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',
 170                             'm3u8' if is_live else 'm3u8_native', m3u8_id=f_id,
 171                             note='Downloading %s m3u8 information' % cdn_name,
 172                             fatal=False)
 173                         formats.extend(fmts)
 174                         self._merge_subtitles(subs, target=subtitles)
 175                     elif files_type == 'dash':
 176                         if 'json=1' in m_url:
 177                             real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
 178                             if real_m_url:
 179                                 m_url = real_m_url
 180                         fmts, subs = self._extract_mpd_formats_and_subtitles(
 181                             m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
 182                             'Downloading %s MPD information' % cdn_name,
 183                             fatal=False)
 184                         formats.extend(fmts)
 185                         self._merge_subtitles(subs, target=subtitles)
 186
 187         live_archive = live_event.get('archive') or {}
 188         live_archive_source_url = live_archive.get('source_url')
 189         if live_archive_source_url and live_archive.get('status') == 'done':
 190             formats.append({
 191                 'format_id': 'live-archive-source',
 192                 'url': live_archive_source_url,
 193                 'quality': 10,
 194             })
 195
 196         for tt in (request.get('text_tracks') or []):
 197             subtitles.setdefault(tt['lang'], []).append({
 198                 'ext': 'vtt',
 199                 'url': urljoin('https://vimeo.com', tt['url']),
 200             })
 201
 202         thumbnails = []
 203         if not is_live:
 204             for key, thumb in (video_data.get('thumbs') or {}).items():
 205                 thumbnails.append({
 206                     'id': key,
 207                     'width': int_or_none(key),
 208                     'url': thumb,
 209                 })
 210             thumbnail = video_data.get('thumbnail')
 211             if thumbnail:
 212                 thumbnails.append({
 213                     'url': thumbnail,
 214                 })
 215
 216         owner = video_data.get('owner') or {}
 217         video_uploader_url = owner.get('url')
 218
 219         duration = int_or_none(video_data.get('duration'))
 220         chapter_data = try_get(config, lambda x: x['embed']['chapters']) or []
 221         chapters = [{
 222             'title': current_chapter.get('title'),
 223             'start_time': current_chapter.get('timecode'),
 224             'end_time': next_chapter.get('timecode'),
 225         } for current_chapter, next_chapter in zip(chapter_data, chapter_data[1:] + [{'timecode': duration}])]
 226         if chapters and chapters[0]['start_time']:  # Chapters may not start from 0
 227             chapters[:0] = [{'title': '<Untitled>', 'start_time': 0, 'end_time': chapters[0]['start_time']}]
 228
 229         return {
 230             'id': str_or_none(video_data.get('id')) or video_id,
 231             'title': video_title,
 232             'uploader': owner.get('name'),
 233             'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
 234             'uploader_url': video_uploader_url,
 235             'thumbnails': thumbnails,
 236             'duration': duration,
 237             'chapters': chapters or None,
 238             'formats': formats,
 239             'subtitles': subtitles,
 240             'is_live': is_live,
 241         }
 242
 243     def _extract_original_format(self, url, video_id, unlisted_hash=None):
 244         query = {'action': 'load_download_config'}
 245         if unlisted_hash:
 246             query['unlisted_hash'] = unlisted_hash
 247         download_data = self._download_json(
 248             url, video_id, fatal=False, query=query,
 249             headers={'X-Requested-With': 'XMLHttpRequest'},
 250             expected_status=(403, 404)) or {}
 251         source_file = download_data.get('source_file')
 252         download_url = try_get(source_file, lambda x: x['download_url'])
 253         if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 254             source_name = source_file.get('public_name', 'Original')
 255             if self._is_valid_url(download_url, video_id, '%s video' % source_name):
 256                 ext = (try_get(
 257                     source_file, lambda x: x['extension'],
 258                     compat_str) or determine_ext(
 259                     download_url, None) or 'mp4').lower()
 260                 return {
 261                     'url': download_url,
 262                     'ext': ext,
 263                     'width': int_or_none(source_file.get('width')),
 264                     'height': int_or_none(source_file.get('height')),
 265                     'filesize': parse_filesize(source_file.get('size')),
 266                     'format_id': source_name,
 267                     'quality': 1,
 268                 }
 269
 270         jwt_response = self._download_json(
 271             'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {}
 272         if not jwt_response.get('jwt'):
 273             return
 274         headers = {'Authorization': 'jwt %s' % jwt_response['jwt']}
 275         original_response = self._download_json(
 276             f'https://api.vimeo.com/videos/{video_id}', video_id,
 277             headers=headers, fatal=False, expected_status=(403, 404)) or {}
 278         for download_data in original_response.get('download') or []:
 279             download_url = download_data.get('link')
 280             if not download_url or download_data.get('quality') != 'source':
 281                 continue
 282             ext = determine_ext(parse_qs(download_url).get('filename', [''])[0].lower(), default_ext=None)
 283             if not ext:
 284                 urlh = self._request_webpage(
 285                     HEADRequest(download_url), video_id, fatal=False, note='Determining source extension')
 286                 ext = urlh and urlhandle_detect_ext(urlh)
 287             return {
 288                 'url': download_url,
 289                 'ext': ext or 'unknown_video',
 290                 'format_id': download_data.get('public_name', 'Original'),
 291                 'width': int_or_none(download_data.get('width')),
 292                 'height': int_or_none(download_data.get('height')),
 293                 'fps': int_or_none(download_data.get('fps')),
 294                 'filesize': int_or_none(download_data.get('size')),
 295                 'quality': 1,
 296             }
 297
 298
 299 class VimeoIE(VimeoBaseInfoExtractor):
 300     """Information extractor for vimeo.com."""
