yt_dlp/extractor/vimeo.py

   1 import base64
   2 import functools
   3 import re
   4 import itertools
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str, compat_urlparse
   8 from ..networking import HEADRequest, Request
   9 from ..networking.exceptions import HTTPError
  10 from ..utils import (
  11     clean_html,
  12     determine_ext,
  13     ExtractorError,
  14     get_element_by_class,
  15     js_to_json,
  16     int_or_none,
  17     merge_dicts,
  18     OnDemandPagedList,
  19     parse_filesize,
  20     parse_iso8601,
  21     parse_qs,
  22     smuggle_url,
  23     str_or_none,
  24     try_get,
  25     unified_timestamp,
  26     unsmuggle_url,
  27     urlencode_postdata,
  28     urljoin,
  29     urlhandle_detect_ext,
  30 )
  31
  32
  33 class VimeoBaseInfoExtractor(InfoExtractor):
  34     _NETRC_MACHINE = 'vimeo'
  35     _LOGIN_REQUIRED = False
  36     _LOGIN_URL = 'https://vimeo.com/log_in'
  37
  38     @staticmethod
  39     def _smuggle_referrer(url, referrer_url):
  40         return smuggle_url(url, {'referer': referrer_url})
  41
  42     def _unsmuggle_headers(self, url):
  43         """@returns (url, smuggled_data, headers)"""
  44         url, data = unsmuggle_url(url, {})
  45         headers = self.get_param('http_headers').copy()
  46         if 'referer' in data:
  47             headers['Referer'] = data['referer']
  48         return url, data, headers
  49
  50     def _perform_login(self, username, password):
  51         webpage = self._download_webpage(
  52             self._LOGIN_URL, None, 'Downloading login page')
  53         token, vuid = self._extract_xsrft_and_vuid(webpage)
  54         data = {
  55             'action': 'login',
  56             'email': username,
  57             'password': password,
  58             'service': 'vimeo',
  59             'token': token,
  60         }
  61         self._set_vimeo_cookie('vuid', vuid)
  62         try:
  63             self._download_webpage(
  64                 self._LOGIN_URL, None, 'Logging in',
  65                 data=urlencode_postdata(data), headers={
  66                     'Content-Type': 'application/x-www-form-urlencoded',
  67                     'Referer': self._LOGIN_URL,
  68                 })
  69         except ExtractorError as e:
  70             if isinstance(e.cause, HTTPError) and e.cause.status == 418:
  71                 raise ExtractorError(
  72                     'Unable to log in: bad username or password',
  73                     expected=True)
  74             raise ExtractorError('Unable to log in')
  75
  76     def _real_initialize(self):
  77         if self._LOGIN_REQUIRED and not self._get_cookies('https://vimeo.com').get('vuid'):
  78             self._raise_login_required()
  79
  80     def _get_video_password(self):
  81         password = self.get_param('videopassword')
  82         if password is None:
  83             raise ExtractorError(
  84                 'This video is protected by a password, use the --video-password option',
  85                 expected=True)
  86         return password
  87
  88     def _verify_video_password(self, url, video_id, password, token, vuid):
  89         if url.startswith('http://'):
  90             # vimeo only supports https now, but the user can give an http url
  91             url = url.replace('http://', 'https://')
  92         self._set_vimeo_cookie('vuid', vuid)
  93         return self._download_webpage(
  94             url + '/password', video_id, 'Verifying the password',
  95             'Wrong password', data=urlencode_postdata({
  96                 'password': password,
  97                 'token': token,
  98             }), headers={
  99                 'Content-Type': 'application/x-www-form-urlencoded',
 100                 'Referer': url,
 101             })
 102
 103     def _extract_xsrft_and_vuid(self, webpage):
 104         xsrft = self._search_regex(
 105             r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
 106             webpage, 'login token', group='xsrft')
 107         vuid = self._search_regex(
 108             r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
 109             webpage, 'vuid', group='vuid')
 110         return xsrft, vuid
 111
 112     def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
 113         vimeo_config = self._search_regex(
 114             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
 115             webpage, 'vimeo config', *args, **kwargs)
 116         if vimeo_config:
 117             return self._parse_json(vimeo_config, video_id)
 118
 119     def _set_vimeo_cookie(self, name, value):
 120         self._set_cookie('vimeo.com', name, value)
 121
 122     def _parse_config(self, config, video_id):
 123         video_data = config['video']
 124         video_title = video_data.get('title')
 125         live_event = video_data.get('live_event') or {}
 126         is_live = live_event.get('status') == 'started'
 127         request = config.get('request') or {}
 128
 129         formats = []
 130         subtitles = {}
 131
 132         config_files = video_data.get('files') or request.get('files') or {}
 133         for f in (config_files.get('progressive') or []):
 134             video_url = f.get('url')
 135             if not video_url:
 136                 continue
 137             formats.append({
 138                 'url': video_url,
 139                 'format_id': 'http-%s' % f.get('quality'),
 140                 'source_preference': 10,
 141                 'width': int_or_none(f.get('width')),
 142                 'height': int_or_none(f.get('height')),
 143                 'fps': int_or_none(f.get('fps')),
 144                 'tbr': int_or_none(f.get('bitrate')),
 145             })
 146
 147         # TODO: fix handling of 308 status code returned for live archive manifest requests
 148         sep_pattern = r'/sep/video/'
 149         for files_type in ('hls', 'dash'):
 150             for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items():
 151                 manifest_url = cdn_data.get('url')
 152                 if not manifest_url:
 153                     continue
 154                 format_id = '%s-%s' % (files_type, cdn_name)
 155                 sep_manifest_urls = []
 156                 if re.search(sep_pattern, manifest_url):
 157                     for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
 158                         sep_manifest_urls.append((format_id + suffix, re.sub(
 159                             sep_pattern, '/%s/' % repl, manifest_url)))
 160                 else:
 161                     sep_manifest_urls = [(format_id, manifest_url)]
 162                 for f_id, m_url in sep_manifest_urls:
 163                     if files_type == 'hls':
 164                         fmts, subs = self._extract_m3u8_formats_and_subtitles(
 165                             m_url, video_id, 'mp4', live=is_live, m3u8_id=f_id,
 166                             note='Downloading %s m3u8 information' % cdn_name,
 167                             fatal=False)
 168                         formats.extend(fmts)
 169                         self._merge_subtitles(subs, target=subtitles)
 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                         fmts, subs = self._extract_mpd_formats_and_subtitles(
 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(fmts)
 180                         self._merge_subtitles(subs, target=subtitles)
 181
 182         live_archive = live_event.get('archive') or {}
 183         live_archive_source_url = live_archive.get('source_url')
 184         if live_archive_source_url and live_archive.get('status') == 'done':
 185             formats.append({
 186                 'format_id': 'live-archive-source',
 187                 'url': live_archive_source_url,
 188                 'quality': 10,
 189             })
 190
 191         for tt in (request.get('text_tracks') or []):
 192             subtitles.setdefault(tt['lang'], []).append({
 193                 'ext': 'vtt',
 194                 'url': urljoin('https://vimeo.com', tt['url']),
 195             })
 196
 197         thumbnails = []
 198         if not is_live:
 199             for key, thumb in (video_data.get('thumbs') or {}).items():
 200                 thumbnails.append({
 201                     'id': key,
 202                     'width': int_or_none(key),
 203                     'url': thumb,
 204                 })
 205             thumbnail = video_data.get('thumbnail')
 206             if thumbnail:
 207                 thumbnails.append({
 208                     'url': thumbnail,
 209                 })
 210
 211         owner = video_data.get('owner') or {}
 212         video_uploader_url = owner.get('url')
 213
 214         duration = int_or_none(video_data.get('duration'))
 215         chapter_data = try_get(config, lambda x: x['embed']['chapters']) or []
 216         chapters = [{
 217             'title': current_chapter.get('title'),
 218             'start_time': current_chapter.get('timecode'),
 219             'end_time': next_chapter.get('timecode'),
 220         } for current_chapter, next_chapter in zip(chapter_data, chapter_data[1:] + [{'timecode': duration}])]
 221         if chapters and chapters[0]['start_time']:  # Chapters may not start from 0
 222             chapters[:0] = [{'title': '<Untitled>', 'start_time': 0, 'end_time': chapters[0]['start_time']}]
 223
 224         return {
 225             'id': str_or_none(video_data.get('id')) or video_id,
 226             'title': video_title,
 227             'uploader': owner.get('name'),
 228             'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
 229             'uploader_url': video_uploader_url,
 230             'thumbnails': thumbnails,
 231             'duration': duration,
 232             'chapters': chapters or None,
 233             'formats': formats,
 234             'subtitles': subtitles,
 235             'is_live': is_live,
 236             # Note: Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
 237             # at the same time without actual units specified.
