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         info = {
 251             'id': video_id,
 252             'title': video_id,
 253             'formats': formats,
 254         }
 255
 256         embed_url = url_or_none(player.get('embedUrl'))
 257         if embed_url:
 258             webpage = self._download_webpage(
 259                 embed_url, video_id, 'Downloading embed page', fatal=False)
 260             if webpage:
 261                 video = self._parse_json(
 262                     self._search_regex(
 263                         r'\bvideo\s*=\s*({.+?})\s*;', webpage, 'video',
 264                         default='{}'), video_id)
 265                 if video:
 266                     title = video.get('episodeTitle')
 267                     subtitles = {}
 268                     subtitles_list = video.get('subtitles')
 269                     if isinstance(subtitles_list, list):
 270                         for cc in subtitles_list:
 271                             cc_url = url_or_none(cc.get('src'))
 272                             if not cc_url:
 273                                 continue
 274                             lang = str_or_none(cc.get('language')) or 'nl'
 275                             subtitles.setdefault(lang, []).append({
 276                                 'url': cc_url,
 277                             })
 278                     return merge_dicts({
 279                         'title': title,
 280                         'description': video.get('description'),
 281                         'thumbnail': url_or_none(
 282                             video.get('still_image_url') or video.get('orig_image_url')),
 283                         'duration': int_or_none(video.get('duration')),
 284                         'timestamp': unified_timestamp(video.get('broadcastDate')),
 285                         'creator': video.get('channel'),
 286                         'series': video.get('title'),
 287                         'episode': title,
 288                         'episode_number': int_or_none(video.get('episodeNumber')),
 289                         'subtitles': subtitles,
 290                     }, info)
 291
 292         return info
 293
 294     def _get_old_info(self, video_id):
 295         metadata = self._download_json(
 296             'http://e.omroep.nl/metadata/%s' % video_id,
 297             video_id,
 298             # We have to remove the javascript callback
 299             transform_source=strip_jsonp,
 300         )
 301
 302         error = metadata.get('error')
 303         if error:
 304             raise ExtractorError(error, expected=True)
 305
 306         # For some videos actual video id (prid) is different (e.g. for
 307         # http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698
 308         # video id is POMS_WNL_853698 but prid is POW_00996502)
 309         video_id = metadata.get('prid') or video_id
 310
 311         # titel is too generic in some cases so utilize aflevering_titel as well
 312         # when available (e.g. http://tegenlicht.vpro.nl/afleveringen/2014-2015/access-to-africa.html)
 313         title = metadata['titel']
 314         sub_title = metadata.get('aflevering_titel')
 315         if sub_title and sub_title != title:
 316             title += ': %s' % sub_title
 317
 318         token = self._get_token(video_id)
 319
 320         formats = []
 321         urls = set()
 322
 323         def is_legal_url(format_url):
 324             return format_url and format_url not in urls and re.match(
 325                 r'^(?:https?:)?//', format_url)
 326
 327         QUALITY_LABELS = ('Laag', 'Normaal', 'Hoog')
 328         QUALITY_FORMATS = ('adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std')
 329
 330         quality_from_label = qualities(QUALITY_LABELS)
 331         quality_from_format_id = qualities(QUALITY_FORMATS)
 332         items = self._download_json(
 333             'http://ida.omroep.nl/app.php/%s' % video_id, video_id,
 334             'Downloading formats JSON', query={
 335                 'adaptive': 'yes',
 336                 'token': token,
 337             })['items'][0]
 338         for num, item in enumerate(items):
 339             item_url = item.get('url')
 340             if not is_legal_url(item_url):
 341                 continue
 342             urls.add(item_url)
 343             format_id = self._search_regex(
 344                 r'video/ida/([^/]+)', item_url, 'format id',
 345                 default=None)
 346
 347             item_label = item.get('label')
 348
 349             def add_format_url(format_url):
 350                 width = int_or_none(self._search_regex(
 351                     r'(\d+)[xX]\d+', format_url, 'width', default=None))
 352                 height = int_or_none(self._search_regex(
 353                     r'\d+[xX](\d+)', format_url, 'height', default=None))
 354                 if item_label in QUALITY_LABELS:
 355                     quality = quality_from_label(item_label)
 356                     f_id = item_label
 357                 elif item_label in QUALITY_FORMATS:
 358                     quality = quality_from_format_id(format_id)
 359                     f_id = format_id
 360                 else:
 361                     quality, f_id = [None] * 2
 362                 formats.append({
