequest',
 661                     })
 662             except ExtractorError as e:
 663                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
 664                     raise ExtractorError('Wrong password', expected=True)
 665                 raise
 666
 667     def _real_extract(self, url):
 668         url, data = unsmuggle_url(url, {})
 669         headers = std_headers.copy()
 670         if 'http_headers' in data:
 671             headers.update(data['http_headers'])
 672         if 'Referer' not in headers:
 673             headers['Referer'] = url
 674
 675         # Extract ID from URL
 676         video_id, unlisted_hash = self._match_valid_url(url).groups()
 677         if unlisted_hash:
 678             token = self._download_json(
 679                 'https://vimeo.com/_rv/jwt', video_id, headers={
 680                     'X-Requested-With': 'XMLHttpRequest'
 681                 })['token']
 682             video = self._download_json(
 683                 'https://api.vimeo.com/videos/%s:%s' % (video_id, unlisted_hash),
 684                 video_id, headers={
 685                     'Authorization': 'jwt ' + token,
 686                 }, query={
 687                     'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
 688                 })
 689             info = self._parse_config(self._download_json(
 690                 video['config_url'], video_id), video_id)
 691             self._vimeo_sort_formats(info['formats'])
 692             get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
 693             info.update({
 694                 'description': video.get('description'),
 695                 'license': video.get('license'),
 696                 'release_timestamp': get_timestamp('release'),
 697                 'timestamp': get_timestamp('created'),
 698                 'view_count': int_or_none(try_get(video, lambda x: x['stats']['plays'])),
 699             })
 700             connections = try_get(
 701                 video, lambda x: x['metadata']['connections'], dict) or {}
 702             for k in ('comment', 'like'):
 703                 info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total']))
 704             return info
 705
 706         orig_url = url
 707         is_pro = 'vimeopro.com/' in url
 708         is_player = '://player.vimeo.com/video/' in url
 709         if is_pro:
 710             # some videos require portfolio_id to be present in player url
 711             # https://github.com/ytdl-org/youtube-dl/issues/20070
 712             url = self._extract_url(url, self._download_webpage(url, video_id))
 713             if not url:
 714                 url = 'https://vimeo.com/' + video_id
 715         elif is_player:
 716             url = 'https://player.vimeo.com/video/' + video_id
 717         elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
 718             url = 'https://vimeo.com/' + video_id
 719
 720         self._try_album_password(url)
 721         try:
 722             # Retrieve video webpage to extract further information
 723             webpage, urlh = self._download_webpage_handle(
 724                 url, video_id, headers=headers)
 725             redirect_url = urlh.geturl()
 726         except ExtractorError as ee:
 727             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 728                 errmsg = ee.cause.read()
 729                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 730                     raise ExtractorError(
 731                         'Cannot download embed-only video without embedding '
 732                         'URL. Please call yt-dlp with the URL of the page '
 733                         'that embeds this video.',
 734                         expected=True)
 735             raise
 736
 737         # Now we begin extracting as much information as we can from what we
 738         # retrieved. First we extract the information common to all extractors,
 739         # and latter we extract those that are Vimeo specific.
 740         self.report_extraction(video_id)
 741
 742         vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
 743         if vimeo_config:
 744             seed_status = vimeo_config.get('seed_status', {})
 745             if seed_status.get('state') == 'failed':
 746                 raise ExtractorError(
 747                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 748                     expected=True)
 749
 750         cc_license = None
 751         timestamp = None
 752         video_description = None
 753
 754         # Extract the config JSON
 755         try:
 756             try:
 757                 config_url = self._html_search_regex(
 758                     r' data-config-url="(.+?)"', webpage,
 759                     'config URL', default=None)
 760                 if not config_url:
 761                     # Sometimes new react-based page is served instead of old one that require
 762                     # different config URL extraction approach (see
 763                     # https://github.com/ytdl-org/youtube-dl/pull/7209)
 764                     page_config = self._parse_json(self._search_regex(
 765                         r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
 766                         webpage, 'page config'), video_id)
 767                     config_url = page_config['player']['config_url']
 768                     cc_license = page_config.get('cc_license')
 769                     timestamp = try_get(
 770                         page_config, lambda x: x['clip']['uploaded_on'],
 771                         compat_str)
 772                     video_description = clean_html(dict_get(
 773                         page_config, ('description', 'description_html_escaped')))
 774                 config = self._download_json(config_url, video_id)
 775             except RegexNotFoundError:
 776                 # For pro videos or player.vimeo.com urls
 777                 # We try to find out to which variable is assigned the config dic
 778                 m_variable_name = re.search(r'(\w)\.video\.id', webpage)
 779                 if m_variable_name is not None:
 780                     config_re = [r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))]
 781                 else:
 782                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
 783                 config_re.append(r'\bvar\s+r\s*=\s*({.+?})\s*;')
 784                 config_re.append(r'\bconfig\s*=\s*({.+?})\s*;')
 785                 config = self._search_regex(config_re, webpage, 'info section',
 786                                             flags=re.DOTALL)
 787                 config = json.loads(config)
 788         except Exception as e:
 789             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
 790                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 791
 792             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
 793                 if '_video_password_verified' in data:
 794                     raise ExtractorError('video password verification failed!')