 238             '_format_sort_fields': ('quality', 'res', 'fps', 'hdr:12', 'source'),
 239         }
 240
 241     def _extract_original_format(self, url, video_id, unlisted_hash=None):
 242         query = {'action': 'load_download_config'}
 243         if unlisted_hash:
 244             query['unlisted_hash'] = unlisted_hash
 245         download_data = self._download_json(
 246             url, video_id, fatal=False, query=query,
 247             headers={'X-Requested-With': 'XMLHttpRequest'},
 248             expected_status=(403, 404)) or {}
 249         source_file = download_data.get('source_file')
 250         download_url = try_get(source_file, lambda x: x['download_url'])
 251         if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 252             source_name = source_file.get('public_name', 'Original')
 253             if self._is_valid_url(download_url, video_id, '%s video' % source_name):
 254                 ext = (try_get(
 255                     source_file, lambda x: x['extension'],
 256                     compat_str) or determine_ext(
 257                     download_url, None) or 'mp4').lower()
 258                 return {
 259                     'url': download_url,
 260                     'ext': ext,
 261                     'width': int_or_none(source_file.get('width')),
 262                     'height': int_or_none(source_file.get('height')),
 263                     'filesize': parse_filesize(source_file.get('size')),
 264                     'format_id': source_name,
 265                     'quality': 1,
 266                 }
 267
 268         jwt_response = self._download_json(
 269             'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {}
 270         if not jwt_response.get('jwt'):
 271             return
 272         headers = {'Authorization': 'jwt %s' % jwt_response['jwt'], 'Accept': 'application/json'}
 273         original_response = self._download_json(
 274             f'https://api.vimeo.com/videos/{video_id}', video_id,
 275             headers=headers, fatal=False, expected_status=(403, 404)) or {}
 276         for download_data in original_response.get('download') or []:
 277             download_url = download_data.get('link')
 278             if not download_url or download_data.get('quality') != 'source':
 279                 continue
 280             ext = determine_ext(parse_qs(download_url).get('filename', [''])[0].lower(), default_ext=None)
 281             if not ext:
 282                 urlh = self._request_webpage(
 283                     HEADRequest(download_url), video_id, fatal=False, note='Determining source extension')
 284                 ext = urlh and urlhandle_detect_ext(urlh)
 285             return {
 286                 'url': download_url,
 287                 'ext': ext or 'unknown_video',
 288                 'format_id': download_data.get('public_name', 'Original'),
 289                 'width': int_or_none(download_data.get('width')),
 290                 'height': int_or_none(download_data.get('height')),
 291                 'fps': int_or_none(download_data.get('fps')),
 292                 'filesize': int_or_none(download_data.get('size')),
 293                 'quality': 1,
 294             }
 295
 296
 297 class VimeoIE(VimeoBaseInfoExtractor):
 298     """Information extractor for vimeo.com."""
 299
 300     # _VALID_URL matches Vimeo URLs
 301     _VALID_URL = r'''(?x)
 302                      https?://
 303                          (?:
 304                              (?:
 305                                  www|
 306                                  player
 307                              )
 308                              \.
 309                          )?
 310                          vimeo\.com/
 311                          (?:
 312                              (?P<u>user)|
 313                              (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
 314                              (?:.*?/)??
 315                              (?P<q>
 316                                  (?:
 317                                      play_redirect_hls|
 318                                      moogaloop\.swf)\?clip_id=
 319                              )?
 320                              (?:videos?/)?
 321                          )
 322                          (?P<id>[0-9]+)
 323                          (?(u)
 324                              /(?!videos|likes)[^/?#]+/?|
 325                              (?(q)|/(?P<unlisted_hash>[\da-f]{10}))?