 301
 302     # _VALID_URL matches Vimeo URLs
 303     _VALID_URL = r'''(?x)
 304                     https?://
 305                         (?:
 306                             (?:
 307                                 www|
 308                                 player
 309                             )
 310                             \.
 311                         )?
 312                         vimeo(?:pro)?\.com/
 313                         (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
 314                         (?:[^/]+/)*?
 315                         (?:
 316                             (?:
 317                                 play_redirect_hls|
 318                                 moogaloop\.swf)\?clip_id=
 319                             )?
 320                         (?:videos?/)?
 321                         (?P<id>[0-9]+)
 322                         (?:/(?P<unlisted_hash>[\da-f]{10}))?
 323                         /?(?:[?&].*)?(?:[#].*)?$
 324                     '''
 325     IE_NAME = 'vimeo'
 326     _TESTS = [
 327         {
 328             'url': 'http://vimeo.com/56015672#at=0',
 329             'md5': '8879b6cc097e987f02484baf890129e5',
 330             'info_dict': {
 331                 'id': '56015672',
 332                 'ext': 'mp4',
 333                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
 334                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
 335                 'timestamp': 1355990239,
 336                 'upload_date': '20121220',
 337                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
 338                 'uploader_id': 'user7108434',
 339                 'uploader': 'Filippo Valsorda',
 340                 'duration': 10,
 341                 'license': 'by-sa',
 342             },
 343             'params': {
 344                 'format': 'best[protocol=https]',
 345             },
 346         },
 347         {
 348             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
 349             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
 350             'note': 'Vimeo Pro video (#1197)',
 351             'info_dict': {
 352                 'id': '68093876',
 353                 'ext': 'mp4',
 354                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
 355                 'uploader_id': 'openstreetmapus',
 356                 'uploader': 'OpenStreetMap US',
 357                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 358                 'description': 'md5:2c362968038d4499f4d79f88458590c1',
 359                 'duration': 1595,
 360                 'upload_date': '20130610',
 361                 'timestamp': 1370893156,
 362                 'license': 'by',
 363             },
 364             'params': {
 365                 'format': 'best[protocol=https]',
 366             },
 367         },
 368         {
 369             'url': 'http://player.vimeo.com/video/54469442',
 370             'md5': '619b811a4417aa4abe78dc653becf511',
 371             'note': 'Videos that embed the url in the player page',
 372             'info_dict': {
 373                 'id': '54469442',
 374                 'ext': 'mp4',
 375                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 376                 'uploader': 'Business of Software',
 377                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
 378                 'uploader_id': 'businessofsoftware',
 379                 'duration': 3610,
 380                 'description': None,
 381             },
 382             'params': {
 383                 'format': 'best[protocol=https]',
 384             },
 385         },
 386         {
 387             'url': 'http://vimeo.com/68375962',
 388             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 389             'note': 'Video protected with password',
 390             'info_dict': {
 391                 'id': '68375962',
 392                 'ext': 'mp4',
 393                 'title': 'youtube-dl password protected test video',
 394                 'timestamp': 1371200155,
 395                 'upload_date': '20130614',
 396                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 397                 'uploader_id': 'user18948128',
 398                 'uploader': 'Jaime Marquínez Ferrándiz',
 399                 'duration': 10,
 400                 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
 401             },
 402             'params': {
 403                 'format': 'best[protocol=https]',
 404                 'videopassword': 'youtube-dl',
 405             },
 406         },
 407         {
 408             'url': 'http://vimeo.com/channels/keypeele/75629013',
 409             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 410             'info_dict': {
 411                 'id': '75629013',
 412                 'ext': 'mp4',
 413                 'title': 'Key & Peele: Terrorist Interrogation',
 414                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 415                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
 416                 'uploader_id': 'atencio',
 417                 'uploader': 'Peter Atencio',
 418                 'channel_id': 'keypeele',
 419                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
 420                 'timestamp': 1380339469,
 421                 'upload_date': '20130928',
 422                 'duration': 187,
 423             },
 424             'params': {'format': 'http-1080p'},
 425         },
 426         {
 427             'url': 'http://vimeo.com/76979871',
 428             'note': 'Video with subtitles',
 429             'info_dict': {
 430                 'id': '76979871',
 431                 'ext': 'mp4',
 432                 'title': 'The New Vimeo Player (You Know, For Videos)',
 433                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 434                 'timestamp': 1381846109,
 435                 'upload_date': '20131015',
 436                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
 437                 'uploader_id': 'staff',
 438                 'uploader': 'Vimeo Staff',
 439                 'duration': 62,
 440                 'subtitles': {
 441                     'de': [{'ext': 'vtt'}],
 442                     'en': [{'ext': 'vtt'}],
 443                     'es': [{'ext': 'vtt'}],
 444                     'fr': [{'ext': 'vtt'}],
 445                 },
 446             },
