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         viewer = self._download_json('https://vimeo.com/_next/viewer', None, 'Downloading login token')
  52         data = {
  53             'action': 'login',
  54             'email': username,
  55             'password': password,
  56             'service': 'vimeo',
  57             'token': viewer['xsrft'],
  58         }
  59         self._set_vimeo_cookie('vuid', viewer['vuid'])
  60         try:
  61             self._download_webpage(
  62                 self._LOGIN_URL, None, 'Logging in',
  63                 data=urlencode_postdata(data), headers={
  64                     'Content-Type': 'application/x-www-form-urlencoded',
  65                     'Referer': self._LOGIN_URL,
  66                 })
  67         except ExtractorError as e:
  68             if isinstance(e.cause, HTTPError) and e.cause.status == 418:
  69                 raise ExtractorError(
  70                     'Unable to log in: bad username or password',
  71                     expected=True)
  72             raise ExtractorError('Unable to log in')
  73
  74     def _real_initialize(self):
  75         if self._LOGIN_REQUIRED and not self._get_cookies('https://vimeo.com').get('vuid'):
  76             self._raise_login_required()
  77
  78     def _get_video_password(self):
  79         password = self.get_param('videopassword')
  80         if password is None:
  81             raise ExtractorError(
  82                 'This video is protected by a password, use the --video-password option',
  83                 expected=True)
  84         return password
  85
  86     def _verify_video_password(self, url, video_id, password, token, vuid):
  87         if url.startswith('http://'):
  88             # vimeo only supports https now, but the user can give an http url
  89             url = url.replace('http://', 'https://')
  90         self._set_vimeo_cookie('vuid', vuid)
  91         return self._download_webpage(
  92             url + '/password', video_id, 'Verifying the password',
  93             'Wrong password', data=urlencode_postdata({
  94                 'password': password,
  95                 'token': token,
  96             }), headers={
  97                 'Content-Type': 'application/x-www-form-urlencoded',
  98                 'Referer': url,
  99             })
 100
 101     def _extract_xsrft_and_vuid(self, webpage):
 102         xsrft = self._search_regex(
 103             r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
 104             webpage, 'login token', group='xsrft')
 105         vuid = self._search_regex(
 106             r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
 107             webpage, 'vuid', group='vuid')
 108         return xsrft, vuid
 109
 110     def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
 111         vimeo_config = self._search_regex(
 112             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
 113             webpage, 'vimeo config', *args, **kwargs)
 114         if vimeo_config:
 115             return self._parse_json(vimeo_config, video_id)
 116
 117     def _set_vimeo_cookie(self, name, value):
 118         self._set_cookie('vimeo.com', name, value)
 119
 120     def _parse_config(self, config, video_id):
 121         video_data = config['video']
 122         video_title = video_data.get('title')
 123         live_event = video_data.get('live_event') or {}
 124         is_live = live_event.get('status') == 'started'
 125         request = config.get('request') or {}
 126
 127         formats = []
 128         subtitles = {}
 129
 130         config_files = video_data.get('files') or request.get('files') or {}
 131         for f in (config_files.get('progressive') or []):
 132             video_url = f.get('url')
 133             if not video_url:
 134                 continue
 135             formats.append({
 136                 'url': video_url,
 137                 'format_id': 'http-%s' % f.get('quality'),
 138                 'source_preference': 10,
 139                 'width': int_or_none(f.get('width')),
 140                 'height': int_or_none(f.get('height')),
 141                 'fps': int_or_none(f.get('fps')),
 142                 'tbr': int_or_none(f.get('bitrate')),
 143             })
 144
 145         # TODO: fix handling of 308 status code returned for live archive manifest requests
 146         sep_pattern = r'/sep/video/'
 147         for files_type in ('hls', 'dash'):
 148             for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items():
 149                 manifest_url = cdn_data.get('url')
 150                 if not manifest_url:
 151                     continue
 152                 format_id = '%s-%s' % (files_type, cdn_name)
 153                 sep_manifest_urls = []
 154                 if re.search(sep_pattern, manifest_url):
 155                     for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
 156                         sep_manifest_urls.append((format_id + suffix, re.sub(
 157                             sep_pattern, '/%s/' % repl, manifest_url)))
 158                 else:
 159                     sep_manifest_urls = [(format_id, manifest_url)]
 160                 for f_id, m_url in sep_manifest_urls:
 161                     if files_type == 'hls':
 162                         fmts, subs = self._extract_m3u8_formats_and_subtitles(
 163                             m_url, video_id, 'mp4', live=is_live, m3u8_id=f_id,
 164                             note='Downloading %s m3u8 information' % cdn_name,
 165                             fatal=False)
 166                         formats.extend(fmts)
 167                         self._merge_subtitles(subs, target=subtitles)
 168                     elif files_type == 'dash':
 169                         if 'json=1' in m_url:
 170                             real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
 171                             if real_m_url:
 172                                 m_url = real_m_url
 173                         fmts, subs = self._extract_mpd_formats_and_subtitles(
 174                             m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
 175                             'Downloading %s MPD information' % cdn_name,
 176                             fatal=False)
 177                         formats.extend(fmts)
 178                         self._merge_subtitles(subs, target=subtitles)
 179
 180         live_archive = live_event.get('archive') or {}
 181         live_archive_source_url = live_archive.get('source_url')
 182         if live_archive_source_url and live_archive.get('status') == 'done':
 183             formats.append({
 184                 'format_id': 'live-archive-source',
 185                 'url': live_archive_source_url,
 186                 'quality': 10,
 187             })
 188
 189         for tt in (request.get('text_tracks') or []):
 190             subtitles.setdefault(tt['lang'], []).append({
 191                 'ext': 'vtt',
 192                 'url': urljoin('https://vimeo.com', tt['url']),
 193             })
 194
 195         thumbnails = []
 196         if not is_live:
 197             for key, thumb in (video_data.get('thumbs') or {}).items():
 198                 thumbnails.append({
 199                     'id': key,
 200                     'width': int_or_none(key),
 201                     'url': thumb,
 202                 })
 203             thumbnail = video_data.get('thumbnail')
 204             if thumbnail:
 205                 thumbnails.append({
 206                     'url': thumbnail,
 207                 })
 208
 209         owner = video_data.get('owner') or {}
 210         video_uploader_url = owner.get('url')
 211
 212         duration = int_or_none(video_data.get('duration'))
 213         chapter_data = try_get(config, lambda x: x['embed']['chapters']) or []
 214         chapters = [{
 215             'title': current_chapter.get('title'),
 216             'start_time': current_chapter.get('timecode'),
 217             'end_time': next_chapter.get('timecode'),
 218         } for current_chapter, next_chapter in zip(chapter_data, chapter_data[1:] + [{'timecode': duration}])]
 219         if chapters and chapters[0]['start_time']:  # Chapters may not start from 0
 220             chapters[:0] = [{'title': '<Untitled>', 'start_time': 0, 'end_time': chapters[0]['start_time']}]
 221
 222         return {
 223             'id': str_or_none(video_data.get('id')) or video_id,
 224             'title': video_title,
 225             'uploader': owner.get('name'),
 226             'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
 227             'uploader_url': video_uploader_url,
 228             'thumbnails': thumbnails,
 229             'duration': duration,
 230             'chapters': chapters or None,
 231             'formats': formats,
 232             'subtitles': subtitles,
 233             'is_live': is_live,
 234             # Note: Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
 235             # at the same time without actual units specified.
