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 (
   8     compat_HTTPError,
   9     compat_str,
  10     compat_urlparse,
  11 )
  12 from ..utils import (
  13     clean_html,
  14     determine_ext,
  15     ExtractorError,
  16     get_element_by_class,
  17     HEADRequest,
  18     js_to_json,
  19     int_or_none,
  20     merge_dicts,
  21     OnDemandPagedList,
  22     parse_filesize,
  23     parse_iso8601,
  24     parse_qs,
  25     sanitized_Request,
  26     smuggle_url,
  27     str_or_none,
  28     try_get,
  29     unified_timestamp,
  30     unsmuggle_url,
  31     urlencode_postdata,
  32     urljoin,
  33     unescapeHTML,
  34     urlhandle_detect_ext,
  35 )
  36
  37
  38 class VimeoBaseInfoExtractor(InfoExtractor):
  39     _NETRC_MACHINE = 'vimeo'
  40     _LOGIN_REQUIRED = False
  41     _LOGIN_URL = 'https://vimeo.com/log_in'
  42
  43     @staticmethod
  44     def _smuggle_referrer(url, referrer_url):
  45         return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
  46
  47     def _unsmuggle_headers(self, url):
  48         """@returns (url, smuggled_data, headers)"""
  49         url, data = unsmuggle_url(url, {})
  50         headers = self.get_param('http_headers').copy()
  51         if 'http_headers' in data:
  52             headers.update(data['http_headers'])
  53         return url, data, headers
  54
  55     def _perform_login(self, username, password):
  56         webpage = self._download_webpage(
  57             self._LOGIN_URL, None, 'Downloading login page')
  58         token, vuid = self._extract_xsrft_and_vuid(webpage)
  59         data = {
  60             'action': 'login',
  61             'email': username,
  62             'password': password,
  63             'service': 'vimeo',
  64             'token': token,
  65         }
  66         self._set_vimeo_cookie('vuid', vuid)
  67         try:
  68             self._download_webpage(
  69                 self._LOGIN_URL, None, 'Logging in',
  70                 data=urlencode_postdata(data), headers={
  71                     'Content-Type': 'application/x-www-form-urlencoded',
  72                     'Referer': self._LOGIN_URL,
  73                 })
  74         except ExtractorError as e:
  75             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418:
  76                 raise ExtractorError(
  77                     'Unable to log in: bad username or password',
  78                     expected=True)
  79             raise ExtractorError('Unable to log in')
  80
  81     def _real_initialize(self):
  82         if self._LOGIN_REQUIRED and not self._get_cookies('https://vimeo.com').get('vuid'):
  83             self._raise_login_required()
  84
  85     def _get_video_password(self):
  86         password = self.get_param('videopassword')
  87         if password is None:
  88             raise ExtractorError(
  89                 'This video is protected by a password, use the --video-password option',
  90                 expected=True)
  91         return password
  92
  93     def _verify_video_password(self, url, video_id, password, token, vuid):
  94         if url.startswith('http://'):
  95             # vimeo only supports https now, but the user can give an http url
  96             url = url.replace('http://', 'https://')
  97         self._set_vimeo_cookie('vuid', vuid)
  98         return self._download_webpage(
  99             url + '/password', video_id, 'Verifying the password',
 100             'Wrong password', data=urlencode_postdata({
 101                 'password': password,
 102                 'token': token,
 103             }), headers={
 104                 'Content-Type': 'application/x-www-form-urlencoded',
 105                 'Referer': url,
 106             })
 107
 108     def _extract_xsrft_and_vuid(self, webpage):
 109         xsrft = self._search_regex(
 110             r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
 111             webpage, 'login token', group='xsrft')
 112         vuid = self._search_regex(
 113             r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
 114             webpage, 'vuid', group='vuid')
 115         return xsrft, vuid
 116
 117     def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
 118         vimeo_config = self._search_regex(
 119             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
 120             webpage, 'vimeo config', *args, **kwargs)
 121         if vimeo_config:
 122             return self._parse_json(vimeo_config, video_id)
 123
 124     def _set_vimeo_cookie(self, name, value):
 125         self._set_cookie('vimeo.com', name, value)
 126
 127     def _vimeo_sort_formats(self, formats):
 128         # Note: Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
 129         # at the same time without actual units specified.
 130         self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source'))
 131
 132     def _parse_config(self, config, video_id):
 133         video_data = config['video']
 134         video_title = video_data.get('title')
 135         live_event = video_data.get('live_event') or {}
 136         is_live = live_event.get('status') == 'started'
 137         request = config.get('request') or {}
 138
 139         formats = []
 140         subtitles = {}
 141
 142         config_files = video_data.get('files') or request.get('files') or {}
 143         for f in (config_files.get('progressive') or []):
 144             video_url = f.get('url')
 145             if not video_url:
 146                 continue
 147             formats.append({
 148                 'url': video_url,
 149                 'format_id': 'http-%s' % f.get('quality'),
 150                 'source_preference': 10,
 151                 'width': int_or_none(f.get('width')),
 152                 'height': int_or_none(f.get('height')),
 153                 'fps': int_or_none(f.get('fps')),
 154                 'tbr': int_or_none(f.get('bitrate')),
 155             })
 156
 157         # TODO: fix handling of 308 status code returned for live archive manifest requests
 158         sep_pattern = r'/sep/video/'
 159         for files_type in ('hls', 'dash'):
 160             for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items():
 161                 manifest_url = cdn_data.get('url')
 162                 if not manifest_url:
 163                     continue
 164                 format_id = '%s-%s' % (files_type, cdn_name)
 165                 sep_manifest_urls = []
 166                 if re.search(sep_pattern, manifest_url):
 167                     for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
 168                         sep_manifest_urls.append((format_id + suffix, re.sub(
 169                             sep_pattern, '/%s/' % repl, manifest_url)))
 170                 else:
 171                     sep_manifest_urls = [(format_id, manifest_url)]
 172                 for f_id, m_url in sep_manifest_urls:
 173                     if files_type == 'hls':
 174                         fmts, subs = self._extract_m3u8_formats_and_subtitles(
 175                             m_url, video_id, 'mp4', live=is_live, m3u8_id=f_id,
 176                             note='Downloading %s m3u8 information' % cdn_name,
 177                             fatal=False)
 178                         formats.extend(fmts)
 179                         self._merge_subtitles(subs, target=subtitles)