 326                          )
 327                          (?:(?(q)[&]|(?(u)|/?)[?]).*?)?(?:[#].*)?$
 328                  '''
 329     IE_NAME = 'vimeo'
 330     _EMBED_REGEX = [
 331         # iframe
 332         r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
 333         # Embedded (swf embed) Vimeo player
 334         r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
 335         # Non-standard embedded Vimeo player
 336         r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
 337     ]
 338     _TESTS = [
 339         {
 340             'url': 'http://vimeo.com/56015672#at=0',
 341             'md5': '8879b6cc097e987f02484baf890129e5',
 342             'info_dict': {
 343                 'id': '56015672',
 344                 'ext': 'mp4',
 345                 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
 346                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
 347                 'timestamp': 1355990239,
 348                 'upload_date': '20121220',
 349                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
 350                 'uploader_id': 'user7108434',
 351                 'uploader': 'Filippo Valsorda',
 352                 'duration': 10,
 353                 'license': 'by-sa',
 354             },
 355             'params': {
 356                 'format': 'best[protocol=https]',
 357             },
 358             'skip': 'No longer available'
 359         },
 360         {
 361             'url': 'http://player.vimeo.com/video/54469442',
 362             'md5': '619b811a4417aa4abe78dc653becf511',
 363             'note': 'Videos that embed the url in the player page',
 364             'info_dict': {
 365                 'id': '54469442',
 366                 'ext': 'mp4',
 367                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 368                 'uploader': 'Business of Software',
 369                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
 370                 'uploader_id': 'businessofsoftware',
 371                 'duration': 3610,
 372                 'description': None,
 373                 'thumbnail': 'https://i.vimeocdn.com/video/376682406-f34043e7b766af6bef2af81366eacd6724f3fc3173179a11a97a1e26587c9529-d_1280',
 374             },
 375             'params': {
 376                 'format': 'best[protocol=https]',
 377             },
 378         },
 379         {
 380             'url': 'http://vimeo.com/68375962',
 381             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 382             'note': 'Video protected with password',
 383             'info_dict': {
 384                 'id': '68375962',
 385                 'ext': 'mp4',
 386                 'title': 'youtube-dl password protected test video',
 387                 'timestamp': 1371200155,
 388                 'upload_date': '20130614',
 389                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 390                 'uploader_id': 'user18948128',
 391                 'uploader': 'Jaime Marquínez Ferrándiz',
 392                 'duration': 10,
 393                 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
 394                 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
 395                 'view_count': int,
 396                 'comment_count': int,
 397                 'like_count': int,
 398             },
 399             'params': {
 400                 'format': 'best[protocol=https]',
 401                 'videopassword': 'youtube-dl',
 402             },
 403         },
 404         {
 405             'url': 'http://vimeo.com/channels/keypeele/75629013',
 406             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 407             'info_dict': {
 408                 'id': '75629013',
 409                 'ext': 'mp4',
 410                 'title': 'Key & Peele: Terrorist Interrogation',
 411                 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
 412                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
 413                 'uploader_id': 'atencio',
 414                 'uploader': 'Peter Atencio',
 415                 'channel_id': 'keypeele',
 416                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
 417                 'timestamp': 1380339469,
 418                 'upload_date': '20130928',
 419                 'duration': 187,
 420                 'thumbnail': 'https://i.vimeocdn.com/video/450239872-a05512d9b1e55d707a7c04365c10980f327b06d966351bc403a5d5d65c95e572-d_1280',
 421                 'view_count': int,
 422                 'comment_count': int,
 423                 'like_count': int,
 424             },
 425             'params': {'format': 'http-1080p'},
 426         },
 427         {
 428             'url': 'http://vimeo.com/76979871',
 429             'note': 'Video with subtitles',
 430             'info_dict': {
 431                 'id': '76979871',
 432                 'ext': 'mov',
 433                 'title': 'The New Vimeo Player (You Know, For Videos)',
 434                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 435                 'timestamp': 1381846109,
 436                 'upload_date': '20131015',
 437                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
 438                 'uploader_id': 'staff',
 439                 'uploader': 'Vimeo Staff',
 440                 'duration': 62,
 441                 'subtitles': {
 442                     'de': [{'ext': 'vtt'}],
 443                     'en': [{'ext': 'vtt'}],
 444                     'es': [{'ext': 'vtt'}],
 445                     'fr': [{'ext': 'vtt'}],
 446                 },
 447             },
 448             'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
 449         },
 450         {
 451             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 452             'url': 'https://player.vimeo.com/video/98044508',
 453             'note': 'The js code contains assignments to the same variable as the config',
 454             'info_dict': {
 455                 'id': '98044508',
 456                 'ext': 'mp4',
 457                 'title': 'Pier Solar OUYA Official Trailer',
 458                 'uploader': 'Tulio Gonçalves',
 459                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
 460                 'uploader_id': 'user28849593',
 461                 'duration': 118,
 462                 'thumbnail': 'https://i.vimeocdn.com/video/478636036-c18440305ef3df9decfb6bf207a61fe39d2d17fa462a96f6f2d93d30492b037d-d_1280',
 463             },
 464         },
 465         {
 466             # contains original format
 467             'url': 'https://vimeo.com/33951933',
 468             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 469             'info_dict': {
 470                 'id': '33951933',
 471                 'ext': 'mp4',
 472                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 473                 'uploader': 'The DMCI',
 474                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
 475                 'uploader_id': 'dmci',
 476                 'timestamp': 1324343742,
 477                 'upload_date': '20111220',
 478                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 479                 'duration': 60,
 480                 'comment_count': int,
 481                 'view_count': int,
 482                 'thumbnail': 'https://i.vimeocdn.com/video/231174622-dd07f015e9221ff529d451e1cc31c982b5d87bfafa48c4189b1da72824ee289a-d_1280',
 483                 'like_count': int,
 484             },
 485         },
 486         {
 487             'note': 'Contains original format not accessible in webpage',
 488             'url': 'https://vimeo.com/393756517',
 489             'md5': 'c464af248b592190a5ffbb5d33f382b0',
 490             'info_dict': {
 491                 'id': '393756517',
 492                 'ext': 'mov',
 493                 'timestamp': 1582642091,
 494                 'uploader_id': 'frameworkla',
 495                 'title': 'Straight To Hell - Sabrina: Netflix',
 496                 'uploader': 'Framework Studio',
 497                 'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
 498                 'upload_date': '20200225',
 499                 'duration': 176,
 500                 'thumbnail': 'https://i.vimeocdn.com/video/859377297-836494a4ef775e9d4edbace83937d9ad34dc846c688c0c419c0e87f7ab06c4b3-d_1280',
 501                 'uploader_url': 'https://vimeo.com/frameworkla',
 502             },
 503         },
 504         {
 505             # only available via https://vimeo.com/channels/tributes/6213729 and
 506             # not via https://vimeo.com/6213729
 507             'url': 'https://vimeo.com/channels/tributes/6213729',
 508             'info_dict': {
 509                 'id': '6213729',
 510                 'ext': 'mp4',
 511                 'title': 'Vimeo Tribute: The Shining',
 512                 'uploader': 'Casey Donahue',
 513                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
 514                 'uploader_id': 'caseydonahue',
 515                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