 236             '_format_sort_fields': ('quality', 'res', 'fps', 'hdr:12', 'source'),
 237         }
 238
 239     def _extract_original_format(self, url, video_id, unlisted_hash=None):
 240         query = {'action': 'load_download_config'}
 241         if unlisted_hash:
 242             query['unlisted_hash'] = unlisted_hash
 243         download_data = self._download_json(
 244             url, video_id, fatal=False, query=query,
 245             headers={'X-Requested-With': 'XMLHttpRequest'},
 246             expected_status=(403, 404)) or {}
 247         source_file = download_data.get('source_file')
 248         download_url = try_get(source_file, lambda x: x['download_url'])
 249         if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 250             source_name = source_file.get('public_name', 'Original')
 251             if self._is_valid_url(download_url, video_id, '%s video' % source_name):
 252                 ext = (try_get(
 253                     source_file, lambda x: x['extension'],
 254                     compat_str) or determine_ext(
 255                     download_url, None) or 'mp4').lower()
 256                 return {
 257                     'url': download_url,
 258                     'ext': ext,
 259                     'width': int_or_none(source_file.get('width')),
 260                     'height': int_or_none(source_file.get('height')),
 261                     'filesize': parse_filesize(source_file.get('size')),
 262                     'format_id': source_name,
 263                     'quality': 1,
 264                 }
 265
 266         jwt_response = self._download_json(
 267             'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {}
 268         if not jwt_response.get('jwt'):
 269             return
 270         headers = {'Authorization': 'jwt %s' % jwt_response['jwt'], 'Accept': 'application/json'}
 271         original_response = self._download_json(
 272             f'https://api.vimeo.com/videos/{video_id}', video_id,
 273             headers=headers, fatal=False, expected_status=(403, 404)) or {}
 274         for download_data in original_response.get('download') or []:
 275             download_url = download_data.get('link')
 276             if not download_url or download_data.get('quality') != 'source':
 277                 continue
 278             ext = determine_ext(parse_qs(download_url).get('filename', [''])[0].lower(), default_ext=None)
 279             if not ext:
 280                 urlh = self._request_webpage(
 281                     HEADRequest(download_url), video_id, fatal=False, note='Determining source extension')
 282                 ext = urlh and urlhandle_detect_ext(urlh)
 283             return {
 284                 'url': download_url,
 285                 'ext': ext or 'unknown_video',
 286                 'format_id': download_data.get('public_name', 'Original'),
 287                 'width': int_or_none(download_data.get('width')),
 288                 'height': int_or_none(download_data.get('height')),
 289                 'fps': int_or_none(download_data.get('fps')),
 290                 'filesize': int_or_none(download_data.get('size')),
 291                 'quality': 1,
 292             }
 293
 294
 295 class VimeoIE(VimeoBaseInfoExtractor):
 296     """Information extractor for vimeo.com."""
 297
 298     # _VALID_URL matches Vimeo URLs
 299     _VALID_URL = r'''(?x)
 300                      https?://
 301                          (?:
 302                              (?:
 303                                  www|
 304                                  player
 305                              )
 306                              \.
 307                          )?
 308                          vimeo\.com/
 309                          (?:
 310                              (?P<u>user)|
 311                              (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
 312                              (?:.*?/)??
 313                              (?P<q>
 314                                  (?:
 315                                      play_redirect_hls|
 316                                      moogaloop\.swf)\?clip_id=
 317                              )?
 318                              (?:videos?/)?
 319                          )
 320                          (?P<id>[0-9]+)
 321                          (?(u)
 322                              /(?!videos|likes)[^/?#]+/?|
 323                              (?(q)|/(?P<unlisted_hash>[\da-f]{10}))?
 324                          )
 325                          (?:(?(q)[&]|(?(u)|/?)[?]).*?)?(?:[#].*)?$
 326                  '''
 327     IE_NAME = 'vimeo'
 328     _EMBED_REGEX = [
 329         # iframe
 330         r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
 331         # Embedded (swf embed) Vimeo player
 332         r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
 333         # Non-standard embedded Vimeo player
 334         r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
 335     ]
 336     _TESTS = [
 337         {
 338             'url': 'http://vimeo.com/56015672#at=0',
 339             'md5': '8879b6cc097e987f02484baf890129e5',
 340             'info_dict': {
 341                 'id': '56015672',
 342                 'ext': 'mp4',
 343                 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
 344                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
 345                 'timestamp': 1355990239,
 346                 'upload_date': '20121220',
 347                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
 348                 'uploader_id': 'user7108434',
 349                 'uploader': 'Filippo Valsorda',
 350                 'duration': 10,
 351                 'license': 'by-sa',
 352             },
 353             'params': {
 354                 'format': 'best[protocol=https]',
 355             },
 356             'skip': 'No longer available'
 357         },
 358         {
 359             'url': 'http://player.vimeo.com/video/54469442',
 360             'md5': '619b811a4417aa4abe78dc653becf511',
 361             'note': 'Videos that embed the url in the player page',
 362             'info_dict': {
 363                 'id': '54469442',
 364                 'ext': 'mp4',
 365                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 366                 'uploader': 'Business of Software',
 367                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
 368                 'uploader_id': 'businessofsoftware',
 369                 'duration': 3610,
 370                 'description': None,
 371                 'thumbnail': 'https://i.vimeocdn.com/video/376682406-f34043e7b766af6bef2af81366eacd6724f3fc3173179a11a97a1e26587c9529-d_1280',
 372             },
 373             'params': {
 374                 'format': 'best[protocol=https]',
 375             },
 376         },
 377         {
 378             'url': 'http://vimeo.com/68375962',
 379             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 380             'note': 'Video protected with password',
 381             'info_dict': {
 382                 'id': '68375962',
 383                 'ext': 'mp4',
 384                 'title': 'youtube-dl password protected test video',
 385                 'timestamp': 1371200155,
 386                 'upload_date': '20130614',
 387                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 388                 'uploader_id': 'user18948128',
 389                 'uploader': 'Jaime Marquínez Ferrándiz',
 390                 'duration': 10,
 391                 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
 392                 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
 393                 'view_count': int,
 394                 'comment_count': int,
 395                 'like_count': int,
 396             },
 397             'params': {
 398                 'format': 'best[protocol=https]',
 399                 'videopassword': 'youtube-dl',
 400             },
 401         },
 402         {
 403             'url': 'http://vimeo.com/channels/keypeele/75629013',
 404             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 405             'info_dict': {
 406                 'id': '75629013',
 407                 'ext': 'mp4',
 408                 'title': 'Key & Peele: Terrorist Interrogation',