 180                     elif files_type == 'dash':
 181                         if 'json=1' in m_url:
 182                             real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
 183                             if real_m_url:
 184                                 m_url = real_m_url
 185                         fmts, subs = self._extract_mpd_formats_and_subtitles(
 186                             m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
 187                             'Downloading %s MPD information' % cdn_name,
 188                             fatal=False)
 189                         formats.extend(fmts)
 190                         self._merge_subtitles(subs, target=subtitles)
 191
 192         live_archive = live_event.get('archive') or {}
 193         live_archive_source_url = live_archive.get('source_url')
 194         if live_archive_source_url and live_archive.get('status') == 'done':
 195             formats.append({
 196                 'format_id': 'live-archive-source',
 197                 'url': live_archive_source_url,
 198                 'quality': 10,
 199             })
 200
 201         for tt in (request.get('text_tracks') or []):
 202             subtitles.setdefault(tt['lang'], []).append({
 203                 'ext': 'vtt',
 204                 'url': urljoin('https://vimeo.com', tt['url']),
 205             })
 206
 207         thumbnails = []
 208         if not is_live:
 209             for key, thumb in (video_data.get('thumbs') or {}).items():
 210                 thumbnails.append({
 211                     'id': key,
 212                     'width': int_or_none(key),
 213                     'url': thumb,
 214                 })
 215             thumbnail = video_data.get('thumbnail')
 216             if thumbnail:
 217                 thumbnails.append({
 218                     'url': thumbnail,
 219                 })
 220
 221         owner = video_data.get('owner') or {}
 222         video_uploader_url = owner.get('url')
 223
 224         duration = int_or_none(video_data.get('duration'))
 225         chapter_data = try_get(config, lambda x: x['embed']['chapters']) or []
 226         chapters = [{
 227             'title': current_chapter.get('title'),
 228             'start_time': current_chapter.get('timecode'),
 229             'end_time': next_chapter.get('timecode'),
 230         } for current_chapter, next_chapter in zip(chapter_data, chapter_data[1:] + [{'timecode': duration}])]
 231         if chapters and chapters[0]['start_time']:  # Chapters may not start from 0
 232             chapters[:0] = [{'title': '<Untitled>', 'start_time': 0, 'end_time': chapters[0]['start_time']}]
 233
 234         return {
 235             'id': str_or_none(video_data.get('id')) or video_id,
 236             'title': video_title,
 237             'uploader': owner.get('name'),
 238             'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
 239             'uploader_url': video_uploader_url,
 240             'thumbnails': thumbnails,
 241             'duration': duration,
 242             'chapters': chapters or None,
 243             'formats': formats,
 244             'subtitles': subtitles,
 245             'is_live': is_live,
 246         }
 247
 248     def _extract_original_format(self, url, video_id, unlisted_hash=None):
 249         query = {'action': 'load_download_config'}
 250         if unlisted_hash:
 251             query['unlisted_hash'] = unlisted_hash
 252         download_data = self._download_json(
 253             url, video_id, fatal=False, query=query,
 254             headers={'X-Requested-With': 'XMLHttpRequest'},
 255             expected_status=(403, 404)) or {}
 256         source_file = download_data.get('source_file')
 257         download_url = try_get(source_file, lambda x: x['download_url'])
 258         if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 259             source_name = source_file.get('public_name', 'Original')
 260             if self._is_valid_url(download_url, video_id, '%s video' % source_name):
 261                 ext = (try_get(
 262                     source_file, lambda x: x['extension'],
 263                     compat_str) or determine_ext(
 264                     download_url, None) or 'mp4').lower()
 265                 return {
 266                     'url': download_url,
 267                     'ext': ext,
 268                     'width': int_or_none(source_file.get('width')),
 269                     'height': int_or_none(source_file.get('height')),
 270                     'filesize': parse_filesize(source_file.get('size')),
 271                     'format_id': source_name,
 272                     'quality': 1,
 273                 }
 274
 275         jwt_response = self._download_json(
 276             'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {}
 277         if not jwt_response.get('jwt'):
 278             return
 279         headers = {'Authorization': 'jwt %s' % jwt_response['jwt']}
 280         original_response = self._download_json(
 281             f'https://api.vimeo.com/videos/{video_id}', video_id,
 282             headers=headers, fatal=False, expected_status=(403, 404)) or {}
 283         for download_data in original_response.get('download') or []:
 284             download_url = download_data.get('link')
 285             if not download_url or download_data.get('quality') != 'source':
 286                 continue
 287             ext = determine_ext(parse_qs(download_url).get('filename', [''])[0].lower(), default_ext=None)
 288             if not ext:
 289                 urlh = self._request_webpage(
 290                     HEADRequest(download_url), video_id, fatal=False, note='Determining source extension')
 291                 ext = urlh and urlhandle_detect_ext(urlh)
 292             return {
 293                 'url': download_url,
 294                 'ext': ext or 'unknown_video',
 295                 'format_id': download_data.get('public_name', 'Original'),
 296                 'width': int_or_none(download_data.get('width')),
 297                 'height': int_or_none(download_data.get('height')),
 298                 'fps': int_or_none(download_data.get('fps')),
 299                 'filesize': int_or_none(download_data.get('size')),
 300                 'quality': 1,
 301             }
 302
 303
 304 class VimeoIE(VimeoBaseInfoExtractor):
 305     """Information extractor for vimeo.com."""
 306
 307     # _VALID_URL matches Vimeo URLs
 308     _VALID_URL = r'''(?x)
 309                     https?://
 310                         (?:
 311                             (?:
 312                                 www|
 313                                 player
 314                             )
 315                             \.
 316                         )?
 317                         vimeo(?:pro)?\.com/
 318                         (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
 319                         (?:[^/]+/)*?
 320                         (?:
 321                             (?:
 322                                 play_redirect_hls|
 323                                 moogaloop\.swf)\?clip_id=
 324                             )?
 325                         (?:videos?/)?
 326                         (?P<id>[0-9]+)
 327                         (?:/(?P<unlisted_hash>[\da-f]{10}))?
