yt_dlp/extractor/vimeo.py

   1 import base64
   2 import functools
   3 import re
   4 import itertools
   5
   6 from .common import InfoExtractor
   7 from ..compat import (
   8     compat_HTTPError,
   9     compat_str,
  10     compat_urlparse,
  11 )
  12 from ..utils import (
  13     clean_html,
  14     determine_ext,
  15     ExtractorError,
  16     get_element_by_class,
  17     HEADRequest,
  18     js_to_json,
  19     int_or_none,
  20     merge_dicts,
  21     OnDemandPagedList,
  22     parse_filesize,
  23     parse_iso8601,
  24     parse_qs,
  25     sanitized_Request,
  26     smuggle_url,
  27     str_or_none,
  28     try_get,
  29     unified_timestamp,
  30     unsmuggle_url,
  31     urlencode_postdata,
  32     urljoin,
  33     urlhandle_detect_ext,
  34 )
  35
  36
  37 class VimeoBaseInfoExtractor(InfoExtractor):
  38     _NETRC_MACHINE = 'vimeo'
  39     _LOGIN_REQUIRED = False
  40     _LOGIN_URL = 'https://vimeo.com/log_in'
  41
  42     @staticmethod
  43     def _smuggle_referrer(url, referrer_url):
  44         return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
  45
  46     def _unsmuggle_headers(self, url):
  47         """@returns (url, smuggled_data, headers)"""
  48         url, data = unsmuggle_url(url, {})
  49         headers = self.get_param('http_headers').copy()
  50         if 'http_headers' in data:
  51             headers.update(data['http_headers'])
  52         return url, data, headers
  53
  54     def _perform_login(self, username, password):
  55         webpage = self._download_webpage(
  56             self._LOGIN_URL, None, 'Downloading login page')
  57         token, vuid = self._extract_xsrft_and_vuid(webpage)
  58         data = {
  59             'action': 'login',
  60             'email': username,
  61             'password': password,
  62             'service': 'vimeo',
  63             'token': token,
  64         }
  65         self._set_vimeo_cookie('vuid', vuid)
  66         try:
  67             self._download_webpage(
  68                 self._LOGIN_URL, None, 'Logging in',
  69                 data=urlencode_postdata(data), headers={
  70                     'Content-Type': 'application/x-www-form-urlencoded',
  71                     'Referer': self._LOGIN_URL,
  72                 })
  73         except ExtractorError as e:
  74             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418:
  75                 raise ExtractorError(
  76                     'Unable to log in: bad username or password',
  77                     expected=True)
  78             raise ExtractorError('Unable to log in')
  79
  80     def _real_initialize(self):
  81         if self._LOGIN_REQUIRED and not self._get_cookies('https://vimeo.com').get('vuid'):
  82             self._raise_login_required()
  83
  84     def _get_video_password(self):
  85         password = self.get_param('videopassword')
  86         if password is None:
  87             raise ExtractorError(
  88                 'This video is protected by a password, use the --video-password option',
  89                 expected=True)
  90         return password
  91
  92     def _verify_video_password(self, url, video_id, password, token, vuid):
  93         if url.startswith('http://'):
  94             # vimeo only supports https now, but the user can give an http url
  95             url = url.replace('http://', 'https://')
  96         self._set_vimeo_cookie('vuid', vuid)
  97         return self._download_webpage(
  98             url + '/password', video_id, 'Verifying the password',
  99             'Wrong password', data=urlencode_postdata({
 100                 'password': password,
 101                 'token': token,
 102             }), headers={
 103                 'Content-Type': 'application/x-www-form-urlencoded',
 104                 'Referer': url,
 105             })
 106
 107     def _extract_xsrft_and_vuid(self, webpage):
 108         xsrft = self._search_regex(
 109             r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
 110             webpage, 'login token', group='xsrft')
 111         vuid = self._search_regex(
 112             r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
 113             webpage, 'vuid', group='vuid')
 114         return xsrft, vuid
 115
 116     def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
 117         vimeo_config = self._search_regex(
 118             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
 119             webpage, 'vimeo config', *args, **kwargs)
 120         if vimeo_config:
 121             return self._parse_json(vimeo_config, video_id)
 122
 123     def _set_vimeo_cookie(self, name, value):
 124         self._set_cookie('vimeo.com', name, value)
 125
 126     def _vimeo_sort_formats(self, formats):
 127         # Note: Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
 128         # at the same time without actual units specified.
 129         self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source'))
 130
 131     def _parse_config(self, config, video_id):
 132         video_data = config['video']
 133         video_title = video_data.get('title')
 134         live_event = video_data.get('live_event') or {}
 135         is_live = live_event.get('status') == 'started'
 136         request = config.get('request') or {}
 137
 138         formats = []
 139         subtitles = {}
 140
 141         config_files = video_data.get('files') or request.get('files') or {}
 142         for f in (config_files.get('progressive') or []):
 143             video_url = f.get('url')
 144             if not video_url:
 145                 continue
 146             formats.append({
 147                 'url': video_url,
 148                 'format_id': 'http-%s' % f.get('quality'),
 149                 'source_preference': 10,
 150                 'width': int_or_none(f.get('width')),
 151                 'height': int_or_none(f.get('height')),
 152                 'fps': int_or_none(f.get('fps')),
 153                 'tbr': int_or_none(f.get('bitrate')),
 154             })
 155
 156         # TODO: fix handling of 308 status code returned for live archive manifest requests
 157         sep_pattern = r'/sep/video/'
 158         for files_type in ('hls', 'dash'):
 159             for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items():
 160                 manifest_url = cdn_data.get('url')
 161                 if not manifest_url:
 162                     continue
 163                 format_id = '%s-%s' % (files_type, cdn_name)
 164                 sep_manifest_urls = []
 165                 if re.search(sep_pattern, manifest_url):
 166                     for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
 167                         sep_manifest_urls.append((format_id + suffix, re.sub(
 168                             sep_pattern, '/%s/' % repl, manifest_url)))
 169                 else:
 170                     sep_manifest_urls = [(format_id, manifest_url)]
 171                 for f_id, m_url in sep_manifest_urls:
 172                     if files_type == 'hls':
 173                         fmts, subs = self._extract_m3u8_formats_and_subtitles(
 174                             m_url, video_id, 'mp4', live=is_live, m3u8_id=f_id,
 175                             note='Downloading %s m3u8 information' % cdn_name,
 176                             fatal=False)
 177                         formats.extend(fmts)
