yt_dlp/extractor/vimeo.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import base64
   5 import functools
   6 import json
   7 import re
   8 import itertools
   9
  10 from .common import InfoExtractor
  11 from ..compat import (
  12     compat_kwargs,
  13     compat_HTTPError,
  14     compat_str,
  15     compat_urlparse,
  16 )
  17 from ..utils import (
  18     clean_html,
  19     determine_ext,
  20     dict_get,
  21     ExtractorError,
  22     js_to_json,
  23     int_or_none,
  24     merge_dicts,
  25     OnDemandPagedList,
  26     parse_filesize,
  27     RegexNotFoundError,
  28     sanitized_Request,
  29     smuggle_url,
  30     std_headers,
  31     str_or_none,
  32     try_get,
  33     unified_timestamp,
  34     unsmuggle_url,
  35     urlencode_postdata,
  36     urljoin,
  37     unescapeHTML,
  38 )
  39
  40
  41 class VimeoBaseInfoExtractor(InfoExtractor):
  42     _NETRC_MACHINE = 'vimeo'
  43     _LOGIN_REQUIRED = False
  44     _LOGIN_URL = 'https://vimeo.com/log_in'
  45
  46     def _login(self):
  47         username, password = self._get_login_info()
  48         if username is None:
  49             if self._LOGIN_REQUIRED:
  50                 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
  51             return
  52         webpage = self._download_webpage(
  53             self._LOGIN_URL, None, 'Downloading login page')
  54         token, vuid = self._extract_xsrft_and_vuid(webpage)
  55         data = {
  56             'action': 'login',
  57             'email': username,
  58             'password': password,
  59             'service': 'vimeo',
  60             'token': token,
  61         }
  62         self._set_vimeo_cookie('vuid', vuid)
  63         try:
  64             self._download_webpage(
  65                 self._LOGIN_URL, None, 'Logging in',
  66                 data=urlencode_postdata(data), headers={
  67                     'Content-Type': 'application/x-www-form-urlencoded',
  68                     'Referer': self._LOGIN_URL,
  69                 })
  70         except ExtractorError as e:
  71             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418:
  72                 raise ExtractorError(
  73                     'Unable to log in: bad username or password',
  74                     expected=True)
  75             raise ExtractorError('Unable to log in')
  76
  77     def _verify_video_password(self, url, video_id, webpage):
  78         password = self._downloader.params.get('videopassword')
  79         if password is None:
  80             raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
  81         token, vuid = self._extract_xsrft_and_vuid(webpage)
  82         data = urlencode_postdata({
  83             'password': password,
  84             'token': token,
  85         })
  86         if url.startswith('http://'):
  87             # vimeo only supports https now, but the user can give an http url
  88             url = url.replace('http://', 'https://')
  89         password_request = sanitized_Request(url + '/password', data)
  90         password_request.add_header('Content-Type', 'application/x-www-form-urlencoded')
  91         password_request.add_header('Referer', url)
  92         self._set_vimeo_cookie('vuid', vuid)
  93         return self._download_webpage(
  94             password_request, video_id,
  95             'Verifying the password', 'Wrong password')
  96
  97     def _extract_xsrft_and_vuid(self, webpage):
  98         xsrft = self._search_regex(
  99             r'(?:(?P<q1>["\'])xsrft(?P=q1)\s*:|xsrft\s*[=:])\s*(?P<q>["\'])(?P<xsrft>.+?)(?P=q)',
 100             webpage, 'login token', group='xsrft')
 101         vuid = self._search_regex(
 102             r'["\']vuid["\']\s*:\s*(["\'])(?P<vuid>.+?)\1',
 103             webpage, 'vuid', group='vuid')
 104         return xsrft, vuid
 105
 106     def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
 107         vimeo_config = self._search_regex(
 108             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
 109             webpage, 'vimeo config', *args, **compat_kwargs(kwargs))
 110         if vimeo_config:
 111             return self._parse_json(vimeo_config, video_id)
 112
 113     def _set_vimeo_cookie(self, name, value):
 114         self._set_cookie('vimeo.com', name, value)
 115
 116     def _vimeo_sort_formats(self, formats):
 117         # Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
 118         # at the same time without actual units specified. This lead to wrong sorting.
 119         # But since yt-dlp prefers 'res,fps' anyway, 'field_preference' is not needed
 120         self._sort_formats(formats)
 121
 122     def _parse_config(self, config, video_id):
 123         video_data = config['video']
 124         video_title = video_data['title']
 125         live_event = video_data.get('live_event') or {}
 126         is_live = live_event.get('status') == 'started'
 127
 128         formats = []
 129         config_files = video_data.get('files') or config['request'].get('files', {})
 130         for f in config_files.get('progressive', []):
 131             video_url = f.get('url')
 132             if not video_url:
 133                 continue
 134             formats.append({
 135                 'url': video_url,
 136                 'format_id': 'http-%s' % f.get('quality'),
 137                 'width': int_or_none(f.get('width')),
 138                 'height': int_or_none(f.get('height')),
 139                 'fps': int_or_none(f.get('fps')),
 140                 'tbr': int_or_none(f.get('bitrate')),
 141             })
 142
 143         # TODO: fix handling of 308 status code returned for live archive manifest requests
 144         sep_pattern = r'/sep/video/'
 145         for files_type in ('hls', 'dash'):
 146             for cdn_name, cdn_data in config_files.get(files_type, {}).get('cdns', {}).items():
 147                 manifest_url = cdn_data.get('url')
 148                 if not manifest_url:
 149                     continue
 150                 format_id = '%s-%s' % (files_type, cdn_name)
 151                 sep_manifest_urls = []