 447             'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
 448         },
 449         {
 450             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 451             'url': 'https://player.vimeo.com/video/98044508',
 452             'note': 'The js code contains assignments to the same variable as the config',
 453             'info_dict': {
 454                 'id': '98044508',
 455                 'ext': 'mp4',
 456                 'title': 'Pier Solar OUYA Official Trailer',
 457                 'uploader': 'Tulio Gonçalves',
 458                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
 459                 'uploader_id': 'user28849593',
 460             },
 461         },
 462         {
 463             # contains original format
 464             'url': 'https://vimeo.com/33951933',
 465             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 466             'info_dict': {
 467                 'id': '33951933',
 468                 'ext': 'mp4',
 469                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 470                 'uploader': 'The DMCI',
 471                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
 472                 'uploader_id': 'dmci',
 473                 'timestamp': 1324343742,
 474                 'upload_date': '20111220',
 475                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 476             },
 477         },
 478         {
 479             'note': 'Contains original format not accessible in webpage',
 480             'url': 'https://vimeo.com/393756517',
 481             'md5': 'c464af248b592190a5ffbb5d33f382b0',
 482             'info_dict': {
 483                 'id': '393756517',
 484                 'ext': 'mov',
 485                 'timestamp': 1582642091,
 486                 'uploader_id': 'frameworkla',
 487                 'title': 'Straight To Hell - Sabrina: Netflix',
 488                 'uploader': 'Framework Studio',
 489                 'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
 490                 'upload_date': '20200225',
 491             },
 492         },
 493         {
 494             # only available via https://vimeo.com/channels/tributes/6213729 and
 495             # not via https://vimeo.com/6213729
 496             'url': 'https://vimeo.com/channels/tributes/6213729',
 497             'info_dict': {
 498                 'id': '6213729',
 499                 'ext': 'mp4',
 500                 'title': 'Vimeo Tribute: The Shining',
 501                 'uploader': 'Casey Donahue',
 502                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
 503                 'uploader_id': 'caseydonahue',
 504                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
 505                 'channel_id': 'tributes',
 506                 'timestamp': 1250886430,
 507                 'upload_date': '20090821',
 508                 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
 509             },
 510             'params': {
 511                 'skip_download': True,
 512             },
 513         },
 514         {
 515             # redirects to ondemand extractor and should be passed through it
 516             # for successful extraction
 517             'url': 'https://vimeo.com/73445910',
 518             'info_dict': {
 519                 'id': '73445910',
 520                 'ext': 'mp4',
 521                 'title': 'The Reluctant Revolutionary',
 522                 'uploader': '10Ft Films',
 523                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
 524                 'uploader_id': 'tenfootfilms',
 525                 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
 526                 'upload_date': '20130830',
 527                 'timestamp': 1377853339,
 528             },
 529             'params': {
 530                 'skip_download': True,
 531             },
 532             'skip': 'this page is no longer available.',
 533         },
 534         {
 535             'url': 'http://player.vimeo.com/video/68375962',
 536             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 537             'info_dict': {
 538                 'id': '68375962',
 539                 'ext': 'mp4',
 540                 'title': 'youtube-dl password protected test video',
 541                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 542                 'uploader_id': 'user18948128',
 543                 'uploader': 'Jaime Marquínez Ferrándiz',
 544                 'duration': 10,
 545             },
 546             'params': {
 547                 'format': 'best[protocol=https]',
 548                 'videopassword': 'youtube-dl',
 549             },
 550         },
 551         {
 552             'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
 553             'only_matching': True,
 554         },
 555         {
 556             'url': 'https://vimeo.com/109815029',
 557             'note': 'Video not completely processed, "failed" seed status',
 558             'only_matching': True,
 559         },
 560         {
 561             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 562             'only_matching': True,
 563         },
 564         {
 565             'url': 'https://vimeo.com/album/2632481/video/79010983',
 566             'only_matching': True,
 567         },
 568         {
 569             'url': 'https://vimeo.com/showcase/3253534/video/119195465',
 570             'note': 'A video in a password protected album (showcase)',
 571             'info_dict': {
 572                 'id': '119195465',
 573                 'ext': 'mp4',
 574                 'title': 'youtube-dl test video \'ä"BaW_jenozKc',
 575                 'uploader': 'Philipp Hagemeister',
 576                 'uploader_id': 'user20132939',
 577                 'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
 578                 'upload_date': '20150209',
 579                 'timestamp': 1423518307,
 580             },
 581             'params': {
 582                 'format': 'best[protocol=https]',
 583                 'videopassword': 'youtube-dl',
 584             },
 585         },
 586         {
 587             # source file returns 403: Forbidden
 588             'url': 'https://vimeo.com/7809605',
 589             'only_matching': True,
 590         },
 591         {
 592             'note': 'Direct URL with hash',
 593             'url': 'https://vimeo.com/160743502/abd0e13fb4',
