yt_dlp/extractor/vimeo.py

   1 import base64
   2 import functools
   3 import itertools
   4 import json
   5 import re
   6 import urllib.parse
   7
   8 from .common import InfoExtractor
   9 from ..networking import HEADRequest, Request
  10 from ..networking.exceptions import HTTPError
  11 from ..utils import (
  12     ExtractorError,
  13     OnDemandPagedList,
  14     clean_html,
  15     determine_ext,
  16     get_element_by_class,
  17     int_or_none,
  18     join_nonempty,
  19     js_to_json,
  20     merge_dicts,
  21     parse_filesize,
  22     parse_iso8601,
  23     parse_qs,
  24     qualities,
  25     smuggle_url,
  26     str_or_none,
  27     traverse_obj,
  28     try_get,
  29     unified_timestamp,
  30     unsmuggle_url,
  31     urlencode_postdata,
  32     urlhandle_detect_ext,
  33     urljoin,
  34 )
  35
  36
  37 class VimeoBaseInfoExtractor(InfoExtractor):
  38     _NETRC_MACHINE = 'vimeo'
  39     _LOGIN_REQUIRED = False
  40     _LOGIN_URL = 'https://vimeo.com/log_in'
  41
  42     @staticmethod
  43     def _smuggle_referrer(url, referrer_url):
  44         return smuggle_url(url, {'referer': referrer_url})
  45
  46     def _unsmuggle_headers(self, url):
  47         """@returns (url, smuggled_data, headers)"""
  48         url, data = unsmuggle_url(url, {})
  49         headers = self.get_param('http_headers').copy()
  50         if 'referer' in data:
  51             headers['Referer'] = data['referer']
  52         return url, data, headers
  53
  54     def _perform_login(self, username, password):
  55         viewer = self._download_json('https://vimeo.com/_next/viewer', None, 'Downloading login token')
  56         data = {
  57             'action': 'login',
  58             'email': username,
  59             'password': password,
  60             'service': 'vimeo',
  61             'token': viewer['xsrft'],
  62         }
  63         self._set_vimeo_cookie('vuid', viewer['vuid'])
  64         try:
  65             self._download_webpage(
  66                 self._LOGIN_URL, None, 'Logging in',
  67                 data=urlencode_postdata(data), headers={
  68                     'Content-Type': 'application/x-www-form-urlencoded',
  69                     'Referer': self._LOGIN_URL,
  70                 })
  71         except ExtractorError as e:
  72             if isinstance(e.cause, HTTPError) and e.cause.status == 418:
  73                 raise ExtractorError(
  74                     'Unable to log in: bad username or password',
  75                     expected=True)
  76             raise ExtractorError('Unable to log in')
  77
  78     def _real_initialize(self):
  79         if self._LOGIN_REQUIRED and not self._get_cookies('https://vimeo.com').get('vuid'):
  80             self._raise_login_required()
  81
  82     def _get_video_password(self):
  83         password = self.get_param('videopassword')
  84         if password is None:
  85             raise ExtractorError(
  86                 'This video is protected by a password, use the --video-password option',
  87                 expected=True)
  88         return password
  89
  90     def _verify_video_password(self, video_id, password, token):
  91         url = f'https://vimeo.com/{video_id}'
  92         try:
  93             return self._download_webpage(
  94                 f'{url}/password', video_id,
  95                 'Submitting video password', data=json.dumps({
  96                     'password': password,
  97                     'token': token,
  98                 }, separators=(',', ':')).encode(), headers={
  99                     'Accept': '*/*',
 100                     'Content-Type': 'application/json',
 101                     'Referer': url,
 102                 }, impersonate=True)
 103         except ExtractorError as error:
 104             if isinstance(error.cause, HTTPError) and error.cause.status == 418:
 105                 raise ExtractorError('Wrong password', expected=True)
 106             raise
 107
 108     def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
 109         vimeo_config = self._search_regex(
 110             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
 111             webpage, 'vimeo config', *args, **kwargs)
 112         if vimeo_config:
 113             return self._parse_json(vimeo_config, video_id)
 114
 115     def _set_vimeo_cookie(self, name, value):
 116         self._set_cookie('vimeo.com', name, value)
 117
 118     def _parse_config(self, config, video_id):
 119         video_data = config['video']
 120         video_title = video_data.get('title')
 121         live_event = video_data.get('live_event') or {}
 122         live_status = {
 123             'pending': 'is_upcoming',
 124             'active': 'is_upcoming',
 125             'started': 'is_live',
 126             'ended': 'post_live',
 127         }.get(live_event.get('status'))
 128         is_live = live_status == 'is_live'
 129         request = config.get('request') or {}
 130
 131         formats = []
 132         subtitles = {}
 133
 134         config_files = video_data.get('files') or request.get('files') or {}
 135         for f in (config_files.get('progressive') or []):
 136             video_url = f.get('url')
 137             if not video_url:
 138                 continue
 139             formats.append({
 140                 'url': video_url,
 141                 'format_id': 'http-{}'.format(f.get('quality')),
 142                 'source_preference': 10,
 143                 'width': int_or_none(f.get('width')),
 144                 'height': int_or_none(f.get('height')),
 145                 'fps': int_or_none(f.get('fps')),
 146                 'tbr': int_or_none(f.get('bitrate')),
 147             })
 148
 149         # TODO: fix handling of 308 status code returned for live archive manifest requests
 150         QUALITIES = ('low', 'medium', 'high')
 151         quality = qualities(QUALITIES)
 152         sep_pattern = r'/sep/video/'
 153         for files_type in ('hls', 'dash'):
 154             for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items():
 155                 manifest_url = cdn_data.get('url')
 156                 if not manifest_url:
 157                     continue
 158                 format_id = f'{files_type}-{cdn_name}'
 159                 sep_manifest_urls = []
 160                 if re.search(sep_pattern, manifest_url):
 161                     for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
 162                         sep_manifest_urls.append((format_id + suffix, re.sub(
 163                             sep_pattern, f'/{repl}/', manifest_url)))
 164                 else:
 165                     sep_manifest_urls = [(format_id, manifest_url)]
 166                 for f_id, m_url in sep_manifest_urls:
 167                     if files_type == 'hls':
 168                         fmts, subs = self._extract_m3u8_formats_and_subtitles(
 169                             m_url, video_id, 'mp4', live=is_live, m3u8_id=f_id,
 170                             note=f'Downloading {cdn_name} m3u8 information',
 171                             fatal=False)
 172                         # m3u8 doesn't give audio bitrates; need to prioritize based on GROUP-ID
 173                         # See: https://github.com/yt-dlp/yt-dlp/issues/10854
 174                         for f in fmts:
 175                             if mobj := re.search(rf'audio-({"|".join(QUALITIES)})', f['format_id']):
 176                                 f['quality'] = quality(mobj.group(1))
 177                         formats.extend(fmts)
 178                         self._merge_subtitles(subs, target=subtitles)
 179                     elif files_type == 'dash':
 180                         if 'json=1' in m_url:
 181                             real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
 182                             if real_m_url:
 183                                 m_url = real_m_url
 184                         fmts, subs = self._extract_mpd_formats_and_subtitles(
 185                             m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
 186                             f'Downloading {cdn_name} MPD information',
 187                             fatal=False)
 188                         formats.extend(fmts)
 189                         self._merge_subtitles(subs, target=subtitles)
 190
 191         live_archive = live_event.get('archive') or {}
 192         live_archive_source_url = live_archive.get('source_url')
 193         if live_archive_source_url and live_archive.get('status') == 'done':
 194             formats.append({
 195                 'format_id': 'live-archive-source',
 196                 'url': live_archive_source_url,
 197                 'quality': 10,
 198             })
 199
 200         for tt in (request.get('text_tracks') or []):
 201             subtitles.setdefault(tt['lang'], []).append({
 202                 'ext': 'vtt',
 203                 'url': urljoin('https://vimeo.com', tt['url']),
 204             })
 205
 206         thumbnails = []
 207         if not is_live:
 208             for key, thumb in (video_data.get('thumbs') or {}).items():
 209                 thumbnails.append({
 210                     'id': key,
 211                     'width': int_or_none(key),
 212                     'url': thumb,
 213                 })
 214             thumbnail = video_data.get('thumbnail')
 215             if thumbnail:
 216                 thumbnails.append({
 217                     'url': thumbnail,
 218                 })
 219
 220         owner = video_data.get('owner') or {}
 221         video_uploader_url = owner.get('url')
 222
 223         return {
 224             'id': str_or_none(video_data.get('id')) or video_id,
 225             'title': video_title,
 226             'uploader': owner.get('name'),
 227             'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
 228             'uploader_url': video_uploader_url,
 229             'thumbnails': thumbnails,
 230             'duration': int_or_none(video_data.get('duration')),
 231             'chapters': sorted(traverse_obj(config, (
 232                 'embed', 'chapters', lambda _, v: int(v['timecode']) is not None, {
 233                     'title': ('title', {str}),
 234                     'start_time': ('timecode', {int_or_none}),
 235                 })), key=lambda c: c['start_time']) or None,
 236             'formats': formats,
 237             'subtitles': subtitles,
 238             'live_status': live_status,
 239             'release_timestamp': traverse_obj(live_event, ('ingest', 'scheduled_start_time', {parse_iso8601})),
 240             # Note: Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
 241             # at the same time without actual units specified.