 152                 if re.search(sep_pattern, manifest_url):
 153                     for suffix, repl in (('', 'video'), ('_sep', 'sep/video')):
 154                         sep_manifest_urls.append((format_id + suffix, re.sub(
 155                             sep_pattern, '/%s/' % repl, manifest_url)))
 156                 else:
 157                     sep_manifest_urls = [(format_id, manifest_url)]
 158                 for f_id, m_url in sep_manifest_urls:
 159                     if files_type == 'hls':
 160                         formats.extend(self._extract_m3u8_formats(
 161                             m_url, video_id, 'mp4',
 162                             'm3u8' if is_live else 'm3u8_native', m3u8_id=f_id,
 163                             note='Downloading %s m3u8 information' % cdn_name,
 164                             fatal=False))
 165                     elif files_type == 'dash':
 166                         if 'json=1' in m_url:
 167                             real_m_url = (self._download_json(m_url, video_id, fatal=False) or {}).get('url')
 168                             if real_m_url:
 169                                 m_url = real_m_url
 170                         mpd_formats = self._extract_mpd_formats(
 171                             m_url.replace('/master.json', '/master.mpd'), video_id, f_id,
 172                             'Downloading %s MPD information' % cdn_name,
 173                             fatal=False)
 174                         formats.extend(mpd_formats)
 175
 176         live_archive = live_event.get('archive') or {}
 177         live_archive_source_url = live_archive.get('source_url')
 178         if live_archive_source_url and live_archive.get('status') == 'done':
 179             formats.append({
 180                 'format_id': 'live-archive-source',
 181                 'url': live_archive_source_url,
 182                 'quality': 10,
 183             })
 184
 185         subtitles = {}
 186         text_tracks = config['request'].get('text_tracks')
 187         if text_tracks:
 188             for tt in text_tracks:
 189                 subtitles[tt['lang']] = [{
 190                     'ext': 'vtt',
 191                     'url': urljoin('https://vimeo.com', tt['url']),
 192                 }]
 193
 194         thumbnails = []
 195         if not is_live:
 196             for key, thumb in video_data.get('thumbs', {}).items():
 197                 thumbnails.append({
 198                     'id': key,
 199                     'width': int_or_none(key),
 200                     'url': thumb,
 201                 })
 202             thumbnail = video_data.get('thumbnail')
 203             if thumbnail:
 204                 thumbnails.append({
 205                     'url': thumbnail,
 206                 })
 207
 208         owner = video_data.get('owner') or {}
 209         video_uploader_url = owner.get('url')
 210
 211         return {
 212             'id': str_or_none(video_data.get('id')) or video_id,
 213             'title': self._live_title(video_title) if is_live else video_title,
 214             'uploader': owner.get('name'),
 215             'uploader_id': video_uploader_url.split('/')[-1] if video_uploader_url else None,
 216             'uploader_url': video_uploader_url,
 217             'thumbnails': thumbnails,
 218             'duration': int_or_none(video_data.get('duration')),
 219             'formats': formats,
 220             'subtitles': subtitles,
 221             'is_live': is_live,
 222         }
 223
 224     def _extract_original_format(self, url, video_id, unlisted_hash=None):
 225         query = {'action': 'load_download_config'}
 226         if unlisted_hash:
 227             query['unlisted_hash'] = unlisted_hash
 228         download_data = self._download_json(
 229             url, video_id, fatal=False, query=query,
 230             headers={'X-Requested-With': 'XMLHttpRequest'})
 231         if download_data:
 232             source_file = download_data.get('source_file')
 233             if isinstance(source_file, dict):
 234                 download_url = source_file.get('download_url')
 235                 if download_url and not source_file.get('is_cold') and not source_file.get('is_defrosting'):
 236                     source_name = source_file.get('public_name', 'Original')
 237                     if self._is_valid_url(download_url, video_id, '%s video' % source_name):
 238                         ext = (try_get(
 239                             source_file, lambda x: x['extension'],
 240                             compat_str) or determine_ext(
 241                             download_url, None) or 'mp4').lower()
 242                         return {
 243                             'url': download_url,
 244                             'ext': ext,
 245                             'width': int_or_none(source_file.get('width')),
 246                             'height': int_or_none(source_file.get('height')),
 247                             'filesize': parse_filesize(source_file.get('size')),
 248                             'format_id': source_name,
 249                             'quality': 1,
 250                         }
 251
 252
 253 class VimeoIE(VimeoBaseInfoExtractor):
 254     """Information extractor for vimeo.com."""
 255
 256     # _VALID_URL matches Vimeo URLs
 257     _VALID_URL = r'''(?x)
 258                     https?://
 259                         (?:
 260                             (?:
 261                                 www|
 262                                 player
 263                             )
 264                             \.
 265                         )?
 266                         vimeo(?:pro)?\.com/
 267                         (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
 268                         (?:.*?/)?
 269                         (?:
 270                             (?:
 271                                 play_redirect_hls|
 272                                 moogaloop\.swf)\?clip_id=
 273                             )?
 274                         (?:videos?/)?
 275                         (?P<id>[0-9]+)
 276                         (?:/[\da-f]+)?
