yt_dlp/extractor/vimeo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import base64
   5 import functools
   6 import re
   7 import itertools
   8
   9 from .common import InfoExtractor
  10 from ..compat import (
  11     compat_kwargs,
  12     compat_HTTPError,
  13     compat_str,
  14     compat_urlparse,
  15 )
  16 from ..utils import (
  17     clean_html,
  18     determine_ext,
  19     ExtractorError,
  20     get_element_by_class,
  21     HEADRequest,
  22     js_to_json,
  23     int_or_none,
  24     merge_dicts,
  25     OnDemandPagedList,
  26     parse_filesize,
  27     parse_iso8601,
  28     parse_qs,
  29     sanitized_Request,
  30     smuggle_url,
  31     std_headers,
  32     str_or_none,
  33     try_get,
  34     unified_timestamp,
  35     unsmuggle_url,
  36     urlencode_postdata,
  37     urljoin,
  38     unescapeHTML,
  39     urlhandle_detect_ext,
  40 )
  41
  42
  43 class VimeoBaseInfoExtractor(InfoExtractor):
  44     _NETRC_MACHINE = 'vimeo'
  45     _LOGIN_REQUIRED = False
  46     _LOGIN_URL = 'https://vimeo.com/log_in'
  47
  48     def _login(self):
  49         username, password = self._get_login_info()
  50         if username is None:
  51             if self._LOGIN_REQUIRED:
  52                 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
  53             return
  54         webpage = self._download_webpage(
  55             self._LOGIN_URL, None, 'Downloading login page')
  56         token, vuid = self._extract_xsrft_and_vuid(webpage)
  57         data = {
  58             'action': 'login',
  59             'email': username,
  60             'password': password,
  61             'service': 'vimeo',
  62             'token': token,
  63         }
  64         self._set_vimeo_cookie('vuid', vuid)
  65         try:
  66             self._download_webpage(
  67                 self._LOGIN_URL, None, 'Logging in',
  68                 data=urlencode_postdata(data), headers={
  69                     'Content-Type': 'application/x-www-form-urlencoded',
  70                     'Referer': self._LOGIN_URL,
  71                 })
  72         except ExtractorError as e:
  73             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418:
  74                 raise ExtractorError(
  75                     'Unable to log in: bad username or password',
  76                     expected=True)
  77             raise ExtractorError('Unable to log in')
  78
  79     def _get_video_password(self):
  80         password = self.get_param('videopassword')
  81         if password is None:
  82             raise ExtractorError(
  83                 'This video is protected by a password, use the --video-password option',
  84                 expected=True)
  85         return password
  86
  87     def _verify_video_password(self, url, video_id, password, token, vuid):
  88         if url.startswith('http://'):
  89             # vimeo only supports https now, but the user can give an http url
  90             url = url.replace('http://', 'https://')
  91         self._set_vimeo_cookie('vuid', vuid)
  92         return self._download_webpage(
  93             url + '/password', video_id, 'Verifying the password',
  94             'Wrong password', data=urlencode_postdata({
  95                 'password': password,
  96                 'token': token,
  97             }), headers={
  98                 'Content-Type': 'application/x-www-form-urlencoded',
  99                 'Referer': url,
 100             })
 101
 102     def _extract_xsrft_and_vuid(self, webpage):
 103         xsrft = self._search_regex(
 104             r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
 105             webpage, 'login token', group='xsrft')
 106         vuid = self._search_regex(
 107             r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
 108             webpage, 'vuid', group='vuid')
 109         return xsrft, vuid
 110
 111     def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
 112         vimeo_config = self._search_regex(
 113             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
 114             webpage, 'vimeo config', *args, **compat_kwargs(kwargs))
 115         if vimeo_config:
 116             return self._parse_json(vimeo_config, video_id)
 117
 118     def _set_vimeo_cookie(self, name, value):
 119         self._set_cookie('vimeo.com', name, value)
 120
 121     def _vimeo_sort_formats(self, formats):
 122         # Note: Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
 123         # at the same time without actual units specified.
 124         self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source'))
 125
 126     def _parse_config(self, config, video_id):
 127         video_data = config['video']
 128         video_title = video_data['title']
 129         live_event = video_data.get('live_event') or {}
 130         is_live = live_event.get('status') == 'started'
 131         request = config.get('request') or {}
 132
 133         formats = []
 134         subtitles = {}
 135
 136         config_files = video_data.get('files') or request.get('files') or {}
 137         for f in (config_files.get('progressive') or []):
 138             video_url = f.get('url')
 139             if not video_url:
 140                 continue
 141             formats.append({
 142                 'url': video_url,
 143                 'format_id': 'http-%s' % f.get('quality'),
 144                 'source_preference': 10,
 145                 'width': int_or_none(f.get('width')),
 146                 'height': int_or_none(f.get('height')),
 147                 'fps': int_or_none(f.get('fps')),
 148                 'tbr': int_or_none(f.get('bitrate')),
 149             })
 150
 151         # TODO: fix handling of 308 status code returned for live archive manifest requests
 152         sep_pattern = r'/sep/video/'
 153         for files_type in ('hls', 'dash'):
 154             for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items():
 155                 manifest_url = cdn_data.get('url')
 156                 if not manifest_url:
 157                     continue
 158                 format_id = '%s-%s' % (files_type, cdn_name)
 159                 sep_manifest_urls = []
 160                 if re.search(sep_pattern, manifest_url):
 161                     for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
 162                         sep_manifest_urls.append((format_id + suffix, re.sub(
 163                             sep_pattern, '/%s/' % repl, manifest_url)))
 164                 else:
 165                     sep_manifest_urls = [(format_id, manifest_url)]
 166                 for f_id, m_url in sep_manifest_urls:
 167                     if files_type == 'hls':
 168                         fmts, subs = self._extract_m3u8_formats_and_subtitles(
