yt_dlp/extractor/npo.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..compat import (
   5     compat_HTTPError,
   6     compat_str,
   7 )
   8 from ..utils import (
   9     determine_ext,
  10     ExtractorError,
  11     fix_xml_ampersands,
  12     int_or_none,
  13     merge_dicts,
  14     orderedSet,
  15     parse_duration,
  16     qualities,
  17     str_or_none,
  18     strip_jsonp,
  19     unified_strdate,
  20     unified_timestamp,
  21     url_or_none,
  22     urlencode_postdata,
  23 )
  24
  25
  26 class NPOBaseIE(InfoExtractor):
  27     def _get_token(self, video_id):
  28         return self._download_json(
  29             'http://ida.omroep.nl/app.php/auth', video_id,
  30             note='Downloading token')['token']
  31
  32
  33 class NPOIE(NPOBaseIE):
  34     IE_NAME = 'npo'
  35     IE_DESC = 'npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl'
  36     _VALID_URL = r'''(?x)
  37                     (?:
  38                         npo:|
  39                         https?://
  40                             (?:www\.)?
  41                             (?:
  42                                 npo\.nl/(?:[^/]+/)*|
  43                                 (?:ntr|npostart)\.nl/(?:[^/]+/){2,}|
  44                                 omroepwnl\.nl/video/fragment/[^/]+__|
  45                                 (?:zapp|npo3)\.nl/(?:[^/]+/){2,}
  46                             )
  47                         )
  48                         (?P<id>[^/?#]+)
  49                 '''
  50
  51     _TESTS = [{
  52         'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
  53         'md5': '4b3f9c429157ec4775f2c9cb7b911016',
  54         'info_dict': {
  55             'id': 'VPWON_1220719',
  56             'ext': 'm4v',
  57             'title': 'Nieuwsuur',
  58             'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
  59             'upload_date': '20140622',
  60         },
  61     }, {
  62         'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
  63         'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
  64         'info_dict': {
  65             'id': 'VARA_101191800',
  66             'ext': 'm4v',
  67             'title': 'De Mega Mike & Mega Thomas show: The best of.',
  68             'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
  69             'upload_date': '20090227',
  70             'duration': 2400,
  71         },
  72     }, {
  73         'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
  74         'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
  75         'info_dict': {
  76             'id': 'VPWON_1169289',
  77             'ext': 'm4v',
  78             'title': 'Tegenlicht: Zwart geld. De toekomst komt uit Afrika',
  79             'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
  80             'upload_date': '20130225',
  81             'duration': 3000,
  82         },
  83     }, {
  84         'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
  85         'info_dict': {
  86             'id': 'WO_VPRO_043706',
  87             'ext': 'm4v',
  88             'title': 'De nieuwe mens - Deel 1',
  89             'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
  90             'duration': 4680,
  91         },
  92         'params': {
  93             'skip_download': True,
  94         }
  95     }, {
  96         # non asf in streams
  97         'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
  98         'info_dict': {
  99             'id': 'WO_NOS_762771',
 100             'ext': 'mp4',
 101             'title': 'Hoe gaat Europa verder na Parijs?',
 102         },
 103         'params': {
 104             'skip_download': True,
 105         }
 106     }, {
 107         'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
 108         'info_dict': {
 109             'id': 'VPWON_1233944',
 110             'ext': 'm4v',
 111             'title': 'Aap, poot, pies',
 112             'description': 'md5:c9c8005d1869ae65b858e82c01a91fde',
 113             'upload_date': '20150508',
 114             'duration': 599,
 115         },
 116         'params': {
 117             'skip_download': True,
 118         }
 119     }, {
 120         'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
 121         'info_dict': {
 122             'id': 'POW_00996502',
 123             'ext': 'm4v',
 124             'title': '''"Dit is wel een 'landslide'..."''',
 125             'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
 126             'upload_date': '20150508',
 127             'duration': 462,
 128         },
 129         'params': {
 130             'skip_download': True,
 131         }
 132     }, {
 133         # audio
 134         'url': 'http://www.npo.nl/jouw-stad-rotterdam/29-01-2017/RBX_FUNX_6683215/RBX_FUNX_7601437',
 135         'info_dict': {
 136             'id': 'RBX_FUNX_6683215',
 137             'ext': 'mp3',
 138             'title': 'Jouw Stad Rotterdam',
 139             'description': 'md5:db251505244f097717ec59fabc372d9f',
 140         },
 141         'params': {
 142             'skip_download': True,