 409                 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
 410                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
 411                 'uploader_id': 'atencio',
 412                 'uploader': 'Peter Atencio',
 413                 'channel_id': 'keypeele',
 414                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
 415                 'timestamp': 1380339469,
 416                 'upload_date': '20130928',
 417                 'duration': 187,
 418                 'thumbnail': 'https://i.vimeocdn.com/video/450239872-a05512d9b1e55d707a7c04365c10980f327b06d966351bc403a5d5d65c95e572-d_1280',
 419                 'view_count': int,
 420                 'comment_count': int,
 421                 'like_count': int,
 422             },
 423             'params': {'format': 'http-1080p'},
 424         },
 425         {
 426             'url': 'http://vimeo.com/76979871',
 427             'note': 'Video with subtitles',
 428             'info_dict': {
 429                 'id': '76979871',
 430                 'ext': 'mov',
 431                 'title': 'The New Vimeo Player (You Know, For Videos)',
 432                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 433                 'timestamp': 1381846109,
 434                 'upload_date': '20131015',
 435                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
 436                 'uploader_id': 'staff',
 437                 'uploader': 'Vimeo Staff',
 438                 'duration': 62,
 439                 'subtitles': {
 440                     'de': [{'ext': 'vtt'}],
 441                     'en': [{'ext': 'vtt'}],
 442                     'es': [{'ext': 'vtt'}],
 443                     'fr': [{'ext': 'vtt'}],
 444                 },
 445             },
 446             'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
 447         },
 448         {
 449             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 450             'url': 'https://player.vimeo.com/video/98044508',
 451             'note': 'The js code contains assignments to the same variable as the config',
 452             'info_dict': {
 453                 'id': '98044508',
 454                 'ext': 'mp4',
 455                 'title': 'Pier Solar OUYA Official Trailer',
 456                 'uploader': 'Tulio Gonçalves',
 457                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
 458                 'uploader_id': 'user28849593',
 459                 'duration': 118,
 460                 'thumbnail': 'https://i.vimeocdn.com/video/478636036-c18440305ef3df9decfb6bf207a61fe39d2d17fa462a96f6f2d93d30492b037d-d_1280',
 461             },
 462         },
 463         {
 464             # contains original format
 465             'url': 'https://vimeo.com/33951933',
 466             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 467             'info_dict': {
 468                 'id': '33951933',
 469                 'ext': 'mp4',
 470                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 471                 'uploader': 'The DMCI',
 472                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
 473                 'uploader_id': 'dmci',
 474                 'timestamp': 1324343742,
 475                 'upload_date': '20111220',
 476                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 477                 'duration': 60,
 478                 'comment_count': int,
 479                 'view_count': int,
 480                 'thumbnail': 'https://i.vimeocdn.com/video/231174622-dd07f015e9221ff529d451e1cc31c982b5d87bfafa48c4189b1da72824ee289a-d_1280',
 481                 'like_count': int,
 482             },
 483         },
 484         {
 485             'note': 'Contains original format not accessible in webpage',
 486             'url': 'https://vimeo.com/393756517',
 487             'md5': 'c464af248b592190a5ffbb5d33f382b0',
 488             'info_dict': {
 489                 'id': '393756517',
 490                 'ext': 'mov',
 491                 'timestamp': 1582642091,
 492                 'uploader_id': 'frameworkla',
 493                 'title': 'Straight To Hell - Sabrina: Netflix',
 494                 'uploader': 'Framework Studio',
 495                 'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
 496                 'upload_date': '20200225',
 497                 'duration': 176,
 498                 'thumbnail': 'https://i.vimeocdn.com/video/859377297-836494a4ef775e9d4edbace83937d9ad34dc846c688c0c419c0e87f7ab06c4b3-d_1280',
 499                 'uploader_url': 'https://vimeo.com/frameworkla',
 500             },
 501         },
 502         {
 503             # only available via https://vimeo.com/channels/tributes/6213729 and
 504             # not via https://vimeo.com/6213729
 505             'url': 'https://vimeo.com/channels/tributes/6213729',
 506             'info_dict': {
 507                 'id': '6213729',
 508                 'ext': 'mp4',
 509                 'title': 'Vimeo Tribute: The Shining',
 510                 'uploader': 'Casey Donahue',
 511                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
 512                 'uploader_id': 'caseydonahue',
 513                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
 514                 'channel_id': 'tributes',
 515                 'timestamp': 1250886430,
 516                 'upload_date': '20090821',
 517                 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
 518                 'duration': 321,
 519                 'comment_count': int,
 520                 'view_count': int,
 521                 'thumbnail': 'https://i.vimeocdn.com/video/22728298-bfc22146f930de7cf497821c7b0b9f168099201ecca39b00b6bd31fcedfca7a6-d_1280',
 522                 'like_count': int,
 523             },
 524             'params': {
 525                 'skip_download': True,
 526             },
 527         },
 528         {
 529             # redirects to ondemand extractor and should be passed through it
 530             # for successful extraction
 531             'url': 'https://vimeo.com/73445910',
 532             'info_dict': {
 533                 'id': '73445910',
 534                 'ext': 'mp4',
 535                 'title': 'The Reluctant Revolutionary',
 536                 'uploader': '10Ft Films',
 537                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
 538                 'uploader_id': 'tenfootfilms',
 539                 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
 540                 'upload_date': '20130830',
 541                 'timestamp': 1377853339,
 542             },
 543             'params': {
 544                 'skip_download': True,
 545             },
 546             'skip': 'this page is no longer available.',
 547         },
 548         {
 549             'url': 'http://player.vimeo.com/video/68375962',
 550             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 551             'info_dict': {
 552                 'id': '68375962',
 553                 'ext': 'mp4',
 554                 'title': 'youtube-dl password protected test video',
 555                 'timestamp': 1371200155,
 556                 'upload_date': '20130614',
 557                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 558                 'uploader_id': 'user18948128',
 559                 'uploader': 'Jaime Marquínez Ferrándiz',
 560                 'duration': 10,
 561                 'description': 'md5:6173f270cd0c0119f22817204b3eb86c',
 562                 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_1280',
 563                 'view_count': int,
 564                 'comment_count': int,
 565                 'like_count': int,
 566             },
 567             'params': {
 568                 'format': 'best[protocol=https]',
 569                 'videopassword': 'youtube-dl',
 570             },
 571         },
 572         {
 573             'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
 574             'only_matching': True,
 575         },
 576         {
 577             'url': 'https://vimeo.com/109815029',
 578             'note': 'Video not completely processed, "failed" seed status',
 579             'only_matching': True,
 580         },
 581         {
 582             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 583             'only_matching': True,