 169                             m_url, video_id, 'mp4', live=is_live, m3u8_id=f_id,
 170                             note='Downloading %s m3u8 information' % cdn_name,
 171                             fatal=False)
 172                         formats.extend(fmts)
 173                         self._merge_subtitles(subs, target=subtitles)
 174                     elif files_type == 'dash':
 175                         if 'json=1' in m_url:
 176                             real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
 177                             if real_m_url:
 178                                 m_url = real_m_url
 179                         fmts, subs = self._extract_mpd_formats_and_subtitles(
 180                             m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
 181                             'Downloading %s MPD information' % cdn_name,
 182                             fatal=False)
 183                         formats.extend(fmts)
 184                         self._merge_subtitles(subs, target=subtitles)
 185
 186         live_archive = live_event.get('archive') or {}
 187         live_archive_source_url = live_archive.get('source_url')
 188         if live_archive_source_url and live_archive.get('status') == 'done':
 189             formats.append({
 190                 'format_id': 'live-archive-source',
 191                 'url': live_archive_source_url,
 192                 'quality': 10,
 193             })
 194
 195         for tt in (request.get('text_tracks') or []):
 196             subtitles.setdefault(tt['lang'], []).append({
 197                 'ext': 'vtt',
 198                 'url': urljoin('https://vimeo.com', tt['url']),
 199             })
 200
 201         thumbnails = []
 202         if not is_live:
 203             for key, thumb in (video_data.get('thumbs') or {}).items():
 204                 thumbnails.append({
 205                     'id': key,
 206                     'width': int_or_none(key),
 207                     'url': thumb,
 208                 })
 209             thumbnail = video_data.get('thumbnail')
 210             if thumbnail:
 211                 thumbnails.append({
 212                     'url': thumbnail,
 213                 })
 214
 215         owner = video_data.get('owner') or {}
 216         video_uploader_url = owner.get('url')
 217
 218         duration = int_or_none(video_data.get('duration'))
 219         chapter_data = try_get(config, lambda x: x['embed']['chapters']) or []
 220         chapters = [{
 221             'title': current_chapter.get('title'),
 222             'start_time': current_chapter.get('timecode'),
 223             'end_time': next_chapter.get('timecode'),
 224         } for current_chapter, next_chapter in zip(chapter_data, chapter_data[1:] + [{'timecode': duration}])]
 225         if chapters and chapters[0]['start_time']:  # Chapters may not start from 0
 226             chapters[:0] = [{'title': '<Untitled>', 'start_time': 0, 'end_time': chapters[0]['start_time']}]
 227
 228         return {
 229             'id': str_or_none(video_data.get('id')) or video_id,
 230             'title': video_title,
 231             'uploader': owner.get('name'),
 232             'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
 233             'uploader_url': video_uploader_url,
 234             'thumbnails': thumbnails,
 235             'duration': duration,
 236             'chapters': chapters or None,
 237             'formats': formats,
 238             'subtitles': subtitles,
 239             'is_live': is_live,
 240         }
 241
 242     def _extract_original_format(self, url, video_id, unlisted_hash=None):
 243         query = {'action': 'load_download_config'}
 244         if unlisted_hash:
 245             query['unlisted_hash'] = unlisted_hash
 246         download_data = self._download_json(
 247             url, video_id, fatal=False, query=query,
 248             headers={'X-Requested-With': 'XMLHttpRequest'},
 249             expected_status=(403, 404)) or {}
 250         source_file = download_data.get('source_file')
 251         download_url = try_get(source_file, lambda x: x['download_url'])
 252         if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 253             source_name = source_file.get('public_name', 'Original')
 254             if self._is_valid_url(download_url, video_id, '%s video' % source_name):
 255                 ext = (try_get(
 256                     source_file, lambda x: x['extension'],
 257                     compat_str) or determine_ext(
 258                     download_url, None) or 'mp4').lower()
 259                 return {
 260                     'url': download_url,
 261                     'ext': ext,
 262                     'width': int_or_none(source_file.get('width')),
 263                     'height': int_or_none(source_file.get('height')),
 264                     'filesize': parse_filesize(source_file.get('size')),
 265                     'format_id': source_name,
 266                     'quality': 1,
 267                 }
 268
 269         jwt_response = self._download_json(
 270             'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {}
 271         if not jwt_response.get('jwt'):
 272             return
 273         headers = {'Authorization': 'jwt %s' % jwt_response['jwt']}
 274         original_response = self._download_json(
 275             f'https://api.vimeo.com/videos/{video_id}', video_id,
 276             headers=headers, fatal=False, expected_status=(403, 404)) or {}
 277         for download_data in original_response.get('download') or []:
 278             download_url = download_data.get('link')
 279             if not download_url or download_data.get('quality') != 'source':
 280                 continue
 281             ext = determine_ext(parse_qs(download_url).get('filename', [''])[0].lower(), default_ext=None)
 282             if not ext:
 283                 urlh = self._request_webpage(
 284                     HEADRequest(download_url), video_id, fatal=False, note='Determining source extension')
 285                 ext = urlh and urlhandle_detect_ext(urlh)
 286             return {
 287                 'url': download_url,
 288                 'ext': ext or 'unknown_video',
 289                 'format_id': download_data.get('public_name', 'Original'),
 290                 'width': int_or_none(download_data.get('width')),
 291                 'height': int_or_none(download_data.get('height')),
 292                 'fps': int_or_none(download_data.get('fps')),
 293                 'filesize': int_or_none(download_data.get('size')),
 294                 'quality': 1,
 295             }
 296
 297
 298 class VimeoIE(VimeoBaseInfoExtractor):
 299     """Information extractor for vimeo.com."""