 277                         /?(?:[?&].*)?(?:[#].*)?$
 278                     '''
 279     IE_NAME = 'vimeo'
 280     _TESTS = [
 281         {
 282             'url': 'http://vimeo.com/56015672#at=0',
 283             'md5': '8879b6cc097e987f02484baf890129e5',
 284             'info_dict': {
 285                 'id': '56015672',
 286                 'ext': 'mp4',
 287                 'title': "youtube-dl test video - \u2605 \" ' \u5e78 / \\ \u00e4 \u21ad \U0001d550",
 288                 'description': 'md5:2d3305bad981a06ff79f027f19865021',
 289                 'timestamp': 1355990239,
 290                 'upload_date': '20121220',
 291                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user7108434',
 292                 'uploader_id': 'user7108434',
 293                 'uploader': 'Filippo Valsorda',
 294                 'duration': 10,
 295                 'license': 'by-sa',
 296             },
 297             'params': {
 298                 'format': 'best[protocol=https]',
 299             },
 300         },
 301         {
 302             'url': 'http://vimeopro.com/openstreetmapus/state-of-the-map-us-2013/video/68093876',
 303             'md5': '3b5ca6aa22b60dfeeadf50b72e44ed82',
 304             'note': 'Vimeo Pro video (#1197)',
 305             'info_dict': {
 306                 'id': '68093876',
 307                 'ext': 'mp4',
 308                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/openstreetmapus',
 309                 'uploader_id': 'openstreetmapus',
 310                 'uploader': 'OpenStreetMap US',
 311                 'title': 'Andy Allan - Putting the Carto into OpenStreetMap Cartography',
 312                 'description': 'md5:2c362968038d4499f4d79f88458590c1',
 313                 'duration': 1595,
 314                 'upload_date': '20130610',
 315                 'timestamp': 1370893156,
 316             },
 317             'params': {
 318                 'format': 'best[protocol=https]',
 319             },
 320         },
 321         {
 322             'url': 'http://player.vimeo.com/video/54469442',
 323             'md5': '619b811a4417aa4abe78dc653becf511',
 324             'note': 'Videos that embed the url in the player page',
 325             'info_dict': {
 326                 'id': '54469442',
 327                 'ext': 'mp4',
 328                 'title': 'Kathy Sierra: Building the minimum Badass User, Business of Software 2012',
 329                 'uploader': 'The BLN & Business of Software',
 330                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/theblnbusinessofsoftware',
 331                 'uploader_id': 'theblnbusinessofsoftware',
 332                 'duration': 3610,
 333                 'description': None,
 334             },
 335             'params': {
 336                 'format': 'best[protocol=https]',
 337             },
 338             'expected_warnings': ['Unable to download JSON metadata'],
 339         },
 340         {
 341             'url': 'http://vimeo.com/68375962',
 342             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 343             'note': 'Video protected with password',
 344             'info_dict': {
 345                 'id': '68375962',
 346                 'ext': 'mp4',
 347                 'title': 'youtube-dl password protected test video',
 348                 'timestamp': 1371200155,
 349                 'upload_date': '20130614',
 350                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 351                 'uploader_id': 'user18948128',
 352                 'uploader': 'Jaime Marquínez Ferrándiz',
 353                 'duration': 10,
 354                 'description': 'md5:dca3ea23adb29ee387127bc4ddfce63f',
 355             },
 356             'params': {
 357                 'format': 'best[protocol=https]',
 358                 'videopassword': 'youtube-dl',
 359             },
 360         },
 361         {
 362             'url': 'http://vimeo.com/channels/keypeele/75629013',
 363             'md5': '2f86a05afe9d7abc0b9126d229bbe15d',
 364             'info_dict': {
 365                 'id': '75629013',
 366                 'ext': 'mp4',
 367                 'title': 'Key & Peele: Terrorist Interrogation',
 368                 'description': 'md5:8678b246399b070816b12313e8b4eb5c',
 369                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/atencio',
 370                 'uploader_id': 'atencio',
 371                 'uploader': 'Peter Atencio',
 372                 'channel_id': 'keypeele',
 373                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/keypeele',
 374                 'timestamp': 1380339469,
 375                 'upload_date': '20130928',
 376                 'duration': 187,
 377             },
 378             'expected_warnings': ['Unable to download JSON metadata'],
 379         },
 380         {
 381             'url': 'http://vimeo.com/76979871',
 382             'note': 'Video with subtitles',
 383             'info_dict': {
 384                 'id': '76979871',
 385                 'ext': 'mp4',
 386                 'title': 'The New Vimeo Player (You Know, For Videos)',
 387                 'description': 'md5:2ec900bf97c3f389378a96aee11260ea',
 388                 'timestamp': 1381846109,
 389                 'upload_date': '20131015',
 390                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/staff',
 391                 'uploader_id': 'staff',
 392                 'uploader': 'Vimeo Staff',
 393                 'duration': 62,
 394             }
 395         },
 396         {
 397             # from https://www.ouya.tv/game/Pier-Solar-and-the-Great-Architects/
 398             'url': 'https://player.vimeo.com/video/98044508',
 399             'note': 'The js code contains assignments to the same variable as the config',
 400             'info_dict': {
 401                 'id': '98044508',
 402                 'ext': 'mp4',
 403                 'title': 'Pier Solar OUYA Official Trailer',
 404                 'uploader': 'Tulio Gonçalves',
 405                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user28849593',
 406                 'uploader_id': 'user28849593',
 407             },
 408         },
 409         {
 410             # contains original format
 411             'url': 'https://vimeo.com/33951933',
 412             'md5': '53c688fa95a55bf4b7293d37a89c5c53',
 413             'info_dict': {
 414                 'id': '33951933',
 415                 'ext': 'mp4',
 416                 'title': 'FOX CLASSICS - Forever Classic ID - A Full Minute',
 417                 'uploader': 'The DMCI',
 418                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/dmci',
 419                 'uploader_id': 'dmci',
 420                 'timestamp': 1324343742,
 421                 'upload_date': '20111220',
 422                 'description': 'md5:ae23671e82d05415868f7ad1aec21147',
 423             },
 424         },
 425         {
 426             # only available via https://vimeo.com/channels/tributes/6213729 and
 427             # not via https://vimeo.com/6213729
 428             'url': 'https://vimeo.com/channels/tributes/6213729',
 429             'info_dict': {
 430                 'id': '6213729',
 431                 'ext': 'mp4',
 432                 'title': 'Vimeo Tribute: The Shining',
 433                 'uploader': 'Casey Donahue',
 434                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/caseydonahue',
 435                 'uploader_id': 'caseydonahue',
 436                 'channel_url': r're:https?://(?:www\.)?vimeo\.com/channels/tributes',
 437                 'channel_id': 'tributes',
 438                 'timestamp': 1250886430,
 439                 'upload_date': '20090821',
