[yt-dlp.git] / yt_dlp / extractor / npo.py

import random
import re
import urllib.parse

from .common import InfoExtractor
from ..utils import (
    determine_ext,
    int_or_none,
    merge_dicts,
    orderedSet,
    str_or_none,
    try_call,
    unified_timestamp,
    url_or_none,
    urlencode_postdata,
)


class NPOIE(InfoExtractor):
    IE_NAME = 'npo'
    IE_DESC = 'npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl'
    _VALID_URL = r'''(?x)
                    (?:
                        npo:|
                        https?://
                            (?:www\.)?
                            (?:
                                npo\.nl/(?:[^/]+/)*|
                                (?:ntr|npostart)\.nl/(?:[^/]+/){2,}|
                                omroepwnl\.nl/video/fragment/[^/]+__|
                                (?:zapp|npo3)\.nl/(?:[^/]+/){2,}
                            )
                        )
                        (?P<id>[^/?#]+)
                '''

    _TESTS = [{
        'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
        'md5': '4b3f9c429157ec4775f2c9cb7b911016',
        'info_dict': {
            'id': 'VPWON_1220719',
            'ext': 'm4v',
            'title': 'Nieuwsuur',
            'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
            'upload_date': '20140622',
        },
        'skip': 'Video was removed',
    }, {
        'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
        'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
        'info_dict': {
            'id': 'VARA_101191800',
            'ext': 'm4v',
            'title': 'De Mega Mike & Mega Thomas show: The best of.',
            'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
            'upload_date': '20090227',
            'duration': 2400,
        },
        'skip': 'Video was removed',
    }, {
        'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
        'md5': '1b279c0547f6b270e014c576415268c5',
        'info_dict': {
            'id': 'VPWON_1169289',
            'ext': 'mp4',
            'title': 'Zwart geld: de toekomst komt uit Afrika',
            'description': 'md5:dffaf3d628a9c36f78ca48d834246261',
            'upload_date': '20130225',
            'duration': 3000,
            'creator': 'NED2',
            'series': 'Tegenlicht',
            'timestamp': 1361822340,
            'thumbnail': 'https://images.npo.nl/tile/1280x720/142854.jpg',
            'episode': 'Zwart geld: de toekomst komt uit Afrika',
            'episode_number': 18,
        },
    }, {
        'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
        'info_dict': {
            'id': 'WO_VPRO_043706',
            'ext': 'mp4',
            'title': 'De nieuwe mens - Deel 1',
            'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
            'duration': 4680,
            'episode': 'De nieuwe mens - Deel 1',
            'thumbnail': 'https://images.npo.nl/tile/1280x720/6289.jpg',
            'timestamp': 1279716057,
            'series': 'De nieuwe mens - Deel 1',
            'upload_date': '20100721',
        },
        'params': {
            'skip_download': True,
        },
    }, {
        # non asf in streams
        'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
        'info_dict': {
            'id': 'WO_NOS_762771',
            'ext': 'mp4',
            'title': 'Hoe gaat Europa verder na Parijs?',
        },
        'params': {
            'skip_download': True,
        },
        'skip': 'Video was removed',
    }, {
        'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
        'info_dict': {
            'id': 'VPWON_1233944',
            'ext': 'mp4',
            'title': 'Aap, poot, pies',
            'description': 'md5:4b46b1b9553b4c036a04d2a532a137e6',
            'upload_date': '20150508',
            'duration': 599,
            'episode': 'Aap, poot, pies',
            'thumbnail': 'https://images.poms.omroep.nl/image/s1280/c1280x720/608118.jpg',
            'timestamp': 1431064200,
            'series': 'Aap, poot, pies',
        },
        'params': {
            'skip_download': True,
        },
    }, {
        'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
        'info_dict': {
            'id': 'POW_00996502',
            'ext': 'm4v',
            'title': '''"Dit is wel een 'landslide'..."''',
            'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
            'upload_date': '20150508',
            'duration': 462,
        },
        'params': {
            'skip_download': True,
        },
        'skip': 'Video was removed',
    }, {
        # audio
        'url': 'http://www.npo.nl/jouw-stad-rotterdam/29-01-2017/RBX_FUNX_6683215/RBX_FUNX_7601437',
        'info_dict': {
            'id': 'RBX_FUNX_6683215',
            'ext': 'mp3',
            'title': 'Jouw Stad Rotterdam',
            'description': 'md5:db251505244f097717ec59fabc372d9f',
        },
        'params': {
            'skip_download': True,
        },
        'skip': 'Video was removed',
    }, {
        'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547',
        'only_matching': True,
    }, {
        'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118',
        'only_matching': True,
    }, {
        'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
        'only_matching': True,
    }, {
        'url': 'https://www.npo3.nl/3onderzoekt/16-09-2015/VPWON_1239870',
        'only_matching': True,
    }, {
        # live stream
        'url': 'npo:LI_NL1_4188102',
        'only_matching': True,
    }, {
        'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373',
        'only_matching': True,
    }, {
        'url': 'https://www.zapp.nl/1803-skelterlab/instructie-video-s/740-instructievideo-s/POMS_AT_11736927',
        'only_matching': True,
    }, {
        'url': 'https://www.npostart.nl/broodje-gezond-ei/28-05-2018/KN_1698996',
        'only_matching': True,
    }, {
        'url': 'https://npo.nl/KN_1698996',
        'only_matching': True,
    }, {
        'url': 'https://www.npo3.nl/the-genius/21-11-2022/VPWON_1341105',
        'info_dict': {
            'id': 'VPWON_1341105',
            'ext': 'mp4',
            'duration': 2658,
            'series': 'The Genius',
            'description': 'md5:db02f1456939ca63f7c408f858044e94',
            'title': 'The Genius',
            'timestamp': 1669062000,
            'creator': 'NED3',
            'episode': 'The Genius',
            'thumbnail': 'https://images.npo.nl/tile/1280x720/1827650.jpg',
            'episode_number': 8,
            'upload_date': '20221121',
        },
        'params': {
            'skip_download': True,
        },
    }]