 328                         /?(?:[?&].*)?(?:[#].*)?$
 329                     '''
 330     IE_NAME = 'vimeo'
 331     _TESTS = [
 332         {
 333             'url': 'http://vimeo.com/56015672#at=0',
 334             'md5': '8879b6cc097e987f02484baf890129e5',
 335             'info_dict': {
 336                 'id': '56015672',
 337                 'ext': 'mp4',
 338                 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
 339                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
 340                 'timestamp': 1355990239,
 341                 'upload_date': '20121220',
 342                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
 343                 'uploader_id': 'user7108434',
 344                 'uploader': 'Filippo Valsorda',
 345                 'duration': 10,
 346                 'license': 'by-sa',
 347             },
 348             'params': {
 349                 'format': 'best[protocol=https]',
 350             },
 351             'skip': 'No longer available'
 352         },
 353         {
 354             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
 355             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
 356             'note': 'Vimeo Pro video (#1197)',
 357             'info_dict': {
 358                 'id': '68093876',
 359                 'ext': 'mp4',
 360                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
 361                 'uploader_id': 'openstreetmapus',
 362                 'uploader': 'OpenStreetMap US',
 363                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 364                 'description': 'md5:2c362968038d4499f4d79f88458590c1',
 365                 'duration': 1595,
 366                 'upload_date': '20130610',
 367                 'timestamp': 1370893156,
 368                 'license': 'by',
 369                 'thumbnail': 'https://i.vimeocdn.com/video/440260469-19b0d92fca3bd84066623b53f1eb8aaa3980c6c809e2d67b6b39ab7b4a77a344-d_960',
 370                 'view_count': int,
 371                 'comment_count': int,
 372                 'like_count': int,
 373             },
 374             'params': {
 375                 'format': 'best[protocol=https]',
 376             },
 377         },
 378         {
 379             'url': 'http://player.vimeo.com/video/54469442',
 380             'md5': 'b3e7f4d2cbb53bd7dc3bb6ff4ed5cfbd',
 381             'note': 'Videos that embed the url in the player page',
 382             'info_dict': {
 383                 'id': '54469442',
 384                 'ext': 'mp4',
 385                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 386                 'uploader': 'Business of Software',
 387                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
 388                 'uploader_id': 'businessofsoftware',
 389                 'duration': 3610,
 390                 'description': None,
 391                 'thumbnail': 'https://i.vimeocdn.com/video/376682406-f34043e7b766af6bef2af81366eacd6724f3fc3173179a11a97a1e26587c9529-d_1280',
 392             },
 393             'params': {
 394                 'format': 'best[protocol=https]',
 395             },
 396         },
 397         {
 398             'url': 'http://vimeo.com/68375962',
 399             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 400             'note': 'Video protected with password',
 401             'info_dict': {
 402                 'id': '68375962',
 403                 'ext': 'mp4',
 404                 'title': 'youtube-dl password protected test video',
 405                 'timestamp': 1371200155,
 406                 'upload_date': '20130614',
 407                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 408                 'uploader_id': 'user18948128',
 409                 'uploader': 'Jaime Marquínez Ferrándiz',
 410                 'duration': 10,
 411                 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
 412                 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_960',
 413                 'view_count': int,
 414                 'comment_count': int,
 415                 'like_count': int,
 416             },
 417             'params': {
 418                 'format': 'best[protocol=https]',
 419                 'videopassword': 'youtube-dl',
 420             },
 421         },
 422         {
 423             'url': 'http://vimeo.com/channels/keypeele/75629013',
 424             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 425             'info_dict': {
 426                 'id': '75629013',
 427                 'ext': 'mp4',
 428                 'title': 'Key & Peele: Terrorist Interrogation',
 429                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 430                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
 431                 'uploader_id': 'atencio',
 432                 'uploader': 'Peter Atencio',
 433                 'channel_id': 'keypeele',
 434                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
 435                 'timestamp': 1380339469,
 436                 'upload_date': '20130928',
 437                 'duration': 187,
 438                 'thumbnail': 'https://i.vimeocdn.com/video/450239872-a05512d9b1e55d707a7c04365c10980f327b06d966351bc403a5d5d65c95e572-d_1280',
 439                 'view_count': int,
 440                 'comment_count': int,
 441                 'like_count': int,
 442             },
 443             'params': {'format': 'http-1080p'},
 444         },
 445         {
 446             'url': 'http://vimeo.com/76979871',
 447             'note': 'Video with subtitles',
 448             'info_dict': {
 449                 'id': '76979871',
 450                 'ext': 'mov',
 451                 'title': 'The New Vimeo Player (You Know, For Videos)',
 452                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 453                 'timestamp': 1381846109,
 454                 'upload_date': '20131015',
 455                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
 456                 'uploader_id': 'staff',
 457                 'uploader': 'Vimeo Staff',
 458                 'duration': 62,
 459                 'subtitles': {
 460                     'de': [{'ext': 'vtt'}],
 461                     'en': [{'ext': 'vtt'}],
 462                     'es': [{'ext': 'vtt'}],
 463                     'fr': [{'ext': 'vtt'}],
 464                 },
 465             },
 466             'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
 467         },
 468         {
 469             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 470             'url': 'https://player.vimeo.com/video/98044508',
 471             'note': 'The js code contains assignments to the same variable as the config',
 472             'info_dict': {
 473                 'id': '98044508',
 474                 'ext': 'mp4',
 475                 'title': 'Pier Solar OUYA Official Trailer',
 476                 'uploader': 'Tulio Gonçalves',
 477                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
 478                 'uploader_id': 'user28849593',
 479                 'duration': 118,
 480                 'thumbnail': 'https://i.vimeocdn.com/video/478636036-c18440305ef3df9decfb6bf207a61fe39d2d17fa462a96f6f2d93d30492b037d-d_1280',
 481             },
 482         },
 483         {
 484             # contains original format
 485             'url': 'https://vimeo.com/33951933',
 486             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 487             'info_dict': {
 488                 'id': '33951933',
 489                 'ext': 'mp4',
 490                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 491                 'uploader': 'The DMCI',
 492                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
 493                 'uploader_id': 'dmci',
 494                 'timestamp': 1324343742,
 495                 'upload_date': '20111220',
 496                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 497                 'duration': 60,
 498                 'comment_count': int,
 499                 'view_count': int,
 500                 'thumbnail': 'https://i.vimeocdn.com/video/231174622-dd07f015e9221ff529d451e1cc31c982b5d87bfafa48c4189b1da72824ee289a-d_1280',