 594             'info_dict': {
 595                 'id': '160743502',
 596                 'ext': 'mp4',
 597                 'uploader': 'Julian Tryba',
 598                 'uploader_id': 'aliniamedia',
 599                 'title': 'Harrisville New Hampshire',
 600                 'timestamp': 1459259666,
 601                 'upload_date': '20160329',
 602             },
 603             'params': {'skip_download': True},
 604         },
 605         {
 606             'url': 'https://vimeo.com/138909882',
 607             'info_dict': {
 608                 'id': '138909882',
 609                 'ext': 'mp4',
 610                 'title': 'Eastnor Castle 2015 Firework Champions - The Promo!',
 611                 'description': 'md5:5967e090768a831488f6e74b7821b3c1',
 612                 'uploader_id': 'fireworkchampions',
 613                 'uploader': 'Firework Champions',
 614                 'upload_date': '20150910',
 615                 'timestamp': 1441901895,
 616             },
 617             'params': {
 618                 'skip_download': True,
 619                 'format': 'Original',
 620             },
 621         },
 622         {
 623             'url': 'https://vimeo.com/channels/staffpicks/143603739',
 624             'info_dict': {
 625                 'id': '143603739',
 626                 'ext': 'mp4',
 627                 'uploader': 'Karim Huu Do',
 628                 'timestamp': 1445846953,
 629                 'upload_date': '20151026',
 630                 'title': 'The Shoes - Submarine Feat. Blaine Harrison',
 631                 'uploader_id': 'karimhd',
 632                 'description': 'md5:8e2eea76de4504c2e8020a9bcfa1e843',
 633             },
 634             'params': {'skip_download': 'm3u8'},
 635         },
 636         {
 637             # requires passing unlisted_hash(a52724358e) to load_download_config request
 638             'url': 'https://vimeo.com/392479337/a52724358e',
 639             'only_matching': True,
 640         },
 641         # https://gettingthingsdone.com/workflowmap/
 642         # vimeo embed with check-password page protected by Referer header
 643     ]
 644
 645     @staticmethod
 646     def _smuggle_referrer(url, referrer_url):
 647         return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
 648
 649     @staticmethod
 650     def _extract_urls(url, webpage):
 651         urls = []
 652         # Look for embedded (iframe) Vimeo player
 653         for mobj in re.finditer(
 654                 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
 655                 webpage):
 656             urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
 657         PLAIN_EMBED_RE = (
 658             # Look for embedded (swf embed) Vimeo player
 659             r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
 660             # Look more for non-standard embedded Vimeo player
 661             r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
 662         )
 663         for embed_re in PLAIN_EMBED_RE:
 664             for mobj in re.finditer(embed_re, webpage):
 665                 urls.append(mobj.group('url'))
 666         return urls
 667
 668     @staticmethod
 669     def _extract_url(url, webpage):
 670         urls = VimeoIE._extract_urls(url, webpage)
 671         return urls[0] if urls else None
 672
 673     def _verify_player_video_password(self, url, video_id, headers):
 674         password = self._get_video_password()
 675         data = urlencode_postdata({
 676             'password': base64.b64encode(password.encode()),
 677         })
 678         headers = merge_dicts(headers, {
 679             'Content-Type': 'application/x-www-form-urlencoded',
 680         })
 681         checked = self._download_json(
 682             url + '/check-password', video_id,
 683             'Verifying the password', data=data, headers=headers)
 684         if checked is False:
 685             raise ExtractorError('Wrong video password', expected=True)
 686         return checked
 687
 688     def _real_initialize(self):
 689         self._login()
 690
 691     def _extract_from_api(self, video_id, unlisted_hash=None):
 692         token = self._download_json(
 693             'https://vimeo.com/_rv/jwt', video_id, headers={
 694                 'X-Requested-With': 'XMLHttpRequest'
 695             })['token']
 696         api_url = 'https://api.vimeo.com/videos/' + video_id
 697         if unlisted_hash:
 698             api_url += ':' + unlisted_hash
 699         video = self._download_json(
 700             api_url, video_id, headers={
 701                 'Authorization': 'jwt ' + token,
 702             }, query={
 703                 'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
 704             })
 705         info = self._parse_config(self._download_json(
 706             video['config_url'], video_id), video_id)
 707         self._vimeo_sort_formats(info['formats'])
 708         get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
 709         info.update({
 710             'description': video.get('description'),
 711             'license': video.get('license'),
 712             'release_timestamp': get_timestamp('release'),
 713             'timestamp': get_timestamp('created'),
 714             'view_count': int_or_none(try_get(video, lambda x: x['stats']['plays'])),
 715         })
 716         connections = try_get(
 717             video, lambda x: x['metadata']['connections'], dict) or {}
 718         for k in ('comment', 'like'):
 719             info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total']))
 720         return info
 721
 722     def _try_album_password(self, url):
 723         album_id = self._search_regex(
 724             r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None)
 725         if not album_id:
 726             return
 727         viewer = self._download_json(
 728             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
 729         if not viewer:
 730             webpage = self._download_webpage(url, album_id)
 731             viewer = self._parse_json(self._search_regex(
 732                 r'bootstrap_data\s*=\s*({.+?})</script>',
 733                 webpage, 'bootstrap data'), album_id)['viewer']
 734         jwt = viewer['jwt']
 735         album = self._download_json(
 736             'https://api.vimeo.com/albums/' + album_id,
 737             album_id, headers={'Authorization': 'jwt ' + jwt},
