yt_dlp/extractor/vimeo.py

   1 import base64
   2 import functools
   3 import re
   4 import itertools
   5 import urllib.error
   6
   7 from .common import InfoExtractor
   8 from ..compat import (
   9     compat_HTTPError,
  10     compat_str,
  11     compat_urlparse,
  12 )
  13 from ..utils import (
  14     clean_html,
  15     determine_ext,
  16     ExtractorError,
  17     get_element_by_class,
  18     HEADRequest,
  19     js_to_json,
  20     int_or_none,
  21     merge_dicts,
  22     OnDemandPagedList,
  23     parse_filesize,
  24     parse_iso8601,
  25     parse_qs,
  26     sanitized_Request,
  27     smuggle_url,
  28     str_or_none,
  29     try_get,
  30     unified_timestamp,
  31     unsmuggle_url,
  32     urlencode_postdata,
  33     urljoin,
  34     urlhandle_detect_ext,
  35 )
  36
  37
  38 class VimeoBaseInfoExtractor(InfoExtractor):
  39     _NETRC_MACHINE = 'vimeo'
  40     _LOGIN_REQUIRED = False
  41     _LOGIN_URL = 'https://vimeo.com/log_in'
  42
  43     @staticmethod
  44     def _smuggle_referrer(url, referrer_url):
  45         return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
  46
  47     def _unsmuggle_headers(self, url):
  48         """@returns (url, smuggled_data, headers)"""
  49         url, data = unsmuggle_url(url, {})
  50         headers = self.get_param('http_headers').copy()
  51         if 'http_headers' in data:
  52             headers.update(data['http_headers'])
  53         return url, data, headers
  54
  55     def _perform_login(self, username, password):
  56         webpage = self._download_webpage(
  57             self._LOGIN_URL, None, 'Downloading login page')
  58         token, vuid = self._extract_xsrft_and_vuid(webpage)
  59         data = {
  60             'action': 'login',
  61             'email': username,
  62             'password': password,
  63             'service': 'vimeo',
  64             'token': token,
  65         }
  66         self._set_vimeo_cookie('vuid', vuid)
  67         try:
  68             self._download_webpage(
  69                 self._LOGIN_URL, None, 'Logging in',
  70                 data=urlencode_postdata(data), headers={
  71                     'Content-Type': 'application/x-www-form-urlencoded',
  72                     'Referer': self._LOGIN_URL,
  73                 })
  74         except ExtractorError as e:
  75             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418:
  76                 raise ExtractorError(
  77                     'Unable to log in: bad username or password',
  78                     expected=True)
  79             raise ExtractorError('Unable to log in')
  80
  81     def _real_initialize(self):
  82         if self._LOGIN_REQUIRED and not self._get_cookies('https://vimeo.com').get('vuid'):
  83             self._raise_login_required()
  84
  85     def _get_video_password(self):
  86         password = self.get_param('videopassword')
  87         if password is None:
  88             raise ExtractorError(
  89                 'This video is protected by a password, use the --video-password option',
  90                 expected=True)
  91         return password
  92
  93     def _verify_video_password(self, url, video_id, password, token, vuid):
  94         if url.startswith('http://'):
  95             # vimeo only supports https now, but the user can give an http url
  96             url = url.replace('http://', 'https://')
  97         self._set_vimeo_cookie('vuid', vuid)
  98         return self._download_webpage(
  99             url + '/password', video_id, 'Verifying the password',
 100             'Wrong password', data=urlencode_postdata({
 101                 'password': password,
 102                 'token': token,
 103             }), headers={
 104                 'Content-Type': 'application/x-www-form-urlencoded',
 105                 'Referer': url,
 106             })
 107
 108     def _extract_xsrft_and_vuid(self, webpage):
 109         xsrft = self._search_regex(
 110             r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
 111             webpage, 'login token', group='xsrft')
 112         vuid = self._search_regex(
 113             r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
 114             webpage, 'vuid', group='vuid')
 115         return xsrft, vuid
 116
 117     def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
 118         vimeo_config = self._search_regex(
 119             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
 120             webpage, 'vimeo config', *args, **kwargs)
 121         if vimeo_config:
 122             return self._parse_json(vimeo_config, video_id)
 123
 124     def _set_vimeo_cookie(self, name, value):
 125         self._set_cookie('vimeo.com', name, value)
 126
 127     def _parse_config(self, config, video_id):
 128         video_data = config['video']
 129         video_title = video_data.get('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         subtitles = {}
 136
 137         config_files = video_data.get('files') or request.get('files') or {}
 138         for f in (config_files.get('progressive') or []):
 139             video_url = f.get('url')
 140             if not video_url:
 141                 continue
 142             formats.append({
 143                 'url': video_url,
 144                 'format_id': 'http-%s' % f.get('quality'),
 145                 'source_preference': 10,
 146                 'width': int_or_none(f.get('width')),
 147                 'height': int_or_none(f.get('height')),
 148                 'fps': int_or_none(f.get('fps')),
 149                 'tbr': int_or_none(f.get('bitrate')),
 150             })
 151
 152         # TODO: fix handling of 308 status code returned for live archive manifest requests
 153         sep_pattern = r'/sep/video/'
 154         for files_type in ('hls', 'dash'):
 155             for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items():
 156                 manifest_url = cdn_data.get('url')
 157                 if not manifest_url:
 158                     continue
 159                 format_id = '%s-%s' % (files_type, cdn_name)
 160                 sep_manifest_urls = []
 161                 if re.search(sep_pattern, manifest_url):
 162                     for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
 163                         sep_manifest_urls.append((format_id + suffix, re.sub(
 164                             sep_pattern, '/%s/' % repl, manifest_url)))
 165                 else:
 166                     sep_manifest_urls = [(format_id, manifest_url)]
 167                 for f_id, m_url in sep_manifest_urls:
 168                     if files_type == 'hls':
 169                         fmts, subs = self._extract_m3u8_formats_and_subtitles(
 170                             m_url, video_id, 'mp4', live=is_live, m3u8_id=f_id,
 171                             note='Downloading %s m3u8 information' % cdn_name,
 172                             fatal=False)
 173                         formats.extend(fmts)
 174                         self._merge_subtitles(subs, target=subtitles)
 175                     elif files_type == 'dash':
 176                         if 'json=1' in m_url:
 177                             real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
 178                             if real_m_url:
 179                                 m_url = real_m_url
 180                         fmts, subs = self._extract_mpd_formats_and_subtitles(
 181                             m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
 182                             'Downloading %s MPD information' % cdn_name,
 183                             fatal=False)
 184                         formats.extend(fmts)
 185                         self._merge_subtitles(subs, target=subtitles)
 186
 187         live_archive = live_event.get('archive') or {}
 188         live_archive_source_url = live_archive.get('source_url')
 189         if live_archive_source_url and live_archive.get('status') == 'done':
 190             formats.append({
 191                 'format_id': 'live-archive-source',
 192                 'url': live_archive_source_url,
 193                 'quality': 10,
 194             })
 195
 196         for tt in (request.get('text_tracks') or []):
 197             subtitles.setdefault(tt['lang'], []).append({
 198                 'ext': 'vtt',
 199                 'url': urljoin('https://vimeo.com', tt['url']),
 200             })
 201
 202         thumbnails = []
 203         if not is_live:
 204             for key, thumb in (video_data.get('thumbs') or {}).items():
 205                 thumbnails.append({
 206                     'id': key,
 207                     'width': int_or_none(key),
 208                     'url': thumb,
 209                 })
 210             thumbnail = video_data.get('thumbnail')
 211             if thumbnail:
 212                 thumbnails.append({
 213                     'url': thumbnail,
 214                 })
 215
 216         owner = video_data.get('owner') or {}
 217         video_uploader_url = owner.get('url')
 218
 219         duration = int_or_none(video_data.get('duration'))
 220         chapter_data = try_get(config, lambda x: x['embed']['chapters']) or []
 221         chapters = [{
 222             'title': current_chapter.get('title'),
 223             'start_time': current_chapter.get('timecode'),
 224             'end_time': next_chapter.get('timecode'),
 225         } for current_chapter, next_chapter in zip(chapter_data, chapter_data[1:] + [{'timecode': duration}])]
 226         if chapters and chapters[0]['start_time']:  # Chapters may not start from 0
 227             chapters[:0] = [{'title': '<Untitled>', 'start_time': 0, 'end_time': chapters[0]['start_time']}]
 228
 229         return {
 230             'id': str_or_none(video_data.get('id')) or video_id,
 231             'title': video_title,
 232             'uploader': owner.get('name'),
 233             'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
 234             'uploader_url': video_uploader_url,
 235             'thumbnails': thumbnails,
 236             'duration': duration,
 237             'chapters': chapters or None,
 238             'formats': formats,
 239             'subtitles': subtitles,
 240             'is_live': is_live,
 241             # Note: Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
 242             # at the same time without actual units specified.