 363                     'url': format_url,
 364                     'format_id': f_id,
 365                     'width': width,
 366                     'height': height,
 367                     'quality': quality,
 368                 })
 369
 370             # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
 371             if item.get('contentType') in ('url', 'audio'):
 372                 add_format_url(item_url)
 373                 continue
 374
 375             try:
 376                 stream_info = self._download_json(
 377                     item_url + '&type=json', video_id,
 378                     'Downloading %s stream JSON'
 379                     % item_label or item.get('format') or format_id or num)
 380             except ExtractorError as ee:
 381                 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
 382                     error = (self._parse_json(
 383                         ee.cause.read().decode(), video_id,
 384                         fatal=False) or {}).get('errorstring')
 385                     if error:
 386                         raise ExtractorError(error, expected=True)
 387                 raise
 388             # Stream URL instead of JSON, example: npo:LI_NL1_4188102
 389             if isinstance(stream_info, compat_str):
 390                 if not stream_info.startswith('http'):
 391                     continue
 392                 video_url = stream_info
 393             # JSON
 394             else:
 395                 video_url = stream_info.get('url')
 396             if not video_url or 'vodnotavailable.' in video_url or video_url in urls:
 397                 continue
 398             urls.add(video_url)
 399             if determine_ext(video_url) == 'm3u8':
 400                 formats.extend(self._extract_m3u8_formats(
 401                     video_url, video_id, ext='mp4',
 402                     entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
 403             else:
 404                 add_format_url(video_url)
 405
 406         is_live = metadata.get('medium') == 'live'
 407
 408         if not is_live:
 409             for num, stream in enumerate(metadata.get('streams', [])):
 410                 stream_url = stream.get('url')
 411                 if not is_legal_url(stream_url):
 412                     continue
 413                 urls.add(stream_url)
 414                 # smooth streaming is not supported
 415                 stream_type = stream.get('type', '').lower()
 416                 if stream_type in ['ss', 'ms']:
 417                     continue
 418                 if stream_type == 'hds':
 419                     f4m_formats = self._extract_f4m_formats(
 420                         stream_url, video_id, fatal=False)
 421                     # f4m downloader downloads only piece of live stream
 422                     for f4m_format in f4m_formats:
 423                         f4m_format['preference'] = -5
 424                     formats.extend(f4m_formats)
 425                 elif stream_type == 'hls':
 426                     formats.extend(self._extract_m3u8_formats(
 427                         stream_url, video_id, ext='mp4', fatal=False))
 428                 # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
 429                 elif '.asf' in stream_url:
 430                     asx = self._download_xml(
 431                         stream_url, video_id,
 432                         'Downloading stream %d ASX playlist' % num,
 433                         transform_source=fix_xml_ampersands, fatal=False)
 434                     if not asx:
 435                         continue
 436                     ref = asx.find('./ENTRY/Ref')
 437                     if ref is None:
 438                         continue
 439                     video_url = ref.get('href')
 440                     if not video_url or video_url in urls:
 441                         continue
 442                     urls.add(video_url)
 443                     formats.append({
 444                         'url': video_url,
 445                         'ext': stream.get('formaat', 'asf'),
 446                         'quality': stream.get('kwaliteit'),
 447                         'preference': -10,
 448                     })
 449                 else:
 450                     formats.append({
 451                         'url': stream_url,
 452                         'quality': stream.get('kwaliteit'),
 453                     })
 454
 455         subtitles = {}
 456         if metadata.get('tt888') == 'ja':
 457             subtitles['nl'] = [{
 458                 'ext': 'vtt',
 459                 'url': 'http://tt888.omroep.nl/tt888/%s' % video_id,
 460             }]
 461
 462         return {
 463             'id': video_id,
 464             'title': title,
 465             'description': metadata.get('info'),
 466             'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
 467             'upload_date': unified_strdate(metadata.get('gidsdatum')),
 468             'duration': parse_duration(metadata.get('tijdsduur')),
 469             'formats': formats,
 470             'subtitles': subtitles,
 471             'is_live': is_live,
 472         }
 473
 474
 475 class NPOLiveIE(NPOBaseIE):
 476     IE_NAME = 'npo.nl:live'
 477     _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P<id>[^/?#&]+))?'