 300
 301     # _VALID_URL matches Vimeo URLs
 302     _VALID_URL = r'''(?x)
 303                     https?://
 304                         (?:
 305                             (?:
 306                                 www|
 307                                 player
 308                             )
 309                             \.
 310                         )?
 311                         vimeo(?:pro)?\.com/
 312                         (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
 313                         (?:[^/]+/)*?
 314                         (?:
 315                             (?:
 316                                 play_redirect_hls|
 317                                 moogaloop\.swf)\?clip_id=
 318                             )?
 319                         (?:videos?/)?
 320                         (?P<id>[0-9]+)
 321                         (?:/(?P<unlisted_hash>[\da-f]{10}))?
 322                         /?(?:[?&].*)?(?:[#].*)?$
 323                     '''
 324     IE_NAME = 'vimeo'
 325     _TESTS = [
 326         {
 327             'url': 'http://vimeo.com/56015672#at=0',
 328             'md5': '8879b6cc097e987f02484baf890129e5',
 329             'info_dict': {
 330                 'id': '56015672',
 331                 'ext': 'mp4',
 332                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
 333                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
 334                 'timestamp': 1355990239,
 335                 'upload_date': '20121220',
 336                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
 337                 'uploader_id': 'user7108434',
 338                 'uploader': 'Filippo Valsorda',
 339                 'duration': 10,
 340                 'license': 'by-sa',
 341             },
 342             'params': {
 343                 'format': 'best[protocol=https]',
 344             },
 345         },
 346         {
 347             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
 348             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
 349             'note': 'Vimeo Pro video (#1197)',
 350             'info_dict': {
 351                 'id': '68093876',
 352                 'ext': 'mp4',
 353                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
 354                 'uploader_id': 'openstreetmapus',
 355                 'uploader': 'OpenStreetMap US',
 356                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 357                 'description': 'md5:2c362968038d4499f4d79f88458590c1',
 358                 'duration': 1595,
 359                 'upload_date': '20130610',
 360                 'timestamp': 1370893156,
 361                 'license': 'by',
 362             },
 363             'params': {
 364                 'format': 'best[protocol=https]',
 365             },
 366         },
 367         {
 368             'url': 'http://player.vimeo.com/video/54469442',
 369             'md5': '619b811a4417aa4abe78dc653becf511',
 370             'note': 'Videos that embed the url in the player page',
 371             'info_dict': {
 372                 'id': '54469442',
 373                 'ext': 'mp4',
 374                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 375                 'uploader': 'Business of Software',
 376                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
 377                 'uploader_id': 'businessofsoftware',
 378                 'duration': 3610,
 379                 'description': None,
 380             },
 381             'params': {
 382                 'format': 'best[protocol=https]',
 383             },
 384         },
 385         {
 386             'url': 'http://vimeo.com/68375962',
 387             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 388             'note': 'Video protected with password',
 389             'info_dict': {
 390                 'id': '68375962',
 391                 'ext': 'mp4',
 392                 'title': 'youtube-dl password protected test video',
 393                 'timestamp': 1371200155,
 394                 'upload_date': '20130614',
 395                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 396                 'uploader_id': 'user18948128',
 397                 'uploader': 'Jaime Marquínez Ferrándiz',
 398                 'duration': 10,
 399                 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
 400             },
 401             'params': {
 402                 'format': 'best[protocol=https]',
 403                 'videopassword': 'youtube-dl',
 404             },
 405         },
 406         {
 407             'url': 'http://vimeo.com/channels/keypeele/75629013',
 408             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 409             'info_dict': {
 410                 'id': '75629013',
 411                 'ext': 'mp4',
 412                 'title': 'Key & Peele: Terrorist Interrogation',
 413                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 414                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
 415                 'uploader_id': 'atencio',
 416                 'uploader': 'Peter Atencio',
 417                 'channel_id': 'keypeele',
 418                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
 419                 'timestamp': 1380339469,
 420                 'upload_date': '20130928',
 421                 'duration': 187,
 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': 'mp4',
 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             },
 460         },
 461         {
 462             # contains original format
 463             'url': 'https://vimeo.com/33951933',
 464             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 465             'info_dict': {
 466                 'id': '33951933',
 467                 'ext': 'mp4',
 468                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 469                 'uploader': 'The DMCI',
 470                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
 471                 'uploader_id': 'dmci',
 472                 'timestamp': 1324343742,
 473                 'upload_date': '20111220',
 474                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 475             },
 476         },
 477         {
 478             'note': 'Contains original format not accessible in webpage',
 479             'url': 'https://vimeo.com/393756517',
 480             'md5': 'c464af248b592190a5ffbb5d33f382b0',
 481             'info_dict': {
 482                 'id': '393756517',
 483                 'ext': 'mov',
 484                 'timestamp': 1582642091,
 485                 'uploader_id': 'frameworkla',
 486                 'title': 'Straight To Hell - Sabrina: Netflix',
 487                 'uploader': 'Framework Studio',
 488                 'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
 489                 'upload_date': '20200225',
 490             },
 491         },
 492         {
 493             # only available via https://vimeo.com/channels/tributes/6213729 and
 494             # not via https://vimeo.com/6213729
 495             'url': 'https://vimeo.com/channels/tributes/6213729',
 496             'info_dict': {
 497                 'id': '6213729',