 440                 'description': 'md5:bdbf314014e58713e6e5b66eb252f4a6',
 441             },
 442             'params': {
 443                 'skip_download': True,
 444             },
 445             'expected_warnings': ['Unable to download JSON metadata'],
 446         },
 447         {
 448             # redirects to ondemand extractor and should be passed through it
 449             # for successful extraction
 450             'url': 'https://vimeo.com/73445910',
 451             'info_dict': {
 452                 'id': '73445910',
 453                 'ext': 'mp4',
 454                 'title': 'The Reluctant Revolutionary',
 455                 'uploader': '10Ft Films',
 456                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/tenfootfilms',
 457                 'uploader_id': 'tenfootfilms',
 458                 'description': 'md5:0fa704e05b04f91f40b7f3ca2e801384',
 459                 'upload_date': '20130830',
 460                 'timestamp': 1377853339,
 461             },
 462             'params': {
 463                 'skip_download': True,
 464             },
 465             'expected_warnings': ['Unable to download JSON metadata'],
 466         },
 467         {
 468             'url': 'http://player.vimeo.com/video/68375962',
 469             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
 470             'info_dict': {
 471                 'id': '68375962',
 472                 'ext': 'mp4',
 473                 'title': 'youtube-dl password protected test video',
 474                 'uploader_url': r're:https?://(?:www\.)?vimeo\.com/user18948128',
 475                 'uploader_id': 'user18948128',
 476                 'uploader': 'Jaime Marquínez Ferrándiz',
 477                 'duration': 10,
 478             },
 479             'params': {
 480                 'format': 'best[protocol=https]',
 481                 'videopassword': 'youtube-dl',
 482             },
 483         },
 484         {
 485             'url': 'http://vimeo.com/moogaloop.swf?clip_id=2539741',
 486             'only_matching': True,
 487         },
 488         {
 489             'url': 'https://vimeo.com/109815029',
 490             'note': 'Video not completely processed, "failed" seed status',
 491             'only_matching': True,
 492         },
 493         {
 494             'url': 'https://vimeo.com/groups/travelhd/videos/22439234',
 495             'only_matching': True,
 496         },
 497         {
 498             'url': 'https://vimeo.com/album/2632481/video/79010983',
 499             'only_matching': True,
 500         },
 501         {
 502             # source file returns 403: Forbidden
 503             'url': 'https://vimeo.com/7809605',
 504             'only_matching': True,
 505         },
 506         {
 507             'url': 'https://vimeo.com/160743502/abd0e13fb4',
 508             'only_matching': True,
 509         },
 510         {
 511             # requires passing unlisted_hash(a52724358e) to load_download_config request
 512             'url': 'https://vimeo.com/392479337/a52724358e',
 513             'only_matching': True,
 514         }
 515         # https://gettingthingsdone.com/workflowmap/
 516         # vimeo embed with check-password page protected by Referer header
 517     ]
 518
 519     @staticmethod
 520     def _smuggle_referrer(url, referrer_url):
 521         return smuggle_url(url, {'http_headers': {'Referer': referrer_url}})
 522
 523     @staticmethod
 524     def _extract_urls(url, webpage):
 525         urls = []
 526         # Look for embedded (iframe) Vimeo player
 527         for mobj in re.finditer(
 528                 r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//player\.vimeo\.com/video/\d+.*?)\1',
 529                 webpage):
 530             urls.append(VimeoIE._smuggle_referrer(unescapeHTML(mobj.group('url')), url))
 531         PLAIN_EMBED_RE = (
 532             # Look for embedded (swf embed) Vimeo player
 533             r'<embed[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/moogaloop\.swf.+?)\1',
 534             # Look more for non-standard embedded Vimeo player
 535             r'<video[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?vimeo\.com/[0-9]+)\1',
 536         )
 537         for embed_re in PLAIN_EMBED_RE:
 538             for mobj in re.finditer(embed_re, webpage):
 539                 urls.append(mobj.group('url'))
 540         return urls
 541
 542     @staticmethod
 543     def _extract_url(url, webpage):
 544         urls = VimeoIE._extract_urls(url, webpage)
 545         return urls[0] if urls else None
 546
 547     def _verify_player_video_password(self, url, video_id, headers):
 548         password = self._downloader.params.get('videopassword')
 549         if password is None:
 550             raise ExtractorError('This video is protected by a password, use the --video-password option', expected=True)
 551         data = urlencode_postdata({
 552             'password': base64.b64encode(password.encode()),
 553         })
 554         headers = merge_dicts(headers, {
 555             'Content-Type': 'application/x-www-form-urlencoded',
 556         })
 557         checked = self._download_json(
 558             url + '/check-password', video_id,
 559             'Verifying the password', data=data, headers=headers)
 560         if checked is False:
 561             raise ExtractorError('Wrong video password', expected=True)
 562         return checked
 563
 564     def _real_initialize(self):
 565         self._login()
 566
 567     def _real_extract(self, url):
 568         url, data = unsmuggle_url(url, {})
 569         headers = std_headers.copy()
 570         if 'http_headers' in data:
 571             headers.update(data['http_headers'])
 572         if 'Referer' not in headers:
 573             headers['Referer'] = url
 574
 575         channel_id = self._search_regex(
 576             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
 577
 578         # Extract ID from URL
 579         video_id = self._match_id(url)
 580         orig_url = url
 581         is_pro = 'vimeopro.com/' in url
 582         is_player = '://player.vimeo.com/video/' in url
 583         if is_pro:
 584             # some videos require portfolio_id to be present in player url
 585             # https://github.com/ytdl-org/youtube-dl/issues/20070
 586             url = self._extract_url(url, self._download_webpage(url, video_id))
 587             if not url:
 588                 url = 'https://vimeo.com/' + video_id
 589         elif is_player:
 590             url = 'https://player.vimeo.com/video/' + video_id
 591         elif any(p in url for p in ('play_redirect_hls', 'moogaloop.swf')):
 592             url = 'https://vimeo.com/' + video_id
 593
 594         try:
 595             # Retrieve video webpage to extract further information
 596             webpage, urlh = self._download_webpage_handle(
 597                 url, video_id, headers=headers)
 598             redirect_url = urlh.geturl()
 599         except ExtractorError as ee:
 600             if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 403:
 601                 errmsg = ee.cause.read()
 602                 if b'Because of its privacy settings, this video cannot be played here' in errmsg:
 603                     raise ExtractorError(
 604                         'Cannot download embed-only video without embedding '
 605                         'URL. Please call yt-dlp with the URL of the page '
 606                         'that embeds this video.',
 607                         expected=True)
 608             raise
 609
 610         # Now we begin extracting as much information as we can from what we
 611         # retrieved. First we extract the information common to all extractors,
 612         # and latter we extract those that are Vimeo specific.