 795                 video_password = self._get_video_password()
 796                 token, vuid = self._extract_xsrft_and_vuid(webpage)
 797                 self._verify_video_password(
 798                     redirect_url, video_id, video_password, token, vuid)
 799                 return self._real_extract(
 800                     smuggle_url(redirect_url, {'_video_password_verified': 'verified'}))
 801             else:
 802                 raise ExtractorError('Unable to extract info section',
 803                                      cause=e)
 804         else:
 805             if config.get('view') == 4:
 806                 config = self._verify_player_video_password(redirect_url, video_id, headers)
 807
 808         video = config.get('video') or {}
 809         vod = video.get('vod') or {}
 810
 811         def is_rented():
 812             if '>You rented this title.<' in webpage:
 813                 return True
 814             if config.get('user', {}).get('purchased'):
 815                 return True
 816             for purchase_option in vod.get('purchase_options', []):
 817                 if purchase_option.get('purchased'):
 818                     return True
 819                 label = purchase_option.get('label_string')
 820                 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
 821                     return True
 822             return False
 823
 824         if is_rented() and vod.get('is_trailer'):
 825             feature_id = vod.get('feature_id')
 826             if feature_id and not data.get('force_feature_id', False):
 827                 return self.url_result(smuggle_url(
 828                     'https://player.vimeo.com/player/%s' % feature_id,
 829                     {'force_feature_id': True}), 'Vimeo')
 830
 831         # Extract video description
 832         if not video_description:
 833             video_description = self._html_search_regex(
 834                 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 835                 webpage, 'description', default=None)
 836         if not video_description:
 837             video_description = self._html_search_meta(
 838                 'description', webpage, default=None)
 839         if not video_description and is_pro:
 840             orig_webpage = self._download_webpage(
 841                 orig_url, video_id,
 842                 note='Downloading webpage for description',
 843                 fatal=False)
 844             if orig_webpage:
 845                 video_description = self._html_search_meta(
 846                     'description', orig_webpage, default=None)
 847         if not video_description and not is_player:
 848             self.report_warning('Cannot find video description')
 849
 850         # Extract upload date
 851         if not timestamp:
 852             timestamp = self._search_regex(
 853                 r'<time[^>]+datetime="([^"]+)"', webpage,
 854                 'timestamp', default=None)
 855
 856         try:
 857             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
 858             like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
 859             comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
 860         except RegexNotFoundError:
 861             # This info is only available in vimeo.com/{id} urls
 862             view_count = None
 863             like_count = None
 864             comment_count = None
 865
 866         formats = []
 867
 868         source_format = self._extract_original_format(
 869             'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
 870         if source_format:
 871             formats.append(source_format)
 872
 873         info_dict_config = self._parse_config(config, video_id)
 874         formats.extend(info_dict_config['formats'])
 875         self._vimeo_sort_formats(formats)
 876
 877         json_ld = self._search_json_ld(webpage, video_id, default={})
 878
 879         if not cc_license:
 880             cc_license = self._search_regex(
 881                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
 882                 webpage, 'license', default=None, group='license')
 883
 884         channel_id = self._search_regex(
 885             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
 886         channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
 887
 888         info_dict = {
 889             'formats': formats,
 890             'timestamp': unified_timestamp(timestamp),
 891             'description': video_description,
 892             'webpage_url': url,
 893             'view_count': view_count,
 894             'like_count': like_count,
 895             'comment_count': comment_count,
 896             'license': cc_license,
 897             'channel_id': channel_id,
 898             'channel_url': channel_url,
 899         }
 900
 901         info_dict = merge_dicts(info_dict, info_dict_config, json_ld)
 902
 903         return info_dict
 904
 905
 906 class VimeoOndemandIE(VimeoIE):
 907     IE_NAME = 'vimeo:ondemand'
 908     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/([^/]+/)?(?P<id>[^/?#&]+)'
 909     _TESTS = [{
 910         # ondemand video not available via https://vimeo.com/id
 911         'url': 'https://vimeo.com/ondemand/20704',
