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