 243             '_format_sort_fields': ('quality', 'res', 'fps', 'hdr:12', 'source'),
 244         }
 245
 246     def _extract_original_format(self, url, video_id, unlisted_hash=None):
 247         query = {'action': 'load_download_config'}
 248         if unlisted_hash:
 249             query['unlisted_hash'] = unlisted_hash
 250         download_data = self._download_json(
 251             url, video_id, fatal=False, query=query,
 252             headers={'X-Requested-With': 'XMLHttpRequest'},
 253             expected_status=(403, 404)) or {}
 254         source_file = download_data.get('source_file')
 255         download_url = try_get(source_file, lambda x: x['download_url'])
 256         if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 257             source_name = source_file.get('public_name', 'Original')
 258             if self._is_valid_url(download_url, video_id, '%s video' % source_name):
 259                 ext = (try_get(
 260                     source_file, lambda x: x['extension'],
 261                     compat_str) or determine_ext(
 262                     download_url, None) or 'mp4').lower()
 263                 return {
 264                     'url': download_url,
 265                     'ext': ext,
 266                     'width': int_or_none(source_file.get('width')),
 267                     'height': int_or_none(source_file.get('height')),
 268                     'filesize': parse_filesize(source_file.get('size')),
 269                     'format_id': source_name,
 270                     'quality': 1,
 271                 }
 272
 273         jwt_response = self._download_json(
 274             'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {}
 275         if not jwt_response.get('jwt'):
 276             return
 277         headers = {'Authorization': 'jwt %s' % jwt_response['jwt']}
 278         original_response = self._download_json(
 279             f'https://api.vimeo.com/videos/{video_id}', video_id,
 280             headers=headers, fatal=False, expected_status=(403, 404)) or {}
 281         for download_data in original_response.get('download') or []:
 282             download_url = download_data.get('link')
 283             if not download_url or download_data.get('quality') != 'source':
 284                 continue
 285             ext = determine_ext(parse_qs(download_url).get('filename', [''])[0].lower(), default_ext=None)
 286             if not ext:
 287                 urlh = self._request_webpage(
 288                     HEADRequest(download_url), video_id, fatal=False, note='Determining source extension')
 289                 ext = urlh and urlhandle_detect_ext(urlh)
 290             return {
 291                 'url': download_url,
 292                 'ext': ext or 'unknown_video',
 293                 'format_id': download_data.get('public_name', 'Original'),
 294                 'width': int_or_none(download_data.get('width')),
 295                 'height': int_or_none(download_data.get('height')),
 296                 'fps': int_or_none(download_data.get('fps')),
 297                 'filesize': int_or_none(download_data.get('size')),
 298                 'quality': 1,
 299             }
 300
 301
 302 class VimeoIE(VimeoBaseInfoExtractor):
 303     """Information extractor for vimeo.com."""
 304
 305     # _VALID_URL matches Vimeo URLs
 306     _VALID_URL = r'''(?x)
 307                     https?://
 308                         (?:
 309                             (?:
 310                                 www|
 311                                 player
 312                             )
 313                             \.
 314                         )?
 315                         vimeo\.com/
 316                         (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
 317                         (?:[^/]+/)*?
 318                         (?:
 319                             (?:
 320                                 play_redirect_hls|
 321                                 moogaloop\.swf)\?clip_id=
 322                             )?
 323                         (?:videos?/)?
 324                         (?P<id>[0-9]+)
 325                         (?:/(?P<unlisted_hash>[\da-f]{10}))?