 912         'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
 913         'info_dict': {
 914             'id': '105442900',
 915             'ext': 'mp4',
 916             'title': 'המעבדה - במאי יותם פלדמן',
 917             'uploader': 'גם סרטים',
 918             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
 919             'uploader_id': 'gumfilms',
 920             'description': 'md5:4c027c965e439de4baab621e48b60791',
 921             'upload_date': '20140906',
 922             'timestamp': 1410032453,
 923         },
 924         'params': {
 925             'format': 'best[protocol=https]',
 926         },
 927         'expected_warnings': ['Unable to download JSON metadata'],
 928     }, {
 929         # requires Referer to be passed along with og:video:url
 930         'url': 'https://vimeo.com/ondemand/36938/126682985',
 931         'info_dict': {
 932             'id': '126584684',
 933             'ext': 'mp4',
 934             'title': 'Rävlock, rätt läte på rätt plats',
 935             'uploader': 'Lindroth & Norin',
 936             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
 937             'uploader_id': 'lindrothnorin',
 938             'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
 939             'upload_date': '20150502',
 940             'timestamp': 1430586422,
 941         },
 942         'params': {
 943             'skip_download': True,
 944         },
 945         'expected_warnings': ['Unable to download JSON metadata'],
 946     }, {
 947         'url': 'https://vimeo.com/ondemand/nazmaalik',
 948         'only_matching': True,
 949     }, {
 950         'url': 'https://vimeo.com/ondemand/141692381',
 951         'only_matching': True,
 952     }, {
 953         'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
 954         'only_matching': True,
 955     }]
 956
 957
 958 class VimeoChannelIE(VimeoBaseInfoExtractor):
 959     IE_NAME = 'vimeo:channel'
 960     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 961     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 962     _TITLE = None
 963     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 964     _TESTS = [{
 965         'url': 'https://vimeo.com/channels/tributes',
 966         'info_dict': {
 967             'id': 'tributes',
 968             'title': 'Vimeo Tributes',
 969         },
 970         'playlist_mincount': 25,
 971     }]
 972     _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
 973
 974     def _page_url(self, base_url, pagenum):
 975         return '%s/videos/page:%d/' % (base_url, pagenum)
 976
 977     def _extract_list_title(self, webpage):
 978         return self._TITLE or self._html_search_regex(
 979             self._TITLE_RE, webpage, 'list title', fatal=False)
 980
 981     def _title_and_entries(self, list_id, base_url):
 982         for pagenum in itertools.count(1):
 983             page_url = self._page_url(base_url, pagenum)
 984             webpage = self._download_webpage(
 985                 page_url, list_id,
 986                 'Downloading page %s' % pagenum)
 987
 988             if pagenum == 1:
 989                 yield self._extract_list_title(webpage)
 990
 991             # Try extracting href first since not all videos are available via
 992             # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
 993             clips = re.findall(
 994                 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
 995             if clips:
 996                 for video_id, video_url, video_title in clips:
 997                     yield self.url_result(
 998                         compat_urlparse.urljoin(base_url, video_url),
 999                         VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
1000             # More relaxed fallback
1001             else:
1002                 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
1003                     yield self.url_result(
1004                         'https://vimeo.com/%s' % video_id,
1005                         VimeoIE.ie_key(), video_id=video_id)
1006
1007             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
1008                 break
1009
1010     def _extract_videos(self, list_id, base_url):
1011         title_and_entries = self._title_and_entries(list_id, base_url)
1012         list_title = next(title_and_entries)
1013         return self.playlist_result(title_and_entries, list_id, list_title)
1014
1015     def _real_extract(self, url):
1016         channel_id = self._match_id(url)
1017         return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
1018
1019
1020 class VimeoUserIE(VimeoChannelIE):
1021     IE_NAME = 'vimeo:user'
1022     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
1023     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
1024     _TESTS = [{
1025         'url': 'https://vimeo.com/nkistudio/videos',
1026         'info_dict': {
1027             'title': 'Nki',
1028             'id': 'nkistudio',
1029         },
1030         'playlist_mincount': 66,
1031     }]
1032     _BASE_URL_TEMPL = 'https://vimeo.com/%s'
1033
1034
1035 class VimeoAlbumIE(VimeoBaseInfoExtractor):
1036     IE_NAME = 'vimeo:album'
1037     _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
1038     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
1039     _TESTS = [{