 178                         self._merge_subtitles(subs, target=subtitles)
 179                     elif files_type == 'dash':
 180                         if 'json=1' in m_url:
 181                             real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
 182                             if real_m_url:
 183                                 m_url = real_m_url
 184                         fmts, subs = self._extract_mpd_formats_and_subtitles(
 185                             m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
 186                             'Downloading %s MPD information' % cdn_name,
 187                             fatal=False)
 188                         formats.extend(fmts)
 189                         self._merge_subtitles(subs, target=subtitles)
 190
 191         live_archive = live_event.get('archive') or {}
 192         live_archive_source_url = live_archive.get('source_url')
 193         if live_archive_source_url and live_archive.get('status') == 'done':
 194             formats.append({
 195                 'format_id': 'live-archive-source',
 196                 'url': live_archive_source_url,
 197                 'quality': 10,
 198             })
 199
 200         for tt in (request.get('text_tracks') or []):
 201             subtitles.setdefault(tt['lang'], []).append({
 202                 'ext': 'vtt',
 203                 'url': urljoin('https://vimeo.com', tt['url']),
 204             })
 205
 206         thumbnails = []
 207         if not is_live:
 208             for key, thumb in (video_data.get('thumbs') or {}).items():
 209                 thumbnails.append({
 210                     'id': key,
 211                     'width': int_or_none(key),
 212                     'url': thumb,
 213                 })
 214             thumbnail = video_data.get('thumbnail')
 215             if thumbnail:
 216                 thumbnails.append({
 217                     'url': thumbnail,
 218                 })
 219
 220         owner = video_data.get('owner') or {}
 221         video_uploader_url = owner.get('url')
 222
 223         duration = int_or_none(video_data.get('duration'))
 224         chapter_data = try_get(config, lambda x: x['embed']['chapters']) or []
 225         chapters = [{
 226             'title': current_chapter.get('title'),
 227             'start_time': current_chapter.get('timecode'),
 228             'end_time': next_chapter.get('timecode'),
 229         } for current_chapter, next_chapter in zip(chapter_data, chapter_data[1:] + [{'timecode': duration}])]
 230         if chapters and chapters[0]['start_time']:  # Chapters may not start from 0
 231             chapters[:0] = [{'title': '<Untitled>', 'start_time': 0, 'end_time': chapters[0]['start_time']}]
 232
 233         return {
 234             'id': str_or_none(video_data.get('id')) or video_id,
 235             'title': video_title,
 236             'uploader': owner.get('name'),
 237             'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
 238             'uploader_url': video_uploader_url,
 239             'thumbnails': thumbnails,
 240             'duration': duration,
 241             'chapters': chapters or None,
 242             'formats': formats,
 243             'subtitles': subtitles,
 244             'is_live': is_live,
 245         }
 246
 247     def _extract_original_format(self, url, video_id, unlisted_hash=None):
 248         query = {'action': 'load_download_config'}
 249         if unlisted_hash:
 250             query['unlisted_hash'] = unlisted_hash
 251         download_data = self._download_json(
 252             url, video_id, fatal=False, query=query,
 253             headers={'X-Requested-With': 'XMLHttpRequest'},
 254             expected_status=(403, 404)) or {}
 255         source_file = download_data.get('source_file')
 256         download_url = try_get(source_file, lambda x: x['download_url'])
 257         if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 258             source_name = source_file.get('public_name', 'Original')
 259             if self._is_valid_url(download_url, video_id, '%s video' % source_name):
 260                 ext = (try_get(
 261                     source_file, lambda x: x['extension'],
 262                     compat_str) or determine_ext(
 263                     download_url, None) or 'mp4').lower()
 264                 return {
 265                     'url': download_url,
 266                     'ext': ext,
 267                     'width': int_or_none(source_file.get('width')),
 268                     'height': int_or_none(source_file.get('height')),
 269                     'filesize': parse_filesize(source_file.get('size')),
 270                     'format_id': source_name,
 271                     'quality': 1,
 272                 }
 273
 274         jwt_response = self._download_json(
 275             'https://vimeo.com/_rv/viewer', video_id, note='Downloading jwt token', fatal=False) or {}
 276         if not jwt_response.get('jwt'):
 277             return
 278         headers = {'Authorization': 'jwt %s' % jwt_response['jwt']}
 279         original_response = self._download_json(
 280             f'https://api.vimeo.com/videos/{video_id}', video_id,
 281             headers=headers, fatal=False, expected_status=(403, 404)) or {}
 282         for download_data in original_response.get('download') or []:
 283             download_url = download_data.get('link')
 284             if not download_url or download_data.get('quality') != 'source':
 285                 continue
 286             ext = determine_ext(parse_qs(download_url).get('filename', [''])[0].lower(), default_ext=None)
 287             if not ext:
 288                 urlh = self._request_webpage(
 289                     HEADRequest(download_url), video_id, fatal=False, note='Determining source extension')
 290                 ext = urlh and urlhandle_detect_ext(urlh)
 291             return {
 292                 'url': download_url,
 293                 'ext': ext or 'unknown_video',
 294                 'format_id': download_data.get('public_name', 'Original'),
 295                 'width': int_or_none(download_data.get('width')),
 296                 'height': int_or_none(download_data.get('height')),
 297                 'fps': int_or_none(download_data.get('fps')),
 298                 'filesize': int_or_none(download_data.get('size')),
 299                 'quality': 1,
 300             }
 301
 302
 303 class VimeoIE(VimeoBaseInfoExtractor):
 304     """Information extractor for vimeo.com."""
 305
 306     # _VALID_URL matches Vimeo URLs
 307     _VALID_URL = r'''(?x)
 308                     https?://
 309                         (?:
 310                             (?:
 311                                 www|
 312                                 player
 313                             )
 314                             \.
 315                         )?
 316                         vimeo(?:pro)?\.com/
 317                         (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
 318                         (?:[^/]+/)*?
 319                         (?:
 320                             (?:
 321                                 play_redirect_hls|
 322                                 moogaloop\.swf)\?clip_id=
 323                             )?
 324                         (?:videos?/)?
 325                         (?P<id>[0-9]+)
 326                         (?:/(?P<unlisted_hash>[\da-f]{10}))?