 143         }
 144     }, {
 145         'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547',
 146         'only_matching': True,
 147     }, {
 148         'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118',
 149         'only_matching': True,
 150     }, {
 151         'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
 152         'only_matching': True,
 153     }, {
 154         'url': 'https://www.npo3.nl/3onderzoekt/16-09-2015/VPWON_1239870',
 155         'only_matching': True,
 156     }, {
 157         # live stream
 158         'url': 'npo:LI_NL1_4188102',
 159         'only_matching': True,
 160     }, {
 161         'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373',
 162         'only_matching': True,
 163     }, {
 164         'url': 'https://www.zapp.nl/1803-skelterlab/instructie-video-s/740-instructievideo-s/POMS_AT_11736927',
 165         'only_matching': True,
 166     }, {
 167         'url': 'https://www.npostart.nl/broodje-gezond-ei/28-05-2018/KN_1698996',
 168         'only_matching': True,
 169     }, {
 170         'url': 'https://npo.nl/KN_1698996',
 171         'only_matching': True,
 172     }]
 173
 174     @classmethod
 175     def suitable(cls, url):
 176         return (False if any(ie.suitable(url)
 177                 for ie in (NPOLiveIE, NPORadioIE, NPORadioFragmentIE))
 178                 else super(NPOIE, cls).suitable(url))
 179
 180     def _real_extract(self, url):
 181         video_id = self._match_id(url)
 182         return self._get_info(url, video_id) or self._get_old_info(video_id)
 183
 184     def _get_info(self, url, video_id):
 185         token = self._download_json(
 186             'https://www.npostart.nl/api/token', video_id,
 187             'Downloading token', headers={
 188                 'Referer': url,
 189                 'X-Requested-With': 'XMLHttpRequest',
 190             })['token']
 191
 192         player = self._download_json(
 193             'https://www.npostart.nl/player/%s' % video_id, video_id,
 194             'Downloading player JSON', data=urlencode_postdata({
 195                 'autoplay': 0,
 196                 'share': 1,
 197                 'pageUrl': url,
 198                 'hasAdConsent': 0,
 199                 '_token': token,
 200             }))
 201
 202         player_token = player['token']
 203
 204         drm = False
 205         format_urls = set()
 206         formats = []
 207         for profile in ('hls', 'dash-widevine', 'dash-playready', 'smooth'):
 208             streams = self._download_json(
 209                 'https://start-player.npo.nl/video/%s/streams' % video_id,
 210                 video_id, 'Downloading %s profile JSON' % profile, fatal=False,
 211                 query={
 212                     'profile': profile,
 213                     'quality': 'npo',
 214                     'tokenId': player_token,
 215                     'streamType': 'broadcast',
 216                 })
 217             if not streams:
 218                 continue
 219             stream = streams.get('stream')
 220             if not isinstance(stream, dict):
 221                 continue
 222             stream_url = url_or_none(stream.get('src'))
 223             if not stream_url or stream_url in format_urls:
 224                 continue
 225             format_urls.add(stream_url)
 226             if stream.get('protection') is not None or stream.get('keySystemOptions') is not None:
 227                 drm = True
 228                 continue
 229             stream_type = stream.get('type')
 230             stream_ext = determine_ext(stream_url)
 231             if stream_type == 'application/dash+xml' or stream_ext == 'mpd':
 232                 formats.extend(self._extract_mpd_formats(
 233                     stream_url, video_id, mpd_id='dash', fatal=False))
 234             elif stream_type == 'application/vnd.apple.mpegurl' or stream_ext == 'm3u8':
 235                 formats.extend(self._extract_m3u8_formats(
 236                     stream_url, video_id, ext='mp4',
 237                     entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
 238             elif re.search(r'\.isml?/Manifest', stream_url):
 239                 formats.extend(self._extract_ism_formats(
 240                     stream_url, video_id, ism_id='mss', fatal=False))
 241             else:
 242                 formats.append({
 243                     'url': stream_url,
 244                 })
 245
 246         if not formats:
 247             if not self.get_param('allow_unplayable_formats') and drm:
 248                 self.report_drm(video_id)
 249
 250         self._sort_formats(formats)
 251
 252         info = {
 253             'id': video_id,
 254             'title': video_id,
 255             'formats': formats,
 256         }
 257
 258         embed_url = url_or_none(player.get('embedUrl'))
 259         if embed_url:
 260             webpage = self._download_webpage(
 261                 embed_url, video_id, 'Downloading embed page', fatal=False)
 262             if webpage:
 263                 video = self._parse_json(