 498                 'ext': 'mp4',
 499                 'title': 'Vimeo Tribute: The Shining',
 500                 'uploader': 'Casey Donahue',
 501                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
 502                 'uploader_id': 'caseydonahue',
 503                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
 504                 'channel_id': 'tributes',
 505                 'timestamp': 1250886430,
 506                 'upload_date': '20090821',
 507                 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
 508             },
 509             'params': {
 510                 'skip_download': True,
 511             },
 512         },
 513         {
 514             # redirects to ondemand extractor and should be passed through it
 515             # for successful extraction
 516             'url': 'https://vimeo.com/73445910',
 517             'info_dict': {
 518                 'id': '73445910',
 519                 'ext': 'mp4',
 520                 'title': 'The Reluctant Revolutionary',
 521                 'uploader': '10Ft Films',
 522                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
 523                 'uploader_id': 'tenfootfilms',
 524                 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
 525                 'upload_date': '20130830',
 526                 'timestamp': 1377853339,
 527             },
 528             'params': {
 529                 'skip_download': True,
 530             },
 531             'skip': 'this page is no longer available.',
 532         },
 533         {
 534             'url': 'http://player.vimeo.com/video/68375962',
 535             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 536             'info_dict': {
 537                 'id': '68375962',
 538                 'ext': 'mp4',
 539                 'title': 'youtube-dl password protected test video',
 540                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 541                 'uploader_id': 'user18948128',
 542                 'uploader': 'Jaime Marquínez Ferrándiz',
 543                 'duration': 10,
 544             },
 545             'params': {
 546                 'format': 'best[protocol=https]',
 547                 'videopassword': 'youtube-dl',
 548             },
 549         },
 550         {
 551             'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
 552             'only_matching': True,
 553         },
 554         {
 555             'url': 'https://vimeo.com/109815029',
 556             'note': 'Video not completely processed, "failed" seed status',
 557             'only_matching': True,
 558         },
 559         {
 560             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 561             'only_matching': True,
 562         },
 563         {
 564             'url': 'https://vimeo.com/album/2632481/video/79010983',
 565             'only_matching': True,
 566         },
 567         {
 568             'url': 'https://vimeo.com/showcase/3253534/video/119195465',
 569             'note': 'A video in a password protected album (showcase)',
 570             'info_dict': {
 571                 'id': '119195465',
 572                 'ext': 'mp4',
 573                 'title': 'youtube-dl test video \'ä"BaW_jenozKc',
 574                 'uploader': 'Philipp Hagemeister',
 575                 'uploader_id': 'user20132939',
 576                 'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
 577                 'upload_date': '20150209',
 578                 'timestamp': 1423518307,
 579             },
 580             'params': {
 581                 'format': 'best[protocol=https]',
 582                 'videopassword': 'youtube-dl',
 583             },
 584         },
 585         {
 586             # source file returns 403: Forbidden
 587             'url': 'https://vimeo.com/7809605',
 588             'only_matching': True,
 589         },
 590         {
 591             'note': 'Direct URL with hash',
 592             'url': 'https://vimeo.com/160743502/abd0e13fb4',
 593             'info_dict': {
 594                 'id': '160743502',
 595                 'ext': 'mp4',
 596                 'uploader': 'Julian Tryba',
 597                 'uploader_id': 'aliniamedia',
 598                 'title': 'Harrisville New Hampshire',
 599                 'timestamp': 1459259666,
 600                 'upload_date': '20160329',
 601             },
 602             'params': {'skip_download': True},
 603         },
 604         {
 605             'url': 'https://vimeo.com/138909882',
 606             'info_dict': {
 607                 'id': '138909882',
 608                 'ext': 'mp4',
 609                 'title': 'Eastnor Castle 2015 Firework Champions - The Promo!',
 610                 'description': 'md5:5967e090768a831488f6e74b7821b3c1',
 611                 'uploader_id': 'fireworkchampions',
 612                 'uploader': 'Firework Champions',
 613                 'upload_date': '20150910',
 614                 'timestamp': 1441901895,
 615             },
 616             'params': {
 617                 'skip_download': True,
 618                 'format': 'Original',
 619             },
 620         },
 621         {
 622             'url': 'https://vimeo.com/channels/staffpicks/143603739',
 623             'info_dict': {
 624                 'id': '143603739',
 625                 'ext': 'mp4',
 626                 'uploader': 'Karim Huu Do',
 627                 'timestamp': 1445846953,
 628                 'upload_date': '20151026',
 629                 'title': 'The Shoes - Submarine Feat. Blaine Harrison',
 630                 'uploader_id': 'karimhd',
 631                 'description': 'md5:8e2eea76de4504c2e8020a9bcfa1e843',
 632             },
 633             'params': {'skip_download': 'm3u8'},
 634         },
 635         {
 636             # requires passing unlisted_hash(a52724358e) to load_download_config request
 637             'url': 'https://vimeo.com/392479337/a52724358e',
 638             'only_matching': True,
 639         },
 640         # https://gettingthingsdone.com/workflowmap/
 641         # vimeo embed with check-password page protected by Referer header
 642     ]
 643
 644     @staticmethod
 645     def _smuggle_referrer(url, referrer_url):
 646         return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
 647
 648     @staticmethod
 649     def _extract_urls(url, webpage):
 650         urls = []
 651         # Look for embedded (iframe) Vimeo player
 652         for mobj in re.finditer(
 653                 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
 654                 webpage):
 655             urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
 656         PLAIN_EMBED_RE = (
 657             # Look for embedded (swf embed) Vimeo player
 658             r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
 659             # Look more for non-standard embedded Vimeo player
 660             r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
 661         )
 662         for embed_re in PLAIN_EMBED_RE:
 663             for mobj in re.finditer(embed_re, webpage):
 664                 urls.append(mobj.group('url'))
 665         return urls
 666
 667     @staticmethod