 327                         /?(?:[?&].*)?(?:[#].*)?$
 328                     '''
 329     IE_NAME = 'vimeo'
 330     _EMBED_REGEX = [
 331         # iframe
 332         r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
 333         # Embedded (swf embed) Vimeo player
 334         r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
 335         # Non-standard embedded Vimeo player
 336         r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
 337     ]
 338     _TESTS = [
 339         {
 340             'url': 'http://vimeo.com/56015672#at=0',
 341             'md5': '8879b6cc097e987f02484baf890129e5',
 342             'info_dict': {
 343                 'id': '56015672',
 344                 'ext': 'mp4',
 345                 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
 346                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
 347                 'timestamp': 1355990239,
 348                 'upload_date': '20121220',
 349                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
 350                 'uploader_id': 'user7108434',
 351                 'uploader': 'Filippo Valsorda',
 352                 'duration': 10,
 353                 'license': 'by-sa',
 354             },
 355             'params': {
 356                 'format': 'best[protocol=https]',
 357             },
 358             'skip': 'No longer available'
 359         },
 360         {
 361             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
 362             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
 363             'note': 'Vimeo Pro video (#1197)',
 364             'info_dict': {
 365                 'id': '68093876',
 366                 'ext': 'mp4',
 367                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
 368                 'uploader_id': 'openstreetmapus',
 369                 'uploader': 'OpenStreetMap US',
 370                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 371                 'description': 'md5:2c362968038d4499f4d79f88458590c1',
 372                 'duration': 1595,
 373                 'upload_date': '20130610',
 374                 'timestamp': 1370893156,
 375                 'license': 'by',
 376                 'thumbnail': 'https://i.vimeocdn.com/video/440260469-19b0d92fca3bd84066623b53f1eb8aaa3980c6c809e2d67b6b39ab7b4a77a344-d_960',
 377                 'view_count': int,
 378                 'comment_count': int,
 379                 'like_count': int,
 380             },
 381             'params': {
 382                 'format': 'best[protocol=https]',
 383             },
 384         },
 385         {
 386             'url': 'http://player.vimeo.com/video/54469442',
 387             'md5': 'b3e7f4d2cbb53bd7dc3bb6ff4ed5cfbd',
 388             'note': 'Videos that embed the url in the player page',
 389             'info_dict': {
 390                 'id': '54469442',
 391                 'ext': 'mp4',
 392                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 393                 'uploader': 'Business of Software',
 394                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/businessofsoftware',
 395                 'uploader_id': 'businessofsoftware',
 396                 'duration': 3610,
 397                 'description': None,
 398                 'thumbnail': 'https://i.vimeocdn.com/video/376682406-f34043e7b766af6bef2af81366eacd6724f3fc3173179a11a97a1e26587c9529-d_1280',
 399             },
 400             'params': {
 401                 'format': 'best[protocol=https]',
 402             },
 403         },
 404         {
 405             'url': 'http://vimeo.com/68375962',
 406             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 407             'note': 'Video protected with password',
 408             'info_dict': {
 409                 'id': '68375962',
 410                 'ext': 'mp4',
 411                 'title': 'youtube-dl password protected test video',
 412                 'timestamp': 1371200155,
 413                 'upload_date': '20130614',
 414                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 415                 'uploader_id': 'user18948128',
 416                 'uploader': 'Jaime Marquínez Ferrándiz',
 417                 'duration': 10,
 418                 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
 419                 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_960',
 420                 'view_count': int,
 421                 'comment_count': int,
 422                 'like_count': int,
 423             },
 424             'params': {
 425                 'format': 'best[protocol=https]',
 426                 'videopassword': 'youtube-dl',
 427             },
 428         },
 429         {
 430             'url': 'http://vimeo.com/channels/keypeele/75629013',
 431             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 432             'info_dict': {
 433                 'id': '75629013',
 434                 'ext': 'mp4',
 435                 'title': 'Key & Peele: Terrorist Interrogation',
 436                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 437                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
 438                 'uploader_id': 'atencio',
 439                 'uploader': 'Peter Atencio',
 440                 'channel_id': 'keypeele',
 441                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
 442                 'timestamp': 1380339469,
 443                 'upload_date': '20130928',
 444                 'duration': 187,
 445                 'thumbnail': 'https://i.vimeocdn.com/video/450239872-a05512d9b1e55d707a7c04365c10980f327b06d966351bc403a5d5d65c95e572-d_1280',
 446                 'view_count': int,
 447                 'comment_count': int,
 448                 'like_count': int,
 449             },
 450             'params': {'format': 'http-1080p'},
 451         },
 452         {
 453             'url': 'http://vimeo.com/76979871',
 454             'note': 'Video with subtitles',
 455             'info_dict': {
 456                 'id': '76979871',
 457                 'ext': 'mov',
 458                 'title': 'The New Vimeo Player (You Know, For Videos)',
 459                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 460                 'timestamp': 1381846109,
 461                 'upload_date': '20131015',
 462                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
 463                 'uploader_id': 'staff',
 464                 'uploader': 'Vimeo Staff',
 465                 'duration': 62,
 466                 'subtitles': {
 467                     'de': [{'ext': 'vtt'}],
 468                     'en': [{'ext': 'vtt'}],
 469                     'es': [{'ext': 'vtt'}],
 470                     'fr': [{'ext': 'vtt'}],
 471                 },
 472             },
 473             'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
 474         },
 475         {
 476             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 477             'url': 'https://player.vimeo.com/video/98044508',
 478             'note': 'The js code contains assignments to the same variable as the config',
 479             'info_dict': {
 480                 'id': '98044508',
 481                 'ext': 'mp4',
 482                 'title': 'Pier Solar OUYA Official Trailer',
 483                 'uploader': 'Tulio Gonçalves',
 484                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
 485                 'uploader_id': 'user28849593',
 486                 'duration': 118,
 487                 'thumbnail': 'https://i.vimeocdn.com/video/478636036-c18440305ef3df9decfb6bf207a61fe39d2d17fa462a96f6f2d93d30492b037d-d_1280',
 488             },
 489         },
 490         {
 491             # contains original format
 492             'url': 'https://vimeo.com/33951933',
 493             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 494             'info_dict': {
 495                 'id': '33951933',
 496                 'ext': 'mp4',
 497                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 498                 'uploader': 'The DMCI',
 499                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