 326                         /?(?:[?&].*)?(?:[#].*)?$
 327                     '''
 328     IE_NAME = 'vimeo'
 329     _EMBED_REGEX = [
 330         # iframe
 331         r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
 332         # Embedded (swf embed) Vimeo player
 333         r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
 334         # Non-standard embedded Vimeo player
 335         r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
 336     ]
 337     _TESTS = [
 338         {
 339             'url': 'http://vimeo.com/56015672#at=0',
 340             'md5': '8879b6cc097e987f02484baf890129e5',
 341             'info_dict': {
 342                 'id': '56015672',
 343                 'ext': 'mp4',
 344                 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
 345                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
 346                 'timestamp': 1355990239,
 347                 'upload_date': '20121220',
 348                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
 349                 'uploader_id': 'user7108434',
 350                 'uploader': 'Filippo Valsorda',
 351                 'duration': 10,
 352                 'license': 'by-sa',
 353             },
 354             'params': {
 355                 'format': 'best[protocol=https]',
 356             },
 357             'skip': 'No longer available'
 358         },
 359         {
 360             'url': 'http://player.vimeo.com/video/54469442',
 361             'md5': '619b811a4417aa4abe78dc653becf511',
 362             'note': 'Videos that embed the url in the player page',
 363             'info_dict': {
 364                 'id': '54469442',
 365                 'ext': 'mp4',
 366                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 367                 'uploader': 'Business of Software',
 368                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
 369                 'uploader_id': 'businessofsoftware',
 370                 'duration': 3610,
 371                 'description': None,
 372                 'thumbnail': 'https://i.vimeocdn.com/video/376682406-f34043e7b766af6bef2af81366eacd6724f3fc3173179a11a97a1e26587c9529-d_1280',
 373             },
 374             'params': {
 375                 'format': 'best[protocol=https]',
 376             },
 377         },
 378         {
 379             'url': 'http://vimeo.com/68375962',
 380             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 381             'note': 'Video protected with password',
 382             'info_dict': {
 383                 'id': '68375962',
 384                 'ext': 'mp4',
 385                 'title': 'youtube-dl password protected test video',
 386                 'timestamp': 1371200155,
 387                 'upload_date': '20130614',
 388                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 389                 'uploader_id': 'user18948128',
 390                 'uploader': 'Jaime Marquínez Ferrándiz',
 391                 'duration': 10,
 392                 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
 393                 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
 394                 'view_count': int,
 395                 'comment_count': int,
 396                 'like_count': int,
 397             },
 398             'params': {
 399                 'format': 'best[protocol=https]',
 400                 'videopassword': 'youtube-dl',
 401             },
 402         },
 403         {
 404             'url': 'http://vimeo.com/channels/keypeele/75629013',
 405             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 406             'info_dict': {
 407                 'id': '75629013',
 408                 'ext': 'mp4',
 409                 'title': 'Key & Peele: Terrorist Interrogation',
 410                 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
 411                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
 412                 'uploader_id': 'atencio',
 413                 'uploader': 'Peter Atencio',
 414                 'channel_id': 'keypeele',
 415                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
 416                 'timestamp': 1380339469,
 417                 'upload_date': '20130928',
 418                 'duration': 187,
 419                 'thumbnail': 'https://i.vimeocdn.com/video/450239872-a05512d9b1e55d707a7c04365c10980f327b06d966351bc403a5d5d65c95e572-d_1280',
 420                 'view_count': int,
 421                 'comment_count': int,
 422                 'like_count': int,
 423             },
 424             'params': {'format': 'http-1080p'},
 425         },
 426         {
 427             'url': 'http://vimeo.com/76979871',
 428             'note': 'Video with subtitles',
 429             'info_dict': {
 430                 'id': '76979871',
 431                 'ext': 'mov',
 432                 'title': 'The New Vimeo Player (You Know, For Videos)',
 433                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 434                 'timestamp': 1381846109,
 435                 'upload_date': '20131015',
 436                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
 437                 'uploader_id': 'staff',
 438                 'uploader': 'Vimeo Staff',
 439                 'duration': 62,
 440                 'subtitles': {
 441                     'de': [{'ext': 'vtt'}],
 442                     'en': [{'ext': 'vtt'}],
 443                     'es': [{'ext': 'vtt'}],
 444                     'fr': [{'ext': 'vtt'}],
 445                 },
 446             },
 447             'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
 448         },
 449         {
 450             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 451             'url': 'https://player.vimeo.com/video/98044508',
 452             'note': 'The js code contains assignments to the same variable as the config',
 453             'info_dict': {
 454                 'id': '98044508',
 455                 'ext': 'mp4',
 456                 'title': 'Pier Solar OUYA Official Trailer',
 457                 'uploader': 'Tulio Gonçalves',
 458                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
 459                 'uploader_id': 'user28849593',
 460                 'duration': 118,
 461                 'thumbnail': 'https://i.vimeocdn.com/video/478636036-c18440305ef3df9decfb6bf207a61fe39d2d17fa462a96f6f2d93d30492b037d-d_1280',
 462             },
 463         },
 464         {
 465             # contains original format
 466             'url': 'https://vimeo.com/33951933',
 467             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 468             'info_dict': {
 469                 'id': '33951933',
 470                 'ext': 'mp4',
 471                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 472                 'uploader': 'The DMCI',
 473                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
 474                 'uploader_id': 'dmci',
 475                 'timestamp': 1324343742,
 476                 'upload_date': '20111220',
 477                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 478                 'duration': 60,
 479                 'comment_count': int,
 480                 'view_count': int,
 481                 'thumbnail': 'https://i.vimeocdn.com/video/231174622-dd07f015e9221ff529d451e1cc31c982b5d87bfafa48c4189b1da72824ee289a-d_1280',
 482                 'like_count': int,
 483             },
 484         },
 485         {
 486             'note': 'Contains original format not accessible in webpage',
 487             'url': 'https://vimeo.com/393756517',
 488             'md5': 'c464af248b592190a5ffbb5d33f382b0',
 489             'info_dict': {
 490                 'id': '393756517',
 491                 'ext': 'mov',
 492                 'timestamp': 1582642091,
 493                 'uploader_id': 'frameworkla',
 494                 'title': 'Straight To Hell - Sabrina: Netflix',
 495                 'uploader': 'Framework Studio',
 496                 'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
 497                 'upload_date': '20200225',
 498                 'duration': 176,
 499                 'thumbnail': 'https://i.vimeocdn.com/video/859377297-836494a4ef775e9d4edbace83937d9ad34dc846c688c0c419c0e87f7ab06c4b3-d_1280',
 500                 'uploader_url': 'https://vimeo.com/frameworkla',
 501             },
 502         },
 503         {
 504             # only available via https://vimeo.com/channels/tributes/6213729 and
 505             # not via https://vimeo.com/6213729
 506             'url': 'https://vimeo.com/channels/tributes/6213729',
 507             'info_dict': {
 508                 'id': '6213729',
 509                 'ext': 'mp4',
 510                 'title': 'Vimeo Tribute: The Shining',
 511                 'uploader': 'Casey Donahue',
 512                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
 513                 'uploader_id': 'caseydonahue',