 516                 'channel_id': 'tributes',
 517                 'timestamp': 1250886430,
 518                 'upload_date': '20090821',
 519                 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
 520                 'duration': 321,
 521                 'comment_count': int,
 522                 'view_count': int,
 523                 'thumbnail': 'https://i.vimeocdn.com/video/22728298-bfc22146f930de7cf497821c7b0b9f168099201ecca39b00b6bd31fcedfca7a6-d_1280',
 524                 'like_count': int,
 525             },
 526             'params': {
 527                 'skip_download': True,
 528             },
 529         },
 530         {
 531             # redirects to ondemand extractor and should be passed through it
 532             # for successful extraction
 533             'url': 'https://vimeo.com/73445910',
 534             'info_dict': {
 535                 'id': '73445910',
 536                 'ext': 'mp4',
 537                 'title': 'The Reluctant Revolutionary',
 538                 'uploader': '10Ft Films',
 539                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
 540                 'uploader_id': 'tenfootfilms',
 541                 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
 542                 'upload_date': '20130830',
 543                 'timestamp': 1377853339,
 544             },
 545             'params': {
 546                 'skip_download': True,
 547             },
 548             'skip': 'this page is no longer available.',
 549         },
 550         {
 551             'url': 'http://player.vimeo.com/video/68375962',
 552             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 553             'info_dict': {
 554                 'id': '68375962',
 555                 'ext': 'mp4',
 556                 'title': 'youtube-dl password protected test video',
 557                 'timestamp': 1371200155,
 558                 'upload_date': '20130614',
 559                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 560                 'uploader_id': 'user18948128',
 561                 'uploader': 'Jaime Marquínez Ferrándiz',
 562                 'duration': 10,
 563                 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
 564                 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
 565                 'view_count': int,
 566                 'comment_count': int,
 567                 'like_count': int,
 568             },
 569             'params': {
 570                 'format': 'best[protocol=https]',
 571                 'videopassword': 'youtube-dl',
 572             },
 573         },
 574         {
 575             'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
 576             'only_matching': True,
 577         },
 578         {
 579             'url': 'https://vimeo.com/109815029',
 580             'note': 'Video not completely processed, "failed" seed status',
 581             'only_matching': True,
 582         },
 583         {
 584             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 585             'only_matching': True,
 586         },
 587         {
 588             'url': 'https://vimeo.com/album/2632481/video/79010983',
 589             'only_matching': True,
 590         },
 591         {
 592             'url': 'https://vimeo.com/showcase/3253534/video/119195465',
 593             'note': 'A video in a password protected album (showcase)',
 594             'info_dict': {
 595                 'id': '119195465',
 596                 'ext': 'mp4',
 597                 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
 598                 'uploader': 'Philipp Hagemeister',
 599                 'uploader_id': 'user20132939',
 600                 'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
 601                 'upload_date': '20150209',
 602                 'timestamp': 1423518307,
 603                 'thumbnail': 'https://i.vimeocdn.com/video/default_1280',
 604                 'duration': 10,
 605                 'like_count': int,
 606                 'uploader_url': 'https://vimeo.com/user20132939',
 607                 'view_count': int,
 608                 'comment_count': int,
 609             },
 610             'params': {
 611                 'format': 'best[protocol=https]',
 612                 'videopassword': 'youtube-dl',
 613             },
 614         },
 615         {
 616             # source file returns 403: Forbidden
 617             'url': 'https://vimeo.com/7809605',
 618             'only_matching': True,
 619         },
 620         {
 621             'note': 'Direct URL with hash',
 622             'url': 'https://vimeo.com/160743502/abd0e13fb4',
 623             'info_dict': {
 624                 'id': '160743502',
 625                 'ext': 'mp4',
 626                 'uploader': 'Julian Tryba',
 627                 'uploader_id': 'aliniamedia',
 628                 'title': 'Harrisville New Hampshire',
 629                 'timestamp': 1459259666,
 630                 'upload_date': '20160329',
 631                 'release_timestamp': 1459259666,
 632                 'license': 'by-nc',
 633                 'duration': 159,
 634                 'comment_count': int,
 635                 'thumbnail': 'https://i.vimeocdn.com/video/562802436-585eeb13b5020c6ac0f171a2234067938098f84737787df05ff0d767f6d54ee9-d_1280',
 636                 'like_count': int,
 637                 'uploader_url': 'https://vimeo.com/aliniamedia',
 638                 'release_date': '20160329',
 639             },
 640             'params': {'skip_download': True},
 641         },
 642         {
 643             'url': 'https://vimeo.com/138909882',
 644             'info_dict': {
 645                 'id': '138909882',
 646                 'ext': 'mp4',
 647                 'title': 'Eastnor Castle 2015 Firework Champions - The Promo!',
 648                 'description': 'md5:5967e090768a831488f6e74b7821b3c1',
 649                 'uploader_id': 'fireworkchampions',
 650                 'uploader': 'Firework Champions',
 651                 'upload_date': '20150910',
 652                 'timestamp': 1441901895,
 653             },
 654             'params': {
 655                 'skip_download': True,
 656                 'format': 'Original',
 657             },
 658         },
 659         {
 660             'url': 'https://vimeo.com/channels/staffpicks/143603739',
 661             'info_dict': {
 662                 'id': '143603739',
 663                 'ext': 'mp4',
 664                 'uploader': 'Karim Huu Do',
 665                 'timestamp': 1445846953,
 666                 'upload_date': '20151026',
 667                 'title': 'The Shoes - Submarine Feat. Blaine Harrison',
 668                 'uploader_id': 'karimhd',
 669                 'description': 'md5:8e2eea76de4504c2e8020a9bcfa1e843',
 670                 'channel_id': 'staffpicks',
 671                 'duration': 336,
 672                 'comment_count': int,
 673                 'view_count': int,
 674                 'thumbnail': 'https://i.vimeocdn.com/video/541243181-b593db36a16db2f0096f655da3f5a4dc46b8766d77b0f440df937ecb0c418347-d_1280',
 675                 'like_count': int,
 676                 'uploader_url': 'https://vimeo.com/karimhd',
 677                 'channel_url': 'https://vimeo.com/channels/staffpicks',
 678             },
 679             'params': {'skip_download': 'm3u8'},
 680         },
 681         {
 682             # requires passing unlisted_hash(a52724358e) to load_download_config request
 683             'url': 'https://vimeo.com/392479337/a52724358e',
 684             'only_matching': True,
 685         },
 686         {
 687             # similar, but all numeric: ID must be 581039021, not 9603038895
 688             # issue #29690
 689             'url': 'https://vimeo.com/581039021/9603038895',
 690             'info_dict': {
 691                 'id': '581039021',
 692                 'ext': 'mp4',
 693                 'timestamp': 1627621014,
 694                 'release_timestamp': 1627621014,
 695                 'duration': 976,
 696                 'comment_count': int,
 697                 'thumbnail': 'https://i.vimeocdn.com/video/1202249320-4ddb2c30398c0dc0ee059172d1bd5ea481ad12f0e0e3ad01d2266f56c744b015-d_1280',
 698                 'like_count': int,
 699                 'uploader_url': 'https://vimeo.com/txwestcapital',
 700                 'release_date': '20210730',
 701                 'uploader': 'Christopher Inks',
 702                 'title': 'Thursday, July 29, 2021 BMA Evening Video Update',
 703                 'uploader_id': 'txwestcapital',
 704                 'upload_date': '20210730',
 705             },
 706             'params': {
 707                 'skip_download': True,
 708             },
 709         },
 710         {
 711             # user playlist alias -> https://vimeo.com/258705797
 712             'url': 'https://vimeo.com/user26785108/newspiritualguide',
 713             'only_matching': True,
 714         },
 715         # https://gettingthingsdone.com/workflowmap/
 716         # vimeo embed with check-password page protected by Referer header