 613         self.report_extraction(video_id)
 614
 615         vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
 616         if vimeo_config:
 617             seed_status = vimeo_config.get('seed_status', {})
 618             if seed_status.get('state') == 'failed':
 619                 raise ExtractorError(
 620                     '%s said: %s' % (self.IE_NAME, seed_status['title']),
 621                     expected=True)
 622
 623         cc_license = None
 624         timestamp = None
 625         video_description = None
 626
 627         # Extract the config JSON
 628         try:
 629             try:
 630                 config_url = self._html_search_regex(
 631                     r' data-config-url="(.+?)"', webpage,
 632                     'config URL', default=None)
 633                 if not config_url:
 634                     # Sometimes new react-based page is served instead of old one that require
 635                     # different config URL extraction approach (see
 636                     # https://github.com/ytdl-org/youtube-dl/pull/7209)
 637                     page_config = self._parse_json(self._search_regex(
 638                         r'vimeo\.(?:clip|vod_title)_page_config\s*=\s*({.+?});',
 639                         webpage, 'page config'), video_id)
 640                     config_url = page_config['player']['config_url']
 641                     cc_license = page_config.get('cc_license')
 642                     timestamp = try_get(
 643                         page_config, lambda x: x['clip']['uploaded_on'],
 644                         compat_str)
 645                     video_description = clean_html(dict_get(
 646                         page_config, ('description', 'description_html_escaped')))
 647                 config = self._download_json(config_url, video_id)
 648             except RegexNotFoundError:
 649                 # For pro videos or player.vimeo.com urls
 650                 # We try to find out to which variable is assigned the config dic
 651                 m_variable_name = re.search(r'(\w)\.video\.id', webpage)
 652                 if m_variable_name is not None:
 653                     config_re = [r'%s=({[^}].+?});' % re.escape(m_variable_name.group(1))]
 654                 else:
 655                     config_re = [r' = {config:({.+?}),assets:', r'(?:[abc])=({.+?});']
 656                 config_re.append(r'\bvar\s+r\s*=\s*({.+?})\s*;')
 657                 config_re.append(r'\bconfig\s*=\s*({.+?})\s*;')
 658                 config = self._search_regex(config_re, webpage, 'info section',
 659                                             flags=re.DOTALL)
 660                 config = json.loads(config)
 661         except Exception as e:
 662             if re.search('The creator of this video has not given you permission to embed it on this domain.', webpage):
 663                 raise ExtractorError('The author has restricted the access to this video, try with the "--referer" option')
 664
 665             if re.search(r'<form[^>]+?id="pw_form"', webpage) is not None:
 666                 if '_video_password_verified' in data:
 667                     raise ExtractorError('video password verification failed!')
 668                 self._verify_video_password(redirect_url, video_id, webpage)
 669                 return self._real_extract(
 670                     smuggle_url(redirect_url, {'_video_password_verified': 'verified'}))
 671             else:
 672                 raise ExtractorError('Unable to extract info section',
 673                                      cause=e)
 674         else:
 675             if config.get('view') == 4:
 676                 config = self._verify_player_video_password(redirect_url, video_id, headers)
 677
 678         video = config.get('video') or {}
 679         vod = video.get('vod') or {}
 680
 681         def is_rented():
 682             if '>You rented this title.<' in webpage:
 683                 return True
 684             if config.get('user', {}).get('purchased'):
 685                 return True
 686             for purchase_option in vod.get('purchase_options', []):
 687                 if purchase_option.get('purchased'):
 688                     return True
 689                 label = purchase_option.get('label_string')
 690                 if label and (label.startswith('You rented this') or label.endswith(' remaining')):
 691                     return True
 692             return False
 693
 694         if is_rented() and vod.get('is_trailer'):
 695             feature_id = vod.get('feature_id')
 696             if feature_id and not data.get('force_feature_id', False):
 697                 return self.url_result(smuggle_url(
 698                     'https://player.vimeo.com/player/%s' % feature_id,
 699                     {'force_feature_id': True}), 'Vimeo')
 700
 701         # Extract video description
 702         if not video_description:
 703             video_description = self._html_search_regex(
 704                 r'(?s)<div\s+class="[^"]*description[^"]*"[^>]*>(.*?)</div>',
 705                 webpage, 'description', default=None)
 706         if not video_description:
 707             video_description = self._html_search_meta(
 708                 'description', webpage, default=None)
 709         if not video_description and is_pro:
 710             orig_webpage = self._download_webpage(
 711                 orig_url, video_id,
 712                 note='Downloading webpage for description',
 713                 fatal=False)
 714             if orig_webpage:
 715                 video_description = self._html_search_meta(
 716                     'description', orig_webpage, default=None)
 717         if not video_description and not is_player:
 718             self._downloader.report_warning('Cannot find video description')
 719
 720         # Extract upload date
 721         if not timestamp:
 722             timestamp = self._search_regex(