 514                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
 515                 'channel_id': 'tributes',
 516                 'timestamp': 1250886430,
 517                 'upload_date': '20090821',
 518                 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
 519                 'duration': 321,
 520                 'comment_count': int,
 521                 'view_count': int,
 522                 'thumbnail': 'https://i.vimeocdn.com/video/22728298-bfc22146f930de7cf497821c7b0b9f168099201ecca39b00b6bd31fcedfca7a6-d_1280',
 523                 'like_count': int,
 524             },
 525             'params': {
 526                 'skip_download': True,
 527             },
 528         },
 529         {
 530             # redirects to ondemand extractor and should be passed through it
 531             # for successful extraction
 532             'url': 'https://vimeo.com/73445910',
 533             'info_dict': {
 534                 'id': '73445910',
 535                 'ext': 'mp4',
 536                 'title': 'The Reluctant Revolutionary',
 537                 'uploader': '10Ft Films',
 538                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
 539                 'uploader_id': 'tenfootfilms',
 540                 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
 541                 'upload_date': '20130830',
 542                 'timestamp': 1377853339,
 543             },
 544             'params': {
 545                 'skip_download': True,
 546             },
 547             'skip': 'this page is no longer available.',
 548         },
 549         {
 550             'url': 'http://player.vimeo.com/video/68375962',
 551             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 552             'info_dict': {
 553                 'id': '68375962',
 554                 'ext': 'mp4',
 555                 'title': 'youtube-dl password protected test video',
 556                 'timestamp': 1371200155,
 557                 'upload_date': '20130614',
 558                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 559                 'uploader_id': 'user18948128',
 560                 'uploader': 'Jaime Marquínez Ferrándiz',
 561                 'duration': 10,
 562                 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
 563                 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
 564                 'view_count': int,
 565                 'comment_count': int,
 566                 'like_count': int,
 567             },
 568             'params': {
 569                 'format': 'best[protocol=https]',
 570                 'videopassword': 'youtube-dl',
 571             },
 572         },
 573         {
 574             'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
 575             'only_matching': True,
 576         },
 577         {
 578             'url': 'https://vimeo.com/109815029',
 579             'note': 'Video not completely processed, "failed" seed status',
 580             'only_matching': True,
 581         },
 582         {
 583             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 584             'only_matching': True,
 585         },
 586         {
 587             'url': 'https://vimeo.com/album/2632481/video/79010983',
 588             'only_matching': True,
 589         },
 590         {
 591             'url': 'https://vimeo.com/showcase/3253534/video/119195465',
 592             'note': 'A video in a password protected album (showcase)',
 593             'info_dict': {
 594                 'id': '119195465',
 595                 'ext': 'mp4',
 596                 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
 597                 'uploader': 'Philipp Hagemeister',
 598                 'uploader_id': 'user20132939',
 599                 'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
 600                 'upload_date': '20150209',
 601                 'timestamp': 1423518307,
 602                 'thumbnail': 'https://i.vimeocdn.com/video/default_1280',
 603                 'duration': 10,
 604                 'like_count': int,
 605                 'uploader_url': 'https://vimeo.com/user20132939',
 606                 'view_count': int,
 607                 'comment_count': int,
 608             },
 609             'params': {
 610                 'format': 'best[protocol=https]',
 611                 'videopassword': 'youtube-dl',
 612             },
 613         },
 614         {
 615             # source file returns 403: Forbidden
 616             'url': 'https://vimeo.com/7809605',
 617             'only_matching': True,
 618         },
 619         {
 620             'note': 'Direct URL with hash',
 621             'url': 'https://vimeo.com/160743502/abd0e13fb4',
 622             'info_dict': {
 623                 'id': '160743502',
 624                 'ext': 'mp4',
 625                 'uploader': 'Julian Tryba',
 626                 'uploader_id': 'aliniamedia',
 627                 'title': 'Harrisville New Hampshire',
 628                 'timestamp': 1459259666,
 629                 'upload_date': '20160329',
 630                 'release_timestamp': 1459259666,
 631                 'license': 'by-nc',
 632                 'duration': 159,
 633                 'comment_count': int,
 634                 'thumbnail': 'https://i.vimeocdn.com/video/562802436-585eeb13b5020c6ac0f171a2234067938098f84737787df05ff0d767f6d54ee9-d_1280',
 635                 'like_count': int,
 636                 'uploader_url': 'https://vimeo.com/aliniamedia',
 637                 'release_date': '20160329',
 638             },
 639             'params': {'skip_download': True},
 640         },
 641         {
 642             'url': 'https://vimeo.com/138909882',
 643             'info_dict': {
 644                 'id': '138909882',
 645                 'ext': 'mp4',
 646                 'title': 'Eastnor Castle 2015 Firework Champions - The Promo!',
 647                 'description': 'md5:5967e090768a831488f6e74b7821b3c1',
 648                 'uploader_id': 'fireworkchampions',
 649                 'uploader': 'Firework Champions',
 650                 'upload_date': '20150910',
 651                 'timestamp': 1441901895,
 652             },
 653             'params': {
 654                 'skip_download': True,
 655                 'format': 'Original',
 656             },
 657         },
 658         {
 659             'url': 'https://vimeo.com/channels/staffpicks/143603739',
 660             'info_dict': {
 661                 'id': '143603739',
 662                 'ext': 'mp4',
 663                 'uploader': 'Karim Huu Do',
 664                 'timestamp': 1445846953,
 665                 'upload_date': '20151026',
 666                 'title': 'The Shoes - Submarine Feat. Blaine Harrison',
 667                 'uploader_id': 'karimhd',
 668                 'description': 'md5:8e2eea76de4504c2e8020a9bcfa1e843',
 669                 'channel_id': 'staffpicks',
 670                 'duration': 336,
 671                 'comment_count': int,
 672                 'view_count': int,
 673                 'thumbnail': 'https://i.vimeocdn.com/video/541243181-b593db36a16db2f0096f655da3f5a4dc46b8766d77b0f440df937ecb0c418347-d_1280',
 674                 'like_count': int,
 675                 'uploader_url': 'https://vimeo.com/karimhd',
 676                 'channel_url': 'https://vimeo.com/channels/staffpicks',
 677             },
 678             'params': {'skip_download': 'm3u8'},
 679         },
 680         {
 681             # requires passing unlisted_hash(a52724358e) to load_download_config request
 682             'url': 'https://vimeo.com/392479337/a52724358e',
 683             'only_matching': True,
 684         },
 685         {
 686             # similar, but all numeric: ID must be 581039021, not 9603038895
 687             # issue #29690
 688             'url': 'https://vimeo.com/581039021/9603038895',
 689             'info_dict': {
 690                 'id': '581039021',
 691                 'ext': 'mp4',
 692                 'timestamp': 1627621014,
 693                 'release_timestamp': 1627621014,
 694                 'duration': 976,
 695                 'comment_count': int,
 696                 'thumbnail': 'https://i.vimeocdn.com/video/1202249320-4ddb2c30398c0dc0ee059172d1bd5ea481ad12f0e0e3ad01d2266f56c744b015-d_1280',
 697                 'like_count': int,
 698                 'uploader_url': 'https://vimeo.com/txwestcapital',
 699                 'release_date': '20210730',
 700                 'uploader': 'Christopher Inks',
 701                 'title': 'Thursday, July 29, 2021 BMA Evening Video Update',
 702                 'uploader_id': 'txwestcapital',
 703                 'upload_date': '20210730',
 704             },
 705             'params': {
 706                 'skip_download': True,
 707             },
 708         }
 709         # https://gettingthingsdone.com/workflowmap/
 710         # vimeo embed with check-password page protected by Referer header
 711     ]
 712
 713     @classmethod