    @classmethod
    def suitable(cls, url):
        return (False if any(ie.suitable(url)
                for ie in (NPOLiveIE, NPORadioIE, NPORadioFragmentIE))
                else super().suitable(url))

    def _real_extract(self, url):
        video_id = self._match_id(url)
        if urllib.parse.urlparse(url).netloc in ['www.ntr.nl', 'ntr.nl']:
            player = self._download_json(
                f'https://www.ntr.nl/ajax/player/embed/{video_id}', video_id,
                'Downloading player JSON', query={
                    'parameters[elementId]': f'npo{random.randint(0, 999)}',
                    'parameters[sterReferralUrl]': url,
                    'parameters[autoplay]': 0,
                })
        else:
            self._request_webpage(
                'https://www.npostart.nl/api/token', video_id,
                'Downloading token', headers={
                    'Referer': url,
                    'X-Requested-With': 'XMLHttpRequest',
                })
            player = self._download_json(
                f'https://www.npostart.nl/player/{video_id}', video_id,
                'Downloading player JSON', data=urlencode_postdata({
                    'autoplay': 0,
                    'share': 1,
                    'pageUrl': url,
                    'hasAdConsent': 0,
                }), headers={
                    'x-xsrf-token': try_call(lambda: urllib.parse.unquote(
                        self._get_cookies('https://www.npostart.nl')['XSRF-TOKEN'].value)),
                })

        player_token = player['token']

        drm = False
        format_urls = set()
        formats = []
        for profile in ('hls', 'dash-widevine', 'dash-playready', 'smooth'):
            streams = self._download_json(
                f'https://start-player.npo.nl/video/{video_id}/streams',
                video_id, f'Downloading {profile} profile JSON', fatal=False,
                query={
                    'profile': profile,
                    'quality': 'npoplus',
                    'tokenId': player_token,
                    'streamType': 'broadcast',
                }, data=b'')  # endpoint requires POST
            if not streams:
                continue
            stream = streams.get('stream')
            if not isinstance(stream, dict):
                continue
            stream_url = url_or_none(stream.get('src'))
            if not stream_url or stream_url in format_urls:
                continue
            format_urls.add(stream_url)
            if stream.get('protection') is not None or stream.get('keySystemOptions') is not None:
                drm = True
                continue
            stream_type = stream.get('type')
            stream_ext = determine_ext(stream_url)
            if stream_type == 'application/dash+xml' or stream_ext == 'mpd':
                formats.extend(self._extract_mpd_formats(
                    stream_url, video_id, mpd_id='dash', fatal=False))
            elif stream_type == 'application/vnd.apple.mpegurl' or stream_ext == 'm3u8':
                formats.extend(self._extract_m3u8_formats(
                    stream_url, video_id, ext='mp4',
                    entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
            elif re.search(r'\.isml?/Manifest', stream_url):
                formats.extend(self._extract_ism_formats(
                    stream_url, video_id, ism_id='mss', fatal=False))
            else:
                formats.append({
                    'url': stream_url,
                })