 723                 r'<time[^>]+datetime="([^"]+)"', webpage,
 724                 'timestamp', default=None)
 725
 726         try:
 727             view_count = int(self._search_regex(r'UserPlays:(\d+)', webpage, 'view count'))
 728             like_count = int(self._search_regex(r'UserLikes:(\d+)', webpage, 'like count'))
 729             comment_count = int(self._search_regex(r'UserComments:(\d+)', webpage, 'comment count'))
 730         except RegexNotFoundError:
 731             # This info is only available in vimeo.com/{id} urls
 732             view_count = None
 733             like_count = None
 734             comment_count = None
 735
 736         formats = []
 737
 738         source_format = self._extract_original_format(
 739             'https://vimeo.com/' + video_id, video_id, video.get('unlisted_hash'))
 740         if source_format:
 741             formats.append(source_format)
 742
 743         info_dict_config = self._parse_config(config, video_id)
 744         formats.extend(info_dict_config['formats'])
 745         self._vimeo_sort_formats(formats)
 746
 747         json_ld = self._search_json_ld(webpage, video_id, default={})
 748
 749         if not cc_license:
 750             cc_license = self._search_regex(
 751                 r'<link[^>]+rel=["\']license["\'][^>]+href=(["\'])(?P<license>(?:(?!\1).)+)\1',
 752                 webpage, 'license', default=None, group='license')
 753
 754         channel_url = 'https://vimeo.com/channels/%s' % channel_id if channel_id else None
 755
 756         info_dict = {
 757             'formats': formats,
 758             'timestamp': unified_timestamp(timestamp),
 759             'description': video_description,
 760             'webpage_url': url,
 761             'view_count': view_count,
 762             'like_count': like_count,
 763             'comment_count': comment_count,
 764             'license': cc_license,
 765             'channel_id': channel_id,
 766             'channel_url': channel_url,
 767         }
 768
 769         info_dict = merge_dicts(info_dict, info_dict_config, json_ld)
 770
 771         return info_dict
 772
 773
 774 class VimeoOndemandIE(VimeoIE):
 775     IE_NAME = 'vimeo:ondemand'
 776     _VALID_URL = r'https?://(?:www\.)?vimeo\.com/ondemand/([^/]+/)?(?P<id>[^/?#&]+)'
 777     _TESTS = [{
 778         # ondemand video not available via https://vimeo.com/id
 779         'url': 'https://vimeo.com/ondemand/20704',
 780         'md5': 'c424deda8c7f73c1dfb3edd7630e2f35',
 781         'info_dict': {
 782             'id': '105442900',
 783             'ext': 'mp4',
 784             'title': 'המעבדה - במאי יותם פלדמן',
 785             'uploader': 'גם סרטים',
 786             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/gumfilms',
 787             'uploader_id': 'gumfilms',
 788             'description': 'md5:4c027c965e439de4baab621e48b60791',
 789             'upload_date': '20140906',
 790             'timestamp': 1410032453,
 791         },
 792         'params': {
 793             'format': 'best[protocol=https]',
 794         },
 795         'expected_warnings': ['Unable to download JSON metadata'],
 796     }, {
 797         # requires Referer to be passed along with og:video:url
 798         'url': 'https://vimeo.com/ondemand/36938/126682985',
 799         'info_dict': {
 800             'id': '126584684',
 801             'ext': 'mp4',
 802             'title': 'Rävlock, rätt läte på rätt plats',
 803             'uploader': 'Lindroth & Norin',
 804             'uploader_url': r're:https?://(?:www\.)?vimeo\.com/lindrothnorin',
 805             'uploader_id': 'lindrothnorin',
 806             'description': 'md5:c3c46a90529612c8279fb6af803fc0df',
 807             'upload_date': '20150502',
 808             'timestamp': 1430586422,
 809         },
 810         'params': {
 811             'skip_download': True,
 812         },
 813         'expected_warnings': ['Unable to download JSON metadata'],
 814     }, {
 815         'url': 'https://vimeo.com/ondemand/nazmaalik',
 816         'only_matching': True,
 817     }, {
 818         'url': 'https://vimeo.com/ondemand/141692381',
 819         'only_matching': True,
 820     }, {
 821         'url': 'https://vimeo.com/ondemand/thelastcolony/150274832',
 822         'only_matching': True,
 823     }]
 824
 825
 826 class VimeoChannelIE(VimeoBaseInfoExtractor):
 827     IE_NAME = 'vimeo:channel'
 828     _VALID_URL = r'https://vimeo\.com/channels/(?P<id>[^/?#]+)/?(?:$|[?#])'
 829     _MORE_PAGES_INDICATOR = r'<a.+?rel="next"'
 830     _TITLE = None
 831     _TITLE_RE = r'<link rel="alternate"[^>]+?title="(.*?)"'
 832     _TESTS = [{
 833         'url': 'https://vimeo.com/channels/tributes',
 834         'info_dict': {
 835             'id': 'tributes',
 836             'title': 'Vimeo Tributes',
 837         },
 838         'playlist_mincount': 25,
 839     }]
 840     _BASE_URL_TEMPL = 'https://vimeo.com/channels/%s'
 841
 842     def _page_url(self, base_url, pagenum):
 843         return '%s/videos/page:%d/' % (base_url, pagenum)
 844
 845     def _extract_list_title(self, webpage):
 846         return self._TITLE or self._html_search_regex(
 847             self._TITLE_RE, webpage, 'list title', fatal=False)
 848
 849     def _title_and_entries(self, list_id, base_url):
 850         for pagenum in itertools.count(1):
 851             page_url = self._page_url(base_url, pagenum)
 852             webpage = self._download_webpage(
 853                 page_url, list_id,
 854                 'Downloading page %s' % pagenum)
 855
 856             if pagenum == 1:
 857                 yield self._extract_list_title(webpage)
 858
 859             # Try extracting href first since not all videos are available via
 860             # short https://vimeo.com/id URL (e.g. https://vimeo.com/channels/tributes/6213729)
 861             clips = re.findall(
 862                 r'id="clip_(\d+)"[^>]*>\s*<a[^>]+href="(/(?:[^/]+/)*\1)(?:[^>]+\btitle="([^"]+)")?', webpage)
 863             if clips:
