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