        if not formats:
            if not self.get_param('allow_unplayable_formats') and drm:
                self.report_drm(video_id)

        info = {
            'id': video_id,
            'title': video_id,
            'formats': formats,
        }

        embed_url = url_or_none(player.get('embedUrl'))
        if embed_url:
            webpage = self._download_webpage(
                embed_url, video_id, 'Downloading embed page', fatal=False)
            if webpage:
                video = self._parse_json(
                    self._search_regex(
                        r'\bvideo\s*=\s*({.+?})\s*;', webpage, 'video',
                        default='{}'), video_id)
                if video:
                    title = video.get('episodeTitle')
                    subtitles = {}
                    subtitles_list = video.get('subtitles')
                    if isinstance(subtitles_list, list):
                        for cc in subtitles_list:
                            cc_url = url_or_none(cc.get('src'))
                            if not cc_url:
                                continue
                            lang = str_or_none(cc.get('language')) or 'nl'
                            subtitles.setdefault(lang, []).append({
                                'url': cc_url,
                            })
                    return merge_dicts({
                        'title': title,
                        'description': video.get('description'),
                        'thumbnail': url_or_none(
                            video.get('still_image_url') or video.get('orig_image_url')),
                        'duration': int_or_none(video.get('duration')),
                        'timestamp': unified_timestamp(video.get('broadcastDate')),
                        'creator': video.get('channel'),
                        'series': video.get('title'),
                        'episode': title,
                        'episode_number': int_or_none(video.get('episodeNumber')),
                        'subtitles': subtitles,
                    }, info)

        return info


class NPOLiveIE(InfoExtractor):
    IE_NAME = 'npo.nl:live'
    _VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P<id>[^/?#&]+))?'

    _TESTS = [{
        'url': 'http://www.npo.nl/live/npo-1',
        'info_dict': {
            'id': 'LI_NL1_4188102',
            'display_id': 'npo-1',
            'ext': 'mp4',
            'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
            'is_live': True,
        },
        'params': {
            'skip_download': True,
        },
    }, {
        'url': 'http://www.npo.nl/live',
        'only_matching': True,
    }, {
        'url': 'https://www.npostart.nl/live/npo-1',
        'only_matching': True,
    }]

    def _real_extract(self, url):
        display_id = self._match_id(url) or 'npo-1'

        webpage = self._download_webpage(url, display_id)

        live_id = self._search_regex(
            [r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id')

        return {
            '_type': 'url_transparent',
            'url': f'npo:{live_id}',
            'ie_key': NPOIE.ie_key(),
            'id': live_id,
            'display_id': display_id,
        }


class NPORadioIE(InfoExtractor):
    IE_NAME = 'npo.nl:radio'
    _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)'

    _TEST = {
        'url': 'http://www.npo.nl/radio/radio-1',
        'info_dict': {
            'id': 'radio-1',
            'ext': 'mp3',
            'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
            'is_live': True,
        },
        'params': {
            'skip_download': True,
        },
    }

    @classmethod
    def suitable(cls, url):
        return False if NPORadioFragmentIE.suitable(url) else super().suitable(url)

    @staticmethod
    def _html_get_attribute_regex(attribute):
        return rf'{attribute}\s*=\s*\'([^\']+)\''

    def _real_extract(self, url):
        video_id = self._match_id(url)

        webpage = self._download_webpage(url, video_id)

        title = self._html_search_regex(
            self._html_get_attribute_regex('data-channel'), webpage, 'title')

        stream = self._parse_json(
            self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
            video_id)

        codec = stream.get('codec')

        return {
            'id': video_id,
            'url': stream['url'],
            'title': title,
            'acodec': codec,
            'ext': codec,
            'is_live': True,
        }


class NPORadioFragmentIE(InfoExtractor):
    IE_NAME = 'npo.nl:radio:fragment'
    _VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'