 478
 479     _TESTS = [{
 480         'url': 'http://www.npo.nl/live/npo-1',
 481         'info_dict': {
 482             'id': 'LI_NL1_4188102',
 483             'display_id': 'npo-1',
 484             'ext': 'mp4',
 485             'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 486             'is_live': True,
 487         },
 488         'params': {
 489             'skip_download': True,
 490         }
 491     }, {
 492         'url': 'http://www.npo.nl/live',
 493         'only_matching': True,
 494     }, {
 495         'url': 'https://www.npostart.nl/live/npo-1',
 496         'only_matching': True,
 497     }]
 498
 499     def _real_extract(self, url):
 500         display_id = self._match_id(url) or 'npo-1'
 501
 502         webpage = self._download_webpage(url, display_id)
 503
 504         live_id = self._search_regex(
 505             [r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id')
 506
 507         return {
 508             '_type': 'url_transparent',
 509             'url': 'npo:%s' % live_id,
 510             'ie_key': NPOIE.ie_key(),
 511             'id': live_id,
 512             'display_id': display_id,
 513         }
 514
 515
 516 class NPORadioIE(InfoExtractor):
 517     IE_NAME = 'npo.nl:radio'
 518     _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)'
 519
 520     _TEST = {
 521         'url': 'http://www.npo.nl/radio/radio-1',
 522         'info_dict': {
 523             'id': 'radio-1',
 524             'ext': 'mp3',
 525             'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 526             'is_live': True,
 527         },
 528         'params': {
 529             'skip_download': True,
 530         }
 531     }
 532
 533     @classmethod
 534     def suitable(cls, url):
 535         return False if NPORadioFragmentIE.suitable(url) else super(NPORadioIE, cls).suitable(url)
 536
 537     @staticmethod
 538     def _html_get_attribute_regex(attribute):
 539         return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)
 540
 541     def _real_extract(self, url):
 542         video_id = self._match_id(url)
 543
 544         webpage = self._download_webpage(url, video_id)
 545
 546         title = self._html_search_regex(
 547             self._html_get_attribute_regex('data-channel'), webpage, 'title')
 548
 549         stream = self._parse_json(
 550             self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
 551             video_id)
 552
 553         codec = stream.get('codec')
 554
 555         return {
 556             'id': video_id,
 557             'url': stream['url'],
 558             'title': title,
 559             'acodec': codec,
 560             'ext': codec,
 561             'is_live': True,
 562         }
 563
 564
 565 class NPORadioFragmentIE(InfoExtractor):
 566     IE_NAME = 'npo.nl:radio:fragment'
 567     _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'
 568
 569     _TEST = {
 570         'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
 571         'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
 572         'info_dict': {
 573             'id': '174356',
 574             'ext': 'mp3',
 575             'title': 'Jubileumconcert Willeke Alberti',
 576         },
 577     }
 578
 579     def _real_extract(self, url):
 580         audio_id = self._match_id(url)
 581
 582         webpage = self._download_webpage(url, audio_id)
 583
 584         title = self._html_search_regex(
 585             r'href="/radio/[^/]+/fragment/%s" title="([^"]+)"' % audio_id,
 586             webpage, 'title')
 587
 588         audio_url = self._search_regex(
 589             r"data-streams='([^']+)'", webpage, 'audio url')
 590
 591         return {
 592             'id': audio_id,
 593             'url': audio_url,
 594             'title': title,
 595         }
 596
 597
 598 class NPODataMidEmbedIE(InfoExtractor):  # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
 599     def _real_extract(self, url):
 600         display_id = self._match_id(url)
 601         webpage = self._download_webpage(url, display_id)
 602         video_id = self._search_regex(
 603             r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
 604         return {
 605             '_type': 'url_transparent',
 606             'ie_key': 'NPO',
 607             'url': 'npo:%s' % video_id,
 608             'display_id': display_id
 609         }
 610
 611
 612 class SchoolTVIE(NPODataMidEmbedIE):
 613     IE_NAME = 'schooltv'
 614     _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'
 615
 616     _TEST = {
 617         'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/',
 618         'info_dict': {
 619             'id': 'WO_NTR_429477',
 620             'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
 621             'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?',
 622             'ext': 'mp4',
 623             'description': 'md5:abfa0ff690adb73fd0297fd033aaa631'
 624         },
 625         'params': {
 626             # Skip because of m3u8 download
 627             'skip_download': True
 628         }
 629     }
 630
 631
 632 class HetKlokhuisIE(NPODataMidEmbedIE):