 242             '_format_sort_fields': ('quality', 'res', 'fps', 'hdr:12', 'source'),
 243         }
 244
 245     def _call_videos_api(self, video_id, jwt_token, unlisted_hash=None, **kwargs):
 246         return self._download_json(
 247             join_nonempty(f'https://api.vimeo.com/videos/{video_id}', unlisted_hash, delim=':'),
 248             video_id, 'Downloading API JSON', headers={
 249                 'Authorization': f'jwt {jwt_token}',
 250                 'Accept': 'application/json',
 251             }, query={
 252                 'fields': ','.join((
 253                     'config_url', 'created_time', 'description', 'download', 'license',
 254                     'metadata.connections.comments.total', 'metadata.connections.likes.total',
 255                     'release_time', 'stats.plays')),
 256             }, **kwargs)
 257
 258     def _extract_original_format(self, url, video_id, unlisted_hash=None, jwt=None, api_data=None):
 259         # Original/source formats are only available when logged in
 260         if not self._get_cookies('https://vimeo.com/').get('vimeo'):
 261             return
 262
 263         query = {'action': 'load_download_config'}
 264         if unlisted_hash:
 265             query['unlisted_hash'] = unlisted_hash
 266         download_data = self._download_json(
 267             url, video_id, 'Loading download config JSON', fatal=False,
 268             query=query, headers={'X-Requested-With': 'XMLHttpRequest'},
 269             expected_status=(403, 404)) or {}
 270         source_file = download_data.get('source_file')
 271         download_url = try_get(source_file, lambda x: x['download_url'])
 272         if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 273             source_name = source_file.get('public_name', 'Original')
 274             if self._is_valid_url(download_url, video_id, f'{source_name} video'):
 275                 ext = (try_get(
 276                     source_file, lambda x: x['extension'],
 277                     str) or determine_ext(
 278                     download_url, None) or 'mp4').lower()
 279                 return {
 280                     'url': download_url,
 281                     'ext': ext,
 282                     'width': int_or_none(source_file.get('width')),
 283                     'height': int_or_none(source_file.get('height')),
 284                     'filesize': parse_filesize(source_file.get('size')),
 285                     'format_id': source_name,
 286                     'quality': 1,
 287                 }
 288
 289         jwt = jwt or traverse_obj(self._download_json(
 290             'https://vimeo.com/_rv/viewer', video_id, 'Downloading jwt token', fatal=False), ('jwt', {str}))
 291         if not jwt:
 292             return
 293         original_response = api_data or self._call_videos_api(
 294             video_id, jwt, unlisted_hash, fatal=False, expected_status=(403, 404))
 295         for download_data in traverse_obj(original_response, ('download', ..., {dict})):
 296             download_url = download_data.get('link')
 297             if not download_url or download_data.get('quality') != 'source':
 298                 continue
 299             ext = determine_ext(parse_qs(download_url).get('filename', [''])[0].lower(), default_ext=None)
 300             if not ext:
 301                 urlh = self._request_webpage(
 302                     HEADRequest(download_url), video_id, fatal=False, note='Determining source extension')
 303                 ext = urlh and urlhandle_detect_ext(urlh)
 304             return {
 305                 'url': download_url,
 306                 'ext': ext or 'unknown_video',
 307                 'format_id': download_data.get('public_name', 'Original'),
 308                 'width': int_or_none(download_data.get('width')),
 309                 'height': int_or_none(download_data.get('height')),
 310                 'fps': int_or_none(download_data.get('fps')),
 311                 'filesize': int_or_none(download_data.get('size')),
 312                 'quality': 1,
 313             }
 314
 315
 316 class VimeoIE(VimeoBaseInfoExtractor):
 317     """Information extractor for vimeo.com."""
 318
 319     # _VALID_URL matches Vimeo URLs
 320     _VALID_URL = r'''(?x)
 321                      https?://
 322                          (?:
 323                              (?:
 324                                  www|
 325                                  player
 326                              )
 327                              \.
 328                          )?
 329                          vimeo\.com/
 330                          (?:
 331                              (?P<u>user)|
 332                              (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
 333                              (?:.*?/)??
 334                              (?P<q>
 335                                  (?:
 336                                      play_redirect_hls|
 337                                      moogaloop\.swf)\?clip_id=
 338                              )?
 339                              (?:videos?/)?
 340                          )
 341                          (?P<id>[0-9]+)
 342                          (?(u)
 343                              /(?!videos|likes)[^/?#]+/?|
 344                              (?(q)|/(?P<unlisted_hash>[\da-f]{10}))?
 345                          )
 346                          (?:(?(q)[&]|(?(u)|/?)[?]).*?)?(?:[#].*)?$
 347                  '''
 348     IE_NAME = 'vimeo'
 349     _EMBED_REGEX = [
 350         # iframe
 351         r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
 352         # Embedded (swf embed) Vimeo player
 353         r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
 354         # Non-standard embedded Vimeo player
 355         r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
 356     ]
 357     _TESTS = [
 358         {
 359             'url': 'http://vimeo.com/56015672#at=0',
 360             'md5': '8879b6cc097e987f02484baf890129e5',
 361             'info_dict': {
 362                 'id': '56015672',
 363                 'ext': 'mp4',
 364                 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
 365                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
 366                 'timestamp': 1355990239,
 367                 'upload_date': '20121220',
 368                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
 369                 'uploader_id': 'user7108434',
 370                 'uploader': 'Filippo Valsorda',
 371                 'duration': 10,
 372                 'license': 'by-sa',
 373             },
 374             'params': {
 375                 'format': 'best[protocol=https]',
 376             },
 377             'skip': 'No longer available',
 378         },
 379         {
 380             'url': 'https://player.vimeo.com/video/54469442',
 381             'md5': '619b811a4417aa4abe78dc653becf511',
 382             'note': 'Videos that embed the url in the player page',
 383             'info_dict': {
 384                 'id': '54469442',
 385                 'ext': 'mp4',
 386                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 387                 'uploader': 'Business of Software',
 388                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
 389                 'uploader_id': 'businessofsoftware',
 390                 'duration': 3610,
 391                 'thumbnail': 'https://i.vimeocdn.com/video/376682406-f34043e7b766af6bef2af81366eacd6724f3fc3173179a11a97a1e26587c9529-d_1280',
 392             },
 393             'params': {
 394                 'format': 'best[protocol=https]',
 395             },
 396             'expected_warnings': ['Failed to parse XML: not well-formed'],
 397         },
 398         {
 399             'url': 'http://vimeo.com/68375962',
 400             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 401             'note': 'Video protected with password',
 402             'info_dict': {
 403                 'id': '68375962',
 404                 'ext': 'mp4',
 405                 'title': 'youtube-dl password protected test video',
 406                 'timestamp': 1371214555,
 407                 'upload_date': '20130614',
 408                 'release_timestamp': 1371214555,
 409                 'release_date': '20130614',
 410                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 411                 'uploader_id': 'user18948128',
 412                 'uploader': 'Jaime Marquínez Ferrándiz',
 413                 'duration': 10,
 414                 'comment_count': int,
 415                 'like_count': int,
 416                 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
 417             },
 418             'params': {
 419                 'format': 'best[protocol=https]',
 420                 'videopassword': 'youtube-dl',
 421             },
 422             'expected_warnings': ['Failed to parse XML: not well-formed'],
 423         },
 424         {
 425             'url': 'http://vimeo.com/channels/keypeele/75629013',
 426             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 427             'info_dict': {
 428                 'id': '75629013',
 429                 'ext': 'mp4',
 430                 'title': 'Key & Peele: Terrorist Interrogation',
 431                 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
 432                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
 433                 'uploader_id': 'atencio',
 434                 'uploader': 'Peter Atencio',
 435                 'channel_id': 'keypeele',
 436                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
 437                 'timestamp': 1380339469,
 438                 'upload_date': '20130928',
 439                 'duration': 187,
 440                 'thumbnail': 'https://i.vimeocdn.com/video/450239872-a05512d9b1e55d707a7c04365c10980f327b06d966351bc403a5d5d65c95e572-d_1280',