 717     ]
 718
 719     @classmethod
 720     def _extract_embed_urls(cls, url, webpage):
 721         for embed_url in super()._extract_embed_urls(url, webpage):
 722             yield cls._smuggle_referrer(embed_url, url)
 723
 724     @classmethod
 725     def _extract_url(cls, url, webpage):
 726         return next(cls._extract_embed_urls(url, webpage), None)
 727
 728     def _verify_player_video_password(self, url, video_id, headers):
 729         password = self._get_video_password()
 730         data = urlencode_postdata({
 731             'password': base64.b64encode(password.encode()),
 732         })
 733         headers = merge_dicts(headers, {
 734             'Content-Type': 'application/x-www-form-urlencoded',
 735         })
 736         checked = self._download_json(
 737             f'{compat_urlparse.urlsplit(url)._replace(query=None).geturl()}/check-password',
 738             video_id, 'Verifying the password', data=data, headers=headers)
 739         if checked is False:
 740             raise ExtractorError('Wrong video password', expected=True)
 741         return checked
 742
 743     def _extract_from_api(self, video_id, unlisted_hash=None):
 744         token = self._download_json(
 745             'https://vimeo.com/_rv/jwt', video_id, headers={
 746                 'X-Requested-With': 'XMLHttpRequest'
 747             })['token']
 748         api_url = 'https://api.vimeo.com/videos/' + video_id
 749         if unlisted_hash:
 750             api_url += ':' + unlisted_hash
 751         video = self._download_json(
 752             api_url, video_id, headers={
 753                 'Authorization': 'jwt ' + token,
 754                 'Accept': 'application/json',
 755             }, query={
 756                 'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
 757             })
 758         info = self._parse_config(self._download_json(
 759             video['config_url'], video_id), video_id)
 760         get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
 761         info.update({
 762             'description': video.get('description'),
 763             'license': video.get('license'),
 764             'release_timestamp': get_timestamp('release'),
 765             'timestamp': get_timestamp('created'),
 766             'view_count': int_or_none(try_get(video, lambda x: x['stats']['plays'])),
 767         })
 768         connections = try_get(
 769             video, lambda x: x['metadata']['connections'], dict) or {}
 770         for k in ('comment', 'like'):
 771             info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total']))
 772         return info
 773
 774     def _try_album_password(self, url):
 775         album_id = self._search_regex(
 776             r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None)
 777         if not album_id:
 778             return
 779         viewer = self._download_json(
 780             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
 781         if not viewer:
 782             webpage = self._download_webpage(url, album_id)
 783             viewer = self._parse_json(self._search_regex(
 784                 r'bootstrap_data\s*=\s*({.+?})</script>',
 785                 webpage, 'bootstrap data'), album_id)['viewer']
 786         jwt = viewer['jwt']
 787         album = self._download_json(
 788             'https://api.vimeo.com/albums/' + album_id,
 789             album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
 790             query={'fields': 'description,name,privacy'})
 791         if try_get(album, lambda x: x['privacy']['view']) == 'password':
 792             password = self.get_param('videopassword')
 793             if not password:
 794                 raise ExtractorError(
 795                     'This album is protected by a password, use the --video-password option',
 796                     expected=True)
 797             self._set_vimeo_cookie('vuid', viewer['vuid'])
 798             try:
 799                 self._download_json(
 800                     'https://vimeo.com/showcase/%s/auth' % album_id,
 801                     album_id, 'Verifying the password', data=urlencode_postdata({
 802                         'password': password,
 803                         'token': viewer['xsrft'],
 804                     }), headers={
 805                         'X-Requested-With': 'XMLHttpRequest',
 806                     })
 807             except ExtractorError as e:
 808                 if isinstance(e.cause, HTTPError) and e.cause.status == 401:
 809                     raise ExtractorError('Wrong password', expected=True)
 810                 raise
 811
 812     def _real_extract(self, url):
 813         url, data, headers = self._unsmuggle_headers(url)
 814         if 'Referer' not in headers:
 815             headers['Referer'] = url
 816
 817         # Extract ID from URL
 818         mobj = self._match_valid_url(url).groupdict()
 819         video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash')
 820         if unlisted_hash:
 821             return self._extract_from_api(video_id, unlisted_hash)
 822
 823         if any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
 824             url = 'https://vimeo.com/' + video_id
 825
 826         self._try_album_password(url)
 827         try:
 828             # Retrieve video webpage to extract further information
 829             webpage, urlh = self._download_webpage_handle(
 830                 url, video_id, headers=headers)
 831             redirect_url = urlh.url
 832         except ExtractorError as ee:
 833             if isinstance(ee.cause, HTTPError) and ee.cause.status == 403:
 834                 errmsg = ee.cause.response.read()
 835                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 836                     raise ExtractorError(
 837                         'Cannot download embed-only video without embedding '
 838                         'URL. Please call yt-dlp with the URL of the page '
 839                         'that embeds this video.',
 840                         expected=True)
 841             raise
 842
 843         if '://player.vimeo.com/video/' in url:
 844             config = self._search_json(
 845                 r'\b(?:playerC|c)onfig\s*=', webpage, 'info section', video_id)
 846             if config.get('view') == 4:
 847                 config = self._verify_player_video_password(
 848                     redirect_url, video_id, headers)
 849             return self._parse_config(config, video_id)
 850
 851         if re.search(r'<form[^>]+?id="pw_form"', webpage):
 852             video_password = self._get_video_password()
 853             token, vuid = self._extract_xsrft_and_vuid(webpage)
 854             webpage = self._verify_video_password(
 855                 redirect_url, video_id, video_password, token, vuid)
 856
 857         vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
 858         if vimeo_config:
 859             seed_status = vimeo_config.get('seed_status') or {}
 860             if seed_status.get('state') == 'failed':
 861                 raise ExtractorError(
 862                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 863                     expected=True)
 864
 865         cc_license = None
 866         timestamp = None
 867         video_description = None
 868         info_dict = {}
 869         config_url = None
 870
 871         channel_id = self._search_regex(
 872             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
 873         if channel_id:
 874             config_url = self._html_search_regex(
 875                 r'\bdata-config-url="([^"]+)"', webpage, 'config URL', default=None)
 876             video_description = clean_html(get_element_by_class('description', webpage))
 877             info_dict.update({
 878                 'channel_id': channel_id,
 879                 'channel_url': 'https://vimeo.com/channels/' + channel_id,
 880             })
 881         if not config_url:
 882             page_config = self._parse_json(self._search_regex(
 883                 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
 884                 webpage, 'page config', default='{}'), video_id, fatal=False)
 885             if not page_config:
 886                 return self._extract_from_api(video_id)
 887             config_url = page_config['player']['config_url']
 888             cc_license = page_config.get('cc_license')
 889             clip = page_config.get('clip') or {}
 890             timestamp = clip.get('uploaded_on')
 891             video_description = clean_html(
 892                 clip.get('description') or page_config.get('description_html_escaped'))
 893         config = self._download_json(config_url, video_id)
 894         video = config.get('video') or {}
 895         vod = video.get('vod') or {}
 896
 897         def is_rented():
 898             if '>You rented this title.<' in webpage:
 899                 return True
 900             if try_get(config, lambda x: x['user']['purchased']):
 901                 return True
 902             for purchase_option in (vod.get('purchase_options') or []):