 264                     self._search_regex(
 265                         r'\bvideo\s*=\s*({.+?})\s*;', webpage, 'video',
 266                         default='{}'), video_id)
 267                 if video:
 268                     title = video.get('episodeTitle')
 269                     subtitles = {}
 270                     subtitles_list = video.get('subtitles')
 271                     if isinstance(subtitles_list, list):
 272                         for cc in subtitles_list:
 273                             cc_url = url_or_none(cc.get('src'))
 274                             if not cc_url:
 275                                 continue
 276                             lang = str_or_none(cc.get('language')) or 'nl'
 277                             subtitles.setdefault(lang, []).append({
 278                                 'url': cc_url,
 279                             })
 280                     return merge_dicts({
 281                         'title': title,
 282                         'description': video.get('description'),
 283                         'thumbnail': url_or_none(
 284                             video.get('still_image_url') or video.get('orig_image_url')),
 285                         'duration': int_or_none(video.get('duration')),
 286                         'timestamp': unified_timestamp(video.get('broadcastDate')),
 287                         'creator': video.get('channel'),
 288                         'series': video.get('title'),
 289                         'episode': title,
 290                         'episode_number': int_or_none(video.get('episodeNumber')),
 291                         'subtitles': subtitles,
 292                     }, info)
 293
 294         return info
 295
 296     def _get_old_info(self, video_id):
 297         metadata = self._download_json(
 298             'http://e.omroep.nl/metadata/%s' % video_id,
 299             video_id,
 300             # We have to remove the javascript callback
 301             transform_source=strip_jsonp,
 302         )
 303
 304         error = metadata.get('error')
 305         if error:
 306             raise ExtractorError(error, expected=True)
 307
 308         # For some videos actual video id (prid) is different (e.g. for
 309         # http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698
 310         # video id is POMS_WNL_853698 but prid is POW_00996502)
 311         video_id = metadata.get('prid') or video_id
 312
 313         # titel is too generic in some cases so utilize aflevering_titel as well
 314         # when available (e.g. http://tegenlicht.vpro.nl/afleveringen/2014-2015/access-to-africa.html)
 315         title = metadata['titel']
 316         sub_title = metadata.get('aflevering_titel')
 317         if sub_title and sub_title != title:
 318             title += ': %s' % sub_title
 319
 320         token = self._get_token(video_id)
 321
 322         formats = []
 323         urls = set()
 324
 325         def is_legal_url(format_url):
 326             return format_url and format_url not in urls and re.match(
 327                 r'^(?:https?:)?//', format_url)
 328
 329         QUALITY_LABELS = ('Laag', 'Normaal', 'Hoog')
 330         QUALITY_FORMATS = ('adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std')
 331
 332         quality_from_label = qualities(QUALITY_LABELS)
 333         quality_from_format_id = qualities(QUALITY_FORMATS)
 334         items = self._download_json(
 335             'http://ida.omroep.nl/app.php/%s' % video_id, video_id,
 336             'Downloading formats JSON', query={
 337                 'adaptive': 'yes',
 338                 'token': token,
 339             })['items'][0]
 340         for num, item in enumerate(items):
 341             item_url = item.get('url')
 342             if not is_legal_url(item_url):
 343                 continue
 344             urls.add(item_url)
 345             format_id = self._search_regex(
 346                 r'video/ida/([^/]+)', item_url, 'format id',
 347                 default=None)
 348
 349             item_label = item.get('label')
 350
 351             def add_format_url(format_url):
 352                 width = int_or_none(self._search_regex(
 353                     r'(\d+)[xX]\d+', format_url, 'width', default=None))
 354                 height = int_or_none(self._search_regex(
 355                     r'\d+[xX](\d+)', format_url, 'height', default=None))
 356                 if item_label in QUALITY_LABELS:
 357                     quality = quality_from_label(item_label)
 358                     f_id = item_label
 359                 elif item_label in QUALITY_FORMATS:
 360                     quality = quality_from_format_id(format_id)
 361                     f_id = format_id
 362                 else:
 363                     quality, f_id = [None] * 2
 364                 formats.append({
 365                     'url': format_url,
 366                     'format_id': f_id,
 367                     'width': width,
 368                     'height': height,
 369                     'quality': quality,
 370                 })
 371
 372             # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