 584         },
 585         {
 586             'url': 'https://vimeo.com/album/2632481/video/79010983',
 587             'only_matching': True,
 588         },
 589         {
 590             'url': 'https://vimeo.com/showcase/3253534/video/119195465',
 591             'note': 'A video in a password protected album (showcase)',
 592             'info_dict': {
 593                 'id': '119195465',
 594                 'ext': 'mp4',
 595                 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
 596                 'uploader': 'Philipp Hagemeister',
 597                 'uploader_id': 'user20132939',
 598                 'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
 599                 'upload_date': '20150209',
 600                 'timestamp': 1423518307,
 601                 'thumbnail': 'https://i.vimeocdn.com/video/default_1280',
 602                 'duration': 10,
 603                 'like_count': int,
 604                 'uploader_url': 'https://vimeo.com/user20132939',
 605                 'view_count': int,
 606                 'comment_count': int,
 607             },
 608             'params': {
 609                 'format': 'best[protocol=https]',
 610                 'videopassword': 'youtube-dl',
 611             },
 612         },
 613         {
 614             # source file returns 403: Forbidden
 615             'url': 'https://vimeo.com/7809605',
 616             'only_matching': True,
 617         },
 618         {
 619             'note': 'Direct URL with hash',
 620             'url': 'https://vimeo.com/160743502/abd0e13fb4',
 621             'info_dict': {
 622                 'id': '160743502',
 623                 'ext': 'mp4',
 624                 'uploader': 'Julian Tryba',
 625                 'uploader_id': 'aliniamedia',
 626                 'title': 'Harrisville New Hampshire',
 627                 'timestamp': 1459259666,
 628                 'upload_date': '20160329',
 629                 'release_timestamp': 1459259666,
 630                 'license': 'by-nc',
 631                 'duration': 159,
 632                 'comment_count': int,
 633                 'thumbnail': 'https://i.vimeocdn.com/video/562802436-585eeb13b5020c6ac0f171a2234067938098f84737787df05ff0d767f6d54ee9-d_1280',
 634                 'like_count': int,
 635                 'uploader_url': 'https://vimeo.com/aliniamedia',
 636                 'release_date': '20160329',
 637             },
 638             'params': {'skip_download': True},
 639         },
 640         {
 641             'url': 'https://vimeo.com/138909882',
 642             'info_dict': {
 643                 'id': '138909882',
 644                 'ext': 'mp4',
 645                 'title': 'Eastnor Castle 2015 Firework Champions - The Promo!',
 646                 'description': 'md5:5967e090768a831488f6e74b7821b3c1',
 647                 'uploader_id': 'fireworkchampions',
 648                 'uploader': 'Firework Champions',
 649                 'upload_date': '20150910',
 650                 'timestamp': 1441901895,
 651             },
 652             'params': {
 653                 'skip_download': True,
 654                 'format': 'Original',
 655             },
 656         },
 657         {
 658             'url': 'https://vimeo.com/channels/staffpicks/143603739',
 659             'info_dict': {
 660                 'id': '143603739',
 661                 'ext': 'mp4',
 662                 'uploader': 'Karim Huu Do',
 663                 'timestamp': 1445846953,
 664                 'upload_date': '20151026',
 665                 'title': 'The Shoes - Submarine Feat. Blaine Harrison',
 666                 'uploader_id': 'karimhd',
 667                 'description': 'md5:8e2eea76de4504c2e8020a9bcfa1e843',
 668                 'channel_id': 'staffpicks',
 669                 'duration': 336,
 670                 'comment_count': int,
 671                 'view_count': int,
 672                 'thumbnail': 'https://i.vimeocdn.com/video/541243181-b593db36a16db2f0096f655da3f5a4dc46b8766d77b0f440df937ecb0c418347-d_1280',
 673                 'like_count': int,
 674                 'uploader_url': 'https://vimeo.com/karimhd',
 675                 'channel_url': 'https://vimeo.com/channels/staffpicks',
 676             },
 677             'params': {'skip_download': 'm3u8'},
 678         },
 679         {
 680             # requires passing unlisted_hash(a52724358e) to load_download_config request
 681             'url': 'https://vimeo.com/392479337/a52724358e',
 682             'only_matching': True,
 683         },
 684         {
 685             # similar, but all numeric: ID must be 581039021, not 9603038895
 686             # issue #29690
 687             'url': 'https://vimeo.com/581039021/9603038895',
 688             'info_dict': {
 689                 'id': '581039021',
 690                 'ext': 'mp4',
 691                 'timestamp': 1627621014,
 692                 'release_timestamp': 1627621014,
 693                 'duration': 976,
 694                 'comment_count': int,
 695                 'thumbnail': 'https://i.vimeocdn.com/video/1202249320-4ddb2c30398c0dc0ee059172d1bd5ea481ad12f0e0e3ad01d2266f56c744b015-d_1280',
 696                 'like_count': int,
 697                 'uploader_url': 'https://vimeo.com/txwestcapital',
 698                 'release_date': '20210730',
 699                 'uploader': 'Christopher Inks',
 700                 'title': 'Thursday, July 29, 2021 BMA Evening Video Update',
 701                 'uploader_id': 'txwestcapital',
 702                 'upload_date': '20210730',
 703             },
 704             'params': {
 705                 'skip_download': True,
 706             },
 707         },
 708         {
 709             # user playlist alias -> https://vimeo.com/258705797
 710             'url': 'https://vimeo.com/user26785108/newspiritualguide',
 711             'only_matching': True,
 712         },
 713         # https://gettingthingsdone.com/workflowmap/
 714         # vimeo embed with check-password page protected by Referer header
 715     ]
 716
 717     @classmethod
 718     def _extract_embed_urls(cls, url, webpage):
 719         for embed_url in super()._extract_embed_urls(url, webpage):
 720             yield cls._smuggle_referrer(embed_url, url)
 721
 722     @classmethod
 723     def _extract_url(cls, url, webpage):
 724         return next(cls._extract_embed_urls(url, webpage), None)
 725
 726     def _verify_player_video_password(self, url, video_id, headers):
 727         password = self._get_video_password()
 728         data = urlencode_postdata({
 729             'password': base64.b64encode(password.encode()),
 730         })
 731         headers = merge_dicts(headers, {
 732             'Content-Type': 'application/x-www-form-urlencoded',
 733         })
 734         checked = self._download_json(
 735             f'{compat_urlparse.urlsplit(url)._replace(query=None).geturl()}/check-password',
 736             video_id, 'Verifying the password', data=data, headers=headers)
 737         if checked is False:
 738             raise ExtractorError('Wrong video password', expected=True)
 739         return checked
 740
 741     def _extract_from_api(self, video_id, unlisted_hash=None):
 742         token = self._download_json(
 743             'https://vimeo.com/_rv/jwt', video_id, headers={
 744                 'X-Requested-With': 'XMLHttpRequest'
 745             })['token']
 746         api_url = 'https://api.vimeo.com/videos/' + video_id
 747         if unlisted_hash:
 748             api_url += ':' + unlisted_hash
 749         video = self._download_json(
 750             api_url, video_id, headers={
 751                 'Authorization': 'jwt ' + token,
 752                 'Accept': 'application/json',
 753             }, query={
 754                 'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
 755             })
 756         info = self._parse_config(self._download_json(
 757             video['config_url'], video_id), video_id)
 758         get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
 759         info.update({
 760             'description': video.get('description'),
 761             'license': video.get('license'),
 762             'release_timestamp': get_timestamp('release'),
 763             'timestamp': get_timestamp('created'),