1040         'url': 'https://vimeo.com/album/2632481',
1041         'info_dict': {
1042             'id': '2632481',
1043             'title': 'Staff Favorites: November 2013',
1044         },
1045         'playlist_mincount': 13,
1046     }, {
1047         'note': 'Password-protected album',
1048         'url': 'https://vimeo.com/album/3253534',
1049         'info_dict': {
1050             'title': 'test',
1051             'id': '3253534',
1052         },
1053         'playlist_count': 1,
1054         'params': {
1055             'videopassword': 'youtube-dl',
1056         }
1057     }]
1058     _PAGE_SIZE = 100
1059
1060     def _fetch_page(self, album_id, authorization, hashed_pass, page):
1061         api_page = page + 1
1062         query = {
1063             'fields': 'link,uri',
1064             'page': api_page,
1065             'per_page': self._PAGE_SIZE,
1066         }
1067         if hashed_pass:
1068             query['_hashed_pass'] = hashed_pass
1069         try:
1070             videos = self._download_json(
1071                 'https://api.vimeo.com/albums/%s/videos' % album_id,
1072                 album_id, 'Downloading page %d' % api_page, query=query, headers={
1073                     'Authorization': 'jwt ' + authorization,
1074                 })['data']
1075         except ExtractorError as e:
1076             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
1077                 return
1078         for video in videos:
1079             link = video.get('link')
1080             if not link:
1081                 continue
1082             uri = video.get('uri')
1083             video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
1084             yield self.url_result(link, VimeoIE.ie_key(), video_id)
1085
1086     def _real_extract(self, url):
1087         album_id = self._match_id(url)
1088         viewer = self._download_json(
1089             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
1090         if not viewer:
1091             webpage = self._download_webpage(url, album_id)
1092             viewer = self._parse_json(self._search_regex(
1093                 r'bootstrap_data\s*=\s*({.+?})</script>',
1094                 webpage, 'bootstrap data'), album_id)['viewer']
1095         jwt = viewer['jwt']
1096         album = self._download_json(
1097             'https://api.vimeo.com/albums/' + album_id,
1098             album_id, headers={'Authorization': 'jwt ' + jwt},
1099             query={'fields': 'description,name,privacy'})
1100         hashed_pass = None
1101         if try_get(album, lambda x: x['privacy']['view']) == 'password':
1102             password = self.get_param('videopassword')
1103             if not password:
1104                 raise ExtractorError(
1105                     'This album is protected by a password, use the --video-password option',
1106                     expected=True)
1107             self._set_vimeo_cookie('vuid', viewer['vuid'])
1108             try:
1109                 hashed_pass = self._download_json(
1110                     'https://vimeo.com/showcase/%s/auth' % album_id,
1111                     album_id, 'Verifying the password', data=urlencode_postdata({
1112                         'password': password,
1113                         'token': viewer['xsrft'],
1114                     }), headers={
1115                         'X-Requested-With': 'XMLHttpRequest',
1116                     })['hashed_pass']
1117             except ExtractorError as e:
1118                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
1119                     raise ExtractorError('Wrong password', expected=True)
1120                 raise
1121         entries = OnDemandPagedList(functools.partial(
1122             self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
1123         return self.playlist_result(
1124             entries, album_id, album.get('name'), album.get('description'))
1125
1126
1127 class VimeoGroupsIE(VimeoChannelIE):
1128     IE_NAME = 'vimeo:group'
1129     _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
1130     _TESTS = [{
1131         'url': 'https://vimeo.com/groups/kattykay',
1132         'info_dict': {
1133             'id': 'kattykay',
1134             'title': 'Katty Kay',
1135         },
1136         'playlist_mincount': 27,
1137     }]
1138     _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
1139
1140
1141 class VimeoReviewIE(VimeoBaseInfoExtractor):
1142     IE_NAME = 'vimeo:review'
1143     IE_DESC = 'Review pages on vimeo'
1144     _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
1145     _TESTS = [{
1146         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1147         'md5': 'c507a72f780cacc12b2248bb4006d253',
1148         'info_dict': {
1149             'id': '75524534',
1150             'ext': 'mp4',
1151             'title': "DICK HARDWICK 'Comedian'",
1152             'uploader': 'Richard Hardwick',
1153             'uploader_id': 'user21297594',
1154             'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1155         },
1156         'expected_warnings': ['Unable to download JSON metadata'],
1157     }, {
1158         'note': 'video player needs Referer',
1159         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1160         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1161         'info_dict': {