    _TEST = {
        'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
        'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
        'info_dict': {
            'id': '174356',
            'ext': 'mp3',
            'title': 'Jubileumconcert Willeke Alberti',
        },
    }

    def _real_extract(self, url):
        audio_id = self._match_id(url)

        webpage = self._download_webpage(url, audio_id)

        title = self._html_search_regex(
            rf'href="/radio/[^/]+/fragment/{audio_id}" title="([^"]+)"',
            webpage, 'title')

        audio_url = self._search_regex(
            r"data-streams='([^']+)'", webpage, 'audio url')

        return {
            'id': audio_id,
            'url': audio_url,
            'title': title,
        }


class NPODataMidEmbedIE(InfoExtractor):  # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
    def _real_extract(self, url):
        display_id = self._match_id(url)
        webpage = self._download_webpage(url, display_id)
        video_id = self._search_regex(
            r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
        return {
            '_type': 'url_transparent',
            'ie_key': 'NPO',
            'url': f'npo:{video_id}',
            'display_id': display_id,
        }


class SchoolTVIE(NPODataMidEmbedIE):
    IE_NAME = 'schooltv'
    _VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'

    _TEST = {
        'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/',
        'info_dict': {
            'id': 'WO_NTR_429477',
            'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
            'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?',
            'ext': 'mp4',
            'description': 'md5:abfa0ff690adb73fd0297fd033aaa631',
        },
        'params': {
            # Skip because of m3u8 download
            'skip_download': True,
        },
    }


class HetKlokhuisIE(NPODataMidEmbedIE):
    IE_NAME = 'hetklokhuis'
    _VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'

    _TEST = {
        'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',
        'info_dict': {
            'id': 'VPWON_1260528',
            'display_id': 'Zwaartekrachtsgolven',
            'ext': 'm4v',
            'title': 'Het Klokhuis: Zwaartekrachtsgolven',
            'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48',
            'upload_date': '20170223',
        },
        'params': {
            'skip_download': True,
        },
    }


class NPOPlaylistBaseIE(NPOIE):  # XXX: Do not subclass from concrete IE
    def _real_extract(self, url):
        playlist_id = self._match_id(url)

        webpage = self._download_webpage(url, playlist_id)

        entries = [
            self.url_result(f'npo:{video_id}' if not video_id.startswith('http') else video_id)
            for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage))
        ]

        playlist_title = self._html_search_regex(
            self._PLAYLIST_TITLE_RE, webpage, 'playlist title',
            default=None) or self._og_search_title(webpage)

        return self.playlist_result(entries, playlist_id, playlist_title)


class VPROIE(NPOPlaylistBaseIE):
    IE_NAME = 'vpro'
    _VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
    _PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].*?\bmedia-platform-title\b.*?["\'][^>]*>([^<]+)',
                          r'<h5[^>]+class=["\'].*?\bmedia-platform-subtitle\b.*?["\'][^>]*>([^<]+)')
    _PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'

    _TESTS = [
        {
            'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
            'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
            'info_dict': {
                'id': 'VPWON_1169289',
                'ext': 'm4v',
                'title': 'De toekomst komt uit Afrika',
                'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
                'upload_date': '20130225',
            },
            'skip': 'Video gone',
        },
        {
            'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html',
            'info_dict': {
                'id': 'sergio-herman',
                'title': 'sergio herman: fucking perfect',
            },
            'playlist_count': 2,
        },
        {
            # playlist with youtube embed
            'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html',
            'info_dict': {
                'id': 'education-education',
                'title': 'education education',
            },
            'playlist_count': 2,
        },
        {
            'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
            'info_dict': {
                'id': 'de-tegenprestatie',
                'title': 'De Tegenprestatie',
            },
            'playlist_count': 2,
        }, {
            'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html',
            'info_dict': {
                'id': 'VARA_101375237',
                'ext': 'm4v',
                'title': 'MH17: Het verdriet van Nederland',
                'description': 'md5:09e1a37c1fdb144621e22479691a9f18',
                'upload_date': '20150716',
            },
            'params': {
                # Skip because of m3u8 download
                'skip_download': True,
            },
        },
    ]


class WNLIE(NPOPlaylistBaseIE):
    IE_NAME = 'wnl'
    _VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
    _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>'
    _PLAYLIST_ENTRY_RE = r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>Deel \d+'

    _TESTS = [{
        'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
        'info_dict': {
            'id': 'vandaag-de-dag-6-mei',
            'title': 'Vandaag de Dag 6 mei',
        },
        'playlist_count': 4,
    }]


class AndereTijdenIE(NPOPlaylistBaseIE):
    IE_NAME = 'anderetijden'
    _VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/programma/(?:[^/]+/)+(?P<id>[^/?#&]+)'
    _PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class=["\'].*?\bpage-title\b.*?["\'][^>]*>(.+?)</h1>'
    _PLAYLIST_ENTRY_RE = r'<figure[^>]+class=["\']episode-container episode-page["\'][^>]+data-prid=["\'](.+?)["\']'