 500                 'uploader_id': 'dmci',
 501                 'timestamp': 1324343742,
 502                 'upload_date': '20111220',
 503                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 504                 'duration': 60,
 505                 'comment_count': int,
 506                 'view_count': int,
 507                 'thumbnail': 'https://i.vimeocdn.com/video/231174622-dd07f015e9221ff529d451e1cc31c982b5d87bfafa48c4189b1da72824ee289a-d_1280',
 508                 'like_count': int,
 509             },
 510         },
 511         {
 512             'note': 'Contains original format not accessible in webpage',
 513             'url': 'https://vimeo.com/393756517',
 514             'md5': 'c464af248b592190a5ffbb5d33f382b0',
 515             'info_dict': {
 516                 'id': '393756517',
 517                 'ext': 'mov',
 518                 'timestamp': 1582642091,
 519                 'uploader_id': 'frameworkla',
 520                 'title': 'Straight To Hell - Sabrina: Netflix',
 521                 'uploader': 'Framework Studio',
 522                 'description': 'md5:f2edc61af3ea7a5592681ddbb683db73',
 523                 'upload_date': '20200225',
 524                 'duration': 176,
 525                 'thumbnail': 'https://i.vimeocdn.com/video/859377297-836494a4ef775e9d4edbace83937d9ad34dc846c688c0c419c0e87f7ab06c4b3-d_1280',
 526                 'uploader_url': 'https://vimeo.com/frameworkla',
 527             },
 528         },
 529         {
 530             # only available via https://vimeo.com/channels/tributes/6213729 and
 531             # not via https://vimeo.com/6213729
 532             'url': 'https://vimeo.com/channels/tributes/6213729',
 533             'info_dict': {
 534                 'id': '6213729',
 535                 'ext': 'mp4',
 536                 'title': 'Vimeo Tribute: The Shining',
 537                 'uploader': 'Casey Donahue',
 538                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
 539                 'uploader_id': 'caseydonahue',
 540                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
 541                 'channel_id': 'tributes',
 542                 'timestamp': 1250886430,
 543                 'upload_date': '20090821',
 544                 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
 545                 'duration': 321,
 546                 'comment_count': int,
 547                 'view_count': int,
 548                 'thumbnail': 'https://i.vimeocdn.com/video/22728298-bfc22146f930de7cf497821c7b0b9f168099201ecca39b00b6bd31fcedfca7a6-d_1280',
 549                 'like_count': int,
 550             },
 551             'params': {
 552                 'skip_download': True,
 553             },
 554         },
 555         {
 556             # redirects to ondemand extractor and should be passed through it
 557             # for successful extraction
 558             'url': 'https://vimeo.com/73445910',
 559             'info_dict': {
 560                 'id': '73445910',
 561                 'ext': 'mp4',
 562                 'title': 'The Reluctant Revolutionary',
 563                 'uploader': '10Ft Films',
 564                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
 565                 'uploader_id': 'tenfootfilms',
 566                 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
 567                 'upload_date': '20130830',
 568                 'timestamp': 1377853339,
 569             },
 570             'params': {
 571                 'skip_download': True,
 572             },
 573             'skip': 'this page is no longer available.',
 574         },
 575         {
 576             'url': 'http://player.vimeo.com/video/68375962',
 577             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 578             'info_dict': {
 579                 'id': '68375962',
 580                 'ext': 'mp4',
 581                 'title': 'youtube-dl password protected test video',
 582                 'timestamp': 1371200155,
 583                 'upload_date': '20130614',
 584                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 585                 'uploader_id': 'user18948128',
 586                 'uploader': 'Jaime Marquínez Ferrándiz',
 587                 'duration': 10,
 588                 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
 589                 'thumbnail': 'https://i.vimeocdn.com/video/440665496-b2c5aee2b61089442c794f64113a8e8f7d5763c3e6b3ebfaf696ae6413f8b1f4-d_960',
 590                 'view_count': int,
 591                 'comment_count': int,
 592                 'like_count': int,
 593             },
 594             'params': {
 595                 'format': 'best[protocol=https]',
 596                 'videopassword': 'youtube-dl',
 597             },
 598         },
 599         {
 600             'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
 601             'only_matching': True,
 602         },
 603         {
 604             'url': 'https://vimeo.com/109815029',
 605             'note': 'Video not completely processed, "failed" seed status',
 606             'only_matching': True,
 607         },
 608         {
 609             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 610             'only_matching': True,
 611         },
 612         {
 613             'url': 'https://vimeo.com/album/2632481/video/79010983',
 614             'only_matching': True,
 615         },
 616         {
 617             'url': 'https://vimeo.com/showcase/3253534/video/119195465',
 618             'note': 'A video in a password protected album (showcase)',
 619             'info_dict': {
 620                 'id': '119195465',
 621                 'ext': 'mp4',
 622                 'title': "youtube-dl test video '' ä↭𝕐-BaW jenozKc",
 623                 'uploader': 'Philipp Hagemeister',
 624                 'uploader_id': 'user20132939',
 625                 'description': 'md5:fa7b6c6d8db0bdc353893df2f111855b',
 626                 'upload_date': '20150209',
 627                 'timestamp': 1423518307,
 628                 'thumbnail': 'https://i.vimeocdn.com/video/default_1280',
 629                 'duration': 10,
 630                 'like_count': int,
 631                 'uploader_url': 'https://vimeo.com/user20132939',
 632                 'view_count': int,
 633                 'comment_count': int,
 634             },
 635             'params': {
 636                 'format': 'best[protocol=https]',
 637                 'videopassword': 'youtube-dl',
 638             },
 639         },
 640         {
 641             # source file returns 403: Forbidden
 642             'url': 'https://vimeo.com/7809605',
 643             'only_matching': True,
 644         },
 645         {
 646             'note': 'Direct URL with hash',
 647             'url': 'https://vimeo.com/160743502/abd0e13fb4',
 648             'info_dict': {
 649                 'id': '160743502',
 650                 'ext': 'mp4',
 651                 'uploader': 'Julian Tryba',
 652                 'uploader_id': 'aliniamedia',
 653                 'title': 'Harrisville New Hampshire',
 654                 'timestamp': 1459259666,
 655                 'upload_date': '20160329',
 656                 'release_timestamp': 1459259666,
 657                 'license': 'by-nc',
 658                 'duration': 159,
 659                 'comment_count': int,
 660                 'thumbnail': 'https://i.vimeocdn.com/video/562802436-585eeb13b5020c6ac0f171a2234067938098f84737787df05ff0d767f6d54ee9-d_1280',
 661                 'like_count': int,
 662                 'uploader_url': 'https://vimeo.com/aliniamedia',
 663                 'release_date': '20160329',
 664             },
 665             'params': {'skip_download': True},
 666         },
 667         {
 668             'url': 'https://vimeo.com/138909882',
 669             'info_dict': {
 670                 'id': '138909882',
 671                 'ext': 'mp4',
 672                 'title': 'Eastnor Castle 2015 Firework Champions - The Promo!',
 673                 'description': 'md5:5967e090768a831488f6e74b7821b3c1',
 674                 'uploader_id': 'fireworkchampions',
 675                 'uploader': 'Firework Champions',