 441                 'view_count': int,
 442                 'comment_count': int,
 443                 'like_count': int,
 444             },
 445             'params': {'format': 'http-1080p'},
 446             'expected_warnings': ['Failed to parse XML: not well-formed'],
 447         },
 448         {
 449             'url': 'http://vimeo.com/76979871',
 450             'note': 'Video with subtitles',
 451             'info_dict': {
 452                 'id': '76979871',
 453                 'ext': 'mp4',
 454                 'title': 'The New Vimeo Player (You Know, For Videos)',
 455                 'description': str,  # FIXME: Dynamic SEO spam description
 456                 'timestamp': 1381860509,
 457                 'upload_date': '20131015',
 458                 'release_timestamp': 1381860509,
 459                 'release_date': '20131015',
 460                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
 461                 'uploader_id': 'staff',
 462                 'uploader': 'Vimeo',
 463                 'duration': 62,
 464                 'comment_count': int,
 465                 'like_count': int,
 466                 'thumbnail': 'https://i.vimeocdn.com/video/452001751-8216e0571c251a09d7a8387550942d89f7f86f6398f8ed886e639b0dd50d3c90-d_1280',
 467                 'subtitles': {
 468                     'de': 'count:3',
 469                     'en': 'count:3',
 470                     'es': 'count:3',
 471                     'fr': 'count:3',
 472                 },
 473             },
 474             'expected_warnings': [
 475                 'Ignoring subtitle tracks found in the HLS manifest',
 476                 'Failed to parse XML: not well-formed',
 477             ],
 478         },
 479         {
 480             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 481             'url': 'https://player.vimeo.com/video/98044508',
 482             'note': 'The js code contains assignments to the same variable as the config',
 483             'info_dict': {
 484                 'id': '98044508',
 485                 'ext': 'mp4',
 486                 'title': 'Pier Solar OUYA Official Trailer',
 487                 'uploader': 'Tulio Gonçalves',
 488                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
 489                 'uploader_id': 'user28849593',
 490                 'duration': 118,
 491                 'thumbnail': 'https://i.vimeocdn.com/video/478636036-c18440305ef3df9decfb6bf207a61fe39d2d17fa462a96f6f2d93d30492b037d-d_1280',
 492             },
 493             'expected_warnings': ['Failed to parse XML: not well-formed'],
 494         },
 495         {
 496             # contains Original format
 497             'url': 'https://vimeo.com/33951933',
 498             # 'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 499             'info_dict': {
 500                 'id': '33951933',
 501                 'ext': 'mp4',
 502                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 503                 'uploader': 'The DMCI',
 504                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
 505                 'uploader_id': 'dmci',
 506                 'timestamp': 1324343742,
 507                 'upload_date': '20111220',
 508                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 509                 'duration': 60,
 510                 'comment_count': int,
 511                 'view_count': int,
 512                 'thumbnail': 'https://i.vimeocdn.com/video/231174622-dd07f015e9221ff529d451e1cc31c982b5d87bfafa48c4189b1da72824ee289a-d_1280',
 513                 'like_count': int,
 514                 'tags': 'count:11',
 515             },
 516             # 'params': {'format': 'Original'},
 517             'expected_warnings': ['Failed to parse XML: not well-formed'],
 518         },
 519         {
 520             'note': 'Contains source format not accessible in webpage',
 521             'url': 'https://vimeo.com/393756517',
 522             # 'md5': 'c464af248b592190a5ffbb5d33f382b0',
 523             'info_dict': {
 524                 'id': '393756517',
 525                 # 'ext': 'mov',
 526                 'ext': 'mp4',
 527                 'timestamp': 1582642091,
 528                 'uploader_id': 'frameworkla',
 529                 'title': 'Straight To Hell - Sabrina: Netflix',
 530                 'uploader': 'Framework Studio',
 531                 'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
 532                 'upload_date': '20200225',
 533                 'duration': 176,
 534                 'thumbnail': 'https://i.vimeocdn.com/video/859377297-836494a4ef775e9d4edbace83937d9ad34dc846c688c0c419c0e87f7ab06c4b3-d_1280',
 535                 'uploader_url': 'https://vimeo.com/frameworkla',
 536             },
 537             # 'params': {'format': 'source'},
 538             'expected_warnings': ['Failed to parse XML: not well-formed'],
 539         },
 540         {
 541             # only available via https://vimeo.com/channels/tributes/6213729 and
 542             # not via https://vimeo.com/6213729
 543             'url': 'https://vimeo.com/channels/tributes/6213729',
 544             'info_dict': {
 545                 'id': '6213729',
 546                 'ext': 'mp4',
 547                 'title': 'Vimeo Tribute: The Shining',
 548                 'uploader': 'Casey Donahue',
 549                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
 550                 'uploader_id': 'caseydonahue',
 551                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
 552                 'channel_id': 'tributes',
 553                 'timestamp': 1250886430,
 554                 'upload_date': '20090821',
 555                 'description': str,  # FIXME: Dynamic SEO spam description
 556                 'duration': 321,
 557                 'comment_count': int,
 558                 'view_count': int,
 559                 'thumbnail': 'https://i.vimeocdn.com/video/22728298-bfc22146f930de7cf497821c7b0b9f168099201ecca39b00b6bd31fcedfca7a6-d_1280',
 560                 'like_count': int,
 561                 'tags': ['[the shining', 'vimeohq', 'cv', 'vimeo tribute]'],
 562             },
 563             'params': {
 564                 'skip_download': True,
 565             },
 566             'expected_warnings': ['Failed to parse XML: not well-formed'],
 567         },
 568         {
 569             # redirects to ondemand extractor and should be passed through it
 570             # for successful extraction
 571             'url': 'https://vimeo.com/73445910',
 572             'info_dict': {
 573                 'id': '73445910',
 574                 'ext': 'mp4',
 575                 'title': 'The Reluctant Revolutionary',
 576                 'uploader': '10Ft Films',
 577                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
 578                 'uploader_id': 'tenfootfilms',
 579                 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
 580                 'upload_date': '20130830',
 581                 'timestamp': 1377853339,
 582             },
 583             'params': {
 584                 'skip_download': True,
 585             },
 586             'skip': 'this page is no longer available.',
 587         },
 588         {
 589             'url': 'https://player.vimeo.com/video/68375962',
 590             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 591             'info_dict': {
 592                 'id': '68375962',
 593                 'ext': 'mp4',
 594                 'title': 'youtube-dl password protected test video',
 595                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 596                 'uploader_id': 'user18948128',
 597                 'uploader': 'Jaime Marquínez Ferrándiz',
 598                 'duration': 10,
 599                 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
 600             },
 601             'params': {
 602                 'format': 'best[protocol=https]',
 603                 'videopassword': 'youtube-dl',
 604             },
 605             'expected_warnings': ['Failed to parse XML: not well-formed'],
 606         },
 607         {
 608             'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
 609             'only_matching': True,
 610         },
 611         {
 612             'url': 'https://vimeo.com/109815029',
 613             'note': 'Video not completely processed, "failed" seed status',
 614             'only_matching': True,
 615         },
 616         {
 617             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 618             'only_matching': True,
 619         },
 620         {
 621             'url': 'https://vimeo.com/album/2632481/video/79010983',
 622             'only_matching': True,
 623         },
 624         {
 625             'url': 'https://vimeo.com/showcase/3253534/video/119195465',
 626             'note': 'A video in a password protected album (showcase)',
 627             'info_dict': {
 628                 'id': '119195465',
 629                 'ext': 'mp4',
 630                 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
 631                 'uploader': 'Philipp Hagemeister',
 632                 'uploader_id': 'user20132939',
 633                 'description': str,  # FIXME: Dynamic SEO spam description
 634                 'upload_date': '20150209',
 635                 'timestamp': 1423518307,
 636                 'thumbnail': 'https://i.vimeocdn.com/video/default_1280',
 637                 'duration': 10,
 638                 'like_count': int,
 639                 'uploader_url': 'https://vimeo.com/user20132939',
 640                 'view_count': int,
 641                 'comment_count': int,
 642             },
 643             'params': {
 644                 'format': 'best[protocol=https]',