    _TESTS = [{
        'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem',
        'info_dict': {
            'id': 'Duitse-soldaten-over-de-Slag-bij-Arnhem',
            'title': 'Duitse soldaten over de Slag bij Arnhem',
        },
        'playlist_count': 3,
    }]
Commit	Line	Data
cc2389c8	1	import random
525daedd	2	import re
cc2389c8	3	import urllib.parse
525daedd	4
171ca612	5	from .common import InfoExtractor
331ae266	6	from ..utils import (
83e8fce6	7	determine_ext,
ee706f10	8	int_or_none,
ff60ec8f	9	merge_dicts,
5742c18b	10	orderedSet,
ff60ec8f	11	str_or_none,
cc2389c8	12	try_call,
ff60ec8f S	13	unified_timestamp,
	14	url_or_none,
	15	urlencode_postdata,
331ae266 JMF	16	)
	17
	18
cc2389c8	19	class NPOIE(InfoExtractor):
e118031e	20	IE_NAME = 'npo'
359aa2fd	21	IE_DESC = 'npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl'
525daedd	22	_VALID_URL = r'''(?x)
03f32a7e S	23	(?:
	24	npo:\|
	25	https?://
	26	(?:www\.)?
	27	(?:
9d581efe S	28	npo\.nl/(?:[^/]+/)*\|
9d581efe S	29	(?:ntr\|npostart)\.nl/(?:[^/]+/){2,}\|
f264c623	30	omroepwnl\.nl/video/fragment/[^/]+__\|
c4e74964	31	(?:zapp\|npo3)\.nl/(?:[^/]+/){2,}
03f32a7e	32	)
525daedd S	33	)
	34	(?P<id>[^/?#]+)
	35	'''
331ae266	36
83e8fce6 S	37	_TESTS = [{
	38	'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
	39	'md5': '4b3f9c429157ec4775f2c9cb7b911016',
	40	'info_dict': {
	41	'id': 'VPWON_1220719',
	42	'ext': 'm4v',
	43	'title': 'Nieuwsuur',
	44	'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
	45	'upload_date': '20140622',
331ae266	46	},
cc2389c8	47	'skip': 'Video was removed',
83e8fce6 S	48	}, {
	49	'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
	50	'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
	51	'info_dict': {
	52	'id': 'VARA_101191800',
	53	'ext': 'm4v',
	54	'title': 'De Mega Mike & Mega Thomas show: The best of.',
	55	'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
	56	'upload_date': '20090227',
	57	'duration': 2400,
944a3de2	58	},
cc2389c8	59	'skip': 'Video was removed',
83e8fce6 S	60	}, {
83e8fce6 S	61	'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
cc2389c8	62	'md5': '1b279c0547f6b270e014c576415268c5',
83e8fce6 S	63	'info_dict': {
83e8fce6 S	64	'id': 'VPWON_1169289',
cc2389c8	65	'ext': 'mp4',
	66	'title': 'Zwart geld: de toekomst komt uit Afrika',
	67	'description': 'md5:dffaf3d628a9c36f78ca48d834246261',
83e8fce6 S	68	'upload_date': '20130225',
83e8fce6 S	69	'duration': 3000,
cc2389c8	70	'creator': 'NED2',
	71	'series': 'Tegenlicht',
	72	'timestamp': 1361822340,
	73	'thumbnail': 'https://images.npo.nl/tile/1280x720/142854.jpg',
	74	'episode': 'Zwart geld: de toekomst komt uit Afrika',
	75	'episode_number': 18,
1ff30d7b	76	},
83e8fce6 S	77	}, {
	78	'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
	79	'info_dict': {
	80	'id': 'WO_VPRO_043706',
cc2389c8	81	'ext': 'mp4',
83e8fce6 S	82	'title': 'De nieuwe mens - Deel 1',
	83	'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
	84	'duration': 4680,
cc2389c8	85	'episode': 'De nieuwe mens - Deel 1',
	86	'thumbnail': 'https://images.npo.nl/tile/1280x720/6289.jpg',
	87	'timestamp': 1279716057,
	88	'series': 'De nieuwe mens - Deel 1',
	89	'upload_date': '20100721',
1ff30d7b	90	},
83e8fce6 S	91	'params': {
83e8fce6 S	92	'skip_download': True,
cc2389c8	93	},
83e8fce6	94	}, {
c85f3683	95	# non asf in streams
83e8fce6 S	96	'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
