yt_dlp/extractor/npo.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import (
   7     compat_HTTPError,
   8     compat_str,
   9 )
  10 from ..utils import (
  11     determine_ext,
  12     ExtractorError,
  13     fix_xml_ampersands,
  14     int_or_none,
  15     merge_dicts,
  16     orderedSet,
  17     parse_duration,
  18     qualities,
  19     str_or_none,
  20     strip_jsonp,
  21     unified_strdate,
  22     unified_timestamp,
  23     url_or_none,
  24     urlencode_postdata,
  25 )
  26
  27
  28 class NPOBaseIE(InfoExtractor):
  29     def _get_token(self, video_id):
  30         return self._download_json(
  31             'http://ida.omroep.nl/app.php/auth', video_id,
  32             note='Downloading token')['token']
  33
  34
  35 class NPOIE(NPOBaseIE):
  36     IE_NAME = 'npo'
  37     IE_DESC = 'npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl'
  38     _VALID_URL = r'''(?x)
  39                     (?:
  40                         npo:|
  41                         https?://
  42                             (?:www\.)?
  43                             (?:
  44                                 npo\.nl/(?:[^/]+/)*|
  45                                 (?:ntr|npostart)\.nl/(?:[^/]+/){2,}|
  46                                 omroepwnl\.nl/video/fragment/[^/]+__|
  47                                 (?:zapp|npo3)\.nl/(?:[^/]+/){2,}
  48                             )
  49                         )
  50                         (?P<id>[^/?#]+)
  51                 '''
  52
  53     _TESTS = [{
  54         'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
  55         'md5': '4b3f9c429157ec4775f2c9cb7b911016',
  56         'info_dict': {
  57             'id': 'VPWON_1220719',
  58             'ext': 'm4v',
  59             'title': 'Nieuwsuur',
  60             'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
  61             'upload_date': '20140622',
  62         },
  63     }, {
  64         'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
  65         'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
  66         'info_dict': {
  67             'id': 'VARA_101191800',
  68             'ext': 'm4v',
  69             'title': 'De Mega Mike & Mega Thomas show: The best of.',
  70             'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
  71             'upload_date': '20090227',
  72             'duration': 2400,
  73         },
  74     }, {
  75         'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
  76         'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
  77         'info_dict': {
  78             'id': 'VPWON_1169289',
  79             'ext': 'm4v',
  80             'title': 'Tegenlicht: Zwart geld. De toekomst komt uit Afrika',
  81             'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
  82             'upload_date': '20130225',
  83             'duration': 3000,
  84         },
  85     }, {
  86         'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
  87         'info_dict': {
  88             'id': 'WO_VPRO_043706',
  89             'ext': 'm4v',
  90             'title': 'De nieuwe mens - Deel 1',
  91             'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
  92             'duration': 4680,
  93         },
  94         'params': {
  95             'skip_download': True,
  96         }
  97     }, {
  98         # non asf in streams
  99         'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
 100         'info_dict': {
 101             'id': 'WO_NOS_762771',
 102             'ext': 'mp4',
 103             'title': 'Hoe gaat Europa verder na Parijs?',
 104         },
 105         'params': {
 106             'skip_download': True,
 107         }
 108     }, {
 109         'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
 110         'info_dict': {
 111             'id': 'VPWON_1233944',
 112             'ext': 'm4v',
 113             'title': 'Aap, poot, pies',
 114             'description': 'md5:c9c8005d1869ae65b858e82c01a91fde',
 115             'upload_date': '20150508',
 116             'duration': 599,
 117         },
 118         'params': {
 119             'skip_download': True,
 120         }
 121     }, {
 122         'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
 123         'info_dict': {
 124             'id': 'POW_00996502',
 125             'ext': 'm4v',
 126             'title': '''"Dit is wel een 'landslide'..."''',
 127             'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
 128             'upload_date': '20150508',
 129             'duration': 462,
 130         },
 131         'params': {
 132             'skip_download': True,
 133         }
 134     }, {
 135         # audio
 136         'url': 'http://www.npo.nl/jouw-stad-rotterdam/29-01-2017/RBX_FUNX_6683215/RBX_FUNX_7601437',
 137         'info_dict': {
 138             'id': 'RBX_FUNX_6683215',
 139             'ext': 'mp3',
 140             'title': 'Jouw Stad Rotterdam',
 141             'description': 'md5:db251505244f097717ec59fabc372d9f',
 142         },
 143         'params': {
 144             'skip_download': True,
 145         }