 373             if item.get('contentType') in ('url', 'audio'):
 374                 add_format_url(item_url)
 375                 continue
 376
 377             try:
 378                 stream_info = self._download_json(
 379                     item_url + '&type=json', video_id,
 380                     'Downloading %s stream JSON'
 381                     % item_label or item.get('format') or format_id or num)
 382             except ExtractorError as ee:
 383                 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
 384                     error = (self._parse_json(
 385                         ee.cause.read().decode(), video_id,
 386                         fatal=False) or {}).get('errorstring')
 387                     if error:
 388                         raise ExtractorError(error, expected=True)
 389                 raise
 390             # Stream URL instead of JSON, example: npo:LI_NL1_4188102
 391             if isinstance(stream_info, compat_str):
 392                 if not stream_info.startswith('http'):
 393                     continue
 394                 video_url = stream_info
 395             # JSON
 396             else:
 397                 video_url = stream_info.get('url')
 398             if not video_url or 'vodnotavailable.' in video_url or video_url in urls:
 399                 continue
 400             urls.add(video_url)
 401             if determine_ext(video_url) == 'm3u8':
 402                 formats.extend(self._extract_m3u8_formats(
 403                     video_url, video_id, ext='mp4',
 404                     entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
 405             else:
 406                 add_format_url(video_url)
 407
 408         is_live = metadata.get('medium') == 'live'
 409
 410         if not is_live:
 411             for num, stream in enumerate(metadata.get('streams', [])):
 412                 stream_url = stream.get('url')
 413                 if not is_legal_url(stream_url):
 414                     continue
 415                 urls.add(stream_url)
 416                 # smooth streaming is not supported
 417                 stream_type = stream.get('type', '').lower()
 418                 if stream_type in ['ss', 'ms']:
 419                     continue
 420                 if stream_type == 'hds':
 421                     f4m_formats = self._extract_f4m_formats(
 422                         stream_url, video_id, fatal=False)
 423                     # f4m downloader downloads only piece of live stream
 424                     for f4m_format in f4m_formats:
 425                         f4m_format['preference'] = -5
 426                     formats.extend(f4m_formats)
 427                 elif stream_type == 'hls':
 428                     formats.extend(self._extract_m3u8_formats(
 429                         stream_url, video_id, ext='mp4', fatal=False))
 430                 # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
 431                 elif '.asf' in stream_url:
 432                     asx = self._download_xml(
 433                         stream_url, video_id,
 434                         'Downloading stream %d ASX playlist' % num,
 435                         transform_source=fix_xml_ampersands, fatal=False)
 436                     if not asx:
 437                         continue
 438                     ref = asx.find('./ENTRY/Ref')
 439                     if ref is None:
 440                         continue
 441                     video_url = ref.get('href')
 442                     if not video_url or video_url in urls:
 443                         continue
 444                     urls.add(video_url)
 445                     formats.append({
 446                         'url': video_url,
 447                         'ext': stream.get('formaat', 'asf'),
 448                         'quality': stream.get('kwaliteit'),
 449                         'preference': -10,
 450                     })
 451                 else:
 452                     formats.append({
 453                         'url': stream_url,
 454                         'quality': stream.get('kwaliteit'),
 455                     })
 456
 457         self._sort_formats(formats)
 458
 459         subtitles = {}
 460         if metadata.get('tt888') == 'ja':
 461             subtitles['nl'] = [{
 462                 'ext': 'vtt',
 463                 'url': 'http://tt888.omroep.nl/tt888/%s' % video_id,
 464             }]
 465
 466         return {
 467             'id': video_id,
 468             'title': title,
 469             'description': metadata.get('info'),
 470             'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
 471             'upload_date': unified_strdate(metadata.get('gidsdatum')),
 472             'duration': parse_duration(metadata.get('tijdsduur')),
 473             'formats': formats,
 474             'subtitles': subtitles,
 475             'is_live': is_live,
 476         }
 477
 478
 479 class NPOLiveIE(NPOBaseIE):
 480     IE_NAME = 'npo.nl:live'
 481     _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P<id>[^/?#&]+))?'