 764             'view_count': int_or_none(try_get(video, lambda x: x['stats']['plays'])),
 765         })
 766         connections = try_get(
 767             video, lambda x: x['metadata']['connections'], dict) or {}
 768         for k in ('comment', 'like'):
 769             info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total']))
 770         return info
 771
 772     def _try_album_password(self, url):
 773         album_id = self._search_regex(
 774             r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None)
 775         if not album_id:
 776             return
 777         viewer = self._download_json(
 778             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
 779         if not viewer:
 780             webpage = self._download_webpage(url, album_id)
 781             viewer = self._parse_json(self._search_regex(
 782                 r'bootstrap_data\s*=\s*({.+?})</script>',
 783                 webpage, 'bootstrap data'), album_id)['viewer']
 784         jwt = viewer['jwt']
 785         album = self._download_json(
 786             'https://api.vimeo.com/albums/' + album_id,
 787             album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
 788             query={'fields': 'description,name,privacy'})
 789         if try_get(album, lambda x: x['privacy']['view']) == 'password':
 790             password = self.get_param('videopassword')
 791             if not password:
 792                 raise ExtractorError(
 793                     'This album is protected by a password, use the --video-password option',
 794                     expected=True)
 795             self._set_vimeo_cookie('vuid', viewer['vuid'])
 796             try:
 797                 self._download_json(
 798                     'https://vimeo.com/showcase/%s/auth' % album_id,
 799                     album_id, 'Verifying the password', data=urlencode_postdata({
 800                         'password': password,
 801                         'token': viewer['xsrft'],
 802                     }), headers={
 803                         'X-Requested-With': 'XMLHttpRequest',
 804                     })
 805             except ExtractorError as e:
 806                 if isinstance(e.cause, HTTPError) and e.cause.status == 401:
 807                     raise ExtractorError('Wrong password', expected=True)
 808                 raise
 809
 810     def _real_extract(self, url):
 811         url, data, headers = self._unsmuggle_headers(url)
 812         if 'Referer' not in headers:
 813             headers['Referer'] = url
 814
 815         # Extract ID from URL
 816         mobj = self._match_valid_url(url).groupdict()
 817         video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash')
 818         if unlisted_hash:
 819             return self._extract_from_api(video_id, unlisted_hash)
 820
 821         if any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
 822             url = 'https://vimeo.com/' + video_id
 823
 824         self._try_album_password(url)
 825         try:
 826             # Retrieve video webpage to extract further information
 827             webpage, urlh = self._download_webpage_handle(
 828                 url, video_id, headers=headers)
 829             redirect_url = urlh.url
 830         except ExtractorError as ee:
 831             if isinstance(ee.cause, HTTPError) and ee.cause.status == 403:
 832                 errmsg = ee.cause.response.read()
 833                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 834                     raise ExtractorError(
 835                         'Cannot download embed-only video without embedding '
 836                         'URL. Please call yt-dlp with the URL of the page '
 837                         'that embeds this video.',
 838                         expected=True)
 839             raise
 840
 841         if '://player.vimeo.com/video/' in url:
 842             config = self._search_json(
 843                 r'\b(?:playerC|c)onfig\s*=', webpage, 'info section', video_id)
 844             if config.get('view') == 4:
 845                 config = self._verify_player_video_password(
 846                     redirect_url, video_id, headers)
 847             return self._parse_config(config, video_id)
 848
 849         if re.search(r'<form[^>]+?id="pw_form"', webpage):
 850             video_password = self._get_video_password()
 851             token, vuid = self._extract_xsrft_and_vuid(webpage)
 852             webpage = self._verify_video_password(
 853                 redirect_url, video_id, video_password, token, vuid)
 854
 855         vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
 856         if vimeo_config:
 857             seed_status = vimeo_config.get('seed_status') or {}
 858             if seed_status.get('state') == 'failed':
 859                 raise ExtractorError(
 860                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 861                     expected=True)
 862
 863         cc_license = None
 864         timestamp = None
 865         video_description = None
 866         info_dict = {}
 867         config_url = None
 868
 869         channel_id = self._search_regex(
 870             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
 871         if channel_id:
 872             config_url = self._html_search_regex(
 873                 r'\bdata-config-url="([^"]+)"', webpage, 'config URL', default=None)
 874             video_description = clean_html(get_element_by_class('description', webpage))
 875             info_dict.update({
 876                 'channel_id': channel_id,
 877                 'channel_url': 'https://vimeo.com/channels/' + channel_id,
 878             })
 879         if not config_url:
 880             page_config = self._parse_json(self._search_regex(
 881                 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
 882                 webpage, 'page config', default='{}'), video_id, fatal=False)
 883             if not page_config:
 884                 return self._extract_from_api(video_id)
 885             config_url = page_config['player']['config_url']
 886             cc_license = page_config.get('cc_license')
 887             clip = page_config.get('clip') or {}
 888             timestamp = clip.get('uploaded_on')
 889             video_description = clean_html(
 890                 clip.get('description') or page_config.get('description_html_escaped'))
 891         config = self._download_json(config_url, video_id)
 892         video = config.get('video') or {}
 893         vod = video.get('vod') or {}
 894
 895         def is_rented():
 896             if '>You rented this title.<' in webpage:
 897                 return True
 898             if try_get(config, lambda x: x['user']['purchased']):
 899                 return True
 900             for purchase_option in (vod.get('purchase_options') or []):
 901                 if purchase_option.get('purchased'):
 902                     return True
 903                 label = purchase_option.get('label_string')
 904                 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
 905                     return True
 906             return False
 907
 908         if is_rented() and vod.get('is_trailer'):
 909             feature_id = vod.get('feature_id')
 910             if feature_id and not data.get('force_feature_id', False):
 911                 return self.url_result(smuggle_url(
 912                     'https://player.vimeo.com/player/%s' % feature_id,
 913                     {'force_feature_id': True}), 'Vimeo')
 914
 915         if not video_description:
 916             video_description = self._html_search_regex(
 917                 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 918                 webpage, 'description', default=None)
 919         if not video_description:
 920             video_description = self._html_search_meta(
 921                 ['description', 'og:description', 'twitter:description'],
 922                 webpage, default=None)
 923         if not video_description:
 924             self.report_warning('Cannot find video description')
 925
 926         if not timestamp:
 927             timestamp = self._search_regex(
 928                 r'<time[^>]+datetime="([^"]+)"', webpage,
 929                 'timestamp', default=None)
 930
 931         view_count = int_or_none(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count', default=None))