 146     }, {
 147         'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547',
 148         'only_matching': True,
 149     }, {
 150         'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118',
 151         'only_matching': True,
 152     }, {
 153         'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
 154         'only_matching': True,
 155     }, {
 156         'url': 'https://www.npo3.nl/3onderzoekt/16-09-2015/VPWON_1239870',
 157         'only_matching': True,
 158     }, {
 159         # live stream
 160         'url': 'npo:LI_NL1_4188102',
 161         'only_matching': True,
 162     }, {
 163         'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373',
 164         'only_matching': True,
 165     }, {
 166         'url': 'https://www.zapp.nl/1803-skelterlab/instructie-video-s/740-instructievideo-s/POMS_AT_11736927',
 167         'only_matching': True,
 168     }, {
 169         'url': 'https://www.npostart.nl/broodje-gezond-ei/28-05-2018/KN_1698996',
 170         'only_matching': True,
 171     }, {
 172         'url': 'https://npo.nl/KN_1698996',
 173         'only_matching': True,
 174     }]
 175
 176     @classmethod
 177     def suitable(cls, url):
 178         return (False if any(ie.suitable(url)
 179                 for ie in (NPOLiveIE, NPORadioIE, NPORadioFragmentIE))
 180                 else super(NPOIE, cls).suitable(url))
 181
 182     def _real_extract(self, url):
 183         video_id = self._match_id(url)
 184         return self._get_info(url, video_id) or self._get_old_info(video_id)
 185
 186     def _get_info(self, url, video_id):
 187         token = self._download_json(
 188             'https://www.npostart.nl/api/token', video_id,
 189             'Downloading token', headers={
 190                 'Referer': url,
 191                 'X-Requested-With': 'XMLHttpRequest',
 192             })['token']
 193
 194         player = self._download_json(
 195             'https://www.npostart.nl/player/%s' % video_id, video_id,
 196             'Downloading player JSON', data=urlencode_postdata({
 197                 'autoplay': 0,
 198                 'share': 1,
 199                 'pageUrl': url,
 200                 'hasAdConsent': 0,
 201                 '_token': token,
 202             }))
 203
 204         player_token = player['token']
 205
 206         drm = False
 207         format_urls = set()
 208         formats = []
 209         for profile in ('hls', 'dash-widevine', 'dash-playready', 'smooth'):
 210             streams = self._download_json(
 211                 'https://start-player.npo.nl/video/%s/streams' % video_id,
 212                 video_id, 'Downloading %s profile JSON' % profile, fatal=False,
 213                 query={
 214                     'profile': profile,
 215                     'quality': 'npo',
 216                     'tokenId': player_token,
 217                     'streamType': 'broadcast',
 218                 })
 219             if not streams:
 220                 continue
 221             stream = streams.get('stream')
 222             if not isinstance(stream, dict):
 223                 continue
 224             stream_url = url_or_none(stream.get('src'))
 225             if not stream_url or stream_url in format_urls:
 226                 continue
 227             format_urls.add(stream_url)
 228             if stream.get('protection') is not None or stream.get('keySystemOptions') is not None:
 229                 drm = True
 230                 continue
 231             stream_type = stream.get('type')
 232             stream_ext = determine_ext(stream_url)
 233             if stream_type == 'application/dash+xml' or stream_ext == 'mpd':
 234                 formats.extend(self._extract_mpd_formats(
 235                     stream_url, video_id, mpd_id='dash', fatal=False))
 236             elif stream_type == 'application/vnd.apple.mpegurl' or stream_ext == 'm3u8':
 237                 formats.extend(self._extract_m3u8_formats(
 238                     stream_url, video_id, ext='mp4',
 239                     entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
 240             elif re.search(r'\.isml?/Manifest', stream_url):
 241                 formats.extend(self._extract_ism_formats(
 242                     stream_url, video_id, ism_id='mss', fatal=False))
 243             else:
 244                 formats.append({
 245                     'url': stream_url,
 246                 })
 247
 248         if not formats:
 249             if not self.get_param('allow_unplayable_formats') and drm:
 250                 self.report_drm(video_id)
 251
 252         self._sort_formats(formats)
 253
 254         info = {
 255             'id': video_id,
 256             'title': video_id,
 257             'formats': formats,
 258         }
 259
 260         embed_url = url_or_none(player.get('embedUrl'))
 261         if embed_url:
 262             webpage = self._download_webpage(
 263                 embed_url, video_id, 'Downloading embed page', fatal=False)
 264             if webpage:
 265                 video = self._parse_json(
 266                     self._search_regex(