 864                 for video_id, video_url, video_title in clips:
 865                     yield self.url_result(
 866                         compat_urlparse.urljoin(base_url, video_url),
 867                         VimeoIE.ie_key(), video_id=video_id, video_title=video_title)
 868             # More relaxed fallback
 869             else:
 870                 for video_id in re.findall(r'id=["\']clip_(\d+)', webpage):
 871                     yield self.url_result(
 872                         'https://vimeo.com/%s' % video_id,
 873                         VimeoIE.ie_key(), video_id=video_id)
 874
 875             if re.search(self._MORE_PAGES_INDICATOR, webpage, re.DOTALL) is None:
 876                 break
 877
 878     def _extract_videos(self, list_id, base_url):
 879         title_and_entries = self._title_and_entries(list_id, base_url)
 880         list_title = next(title_and_entries)
 881         return self.playlist_result(title_and_entries, list_id, list_title)
 882
 883     def _real_extract(self, url):
 884         channel_id = self._match_id(url)
 885         return self._extract_videos(channel_id, self._BASE_URL_TEMPL % channel_id)
 886
 887
 888 class VimeoUserIE(VimeoChannelIE):
 889     IE_NAME = 'vimeo:user'
 890     _VALID_URL = r'https://vimeo\.com/(?!(?:[0-9]+|watchlater)(?:$|[?#/]))(?P<id>[^/]+)(?:/videos|[#?]|$)'
 891     _TITLE_RE = r'<a[^>]+?class="user">([^<>]+?)</a>'
 892     _TESTS = [{
 893         'url': 'https://vimeo.com/nkistudio/videos',
 894         'info_dict': {
 895             'title': 'Nki',
 896             'id': 'nkistudio',
 897         },
 898         'playlist_mincount': 66,
 899     }]
 900     _BASE_URL_TEMPL = 'https://vimeo.com/%s'
 901
 902
 903 class VimeoAlbumIE(VimeoBaseInfoExtractor):
 904     IE_NAME = 'vimeo:album'
 905     _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P<id>\d+)(?:$|[?#]|/(?!video))'
 906     _TITLE_RE = r'<header id="page_header">\n\s*<h1>(.*?)</h1>'
 907     _TESTS = [{
 908         'url': 'https://vimeo.com/album/2632481',
 909         'info_dict': {
 910             'id': '2632481',
 911             'title': 'Staff Favorites: November 2013',
 912         },
 913         'playlist_mincount': 13,
 914     }, {
 915         'note': 'Password-protected album',
 916         'url': 'https://vimeo.com/album/3253534',
 917         'info_dict': {
 918             'title': 'test',
 919             'id': '3253534',
 920         },
 921         'playlist_count': 1,
 922         'params': {
 923             'videopassword': 'youtube-dl',
 924         }
 925     }]
 926     _PAGE_SIZE = 100
 927
 928     def _fetch_page(self, album_id, authorization, hashed_pass, page):
 929         api_page = page + 1
 930         query = {
 931             'fields': 'link,uri',
 932             'page': api_page,
 933             'per_page': self._PAGE_SIZE,
 934         }
 935         if hashed_pass:
 936             query['_hashed_pass'] = hashed_pass
 937         videos = self._download_json(
 938             'https://api.vimeo.com/albums/%s/videos' % album_id,
 939             album_id, 'Downloading page %d' % api_page, query=query, headers={
 940                 'Authorization': 'jwt ' + authorization,
 941             })['data']
 942         for video in videos:
 943             link = video.get('link')
 944             if not link:
 945                 continue
 946             uri = video.get('uri')
 947             video_id = self._search_regex(r'/videos/(\d+)', uri, 'video_id', default=None) if uri else None
 948             yield self.url_result(link, VimeoIE.ie_key(), video_id)
 949
 950     def _real_extract(self, url):
 951         album_id = self._match_id(url)
 952         viewer = self._download_json(
 953             'https://vimeo.com/_rv/viewer', album_id, fatal=False)
 954         if not viewer:
 955             webpage = self._download_webpage(url, album_id)
 956             viewer = self._parse_json(self._search_regex(
 957                 r'bootstrap_data\s*=\s*({.+?})</script>',
 958                 webpage, 'bootstrap data'), album_id)['viewer']
 959         jwt = viewer['jwt']
 960         album = self._download_json(
 961             'https://api.vimeo.com/albums/' + album_id,
 962             album_id, headers={'Authorization': 'jwt ' + jwt},
 963             query={'fields': 'description,name,privacy'})
 964         hashed_pass = None
 965         if try_get(album, lambda x: x['privacy']['view']) == 'password':
 966             password = self._downloader.params.get('videopassword')
 967             if not password:
 968                 raise ExtractorError(
 969                     'This album is protected by a password, use the --video-password option',
 970                     expected=True)
 971             self._set_vimeo_cookie('vuid', viewer['vuid'])
 972             try:
 973                 hashed_pass = self._download_json(
 974                     'https://vimeo.com/showcase/%s/auth' % album_id,
 975                     album_id, 'Verifying the password', data=urlencode_postdata({
 976                         'password': password,
 977                         'token': viewer['xsrft'],
 978                     }), headers={
 979                         'X-Requested-With': 'XMLHttpRequest',
 980                     })['hashed_pass']
 981             except ExtractorError as e:
 982                 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
 983                     raise ExtractorError('Wrong password', expected=True)
 984                 raise
 985         entries = OnDemandPagedList(functools.partial(
 986             self._fetch_page, album_id, jwt, hashed_pass), self._PAGE_SIZE)
 987         return self.playlist_result(
 988             entries, album_id, album.get('name'), album.get('description'))
 989
 990
 991 class VimeoGroupsIE(VimeoChannelIE):
 992     IE_NAME = 'vimeo:group'
 993     _VALID_URL = r'https://vimeo\.com/groups/(?P<id>[^/]+)(?:/(?!videos?/\d+)|$)'
 994     _TESTS = [{
 995         'url': 'https://vimeo.com/groups/kattykay',