 714     def _extract_embed_urls(cls, url, webpage):
 715         for embed_url in super()._extract_embed_urls(url, webpage):
 716             yield cls._smuggle_referrer(embed_url, url)
 717
 718     @classmethod
 719     def _extract_url(cls, url, webpage):
 720         return next(cls._extract_embed_urls(url, webpage), None)
 721
 722     def _verify_player_video_password(self, url, video_id, headers):
 723         password = self._get_video_password()
 724         data = urlencode_postdata({
 725             'password': base64.b64encode(password.encode()),
 726         })
 727         headers = merge_dicts(headers, {
 728             'Content-Type': 'application/x-www-form-urlencoded',
 729         })
 730         checked = self._download_json(
 731             f'{compat_urlparse.urlsplit(url)._replace(query=None).geturl()}/check-password',
 732             video_id, 'Verifying the password', data=data, headers=headers)
 733         if checked is False:
 734             raise ExtractorError('Wrong video password', expected=True)
 735         return checked
 736
 737     def _extract_from_api(self, video_id, unlisted_hash=None):
 738         token = self._download_json(
 739             'https://vimeo.com/_rv/jwt', video_id, headers={
 740                 'X-Requested-With': 'XMLHttpRequest'
 741             })['token']
 742         api_url = 'https://api.vimeo.com/videos/' + video_id
 743         if unlisted_hash:
 744             api_url += ':' + unlisted_hash
 745         video = self._download_json(
 746             api_url, video_id, headers={
 747                 'Authorization': 'jwt ' + token,
 748             }, query={
 749                 'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
 750             })
 751         info = self._parse_config(self._download_json(
 752             video['config_url'], video_id), video_id)
 753         get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
 754         info.update({
 755             'description': video.get('description'),
 756             'license': video.get('license'),
 757             'release_timestamp': get_timestamp('release'),
 758             'timestamp': get_timestamp('created'),
 759             'view_count': int_or_none(try_get(video, lambda x: x['stats']['plays'])),
 760         })
 761         connections = try_get(
 762             video, lambda x: x['metadata']['connections'], dict) or {}
 763         for k in ('comment', 'like'):
 764             info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total']))
 765         return info
 766
 767     def _try_album_password(self, url):
 768         album_id = self._search_regex(
 769             r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None)
 770         if not album_id:
 771             return
 772         viewer = self._download_json(
 773             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
 774         if not viewer:
 775             webpage = self._download_webpage(url, album_id)
 776             viewer = self._parse_json(self._search_regex(
 777                 r'bootstrap_data\s*=\s*({.+?})</script>',
 778                 webpage, 'bootstrap data'), album_id)['viewer']
 779         jwt = viewer['jwt']
 780         album = self._download_json(
 781             'https://api.vimeo.com/albums/' + album_id,
 782             album_id, headers={'Authorization': 'jwt ' + jwt},
 783             query={'fields': 'description,name,privacy'})
 784         if try_get(album, lambda x: x['privacy']['view']) == 'password':
 785             password = self.get_param('videopassword')
 786             if not password:
 787                 raise ExtractorError(
 788                     'This album is protected by a password, use the --video-password option',
 789                     expected=True)
 790             self._set_vimeo_cookie('vuid', viewer['vuid'])
 791             try:
 792                 self._download_json(
 793                     'https://vimeo.com/showcase/%s/auth' % album_id,
 794                     album_id, 'Verifying the password', data=urlencode_postdata({
 795                         'password': password,
 796                         'token': viewer['xsrft'],
 797                     }), headers={
 798                         'X-Requested-With': 'XMLHttpRequest',
 799                     })
 800             except ExtractorError as e:
 801                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
 802                     raise ExtractorError('Wrong password', expected=True)
 803                 raise
 804
 805     def _real_extract(self, url):
 806         url, data, headers = self._unsmuggle_headers(url)
 807         if 'Referer' not in headers:
 808             headers['Referer'] = url
 809
 810         # Extract ID from URL
 811         mobj = self._match_valid_url(url).groupdict()
 812         video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash')
 813         if unlisted_hash:
 814             return self._extract_from_api(video_id, unlisted_hash)
 815
 816         if any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
 817             url = 'https://vimeo.com/' + video_id
 818
 819         self._try_album_password(url)
 820         try:
 821             # Retrieve video webpage to extract further information
 822             webpage, urlh = self._download_webpage_handle(
 823                 url, video_id, headers=headers)
 824             redirect_url = urlh.geturl()
 825         except ExtractorError as ee:
 826             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 827                 errmsg = ee.cause.read()
 828                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 829                     raise ExtractorError(
 830                         'Cannot download embed-only video without embedding '
 831                         'URL. Please call yt-dlp with the URL of the page '
 832                         'that embeds this video.',
 833                         expected=True)
 834             raise
 835
 836         if '://player.vimeo.com/video/' in url:
 837             config = self._search_json(
 838                 r'\b(?:playerC|c)onfig\s*=', webpage, 'info section', video_id)
 839             if config.get('view') == 4:
 840                 config = self._verify_player_video_password(
 841                     redirect_url, video_id, headers)
 842             return self._parse_config(config, video_id)
 843
 844         if re.search(r'<form[^>]+?id="pw_form"', webpage):
 845             video_password = self._get_video_password()
 846             token, vuid = self._extract_xsrft_and_vuid(webpage)
 847             webpage = self._verify_video_password(
 848                 redirect_url, video_id, video_password, token, vuid)
 849
 850         vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
 851         if vimeo_config:
 852             seed_status = vimeo_config.get('seed_status') or {}
 853             if seed_status.get('state') == 'failed':
 854                 raise ExtractorError(
 855                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 856                     expected=True)
 857
 858         cc_license = None
 859         timestamp = None
 860         video_description = None
 861         info_dict = {}
 862         config_url = None
 863
 864         channel_id = self._search_regex(
 865             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
 866         if channel_id:
 867             config_url = self._html_search_regex(
 868                 r'\bdata-config-url="([^"]+)"', webpage, 'config URL', default=None)
 869             video_description = clean_html(get_element_by_class('description', webpage))
 870             info_dict.update({
 871                 'channel_id': channel_id,
 872                 'channel_url': 'https://vimeo.com/channels/' + channel_id,
 873             })
 874         if not config_url:
 875             page_config = self._parse_json(self._search_regex(
 876                 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
 877                 webpage, 'page config', default='{}'), video_id, fatal=False)
 878             if not page_config:
 879                 return self._extract_from_api(video_id)
 880             config_url = page_config['player']['config_url']
 881             cc_license = page_config.get('cc_license')
 882             clip = page_config.get('clip') or {}
 883             timestamp = clip.get('uploaded_on')
 884             video_description = clean_html(
 885                 clip.get('description') or page_config.get('description_html_escaped'))
 886         config = self._download_json(config_url, video_id)
 887         video = config.get('video') or {}
 888         vod = video.get('vod') or {}
 889
 890         def is_rented():
 891             if '>You rented this title.<' in webpage:
 892                 return True
 893             if try_get(config, lambda x: x['user']['purchased']):
 894                 return True
 895             for purchase_option in (vod.get('purchase_options') or []):
 896                 if purchase_option.get('purchased'):