 676                 'upload_date': '20150910',
 677                 'timestamp': 1441901895,
 678             },
 679             'params': {
 680                 'skip_download': True,
 681                 'format': 'Original',
 682             },
 683         },
 684         {
 685             'url': 'https://vimeo.com/channels/staffpicks/143603739',
 686             'info_dict': {
 687                 'id': '143603739',
 688                 'ext': 'mp4',
 689                 'uploader': 'Karim Huu Do',
 690                 'timestamp': 1445846953,
 691                 'upload_date': '20151026',
 692                 'title': 'The Shoes - Submarine Feat. Blaine Harrison',
 693                 'uploader_id': 'karimhd',
 694                 'description': 'md5:8e2eea76de4504c2e8020a9bcfa1e843',
 695                 'channel_id': 'staffpicks',
 696                 'duration': 336,
 697                 'comment_count': int,
 698                 'view_count': int,
 699                 'thumbnail': 'https://i.vimeocdn.com/video/541243181-b593db36a16db2f0096f655da3f5a4dc46b8766d77b0f440df937ecb0c418347-d_1280',
 700                 'like_count': int,
 701                 'uploader_url': 'https://vimeo.com/karimhd',
 702                 'channel_url': 'https://vimeo.com/channels/staffpicks',
 703             },
 704             'params': {'skip_download': 'm3u8'},
 705         },
 706         {
 707             # requires passing unlisted_hash(a52724358e) to load_download_config request
 708             'url': 'https://vimeo.com/392479337/a52724358e',
 709             'only_matching': True,
 710         },
 711         {
 712             # similar, but all numeric: ID must be 581039021, not 9603038895
 713             # issue #29690
 714             'url': 'https://vimeo.com/581039021/9603038895',
 715             'info_dict': {
 716                 'id': '581039021',
 717                 'ext': 'mp4',
 718                 'timestamp': 1627621014,
 719                 'release_timestamp': 1627621014,
 720                 'duration': 976,
 721                 'comment_count': int,
 722                 'thumbnail': 'https://i.vimeocdn.com/video/1202249320-4ddb2c30398c0dc0ee059172d1bd5ea481ad12f0e0e3ad01d2266f56c744b015-d_1280',
 723                 'like_count': int,
 724                 'uploader_url': 'https://vimeo.com/txwestcapital',
 725                 'release_date': '20210730',
 726                 'uploader': 'Christopher Inks',
 727                 'title': 'Thursday, July 29, 2021 BMA Evening Video Update',
 728                 'uploader_id': 'txwestcapital',
 729                 'upload_date': '20210730',
 730             },
 731             'params': {
 732                 'skip_download': True,
 733             },
 734         }
 735         # https://gettingthingsdone.com/workflowmap/
 736         # vimeo embed with check-password page protected by Referer header
 737     ]
 738
 739     @classmethod
 740     def _extract_embed_urls(cls, url, webpage):
 741         for embed_url in super()._extract_embed_urls(url, webpage):
 742             yield cls._smuggle_referrer(embed_url, url)
 743
 744     def _verify_player_video_password(self, url, video_id, headers):
 745         password = self._get_video_password()
 746         data = urlencode_postdata({
 747             'password': base64.b64encode(password.encode()),
 748         })
 749         headers = merge_dicts(headers, {
 750             'Content-Type': 'application/x-www-form-urlencoded',
 751         })
 752         checked = self._download_json(
 753             f'{compat_urlparse.urlsplit(url)._replace(query=None).geturl()}/check-password',
 754             video_id, 'Verifying the password', data=data, headers=headers)
 755         if checked is False:
 756             raise ExtractorError('Wrong video password', expected=True)
 757         return checked
 758
 759     def _extract_from_api(self, video_id, unlisted_hash=None):
 760         token = self._download_json(
 761             'https://vimeo.com/_rv/jwt', video_id, headers={
 762                 'X-Requested-With': 'XMLHttpRequest'
 763             })['token']
 764         api_url = 'https://api.vimeo.com/videos/' + video_id
 765         if unlisted_hash:
 766             api_url += ':' + unlisted_hash
 767         video = self._download_json(
 768             api_url, video_id, headers={
 769                 'Authorization': 'jwt ' + token,
 770             }, query={
 771                 'fields': 'config_url,created_time,description,license,metadata.connections.comments.total,metadata.connections.likes.total,release_time,stats.plays',
 772             })
 773         info = self._parse_config(self._download_json(
 774             video['config_url'], video_id), video_id)
 775         self._vimeo_sort_formats(info['formats'])
 776         get_timestamp = lambda x: parse_iso8601(video.get(x + '_time'))
 777         info.update({
 778             'description': video.get('description'),
 779             'license': video.get('license'),
 780             'release_timestamp': get_timestamp('release'),
 781             'timestamp': get_timestamp('created'),
 782             'view_count': int_or_none(try_get(video, lambda x: x['stats']['plays'])),
 783         })
 784         connections = try_get(
 785             video, lambda x: x['metadata']['connections'], dict) or {}
 786         for k in ('comment', 'like'):
 787             info[k + '_count'] = int_or_none(try_get(connections, lambda x: x[k + 's']['total']))
 788         return info
 789
 790     def _try_album_password(self, url):
 791         album_id = self._search_regex(
 792             r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None)
 793         if not album_id:
 794             return
 795         viewer = self._download_json(
 796             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
 797         if not viewer:
 798             webpage = self._download_webpage(url, album_id)
 799             viewer = self._parse_json(self._search_regex(
 800                 r'bootstrap_data\s*=\s*({.+?})</script>',
 801                 webpage, 'bootstrap data'), album_id)['viewer']
 802         jwt = viewer['jwt']
 803         album = self._download_json(
 804             'https://api.vimeo.com/albums/' + album_id,
 805             album_id, headers={'Authorization': 'jwt ' + jwt},
 806             query={'fields': 'description,name,privacy'})
 807         if try_get(album, lambda x: x['privacy']['view']) == 'password':
 808             password = self.get_param('videopassword')
 809             if not password:
 810                 raise ExtractorError(
 811                     'This album is protected by a password, use the --video-password option',
 812                     expected=True)
 813             self._set_vimeo_cookie('vuid', viewer['vuid'])
 814             try:
 815                 self._download_json(
 816                     'https://vimeo.com/showcase/%s/auth' % album_id,
 817                     album_id, 'Verifying the password', data=urlencode_postdata({
 818                         'password': password,
 819                         'token': viewer['xsrft'],
 820                     }), headers={
 821                         'X-Requested-With': 'XMLHttpRequest',
 822                     })
 823             except ExtractorError as e:
 824                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
 825                     raise ExtractorError('Wrong password', expected=True)
 826                 raise
 827
 828     def _real_extract(self, url):
 829         url, data, headers = self._unsmuggle_headers(url)
 830         if 'Referer' not in headers:
 831             headers['Referer'] = url
 832
 833         # Extract ID from URL
 834         mobj = self._match_valid_url(url).groupdict()
 835         video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash')
 836         if unlisted_hash:
 837             return self._extract_from_api(video_id, unlisted_hash)
 838
 839         orig_url = url
 840         is_pro = 'vimeopro.com/' in url
 841         if is_pro:
 842             # some videos require portfolio_id to be present in player url
 843             # https://github.com/ytdl-org/youtube-dl/issues/20070
 844             url = self._extract_url(url, self._download_webpage(url, video_id))