 267                         r'\bvideo\s*=\s*({.+?})\s*;', webpage, 'video',
 268                         default='{}'), video_id)
 269                 if video:
 270                     title = video.get('episodeTitle')
 271                     subtitles = {}
 272                     subtitles_list = video.get('subtitles')
 273                     if isinstance(subtitles_list, list):
 274                         for cc in subtitles_list:
 275                             cc_url = url_or_none(cc.get('src'))
 276                             if not cc_url:
 277                                 continue
 278                             lang = str_or_none(cc.get('language')) or 'nl'
 279                             subtitles.setdefault(lang, []).append({
 280                                 'url': cc_url,
 281                             })
 282                     return merge_dicts({
 283                         'title': title,
 284                         'description': video.get('description'),
 285                         'thumbnail': url_or_none(
 286                             video.get('still_image_url') or video.get('orig_image_url')),
 287                         'duration': int_or_none(video.get('duration')),
 288                         'timestamp': unified_timestamp(video.get('broadcastDate')),
 289                         'creator': video.get('channel'),
 290                         'series': video.get('title'),
 291                         'episode': title,
 292                         'episode_number': int_or_none(video.get('episodeNumber')),
 293                         'subtitles': subtitles,
 294                     }, info)
 295
 296         return info
 297
 298     def _get_old_info(self, video_id):
 299         metadata = self._download_json(
 300             'http://e.omroep.nl/metadata/%s' % video_id,
 301             video_id,
 302             # We have to remove the javascript callback
 303             transform_source=strip_jsonp,
 304         )
 305
 306         error = metadata.get('error')
 307         if error:
 308             raise ExtractorError(error, expected=True)
 309
 310         # For some videos actual video id (prid) is different (e.g. for
 311         # http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698
 312         # video id is POMS_WNL_853698 but prid is POW_00996502)
 313         video_id = metadata.get('prid') or video_id
 314
 315         # titel is too generic in some cases so utilize aflevering_titel as well
 316         # when available (e.g. http://tegenlicht.vpro.nl/afleveringen/2014-2015/access-to-africa.html)
 317         title = metadata['titel']
 318         sub_title = metadata.get('aflevering_titel')
 319         if sub_title and sub_title != title:
 320             title += ': %s' % sub_title
 321
 322         token = self._get_token(video_id)
 323
 324         formats = []
 325         urls = set()
 326
 327         def is_legal_url(format_url):
 328             return format_url and format_url not in urls and re.match(
 329                 r'^(?:https?:)?//', format_url)
 330
 331         QUALITY_LABELS = ('Laag', 'Normaal', 'Hoog')
 332         QUALITY_FORMATS = ('adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std')
 333
 334         quality_from_label = qualities(QUALITY_LABELS)
 335         quality_from_format_id = qualities(QUALITY_FORMATS)
 336         items = self._download_json(
 337             'http://ida.omroep.nl/app.php/%s' % video_id, video_id,
 338             'Downloading formats JSON', query={
 339                 'adaptive': 'yes',
 340                 'token': token,
 341             })['items'][0]
 342         for num, item in enumerate(items):
 343             item_url = item.get('url')
 344             if not is_legal_url(item_url):
 345                 continue
 346             urls.add(item_url)
 347             format_id = self._search_regex(
 348                 r'video/ida/([^/]+)', item_url, 'format id',
 349                 default=None)
 350
 351             item_label = item.get('label')
 352
 353             def add_format_url(format_url):
 354                 width = int_or_none(self._search_regex(
 355                     r'(\d+)[xX]\d+', format_url, 'width', default=None))
 356                 height = int_or_none(self._search_regex(
 357                     r'\d+[xX](\d+)', format_url, 'height', default=None))
 358                 if item_label in QUALITY_LABELS:
 359                     quality = quality_from_label(item_label)
 360                     f_id = item_label
 361                 elif item_label in QUALITY_FORMATS:
 362                     quality = quality_from_format_id(format_id)
 363                     f_id = format_id
 364                 else:
 365                     quality, f_id = [None] * 2
 366                 formats.append({
 367                     'url': format_url,
 368                     'format_id': f_id,
 369                     'width': width,
 370                     'height': height,
 371                     'quality': quality,
 372                 })
 373
 374             # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