 738             query={'fields': 'description,name,privacy'})
 739         if try_get(album, lambda x: x['privacy']['view']) == 'password':
 740             password = self.get_param('videopassword')
 741             if not password:
 742                 raise ExtractorError(
 743                     'This album is protected by a password, use the --video-password option',
 744                     expected=True)
 745             self._set_vimeo_cookie('vuid', viewer['vuid'])
 746             try:
 747                 self._download_json(
 748                     'https://vimeo.com/showcase/%s/auth' % album_id,
 749                     album_id, 'Verifying the password', data=urlencode_postdata({
 750                         'password': password,
 751                         'token': viewer['xsrft'],
 752                     }), headers={
 753                         'X-Requested-With': 'XMLHttpRequest',
 754                     })
 755             except ExtractorError as e:
 756                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
 757                     raise ExtractorError('Wrong password', expected=True)
 758                 raise
 759
 760     def _real_extract(self, url):
 761         url, data = unsmuggle_url(url, {})
 762         headers = std_headers.copy()
 763         if 'http_headers' in data:
 764             headers.update(data['http_headers'])
 765         if 'Referer' not in headers:
 766             headers['Referer'] = url
 767
 768         # Extract ID from URL
 769         mobj = self._match_valid_url(url).groupdict()
 770         video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash')
 771         if unlisted_hash:
 772             return self._extract_from_api(video_id, unlisted_hash)
 773
 774         orig_url = url
 775         is_pro = 'vimeopro.com/' in url
 776         if is_pro:
 777             # some videos require portfolio_id to be present in player url
 778             # https://github.com/ytdl-org/youtube-dl/issues/20070
 779             url = self._extract_url(url, self._download_webpage(url, video_id))
 780             if not url:
 781                 url = 'https://vimeo.com/' + video_id
 782         elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
 783             url = 'https://vimeo.com/' + video_id
 784
 785         self._try_album_password(url)
 786         try:
 787             # Retrieve video webpage to extract further information
 788             webpage, urlh = self._download_webpage_handle(
 789                 url, video_id, headers=headers)
 790             redirect_url = urlh.geturl()
 791         except ExtractorError as ee:
 792             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 793                 errmsg = ee.cause.read()
 794                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 795                     raise ExtractorError(
 796                         'Cannot download embed-only video without embedding '
 797                         'URL. Please call yt-dlp with the URL of the page '
 798                         'that embeds this video.',
 799                         expected=True)
 800             raise
 801
 802         if '://player.vimeo.com/video/' in url:
 803             config = self._parse_json(self._search_regex(
 804                 r'\bconfig\s*=\s*({.+?})\s*;', webpage, 'info section'), video_id)
 805             if config.get('view') == 4:
 806                 config = self._verify_player_video_password(
 807                     redirect_url, video_id, headers)
 808             info = self._parse_config(config, video_id)
 809             self._vimeo_sort_formats(info['formats'])
 810             return info
 811
 812         if re.search(r'<form[^>]+?id="pw_form"', webpage):
 813             video_password = self._get_video_password()
 814             token, vuid = self._extract_xsrft_and_vuid(webpage)
 815             webpage = self._verify_video_password(
 816                 redirect_url, video_id, video_password, token, vuid)
 817
 818         vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
 819         if vimeo_config:
 820             seed_status = vimeo_config.get('seed_status') or {}
 821             if seed_status.get('state') == 'failed':
 822                 raise ExtractorError(
 823                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 824                     expected=True)
 825
 826         cc_license = None
 827         timestamp = None
 828         video_description = None
 829         info_dict = {}
 830         config_url = None
 831
 832         channel_id = self._search_regex(
 833             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
 834         if channel_id:
 835             config_url = self._html_search_regex(
 836                 r'\bdata-config-url="([^"]+)"', webpage, 'config URL', default=None)
 837             video_description = clean_html(get_element_by_class('description', webpage))
 838             info_dict.update({
 839                 'channel_id': channel_id,
 840                 'channel_url': 'https://vimeo.com/channels/' + channel_id,
 841             })
 842         if not config_url:
 843             page_config = self._parse_json(self._search_regex(
 844                 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
 845                 webpage, 'page config', default='{}'), video_id, fatal=False)
 846             if not page_config:
 847                 return self._extract_from_api(video_id)
 848             config_url = page_config['player']['config_url']
 849             cc_license = page_config.get('cc_license')
 850             clip = page_config.get('clip') or {}
 851             timestamp = clip.get('uploaded_on')
 852             video_description = clean_html(
 853                 clip.get('description') or page_config.get('description_html_escaped'))
 854         config = self._download_json(config_url, video_id)
 855         video = config.get('video') or {}
 856         vod = video.get('vod') or {}
 857
 858         def is_rented():
 859             if '>You rented this title.<' in webpage:
 860                 return True
 861             if try_get(config, lambda x: x['user']['purchased']):
 862                 return True
 863             for purchase_option in (vod.get('purchase_options') or []):
 864                 if purchase_option.get('purchased'):
 865                     return True
 866                 label = purchase_option.get('label_string')