 501                 'like_count': int,
 502             },
 503         },
 504         {
 505             'note': 'Contains original format not accessible in webpage',
 506             'url': 'https://vimeo.com/393756517',
 507             'md5': 'c464af248b592190a5ffbb5d33f382b0',
 508             'info_dict': {
 509                 'id': '393756517',
 510                 'ext': 'mov',
 511                 'timestamp': 1582642091,
 512                 'uploader_id': 'frameworkla',
 513                 'title': 'Straight To Hell - Sabrina: Netflix',
 514                 'uploader': 'Framework Studio',
 515                 'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
 516                 'upload_date': '20200225',
 517                 'duration': 176,
 518                 'thumbnail': 'https://i.vimeocdn.com/video/859377297-836494a4ef775e9d4edbace83937d9ad34dc846c688c0c419c0e87f7ab06c4b3-d_1280',
 519                 'uploader_url': 'https://vimeo.com/frameworkla',
 520             },
 521         },
 522         {
 523             # only available via https://vimeo.com/channels/tributes/6213729 and
 524             # not via https://vimeo.com/6213729
 525             'url': 'https://vimeo.com/channels/tributes/6213729',
 526             'info_dict': {
 527                 'id': '6213729',
 528                 'ext': 'mp4',
 529                 'title': 'Vimeo Tribute: The Shining',
 530                 'uploader': 'Casey Donahue',
 531                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
 532                 'uploader_id': 'caseydonahue',
 533                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
 534                 'channel_id': 'tributes',
 535                 'timestamp': 1250886430,
 536                 'upload_date': '20090821',
 537                 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
 538                 'duration': 321,
 539                 'comment_count': int,
 540                 'view_count': int,
 541                 'thumbnail': 'https://i.vimeocdn.com/video/22728298-bfc22146f930de7cf497821c7b0b9f168099201ecca39b00b6bd31fcedfca7a6-d_1280',
 542                 'like_count': int,
 543             },
 544             'params': {
 545                 'skip_download': True,
 546             },
 547         },
 548         {
 549             # redirects to ondemand extractor and should be passed through it
 550             # for successful extraction
 551             'url': 'https://vimeo.com/73445910',
 552             'info_dict': {
 553                 'id': '73445910',
 554                 'ext': 'mp4',
 555                 'title': 'The Reluctant Revolutionary',
 556                 'uploader': '10Ft Films',
 557                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
 558                 'uploader_id': 'tenfootfilms',
 559                 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
 560                 'upload_date': '20130830',
 561                 'timestamp': 1377853339,
 562             },
 563             'params': {
 564                 'skip_download': True,
 565             },
 566             'skip': 'this page is no longer available.',
 567         },
 568         {
 569             'url': 'http://player.vimeo.com/video/68375962',
 570             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 571             'info_dict': {
 572                 'id': '68375962',
 573                 'ext': 'mp4',
 574                 'title': 'youtube-dl password protected test video',
 575                 'timestamp': 1371200155,
 576                 'upload_date': '20130614',
 577                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 578                 'uploader_id': 'user18948128',
 579                 'uploader': 'Jaime Marquínez Ferrándiz',
 580                 'duration': 10,
 581                 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
 582                 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_960',
 583                 'view_count': int,
 584                 'comment_count': int,
 585                 'like_count': int,
 586             },
 587             'params': {
 588                 'format': 'best[protocol=https]',
 589                 'videopassword': 'youtube-dl',
 590             },
 591         },
 592         {
 593             'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
 594             'only_matching': True,
 595         },
 596         {
 597             'url': 'https://vimeo.com/109815029',
 598             'note': 'Video not completely processed, "failed" seed status',
 599             'only_matching': True,
 600         },
 601         {
 602             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 603             'only_matching': True,
 604         },
 605         {
 606             'url': 'https://vimeo.com/album/2632481/video/79010983',
 607             'only_matching': True,
 608         },
 609         {
 610             'url': 'https://vimeo.com/showcase/3253534/video/119195465',
 611             'note': 'A video in a password protected album (showcase)',
 612             'info_dict': {
 613                 'id': '119195465',
 614                 'ext': 'mp4',
 615                 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
 616                 'uploader': 'Philipp Hagemeister',
 617                 'uploader_id': 'user20132939',
 618                 'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
 619                 'upload_date': '20150209',
 620                 'timestamp': 1423518307,
 621                 'thumbnail': 'https://i.vimeocdn.com/video/default_1280',
 622                 'duration': 10,
 623                 'like_count': int,
 624                 'uploader_url': 'https://vimeo.com/user20132939',
 625                 'view_count': int,
 626                 'comment_count': int,
 627             },
 628             'params': {
 629                 'format': 'best[protocol=https]',
 630                 'videopassword': 'youtube-dl',
 631             },
 632         },
 633         {
 634             # source file returns 403: Forbidden
 635             'url': 'https://vimeo.com/7809605',
 636             'only_matching': True,
 637         },
 638         {
 639             'note': 'Direct URL with hash',
 640             'url': 'https://vimeo.com/160743502/abd0e13fb4',
 641             'info_dict': {
 642                 'id': '160743502',
 643                 'ext': 'mp4',
 644                 'uploader': 'Julian Tryba',
 645                 'uploader_id': 'aliniamedia',
 646                 'title': 'Harrisville New Hampshire',
 647                 'timestamp': 1459259666,
 648                 'upload_date': '20160329',
 649                 'release_timestamp': 1459259666,
 650                 'license': 'by-nc',
 651                 'duration': 159,
 652                 'comment_count': int,
 653                 'thumbnail': 'https://i.vimeocdn.com/video/562802436-585eeb13b5020c6ac0f171a2234067938098f84737787df05ff0d767f6d54ee9-d_1280',
 654                 'like_count': int,
 655                 'uploader_url': 'https://vimeo.com/aliniamedia',
 656                 'release_date': '20160329',
 657             },
 658             'params': {'skip_download': True},
 659         },
 660         {
 661             'url': 'https://vimeo.com/138909882',
 662             'info_dict': {
 663                 'id': '138909882',
 664                 'ext': 'mp4',
 665                 'title': 'Eastnor Castle 2015 Firework Champions - The Promo!',
 666                 'description': 'md5:5967e090768a831488f6e74b7821b3c1',
 667                 'uploader_id': 'fireworkchampions',
 668                 'uploader': 'Firework Champions',
 669                 'upload_date': '20150910',
 670                 'timestamp': 1441901895,
 671             },
 672             'params': {
 673                 'skip_download': True,
 674                 'format': 'Original',
 675             },
 676         },
 677         {
 678             'url': 'https://vimeo.com/channels/staffpicks/143603739',
 679             'info_dict': {
 680                 'id': '143603739',
 681                 'ext': 'mp4',
 682                 'uploader': 'Karim Huu Do',