 845             if not url:
 846                 url = 'https://vimeo.com/' + video_id
 847         elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
 848             url = 'https://vimeo.com/' + video_id
 849
 850         self._try_album_password(url)
 851         try:
 852             # Retrieve video webpage to extract further information
 853             webpage, urlh = self._download_webpage_handle(
 854                 url, video_id, headers=headers)
 855             redirect_url = urlh.geturl()
 856         except ExtractorError as ee:
 857             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 858                 errmsg = ee.cause.read()
 859                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 860                     raise ExtractorError(
 861                         'Cannot download embed-only video without embedding '
 862                         'URL. Please call yt-dlp with the URL of the page '
 863                         'that embeds this video.',
 864                         expected=True)
 865             raise
 866
 867         if '://player.vimeo.com/video/' in url:
 868             config = self._parse_json(self._search_regex(
 869                 r'\bconfig\s*=\s*({.+?})\s*;', webpage, 'info section'), video_id)
 870             if config.get('view') == 4:
 871                 config = self._verify_player_video_password(
 872                     redirect_url, video_id, headers)
 873             info = self._parse_config(config, video_id)
 874             self._vimeo_sort_formats(info['formats'])
 875             return info
 876
 877         if re.search(r'<form[^>]+?id="pw_form"', webpage):
 878             video_password = self._get_video_password()
 879             token, vuid = self._extract_xsrft_and_vuid(webpage)
 880             webpage = self._verify_video_password(
 881                 redirect_url, video_id, video_password, token, vuid)
 882
 883         vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
 884         if vimeo_config:
 885             seed_status = vimeo_config.get('seed_status') or {}
 886             if seed_status.get('state') == 'failed':
 887                 raise ExtractorError(
 888                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 889                     expected=True)
 890
 891         cc_license = None
 892         timestamp = None
 893         video_description = None
 894         info_dict = {}
 895         config_url = None
 896
 897         channel_id = self._search_regex(
 898             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
 899         if channel_id:
 900             config_url = self._html_search_regex(
 901                 r'\bdata-config-url="([^"]+)"', webpage, 'config URL', default=None)
 902             video_description = clean_html(get_element_by_class('description', webpage))
 903             info_dict.update({
 904                 'channel_id': channel_id,
 905                 'channel_url': 'https://vimeo.com/channels/' + channel_id,
 906             })
 907         if not config_url:
 908             page_config = self._parse_json(self._search_regex(
 909                 r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
 910                 webpage, 'page config', default='{}'), video_id, fatal=False)
 911             if not page_config:
 912                 return self._extract_from_api(video_id)
 913             config_url = page_config['player']['config_url']
 914             cc_license = page_config.get('cc_license')
 915             clip = page_config.get('clip') or {}
 916             timestamp = clip.get('uploaded_on')
 917             video_description = clean_html(
 918                 clip.get('description') or page_config.get('description_html_escaped'))
 919         config = self._download_json(config_url, video_id)
 920         video = config.get('video') or {}
 921         vod = video.get('vod') or {}
 922
 923         def is_rented():
 924             if '>You rented this title.<' in webpage:
 925                 return True
 926             if try_get(config, lambda x: x['user']['purchased']):
 927                 return True
 928             for purchase_option in (vod.get('purchase_options') or []):
 929                 if purchase_option.get('purchased'):
 930                     return True
 931                 label = purchase_option.get('label_string')
 932                 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
 933                     return True
 934             return False
 935
 936         if is_rented() and vod.get('is_trailer'):
 937             feature_id = vod.get('feature_id')
 938             if feature_id and not data.get('force_feature_id', False):
 939                 return self.url_result(smuggle_url(
 940                     'https://player.vimeo.com/player/%s' % feature_id,
 941                     {'force_feature_id': True}), 'Vimeo')
 942
 943         if not video_description:
 944             video_description = self._html_search_regex(
 945                 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 946                 webpage, 'description', default=None)
 947         if not video_description:
 948             video_description = self._html_search_meta(
 949                 ['description', 'og:description', 'twitter:description'],
 950                 webpage, default=None)
 951         if not video_description and is_pro:
 952             orig_webpage = self._download_webpage(
 953                 orig_url, video_id,
 954                 note='Downloading webpage for description',
 955                 fatal=False)
 956             if orig_webpage:
 957                 video_description = self._html_search_meta(
 958                     'description', orig_webpage, default=None)
 959         if not video_description:
 960             self.report_warning('Cannot find video description')
 961
 962         if not timestamp:
 963             timestamp = self._search_regex(
 964                 r'<time[^>]+datetime="([^"]+)"', webpage,
 965                 'timestamp', default=None)
 966
 967         view_count = int_or_none(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count', default=None))
 968         like_count = int_or_none(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count', default=None))
 969         comment_count = int_or_none(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count', default=None))
 970
 971         formats = []
 972
 973         source_format = self._extract_original_format(
 974             'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
 975         if source_format:
 976             formats.append(source_format)
 977
 978         info_dict_config = self._parse_config(config, video_id)
 979         formats.extend(info_dict_config['formats'])
 980         self._vimeo_sort_formats(formats)
 981
 982         json_ld = self._search_json_ld(webpage, video_id, default={})
 983
 984         if not cc_license:
 985             cc_license = self._search_regex(
 986                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
 987                 webpage, 'license', default=None, group='license')
 988
 989         info_dict.update({
 990             'formats': formats,
 991             'timestamp': unified_timestamp(timestamp),
 992             'description': video_description,
 993             'webpage_url': url,
 994             'view_count': view_count,
 995             'like_count': like_count,
 996             'comment_count': comment_count,
 997             'license': cc_license,
 998         })
 999
1000         return merge_dicts(info_dict, info_dict_config, json_ld)
1001
1002
1003 class VimeoOndemandIE(VimeoIE):
1004     IE_NAME = 'vimeo:ondemand'
1005     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/(?:[^/]+/)?(?P<id>[^/?#&]+)'
1006     _TESTS = [{
1007         # ondemand video not available via https://vimeo.com/id
1008         'url': 'https://vimeo.com/ondemand/20704',
1009         'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
1010         'info_dict': {
1011             'id': '105442900',
1012             'ext': 'mp4',
1013             'title': 'המעבדה - במאי יותם פלדמן',
1014             'uploader': 'גם סרטים',