1162             'id': '91613211',
1163             'ext': 'mp4',
1164             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1165             'uploader': 'DevWeek Events',
1166             'duration': 2773,
1167             'thumbnail': r're:^https?://.*\.jpg$',
1168             'uploader_id': 'user22258446',
1169         },
1170         'skip': 'video gone',
1171     }, {
1172         'note': 'Password protected',
1173         'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1174         'info_dict': {
1175             'id': '138823582',
1176             'ext': 'mp4',
1177             'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1178             'uploader': 'TMB',
1179             'uploader_id': 'user37284429',
1180         },
1181         'params': {
1182             'videopassword': 'holygrail',
1183         },
1184         'skip': 'video gone',
1185     }]
1186
1187     def _real_initialize(self):
1188         self._login()
1189
1190     def _real_extract(self, url):
1191         page_url, video_id = self._match_valid_url(url).groups()
1192         data = self._download_json(
1193             page_url.replace('/review/', '/review/data/'), video_id)
1194         if data.get('isLocked') is True:
1195             video_password = self._get_video_password()
1196             viewer = self._download_json(
1197                 'https://vimeo.com/_rv/viewer', video_id)
1198             webpage = self._verify_video_password(
1199                 'https://vimeo.com/' + video_id, video_id,
1200                 video_password, viewer['xsrft'], viewer['vuid'])
1201             clip_page_config = self._parse_json(self._search_regex(
1202                 r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
1203                 webpage, 'clip page config'), video_id)
1204             config_url = clip_page_config['player']['config_url']
1205             clip_data = clip_page_config.get('clip') or {}
1206         else:
1207             clip_data = data['clipData']
1208             config_url = clip_data['configUrl']
1209         config = self._download_json(config_url, video_id)
1210         info_dict = self._parse_config(config, video_id)
1211         source_format = self._extract_original_format(
1212             page_url + '/action', video_id)
1213         if source_format:
1214             info_dict['formats'].append(source_format)
1215         self._vimeo_sort_formats(info_dict['formats'])
1216         info_dict['description'] = clean_html(clip_data.get('description'))
1217         return info_dict
1218
1219
1220 class VimeoWatchLaterIE(VimeoChannelIE):
1221     IE_NAME = 'vimeo:watchlater'
1222     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
1223     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1224     _TITLE = 'Watch Later'
1225     _LOGIN_REQUIRED = True
1226     _TESTS = [{
1227         'url': 'https://vimeo.com/watchlater',
1228         'only_matching': True,
1229     }]
1230
1231     def _real_initialize(self):
1232         self._login()
1233
1234     def _page_url(self, base_url, pagenum):
1235         url = '%s/page:%d/' % (base_url, pagenum)
1236         request = sanitized_Request(url)
1237         # Set the header to get a partial html page with the ids,
1238         # the normal page doesn't contain them.
1239         request.add_header('X-Requested-With', 'XMLHttpRequest')
1240         return request
1241
1242     def _real_extract(self, url):
1243         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1244
1245
1246 class VimeoLikesIE(VimeoChannelIE):
1247     _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1248     IE_NAME = 'vimeo:likes'
1249     IE_DESC = 'Vimeo user likes'
1250     _TESTS = [{
1251         'url': 'https://vimeo.com/user755559/likes/',
1252         'playlist_mincount': 293,
1253         'info_dict': {
1254             'id': 'user755559',
1255             'title': 'urza’s Likes',
1256         },
1257     }, {
1258         'url': 'https://vimeo.com/stormlapse/likes',
1259         'only_matching': True,
1260     }]
1261
1262     def _page_url(self, base_url, pagenum):
1263         return '%s/page:%d/' % (base_url, pagenum)
1264
1265     def _real_extract(self, url):
1266         user_id = self._match_id(url)
1267         return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
1268
1269
1270 class VHXEmbedIE(VimeoBaseInfoExtractor):
1271     IE_NAME = 'vhx:embed'
1272     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1273
1274     @staticmethod
1275     def _extract_url(webpage):
1276         mobj = re.search(
1277             r'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage)
1278         return unescapeHTML(mobj.group(1)) if mobj else None
1279
1280     def _real_extract(self, url):
1281         video_id = self._match_id(url)
1282         webpage = self._download_webpage(url, video_id)
1283         config_url = self._parse_json(self._search_regex(
1284             r'window\.OTTData\s*=\s*({.+})', webpage,
1285             'ott data'), video_id, js_to_json)['config_url']
1286         config = self._download_json(config_url, video_id)
1287         info = self._parse_config(config, video_id)
1288         info['id'] = video_id
1289         self._vimeo_sort_formats(info['formats'])
1290         return info