 645                 'videopassword': 'youtube-dl',
 646             },
 647             'expected_warnings': ['Failed to parse XML: not well-formed'],
 648         },
 649         {
 650             # source file returns 403: Forbidden
 651             'url': 'https://vimeo.com/7809605',
 652             'only_matching': True,
 653         },
 654         {
 655             'note': 'Direct URL with hash',
 656             'url': 'https://vimeo.com/160743502/abd0e13fb4',
 657             'info_dict': {
 658                 'id': '160743502',
 659                 'ext': 'mp4',
 660                 'uploader': 'Julian Tryba',
 661                 'uploader_id': 'aliniamedia',
 662                 'title': 'Harrisville New Hampshire',
 663                 'timestamp': 1459259666,
 664                 'upload_date': '20160329',
 665                 'release_timestamp': 1459259666,
 666                 'license': 'by-nc',
 667                 'duration': 159,
 668                 'comment_count': int,
 669                 'thumbnail': 'https://i.vimeocdn.com/video/562802436-585eeb13b5020c6ac0f171a2234067938098f84737787df05ff0d767f6d54ee9-d_1280',
 670                 'like_count': int,
 671                 'uploader_url': 'https://vimeo.com/aliniamedia',
 672                 'release_date': '20160329',
 673             },
 674             'params': {'skip_download': True},
 675             'expected_warnings': ['Failed to parse XML: not well-formed'],
 676         },
 677         {
 678             'url': 'https://vimeo.com/138909882',
 679             'info_dict': {
 680                 'id': '138909882',
 681                 # 'ext': 'm4v',
 682                 'ext': 'mp4',
 683                 'title': 'Eastnor Castle 2015 Firework Champions - The Promo!',
 684                 'description': 'md5:5967e090768a831488f6e74b7821b3c1',
 685                 'uploader_id': 'fireworkchampions',
 686                 'uploader': 'Firework Champions',
 687                 'upload_date': '20150910',
 688                 'timestamp': 1441901895,
 689                 'thumbnail': 'https://i.vimeocdn.com/video/534715882-6ff8e4660cbf2fea68282876d8d44f318825dfe572cc4016e73b3266eac8ae3a-d_1280',
 690                 'uploader_url': 'https://vimeo.com/fireworkchampions',
 691                 'tags': 'count:6',
 692                 'duration': 229,
 693                 'view_count': int,
 694                 'like_count': int,
 695                 'comment_count': int,
 696             },
 697             'params': {
 698                 'skip_download': True,
 699                 # 'format': 'source',
 700             },
 701             'expected_warnings': ['Failed to parse XML: not well-formed'],
 702         },
 703         {
 704             'url': 'https://vimeo.com/channels/staffpicks/143603739',
 705             'info_dict': {
 706                 'id': '143603739',
 707                 'ext': 'mp4',
 708                 'uploader': 'Karim Huu Do',
 709                 'timestamp': 1445846953,
 710                 'upload_date': '20151026',
 711                 'title': 'The Shoes - Submarine Feat. Blaine Harrison',
 712                 'uploader_id': 'karimhd',
 713                 'description': 'md5:8e2eea76de4504c2e8020a9bcfa1e843',
 714                 'channel_id': 'staffpicks',
 715                 'duration': 336,
 716                 'comment_count': int,
 717                 'view_count': int,
 718                 'thumbnail': 'https://i.vimeocdn.com/video/541243181-b593db36a16db2f0096f655da3f5a4dc46b8766d77b0f440df937ecb0c418347-d_1280',
 719                 'like_count': int,
 720                 'uploader_url': 'https://vimeo.com/karimhd',
 721                 'channel_url': 'https://vimeo.com/channels/staffpicks',
 722                 'tags': 'count:6',
 723             },
 724             'params': {'skip_download': 'm3u8'},
 725             'expected_warnings': ['Failed to parse XML: not well-formed'],
 726         },
 727         {
 728             # requires passing unlisted_hash(a52724358e) to load_download_config request
 729             'url': 'https://vimeo.com/392479337/a52724358e',
 730             'only_matching': True,
 731         },
 732         {
 733             # similar, but all numeric: ID must be 581039021, not 9603038895
 734             # issue #29690
 735             'url': 'https://vimeo.com/581039021/9603038895',
 736             'info_dict': {
 737                 'id': '581039021',
 738                 'ext': 'mp4',
 739                 'timestamp': 1627621014,
 740                 'release_timestamp': 1627621014,
 741                 'duration': 976,
 742                 'comment_count': int,
 743                 'thumbnail': 'https://i.vimeocdn.com/video/1202249320-4ddb2c30398c0dc0ee059172d1bd5ea481ad12f0e0e3ad01d2266f56c744b015-d_1280',
 744                 'like_count': int,
 745                 'uploader_url': 'https://vimeo.com/txwestcapital',
 746                 'release_date': '20210730',
 747                 'uploader': 'Christopher Inks',
 748                 'title': 'Thursday, July 29, 2021 BMA Evening Video Update',
 749                 'uploader_id': 'txwestcapital',
 750                 'upload_date': '20210730',
 751             },
 752             'params': {
 753                 'skip_download': True,
 754             },
 755             'expected_warnings': ['Failed to parse XML: not well-formed'],
 756         },
 757         {
 758             # chapters must be sorted, see: https://github.com/yt-dlp/yt-dlp/issues/5308
 759             'url': 'https://player.vimeo.com/video/756714419',
 760             'info_dict': {
 761                 'id': '756714419',
 762                 'ext': 'mp4',
 763                 'title': 'Dr Arielle Schwartz - Therapeutic yoga for optimum sleep',
 764                 'uploader': 'Alex Howard',
 765                 'uploader_id': 'user54729178',
 766                 'uploader_url': 'https://vimeo.com/user54729178',
 767                 'thumbnail': r're:https://i\.vimeocdn\.com/video/1520099929-[\da-f]+-d_1280',
 768                 'duration': 2636,
 769                 'chapters': [
 770                     {'start_time': 0, 'end_time': 10, 'title': '<Untitled Chapter 1>'},
 771                     {'start_time': 10, 'end_time': 106, 'title': 'Welcoming Dr Arielle Schwartz'},
 772                     {'start_time': 106, 'end_time': 305, 'title': 'What is therapeutic yoga?'},
 773                     {'start_time': 305, 'end_time': 594, 'title': 'Vagal toning practices'},
 774                     {'start_time': 594, 'end_time': 888, 'title': 'Trauma and difficulty letting go'},
 775                     {'start_time': 888, 'end_time': 1059, 'title': "Dr Schwartz' insomnia experience"},
 776                     {'start_time': 1059, 'end_time': 1471, 'title': 'A strategy for helping sleep issues'},
 777                     {'start_time': 1471, 'end_time': 1667, 'title': 'Yoga nidra'},
 778                     {'start_time': 1667, 'end_time': 2121, 'title': 'Wisdom in stillness'},
 779                     {'start_time': 2121, 'end_time': 2386, 'title': 'What helps us be more able to let go?'},
 780                     {'start_time': 2386, 'end_time': 2510, 'title': 'Practical tips to help ourselves'},
 781                     {'start_time': 2510, 'end_time': 2636, 'title': 'Where to find out more'},
 782                 ],
 783             },
 784             'params': {
 785                 'http_headers': {'Referer': 'https://sleepsuperconference.com'},
 786                 'skip_download': 'm3u8',
 787             },
 788             'expected_warnings': ['Failed to parse XML: not well-formed'],
 789         },
 790         {
 791             # vimeo.com URL with unlisted hash and Original format
 792             'url': 'https://vimeo.com/144579403/ec02229140',
 793             # 'md5': '6b662c2884e0373183fbde2a0d15cb78',
 794             'info_dict': {
 795                 'id': '144579403',
 796                 'ext': 'mp4',
 797                 'title': 'SALESMANSHIP',
 798                 'description': 'md5:4338302f347a1ff8841b4a3aecaa09f0',
 799                 'uploader': 'Off the Picture Pictures',
 800                 'uploader_id': 'offthepicturepictures',
 801                 'uploader_url': 'https://vimeo.com/offthepicturepictures',
 802                 'duration': 669,
 803                 'upload_date': '20151104',
 804                 'timestamp': 1446607180,
 805                 'release_date': '20151104',
 806                 'release_timestamp': 1446607180,
 807                 'like_count': int,
 808                 'view_count': int,
 809                 'comment_count': int,
 810                 'thumbnail': r're:https://i\.vimeocdn\.com/video/1018638656-[\da-f]+-d_1280',
 811             },
 812             # 'params': {'format': 'Original'},
 813             'expected_warnings': ['Failed to parse XML: not well-formed'],
 814         },
 815         {
 816             # player.vimeo.com URL with source format
 817             'url': 'https://player.vimeo.com/video/859028877',
 818             # 'md5': '19ca3d2463441dee2d2f0671ac2916a2',
 819             'info_dict': {
 820                 'id': '859028877',
 821                 'ext': 'mp4',
 822                 'title': 'Ariana Grande - Honeymoon Avenue (Live from London)',
 823                 'uploader': 'Raja Virdi',
 824                 'uploader_id': 'rajavirdi',
 825                 'uploader_url': 'https://vimeo.com/rajavirdi',
 826                 'duration': 309,
 827                 'thumbnail': r're:https://i\.vimeocdn\.com/video/1716727772-[\da-f]+-d_1280',
 828             },
 829             # 'params': {'format': 'source'},
 830             'expected_warnings': ['Failed to parse XML: not well-formed'],
 831         },
 832         {
 833             # user playlist alias -> https://vimeo.com/258705797
 834             'url': 'https://vimeo.com/user26785108/newspiritualguide',