 867                 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
 868                     return True
 869             return False
 870
 871         if is_rented() and vod.get('is_trailer'):
 872             feature_id = vod.get('feature_id')
 873             if feature_id and not data.get('force_feature_id', False):
 874                 return self.url_result(smuggle_url(
 875                     'https://player.vimeo.com/player/%s' % feature_id,
 876                     {'force_feature_id': True}), 'Vimeo')
 877
 878         if not video_description:
 879             video_description = self._html_search_regex(
 880                 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 881                 webpage, 'description', default=None)
 882         if not video_description:
 883             video_description = self._html_search_meta(
 884                 ['description', 'og:description', 'twitter:description'],
 885                 webpage, default=None)
 886         if not video_description and is_pro:
 887             orig_webpage = self._download_webpage(
 888                 orig_url, video_id,
 889                 note='Downloading webpage for description',
 890                 fatal=False)
 891             if orig_webpage:
 892                 video_description = self._html_search_meta(
 893                     'description', orig_webpage, default=None)
 894         if not video_description:
 895             self.report_warning('Cannot find video description')
 896
 897         if not timestamp:
 898             timestamp = self._search_regex(
 899                 r'<time[^>]+datetime="([^"]+)"', webpage,
 900                 'timestamp', default=None)
 901
 902         view_count = int_or_none(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count', default=None))
 903         like_count = int_or_none(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count', default=None))
 904         comment_count = int_or_none(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count', default=None))
 905
 906         formats = []
 907
 908         source_format = self._extract_original_format(
 909             'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
 910         if source_format:
 911             formats.append(source_format)
 912
 913         info_dict_config = self._parse_config(config, video_id)
 914         formats.extend(info_dict_config['formats'])
 915         self._vimeo_sort_formats(formats)
 916
 917         json_ld = self._search_json_ld(webpage, video_id, default={})
 918
 919         if not cc_license:
 920             cc_license = self._search_regex(
 921                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
 922                 webpage, 'license', default=None, group='license')
 923
 924         info_dict.update({
 925             'formats': formats,
 926             'timestamp': unified_timestamp(timestamp),
 927             'description': video_description,
 928             'webpage_url': url,
 929             'view_count': view_count,
 930             'like_count': like_count,
 931             'comment_count': comment_count,
 932             'license': cc_license,
 933         })
 934
 935         return merge_dicts(info_dict, info_dict_config, json_ld)
 936
 937
 938 class VimeoOndemandIE(VimeoIE):
 939     IE_NAME = 'vimeo:ondemand'
 940     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)'
 941     _TESTS = [{
 942         # ondemand video not available via https://vimeo.com/id
 943         'url': 'https://vimeo.com/ondemand/20704',
 944         'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
 945         'info_dict': {
 946             'id': '105442900',
 947             'ext': 'mp4',
 948             'title': 'המעבדה - במאי יותם פלדמן',
 949             'uploader': 'גם סרטים',
 950             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
 951             'uploader_id': 'gumfilms',
 952             'description': 'md5:4c027c965e439de4baab621e48b60791',
 953             'upload_date': '20140906',
 954             'timestamp': 1410032453,
 955         },
 956         'params': {
 957             'format': 'best[protocol=https]',
 958         },
 959         'expected_warnings': ['Unable to download JSON metadata'],
 960     }, {
 961         # requires Referer to be passed along with og:video:url
 962         'url': 'https://vimeo.com/ondemand/36938/126682985',
 963         'info_dict': {
 964             'id': '126584684',
 965             'ext': 'mp4',
 966             'title': 'Rävlock, rätt läte på rätt plats',
 967             'uploader': 'Lindroth & Norin',
 968             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
 969             'uploader_id': 'lindrothnorin',
 970             'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
 971             'upload_date': '20150502',
 972             'timestamp': 1430586422,
 973         },
 974         'params': {
 975             'skip_download': True,
 976         },
 977         'expected_warnings': ['Unable to download JSON metadata'],
 978     }, {
 979         'url': 'https://vimeo.com/ondemand/nazmaalik',
 980         'only_matching': True,
 981     }, {
 982         'url': 'https://vimeo.com/ondemand/141692381',
 983         'only_matching': True,
 984     }, {
 985         'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
 986         'only_matching': True,
 987     }]
 988
 989
 990 class VimeoChannelIE(VimeoBaseInfoExtractor):
 991     IE_NAME = 'vimeo:channel'
 992     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 993     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 994     _TITLE = None
 995     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 996     _TESTS = [{
 997         'url': 'https://vimeo.com/channels/tributes',
 998         'info_dict': {
 999             'id': 'tributes',
1000             'title': 'Vimeo Tributes',
1001         },
1002         'playlist_mincount': 25,
1003     }]
1004     _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
1005
1006     def _page_url(self, base_url, pagenum):
1007         return '%s/videos/page:%d/' % (base_url, pagenum)
1008
1009     def _extract_list_title(self, webpage):
1010         return self._TITLE or self._html_search_regex(
1011             self._TITLE_RE, webpage, 'list title', fatal=False)
1012
1013     def _title_and_entries(self, list_id, base_url):
1014         for pagenum in itertools.count(1):
1015             page_url = self._page_url(base_url, pagenum)