 897                     return True
 898                 label = purchase_option.get('label_string')
 899                 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
 900                     return True
 901             return False
 902
 903         if is_rented() and vod.get('is_trailer'):
 904             feature_id = vod.get('feature_id')
 905             if feature_id and not data.get('force_feature_id', False):
 906                 return self.url_result(smuggle_url(
 907                     'https://player.vimeo.com/player/%s' % feature_id,
 908                     {'force_feature_id': True}), 'Vimeo')
 909
 910         if not video_description:
 911             video_description = self._html_search_regex(
 912                 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 913                 webpage, 'description', default=None)
 914         if not video_description:
 915             video_description = self._html_search_meta(
 916                 ['description', 'og:description', 'twitter:description'],
 917                 webpage, default=None)
 918         if not video_description:
 919             self.report_warning('Cannot find video description')
 920
 921         if not timestamp:
 922             timestamp = self._search_regex(
 923                 r'<time[^>]+datetime="([^"]+)"', webpage,
 924                 'timestamp', default=None)
 925
 926         view_count = int_or_none(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count', default=None))
 927         like_count = int_or_none(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count', default=None))
 928         comment_count = int_or_none(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count', default=None))
 929
 930         formats = []
 931
 932         source_format = self._extract_original_format(
 933             'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
 934         if source_format:
 935             formats.append(source_format)
 936
 937         info_dict_config = self._parse_config(config, video_id)
 938         formats.extend(info_dict_config['formats'])
 939         info_dict['_format_sort_fields'] = info_dict_config['_format_sort_fields']
 940
 941         json_ld = self._search_json_ld(webpage, video_id, default={})
 942
 943         if not cc_license:
 944             cc_license = self._search_regex(
 945                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
 946                 webpage, 'license', default=None, group='license')
 947
 948         info_dict.update({
 949             'formats': formats,
 950             'timestamp': unified_timestamp(timestamp),
 951             'description': video_description,
 952             'webpage_url': url,
 953             'view_count': view_count,
 954             'like_count': like_count,
 955             'comment_count': comment_count,
 956             'license': cc_license,
 957         })
 958
 959         return merge_dicts(info_dict, info_dict_config, json_ld)
 960
 961
 962 class VimeoOndemandIE(VimeoIE):  # XXX: Do not subclass from concrete IE
 963     IE_NAME = 'vimeo:ondemand'
 964     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)'
 965     _TESTS = [{
 966         # ondemand video not available via https://vimeo.com/id
 967         'url': 'https://vimeo.com/ondemand/20704',
 968         'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
 969         'info_dict': {
 970             'id': '105442900',
 971             'ext': 'mp4',
 972             'title': 'המעבדה - במאי יותם פלדמן',
 973             'uploader': 'גם סרטים',
 974             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
 975             'uploader_id': 'gumfilms',
 976             'description': 'md5:aeeba3dbd4d04b0fa98a4fdc9c639998',
 977             'upload_date': '20140906',
 978             'timestamp': 1410032453,
 979             'thumbnail': 'https://i.vimeocdn.com/video/488238335-d7bf151c364cff8d467f1b73784668fe60aae28a54573a35d53a1210ae283bd8-d_1280',
 980             'comment_count': int,
 981             'license': 'https://creativecommons.org/licenses/by-nc-nd/3.0/',
 982             'duration': 53,
 983             'view_count': int,
 984             'like_count': int,
 985         },
 986         'params': {
 987             'format': 'best[protocol=https]',
 988         },
 989         'expected_warnings': ['Unable to download JSON metadata'],
 990     }, {
 991         # requires Referer to be passed along with og:video:url
 992         'url': 'https://vimeo.com/ondemand/36938/126682985',
 993         'info_dict': {
 994             'id': '126584684',
 995             'ext': 'mp4',
 996             'title': 'Rävlock, rätt läte på rätt plats',
 997             'uploader': 'Lindroth & Norin',
 998             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
 999             'uploader_id': 'lindrothnorin',
1000             'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
1001             'upload_date': '20150502',
1002             'timestamp': 1430586422,
1003             'duration': 121,
1004             'comment_count': int,
1005             'view_count': int,
1006             'thumbnail': 'https://i.vimeocdn.com/video/517077723-7066ae1d9a79d3eb361334fb5d58ec13c8f04b52f8dd5eadfbd6fb0bcf11f613-d_1280',
1007             'like_count': int,
1008         },
1009         'params': {
1010             'skip_download': True,
1011         },
1012         'expected_warnings': ['Unable to download JSON metadata'],
1013     }, {
1014         'url': 'https://vimeo.com/ondemand/nazmaalik',
1015         'only_matching': True,
1016     }, {
1017         'url': 'https://vimeo.com/ondemand/141692381',
1018         'only_matching': True,
1019     }, {
1020         'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
1021         'only_matching': True,
1022     }]
1023
1024
1025 class VimeoChannelIE(VimeoBaseInfoExtractor):
1026     IE_NAME = 'vimeo:channel'
1027     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
1028     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
1029     _TITLE = None
1030     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
1031     _TESTS = [{
1032         'url': 'https://vimeo.com/channels/tributes',
1033         'info_dict': {
1034             'id': 'tributes',
1035             'title': 'Vimeo Tributes',
1036         },
1037         'playlist_mincount': 22,
1038     }]
1039     _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
1040
1041     def _page_url(self, base_url, pagenum):
1042         return '%s/videos/page:%d/' % (base_url, pagenum)
1043
1044     def _extract_list_title(self, webpage):
1045         return self._TITLE or self._html_search_regex(
1046             self._TITLE_RE, webpage, 'list title', fatal=False)
1047
1048     def _title_and_entries(self, list_id, base_url):
1049         for pagenum in itertools.count(1):
1050             page_url = self._page_url(base_url, pagenum)
1051             webpage = self._download_webpage(
1052                 page_url, list_id,
1053                 'Downloading page %s' % pagenum)
1054
1055             if pagenum == 1:
1056                 yield self._extract_list_title(webpage)
1057
1058             # Try extracting href first since not all videos are available via
1059             # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
1060             clips = re.findall(
1061                 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
1062             if clips:
1063                 for video_id, video_url, video_title in clips:
1064                     yield self.url_result(
1065                         compat_urlparse.urljoin(base_url, video_url),
1066                         VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
1067             # More relaxed fallback
1068             else:
1069                 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
1070                     yield self.url_result(
1071                         'https://vimeo.com/%s' % video_id,
1072                         VimeoIE.ie_key(), video_id=video_id)
1073
1074             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
1075                 break
1076
1077     def _extract_videos(self, list_id, base_url):
1078         title_and_entries = self._title_and_entries(list_id, base_url)
1079         list_title = next(title_and_entries)
1080         return self.playlist_result(title_and_entries, list_id, list_title)
1081
1082     def _real_extract(self, url):
1083         channel_id = self._match_id(url)
1084         return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
1085
1086
1087 class VimeoUserIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1088     IE_NAME = 'vimeo:user'
1089     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos)?/?(?:$|[?#])'
1090     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
1091     _TESTS = [{
1092         'url': 'https://vimeo.com/nkistudio/videos',
1093         'info_dict': {
1094             'title': 'Nki',
1095             'id': 'nkistudio',
1096         },
1097         'playlist_mincount': 66,
1098     }, {