 482
 483     _TESTS = [{
 484         'url': 'http://www.npo.nl/live/npo-1',
 485         'info_dict': {
 486             'id': 'LI_NL1_4188102',
 487             'display_id': 'npo-1',
 488             'ext': 'mp4',
 489             'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 490             'is_live': True,
 491         },
 492         'params': {
 493             'skip_download': True,
 494         }
 495     }, {
 496         'url': 'http://www.npo.nl/live',
 497         'only_matching': True,
 498     }, {
 499         'url': 'https://www.npostart.nl/live/npo-1',
 500         'only_matching': True,
 501     }]
 502
 503     def _real_extract(self, url):
 504         display_id = self._match_id(url) or 'npo-1'
 505
 506         webpage = self._download_webpage(url, display_id)
 507
 508         live_id = self._search_regex(
 509             [r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id')
 510
 511         return {
 512             '_type': 'url_transparent',
 513             'url': 'npo:%s' % live_id,
 514             'ie_key': NPOIE.ie_key(),
 515             'id': live_id,
 516             'display_id': display_id,
 517         }
 518
 519
 520 class NPORadioIE(InfoExtractor):
 521     IE_NAME = 'npo.nl:radio'
 522     _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)'
 523
 524     _TEST = {
 525         'url': 'http://www.npo.nl/radio/radio-1',
 526         'info_dict': {
 527             'id': 'radio-1',
 528             'ext': 'mp3',
 529             'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 530             'is_live': True,
 531         },
 532         'params': {
 533             'skip_download': True,
 534         }
 535     }
 536
 537     @classmethod
 538     def suitable(cls, url):
 539         return False if NPORadioFragmentIE.suitable(url) else super(NPORadioIE, cls).suitable(url)
 540
 541     @staticmethod
 542     def _html_get_attribute_regex(attribute):
 543         return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)
 544
 545     def _real_extract(self, url):
 546         video_id = self._match_id(url)
 547
 548         webpage = self._download_webpage(url, video_id)
 549
 550         title = self._html_search_regex(
 551             self._html_get_attribute_regex('data-channel'), webpage, 'title')
 552
 553         stream = self._parse_json(
 554             self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
 555             video_id)
 556
 557         codec = stream.get('codec')
 558
 559         return {
 560             'id': video_id,
 561             'url': stream['url'],
 562             'title': title,
 563             'acodec': codec,
 564             'ext': codec,
 565             'is_live': True,
 566         }
 567
 568
 569 class NPORadioFragmentIE(InfoExtractor):
 570     IE_NAME = 'npo.nl:radio:fragment'
 571     _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'
 572
 573     _TEST = {
 574         'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
 575         'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
 576         'info_dict': {
 577             'id': '174356',
 578             'ext': 'mp3',
 579             'title': 'Jubileumconcert Willeke Alberti',
 580         },
 581     }
 582
 583     def _real_extract(self, url):
 584         audio_id = self._match_id(url)
 585
 586         webpage = self._download_webpage(url, audio_id)
 587
 588         title = self._html_search_regex(
 589             r'href="/radio/[^/]+/fragment/%s" title="([^"]+)"' % audio_id,
 590             webpage, 'title')
 591
 592         audio_url = self._search_regex(
 593             r"data-streams='([^']+)'", webpage, 'audio url')
 594
 595         return {
 596             'id': audio_id,
 597             'url': audio_url,
 598             'title': title,
 599         }
 600
 601
 602 class NPODataMidEmbedIE(InfoExtractor):
 603     def _real_extract(self, url):
 604         display_id = self._match_id(url)
 605         webpage = self._download_webpage(url, display_id)
 606         video_id = self._search_regex(
 607             r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
 608         return {
 609             '_type': 'url_transparent',
 610             'ie_key': 'NPO',
 611             'url': 'npo:%s' % video_id,
 612             'display_id': display_id
 613         }
 614
 615
 616 class SchoolTVIE(NPODataMidEmbedIE):
 617     IE_NAME = 'schooltv'
 618     _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'
 619
 620     _TEST = {
 621         'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/',
 622         'info_dict': {
 623             'id': 'WO_NTR_429477',
 624             'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
 625             'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?',
 626             'ext': 'mp4',
 627             'description': 'md5:abfa0ff690adb73fd0297fd033aaa631'
 628         },
 629         'params': {
 630             # Skip because of m3u8 download
 631             'skip_download': True
 632         }
 633     }
 634
 635
 636 class HetKlokhuisIE(NPODataMidEmbedIE):