 903                 if purchase_option.get('purchased'):
 904                     return True
 905                 label = purchase_option.get('label_string')
 906                 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
 907                     return True
 908             return False
 909
 910         if is_rented() and vod.get('is_trailer'):
 911             feature_id = vod.get('feature_id')
 912             if feature_id and not data.get('force_feature_id', False):
 913                 return self.url_result(smuggle_url(
 914                     'https://player.vimeo.com/player/%s' % feature_id,
 915                     {'force_feature_id': True}), 'Vimeo')
 916
 917         if not video_description:
 918             video_description = self._html_search_regex(
 919                 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 920                 webpage, 'description', default=None)
 921         if not video_description:
 922             video_description = self._html_search_meta(
 923                 ['description', 'og:description', 'twitter:description'],
 924                 webpage, default=None)
 925         if not video_description:
 926             self.report_warning('Cannot find video description')
 927
 928         if not timestamp:
 929             timestamp = self._search_regex(
 930                 r'<time[^>]+datetime="([^"]+)"', webpage,
 931                 'timestamp', default=None)
 932
 933         view_count = int_or_none(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count', default=None))
 934         like_count = int_or_none(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count', default=None))
 935         comment_count = int_or_none(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count', default=None))
 936
 937         formats = []
 938
 939         source_format = self._extract_original_format(
 940             'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
 941         if source_format:
 942             formats.append(source_format)
 943
 944         info_dict_config = self._parse_config(config, video_id)
 945         formats.extend(info_dict_config['formats'])
 946         info_dict['_format_sort_fields'] = info_dict_config['_format_sort_fields']
 947
 948         json_ld = self._search_json_ld(webpage, video_id, default={})
 949
 950         if not cc_license:
 951             cc_license = self._search_regex(
 952                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
 953                 webpage, 'license', default=None, group='license')
 954
 955         info_dict.update({
 956             'formats': formats,
 957             'timestamp': unified_timestamp(timestamp),
 958             'description': video_description,
 959             'webpage_url': url,
 960             'view_count': view_count,
 961             'like_count': like_count,
 962             'comment_count': comment_count,
 963             'license': cc_license,
 964         })
 965
 966         return merge_dicts(info_dict, info_dict_config, json_ld)
 967
 968
 969 class VimeoOndemandIE(VimeoIE):  # XXX: Do not subclass from concrete IE
 970     IE_NAME = 'vimeo:ondemand'
 971     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)'
 972     _TESTS = [{
 973         # ondemand video not available via https://vimeo.com/id
 974         'url': 'https://vimeo.com/ondemand/20704',
 975         'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
 976         'info_dict': {
 977             'id': '105442900',
 978             'ext': 'mp4',
 979             'title': 'המעבדה - במאי יותם פלדמן',
 980             'uploader': 'גם סרטים',
 981             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
 982             'uploader_id': 'gumfilms',
 983             'description': 'md5:aeeba3dbd4d04b0fa98a4fdc9c639998',
 984             'upload_date': '20140906',
 985             'timestamp': 1410032453,
 986             'thumbnail': 'https://i.vimeocdn.com/video/488238335-d7bf151c364cff8d467f1b73784668fe60aae28a54573a35d53a1210ae283bd8-d_1280',
 987             'comment_count': int,
 988             'license': 'https://creativecommons.org/licenses/by-nc-nd/3.0/',
 989             'duration': 53,
 990             'view_count': int,
 991             'like_count': int,
 992         },
 993         'params': {
 994             'format': 'best[protocol=https]',
 995         },
 996         'expected_warnings': ['Unable to download JSON metadata'],
 997     }, {
 998         # requires Referer to be passed along with og:video:url
 999         'url': 'https://vimeo.com/ondemand/36938/126682985',
1000         'info_dict': {
1001             'id': '126584684',
1002             'ext': 'mp4',
1003             'title': 'Rävlock, rätt läte på rätt plats',
1004             'uploader': 'Lindroth & Norin',
1005             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
1006             'uploader_id': 'lindrothnorin',
1007             'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
1008             'upload_date': '20150502',
1009             'timestamp': 1430586422,
1010             'duration': 121,
1011             'comment_count': int,
1012             'view_count': int,
1013             'thumbnail': 'https://i.vimeocdn.com/video/517077723-7066ae1d9a79d3eb361334fb5d58ec13c8f04b52f8dd5eadfbd6fb0bcf11f613-d_1280',
1014             'like_count': int,
1015         },
1016         'params': {
1017             'skip_download': True,
1018         },
1019         'expected_warnings': ['Unable to download JSON metadata'],
1020     }, {
1021         'url': 'https://vimeo.com/ondemand/nazmaalik',
1022         'only_matching': True,
1023     }, {
1024         'url': 'https://vimeo.com/ondemand/141692381',
1025         'only_matching': True,
1026     }, {
1027         'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
1028         'only_matching': True,
1029     }]
1030
1031
1032 class VimeoChannelIE(VimeoBaseInfoExtractor):
1033     IE_NAME = 'vimeo:channel'
1034     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
1035     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
1036     _TITLE = None
1037     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
1038     _TESTS = [{
1039         'url': 'https://vimeo.com/channels/tributes',
1040         'info_dict': {
1041             'id': 'tributes',
1042             'title': 'Vimeo Tributes',
1043         },
1044         'playlist_mincount': 22,
1045     }]
1046     _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
1047
1048     def _page_url(self, base_url, pagenum):
1049         return '%s/videos/page:%d/' % (base_url, pagenum)
1050
1051     def _extract_list_title(self, webpage):
1052         return self._TITLE or self._html_search_regex(
1053             self._TITLE_RE, webpage, 'list title', fatal=False)
1054
1055     def _title_and_entries(self, list_id, base_url):
1056         for pagenum in itertools.count(1):
1057             page_url = self._page_url(base_url, pagenum)
1058             webpage = self._download_webpage(
1059                 page_url, list_id,
1060                 'Downloading page %s' % pagenum)
1061
1062             if pagenum == 1:
1063                 yield self._extract_list_title(webpage)
1064
1065             # Try extracting href first since not all videos are available via
1066             # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
1067             clips = re.findall(
1068                 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
1069             if clips:
1070                 for video_id, video_url, video_title in clips:
1071                     yield self.url_result(
1072                         compat_urlparse.urljoin(base_url, video_url),
1073                         VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
1074             # More relaxed fallback
1075             else:
1076                 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
1077                     yield self.url_result(
1078                         'https://vimeo.com/%s' % video_id,
1079                         VimeoIE.ie_key(), video_id=video_id)
1080
1081             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
1082                 break
1083
1084     def _extract_videos(self, list_id, base_url):
1085         title_and_entries = self._title_and_entries(list_id, base_url)
1086         list_title = next(title_and_entries)
1087         return self.playlist_result(title_and_entries, list_id, list_title)
1088
1089     def _real_extract(self, url):
1090         channel_id = self._match_id(url)
1091         return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
1092
1093
1094 class VimeoUserIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1095     IE_NAME = 'vimeo:user'
1096     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos)?/?(?:$|[?#])'
1097     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
1098     _TESTS = [{
1099         'url': 'https://vimeo.com/nkistudio/videos',
1100         'info_dict': {
1101             'title': 'Nki',
1102             'id': 'nkistudio',
1103         },
1104         'playlist_mincount': 66,
1105     }, {