 633     IE_NAME = 'hetklokhuis'
 634     _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
 635
 636     _TEST = {
 637         'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',
 638         'info_dict': {
 639             'id': 'VPWON_1260528',
 640             'display_id': 'Zwaartekrachtsgolven',
 641             'ext': 'm4v',
 642             'title': 'Het Klokhuis: Zwaartekrachtsgolven',
 643             'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48',
 644             'upload_date': '20170223',
 645         },
 646         'params': {
 647             'skip_download': True
 648         }
 649     }
 650
 651
 652 class NPOPlaylistBaseIE(NPOIE):  # XXX: Do not subclass from concrete IE
 653     def _real_extract(self, url):
 654         playlist_id = self._match_id(url)
 655
 656         webpage = self._download_webpage(url, playlist_id)
 657
 658         entries = [
 659             self.url_result('npo:%s' % video_id if not video_id.startswith('http') else video_id)
 660             for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage))
 661         ]
 662
 663         playlist_title = self._html_search_regex(
 664             self._PLAYLIST_TITLE_RE, webpage, 'playlist title',
 665             default=None) or self._og_search_title(webpage)
 666
 667         return self.playlist_result(entries, playlist_id, playlist_title)
 668
 669
 670 class VPROIE(NPOPlaylistBaseIE):
 671     IE_NAME = 'vpro'
 672     _VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
 673     _PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)',
 674                           r'<h5[^>]+class=["\'].*?\bmedia-platform-subtitle\b.*?["\'][^>]*>([^<]+)')
 675     _PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'
 676
 677     _TESTS = [
 678         {
 679             'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
 680             'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
 681             'info_dict': {
 682                 'id': 'VPWON_1169289',
 683                 'ext': 'm4v',
 684                 'title': 'De toekomst komt uit Afrika',
 685                 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
 686                 'upload_date': '20130225',
 687             },
 688             'skip': 'Video gone',
 689         },
 690         {
 691             'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html',
 692             'info_dict': {
 693                 'id': 'sergio-herman',
 694                 'title': 'sergio herman: fucking perfect',
 695             },
 696             'playlist_count': 2,
 697         },
 698         {
 699             # playlist with youtube embed
 700             'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html',
 701             'info_dict': {
 702                 'id': 'education-education',
 703                 'title': 'education education',
 704             },
 705             'playlist_count': 2,
 706         },
 707         {
 708             'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
 709             'info_dict': {
 710                 'id': 'de-tegenprestatie',
 711                 'title': 'De Tegenprestatie',
 712             },
 713             'playlist_count': 2,
 714         }, {
 715             'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html',
 716             'info_dict': {
 717                 'id': 'VARA_101375237',
 718                 'ext': 'm4v',
 719                 'title': 'MH17: Het verdriet van Nederland',
 720                 'description': 'md5:09e1a37c1fdb144621e22479691a9f18',
 721                 'upload_date': '20150716',
 722             },
 723             'params': {
 724                 # Skip because of m3u8 download
 725                 'skip_download': True
 726             },
 727         }
 728     ]
 729
 730
 731 class WNLIE(NPOPlaylistBaseIE):
 732     IE_NAME = 'wnl'
 733     _VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
 734     _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>'
 735     _PLAYLIST_ENTRY_RE = r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>Deel \d+'
 736
 737     _TESTS = [{
 738         'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
 739         'info_dict': {
 740             'id': 'vandaag-de-dag-6-mei',
 741             'title': 'Vandaag de Dag 6 mei',
 742         },
 743         'playlist_count': 4,
 744     }]
 745
 746
 747 class AndereTijdenIE(NPOPlaylistBaseIE):
 748     IE_NAME = 'anderetijden'
 749     _VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/programma/(?:[^/]+/)+(?P<id>[^/?#&]+)'
 750     _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class=["\'].*?\bpage-title\b.*?["\'][^>]*>(.+?)</h1>'
 751     _PLAYLIST_ENTRY_RE = r'<figure[^>]+class=["\']episode-container episode-page["\'][^>]+data-prid=["\'](.+?)["\']'
 752
 753     _TESTS = [{
 754         'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem',
 755         'info_dict': {
 756             'id': 'Duitse-soldaten-over-de-Slag-bij-Arnhem',
 757             'title': 'Duitse soldaten over de Slag bij Arnhem',
 758         },
 759         'playlist_count': 3,
 760     }]