 668     def _extract_url(url, webpage):
 669         urls = VimeoIE._extract_urls(url, webpage)
 670         return urls[0] if urls else None
 671
 672     def _verify_player_video_password(self, url, video_id, headers):
 673         password = self._get_video_password()
 674         data = urlencode_postdata({
 675             'password': base64.b64encode(password.encode()),
 676         })
 677         headers = merge_dicts(headers, {
 678             'Content-Type': 'application/x-www-form-urlencoded',
 679         })
 680         checked = self._download_json(
 681             url + '/check-password', video_id,
 682             'Verifying the password', data=data, headers=headers)
 683         if checked is False:
 684             raise ExtractorError('Wrong video password', expected=True)
 685         return checked
 686
 687     def _real_initialize(self):
 688         self._login()
 689
 690     def _extract_from_api(self, video_id, unlisted_hash=None):
 691         token = self._download_json(
 692             'https://vimeo.com/_rv/jwt', video_id, headers={
 693                 'X-Requested-With': 'XMLHttpRequest'
 694             })['token']
 695         api_url = 'https://api.vimeo.com/videos/' + video_id
 696         if unlisted_hash:
 697             api_url += ':' + unlisted_hash
 698         video = self._download_json(
 699             api_url, video_id, headers={
 700                 'Authorization': 'jwt ' + token,
 701             }, query={
 702                 'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
 703             })
 704         info = self._parse_config(self._download_json(
 705             video['config_url'], video_id), video_id)
 706         self._vimeo_sort_formats(info['formats'])
 707         get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
 708         info.update({
 709             'description': video.get('description'),
 710             'license': video.get('license'),
 711             'release_timestamp': get_timestamp('release'),
 712             'timestamp': get_timestamp('created'),
 713             'view_count': int_or_none(try_get(video, lambda x: x['stats']['plays'])),
 714         })
 715         connections = try_get(
 716             video, lambda x: x['metadata']['connections'], dict) or {}
 717         for k in ('comment', 'like'):
 718             info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total']))
 719         return info
 720
 721     def _try_album_password(self, url):
 722         album_id = self._search_regex(
 723             r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None)
 724         if not album_id:
 725             return
 726         viewer = self._download_json(
 727             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
 728         if not viewer:
 729             webpage = self._download_webpage(url, album_id)
 730             viewer = self._parse_json(self._search_regex(
 731                 r'bootstrap_data\s*=\s*({.+?})</script>',
 732                 webpage, 'bootstrap data'), album_id)['viewer']
 733         jwt = viewer['jwt']
 734         album = self._download_json(
 735             'https://api.vimeo.com/albums/' + album_id,
 736             album_id, headers={'Authorization': 'jwt ' + jwt},
 737             query={'fields': 'description,name,privacy'})
 738         if try_get(album, lambda x: x['privacy']['view']) == 'password':
 739             password = self.get_param('videopassword')
 740             if not password:
 741                 raise ExtractorError(
 742                     'This album is protected by a password, use the --video-password option',
 743                     expected=True)
 744             self._set_vimeo_cookie('vuid', viewer['vuid'])
 745             try:
 746                 self._download_json(
 747                     'https://vimeo.com/showcase/%s/auth' % album_id,
 748                     album_id, 'Verifying the password', data=urlencode_postdata({
 749                         'password': password,
 750                         'token': viewer['xsrft'],
 751                     }), headers={
 752                         'X-Requested-With': 'XMLHttpRequest',
 753                     })
 754             except ExtractorError as e:
 755                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
 756                     raise ExtractorError('Wrong password', expected=True)
 757                 raise
 758
 759     def _real_extract(self, url):
 760         url, data = unsmuggle_url(url, {})
 761         headers = std_headers.copy()
 762         if 'http_headers' in data:
 763             headers.update(data['http_headers'])
 764         if 'Referer' not in headers:
 765             headers['Referer'] = url
 766
 767         # Extract ID from URL
 768         mobj = self._match_valid_url(url).groupdict()
 769         video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash')
 770         if unlisted_hash:
 771             return self._extract_from_api(video_id, unlisted_hash)
 772
 773         orig_url = url
 774         is_pro = 'vimeopro.com/' in url
 775         if is_pro:
 776             # some videos require portfolio_id to be present in player url
 777             # https://github.com/ytdl-org/youtube-dl/issues/20070
 778             url = self._extract_url(url, self._download_webpage(url, video_id))
 779             if not url:
 780                 url = 'https://vimeo.com/' + video_id
 781         elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
 782             url = 'https://vimeo.com/' + video_id
 783
 784         self._try_album_password(url)
 785         try:
 786             # Retrieve video webpage to extract further information
 787             webpage, urlh = self._download_webpage_handle(
 788                 url, video_id, headers=headers)
 789             redirect_url = urlh.geturl()
 790         except ExtractorError as ee:
 791             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 792                 errmsg = ee.cause.read()
 793                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 794                     raise ExtractorError(
 795                         'Cannot download embed-only video without embedding '
 796                         'URL. Please call yt-dlp with the URL of the page '
 797                         'that embeds this video.',
 798                         expected=True)
 799             raise
 800
 801         if '://player.vimeo.com/video/' in url:
 802             config = self._parse_json(self._search_regex(
 803                 r'\bconfig\s*=\s*({.+?})\s*;', webpage, 'info section'), video_id)
 804             if config.get('view') == 4:
 805                 config = self._verify_player_video_password(
 806                     redirect_url, video_id, headers)
 807             info = self._parse_config(config, video_id)
 808             self._vimeo_sort_formats(info['formats'])
 809             return info
 810
 811         if re.search(r'<form[^>]+?id="pw_form"', webpage):
 812             video_password = self._get_video_password()
 813             token, vuid = self._extract_xsrft_and_vuid(webpage)
 814             webpage = self._verify_video_password(
 815                 redirect_url, video_id, video_password, token, vuid)
 816