 375             if item.get('contentType') in ('url', 'audio'):
 376                 add_format_url(item_url)
 377                 continue
 378
 379             try:
 380                 stream_info = self._download_json(
 381                     item_url + '&type=json', video_id,
 382                     'Downloading %s stream JSON'
 383                     % item_label or item.get('format') or format_id or num)
 384             except ExtractorError as ee:
 385                 if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
 386                     error = (self._parse_json(
 387                         ee.cause.read().decode(), video_id,
 388                         fatal=False) or {}).get('errorstring')
 389                     if error:
 390                         raise ExtractorError(error, expected=True)
 391                 raise
 392             # Stream URL instead of JSON, example: npo:LI_NL1_4188102
 393             if isinstance(stream_info, compat_str):
 394                 if not stream_info.startswith('http'):
 395                     continue
 396                 video_url = stream_info
 397             # JSON
 398             else:
 399                 video_url = stream_info.get('url')
 400             if not video_url or 'vodnotavailable.' in video_url or video_url in urls:
 401                 continue
 402             urls.add(video_url)
 403             if determine_ext(video_url) == 'm3u8':
 404                 formats.extend(self._extract_m3u8_formats(
 405                     video_url, video_id, ext='mp4',
 406                     entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
 407             else:
 408                 add_format_url(video_url)
 409
 410         is_live = metadata.get('medium') == 'live'
 411
 412         if not is_live:
 413             for num, stream in enumerate(metadata.get('streams', [])):
 414                 stream_url = stream.get('url')
 415                 if not is_legal_url(stream_url):
 416                     continue
 417                 urls.add(stream_url)
 418                 # smooth streaming is not supported
 419                 stream_type = stream.get('type', '').lower()
 420                 if stream_type in ['ss', 'ms']:
 421                     continue
 422                 if stream_type == 'hds':
 423                     f4m_formats = self._extract_f4m_formats(
 424                         stream_url, video_id, fatal=False)
 425                     # f4m downloader downloads only piece of live stream
 426                     for f4m_format in f4m_formats:
 427                         f4m_format['preference'] = -5
 428                     formats.extend(f4m_formats)
 429                 elif stream_type == 'hls':
 430                     formats.extend(self._extract_m3u8_formats(
 431                         stream_url, video_id, ext='mp4', fatal=False))
 432                 # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
 433                 elif '.asf' in stream_url:
 434                     asx = self._download_xml(
 435                         stream_url, video_id,
 436                         'Downloading stream %d ASX playlist' % num,
 437                         transform_source=fix_xml_ampersands, fatal=False)
 438                     if not asx:
 439                         continue
 440                     ref = asx.find('./ENTRY/Ref')
 441                     if ref is None:
 442                         continue
 443                     video_url = ref.get('href')
 444                     if not video_url or video_url in urls:
 445                         continue
 446                     urls.add(video_url)
 447                     formats.append({
 448                         'url': video_url,
 449                         'ext': stream.get('formaat', 'asf'),
 450                         'quality': stream.get('kwaliteit'),
 451                         'preference': -10,
 452                     })
 453                 else:
 454                     formats.append({
 455                         'url': stream_url,
 456                         'quality': stream.get('kwaliteit'),
 457                     })
 458
 459         self._sort_formats(formats)
 460
 461         subtitles = {}
 462         if metadata.get('tt888') == 'ja':
 463             subtitles['nl'] = [{
 464                 'ext': 'vtt',
 465                 'url': 'http://tt888.omroep.nl/tt888/%s' % video_id,
 466             }]
 467
 468         return {
 469             'id': video_id,
 470             'title': self._live_title(title) if is_live else title,
 471             'description': metadata.get('info'),
 472             'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
 473             'upload_date': unified_strdate(metadata.get('gidsdatum')),
 474             'duration': parse_duration(metadata.get('tijdsduur')),
 475             'formats': formats,
 476             'subtitles': subtitles,
 477             'is_live': is_live,
 478         }
 479
 480
 481 class NPOLiveIE(NPOBaseIE):
 482     IE_NAME = 'npo.nl:live'
 483     _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P<id>[^/?#&]+))?'