1015             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
1016             'uploader_id': 'gumfilms',
1017             'description': 'md5:aeeba3dbd4d04b0fa98a4fdc9c639998',
1018             'upload_date': '20140906',
1019             'timestamp': 1410032453,
1020             'thumbnail': 'https://i.vimeocdn.com/video/488238335-d7bf151c364cff8d467f1b73784668fe60aae28a54573a35d53a1210ae283bd8-d_1280',
1021             'comment_count': int,
1022             'license': 'https://creativecommons.org/licenses/by-nc-nd/3.0/',
1023             'duration': 53,
1024             'view_count': int,
1025             'like_count': int,
1026         },
1027         'params': {
1028             'format': 'best[protocol=https]',
1029         },
1030         'expected_warnings': ['Unable to download JSON metadata'],
1031     }, {
1032         # requires Referer to be passed along with og:video:url
1033         'url': 'https://vimeo.com/ondemand/36938/126682985',
1034         'info_dict': {
1035             'id': '126584684',
1036             'ext': 'mp4',
1037             'title': 'Rävlock, rätt läte på rätt plats',
1038             'uploader': 'Lindroth & Norin',
1039             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
1040             'uploader_id': 'lindrothnorin',
1041             'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
1042             'upload_date': '20150502',
1043             'timestamp': 1430586422,
1044             'duration': 121,
1045             'comment_count': int,
1046             'view_count': int,
1047             'thumbnail': 'https://i.vimeocdn.com/video/517077723-7066ae1d9a79d3eb361334fb5d58ec13c8f04b52f8dd5eadfbd6fb0bcf11f613-d_1280',
1048             'like_count': int,
1049         },
1050         'params': {
1051             'skip_download': True,
1052         },
1053         'expected_warnings': ['Unable to download JSON metadata'],
1054     }, {
1055         'url': 'https://vimeo.com/ondemand/nazmaalik',
1056         'only_matching': True,
1057     }, {
1058         'url': 'https://vimeo.com/ondemand/141692381',
1059         'only_matching': True,
1060     }, {
1061         'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
1062         'only_matching': True,
1063     }]
1064
1065
1066 class VimeoChannelIE(VimeoBaseInfoExtractor):
1067     IE_NAME = 'vimeo:channel'
1068     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
1069     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
1070     _TITLE = None
1071     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
1072     _TESTS = [{
1073         'url': 'https://vimeo.com/channels/tributes',
1074         'info_dict': {
1075             'id': 'tributes',
1076             'title': 'Vimeo Tributes',
1077         },
1078         'playlist_mincount': 22,
1079     }]
1080     _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
1081
1082     def _page_url(self, base_url, pagenum):
1083         return '%s/videos/page:%d/' % (base_url, pagenum)
1084
1085     def _extract_list_title(self, webpage):
1086         return self._TITLE or self._html_search_regex(
1087             self._TITLE_RE, webpage, 'list title', fatal=False)
1088
1089     def _title_and_entries(self, list_id, base_url):
1090         for pagenum in itertools.count(1):
1091             page_url = self._page_url(base_url, pagenum)
1092             webpage = self._download_webpage(
1093                 page_url, list_id,
1094                 'Downloading page %s' % pagenum)
1095
1096             if pagenum == 1:
1097                 yield self._extract_list_title(webpage)
1098
1099             # Try extracting href first since not all videos are available via
1100             # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
1101             clips = re.findall(
1102                 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
1103             if clips:
1104                 for video_id, video_url, video_title in clips:
1105                     yield self.url_result(
1106                         compat_urlparse.urljoin(base_url, video_url),
1107                         VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
1108             # More relaxed fallback
1109             else:
1110                 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
1111                     yield self.url_result(
1112                         'https://vimeo.com/%s' % video_id,
1113                         VimeoIE.ie_key(), video_id=video_id)
1114
1115             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
1116                 break
1117
1118     def _extract_videos(self, list_id, base_url):
1119         title_and_entries = self._title_and_entries(list_id, base_url)
1120         list_title = next(title_and_entries)
1121         return self.playlist_result(title_and_entries, list_id, list_title)
1122
1123     def _real_extract(self, url):
1124         channel_id = self._match_id(url)
1125         return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
1126
1127
1128 class VimeoUserIE(VimeoChannelIE):
1129     IE_NAME = 'vimeo:user'
1130     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
1131     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
1132     _TESTS = [{
1133         'url': 'https://vimeo.com/nkistudio/videos',
1134         'info_dict': {
1135             'title': 'Nki',
1136             'id': 'nkistudio',
1137         },
1138         'playlist_mincount': 66,
1139     }]
1140     _BASE_URL_TEMPL = 'https://vimeo.com/%s'
1141
1142
1143 class VimeoAlbumIE(VimeoBaseInfoExtractor):
1144     IE_NAME = 'vimeo:album'
1145     _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
1146     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
1147     _TESTS = [{
1148         'url': 'https://vimeo.com/album/2632481',
1149         'info_dict': {
1150             'id': '2632481',
1151             'title': 'Staff Favorites: November 2013',
1152         },
1153         'playlist_mincount': 13,
1154     }, {
1155         'note': 'Password-protected album',
1156         'url': 'https://vimeo.com/album/3253534',
1157         'info_dict': {
1158             'title': 'test',
1159             'id': '3253534',
1160         },
1161         'playlist_count': 1,
1162         'params': {
1163             'videopassword': 'youtube-dl',
1164         }
1165     }]
1166     _PAGE_SIZE = 100
1167
1168     def _fetch_page(self, album_id, authorization, hashed_pass, page):
1169         api_page = page + 1
1170         query = {
1171             'fields': 'link,uri',
1172             'page': api_page,
1173             'per_page': self._PAGE_SIZE,
1174         }
1175         if hashed_pass:
1176             query['_hashed_pass'] = hashed_pass
1177         try:
1178             videos = self._download_json(
1179                 'https://api.vimeo.com/albums/%s/videos' % album_id,
1180                 album_id, 'Downloading page %d' % api_page, query=query, headers={
1181                     'Authorization': 'jwt ' + authorization,
1182                 })['data']
1183         except ExtractorError as e:
1184             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
1185                 return
1186         for video in videos:
1187             link = video.get('link')
1188             if not link:
1189                 continue
1190             uri = video.get('uri')
1191             video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
1192             yield self.url_result(link, VimeoIE.ie_key(), video_id)
1193
1194     def _real_extract(self, url):
1195         album_id = self._match_id(url)
1196         viewer = self._download_json(
1197             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
1198         if not viewer:
1199             webpage = self._download_webpage(url, album_id)
1200             viewer = self._parse_json(self._search_regex(
1201                 r'bootstrap_data\s*=\s*({.+?})</script>',
1202                 webpage, 'bootstrap data'), album_id)['viewer']
1203         jwt = viewer['jwt']
1204         album = self._download_json(
1205             'https://api.vimeo.com/albums/' + album_id,
1206             album_id, headers={'Authorization': 'jwt ' + jwt},
1207             query={'fields': 'description,name,privacy'})
1208         hashed_pass = None