1099         'url': 'https://vimeo.com/nkistudio/',
1100         'only_matching': True,
1101     }]
1102     _BASE_URL_TEMPL = 'https://vimeo.com/%s'
1103
1104
1105 class VimeoAlbumIE(VimeoBaseInfoExtractor):
1106     IE_NAME = 'vimeo:album'
1107     _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
1108     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
1109     _TESTS = [{
1110         'url': 'https://vimeo.com/album/2632481',
1111         'info_dict': {
1112             'id': '2632481',
1113             'title': 'Staff Favorites: November 2013',
1114         },
1115         'playlist_mincount': 13,
1116     }, {
1117         'note': 'Password-protected album',
1118         'url': 'https://vimeo.com/album/3253534',
1119         'info_dict': {
1120             'title': 'test',
1121             'id': '3253534',
1122         },
1123         'playlist_count': 1,
1124         'params': {
1125             'videopassword': 'youtube-dl',
1126         }
1127     }]
1128     _PAGE_SIZE = 100
1129
1130     def _fetch_page(self, album_id, authorization, hashed_pass, page):
1131         api_page = page + 1
1132         query = {
1133             'fields': 'link,uri',
1134             'page': api_page,
1135             'per_page': self._PAGE_SIZE,
1136         }
1137         if hashed_pass:
1138             query['_hashed_pass'] = hashed_pass
1139         try:
1140             videos = self._download_json(
1141                 'https://api.vimeo.com/albums/%s/videos' % album_id,
1142                 album_id, 'Downloading page %d' % api_page, query=query, headers={
1143                     'Authorization': 'jwt ' + authorization,
1144                 })['data']
1145         except ExtractorError as e:
1146             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
1147                 return
1148         for video in videos:
1149             link = video.get('link')
1150             if not link:
1151                 continue
1152             uri = video.get('uri')
1153             video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
1154             yield self.url_result(link, VimeoIE.ie_key(), video_id)
1155
1156     def _real_extract(self, url):
1157         album_id = self._match_id(url)
1158         viewer = self._download_json(
1159             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
1160         if not viewer:
1161             webpage = self._download_webpage(url, album_id)
1162             viewer = self._parse_json(self._search_regex(
1163                 r'bootstrap_data\s*=\s*({.+?})</script>',
1164                 webpage, 'bootstrap data'), album_id)['viewer']
1165         jwt = viewer['jwt']
1166         album = self._download_json(
1167             'https://api.vimeo.com/albums/' + album_id,
1168             album_id, headers={'Authorization': 'jwt ' + jwt},
1169             query={'fields': 'description,name,privacy'})
1170         hashed_pass = None
1171         if try_get(album, lambda x: x['privacy']['view']) == 'password':
1172             password = self.get_param('videopassword')
1173             if not password:
1174                 raise ExtractorError(
1175                     'This album is protected by a password, use the --video-password option',
1176                     expected=True)
1177             self._set_vimeo_cookie('vuid', viewer['vuid'])
1178             try:
1179                 hashed_pass = self._download_json(
1180                     'https://vimeo.com/showcase/%s/auth' % album_id,
1181                     album_id, 'Verifying the password', data=urlencode_postdata({
1182                         'password': password,
1183                         'token': viewer['xsrft'],
1184                     }), headers={
1185                         'X-Requested-With': 'XMLHttpRequest',
1186                     })['hashed_pass']
1187             except ExtractorError as e:
1188                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
1189                     raise ExtractorError('Wrong password', expected=True)
1190                 raise
1191         entries = OnDemandPagedList(functools.partial(
1192             self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
1193         return self.playlist_result(
1194             entries, album_id, album.get('name'), album.get('description'))
1195
1196
1197 class VimeoGroupsIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1198     IE_NAME = 'vimeo:group'
1199     _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
1200     _TESTS = [{
1201         'url': 'https://vimeo.com/groups/meetup',
1202         'info_dict': {
1203             'id': 'meetup',
1204             'title': 'Vimeo Meetup!',
1205         },
1206         'playlist_mincount': 27,
1207     }]
1208     _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
1209
1210
1211 class VimeoReviewIE(VimeoBaseInfoExtractor):
1212     IE_NAME = 'vimeo:review'
1213     IE_DESC = 'Review pages on vimeo'
1214     _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
1215     _TESTS = [{
1216         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1217         'md5': 'c507a72f780cacc12b2248bb4006d253',
1218         'info_dict': {
1219             'id': '75524534',
1220             'ext': 'mp4',
1221             'title': "DICK HARDWICK 'Comedian'",
1222             'uploader': 'Richard Hardwick',
1223             'uploader_id': 'user21297594',
1224             'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1225             'duration': 304,
1226             'thumbnail': 'https://i.vimeocdn.com/video/450115033-43303819d9ebe24c2630352e18b7056d25197d09b3ae901abdac4c4f1d68de71-d_1280',
1227             'uploader_url': 'https://vimeo.com/user21297594',
1228         },
1229     }, {
1230         'note': 'video player needs Referer',
1231         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1232         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1233         'info_dict': {
1234             'id': '91613211',
1235             'ext': 'mp4',
1236             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1237             'uploader': 'DevWeek Events',
1238             'duration': 2773,
1239             'thumbnail': r're:^https?://.*\.jpg$',
1240             'uploader_id': 'user22258446',
1241         },
1242         'skip': 'video gone',
1243     }, {
1244         'note': 'Password protected',
1245         'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1246         'info_dict': {
1247             'id': '138823582',
1248             'ext': 'mp4',
1249             'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1250             'uploader': 'TMB',
1251             'uploader_id': 'user37284429',
1252         },
1253         'params': {
1254             'videopassword': 'holygrail',
1255         },
1256         'skip': 'video gone',
1257     }]
1258
1259     def _real_extract(self, url):
1260         page_url, video_id = self._match_valid_url(url).groups()
1261         data = self._download_json(
1262             page_url.replace('/review/', '/review/data/'), video_id)
1263         if data.get('isLocked') is True:
1264             video_password = self._get_video_password()
1265             viewer = self._download_json(
1266                 'https://vimeo.com/_rv/viewer', video_id)
1267             webpage = self._verify_video_password(
1268                 'https://vimeo.com/' + video_id, video_id,
1269                 video_password, viewer['xsrft'], viewer['vuid'])
1270             clip_page_config = self._parse_json(self._search_regex(
1271                 r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
1272                 webpage, 'clip page config'), video_id)
1273             config_url = clip_page_config['player']['config_url']
1274             clip_data = clip_page_config.get('clip') or {}
1275         else:
1276             clip_data = data['clipData']
1277             config_url = clip_data['configUrl']
1278         config = self._download_json(config_url, video_id)
1279         info_dict = self._parse_config(config, video_id)
1280         source_format = self._extract_original_format(
1281             page_url + '/action', video_id)
1282         if source_format:
1283             info_dict['formats'].append(source_format)
1284         info_dict['description'] = clean_html(clip_data.get('description'))
1285         return info_dict
1286
1287
1288 class VimeoWatchLaterIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1289     IE_NAME = 'vimeo:watchlater'
1290     IE_DESC = 'Vimeo watch later list, ":vimeowatchlater" keyword (requires authentication)'
1291     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1292     _TITLE = 'Watch Later'
1293     _LOGIN_REQUIRED = True
1294     _TESTS = [{
1295         'url': 'https://vimeo.com/watchlater',
1296         'only_matching': True,
1297     }]
1298
1299     def _page_url(self, base_url, pagenum):
1300         url = '%s/page:%d/' % (base_url, pagenum)
1301         request = sanitized_Request(url)
1302         # Set the header to get a partial html page with the ids,
1303         # the normal page doesn't contain them.