 484
 485     _TESTS = [{
 486         'url': 'http://www.npo.nl/live/npo-1',
 487         'info_dict': {
 488             'id': 'LI_NL1_4188102',
 489             'display_id': 'npo-1',
 490             'ext': 'mp4',
 491             'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 492             'is_live': True,
 493         },
 494         'params': {
 495             'skip_download': True,
 496         }
 497     }, {
 498         'url': 'http://www.npo.nl/live',
 499         'only_matching': True,
 500     }, {
 501         'url': 'https://www.npostart.nl/live/npo-1',
 502         'only_matching': True,
 503     }]
 504
 505     def _real_extract(self, url):
 506         display_id = self._match_id(url) or 'npo-1'
 507
 508         webpage = self._download_webpage(url, display_id)
 509
 510         live_id = self._search_regex(
 511             [r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id')
 512
 513         return {
 514             '_type': 'url_transparent',
 515             'url': 'npo:%s' % live_id,
 516             'ie_key': NPOIE.ie_key(),
 517             'id': live_id,
 518             'display_id': display_id,
 519         }
 520
 521
 522 class NPORadioIE(InfoExtractor):
 523     IE_NAME = 'npo.nl:radio'
 524     _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)'
 525
 526     _TEST = {
 527         'url': 'http://www.npo.nl/radio/radio-1',
 528         'info_dict': {
 529             'id': 'radio-1',
 530             'ext': 'mp3',
 531             'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
 532             'is_live': True,
 533         },
 534         'params': {
 535             'skip_download': True,
 536         }
 537     }
 538
 539     @classmethod
 540     def suitable(cls, url):
 541         return False if NPORadioFragmentIE.suitable(url) else super(NPORadioIE, cls).suitable(url)
 542
 543     @staticmethod
 544     def _html_get_attribute_regex(attribute):
 545         return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)
 546
 547     def _real_extract(self, url):
 548         video_id = self._match_id(url)
 549
 550         webpage = self._download_webpage(url, video_id)
 551
 552         title = self._html_search_regex(
 553             self._html_get_attribute_regex('data-channel'), webpage, 'title')
 554
 555         stream = self._parse_json(
 556             self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
 557             video_id)
 558
 559         codec = stream.get('codec')
 560
 561         return {
 562             'id': video_id,
 563             'url': stream['url'],
 564             'title': self._live_title(title),
 565             'acodec': codec,
 566             'ext': codec,
 567             'is_live': True,
 568         }
 569
 570
 571 class NPORadioFragmentIE(InfoExtractor):
 572     IE_NAME = 'npo.nl:radio:fragment'
 573     _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'
 574
 575     _TEST = {
 576         'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
 577         'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
 578         'info_dict': {
 579             'id': '174356',
 580             'ext': 'mp3',
 581             'title': 'Jubileumconcert Willeke Alberti',
 582         },
 583     }
 584
 585     def _real_extract(self, url):
 586         audio_id = self._match_id(url)
 587
 588         webpage = self._download_webpage(url, audio_id)
 589
 590         title = self._html_search_regex(
 591             r'href="/radio/[^/]+/fragment/%s" title="([^"]+)"' % audio_id,
 592             webpage, 'title')
 593
 594         audio_url = self._search_regex(
 595             r"data-streams='([^']+)'", webpage, 'audio url')
 596
 597         return {
 598             'id': audio_id,
 599             'url': audio_url,
 600             'title': title,
 601         }
 602
 603
 604 class NPODataMidEmbedIE(InfoExtractor):
 605     def _real_extract(self, url):
 606         display_id = self._match_id(url)
 607         webpage = self._download_webpage(url, display_id)
 608         video_id = self._search_regex(
 609             r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
 610         return {
 611             '_type': 'url_transparent',
 612             'ie_key': 'NPO',
 613             'url': 'npo:%s' % video_id,
 614             'display_id': display_id
 615         }
 616
 617
 618 class SchoolTVIE(NPODataMidEmbedIE):
 619     IE_NAME = 'schooltv'
 620     _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'
 621
 622     _TEST = {
 623         'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/',
 624         'info_dict': {
 625             'id': 'WO_NTR_429477',
 626             'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
 627             'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?',
 628             'ext': 'mp4',
 629             'description': 'md5:abfa0ff690adb73fd0297fd033aaa631'
 630         },
 631         'params': {
 632             # Skip because of m3u8 download
 633             'skip_download': True
 634         }
 635     }
 636
 637
 638 class HetKlokhuisIE(NPODataMidEmbedIE):