1106         'url': 'https://vimeo.com/nkistudio/',
1107         'only_matching': True,
1108     }]
1109     _BASE_URL_TEMPL = 'https://vimeo.com/%s'
1110
1111
1112 class VimeoAlbumIE(VimeoBaseInfoExtractor):
1113     IE_NAME = 'vimeo:album'
1114     _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
1115     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
1116     _TESTS = [{
1117         'url': 'https://vimeo.com/album/2632481',
1118         'info_dict': {
1119             'id': '2632481',
1120             'title': 'Staff Favorites: November 2013',
1121         },
1122         'playlist_mincount': 13,
1123     }, {
1124         'note': 'Password-protected album',
1125         'url': 'https://vimeo.com/album/3253534',
1126         'info_dict': {
1127             'title': 'test',
1128             'id': '3253534',
1129         },
1130         'playlist_count': 1,
1131         'params': {
1132             'videopassword': 'youtube-dl',
1133         }
1134     }]
1135     _PAGE_SIZE = 100
1136
1137     def _fetch_page(self, album_id, authorization, hashed_pass, page):
1138         api_page = page + 1
1139         query = {
1140             'fields': 'link,uri',
1141             'page': api_page,
1142             'per_page': self._PAGE_SIZE,
1143         }
1144         if hashed_pass:
1145             query['_hashed_pass'] = hashed_pass
1146         try:
1147             videos = self._download_json(
1148                 'https://api.vimeo.com/albums/%s/videos' % album_id,
1149                 album_id, 'Downloading page %d' % api_page, query=query, headers={
1150                     'Authorization': 'jwt ' + authorization,
1151                     'Accept': 'application/json',
1152                 })['data']
1153         except ExtractorError as e:
1154             if isinstance(e.cause, HTTPError) and e.cause.status == 400:
1155                 return
1156             raise
1157         for video in videos:
1158             link = video.get('link')
1159             if not link:
1160                 continue
1161             uri = video.get('uri')
1162             video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
1163             yield self.url_result(link, VimeoIE.ie_key(), video_id)
1164
1165     def _real_extract(self, url):
1166         album_id = self._match_id(url)
1167         viewer = self._download_json(
1168             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
1169         if not viewer:
1170             webpage = self._download_webpage(url, album_id)
1171             viewer = self._parse_json(self._search_regex(
1172                 r'bootstrap_data\s*=\s*({.+?})</script>',
1173                 webpage, 'bootstrap data'), album_id)['viewer']
1174         jwt = viewer['jwt']
1175         album = self._download_json(
1176             'https://api.vimeo.com/albums/' + album_id,
1177             album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
1178             query={'fields': 'description,name,privacy'})
1179         hashed_pass = None
1180         if try_get(album, lambda x: x['privacy']['view']) == 'password':
1181             password = self.get_param('videopassword')
1182             if not password:
1183                 raise ExtractorError(
1184                     'This album is protected by a password, use the --video-password option',
1185                     expected=True)
1186             self._set_vimeo_cookie('vuid', viewer['vuid'])
1187             try:
1188                 hashed_pass = self._download_json(
1189                     'https://vimeo.com/showcase/%s/auth' % album_id,
1190                     album_id, 'Verifying the password', data=urlencode_postdata({
1191                         'password': password,
1192                         'token': viewer['xsrft'],
1193                     }), headers={
1194                         'X-Requested-With': 'XMLHttpRequest',
1195                     })['hashed_pass']
1196             except ExtractorError as e:
1197                 if isinstance(e.cause, HTTPError) and e.cause.status == 401:
1198                     raise ExtractorError('Wrong password', expected=True)
1199                 raise
1200         entries = OnDemandPagedList(functools.partial(
1201             self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
1202         return self.playlist_result(
1203             entries, album_id, album.get('name'), album.get('description'))
1204
1205
1206 class VimeoGroupsIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1207     IE_NAME = 'vimeo:group'
1208     _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
1209     _TESTS = [{
1210         'url': 'https://vimeo.com/groups/meetup',
1211         'info_dict': {
1212             'id': 'meetup',
1213             'title': 'Vimeo Meetup!',
1214         },
1215         'playlist_mincount': 27,
1216     }]
1217     _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
1218
1219
1220 class VimeoReviewIE(VimeoBaseInfoExtractor):
1221     IE_NAME = 'vimeo:review'
1222     IE_DESC = 'Review pages on vimeo'
1223     _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
1224     _TESTS = [{
1225         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1226         'md5': 'c507a72f780cacc12b2248bb4006d253',
1227         'info_dict': {
1228             'id': '75524534',
1229             'ext': 'mp4',
1230             'title': "DICK HARDWICK 'Comedian'",
1231             'uploader': 'Richard Hardwick',
1232             'uploader_id': 'user21297594',
1233             'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1234             'duration': 304,
1235             'thumbnail': 'https://i.vimeocdn.com/video/450115033-43303819d9ebe24c2630352e18b7056d25197d09b3ae901abdac4c4f1d68de71-d_1280',
1236             'uploader_url': 'https://vimeo.com/user21297594',
1237         },
1238     }, {
1239         'note': 'video player needs Referer',
1240         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1241         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1242         'info_dict': {
1243             'id': '91613211',
1244             'ext': 'mp4',
1245             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1246             'uploader': 'DevWeek Events',
1247             'duration': 2773,
1248             'thumbnail': r're:^https?://.*\.jpg$',
1249             'uploader_id': 'user22258446',
1250         },
1251         'skip': 'video gone',
1252     }, {
1253         'note': 'Password protected',
1254         'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1255         'info_dict': {
1256             'id': '138823582',
1257             'ext': 'mp4',
1258             'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1259             'uploader': 'TMB',
1260             'uploader_id': 'user37284429',
1261         },
1262         'params': {
1263             'videopassword': 'holygrail',
1264         },
1265         'skip': 'video gone',
1266     }]
1267
1268     def _real_extract(self, url):
1269         page_url, video_id = self._match_valid_url(url).groups()
1270         data = self._download_json(
1271             page_url.replace('/review/', '/review/data/'), video_id)
1272         if data.get('isLocked') is True:
1273             video_password = self._get_video_password()
1274             viewer = self._download_json(
1275                 'https://vimeo.com/_rv/viewer', video_id)
1276             webpage = self._verify_video_password(
1277                 'https://vimeo.com/' + video_id, video_id,
1278                 video_password, viewer['xsrft'], viewer['vuid'])
1279             clip_page_config = self._parse_json(self._search_regex(
1280                 r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
1281                 webpage, 'clip page config'), video_id)
1282             config_url = clip_page_config['player']['config_url']
1283             clip_data = clip_page_config.get('clip') or {}
1284         else:
1285             clip_data = data['clipData']
1286             config_url = clip_data['configUrl']
1287         config = self._download_json(config_url, video_id)
1288         info_dict = self._parse_config(config, video_id)
1289         source_format = self._extract_original_format(
1290             page_url + '/action', video_id)
1291         if source_format:
1292             info_dict['formats'].append(source_format)
1293         info_dict['description'] = clean_html(clip_data.get('description'))
1294         return info_dict
1295
1296
1297 class VimeoWatchLaterIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1298     IE_NAME = 'vimeo:watchlater'
1299     IE_DESC = 'Vimeo watch later list, ":vimeowatchlater" keyword (requires authentication)'
1300     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1301     _TITLE = 'Watch Later'
1302     _LOGIN_REQUIRED = True
1303     _TESTS = [{
1304         'url': 'https://vimeo.com/watchlater',
1305         'only_matching': True,
1306     }]
1307
1308     def _page_url(self, base_url, pagenum):
1309         url = '%s/page:%d/' % (base_url, pagenum)
1310         request = Request(url)
1311         # Set the header to get a partial html page with the ids,
1312         # the normal page doesn't contain them.