	97	'info_dict': {
	98	'id': 'WO_NOS_762771',
	99	'ext': 'mp4',
	100	'title': 'Hoe gaat Europa verder na Parijs?',
f264c623	101	},
83e8fce6 S	102	'params': {
83e8fce6 S	103	'skip_download': True,
cc2389c8	104	},
cc2389c8	105	'skip': 'Video was removed',
83e8fce6 S	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',
cc2389c8	110	'ext': 'mp4',
83e8fce6	111	'title': 'Aap, poot, pies',
cc2389c8	112	'description': 'md5:4b46b1b9553b4c036a04d2a532a137e6',
83e8fce6 S	113	'upload_date': '20150508',
83e8fce6 S	114	'duration': 599,
cc2389c8	115	'episode': 'Aap, poot, pies',
	116	'thumbnail': 'https://images.poms.omroep.nl/image/s1280/c1280x720/608118.jpg',
	117	'timestamp': 1431064200,
	118	'series': 'Aap, poot, pies',
f264c623	119	},
83e8fce6 S	120	'params': {
83e8fce6 S	121	'skip_download': True,
cc2389c8	122	},
83e8fce6 S	123	}, {
	124	'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
	125	'info_dict': {
	126	'id': 'POW_00996502',
	127	'ext': 'm4v',
	128	'title': '''"Dit is wel een 'landslide'..."''',
	129	'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
	130	'upload_date': '20150508',
	131	'duration': 462,
18abb743	132	},
83e8fce6 S	133	'params': {
83e8fce6 S	134	'skip_download': True,
cc2389c8	135	},
cc2389c8	136	'skip': 'Video was removed',
4b8a984c S	137	}, {
	138	# audio
	139	'url': 'http://www.npo.nl/jouw-stad-rotterdam/29-01-2017/RBX_FUNX_6683215/RBX_FUNX_7601437',
	140	'info_dict': {
	141	'id': 'RBX_FUNX_6683215',
	142	'ext': 'mp3',
	143	'title': 'Jouw Stad Rotterdam',
	144	'description': 'md5:db251505244f097717ec59fabc372d9f',
	145	},
	146	'params': {
	147	'skip_download': True,
cc2389c8	148	},
cc2389c8	149	'skip': 'Video was removed',
83e8fce6 S	150	}, {
	151	'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547',
	152	'only_matching': True,
	153	}, {
	154	'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118',
	155	'only_matching': True,
	156	}, {
	157	'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
	158	'only_matching': True,
359aa2fd	159	}, {
	160	'url': 'https://www.npo3.nl/3onderzoekt/16-09-2015/VPWON_1239870',
	161	'only_matching': True,
83e8fce6 S	162	}, {
	163	# live stream
	164	'url': 'npo:LI_NL1_4188102',
	165	'only_matching': True,
7dd5415c S	166	}, {
	167	'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373',
	168	'only_matching': True,
c4e74964 S	169	}, {
	170	'url': 'https://www.zapp.nl/1803-skelterlab/instructie-video-s/740-instructievideo-s/POMS_AT_11736927',
	171	'only_matching': True,
9d581efe S	172	}, {
	173	'url': 'https://www.npostart.nl/broodje-gezond-ei/28-05-2018/KN_1698996',
	174	'only_matching': True,
	175	}, {
	176	'url': 'https://npo.nl/KN_1698996',
	177	'only_matching': True,
cc2389c8	178	}, {
	179	'url': 'https://www.npo3.nl/the-genius/21-11-2022/VPWON_1341105',
	180	'info_dict': {
	181	'id': 'VPWON_1341105',
	182	'ext': 'mp4',
	183	'duration': 2658,
	184	'series': 'The Genius',
	185	'description': 'md5:db02f1456939ca63f7c408f858044e94',
	186	'title': 'The Genius',
	187	'timestamp': 1669062000,
	188	'creator': 'NED3',
	189	'episode': 'The Genius',
	190	'thumbnail': 'https://images.npo.nl/tile/1280x720/1827650.jpg',
	191	'episode_number': 8,
	192	'upload_date': '20221121',
	193	},
	194	'params': {
	195	'skip_download': True,
	196	},
83e8fce6	197	}]
331ae266	198
9d581efe S	199	@classmethod
	200	def suitable(cls, url):