 637     IE_NAME = 'hetklokhuis'
 638     _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
 639
 640     _TEST = {
 641         'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',
 642         'info_dict': {
 643             'id': 'VPWON_1260528',
 644             'display_id': 'Zwaartekrachtsgolven',
 645             'ext': 'm4v',
 646             'title': 'Het Klokhuis: Zwaartekrachtsgolven',
 647             'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48',
 648             'upload_date': '20170223',
 649         },
 650         'params': {
 651             'skip_download': True
 652         }
 653     }
 654
 655
 656 class NPOPlaylistBaseIE(NPOIE):
 657     def _real_extract(self, url):
 658         playlist_id = self._match_id(url)
 659
 660         webpage = self._download_webpage(url, playlist_id)
 661
 662         entries = [
 663             self.url_result('npo:%s' % video_id if not video_id.startswith('http') else video_id)
 664             for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage))
 665         ]
 666
 667         playlist_title = self._html_search_regex(
 668             self._PLAYLIST_TITLE_RE, webpage, 'playlist title',
 669             default=None) or self._og_search_title(webpage)
 670
 671         return self.playlist_result(entries, playlist_id, playlist_title)
 672
 673
 674 class VPROIE(NPOPlaylistBaseIE):
 675     IE_NAME = 'vpro'
 676     _VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
 677     _PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)',
 678                           r'<h5[^>]+class=["\'].*?\bmedia-platform-subtitle\b.*?["\'][^>]*>([^<]+)')
 679     _PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'
 680
 681     _TESTS = [
 682         {
 683             'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
 684             'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
 685             'info_dict': {
 686                 'id': 'VPWON_1169289',
 687                 'ext': 'm4v',
 688                 'title': 'De toekomst komt uit Afrika',
 689                 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
 690                 'upload_date': '20130225',
 691             },
 692             'skip': 'Video gone',
 693         },
 694         {
 695             'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html',
 696             'info_dict': {
 697                 'id': 'sergio-herman',
 698                 'title': 'sergio herman: fucking perfect',
 699             },
 700             'playlist_count': 2,
 701         },
 702         {
 703             # playlist with youtube embed
 704             'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html',
 705             'info_dict': {
 706                 'id': 'education-education',
 707                 'title': 'education education',
 708             },
 709             'playlist_count': 2,
 710         },
 711         {
 712             'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
 713             'info_dict': {
 714                 'id': 'de-tegenprestatie',
 715                 'title': 'De Tegenprestatie',
 716             },
 717             'playlist_count': 2,
 718         }, {
 719             'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html',
 720             'info_dict': {
 721                 'id': 'VARA_101375237',
 722                 'ext': 'm4v',
 723                 'title': 'MH17: Het verdriet van Nederland',
 724                 'description': 'md5:09e1a37c1fdb144621e22479691a9f18',
 725                 'upload_date': '20150716',
 726             },
 727             'params': {
 728                 # Skip because of m3u8 download
 729                 'skip_download': True
 730             },
 731         }
 732     ]
 733
 734
 735 class WNLIE(NPOPlaylistBaseIE):
 736     IE_NAME = 'wnl'
 737     _VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
 738     _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>'
 739     _PLAYLIST_ENTRY_RE = r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>Deel \d+'
 740
 741     _TESTS = [{
 742         'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
 743         'info_dict': {
 744             'id': 'vandaag-de-dag-6-mei',
 745             'title': 'Vandaag de Dag 6 mei',
 746         },
 747         'playlist_count': 4,
 748     }]
 749
 750
 751 class AndereTijdenIE(NPOPlaylistBaseIE):
 752     IE_NAME = 'anderetijden'
 753     _VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/programma/(?:[^/]+/)+(?P<id>[^/?#&]+)'
 754     _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class=["\'].*?\bpage-title\b.*?["\'][^>]*>(.+?)</h1>'
 755     _PLAYLIST_ENTRY_RE = r'<figure[^>]+class=["\']episode-container episode-page["\'][^>]+data-prid=["\'](.+?)["\']'
 756
 757     _TESTS = [{
 758         'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem',
 759         'info_dict': {
 760             'id': 'Duitse-soldaten-over-de-Slag-bij-Arnhem',
 761             'title': 'Duitse soldaten over de Slag bij Arnhem',
 762         },
 763         'playlist_count': 3,
 764     }]