 639     IE_NAME = 'hetklokhuis'
 640     _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
 641
 642     _TEST = {
 643         'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',
 644         'info_dict': {
 645             'id': 'VPWON_1260528',
 646             'display_id': 'Zwaartekrachtsgolven',
 647             'ext': 'm4v',
 648             'title': 'Het Klokhuis: Zwaartekrachtsgolven',
 649             'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48',
 650             'upload_date': '20170223',
 651         },
 652         'params': {
 653             'skip_download': True
 654         }
 655     }
 656
 657
 658 class NPOPlaylistBaseIE(NPOIE):
 659     def _real_extract(self, url):
 660         playlist_id = self._match_id(url)
 661
 662         webpage = self._download_webpage(url, playlist_id)
 663
 664         entries = [
 665             self.url_result('npo:%s' % video_id if not video_id.startswith('http') else video_id)
 666             for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage))
 667         ]
 668
 669         playlist_title = self._html_search_regex(
 670             self._PLAYLIST_TITLE_RE, webpage, 'playlist title',
 671             default=None) or self._og_search_title(webpage)
 672
 673         return self.playlist_result(entries, playlist_id, playlist_title)
 674
 675
 676 class VPROIE(NPOPlaylistBaseIE):
 677     IE_NAME = 'vpro'
 678     _VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
 679     _PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)',
 680                           r'<h5[^>]+class=["\'].*?\bmedia-platform-subtitle\b.*?["\'][^>]*>([^<]+)')
 681     _PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'
 682
 683     _TESTS = [
 684         {
 685             'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
 686             'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
 687             'info_dict': {
 688                 'id': 'VPWON_1169289',
 689                 'ext': 'm4v',
 690                 'title': 'De toekomst komt uit Afrika',
 691                 'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
 692                 'upload_date': '20130225',
 693             },
 694             'skip': 'Video gone',
 695         },
 696         {
 697             'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html',
 698             'info_dict': {
 699                 'id': 'sergio-herman',
 700                 'title': 'sergio herman: fucking perfect',
 701             },
 702             'playlist_count': 2,
 703         },
 704         {
 705             # playlist with youtube embed
 706             'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html',
 707             'info_dict': {
 708                 'id': 'education-education',
 709                 'title': 'education education',
 710             },
 711             'playlist_count': 2,
 712         },
 713         {
 714             'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
 715             'info_dict': {
 716                 'id': 'de-tegenprestatie',
 717                 'title': 'De Tegenprestatie',
 718             },
 719             'playlist_count': 2,
 720         }, {
 721             'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html',
 722             'info_dict': {
 723                 'id': 'VARA_101375237',
 724                 'ext': 'm4v',
 725                 'title': 'MH17: Het verdriet van Nederland',
 726                 'description': 'md5:09e1a37c1fdb144621e22479691a9f18',
 727                 'upload_date': '20150716',
 728             },
 729             'params': {
 730                 # Skip because of m3u8 download
 731                 'skip_download': True
 732             },
 733         }
 734     ]
 735
 736
 737 class WNLIE(NPOPlaylistBaseIE):
 738     IE_NAME = 'wnl'
 739     _VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
 740     _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>'
 741     _PLAYLIST_ENTRY_RE = r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>Deel \d+'
 742
 743     _TESTS = [{
 744         'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
 745         'info_dict': {
 746             'id': 'vandaag-de-dag-6-mei',
 747             'title': 'Vandaag de Dag 6 mei',
 748         },
 749         'playlist_count': 4,
 750     }]
 751
 752
 753 class AndereTijdenIE(NPOPlaylistBaseIE):
 754     IE_NAME = 'anderetijden'
 755     _VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/programma/(?:[^/]+/)+(?P<id>[^/?#&]+)'
 756     _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class=["\'].*?\bpage-title\b.*?["\'][^>]*>(.+?)</h1>'
 757     _PLAYLIST_ENTRY_RE = r'<figure[^>]+class=["\']episode-container episode-page["\'][^>]+data-prid=["\'](.+?)["\']'
 758
 759     _TESTS = [{
 760         'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem',
 761         'info_dict': {
 762             'id': 'Duitse-soldaten-over-de-Slag-bij-Arnhem',
 763             'title': 'Duitse soldaten over de Slag bij Arnhem',
 764         },
 765         'playlist_count': 3,
 766     }]