 835             'only_matching': True,
 836         },
 837         # https://gettingthingsdone.com/workflowmap/
 838         # vimeo embed with check-password page protected by Referer header
 839     ]
 840
 841     @classmethod
 842     def _extract_embed_urls(cls, url, webpage):
 843         for embed_url in super()._extract_embed_urls(url, webpage):
 844             yield cls._smuggle_referrer(embed_url, url)
 845
 846     @classmethod
 847     def _extract_url(cls, url, webpage):
 848         return next(cls._extract_embed_urls(url, webpage), None)
 849
 850     def _verify_player_video_password(self, url, video_id, headers):
 851         password = self._get_video_password()
 852         data = urlencode_postdata({
 853             'password': base64.b64encode(password.encode()),
 854         })
 855         headers = merge_dicts(headers, {
 856             'Content-Type': 'application/x-www-form-urlencoded',
 857         })
 858         checked = self._download_json(
 859             f'{urllib.parse.urlsplit(url)._replace(query=None).geturl()}/check-password',
 860             video_id, 'Verifying the password', data=data, headers=headers)
 861         if checked is False:
 862             raise ExtractorError('Wrong video password', expected=True)
 863         return checked
 864
 865     def _extract_from_api(self, video_id, unlisted_hash=None):
 866         viewer = self._download_json(
 867             'https://vimeo.com/_next/viewer', video_id, 'Downloading viewer info')
 868
 869         for retry in (False, True):
 870             try:
 871                 video = self._call_videos_api(video_id, viewer['jwt'], unlisted_hash)
 872                 break
 873             except ExtractorError as e:
 874                 if (not retry and isinstance(e.cause, HTTPError) and e.cause.status == 400
 875                     and 'password' in traverse_obj(
 876                         self._webpage_read_content(e.cause.response, e.cause.response.url, video_id, fatal=False),
 877                         ({json.loads}, 'invalid_parameters', ..., 'field'),
 878                 )):
 879                     self._verify_video_password(
 880                         video_id, self._get_video_password(), viewer['xsrft'])
 881                     continue
 882                 raise
 883
 884         info = self._parse_config(self._download_json(
 885             video['config_url'], video_id), video_id)
 886         source_format = self._extract_original_format(
 887             f'https://vimeo.com/{video_id}', video_id, unlisted_hash, jwt=viewer['jwt'], api_data=video)
 888         if source_format:
 889             info['formats'].append(source_format)
 890
 891         get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
 892         info.update({
 893             'description': video.get('description'),
 894             'license': video.get('license'),
 895             'release_timestamp': get_timestamp('release'),
 896             'timestamp': get_timestamp('created'),
 897             'view_count': int_or_none(try_get(video, lambda x: x['stats']['plays'])),
 898         })
 899         connections = try_get(
 900             video, lambda x: x['metadata']['connections'], dict) or {}
 901         for k in ('comment', 'like'):
 902             info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total']))
 903         return info
 904
 905     def _try_album_password(self, url):
 906         album_id = self._search_regex(
 907             r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None)
 908         if not album_id:
 909             return
 910         viewer = self._download_json(
 911             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
 912         if not viewer:
 913             webpage = self._download_webpage(url, album_id)
 914             viewer = self._parse_json(self._search_regex(
 915                 r'bootstrap_data\s*=\s*({.+?})</script>',
 916                 webpage, 'bootstrap data'), album_id)['viewer']
 917         jwt = viewer['jwt']
 918         album = self._download_json(
 919             'https://api.vimeo.com/albums/' + album_id,
 920             album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
 921             query={'fields': 'description,name,privacy'})
 922         if try_get(album, lambda x: x['privacy']['view']) == 'password':
 923             password = self.get_param('videopassword')
 924             if not password:
 925                 raise ExtractorError(
 926                     'This album is protected by a password, use the --video-password option',
 927                     expected=True)
 928             self._set_vimeo_cookie('vuid', viewer['vuid'])
 929             try:
 930                 self._download_json(
 931                     f'https://vimeo.com/showcase/{album_id}/auth',
 932                     album_id, 'Verifying the password', data=urlencode_postdata({
 933                         'password': password,
 934                         'token': viewer['xsrft'],
 935                     }), headers={
 936                         'X-Requested-With': 'XMLHttpRequest',
 937                     })
 938             except ExtractorError as e:
 939                 if isinstance(e.cause, HTTPError) and e.cause.status == 401:
 940                     raise ExtractorError('Wrong password', expected=True)
 941                 raise
 942
 943     def _real_extract(self, url):
 944         url, data, headers = self._unsmuggle_headers(url)
 945         if 'Referer' not in headers:
 946             headers['Referer'] = url
 947
 948         # Extract ID from URL
 949         mobj = self._match_valid_url(url).groupdict()
 950         video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash')
 951         if unlisted_hash:
 952             return self._extract_from_api(video_id, unlisted_hash)
 953
 954         if any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
 955             url = 'https://vimeo.com/' + video_id
 956
 957         self._try_album_password(url)
 958         is_secure = urllib.parse.urlparse(url).scheme == 'https'
 959         try:
 960             # Retrieve video webpage to extract further information
 961             webpage, urlh = self._download_webpage_handle(
 962                 url, video_id, headers=headers, impersonate=is_secure)
 963             redirect_url = urlh.url
 964         except ExtractorError as error:
 965             if not isinstance(error.cause, HTTPError) or error.cause.status not in (403, 429):
 966                 raise
 967             errmsg = error.cause.response.read()
 968             if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 969                 raise ExtractorError(
 970                     'Cannot download embed-only video without embedding URL. Please call yt-dlp '
 971                     'with the URL of the page that embeds this video.', expected=True)
 972             # 403 == vimeo.com TLS fingerprint or DC IP block; 429 == player.vimeo.com TLS FP block
 973             status = error.cause.status
 974             dcip_msg = 'If you are using a data center IP or VPN/proxy, your IP may be blocked'
 975             if target := error.cause.response.extensions.get('impersonate'):
 976                 raise ExtractorError(
 977                     f'Got HTTP Error {status} when using impersonate target "{target}". {dcip_msg}')
 978             elif not is_secure:
 979                 raise ExtractorError(f'Got HTTP Error {status}. {dcip_msg}', expected=True)
 980             raise ExtractorError(
 981                 'This request has been blocked due to its TLS fingerprint. Install a '
 982                 'required impersonation dependency if possible, or else if you are okay with '
 983                 f'{self._downloader._format_err("compromising your security/cookies", "light red")}, '
 984                 f'try replacing "https:" with "http:" in the input URL. {dcip_msg}.', expected=True)
 985
 986         if '://player.vimeo.com/video/' in url:
 987             config = self._search_json(
 988                 r'\b(?:playerC|c)onfig\s*=', webpage, 'info section', video_id)
 989             if config.get('view') == 4:
 990                 config = self._verify_player_video_password(
 991                     redirect_url, video_id, headers)
 992             info = self._parse_config(config, video_id)
 993             source_format = self._extract_original_format(
 994                 f'https://vimeo.com/{video_id}', video_id, unlisted_hash)
 995             if source_format:
 996                 info['formats'].append(source_format)
 997             return info
 998
 999         vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
1000         if vimeo_config:
1001             seed_status = vimeo_config.get('seed_status') or {}
1002             if seed_status.get('state') == 'failed':
1003                 raise ExtractorError(
1004                     '{} said: {}'.format(self.IE_NAME, seed_status['title']),
1005                     expected=True)
1006
1007         cc_license = None
1008         timestamp = None
1009         video_description = None
1010         info_dict = {}
1011         config_url = None
1012
1013         channel_id = self._search_regex(
1014             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
1015         if channel_id:
1016             config_url = self._html_search_regex(
1017                 r'\bdata-config-url="([^"]+)"', webpage, 'config URL', default=None)
1018             video_description = clean_html(get_element_by_class('description', webpage))
1019             info_dict.update({
1020                 'channel_id': channel_id,
1021                 'channel_url': 'https://vimeo.com/channels/' + channel_id,
1022             })
1023         if not config_url:
1024             page_config = self._parse_json(self._search_regex(
1025                 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