1209         if try_get(album, lambda x: x['privacy']['view']) == 'password':
1210             password = self.get_param('videopassword')
1211             if not password:
1212                 raise ExtractorError(
1213                     'This album is protected by a password, use the --video-password option',
1214                     expected=True)
1215             self._set_vimeo_cookie('vuid', viewer['vuid'])
1216             try:
1217                 hashed_pass = self._download_json(
1218                     'https://vimeo.com/showcase/%s/auth' % album_id,
1219                     album_id, 'Verifying the password', data=urlencode_postdata({
1220                         'password': password,
1221                         'token': viewer['xsrft'],
1222                     }), headers={
1223                         'X-Requested-With': 'XMLHttpRequest',
1224                     })['hashed_pass']
1225             except ExtractorError as e:
1226                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
1227                     raise ExtractorError('Wrong password', expected=True)
1228                 raise
1229         entries = OnDemandPagedList(functools.partial(
1230             self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
1231         return self.playlist_result(
1232             entries, album_id, album.get('name'), album.get('description'))
1233
1234
1235 class VimeoGroupsIE(VimeoChannelIE):
1236     IE_NAME = 'vimeo:group'
1237     _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
1238     _TESTS = [{
1239         'url': 'https://vimeo.com/groups/meetup',
1240         'info_dict': {
1241             'id': 'meetup',
1242             'title': 'Vimeo Meetup!',
1243         },
1244         'playlist_mincount': 27,
1245     }]
1246     _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
1247
1248
1249 class VimeoReviewIE(VimeoBaseInfoExtractor):
1250     IE_NAME = 'vimeo:review'
1251     IE_DESC = 'Review pages on vimeo'
1252     _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
1253     _TESTS = [{
1254         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1255         'md5': 'c507a72f780cacc12b2248bb4006d253',
1256         'info_dict': {
1257             'id': '75524534',
1258             'ext': 'mp4',
1259             'title': "DICK HARDWICK 'Comedian'",
1260             'uploader': 'Richard Hardwick',
1261             'uploader_id': 'user21297594',
1262             'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1263             'duration': 304,
1264             'thumbnail': 'https://i.vimeocdn.com/video/450115033-43303819d9ebe24c2630352e18b7056d25197d09b3ae901abdac4c4f1d68de71-d_1280',
1265             'uploader_url': 'https://vimeo.com/user21297594',
1266         },
1267     }, {
1268         'note': 'video player needs Referer',
1269         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1270         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1271         'info_dict': {
1272             'id': '91613211',
1273             'ext': 'mp4',
1274             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1275             'uploader': 'DevWeek Events',
1276             'duration': 2773,
1277             'thumbnail': r're:^https?://.*\.jpg$',
1278             'uploader_id': 'user22258446',
1279         },
1280         'skip': 'video gone',
1281     }, {
1282         'note': 'Password protected',
1283         'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1284         'info_dict': {
1285             'id': '138823582',
1286             'ext': 'mp4',
1287             'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1288             'uploader': 'TMB',
1289             'uploader_id': 'user37284429',
1290         },
1291         'params': {
1292             'videopassword': 'holygrail',
1293         },
1294         'skip': 'video gone',
1295     }]
1296
1297     def _real_extract(self, url):
1298         page_url, video_id = self._match_valid_url(url).groups()
1299         data = self._download_json(
1300             page_url.replace('/review/', '/review/data/'), video_id)
1301         if data.get('isLocked') is True:
1302             video_password = self._get_video_password()
1303             viewer = self._download_json(
1304                 'https://vimeo.com/_rv/viewer', video_id)
1305             webpage = self._verify_video_password(
1306                 'https://vimeo.com/' + video_id, video_id,
1307                 video_password, viewer['xsrft'], viewer['vuid'])
1308             clip_page_config = self._parse_json(self._search_regex(
1309                 r'window\.vimeo\.clip_page_config\s*=\s*({.+?});',
1310                 webpage, 'clip page config'), video_id)
1311             config_url = clip_page_config['player']['config_url']
1312             clip_data = clip_page_config.get('clip') or {}
1313         else:
1314             clip_data = data['clipData']
1315             config_url = clip_data['configUrl']
1316         config = self._download_json(config_url, video_id)
1317         info_dict = self._parse_config(config, video_id)
1318         source_format = self._extract_original_format(
1319             page_url + '/action', video_id)
1320         if source_format:
1321             info_dict['formats'].append(source_format)
1322         self._vimeo_sort_formats(info_dict['formats'])
1323         info_dict['description'] = clean_html(clip_data.get('description'))
1324         return info_dict
1325
1326
1327 class VimeoWatchLaterIE(VimeoChannelIE):
1328     IE_NAME = 'vimeo:watchlater'
1329     IE_DESC = 'Vimeo watch later list, ":vimeowatchlater" keyword (requires authentication)'
1330     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1331     _TITLE = 'Watch Later'
1332     _LOGIN_REQUIRED = True
1333     _TESTS = [{
1334         'url': 'https://vimeo.com/watchlater',
1335         'only_matching': True,
1336     }]
1337
1338     def _page_url(self, base_url, pagenum):
1339         url = '%s/page:%d/' % (base_url, pagenum)
1340         request = sanitized_Request(url)
1341         # Set the header to get a partial html page with the ids,
1342         # the normal page doesn't contain them.
1343         request.add_header('X-Requested-With', 'XMLHttpRequest')
1344         return request
1345
1346     def _real_extract(self, url):
1347         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1348
1349
1350 class VimeoLikesIE(VimeoChannelIE):
1351     _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1352     IE_NAME = 'vimeo:likes'
1353     IE_DESC = 'Vimeo user likes'
1354     _TESTS = [{
1355         'url': 'https://vimeo.com/user755559/likes/',
1356         'playlist_mincount': 293,
1357         'info_dict': {
1358             'id': 'user755559',
1359             'title': 'urza’s Likes',
1360         },
1361     }, {
1362         'url': 'https://vimeo.com/stormlapse/likes',
1363         'only_matching': True,
1364     }]
1365
1366     def _page_url(self, base_url, pagenum):
1367         return '%s/page:%d/' % (base_url, pagenum)
1368
1369     def _real_extract(self, url):
1370         user_id = self._match_id(url)
1371         return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
1372
1373
1374 class VHXEmbedIE(VimeoBaseInfoExtractor):
1375     IE_NAME = 'vhx:embed'
1376     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1377     _EMBED_REGEX = [r'<iframe[^>]+src="(?P<url>https?://embed\.vhx\.tv/videos/\d+[^"]*)"']
1378
1379     @classmethod
1380     def _extract_embed_urls(cls, url, webpage):
1381         for embed_url in super()._extract_embed_urls(url, webpage):
1382             yield cls._smuggle_referrer(embed_url, url)
1383
1384     def _real_extract(self, url):
1385         video_id = self._match_id(url)
1386         url, _, headers = self._unsmuggle_headers(url)
1387         webpage = self._download_webpage(url, video_id, headers=headers)
1388         config_url = self._parse_json(self._search_regex(
1389             r'window\.OTTData\s*=\s*({.+})', webpage,
1390             'ott data'), video_id, js_to_json)['config_url']
1391         config = self._download_json(config_url, video_id)
1392         info = self._parse_config(config, video_id)
1393         info['id'] = video_id
1394         self._vimeo_sort_formats(info['formats'])
1395         return info