 683                 'timestamp': 1445846953,
 684                 'upload_date': '20151026',
 685                 'title': 'The Shoes - Submarine Feat. Blaine Harrison',
 686                 'uploader_id': 'karimhd',
 687                 'description': 'md5:8e2eea76de4504c2e8020a9bcfa1e843',
 688                 'channel_id': 'staffpicks',
 689                 'duration': 336,
 690                 'comment_count': int,
 691                 'view_count': int,
 692                 'thumbnail': 'https://i.vimeocdn.com/video/541243181-b593db36a16db2f0096f655da3f5a4dc46b8766d77b0f440df937ecb0c418347-d_1280',
 693                 'like_count': int,
 694                 'uploader_url': 'https://vimeo.com/karimhd',
 695                 'channel_url': 'https://vimeo.com/channels/staffpicks',
 696             },
 697             'params': {'skip_download': 'm3u8'},
 698         },
 699         {
 700             # requires passing unlisted_hash(a52724358e) to load_download_config request
 701             'url': 'https://vimeo.com/392479337/a52724358e',
 702             'only_matching': True,
 703         },
 704         {
 705             # similar, but all numeric: ID must be 581039021, not 9603038895
 706             # issue #29690
 707             'url': 'https://vimeo.com/581039021/9603038895',
 708             'info_dict': {
 709                 'id': '581039021',
 710                 'ext': 'mp4',
 711                 'timestamp': 1627621014,
 712                 'release_timestamp': 1627621014,
 713                 'duration': 976,
 714                 'comment_count': int,
 715                 'thumbnail': 'https://i.vimeocdn.com/video/1202249320-4ddb2c30398c0dc0ee059172d1bd5ea481ad12f0e0e3ad01d2266f56c744b015-d_1280',
 716                 'like_count': int,
 717                 'uploader_url': 'https://vimeo.com/txwestcapital',
 718                 'release_date': '20210730',
 719                 'uploader': 'Christopher Inks',
 720                 'title': 'Thursday, July 29, 2021 BMA Evening Video Update',
 721                 'uploader_id': 'txwestcapital',
 722                 'upload_date': '20210730',
 723             },
 724             'params': {
 725                 'skip_download': True,
 726             },
 727         }
 728         # https://gettingthingsdone.com/workflowmap/
 729         # vimeo embed with check-password page protected by Referer header
 730     ]
 731
 732     @staticmethod
 733     def _extract_urls(url, webpage):
 734         urls = []
 735         # Look for embedded (iframe) Vimeo player
 736         for mobj in re.finditer(
 737                 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
 738                 webpage):
 739             urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
 740         PLAIN_EMBED_RE = (
 741             # Look for embedded (swf embed) Vimeo player
 742             r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
 743             # Look more for non-standard embedded Vimeo player
 744             r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
 745         )
 746         for embed_re in PLAIN_EMBED_RE:
 747             for mobj in re.finditer(embed_re, webpage):
 748                 urls.append(mobj.group('url'))
 749         return urls
 750
 751     @staticmethod
 752     def _extract_url(url, webpage):
 753         urls = VimeoIE._extract_urls(url, webpage)
 754         return urls[0] if urls else None
 755
 756     def _verify_player_video_password(self, url, video_id, headers):
 757         password = self._get_video_password()
 758         data = urlencode_postdata({
 759             'password': base64.b64encode(password.encode()),
 760         })
 761         headers = merge_dicts(headers, {
 762             'Content-Type': 'application/x-www-form-urlencoded',
 763         })
 764         checked = self._download_json(
 765             f'{compat_urlparse.urlsplit(url)._replace(query=None).geturl()}/check-password',
 766             video_id, 'Verifying the password', data=data, headers=headers)
 767         if checked is False:
 768             raise ExtractorError('Wrong video password', expected=True)
 769         return checked
 770
 771     def _extract_from_api(self, video_id, unlisted_hash=None):
 772         token = self._download_json(
 773             'https://vimeo.com/_rv/jwt', video_id, headers={
 774                 'X-Requested-With': 'XMLHttpRequest'
 775             })['token']
 776         api_url = 'https://api.vimeo.com/videos/' + video_id
 777         if unlisted_hash:
 778             api_url += ':' + unlisted_hash
 779         video = self._download_json(
 780             api_url, video_id, headers={
 781                 'Authorization': 'jwt ' + token,
 782             }, query={
 783                 'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
 784             })
 785         info = self._parse_config(self._download_json(
 786             video['config_url'], video_id), video_id)
 787         self._vimeo_sort_formats(info['formats'])
 788         get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
 789         info.update({
 790             'description': video.get('description'),
 791             'license': video.get('license'),
 792             'release_timestamp': get_timestamp('release'),
 793             'timestamp': get_timestamp('created'),
 794             'view_count': int_or_none(try_get(video, lambda x: x['stats']['plays'])),
 795         })
 796         connections = try_get(
 797             video, lambda x: x['metadata']['connections'], dict) or {}
 798         for k in ('comment', 'like'):
 799             info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total']))
 800         return info
 801
 802     def _try_album_password(self, url):
 803         album_id = self._search_regex(
 804             r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None)
 805         if not album_id:
 806             return
 807         viewer = self._download_json(
 808             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
 809         if not viewer:
 810             webpage = self._download_webpage(url, album_id)
 811             viewer = self._parse_json(self._search_regex(
 812                 r'bootstrap_data\s*=\s*({.+?})</script>',
 813                 webpage, 'bootstrap data'), album_id)['viewer']
 814         jwt = viewer['jwt']
 815         album = self._download_json(
 816             'https://api.vimeo.com/albums/' + album_id,
 817             album_id, headers={'Authorization': 'jwt ' + jwt},
 818             query={'fields': 'description,name,privacy'})
 819         if try_get(album, lambda x: x['privacy']['view']) == 'password':
 820             password = self.get_param('videopassword')
 821             if not password:
 822                 raise ExtractorError(
 823                     'This album is protected by a password, use the --video-password option',
 824                     expected=True)
 825             self._set_vimeo_cookie('vuid', viewer['vuid'])
 826             try:
 827                 self._download_json(
 828                     'https://vimeo.com/showcase/%s/auth' % album_id,
 829                     album_id, 'Verifying the password', data=urlencode_postdata({
 830                         'password': password,
 831                         'token': viewer['xsrft'],
 832                     }), headers={
 833                         'X-Requested-With': 'XMLHttpRequest',
 834                     })
 835             except ExtractorError as e:
 836                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
 837                     raise ExtractorError('Wrong password', expected=True)
 838                 raise
 839
 840     def _real_extract(self, url):
 841         url, data, headers = self._unsmuggle_headers(url)
 842         if 'Referer' not in headers:
 843             headers['Referer'] = url
 844
 845         # Extract ID from URL
 846         mobj = self._match_valid_url(url).groupdict()
 847         video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash')
 848         if unlisted_hash:
 849             return self._extract_from_api(video_id, unlisted_hash)
 850
 851         orig_url = url
 852         is_pro = 'vimeopro.com/' in url
 853         if is_pro:
 854             # some videos require portfolio_id to be present in player url
 855             # https://github.com/ytdl-org/youtube-dl/issues/20070
 856             url = self._extract_url(url, self._download_webpage(url, video_id))
 857             if not url:
 858                 url = 'https://vimeo.com/' + video_id
 859         elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
 860             url = 'https://vimeo.com/' + video_id
 861
 862         self._try_album_password(url)
 863         try:
 864             # Retrieve video webpage to extract further information
 865             webpage, urlh = self._download_webpage_handle(
 866                 url, video_id, headers=headers)
 867             redirect_url = urlh.geturl()
 868         except ExtractorError as ee:
 869             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 870                 errmsg = ee.cause.read()
 871                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 872                     raise ExtractorError(
 873                         'Cannot download embed-only video without embedding '
 874                         'URL. Please call yt-dlp with the URL of the page '
 875                         'that embeds this video.',
 876                         expected=True)
 877             raise
 878
 879         if '://player.vimeo.com/video/' in url:
 880             config = self._parse_json(self._search_regex(
 881                 r'\bconfig\s*=\s*({.+?})\s*;', webpage, 'info section'), video_id)
 882             if config.get('view') == 4:
 883                 config = self._verify_player_video_password(
 884                     redirect_url, video_id, headers)
 885             info = self._parse_config(config, video_id)
 886             self._vimeo_sort_formats(info['formats'])
 887             return info
 888
 889         if re.search(r'<form[^>]+?id="pw_form"', webpage):
 890             video_password = self._get_video_password()
 891             token, vuid = self._extract_xsrft_and_vuid(webpage)
 892             webpage = self._verify_video_password(
 893                 redirect_url, video_id, video_password, token, vuid)
 894
 895         vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
 896         if vimeo_config:
 897             seed_status = vimeo_config.get('seed_status') or {}
 898             if seed_status.get('state') == 'failed':
 899                 raise ExtractorError(
 900                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 901                     expected=True)
 902
 903         cc_license = None
 904         timestamp = None
 905         video_description = None
 906         info_dict = {}
 907         config_url = None
 908
 909         channel_id = self._search_regex(
 910             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
 911         if channel_id:
 912             config_url = self._html_search_regex(
 913                 r'\bdata-config-url="([^"]+)"', webpage, 'config URL', default=None)
 914             video_description = clean_html(get_element_by_class('description', webpage))
 915             info_dict.update({
 916                 'channel_id': channel_id,
 917                 'channel_url': 'https://vimeo.com/channels/' + channel_id,
 918             })
 919         if not config_url:
 920             page_config = self._parse_json(self._search_regex(
 921                 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
 922                 webpage, 'page config', default='{}'), video_id, fatal=False)
 923             if not page_config:
 924                 return self._extract_from_api(video_id)
 925             config_url = page_config['player']['config_url']
 926             cc_license = page_config.get('cc_license')
 927             clip = page_config.get('clip') or {}
 928             timestamp = clip.get('uploaded_on')
 929             video_description = clean_html(
 930                 clip.get('description') or page_config.get('description_html_escaped'))
 931         config = self._download_json(config_url, video_id)
 932         video = config.get('video') or {}
 933         vod = video.get('vod') or {}
 934
 935         def is_rented():
 936             if '>You rented this title.<' in webpage:
 937                 return True
 938             if try_get(config, lambda x: x['user']['purchased']):
 939                 return True
 940             for purchase_option in (vod.get('purchase_options') or []):
 941                 if purchase_option.get('purchased'):
 942                     return True
 943                 label = purchase_option.get('label_string')
 944                 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
 945                     return True
 946             return False
 947
 948         if is_rented() and vod.get('is_trailer'):
 949             feature_id = vod.get('feature_id')
 950             if feature_id and not data.get('force_feature_id', False):
 951                 return self.url_result(smuggle_url(
 952                     'https://player.vimeo.com/player/%s' % feature_id,
 953                     {'force_feature_id': True}), 'Vimeo')
 954
 955         if not video_description:
 956             video_description = self._html_search_regex(
 957                 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 958                 webpage, 'description', default=None)
 959         if not video_description:
 960             video_description = self._html_search_meta(
 961                 ['description', 'og:description', 'twitter:description'],
 962                 webpage, default=None)
 963         if not video_description and is_pro:
 964             orig_webpage = self._download_webpage(
 965                 orig_url, video_id,
 966                 note='Downloading webpage for description',
 967                 fatal=False)
 968             if orig_webpage:
 969                 video_description = self._html_search_meta(
 970                     'description', orig_webpage, default=None)
 971         if not video_description:
 972             self.report_warning('Cannot find video description')
 973
 974         if not timestamp:
 975             timestamp = self._search_regex(
 976                 r'<time[^>]+datetime="([^"]+)"', webpage,
 977                 'timestamp', default=None)
 978
 979         view_count = int_or_none(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count', default=None))
 980         like_count = int_or_none(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count', default=None))
 981         comment_count = int_or_none(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count', default=None))
 982
 983         formats = []
 984
 985         source_format = self._extract_original_format(
 986             'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
 987         if source_format:
 988             formats.append(source_format)
 989
 990         info_dict_config = self._parse_config(config, video_id)
 991         formats.extend(info_dict_config['formats'])
 992         self._vimeo_sort_formats(formats)
 993
 994         json_ld = self._search_json_ld(webpage, video_id, default={})
 995
 996         if not cc_license:
 997             cc_license = self._search_regex(
 998                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
 999                 webpage, 'license', default=None, group='license')
1000
1001         info_dict.update({
1002             'formats': formats,
1003             'timestamp': unified_timestamp(timestamp),
1004             'description': video_description,
1005             'webpage_url': url,
1006             'view_count': view_count,
1007             'like_count': like_count,
1008             'comment_count': comment_count,
1009             'license': cc_license,
1010         })
1011
1012         return merge_dicts(info_dict, info_dict_config, json_ld)
1013
1014
1015 class VimeoOndemandIE(VimeoIE):
1016     IE_NAME = 'vimeo:ondemand'
1017     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)'
1018     _TESTS = [{
1019         # ondemand video not available via https://vimeo.com/id
1020         'url': 'https://vimeo.com/ondemand/20704',
1021         'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
1022         'info_dict': {
1023             'id': '105442900',
1024             'ext': 'mp4',