1026                 webpage, 'page config', default='{}'), video_id, fatal=False)
1027             if not page_config:
1028                 return self._extract_from_api(video_id)
1029             config_url = page_config['player']['config_url']
1030             cc_license = page_config.get('cc_license')
1031             clip = page_config.get('clip') or {}
1032             timestamp = clip.get('uploaded_on')
1033             video_description = clean_html(
1034                 clip.get('description') or page_config.get('description_html_escaped'))
1035         config = self._download_json(config_url, video_id)
1036         video = config.get('video') or {}
1037         vod = video.get('vod') or {}
1038
1039         def is_rented():
1040             if '>You rented this title.<' in webpage:
1041                 return True
1042             if try_get(config, lambda x: x['user']['purchased']):
1043                 return True
1044             for purchase_option in (vod.get('purchase_options') or []):
1045                 if purchase_option.get('purchased'):
1046                     return True
1047                 label = purchase_option.get('label_string')
1048                 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
1049                     return True
1050             return False
1051
1052         if is_rented() and vod.get('is_trailer'):
1053             feature_id = vod.get('feature_id')
1054             if feature_id and not data.get('force_feature_id', False):
1055                 return self.url_result(smuggle_url(
1056                     f'https://player.vimeo.com/player/{feature_id}',
1057                     {'force_feature_id': True}), 'Vimeo')
1058
1059         if not video_description:
1060             video_description = self._html_search_regex(
1061                 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
1062                 webpage, 'description', default=None)
1063         if not video_description:
1064             video_description = self._html_search_meta(
1065                 ['description', 'og:description', 'twitter:description'],
1066                 webpage, default=None)
1067         if not video_description:
1068             self.report_warning('Cannot find video description')
1069
1070         if not timestamp:
1071             timestamp = self._search_regex(
1072                 r'<time[^>]+datetime="([^"]+)"', webpage,
1073                 'timestamp', default=None)
1074
1075         view_count = int_or_none(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count', default=None))
1076         like_count = int_or_none(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count', default=None))
1077         comment_count = int_or_none(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count', default=None))
1078
1079         formats = []
1080
1081         source_format = self._extract_original_format(
1082             'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
1083         if source_format:
1084             formats.append(source_format)
1085
1086         info_dict_config = self._parse_config(config, video_id)
1087         formats.extend(info_dict_config['formats'])
1088         info_dict['_format_sort_fields'] = info_dict_config['_format_sort_fields']
1089
1090         json_ld = self._search_json_ld(webpage, video_id, default={})
1091
1092         if not cc_license:
1093             cc_license = self._search_regex(
1094                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
1095                 webpage, 'license', default=None, group='license')
1096
1097         info_dict.update({
1098             'formats': formats,
1099             'timestamp': unified_timestamp(timestamp),
1100             'description': video_description,
1101             'webpage_url': url,
1102             'view_count': view_count,
1103             'like_count': like_count,
1104             'comment_count': comment_count,
1105             'license': cc_license,
1106         })
1107
1108         return merge_dicts(info_dict, info_dict_config, json_ld)
1109
1110
1111 class VimeoOndemandIE(VimeoIE):  # XXX: Do not subclass from concrete IE
1112     IE_NAME = 'vimeo:ondemand'
1113     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)'
1114     _TESTS = [{
1115         # ondemand video not available via https://vimeo.com/id
1116         'url': 'https://vimeo.com/ondemand/20704',
1117         'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
1118         'info_dict': {
1119             'id': '105442900',
1120             'ext': 'mp4',
1121             'title': 'המעבדה - במאי יותם פלדמן',
1122             'uploader': 'גם סרטים',
1123             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
1124             'uploader_id': 'gumfilms',
1125             'description': 'md5:aeeba3dbd4d04b0fa98a4fdc9c639998',
1126             'upload_date': '20140906',
1127             'timestamp': 1410032453,
1128             'thumbnail': 'https://i.vimeocdn.com/video/488238335-d7bf151c364cff8d467f1b73784668fe60aae28a54573a35d53a1210ae283bd8-d_1280',
1129             'comment_count': int,
1130             'license': 'https://creativecommons.org/licenses/by-nc-nd/3.0/',
1131             'duration': 53,
1132             'view_count': int,
1133             'like_count': int,
1134         },
1135         'params': {
1136             'format': 'best[protocol=https]',
1137         },
1138         'expected_warnings': ['Unable to download JSON metadata'],
1139     }, {
1140         # requires Referer to be passed along with og:video:url
1141         'url': 'https://vimeo.com/ondemand/36938/126682985',
1142         'info_dict': {
1143             'id': '126584684',
1144             'ext': 'mp4',
1145             'title': 'Rävlock, rätt läte på rätt plats',
1146             'uploader': 'Lindroth & Norin',
1147             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
1148             'uploader_id': 'lindrothnorin',
1149             'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
1150             'upload_date': '20150502',
1151             'timestamp': 1430586422,
1152             'duration': 121,
1153             'comment_count': int,
1154             'view_count': int,
1155             'thumbnail': 'https://i.vimeocdn.com/video/517077723-7066ae1d9a79d3eb361334fb5d58ec13c8f04b52f8dd5eadfbd6fb0bcf11f613-d_1280',
1156             'like_count': int,
1157         },
1158         'params': {
1159             'skip_download': True,
1160         },
1161         'expected_warnings': ['Unable to download JSON metadata'],
1162     }, {
1163         'url': 'https://vimeo.com/ondemand/nazmaalik',
1164         'only_matching': True,
1165     }, {
1166         'url': 'https://vimeo.com/ondemand/141692381',
1167         'only_matching': True,
1168     }, {
1169         'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
1170         'only_matching': True,
1171     }]
1172
1173
1174 class VimeoChannelIE(VimeoBaseInfoExtractor):
1175     IE_NAME = 'vimeo:channel'
1176     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
1177     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
1178     _TITLE = None
1179     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
1180     _TESTS = [{
1181         'url': 'https://vimeo.com/channels/tributes',
1182         'info_dict': {
1183             'id': 'tributes',
1184             'title': 'Vimeo Tributes',
1185         },
1186         'playlist_mincount': 22,
1187     }]
1188     _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
1189
1190     def _page_url(self, base_url, pagenum):
1191         return f'{base_url}/videos/page:{pagenum}/'
1192
1193     def _extract_list_title(self, webpage):
1194         return self._TITLE or self._html_search_regex(
1195             self._TITLE_RE, webpage, 'list title', fatal=False)
1196
1197     def _title_and_entries(self, list_id, base_url):
1198         for pagenum in itertools.count(1):
1199             page_url = self._page_url(base_url, pagenum)
1200             webpage = self._download_webpage(
1201                 page_url, list_id,
1202                 f'Downloading page {pagenum}')
1203
1204             if pagenum == 1:
1205                 yield self._extract_list_title(webpage)
1206
1207             # Try extracting href first since not all videos are available via
1208             # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
1209             clips = re.findall(
1210                 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
1211             if clips:
1212                 for video_id, video_url, video_title in clips:
1213                     yield self.url_result(
1214                         urllib.parse.urljoin(base_url, video_url),
1215                         VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
1216             # More relaxed fallback
1217             else:
1218                 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
1219                     yield self.url_result(
1220                         f'https://vimeo.com/{video_id}',
1221                         VimeoIE.ie_key(), video_id=video_id)
1222
1223             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
1224                 break
1225
1226     def _extract_videos(self, list_id, base_url):
1227         title_and_entries = self._title_and_entries(list_id, base_url)
1228         list_title = next(title_and_entries)
1229         return self.playlist_result(title_and_entries, list_id, list_title)
1230
1231     def _real_extract(self, url):
1232         channel_id = self._match_id(url)
1233         return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
1234
1235
1236 class VimeoUserIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1237     IE_NAME = 'vimeo:user'
1238     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos)?/?(?:$|[?#])'
1239     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
1240     _TESTS = [{
1241         'url': 'https://vimeo.com/nkistudio/videos',