 932         like_count = int_or_none(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count', default=None))
 933         comment_count = int_or_none(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count', default=None))
 934
 935         formats = []
 936
 937         source_format = self._extract_original_format(
 938             'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
 939         if source_format:
 940             formats.append(source_format)
 941
 942         info_dict_config = self._parse_config(config, video_id)
 943         formats.extend(info_dict_config['formats'])
 944         info_dict['_format_sort_fields'] = info_dict_config['_format_sort_fields']
 945
 946         json_ld = self._search_json_ld(webpage, video_id, default={})
 947
 948         if not cc_license:
 949             cc_license = self._search_regex(
 950                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
 951                 webpage, 'license', default=None, group='license')
 952
 953         info_dict.update({
 954             'formats': formats,
 955             'timestamp': unified_timestamp(timestamp),
 956             'description': video_description,
 957             'webpage_url': url,
 958             'view_count': view_count,
 959             'like_count': like_count,
 960             'comment_count': comment_count,
 961             'license': cc_license,
 962         })
 963
 964         return merge_dicts(info_dict, info_dict_config, json_ld)
 965
 966
 967 class VimeoOndemandIE(VimeoIE):  # XXX: Do not subclass from concrete IE
 968     IE_NAME = 'vimeo:ondemand'
 969     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)'
 970     _TESTS = [{
 971         # ondemand video not available via https://vimeo.com/id
 972         'url': 'https://vimeo.com/ondemand/20704',
 973         'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
 974         'info_dict': {
 975             'id': '105442900',
 976             'ext': 'mp4',
 977             'title': 'המעבדה - במאי יותם פלדמן',
 978             'uploader': 'גם סרטים',
 979             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
 980             'uploader_id': 'gumfilms',
 981             'description': 'md5:aeeba3dbd4d04b0fa98a4fdc9c639998',
 982             'upload_date': '20140906',
 983             'timestamp': 1410032453,
 984             'thumbnail': 'https://i.vimeocdn.com/video/488238335-d7bf151c364cff8d467f1b73784668fe60aae28a54573a35d53a1210ae283bd8-d_1280',
 985             'comment_count': int,
 986             'license': 'https://creativecommons.org/licenses/by-nc-nd/3.0/',
 987             'duration': 53,
 988             'view_count': int,
 989             'like_count': int,
 990         },
 991         'params': {
 992             'format': 'best[protocol=https]',
 993         },
 994         'expected_warnings': ['Unable to download JSON metadata'],
 995     }, {
 996         # requires Referer to be passed along with og:video:url
 997         'url': 'https://vimeo.com/ondemand/36938/126682985',
 998         'info_dict': {
 999             'id': '126584684',
1000             'ext': 'mp4',
1001             'title': 'Rävlock, rätt läte på rätt plats',
1002             'uploader': 'Lindroth & Norin',
1003             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
1004             'uploader_id': 'lindrothnorin',
1005             'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
1006             'upload_date': '20150502',
1007             'timestamp': 1430586422,
1008             'duration': 121,
1009             'comment_count': int,
1010             'view_count': int,
1011             'thumbnail': 'https://i.vimeocdn.com/video/517077723-7066ae1d9a79d3eb361334fb5d58ec13c8f04b52f8dd5eadfbd6fb0bcf11f613-d_1280',
1012             'like_count': int,
1013         },
1014         'params': {
1015             'skip_download': True,
1016         },
1017         'expected_warnings': ['Unable to download JSON metadata'],
1018     }, {
1019         'url': 'https://vimeo.com/ondemand/nazmaalik',
1020         'only_matching': True,
1021     }, {
1022         'url': 'https://vimeo.com/ondemand/141692381',
1023         'only_matching': True,
1024     }, {
1025         'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
1026         'only_matching': True,
1027     }]
1028
1029
1030 class VimeoChannelIE(VimeoBaseInfoExtractor):
1031     IE_NAME = 'vimeo:channel'
1032     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
1033     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
1034     _TITLE = None
1035     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
1036     _TESTS = [{
1037         'url': 'https://vimeo.com/channels/tributes',
1038         'info_dict': {
1039             'id': 'tributes',
1040             'title': 'Vimeo Tributes',
1041         },
1042         'playlist_mincount': 22,
1043     }]
1044     _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
1045
1046     def _page_url(self, base_url, pagenum):
1047         return '%s/videos/page:%d/' % (base_url, pagenum)
1048
1049     def _extract_list_title(self, webpage):
1050         return self._TITLE or self._html_search_regex(
1051             self._TITLE_RE, webpage, 'list title', fatal=False)
1052
1053     def _title_and_entries(self, list_id, base_url):
1054         for pagenum in itertools.count(1):
1055             page_url = self._page_url(base_url, pagenum)
1056             webpage = self._download_webpage(
1057                 page_url, list_id,
1058                 'Downloading page %s' % pagenum)
1059
1060             if pagenum == 1:
1061                 yield self._extract_list_title(webpage)
1062
1063             # Try extracting href first since not all videos are available via
1064             # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
1065             clips = re.findall(
1066                 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
1067             if clips:
1068                 for video_id, video_url, video_title in clips:
1069                     yield self.url_result(
1070                         compat_urlparse.urljoin(base_url, video_url),
1071                         VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
1072             # More relaxed fallback
1073             else:
1074                 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
1075                     yield self.url_result(
1076                         'https://vimeo.com/%s' % video_id,
1077                         VimeoIE.ie_key(), video_id=video_id)
1078
1079             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
1080                 break
1081
1082     def _extract_videos(self, list_id, base_url):
1083         title_and_entries = self._title_and_entries(list_id, base_url)
1084         list_title = next(title_and_entries)
1085         return self.playlist_result(title_and_entries, list_id, list_title)
1086
1087     def _real_extract(self, url):
1088         channel_id = self._match_id(url)
1089         return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
1090
1091
1092 class VimeoUserIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1093     IE_NAME = 'vimeo:user'
1094     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos)?/?(?:$|[?#])'
1095     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
1096     _TESTS = [{
1097         'url': 'https://vimeo.com/nkistudio/videos',
1098         'info_dict': {
1099             'title': 'Nki',
1100             'id': 'nkistudio',
1101         },
1102         'playlist_mincount': 66,
1103     }, {
1104         'url': 'https://vimeo.com/nkistudio/',
1105         'only_matching': True,
1106     }]
1107     _BASE_URL_TEMPL = 'https://vimeo.com/%s'
1108
1109
1110 class VimeoAlbumIE(VimeoBaseInfoExtractor):
1111     IE_NAME = 'vimeo:album'
1112     _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
1113     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
1114     _TESTS = [{
1115         'url': 'https://vimeo.com/album/2632481',
1116         'info_dict': {
1117             'id': '2632481',
1118             'title': 'Staff Favorites: November 2013',
1119         },
1120         'playlist_mincount': 13,
1121     }, {
1122         'note': 'Password-protected album',
1123         'url': 'https://vimeo.com/album/3253534',
1124         'info_dict': {
1125             'title': 'test',
1126             'id': '3253534',