1313         request.headers['X-Requested-With'] = 'XMLHttpRequest'
1314         return request
1315
1316     def _real_extract(self, url):
1317         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1318
1319
1320 class VimeoLikesIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1321     _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1322     IE_NAME = 'vimeo:likes'
1323     IE_DESC = 'Vimeo user likes'
1324     _TESTS = [{
1325         'url': 'https://vimeo.com/user755559/likes/',
1326         'playlist_mincount': 293,
1327         'info_dict': {
1328             'id': 'user755559',
1329             'title': 'urza’s Likes',
1330         },
1331     }, {
1332         'url': 'https://vimeo.com/stormlapse/likes',
1333         'only_matching': True,
1334     }]
1335
1336     def _page_url(self, base_url, pagenum):
1337         return '%s/page:%d/' % (base_url, pagenum)
1338
1339     def _real_extract(self, url):
1340         user_id = self._match_id(url)
1341         return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
1342
1343
1344 class VHXEmbedIE(VimeoBaseInfoExtractor):
1345     IE_NAME = 'vhx:embed'
1346     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1347     _EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://embed\.vhx\.tv/videos/\d+[^"]*)"']
1348
1349     @classmethod
1350     def _extract_embed_urls(cls, url, webpage):
1351         for embed_url in super()._extract_embed_urls(url, webpage):
1352             yield cls._smuggle_referrer(embed_url, url)
1353
1354     def _real_extract(self, url):
1355         video_id = self._match_id(url)
1356         url, _, headers = self._unsmuggle_headers(url)
1357         webpage = self._download_webpage(url, video_id, headers=headers)
1358         config_url = self._parse_json(self._search_regex(
1359             r'window\.OTTData\s*=\s*({.+})', webpage,
1360             'ott data'), video_id, js_to_json)['config_url']
1361         config = self._download_json(config_url, video_id)
1362         info = self._parse_config(config, video_id)
1363         info['id'] = video_id
1364         return info
1365
1366
1367 class VimeoProIE(VimeoBaseInfoExtractor):
1368     IE_NAME = 'vimeo:pro'
1369     _VALID_URL = r'https?://(?:www\.)?vimeopro\.com/[^/?#]+/(?P<slug>[^/?#]+)(?:(?:/videos?/(?P<id>[0-9]+)))?'
1370     _TESTS = [{
1371         # Vimeo URL derived from video_id
1372         'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
1373         'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
1374         'note': 'Vimeo Pro video (#1197)',
1375         'info_dict': {
1376             'id': '68093876',
1377             'ext': 'mp4',
1378             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
1379             'uploader_id': 'openstreetmapus',
1380             'uploader': 'OpenStreetMap US',
1381             'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
1382             'description': 'md5:2c362968038d4499f4d79f88458590c1',
1383             'duration': 1595,
1384             'upload_date': '20130610',
1385             'timestamp': 1370893156,
1386             'license': 'by',
1387             'thumbnail': 'https://i.vimeocdn.com/video/440260469-19b0d92fca3bd84066623b53f1eb8aaa3980c6c809e2d67b6b39ab7b4a77a344-d_960',
1388             'view_count': int,
1389             'comment_count': int,
1390             'like_count': int,
1391             'tags': 'count:1',
1392         },
1393         'params': {
1394             'format': 'best[protocol=https]',
1395         },
1396     }, {
1397         # password-protected VimeoPro page with Vimeo player embed
1398         'url': 'https://vimeopro.com/cadfem/simulation-conference-mechanische-systeme-in-perfektion',
1399         'info_dict': {
1400             'id': '764543723',
1401             'ext': 'mp4',
1402             'title': 'Mechanische Systeme in Perfektion: Realität erfassen, Innovation treiben',
1403             'thumbnail': 'https://i.vimeocdn.com/video/1543784598-a1a750494a485e601110136b9fe11e28c2131942452b3a5d30391cb3800ca8fd-d_1280',
1404             'description': 'md5:2a9d195cd1b0f6f79827107dc88c2420',
1405             'uploader': 'CADFEM',
1406             'uploader_id': 'cadfem',
1407             'uploader_url': 'https://vimeo.com/cadfem',
1408             'duration': 12505,
1409             'chapters': 'count:10',
1410         },
1411         'params': {
1412             'videopassword': 'Conference2022',
1413             'skip_download': True,
1414         },
1415     }]
1416
1417     def _real_extract(self, url):
1418         display_id, video_id = self._match_valid_url(url).group('slug', 'id')
1419         if video_id:
1420             display_id = video_id
1421         webpage = self._download_webpage(url, display_id)
1422
1423         password_form = self._search_regex(
1424             r'(?is)<form[^>]+?method=["\']post["\'][^>]*>(.+?password.+?)</form>',
1425             webpage, 'password form', default=None)
1426         if password_form:
1427             try:
1428                 webpage = self._download_webpage(url, display_id, data=urlencode_postdata({
1429                     'password': self._get_video_password(),
1430                     **self._hidden_inputs(password_form),
1431                 }), note='Logging in with video password')
1432             except ExtractorError as e:
1433                 if isinstance(e.cause, HTTPError) and e.cause.status == 418:
1434                     raise ExtractorError('Wrong video password', expected=True)
1435                 raise
1436
1437         description = None
1438         # even if we have video_id, some videos require player URL with portfolio_id query param
1439         # https://github.com/ytdl-org/youtube-dl/issues/20070
1440         vimeo_url = VimeoIE._extract_url(url, webpage)
1441         if vimeo_url:
1442             description = self._html_search_meta('description', webpage, default=None)
1443         elif video_id:
1444             vimeo_url = f'https://vimeo.com/{video_id}'
1445         else:
1446             raise ExtractorError(
1447                 'No Vimeo embed or video ID could be found in VimeoPro page', expected=True)
1448
1449         return self.url_result(vimeo_url, VimeoIE, video_id, url_transparent=True,
1450                                description=description)