1242         'info_dict': {
1243             'title': 'Nki',
1244             'id': 'nkistudio',
1245         },
1246         'playlist_mincount': 66,
1247     }, {
1248         'url': 'https://vimeo.com/nkistudio/',
1249         'only_matching': True,
1250     }]
1251     _BASE_URL_TEMPL = 'https://vimeo.com/%s'
1252
1253
1254 class VimeoAlbumIE(VimeoBaseInfoExtractor):
1255     IE_NAME = 'vimeo:album'
1256     _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
1257     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
1258     _TESTS = [{
1259         'url': 'https://vimeo.com/album/2632481',
1260         'info_dict': {
1261             'id': '2632481',
1262             'title': 'Staff Favorites: November 2013',
1263         },
1264         'playlist_mincount': 13,
1265     }, {
1266         'note': 'Password-protected album',
1267         'url': 'https://vimeo.com/album/3253534',
1268         'info_dict': {
1269             'title': 'test',
1270             'id': '3253534',
1271         },
1272         'playlist_count': 1,
1273         'params': {
1274             'videopassword': 'youtube-dl',
1275         },
1276     }]
1277     _PAGE_SIZE = 100
1278
1279     def _fetch_page(self, album_id, authorization, hashed_pass, page):
1280         api_page = page + 1
1281         query = {
1282             'fields': 'link,uri',
1283             'page': api_page,
1284             'per_page': self._PAGE_SIZE,
1285         }
1286         if hashed_pass:
1287             query['_hashed_pass'] = hashed_pass
1288         try:
1289             videos = self._download_json(
1290                 f'https://api.vimeo.com/albums/{album_id}/videos',
1291                 album_id, f'Downloading page {api_page}', query=query, headers={
1292                     'Authorization': 'jwt ' + authorization,
1293                     'Accept': 'application/json',
1294                 })['data']
1295         except ExtractorError as e:
1296             if isinstance(e.cause, HTTPError) and e.cause.status == 400:
1297                 return
1298             raise
1299         for video in videos:
1300             link = video.get('link')
1301             if not link:
1302                 continue
1303             uri = video.get('uri')
1304             video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
1305             yield self.url_result(link, VimeoIE.ie_key(), video_id)
1306
1307     def _real_extract(self, url):
1308         album_id = self._match_id(url)
1309         viewer = self._download_json(
1310             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
1311         if not viewer:
1312             webpage = self._download_webpage(url, album_id)
1313             viewer = self._parse_json(self._search_regex(
1314                 r'bootstrap_data\s*=\s*({.+?})</script>',
1315                 webpage, 'bootstrap data'), album_id)['viewer']
1316         jwt = viewer['jwt']
1317         album = self._download_json(
1318             'https://api.vimeo.com/albums/' + album_id,
1319             album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
1320             query={'fields': 'description,name,privacy'})
1321         hashed_pass = None
1322         if try_get(album, lambda x: x['privacy']['view']) == 'password':
1323             password = self.get_param('videopassword')
1324             if not password:
1325                 raise ExtractorError(
1326                     'This album is protected by a password, use the --video-password option',
1327                     expected=True)
1328             self._set_vimeo_cookie('vuid', viewer['vuid'])
1329             try:
1330                 hashed_pass = self._download_json(
1331                     f'https://vimeo.com/showcase/{album_id}/auth',
1332                     album_id, 'Verifying the password', data=urlencode_postdata({
1333                         'password': password,
1334                         'token': viewer['xsrft'],
1335                     }), headers={
1336                         'X-Requested-With': 'XMLHttpRequest',
1337                     })['hashed_pass']
1338             except ExtractorError as e:
1339                 if isinstance(e.cause, HTTPError) and e.cause.status == 401:
1340                     raise ExtractorError('Wrong password', expected=True)
1341                 raise
1342         entries = OnDemandPagedList(functools.partial(
1343             self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
1344         return self.playlist_result(
1345             entries, album_id, album.get('name'), album.get('description'))
1346
1347
1348 class VimeoGroupsIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1349     IE_NAME = 'vimeo:group'
1350     _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
1351     _TESTS = [{
1352         'url': 'https://vimeo.com/groups/meetup',
1353         'info_dict': {
1354             'id': 'meetup',
1355             'title': 'Vimeo Meetup!',
1356         },
1357         'playlist_mincount': 27,
1358     }]
1359     _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
1360
1361
1362 class VimeoReviewIE(VimeoBaseInfoExtractor):
1363     IE_NAME = 'vimeo:review'
1364     IE_DESC = 'Review pages on vimeo'
1365     _VALID_URL = r'https?://vimeo\.com/(?P<user>[^/?#]+)/review/(?P<id>\d+)/(?P<hash>[\da-f]{10})'
1366     _TESTS = [{
1367         'url': 'https://vimeo.com/user170863801/review/996447483/a316d6ed8d',
1368         'info_dict': {
1369             'id': '996447483',
1370             'ext': 'mp4',
1371             'title': 'Rodeo day 1-_2',
1372             'uploader': 'BROADKAST',
1373             'uploader_id': 'user170863801',
1374             'uploader_url': 'https://vimeo.com/user170863801',
1375             'duration': 30,
1376             'thumbnail': 'https://i.vimeocdn.com/video/1912612821-09a43bd2e75c203d503aed89de7534f28fc4474a48f59c51999716931a246af5-d_1280',
1377         },
1378         'params': {'skip_download': 'm3u8'},
1379         'expected_warnings': ['Failed to parse XML'],
1380     }, {
1381         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1382         'md5': 'c507a72f780cacc12b2248bb4006d253',
1383         'info_dict': {
1384             'id': '75524534',
1385             'ext': 'mp4',
1386             'title': "DICK HARDWICK 'Comedian'",
1387             'uploader': 'Richard Hardwick',
1388             'uploader_id': 'user21297594',
1389             'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1390             'duration': 304,
1391             'thumbnail': 'https://i.vimeocdn.com/video/450115033-43303819d9ebe24c2630352e18b7056d25197d09b3ae901abdac4c4f1d68de71-d_1280',
1392             'uploader_url': 'https://vimeo.com/user21297594',
1393         },
1394         'skip': '404 Not Found',
1395     }, {
1396         'note': 'video player needs Referer',
1397         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1398         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1399         'info_dict': {
1400             'id': '91613211',
1401             'ext': 'mp4',
1402             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1403             'uploader': 'DevWeek Events',
1404             'duration': 2773,
1405             'thumbnail': r're:^https?://.*\.jpg$',
1406             'uploader_id': 'user22258446',
1407         },
1408         'skip': 'video gone',
1409     }, {
1410         'note': 'Password protected',
1411         'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1412         'info_dict': {
1413             'id': '138823582',
1414             'ext': 'mp4',
1415             'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1416             'uploader': 'TMB',
1417             'uploader_id': 'user37284429',
1418         },
1419         'params': {
1420             'videopassword': 'holygrail',
1421         },
1422         'skip': 'video gone',
1423     }]
1424
1425     def _real_extract(self, url):
1426         user, video_id, review_hash = self._match_valid_url(url).group('user', 'id', 'hash')
1427         data_url = f'https://vimeo.com/{user}/review/data/{video_id}/{review_hash}'
1428         data = self._download_json(data_url, video_id)
1429         viewer = {}
1430         if data.get('isLocked') is True:
1431             video_password = self._get_video_password()
1432             viewer = self._download_json(
1433                 'https://vimeo.com/_rv/viewer', video_id)
1434             self._verify_video_password(video_id, video_password, viewer['xsrft'])
1435             data = self._download_json(data_url, video_id)
1436         clip_data = data['clipData']
1437         config_url = clip_data['configUrl']
1438         config = self._download_json(config_url, video_id)
1439         info_dict = self._parse_config(config, video_id)
1440         source_format = self._extract_original_format(
1441             f'https://vimeo.com/{user}/review/{video_id}/{review_hash}/action',
1442             video_id, unlisted_hash=clip_data.get('unlistedHash'), jwt=viewer.get('jwt'))
1443         if source_format:
1444             info_dict['formats'].append(source_format)
1445         info_dict['description'] = clean_html(clip_data.get('description'))
1446         return info_dict
1447
1448
1449 class VimeoWatchLaterIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1450     IE_NAME = 'vimeo:watchlater'
1451     IE_DESC = 'Vimeo watch later list, ":vimeowatchlater" keyword (requires authentication)'
1452     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1453     _TITLE = 'Watch Later'
1454     _LOGIN_REQUIRED = True
1455     _TESTS = [{
1456         'url': 'https://vimeo.com/watchlater',
1457         'only_matching': True,
1458     }]
1459
1460     def _page_url(self, base_url, pagenum):
1461         url = f'{base_url}/page:{pagenum}/'
1462         request = Request(url)
1463         # Set the header to get a partial html page with the ids,
1464         # the normal page doesn't contain them.