1025             'title': 'המעבדה - במאי יותם פלדמן',
1026             'uploader': 'גם סרטים',
1027             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
1028             'uploader_id': 'gumfilms',
1029             'description': 'md5:aeeba3dbd4d04b0fa98a4fdc9c639998',
1030             'upload_date': '20140906',
1031             'timestamp': 1410032453,
1032             'thumbnail': 'https://i.vimeocdn.com/video/488238335-d7bf151c364cff8d467f1b73784668fe60aae28a54573a35d53a1210ae283bd8-d_1280',
1033             'comment_count': int,
1034             'license': 'https://creativecommons.org/licenses/by-nc-nd/3.0/',
1035             'duration': 53,
1036             'view_count': int,
1037             'like_count': int,
1038         },
1039         'params': {
1040             'format': 'best[protocol=https]',
1041         },
1042         'expected_warnings': ['Unable to download JSON metadata'],
1043     }, {
1044         # requires Referer to be passed along with og:video:url
1045         'url': 'https://vimeo.com/ondemand/36938/126682985',
1046         'info_dict': {
1047             'id': '126584684',
1048             'ext': 'mp4',
1049             'title': 'Rävlock, rätt läte på rätt plats',
1050             'uploader': 'Lindroth & Norin',
1051             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
1052             'uploader_id': 'lindrothnorin',
1053             'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
1054             'upload_date': '20150502',
1055             'timestamp': 1430586422,
1056             'duration': 121,
1057             'comment_count': int,
1058             'view_count': int,
1059             'thumbnail': 'https://i.vimeocdn.com/video/517077723-7066ae1d9a79d3eb361334fb5d58ec13c8f04b52f8dd5eadfbd6fb0bcf11f613-d_1280',
1060             'like_count': int,
1061         },
1062         'params': {
1063             'skip_download': True,
1064         },
1065         'expected_warnings': ['Unable to download JSON metadata'],
1066     }, {
1067         'url': 'https://vimeo.com/ondemand/nazmaalik',
1068         'only_matching': True,
1069     }, {
1070         'url': 'https://vimeo.com/ondemand/141692381',
1071         'only_matching': True,
1072     }, {
1073         'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
1074         'only_matching': True,
1075     }]
1076
1077
1078 class VimeoChannelIE(VimeoBaseInfoExtractor):
1079     IE_NAME = 'vimeo:channel'
1080     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
1081     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
1082     _TITLE = None
1083     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
1084     _TESTS = [{
1085         'url': 'https://vimeo.com/channels/tributes',
1086         'info_dict': {
1087             'id': 'tributes',
1088             'title': 'Vimeo Tributes',
1089         },
1090         'playlist_mincount': 22,
1091     }]
1092     _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
1093
1094     def _page_url(self, base_url, pagenum):
1095         return '%s/videos/page:%d/' % (base_url, pagenum)
1096
1097     def _extract_list_title(self, webpage):
1098         return self._TITLE or self._html_search_regex(
1099             self._TITLE_RE, webpage, 'list title', fatal=False)
1100
1101     def _title_and_entries(self, list_id, base_url):
1102         for pagenum in itertools.count(1):
1103             page_url = self._page_url(base_url, pagenum)
1104             webpage = self._download_webpage(
1105                 page_url, list_id,
1106                 'Downloading page %s' % pagenum)
1107
1108             if pagenum == 1:
1109                 yield self._extract_list_title(webpage)
1110
1111             # Try extracting href first since not all videos are available via
1112             # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
1113             clips = re.findall(
1114                 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
1115             if clips:
1116                 for video_id, video_url, video_title in clips:
1117                     yield self.url_result(
1118                         compat_urlparse.urljoin(base_url, video_url),
1119                         VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
1120             # More relaxed fallback
1121             else:
1122                 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
1123                     yield self.url_result(
1124                         'https://vimeo.com/%s' % video_id,
1125                         VimeoIE.ie_key(), video_id=video_id)
1126
1127             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
1128                 break
1129
1130     def _extract_videos(self, list_id, base_url):
1131         title_and_entries = self._title_and_entries(list_id, base_url)
1132         list_title = next(title_and_entries)
1133         return self.playlist_result(title_and_entries, list_id, list_title)
1134
1135     def _real_extract(self, url):
1136         channel_id = self._match_id(url)
1137         return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
1138
1139
1140 class VimeoUserIE(VimeoChannelIE):
1141     IE_NAME = 'vimeo:user'
1142     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
1143     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
1144     _TESTS = [{
1145         'url': 'https://vimeo.com/nkistudio/videos',
1146         'info_dict': {
1147             'title': 'Nki',
1148             'id': 'nkistudio',
1149         },
1150         'playlist_mincount': 66,
1151     }]
1152     _BASE_URL_TEMPL = 'https://vimeo.com/%s'
1153
1154
1155 class VimeoAlbumIE(VimeoBaseInfoExtractor):
1156     IE_NAME = 'vimeo:album'
1157     _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
1158     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
1159     _TESTS = [{
1160         'url': 'https://vimeo.com/album/2632481',
1161         'info_dict': {
1162             'id': '2632481',
1163             'title': 'Staff Favorites: November 2013',
1164         },
1165         'playlist_mincount': 13,
1166     }, {
1167         'note': 'Password-protected album',
1168         'url': 'https://vimeo.com/album/3253534',
1169         'info_dict': {
1170             'title': 'test',
1171             'id': '3253534',
1172         },
1173         'playlist_count': 1,
1174         'params': {
1175             'videopassword': 'youtube-dl',
1176         }
1177     }]
1178     _PAGE_SIZE = 100
1179
1180     def _fetch_page(self, album_id, authorization, hashed_pass, page):
1181         api_page = page + 1
1182         query = {
1183             'fields': 'link,uri',
1184             'page': api_page,
1185             'per_page': self._PAGE_SIZE,
1186         }
1187         if hashed_pass:
1188             query['_hashed_pass'] = hashed_pass
1189         try:
1190             videos = self._download_json(
1191                 'https://api.vimeo.com/albums/%s/videos' % album_id,
1192                 album_id, 'Downloading page %d' % api_page, query=query, headers={
1193                     'Authorization': 'jwt ' + authorization,
1194                 })['data']
1195         except ExtractorError as e:
1196             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
1197                 return
1198         for video in videos:
1199             link = video.get('link')
1200             if not link:
1201                 continue
1202             uri = video.get('uri')
1203             video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
1204             yield self.url_result(link, VimeoIE.ie_key(), video_id)
1205
1206     def _real_extract(self, url):
1207         album_id = self._match_id(url)
1208         viewer = self._download_json(
1209             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
1210         if not viewer:
1211             webpage = self._download_webpage(url, album_id)
1212             viewer = self._parse_json(self._search_regex(
1213                 r'bootstrap_data\s*=\s*({.+?})</script>',
1214                 webpage, 'bootstrap data'), album_id)['viewer']
1215         jwt = viewer['jwt']
1216         album = self._download_json(
1217             'https://api.vimeo.com/albums/' + album_id,
1218             album_id, headers={'Authorization': 'jwt ' + jwt},
1219             query={'fields': 'description,name,privacy'})