 817         vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
 818         if vimeo_config:
 819             seed_status = vimeo_config.get('seed_status') or {}
 820             if seed_status.get('state') == 'failed':
 821                 raise ExtractorError(
 822                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 823                     expected=True)
 824
 825         cc_license = None
 826         timestamp = None
 827         video_description = None
 828         info_dict = {}
 829         config_url = None
 830
 831         channel_id = self._search_regex(
 832             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
 833         if channel_id:
 834             config_url = self._html_search_regex(
 835                 r'\bdata-config-url="([^"]+)"', webpage, 'config URL', default=None)
 836             video_description = clean_html(get_element_by_class('description', webpage))
 837             info_dict.update({
 838                 'channel_id': channel_id,
 839                 'channel_url': 'https://vimeo.com/channels/' + channel_id,
 840             })
 841         if not config_url:
 842             page_config = self._parse_json(self._search_regex(
 843                 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
 844                 webpage, 'page config', default='{}'), video_id, fatal=False)
 845             if not page_config:
 846                 return self._extract_from_api(video_id)
 847             config_url = page_config['player']['config_url']
 848             cc_license = page_config.get('cc_license')
 849             clip = page_config.get('clip') or {}
 850             timestamp = clip.get('uploaded_on')
 851             video_description = clean_html(
 852                 clip.get('description') or page_config.get('description_html_escaped'))
 853         config = self._download_json(config_url, video_id)
 854         video = config.get('video') or {}
 855         vod = video.get('vod') or {}
 856
 857         def is_rented():
 858             if '>You rented this title.<' in webpage:
 859                 return True
 860             if try_get(config, lambda x: x['user']['purchased']):
 861                 return True
 862             for purchase_option in (vod.get('purchase_options') or []):
 863                 if purchase_option.get('purchased'):
 864                     return True
 865                 label = purchase_option.get('label_string')
 866                 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
 867                     return True
 868             return False
 869
 870         if is_rented() and vod.get('is_trailer'):
 871             feature_id = vod.get('feature_id')
 872             if feature_id and not data.get('force_feature_id', False):
 873                 return self.url_result(smuggle_url(
 874                     'https://player.vimeo.com/player/%s' % feature_id,
 875                     {'force_feature_id': True}), 'Vimeo')
 876
 877         if not video_description:
 878             video_description = self._html_search_regex(
 879                 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 880                 webpage, 'description', default=None)
 881         if not video_description:
 882             video_description = self._html_search_meta(
 883                 ['description', 'og:description', 'twitter:description'],
 884                 webpage, default=None)
 885         if not video_description and is_pro:
 886             orig_webpage = self._download_webpage(
 887                 orig_url, video_id,
 888                 note='Downloading webpage for description',
 889                 fatal=False)
 890             if orig_webpage:
 891                 video_description = self._html_search_meta(
 892                     'description', orig_webpage, default=None)
 893         if not video_description:
 894             self.report_warning('Cannot find video description')
 895
 896         if not timestamp:
 897             timestamp = self._search_regex(
 898                 r'<time[^>]+datetime="([^"]+)"', webpage,
 899                 'timestamp', default=None)
 900
 901         view_count = int_or_none(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count', default=None))
 902         like_count = int_or_none(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count', default=None))
 903         comment_count = int_or_none(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count', default=None))
 904
 905         formats = []
 906
 907         source_format = self._extract_original_format(
 908             'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
 909         if source_format:
 910             formats.append(source_format)
 911
 912         info_dict_config = self._parse_config(config, video_id)
 913         formats.extend(info_dict_config['formats'])
 914         self._vimeo_sort_formats(formats)
 915
 916         json_ld = self._search_json_ld(webpage, video_id, default={})
 917
 918         if not cc_license:
 919             cc_license = self._search_regex(
 920                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
 921                 webpage, 'license', default=None, group='license')
 922
 923         info_dict.update({
 924             'formats': formats,
 925             'timestamp': unified_timestamp(timestamp),
 926             'description': video_description,
 927             'webpage_url': url,
 928             'view_count': view_count,
 929             'like_count': like_count,
 930             'comment_count': comment_count,
 931             'license': cc_license,
 932         })
 933
 934         return merge_dicts(info_dict, info_dict_config, json_ld)
 935
 936
 937 class VimeoOndemandIE(VimeoIE):
 938     IE_NAME = 'vimeo:ondemand'
 939     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)'
 940     _TESTS = [{
 941         # ondemand video not available via https://vimeo.com/id
 942         'url': 'https://vimeo.com/ondemand/20704',
 943         'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
 944         'info_dict': {
 945             'id': '105442900',
 946             'ext': 'mp4',
 947             'title': 'המעבדה - במאי יותם פלדמן',
 948             'uploader': 'גם סרטים',
 949             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
 950             'uploader_id': 'gumfilms',
 951             'description': 'md5:4c027c965e439de4baab621e48b60791',
 952             'upload_date': '20140906',
 953             'timestamp': 1410032453,
 954         },
 955         'params': {
 956             'format': 'best[protocol=https]',
 957         },
 958         'expected_warnings': ['Unable to download JSON metadata'],
 959     }, {
 960         # requires Referer to be passed along with og:video:url
 961         'url': 'https://vimeo.com/ondemand/36938/126682985',
 962         'info_dict': {
 963             'id': '126584684',
 964             'ext': 'mp4',
 965             'title': 'Rävlock, rätt läte på rätt plats',
 966             'uploader': 'Lindroth & Norin',
 967             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
 968             'uploader_id': 'lindrothnorin',
 969             'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
 970             'upload_date': '20150502',