1465         request.headers['X-Requested-With'] = 'XMLHttpRequest'
1466         return request
1467
1468     def _real_extract(self, url):
1469         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1470
1471
1472 class VimeoLikesIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1473     _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1474     IE_NAME = 'vimeo:likes'
1475     IE_DESC = 'Vimeo user likes'
1476     _TESTS = [{
1477         'url': 'https://vimeo.com/user755559/likes/',
1478         'playlist_mincount': 293,
1479         'info_dict': {
1480             'id': 'user755559',
1481             'title': 'urza’s Likes',
1482         },
1483     }, {
1484         'url': 'https://vimeo.com/stormlapse/likes',
1485         'only_matching': True,
1486     }]
1487
1488     def _page_url(self, base_url, pagenum):
1489         return f'{base_url}/page:{pagenum}/'
1490
1491     def _real_extract(self, url):
1492         user_id = self._match_id(url)
1493         return self._extract_videos(user_id, f'https://vimeo.com/{user_id}/likes')
1494
1495
1496 class VHXEmbedIE(VimeoBaseInfoExtractor):
1497     IE_NAME = 'vhx:embed'
1498     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1499     _EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://embed\.vhx\.tv/videos/\d+[^"]*)"']
1500
1501     @classmethod
1502     def _extract_embed_urls(cls, url, webpage):
1503         for embed_url in super()._extract_embed_urls(url, webpage):
1504             yield cls._smuggle_referrer(embed_url, url)
1505
1506     def _real_extract(self, url):
1507         video_id = self._match_id(url)
1508         url, _, headers = self._unsmuggle_headers(url)
1509         webpage = self._download_webpage(url, video_id, headers=headers)
1510         config_url = self._parse_json(self._search_regex(
1511             r'window\.OTTData\s*=\s*({.+})', webpage,
1512             'ott data'), video_id, js_to_json)['config_url']
1513         config = self._download_json(config_url, video_id)
1514         info = self._parse_config(config, video_id)
1515         info['id'] = video_id
1516         return info
1517
1518
1519 class VimeoProIE(VimeoBaseInfoExtractor):
1520     IE_NAME = 'vimeo:pro'
1521     _VALID_URL = r'https?://(?:www\.)?vimeopro\.com/[^/?#]+/(?P<slug>[^/?#]+)(?:(?:/videos?/(?P<id>[0-9]+)))?'
1522     _TESTS = [{
1523         # Vimeo URL derived from video_id
1524         'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
1525         'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
1526         'note': 'Vimeo Pro video (#1197)',
1527         'info_dict': {
1528             'id': '68093876',
1529             'ext': 'mp4',
1530             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
1531             'uploader_id': 'openstreetmapus',
1532             'uploader': 'OpenStreetMap US',
1533             'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
1534             'description': 'md5:2c362968038d4499f4d79f88458590c1',
1535             'duration': 1595,
1536             'upload_date': '20130610',
1537             'timestamp': 1370893156,
1538             'license': 'by',
1539             'thumbnail': 'https://i.vimeocdn.com/video/440260469-19b0d92fca3bd84066623b53f1eb8aaa3980c6c809e2d67b6b39ab7b4a77a344-d_960',
1540             'view_count': int,
1541             'comment_count': int,
1542             'like_count': int,
1543             'tags': 'count:1',
1544         },
1545         'params': {
1546             'format': 'best[protocol=https]',
1547         },
1548     }, {
1549         # password-protected VimeoPro page with Vimeo player embed
1550         'url': 'https://vimeopro.com/cadfem/simulation-conference-mechanische-systeme-in-perfektion',
1551         'info_dict': {
1552             'id': '764543723',
1553             'ext': 'mp4',
1554             'title': 'Mechanische Systeme in Perfektion: Realität erfassen, Innovation treiben',
1555             'thumbnail': 'https://i.vimeocdn.com/video/1543784598-a1a750494a485e601110136b9fe11e28c2131942452b3a5d30391cb3800ca8fd-d_1280',
1556             'description': 'md5:2a9d195cd1b0f6f79827107dc88c2420',
1557             'uploader': 'CADFEM',
1558             'uploader_id': 'cadfem',
1559             'uploader_url': 'https://vimeo.com/cadfem',
1560             'duration': 12505,
1561             'chapters': 'count:10',
1562         },
1563         'params': {
1564             'videopassword': 'Conference2022',
1565             'skip_download': True,
1566         },
1567     }]
1568
1569     def _real_extract(self, url):
1570         display_id, video_id = self._match_valid_url(url).group('slug', 'id')
1571         if video_id:
1572             display_id = video_id
1573         webpage = self._download_webpage(url, display_id)
1574
1575         password_form = self._search_regex(
1576             r'(?is)<form[^>]+?method=["\']post["\'][^>]*>(.+?password.+?)</form>',
1577             webpage, 'password form', default=None)
1578         if password_form:
1579             try:
1580                 webpage = self._download_webpage(url, display_id, data=urlencode_postdata({
1581                     'password': self._get_video_password(),
1582                     **self._hidden_inputs(password_form),
1583                 }), note='Logging in with video password')
1584             except ExtractorError as e:
1585                 if isinstance(e.cause, HTTPError) and e.cause.status == 418:
1586                     raise ExtractorError('Wrong video password', expected=True)
1587                 raise
1588
1589         description = None
1590         # even if we have video_id, some videos require player URL with portfolio_id query param
1591         # https://github.com/ytdl-org/youtube-dl/issues/20070
1592         vimeo_url = VimeoIE._extract_url(url, webpage)
1593         if vimeo_url:
1594             description = self._html_search_meta('description', webpage, default=None)
1595         elif video_id:
1596             vimeo_url = f'https://vimeo.com/{video_id}'
1597         else:
1598             raise ExtractorError(
1599                 'No Vimeo embed or video ID could be found in VimeoPro page', expected=True)
1600
1601         return self.url_result(vimeo_url, VimeoIE, video_id, url_transparent=True,
1602                                description=description)