1016             webpage = self._download_webpage(
1017                 page_url, list_id,
1018                 'Downloading page %s' % pagenum)
1019
1020             if pagenum == 1:
1021                 yield self._extract_list_title(webpage)
1022
1023             # Try extracting href first since not all videos are available via
1024             # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
1025             clips = re.findall(
1026                 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
1027             if clips:
1028                 for video_id, video_url, video_title in clips:
1029                     yield self.url_result(
1030                         compat_urlparse.urljoin(base_url, video_url),
1031                         VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
1032             # More relaxed fallback
1033             else:
1034                 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
1035                     yield self.url_result(
1036                         'https://vimeo.com/%s' % video_id,
1037                         VimeoIE.ie_key(), video_id=video_id)
1038
1039             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
1040                 break
1041
1042     def _extract_videos(self, list_id, base_url):
1043         title_and_entries = self._title_and_entries(list_id, base_url)
1044         list_title = next(title_and_entries)
1045         return self.playlist_result(title_and_entries, list_id, list_title)
1046
1047     def _real_extract(self, url):
1048         channel_id = self._match_id(url)
1049         return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
1050
1051
1052 class VimeoUserIE(VimeoChannelIE):
1053     IE_NAME = 'vimeo:user'
1054     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
1055     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
1056     _TESTS = [{
1057         'url': 'https://vimeo.com/nkistudio/videos',
1058         'info_dict': {
1059             'title': 'Nki',
1060             'id': 'nkistudio',
1061         },
1062         'playlist_mincount': 66,
1063     }]
1064     _BASE_URL_TEMPL = 'https://vimeo.com/%s'
1065
1066
1067 class VimeoAlbumIE(VimeoBaseInfoExtractor):
1068     IE_NAME = 'vimeo:album'
1069     _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
1070     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
1071     _TESTS = [{
1072         'url': 'https://vimeo.com/album/2632481',
1073         'info_dict': {
1074             'id': '2632481',
1075             'title': 'Staff Favorites: November 2013',
1076         },
1077         'playlist_mincount': 13,
1078     }, {
1079         'note': 'Password-protected album',
1080         'url': 'https://vimeo.com/album/3253534',
1081         'info_dict': {
1082             'title': 'test',
1083             'id': '3253534',
1084         },
1085         'playlist_count': 1,
1086         'params': {
1087             'videopassword': 'youtube-dl',
1088         }
1089     }]
1090     _PAGE_SIZE = 100
1091
1092     def _fetch_page(self, album_id, authorization, hashed_pass, page):
1093         api_page = page + 1
1094         query = {
1095             'fields': 'link,uri',
1096             'page': api_page,
1097             'per_page': self._PAGE_SIZE,
1098         }
1099         if hashed_pass:
1100             query['_hashed_pass'] = hashed_pass
1101         try:
1102             videos = self._download_json(
1103                 'https://api.vimeo.com/albums/%s/videos' % album_id,
1104                 album_id, 'Downloading page %d' % api_page, query=query, headers={
1105                     'Authorization': 'jwt ' + authorization,
1106                 })['data']
1107         except ExtractorError as e:
1108             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
1109                 return
1110         for video in videos:
1111             link = video.get('link')
1112             if not link:
1113                 continue
1114             uri = video.get('uri')
1115             video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
1116             yield self.url_result(link, VimeoIE.ie_key(), video_id)
1117
1118     def _real_extract(self, url):
1119         album_id = self._match_id(url)
1120         viewer = self._download_json(
1121             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
1122         if not viewer:
1123             webpage = self._download_webpage(url, album_id)
1124             viewer = self._parse_json(self._search_regex(
1125                 r'bootstrap_data\s*=\s*({.+?})</script>',
1126                 webpage, 'bootstrap data'), album_id)['viewer']
1127         jwt = viewer['jwt']
1128         album = self._download_json(
1129             'https://api.vimeo.com/albums/' + album_id,
1130             album_id, headers={'Authorization': 'jwt ' + jwt},
1131             query={'fields': 'description,name,privacy'})
1132         hashed_pass = None
1133         if try_get(album, lambda x: x['privacy']['view']) == 'password':
1134             password = self.get_param('videopassword')
1135             if not password:
1136                 raise ExtractorError(
1137                     'This album is protected by a password, use the --video-password option',
1138                     expected=True)
1139             self._set_vimeo_cookie('vuid', viewer['vuid'])
1140             try:
1141                 hashed_pass = self._download_json(
1142                     'https://vimeo.com/showcase/%s/auth' % album_id,
1143                     album_id, 'Verifying the password', data=urlencode_postdata({
1144                         'password': password,
1145                         'token': viewer['xsrft'],
1146                     }), headers={
1147                         'X-Requested-With': 'XMLHttpRequest',
1148                     })['hashed_pass']
1149             except ExtractorError as e:
1150                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
1151                     raise ExtractorError('Wrong password', expected=True)
1152                 raise
1153         entries = OnDemandPagedList(functools.partial(
1154             self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
1155         return self.playlist_result(
1156             entries, album_id, album.get('name'), album.get('description'))
1157
1158
1159 class VimeoGroupsIE(VimeoChannelIE):
1160     IE_NAME = 'vimeo:group'
1161     _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