 996         'info_dict': {
 997             'id': 'kattykay',
 998             'title': 'Katty Kay',
 999         },
1000         'playlist_mincount': 27,
1001     }]
1002     _BASE_URL_TEMPL = 'https://vimeo.com/groups/%s'
1003
1004
1005 class VimeoReviewIE(VimeoBaseInfoExtractor):
1006     IE_NAME = 'vimeo:review'
1007     IE_DESC = 'Review pages on vimeo'
1008     _VALID_URL = r'(?P<url>https://vimeo\.com/[^/]+/review/(?P<id>[^/]+)/[0-9a-f]{10})'
1009     _TESTS = [{
1010         'url': 'https://vimeo.com/user21297594/review/75524534/3c257a1b5d',
1011         'md5': 'c507a72f780cacc12b2248bb4006d253',
1012         'info_dict': {
1013             'id': '75524534',
1014             'ext': 'mp4',
1015             'title': "DICK HARDWICK 'Comedian'",
1016             'uploader': 'Richard Hardwick',
1017             'uploader_id': 'user21297594',
1018             'description': "Comedian Dick Hardwick's five minute demo filmed in front of a live theater audience.\nEdit by Doug Mattocks",
1019         },
1020         'expected_warnings': ['Unable to download JSON metadata'],
1021     }, {
1022         'note': 'video player needs Referer',
1023         'url': 'https://vimeo.com/user22258446/review/91613211/13f927e053',
1024         'md5': '6295fdab8f4bf6a002d058b2c6dce276',
1025         'info_dict': {
1026             'id': '91613211',
1027             'ext': 'mp4',
1028             'title': 're:(?i)^Death by dogma versus assembling agile . Sander Hoogendoorn',
1029             'uploader': 'DevWeek Events',
1030             'duration': 2773,
1031             'thumbnail': r're:^https?://.*\.jpg$',
1032             'uploader_id': 'user22258446',
1033         },
1034         'skip': 'video gone',
1035     }, {
1036         'note': 'Password protected',
1037         'url': 'https://vimeo.com/user37284429/review/138823582/c4d865efde',
1038         'info_dict': {
1039             'id': '138823582',
1040             'ext': 'mp4',
1041             'title': 'EFFICIENT PICKUP MASTERCLASS MODULE 1',
1042             'uploader': 'TMB',
1043             'uploader_id': 'user37284429',
1044         },
1045         'params': {
1046             'videopassword': 'holygrail',
1047         },
1048         'skip': 'video gone',
1049     }]
1050
1051     def _real_initialize(self):
1052         self._login()
1053
1054     def _real_extract(self, url):
1055         page_url, video_id = re.match(self._VALID_URL, url).groups()
1056         clip_data = self._download_json(
1057             page_url.replace('/review/', '/review/data/'),
1058             video_id)['clipData']
1059         config_url = clip_data['configUrl']
1060         config = self._download_json(config_url, video_id)
1061         info_dict = self._parse_config(config, video_id)
1062         source_format = self._extract_original_format(
1063             page_url + '/action', video_id)
1064         if source_format:
1065             info_dict['formats'].append(source_format)
1066         self._vimeo_sort_formats(info_dict['formats'])
1067         info_dict['description'] = clean_html(clip_data.get('description'))
1068         return info_dict
1069
1070
1071 class VimeoWatchLaterIE(VimeoChannelIE):
1072     IE_NAME = 'vimeo:watchlater'
1073     IE_DESC = 'Vimeo watch later list, "vimeowatchlater" keyword (requires authentication)'
1074     _VALID_URL = r'https://vimeo\.com/(?:home/)?watchlater|:vimeowatchlater'
1075     _TITLE = 'Watch Later'
1076     _LOGIN_REQUIRED = True
1077     _TESTS = [{
1078         'url': 'https://vimeo.com/watchlater',
1079         'only_matching': True,
1080     }]
1081
1082     def _real_initialize(self):
1083         self._login()
1084
1085     def _page_url(self, base_url, pagenum):
1086         url = '%s/page:%d/' % (base_url, pagenum)
1087         request = sanitized_Request(url)
1088         # Set the header to get a partial html page with the ids,
1089         # the normal page doesn't contain them.
1090         request.add_header('X-Requested-With', 'XMLHttpRequest')
1091         return request
1092
1093     def _real_extract(self, url):
1094         return self._extract_videos('watchlater', 'https://vimeo.com/watchlater')
1095
1096
1097 class VimeoLikesIE(VimeoChannelIE):
1098     _VALID_URL = r'https://(?:www\.)?vimeo\.com/(?P<id>[^/]+)/likes/?(?:$|[?#]|sort:)'
1099     IE_NAME = 'vimeo:likes'
1100     IE_DESC = 'Vimeo user likes'
1101     _TESTS = [{
1102         'url': 'https://vimeo.com/user755559/likes/',
1103         'playlist_mincount': 293,
1104         'info_dict': {
1105             'id': 'user755559',
1106             'title': 'urza’s Likes',
1107         },
1108     }, {
1109         'url': 'https://vimeo.com/stormlapse/likes',
1110         'only_matching': True,
1111     }]
1112
1113     def _page_url(self, base_url, pagenum):
1114         return '%s/page:%d/' % (base_url, pagenum)
1115
1116     def _real_extract(self, url):
1117         user_id = self._match_id(url)
1118         return self._extract_videos(user_id, 'https://vimeo.com/%s/likes' % user_id)
1119
1120
1121 class VHXEmbedIE(VimeoBaseInfoExtractor):
1122     IE_NAME = 'vhx:embed'
1123     _VALID_URL = r'https?://embed\.vhx\.tv/videos/(?P<id>\d+)'
1124
1125     @staticmethod
1126     def _extract_url(webpage):
1127         mobj = re.search(
1128             r'<iframe[^>]+src="(https?://embed\.vhx\.tv/videos/\d+[^"]*)"', webpage)
1129         return unescapeHTML(mobj.group(1)) if mobj else None
1130
1131     def _real_extract(self, url):
1132         video_id = self._match_id(url)
1133         webpage = self._download_webpage(url, video_id)
1134         config_url = self._parse_json(self._search_regex(
1135             r'window\.OTTData\s*=\s*({.+})', webpage,
1136             'ott data'), video_id, js_to_json)['config_url']
1137         config = self._download_json(config_url, video_id)
1138         info = self._parse_config(config, video_id)
1139         info['id'] = video_id
1140         self._vimeo_sort_formats(info['formats'])
1141         return info