 971             'timestamp': 1430586422,
 972         },
 973         'params': {
 974             'skip_download': True,
 975         },
 976         'expected_warnings': ['Unable to download JSON metadata'],
 977     }, {
 978         'url': 'https://vimeo.com/ondemand/nazmaalik',
 979         'only_matching': True,
 980     }, {
 981         'url': 'https://vimeo.com/ondemand/141692381',
 982         'only_matching': True,
 983     }, {
 984         'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
 985         'only_matching': True,
 986     }]
 987
 988
 989 class VimeoChannelIE(VimeoBaseInfoExtractor):
 990     IE_NAME = 'vimeo:channel'
 991     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 992     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 993     _TITLE = None
 994     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 995     _TESTS = [{
 996         'url': 'https://vimeo.com/channels/tributes',
 997         'info_dict': {
 998             'id': 'tributes',
 999             'title': 'Vimeo Tributes',
1000         },
1001         'playlist_mincount': 25,
1002     }]
1003     _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
1004
1005     def _page_url(self, base_url, pagenum):
1006         return '%s/videos/page:%d/' % (base_url, pagenum)
1007
1008     def _extract_list_title(self, webpage):
1009         return self._TITLE or self._html_search_regex(
1010             self._TITLE_RE, webpage, 'list title', fatal=False)
1011
1012     def _title_and_entries(self, list_id, base_url):
1013         for pagenum in itertools.count(1):
1014             page_url = self._page_url(base_url, pagenum)
1015             webpage = self._download_webpage(
1016                 page_url, list_id,
1017                 'Downloading page %s' % pagenum)
1018
1019             if pagenum == 1:
1020                 yield self._extract_list_title(webpage)
1021
1022             # Try extracting href first since not all videos are available via
1023             # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
1024             clips = re.findall(
1025                 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
1026             if clips:
1027                 for video_id, video_url, video_title in clips:
1028                     yield self.url_result(
1029                         compat_urlparse.urljoin(base_url, video_url),
1030                         VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
1031             # More relaxed fallback
1032             else:
1033                 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
1034                     yield self.url_result(
1035                         'https://vimeo.com/%s' % video_id,
1036                         VimeoIE.ie_key(), video_id=video_id)
1037
1038             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
1039                 break
1040
1041     def _extract_videos(self, list_id, base_url):
1042         title_and_entries = self._title_and_entries(list_id, base_url)
1043         list_title = next(title_and_entries)
1044         return self.playlist_result(title_and_entries, list_id, list_title)
1045
1046     def _real_extract(self, url):
1047         channel_id = self._match_id(url)
1048         return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
1049
1050
1051 class VimeoUserIE(VimeoChannelIE):
1052     IE_NAME = 'vimeo:user'
1053     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
1054     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
1055     _TESTS = [{
1056         'url': 'https://vimeo.com/nkistudio/videos',
1057         'info_dict': {
1058             'title': 'Nki',
1059             'id': 'nkistudio',
1060         },
1061         'playlist_mincount': 66,
1062     }]
1063     _BASE_URL_TEMPL = 'https://vimeo.com/%s'
1064
1065
1066 class VimeoAlbumIE(VimeoBaseInfoExtractor):
1067     IE_NAME = 'vimeo:album'
1068     _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
1069     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
1070     _TESTS = [{
1071         'url': 'https://vimeo.com/album/2632481',
1072         'info_dict': {
1073             'id': '2632481',
1074             'title': 'Staff Favorites: November 2013',
1075         },
1076         'playlist_mincount': 13,
1077     }, {
1078         'note': 'Password-protected album',
1079         'url': 'https://vimeo.com/album/3253534',
1080         'info_dict': {
1081             'title': 'test',
1082             'id': '3253534',
1083         },
1084         'playlist_count': 1,
1085         'params': {
1086             'videopassword': 'youtube-dl',
1087         }
1088     }]
1089     _PAGE_SIZE = 100
1090
1091     def _fetch_page(self, album_id, authorization, hashed_pass, page):
1092         api_page = page + 1
1093         query = {
1094             'fields': 'link,uri',
1095             'page': api_page,
1096             'per_page': self._PAGE_SIZE,
1097         }
1098         if hashed_pass:
1099             query['_hashed_pass'] = hashed_pass
1100         try:
1101             videos = self._download_json(
1102                 'https://api.vimeo.com/albums/%s/videos' % album_id,
1103                 album_id, 'Downloading page %d' % api_page, query=query, headers={
1104                     'Authorization': 'jwt ' + authorization,
1105                 })['data']
1106         except ExtractorError as e:
1107             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
1108                 return
1109         for video in videos:
1110             link = video.get('link')
1111             if not link:
1112                 continue
1113             uri = video.get('uri')
1114             video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
1115             yield self.url_result(link, VimeoIE.ie_key(), video_id)
1116
1117     def _real_extract(self, url):
1118         album_id = self._match_id(url)
1119         viewer = self._download_json(
1120             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
1121         if not viewer:
1122             webpage = self._download_webpage(url, album_id)
1123             viewer = self._parse_json(self._search_regex(
1124                 r'bootstrap_data\s*=\s*({.+?})</script>',
1125                 webpage, 'bootstrap data'), album_id)['viewer']
1126         jwt = viewer['jwt']
1127         album = self._download_json(
1128             'https://api.vimeo.com/albums/' + album_id,
1129             album_id, headers={'Authorization': 'jwt ' + jwt},
1130             query={'fields': 'description,name,privacy'})
1131         hashed_pass = None
1132         if try_get(album, lambda x: x['privacy']['view']) == 'password':
1133             password = self.get_param('videopassword')
1134             if not password:
1135                 raise ExtractorError(
1136                     'This album is protected by a password, use the --video-password option',
1137                     expected=True)
1138             self._set_vimeo_cookie('vuid', viewer['vuid'])
1139             try:
1140                 hashed_pass = self._download_json(
1141                     'https://vimeo.com/showcase/%s/auth' % album_id,
1142                     album_id, 'Verifying the password', data=urlencode_postdata({
1143                         'password': password,