1127         },
1128         'playlist_count': 1,
1129         'params': {
1130             'videopassword': 'youtube-dl',
1131         }
1132     }]
1133     _PAGE_SIZE = 100
1134
1135     def _fetch_page(self, album_id, authorization, hashed_pass, page):
1136         api_page = page + 1
1137         query = {
1138             'fields': 'link,uri',
1139             'page': api_page,
1140             'per_page': self._PAGE_SIZE,
1141         }
1142         if hashed_pass:
1143             query['_hashed_pass'] = hashed_pass
1144         try:
1145             videos = self._download_json(
1146                 'https://api.vimeo.com/albums/%s/videos' % album_id,
1147                 album_id, 'Downloading page %d' % api_page, query=query, headers={
1148                     'Authorization': 'jwt ' + authorization,
1149                     'Accept': 'application/json',
1150                 })['data']
1151         except ExtractorError as e:
1152             if isinstance(e.cause, HTTPError) and e.cause.status == 400:
1153                 return
1154             raise
1155         for video in videos:
1156             link = video.get('link')
1157             if not link:
1158                 continue
1159             uri = video.get('uri')
1160             video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
1161             yield self.url_result(link, VimeoIE.ie_key(), video_id)
1162
1163     def _real_extract(self, url):
1164         album_id = self._match_id(url)
1165         viewer = self._download_json(
1166             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
1167         if not viewer:
1168             webpage = self._download_webpage(url, album_id)
1169             viewer = self._parse_json(self._search_regex(
1170                 r'bootstrap_data\s*=\s*({.+?})</script>',
1171                 webpage, 'bootstrap data'), album_id)['viewer']
1172         jwt = viewer['jwt']
1173         album = self._download_json(
1174             'https://api.vimeo.com/albums/' + album_id,
1175             album_id, headers={'Authorization': 'jwt ' + jwt, 'Accept': 'application/json'},
1176             query={'fields': 'description,name,privacy'})
1177         hashed_pass = None
1178         if try_get(album, lambda x: x['privacy']['view']) == 'password':
1179             password = self.get_param('videopassword')
1180             if not password:
1181                 raise ExtractorError(
1182                     'This album is protected by a password, use the --video-password option',
1183                     expected=True)
1184             self._set_vimeo_cookie('vuid', viewer['vuid'])
1185             try:
1186                 hashed_pass = self._download_json(
1187                     'https://vimeo.com/showcase/%s/auth' % album_id,
1188                     album_id, 'Verifying the password', data=urlencode_postdata({
1189                         'password': password,
1190                         'token': viewer['xsrft'],
1191                     }), headers={
1192                         'X-Requested-With': 'XMLHttpRequest',
1193                     })['hashed_pass']
1194             except ExtractorError as e:
1195                 if isinstance(e.cause, HTTPError) and e.cause.status == 401:
1196                     raise ExtractorError('Wrong password', expected=True)
1197                 raise
1198         entries = OnDemandPagedList(functools.partial(
1199             self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
1200         return self.playlist_result(
1201             entries, album_id, album.get('name'), album.get('description'))
1202
1203
1204 class VimeoGroupsIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1205     IE_NAME = 'vimeo:group'
1206     _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
1207     _TESTS = [{
1208         'url': 'https://vimeo.com/groups/meetup',
1209         'info_dict': {
1210             'id': 'meetup',
1211             'title': 'Vimeo Meetup!',
1212         },
1213         'playlist_mincount': 27,
1214     }]
1215     _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
1216
1217
1218 class VimeoReviewIE(VimeoBaseInfoExtractor):
1219     IE_NAME = 'vimeo:review'
1220     IE_DESC = 'Review pages on vimeo'
1221     _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
1222     _TESTS = [{
1223         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1224         'md5': 'c507a72f780cacc12b2248bb4006d253',
1225         'info_dict': {
1226             'id': '75524534',
1227             'ext': 'mp4',
1228             'title': "DICK HARDWICK 'Comedian'",
1229             'uploader': 'Richard Hardwick',
1230             'uploader_id': 'user21297594',
1231             'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1232             'duration': 304,
1233             'thumbnail': 'https://i.vimeocdn.com/video/450115033-43303819d9ebe24c2630352e18b7056d25197d09b3ae901abdac4c4f1d68de71-d_1280',
1234             'uploader_url': 'https://vimeo.com/user21297594',
1235         },
1236     }, {
1237         'note': 'video player needs Referer',
1238         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1239         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1240         'info_dict': {
1241             'id': '91613211',
1242             'ext': 'mp4',
1243             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1244             'uploader': 'DevWeek Events',
1245             'duration': 2773,
1246             'thumbnail': r're:^https?://.*\.jpg$',
1247             'uploader_id': 'user22258446',
1248         },
1249         'skip': 'video gone',
1250     }, {
1251         'note': 'Password protected',
1252         'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1253         'info_dict': {
1254             'id': '138823582',
1255             'ext': 'mp4',
1256             'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1257             'uploader': 'TMB',
1258             'uploader_id': 'user37284429',
1259         },
1260         'params': {
1261             'videopassword': 'holygrail',
1262         },
1263         'skip': 'video gone',
1264     }]
1265
1266     def _real_extract(self, url):
1267         page_url, video_id = self._match_valid_url(url).groups()
1268         data = self._download_json(
1269             page_url.replace('/review/', '/review/data/'), video_id)
1270         if data.get('isLocked') is True:
1271             video_password = self._get_video_password()
1272             viewer = self._download_json(
1273                 'https://vimeo.com/_rv/viewer', video_id)
1274             webpage = self._verify_video_password(
1275                 'https://vimeo.com/' + video_id, video_id,
1276                 video_password, viewer['xsrft'], viewer['vuid'])
1277             clip_page_config = self._parse_json(self._search_regex(
1278                 r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
1279                 webpage, 'clip page config'), video_id)
1280             config_url = clip_page_config['player']['config_url']
1281             clip_data = clip_page_config.get('clip') or {}
1282         else:
1283             clip_data = data['clipData']
1284             config_url = clip_data['configUrl']
1285         config = self._download_json(config_url, video_id)
1286         info_dict = self._parse_config(config, video_id)
1287         source_format = self._extract_original_format(
1288             page_url + '/action', video_id)
1289         if source_format:
1290             info_dict['formats'].append(source_format)
1291         info_dict['description'] = clean_html(clip_data.get('description'))
1292         return info_dict
1293
1294
1295 class VimeoWatchLaterIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1296     IE_NAME = 'vimeo:watchlater'
1297     IE_DESC = 'Vimeo watch later list, ":vimeowatchlater" keyword (requires authentication)'
1298     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1299     _TITLE = 'Watch Later'
1300     _LOGIN_REQUIRED = True
1301     _TESTS = [{
1302         'url': 'https://vimeo.com/watchlater',
1303         'only_matching': True,
1304     }]
1305
1306     def _page_url(self, base_url, pagenum):
1307         url = '%s/page:%d/' % (base_url, pagenum)
1308         request = Request(url)
1309         # Set the header to get a partial html page with the ids,
1310         # the normal page doesn't contain them.