1162     _TESTS = [{
1163         'url': 'https://vimeo.com/groups/meetup',
1164         'info_dict': {
1165             'id': 'meetup',
1166             'title': 'Vimeo Meetup!',
1167         },
1168         'playlist_mincount': 27,
1169     }]
1170     _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
1171
1172
1173 class VimeoReviewIE(VimeoBaseInfoExtractor):
1174     IE_NAME = 'vimeo:review'
1175     IE_DESC = 'Review pages on vimeo'
1176     _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
1177     _TESTS = [{
1178         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1179         'md5': 'c507a72f780cacc12b2248bb4006d253',
1180         'info_dict': {
1181             'id': '75524534',
1182             'ext': 'mp4',
1183             'title': "DICK HARDWICK 'Comedian'",
1184             'uploader': 'Richard Hardwick',
1185             'uploader_id': 'user21297594',
1186             'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1187         },
1188     }, {
1189         'note': 'video player needs Referer',
1190         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1191         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1192         'info_dict': {
1193             'id': '91613211',
1194             'ext': 'mp4',
1195             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1196             'uploader': 'DevWeek Events',
1197             'duration': 2773,
1198             'thumbnail': r're:^https?://.*\.jpg$',
1199             'uploader_id': 'user22258446',
1200         },
1201         'skip': 'video gone',
1202     }, {
1203         'note': 'Password protected',
1204         'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1205         'info_dict': {
1206             'id': '138823582',
1207             'ext': 'mp4',
1208             'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1209             'uploader': 'TMB',
1210             'uploader_id': 'user37284429',
1211         },
1212         'params': {
1213             'videopassword': 'holygrail',
1214         },
1215         'skip': 'video gone',
1216     }]
1217
1218     def _real_initialize(self):
1219         self._login()
1220
1221     def _real_extract(self, url):
1222         page_url, video_id = self._match_valid_url(url).groups()
1223         data = self._download_json(
1224             page_url.replace('/review/', '/review/data/'), video_id)
1225         if data.get('isLocked') is True:
1226             video_password = self._get_video_password()
1227             viewer = self._download_json(
1228                 'https://vimeo.com/_rv/viewer', video_id)
1229             webpage = self._verify_video_password(
1230                 'https://vimeo.com/' + video_id, video_id,
1231                 video_password, viewer['xsrft'], viewer['vuid'])
1232             clip_page_config = self._parse_json(self._search_regex(
1233                 r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
1234                 webpage, 'clip page config'), video_id)
1235             config_url = clip_page_config['player']['config_url']
1236             clip_data = clip_page_config.get('clip') or {}
1237         else:
1238             clip_data = data['clipData']
1239             config_url = clip_data['configUrl']
1240         config = self._download_json(config_url, video_id)
1241         info_dict = self._parse_config(config, video_id)
1242         source_format = self._extract_original_format(
1243             page_url + '/action', video_id)
1244         if source_format:
1245             info_dict['formats'].append(source_format)
1246         self._vimeo_sort_formats(info_dict['formats'])
1247         info_dict['description'] = clean_html(clip_data.get('description'))
1248         return info_dict
1249
1250
1251 class VimeoWatchLaterIE(VimeoChannelIE):
1252     IE_NAME = 'vimeo:watchlater'
1253     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
1254     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1255     _TITLE = 'Watch Later'
1256     _LOGIN_REQUIRED = True
1257     _TESTS = [{
1258         'url': 'https://vimeo.com/watchlater',
1259         'only_matching': True,
1260     }]
1261
1262     def _real_initialize(self):
1263         self._login()
1264
1265     def _page_url(self, base_url, pagenum):
1266         url = '%s/page:%d/' % (base_url, pagenum)
1267         request = sanitized_Request(url)
1268         # Set the header to get a partial html page with the ids,
1269         # the normal page doesn't contain them.
1270         request.add_header('X-Requested-With', 'XMLHttpRequest')
1271         return request
1272
1273     def _real_extract(self, url):
1274         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1275
1276
1277 class VimeoLikesIE(VimeoChannelIE):
1278     _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1279     IE_NAME = 'vimeo:likes'
1280     IE_DESC = 'Vimeo user likes'
1281     _TESTS = [{
1282         'url': 'https://vimeo.com/user755559/likes/',
1283         'playlist_mincount': 293,
1284         'info_dict': {
1285             'id': 'user755559',
1286             'title': 'urza’s Likes',
1287         },
1288     }, {
1289         'url': 'https://vimeo.com/stormlapse/likes',
1290         'only_matching': True,
1291     }]
1292
1293     def _page_url(self, base_url, pagenum):
1294         return '%s/page:%d/' % (base_url, pagenum)
1295
1296     def _real_extract(self, url):
1297         user_id = self._match_id(url)
1298         return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
1299
1300
1301 class VHXEmbedIE(VimeoBaseInfoExtractor):
1302     IE_NAME = 'vhx:embed'
1303     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1304
1305     @staticmethod
1306     def _extract_url(webpage):
1307         mobj = re.search(
1308             r'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage)
1309         return unescapeHTML(mobj.group(1)) if mobj else None
1310
1311     def _real_extract(self, url):
1312         video_id = self._match_id(url)
1313         webpage = self._download_webpage(url, video_id)
1314         config_url = self._parse_json(self._search_regex(
1315             r'window\.OTTData\s*=\s*({.+})', webpage,
1316             'ott data'), video_id, js_to_json)['config_url']
1317         config = self._download_json(config_url, video_id)
1318         info = self._parse_config(config, video_id)
1319         info['id'] = video_id
1320         self._vimeo_sort_formats(info['formats'])
1321         return info