1304         request.add_header('X-Requested-With', 'XMLHttpRequest')
1305         return request
1306
1307     def _real_extract(self, url):
1308         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1309
1310
1311 class VimeoLikesIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1312     _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1313     IE_NAME = 'vimeo:likes'
1314     IE_DESC = 'Vimeo user likes'
1315     _TESTS = [{
1316         'url': 'https://vimeo.com/user755559/likes/',
1317         'playlist_mincount': 293,
1318         'info_dict': {
1319             'id': 'user755559',
1320             'title': 'urza’s Likes',
1321         },
1322     }, {
1323         'url': 'https://vimeo.com/stormlapse/likes',
1324         'only_matching': True,
1325     }]
1326
1327     def _page_url(self, base_url, pagenum):
1328         return '%s/page:%d/' % (base_url, pagenum)
1329
1330     def _real_extract(self, url):
1331         user_id = self._match_id(url)
1332         return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
1333
1334
1335 class VHXEmbedIE(VimeoBaseInfoExtractor):
1336     IE_NAME = 'vhx:embed'
1337     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1338     _EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://embed\.vhx\.tv/videos/\d+[^"]*)"']
1339
1340     @classmethod
1341     def _extract_embed_urls(cls, url, webpage):
1342         for embed_url in super()._extract_embed_urls(url, webpage):
1343             yield cls._smuggle_referrer(embed_url, url)
1344
1345     def _real_extract(self, url):
1346         video_id = self._match_id(url)
1347         url, _, headers = self._unsmuggle_headers(url)
1348         webpage = self._download_webpage(url, video_id, headers=headers)
1349         config_url = self._parse_json(self._search_regex(
1350             r'window\.OTTData\s*=\s*({.+})', webpage,
1351             'ott data'), video_id, js_to_json)['config_url']
1352         config = self._download_json(config_url, video_id)
1353         info = self._parse_config(config, video_id)
1354         info['id'] = video_id
1355         return info
1356
1357
1358 class VimeoProIE(VimeoBaseInfoExtractor):
1359     IE_NAME = 'vimeo:pro'
1360     _VALID_URL = r'https?://(?:www\.)?vimeopro\.com/[^/?#]+/(?P<slug>[^/?#]+)(?:(?:/videos?/(?P<id>[0-9]+)))?'
1361     _TESTS = [{
1362         # Vimeo URL derived from video_id
1363         'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
1364         'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
1365         'note': 'Vimeo Pro video (#1197)',
1366         'info_dict': {
1367             'id': '68093876',
1368             'ext': 'mp4',
1369             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
1370             'uploader_id': 'openstreetmapus',
1371             'uploader': 'OpenStreetMap US',
1372             'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
1373             'description': 'md5:2c362968038d4499f4d79f88458590c1',
1374             'duration': 1595,
1375             'upload_date': '20130610',
1376             'timestamp': 1370893156,
1377             'license': 'by',
1378             'thumbnail': 'https://i.vimeocdn.com/video/440260469-19b0d92fca3bd84066623b53f1eb8aaa3980c6c809e2d67b6b39ab7b4a77a344-d_960',
1379             'view_count': int,
1380             'comment_count': int,
1381             'like_count': int,
1382             'tags': 'count:1',
1383         },
1384         'params': {
1385             'format': 'best[protocol=https]',
1386         },
1387     }, {
1388         # password-protected VimeoPro page with Vimeo player embed
1389         'url': 'https://vimeopro.com/cadfem/simulation-conference-mechanische-systeme-in-perfektion',
1390         'info_dict': {
1391             'id': '764543723',
1392             'ext': 'mp4',
1393             'title': 'Mechanische Systeme in Perfektion: Realität erfassen, Innovation treiben',
1394             'thumbnail': 'https://i.vimeocdn.com/video/1543784598-a1a750494a485e601110136b9fe11e28c2131942452b3a5d30391cb3800ca8fd-d_1280',
1395             'description': 'md5:2a9d195cd1b0f6f79827107dc88c2420',
1396             'uploader': 'CADFEM',
1397             'uploader_id': 'cadfem',
1398             'uploader_url': 'https://vimeo.com/cadfem',
1399             'duration': 12505,
1400             'chapters': 'count:10',
1401         },
1402         'params': {
1403             'videopassword': 'Conference2022',
1404             'skip_download': True,
1405         },
1406     }]
1407
1408     def _real_extract(self, url):
1409         display_id, video_id = self._match_valid_url(url).group('slug', 'id')
1410         if video_id:
1411             display_id = video_id
1412         webpage = self._download_webpage(url, display_id)
1413
1414         password_form = self._search_regex(
1415             r'(?is)<form[^>]+?method=["\']post["\'][^>]*>(.+?password.+?)</form>',
1416             webpage, 'password form', default=None)
1417         if password_form:
1418             try:
1419                 webpage = self._download_webpage(url, display_id, data=urlencode_postdata({
1420                     'password': self._get_video_password(),
1421                     **self._hidden_inputs(password_form),
1422                 }), note='Logging in with video password')
1423             except ExtractorError as e:
1424                 if isinstance(e.cause, urllib.error.HTTPError) and e.cause.code == 418:
1425                     raise ExtractorError('Wrong video password', expected=True)
1426                 raise
1427
1428         description = None
1429         # even if we have video_id, some videos require player URL with portfolio_id query param
1430         # https://github.com/ytdl-org/youtube-dl/issues/20070
1431         vimeo_url = VimeoIE._extract_url(url, webpage)
1432         if vimeo_url:
1433             description = self._html_search_meta('description', webpage, default=None)
1434         elif video_id:
1435             vimeo_url = f'https://vimeo.com/{video_id}'
1436         else:
1437             raise ExtractorError(
1438                 'No Vimeo embed or video ID could be found in VimeoPro page', expected=True)
1439
1440         return self.url_result(vimeo_url, VimeoIE, video_id, url_transparent=True,
1441                                description=description)