1311         request.headers['X-Requested-With'] = 'XMLHttpRequest'
1312         return request
1313
1314     def _real_extract(self, url):
1315         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1316
1317
1318 class VimeoLikesIE(VimeoChannelIE):  # XXX: Do not subclass from concrete IE
1319     _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1320     IE_NAME = 'vimeo:likes'
1321     IE_DESC = 'Vimeo user likes'
1322     _TESTS = [{
1323         'url': 'https://vimeo.com/user755559/likes/',
1324         'playlist_mincount': 293,
1325         'info_dict': {
1326             'id': 'user755559',
1327             'title': 'urza’s Likes',
1328         },
1329     }, {
1330         'url': 'https://vimeo.com/stormlapse/likes',
1331         'only_matching': True,
1332     }]
1333
1334     def _page_url(self, base_url, pagenum):
1335         return '%s/page:%d/' % (base_url, pagenum)
1336
1337     def _real_extract(self, url):
1338         user_id = self._match_id(url)
1339         return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
1340
1341
1342 class VHXEmbedIE(VimeoBaseInfoExtractor):
1343     IE_NAME = 'vhx:embed'
1344     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1345     _EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://embed\.vhx\.tv/videos/\d+[^"]*)"']
1346
1347     @classmethod
1348     def _extract_embed_urls(cls, url, webpage):
1349         for embed_url in super()._extract_embed_urls(url, webpage):
1350             yield cls._smuggle_referrer(embed_url, url)
1351
1352     def _real_extract(self, url):
1353         video_id = self._match_id(url)
1354         url, _, headers = self._unsmuggle_headers(url)
1355         webpage = self._download_webpage(url, video_id, headers=headers)
1356         config_url = self._parse_json(self._search_regex(
1357             r'window\.OTTData\s*=\s*({.+})', webpage,
1358             'ott data'), video_id, js_to_json)['config_url']
1359         config = self._download_json(config_url, video_id)
1360         info = self._parse_config(config, video_id)
1361         info['id'] = video_id
1362         return info
1363
1364
1365 class VimeoProIE(VimeoBaseInfoExtractor):
1366     IE_NAME = 'vimeo:pro'
1367     _VALID_URL = r'https?://(?:www\.)?vimeopro\.com/[^/?#]+/(?P<slug>[^/?#]+)(?:(?:/videos?/(?P<id>[0-9]+)))?'
1368     _TESTS = [{
1369         # Vimeo URL derived from video_id
1370         'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
1371         'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
1372         'note': 'Vimeo Pro video (#1197)',
1373         'info_dict': {
1374             'id': '68093876',
1375             'ext': 'mp4',
1376             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
1377             'uploader_id': 'openstreetmapus',
1378             'uploader': 'OpenStreetMap US',
1379             'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
1380             'description': 'md5:2c362968038d4499f4d79f88458590c1',
1381             'duration': 1595,
1382             'upload_date': '20130610',
1383             'timestamp': 1370893156,
1384             'license': 'by',
1385             'thumbnail': 'https://i.vimeocdn.com/video/440260469-19b0d92fca3bd84066623b53f1eb8aaa3980c6c809e2d67b6b39ab7b4a77a344-d_960',
1386             'view_count': int,
1387             'comment_count': int,
1388             'like_count': int,
1389             'tags': 'count:1',
1390         },
1391         'params': {
1392             'format': 'best[protocol=https]',
1393         },
1394     }, {
1395         # password-protected VimeoPro page with Vimeo player embed
1396         'url': 'https://vimeopro.com/cadfem/simulation-conference-mechanische-systeme-in-perfektion',
1397         'info_dict': {
1398             'id': '764543723',
1399             'ext': 'mp4',
1400             'title': 'Mechanische Systeme in Perfektion: Realität erfassen, Innovation treiben',
1401             'thumbnail': 'https://i.vimeocdn.com/video/1543784598-a1a750494a485e601110136b9fe11e28c2131942452b3a5d30391cb3800ca8fd-d_1280',
1402             'description': 'md5:2a9d195cd1b0f6f79827107dc88c2420',
1403             'uploader': 'CADFEM',
1404             'uploader_id': 'cadfem',
1405             'uploader_url': 'https://vimeo.com/cadfem',
1406             'duration': 12505,
1407             'chapters': 'count:10',
1408         },
1409         'params': {
1410             'videopassword': 'Conference2022',
1411             'skip_download': True,
1412         },
1413     }]
1414
1415     def _real_extract(self, url):
1416         display_id, video_id = self._match_valid_url(url).group('slug', 'id')
1417         if video_id:
1418             display_id = video_id
1419         webpage = self._download_webpage(url, display_id)
1420
1421         password_form = self._search_regex(
1422             r'(?is)<form[^>]+?method=["\']post["\'][^>]*>(.+?password.+?)</form>',
1423             webpage, 'password form', default=None)
1424         if password_form:
1425             try:
1426                 webpage = self._download_webpage(url, display_id, data=urlencode_postdata({
1427                     'password': self._get_video_password(),
1428                     **self._hidden_inputs(password_form),
1429                 }), note='Logging in with video password')
1430             except ExtractorError as e:
1431                 if isinstance(e.cause, HTTPError) and e.cause.status == 418:
1432                     raise ExtractorError('Wrong video password', expected=True)
1433                 raise
1434
1435         description = None
1436         # even if we have video_id, some videos require player URL with portfolio_id query param
1437         # https://github.com/ytdl-org/youtube-dl/issues/20070
1438         vimeo_url = VimeoIE._extract_url(url, webpage)
1439         if vimeo_url:
1440             description = self._html_search_meta('description', webpage, default=None)
1441         elif video_id:
1442             vimeo_url = f'https://vimeo.com/{video_id}'
1443         else:
1444             raise ExtractorError(
1445                 'No Vimeo embed or video ID could be found in VimeoPro page', expected=True)
1446
1447         return self.url_result(vimeo_url, VimeoIE, video_id, url_transparent=True,
1448                                description=description)