1220         hashed_pass = None
1221         if try_get(album, lambda x: x['privacy']['view']) == 'password':
1222             password = self.get_param('videopassword')
1223             if not password:
1224                 raise ExtractorError(
1225                     'This album is protected by a password, use the --video-password option',
1226                     expected=True)
1227             self._set_vimeo_cookie('vuid', viewer['vuid'])
1228             try:
1229                 hashed_pass = self._download_json(
1230                     'https://vimeo.com/showcase/%s/auth' % album_id,
1231                     album_id, 'Verifying the password', data=urlencode_postdata({
1232                         'password': password,
1233                         'token': viewer['xsrft'],
1234                     }), headers={
1235                         'X-Requested-With': 'XMLHttpRequest',
1236                     })['hashed_pass']
1237             except ExtractorError as e:
1238                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
1239                     raise ExtractorError('Wrong password', expected=True)
1240                 raise
1241         entries = OnDemandPagedList(functools.partial(
1242             self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
1243         return self.playlist_result(
1244             entries, album_id, album.get('name'), album.get('description'))
1245
1246
1247 class VimeoGroupsIE(VimeoChannelIE):
1248     IE_NAME = 'vimeo:group'
1249     _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
1250     _TESTS = [{
1251         'url': 'https://vimeo.com/groups/meetup',
1252         'info_dict': {
1253             'id': 'meetup',
1254             'title': 'Vimeo Meetup!',
1255         },
1256         'playlist_mincount': 27,
1257     }]
1258     _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
1259
1260
1261 class VimeoReviewIE(VimeoBaseInfoExtractor):
1262     IE_NAME = 'vimeo:review'
1263     IE_DESC = 'Review pages on vimeo'
1264     _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
1265     _TESTS = [{
1266         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1267         'md5': 'c507a72f780cacc12b2248bb4006d253',
1268         'info_dict': {
1269             'id': '75524534',
1270             'ext': 'mp4',
1271             'title': "DICK HARDWICK 'Comedian'",
1272             'uploader': 'Richard Hardwick',
1273             'uploader_id': 'user21297594',
1274             'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1275             'duration': 304,
1276             'thumbnail': 'https://i.vimeocdn.com/video/450115033-43303819d9ebe24c2630352e18b7056d25197d09b3ae901abdac4c4f1d68de71-d_1280',
1277             'uploader_url': 'https://vimeo.com/user21297594',
1278         },
1279     }, {
1280         'note': 'video player needs Referer',
1281         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1282         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1283         'info_dict': {
1284             'id': '91613211',
1285             'ext': 'mp4',
1286             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1287             'uploader': 'DevWeek Events',
1288             'duration': 2773,
1289             'thumbnail': r're:^https?://.*\.jpg$',
1290             'uploader_id': 'user22258446',
1291         },
1292         'skip': 'video gone',
1293     }, {
1294         'note': 'Password protected',
1295         'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1296         'info_dict': {
1297             'id': '138823582',
1298             'ext': 'mp4',
1299             'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1300             'uploader': 'TMB',
1301             'uploader_id': 'user37284429',
1302         },
1303         'params': {
1304             'videopassword': 'holygrail',
1305         },
1306         'skip': 'video gone',
1307     }]
1308
1309     def _real_extract(self, url):
1310         page_url, video_id = self._match_valid_url(url).groups()
1311         data = self._download_json(
1312             page_url.replace('/review/', '/review/data/'), video_id)
1313         if data.get('isLocked') is True:
1314             video_password = self._get_video_password()
1315             viewer = self._download_json(
1316                 'https://vimeo.com/_rv/viewer', video_id)
1317             webpage = self._verify_video_password(
1318                 'https://vimeo.com/' + video_id, video_id,
1319                 video_password, viewer['xsrft'], viewer['vuid'])
1320             clip_page_config = self._parse_json(self._search_regex(
1321                 r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
1322                 webpage, 'clip page config'), video_id)
1323             config_url = clip_page_config['player']['config_url']
1324             clip_data = clip_page_config.get('clip') or {}
1325         else:
1326             clip_data = data['clipData']
1327             config_url = clip_data['configUrl']
1328         config = self._download_json(config_url, video_id)
1329         info_dict = self._parse_config(config, video_id)
1330         source_format = self._extract_original_format(
1331             page_url + '/action', video_id)
1332         if source_format:
1333             info_dict['formats'].append(source_format)
1334         self._vimeo_sort_formats(info_dict['formats'])
1335         info_dict['description'] = clean_html(clip_data.get('description'))
1336         return info_dict
1337
1338
1339 class VimeoWatchLaterIE(VimeoChannelIE):
1340     IE_NAME = 'vimeo:watchlater'
1341     IE_DESC = 'Vimeo watch later list, ":vimeowatchlater" keyword (requires authentication)'
1342     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1343     _TITLE = 'Watch Later'
1344     _LOGIN_REQUIRED = True
1345     _TESTS = [{
1346         'url': 'https://vimeo.com/watchlater',
1347         'only_matching': True,
1348     }]
1349
1350     def _page_url(self, base_url, pagenum):
1351         url = '%s/page:%d/' % (base_url, pagenum)
1352         request = sanitized_Request(url)
1353         # Set the header to get a partial html page with the ids,
1354         # the normal page doesn't contain them.
1355         request.add_header('X-Requested-With', 'XMLHttpRequest')
1356         return request
1357
1358     def _real_extract(self, url):
1359         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1360
1361
1362 class VimeoLikesIE(VimeoChannelIE):
1363     _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1364     IE_NAME = 'vimeo:likes'
1365     IE_DESC = 'Vimeo user likes'
1366     _TESTS = [{
1367         'url': 'https://vimeo.com/user755559/likes/',
1368         'playlist_mincount': 293,
1369         'info_dict': {
1370             'id': 'user755559',
1371             'title': 'urza’s Likes',
1372         },
1373     }, {
1374         'url': 'https://vimeo.com/stormlapse/likes',
1375         'only_matching': True,
1376     }]
1377
1378     def _page_url(self, base_url, pagenum):
1379         return '%s/page:%d/' % (base_url, pagenum)
1380
1381     def _real_extract(self, url):
1382         user_id = self._match_id(url)
1383         return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
1384
1385
1386 class VHXEmbedIE(VimeoBaseInfoExtractor):
1387     IE_NAME = 'vhx:embed'
1388     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1389
1390     @staticmethod
1391     def _extract_url(url, webpage):
1392         mobj = re.search(
1393             r'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage)
1394         return VimeoIE._smuggle_referrer(unescapeHTML(mobj.group(1)), url) if mobj else None
1395
1396     def _real_extract(self, url):
1397         video_id = self._match_id(url)
1398         url, _, headers = self._unsmuggle_headers(url)
1399         webpage = self._download_webpage(url, video_id, headers=headers)
1400         config_url = self._parse_json(self._search_regex(
1401             r'window\.OTTData\s*=\s*({.+})', webpage,
1402             'ott data'), video_id, js_to_json)['config_url']
1403         config = self._download_json(config_url, video_id)
1404         info = self._parse_config(config, video_id)
1405         info['id'] = video_id
1406         self._vimeo_sort_formats(info['formats'])
1407         return info