1144                         'token': viewer['xsrft'],
1145                     }), headers={
1146                         'X-Requested-With': 'XMLHttpRequest',
1147                     })['hashed_pass']
1148             except ExtractorError as e:
1149                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
1150                     raise ExtractorError('Wrong password', expected=True)
1151                 raise
1152         entries = OnDemandPagedList(functools.partial(
1153             self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
1154         return self.playlist_result(
1155             entries, album_id, album.get('name'), album.get('description'))
1156
1157
1158 class VimeoGroupsIE(VimeoChannelIE):
1159     IE_NAME = 'vimeo:group'
1160     _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
1161     _TESTS = [{
1162         'url': 'https://vimeo.com/groups/meetup',
1163         'info_dict': {
1164             'id': 'meetup',
1165             'title': 'Vimeo Meetup!',
1166         },
1167         'playlist_mincount': 27,
1168     }]
1169     _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
1170
1171
1172 class VimeoReviewIE(VimeoBaseInfoExtractor):
1173     IE_NAME = 'vimeo:review'
1174     IE_DESC = 'Review pages on vimeo'
1175     _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
1176     _TESTS = [{
1177         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1178         'md5': 'c507a72f780cacc12b2248bb4006d253',
1179         'info_dict': {
1180             'id': '75524534',
1181             'ext': 'mp4',
1182             'title': "DICK HARDWICK 'Comedian'",
1183             'uploader': 'Richard Hardwick',
1184             'uploader_id': 'user21297594',
1185             'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1186         },
1187     }, {
1188         'note': 'video player needs Referer',
1189         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1190         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1191         'info_dict': {
1192             'id': '91613211',
1193             'ext': 'mp4',
1194             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1195             'uploader': 'DevWeek Events',
1196             'duration': 2773,
1197             'thumbnail': r're:^https?://.*\.jpg$',
1198             'uploader_id': 'user22258446',
1199         },
1200         'skip': 'video gone',
1201     }, {
1202         'note': 'Password protected',
1203         'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1204         'info_dict': {
1205             'id': '138823582',
1206             'ext': 'mp4',
1207             'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1208             'uploader': 'TMB',
1209             'uploader_id': 'user37284429',
1210         },
1211         'params': {
1212             'videopassword': 'holygrail',
1213         },
1214         'skip': 'video gone',
1215     }]
1216
1217     def _real_initialize(self):
1218         self._login()
1219
1220     def _real_extract(self, url):
1221         page_url, video_id = self._match_valid_url(url).groups()
1222         data = self._download_json(
1223             page_url.replace('/review/', '/review/data/'), video_id)
1224         if data.get('isLocked') is True:
1225             video_password = self._get_video_password()
1226             viewer = self._download_json(
1227                 'https://vimeo.com/_rv/viewer', video_id)
1228             webpage = self._verify_video_password(
1229                 'https://vimeo.com/' + video_id, video_id,
1230                 video_password, viewer['xsrft'], viewer['vuid'])
1231             clip_page_config = self._parse_json(self._search_regex(
1232                 r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
1233                 webpage, 'clip page config'), video_id)
1234             config_url = clip_page_config['player']['config_url']
1235             clip_data = clip_page_config.get('clip') or {}
1236         else:
1237             clip_data = data['clipData']
1238             config_url = clip_data['configUrl']
1239         config = self._download_json(config_url, video_id)
1240         info_dict = self._parse_config(config, video_id)
1241         source_format = self._extract_original_format(
1242             page_url + '/action', video_id)
1243         if source_format:
1244             info_dict['formats'].append(source_format)
1245         self._vimeo_sort_formats(info_dict['formats'])
1246         info_dict['description'] = clean_html(clip_data.get('description'))
1247         return info_dict
1248
1249
1250 class VimeoWatchLaterIE(VimeoChannelIE):
1251     IE_NAME = 'vimeo:watchlater'
1252     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
1253     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1254     _TITLE = 'Watch Later'
1255     _LOGIN_REQUIRED = True
1256     _TESTS = [{
1257         'url': 'https://vimeo.com/watchlater',
1258         'only_matching': True,
1259     }]
1260
1261     def _real_initialize(self):
1262         self._login()
1263
1264     def _page_url(self, base_url, pagenum):
1265         url = '%s/page:%d/' % (base_url, pagenum)
1266         request = sanitized_Request(url)
1267         # Set the header to get a partial html page with the ids,
1268         # the normal page doesn't contain them.
1269         request.add_header('X-Requested-With', 'XMLHttpRequest')
1270         return request
1271
1272     def _real_extract(self, url):
1273         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1274
1275
1276 class VimeoLikesIE(VimeoChannelIE):
1277     _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1278     IE_NAME = 'vimeo:likes'
1279     IE_DESC = 'Vimeo user likes'
1280     _TESTS = [{
1281         'url': 'https://vimeo.com/user755559/likes/',
1282         'playlist_mincount': 293,
1283         'info_dict': {
1284             'id': 'user755559',
1285             'title': 'urza’s Likes',
1286         },
1287     }, {
1288         'url': 'https://vimeo.com/stormlapse/likes',
1289         'only_matching': True,
1290     }]
1291
1292     def _page_url(self, base_url, pagenum):
1293         return '%s/page:%d/' % (base_url, pagenum)
1294
1295     def _real_extract(self, url):
1296         user_id = self._match_id(url)
1297         return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
1298
1299
1300 class VHXEmbedIE(VimeoBaseInfoExtractor):
1301     IE_NAME = 'vhx:embed'
1302     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1303
1304     @staticmethod
1305     def _extract_url(webpage):
1306         mobj = re.search(
1307             r'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage)
1308         return unescapeHTML(mobj.group(1)) if mobj else None
1309
1310     def _real_extract(self, url):
1311         video_id = self._match_id(url)
1312         webpage = self._download_webpage(url, video_id)
1313         config_url = self._parse_json(self._search_regex(
1314             r'window\.OTTData\s*=\s*({.+})', webpage,
1315             'ott data'), video_id, js_to_json)['config_url']
1316         config = self._download_json(config_url, video_id)
1317         info = self._parse_config(config, video_id)
1318         info['id'] = video_id
1319         self._vimeo_sort_formats(info['formats'])
1320         return info