	201	return (False if any(ie.suitable(url)
	202	for ie in (NPOLiveIE, NPORadioIE, NPORadioFragmentIE))
add96eb9	203	else super().suitable(url))
9d581efe	204
331ae266	205	def _real_extract(self, url):
04e0bac2	206	video_id = self._match_id(url)
cc2389c8	207	if urllib.parse.urlparse(url).netloc in ['www.ntr.nl', 'ntr.nl']:
	208	player = self._download_json(
	209	f'https://www.ntr.nl/ajax/player/embed/{video_id}', video_id,
	210	'Downloading player JSON', query={
	211	'parameters[elementId]': f'npo{random.randint(0, 999)}',
	212	'parameters[sterReferralUrl]': url,
	213	'parameters[autoplay]': 0,
	214	})
	215	else:
	216	self._request_webpage(
	217	'https://www.npostart.nl/api/token', video_id,
	218	'Downloading token', headers={
	219	'Referer': url,
	220	'X-Requested-With': 'XMLHttpRequest',
	221	})
	222	player = self._download_json(
	223	f'https://www.npostart.nl/player/{video_id}', video_id,
	224	'Downloading player JSON', data=urlencode_postdata({
	225	'autoplay': 0,
	226	'share': 1,
	227	'pageUrl': url,
	228	'hasAdConsent': 0,
	229	}), headers={
	230	'x-xsrf-token': try_call(lambda: urllib.parse.unquote(
add96eb9	231	self._get_cookies('https://www.npostart.nl')['XSRF-TOKEN'].value)),
cc2389c8	232	})
ff60ec8f S	233
	234	player_token = player['token']
	235
8cb10807	236	drm = False
ff60ec8f S	237	format_urls = set()
	238	formats = []
	239	for profile in ('hls', 'dash-widevine', 'dash-playready', 'smooth'):
	240	streams = self._download_json(
add96eb9	241	f'https://start-player.npo.nl/video/{video_id}/streams',
add96eb9	242	video_id, f'Downloading {profile} profile JSON', fatal=False,
ff60ec8f S	243	query={
ff60ec8f S	244	'profile': profile,
cc2389c8	245	'quality': 'npoplus',
ff60ec8f S	246	'tokenId': player_token,
ff60ec8f S	247	'streamType': 'broadcast',
8e02a4dc	248	}, data=b'') # endpoint requires POST
ff60ec8f S	249	if not streams:
	250	continue
	251	stream = streams.get('stream')
	252	if not isinstance(stream, dict):
	253	continue
	254	stream_url = url_or_none(stream.get('src'))
	255	if not stream_url or stream_url in format_urls:
	256	continue
	257	format_urls.add(stream_url)
8cb10807 S	258	if stream.get('protection') is not None or stream.get('keySystemOptions') is not None:
8cb10807 S	259	drm = True
ff60ec8f S	260	continue
	261	stream_type = stream.get('type')
	262	stream_ext = determine_ext(stream_url)
	263	if stream_type == 'application/dash+xml' or stream_ext == 'mpd':
	264	formats.extend(self._extract_mpd_formats(
	265	stream_url, video_id, mpd_id='dash', fatal=False))
	266	elif stream_type == 'application/vnd.apple.mpegurl' or stream_ext == 'm3u8':
	267	formats.extend(self._extract_m3u8_formats(
	268	stream_url, video_id, ext='mp4',
	269	entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
bb6f112d	270	elif re.search(r'\.isml?/Manifest', stream_url):
ff60ec8f S	271	formats.extend(self._extract_ism_formats(
	272	stream_url, video_id, ism_id='mss', fatal=False))
	273	else:
	274	formats.append({
	275	'url': stream_url,
	276	})
	277
8cb10807	278	if not formats:
a06916d9	279	if not self.get_param('allow_unplayable_formats') and drm:
88acdbc2	280	self.report_drm(video_id)
8cb10807	281
ff60ec8f S	282	info = {
	283	'id': video_id,
	284	'title': video_id,
	285	'formats': formats,
	286	}
	287
	288	embed_url = url_or_none(player.get('embedUrl'))
	289	if embed_url:
	290	webpage = self._download_webpage(
	291	embed_url, video_id, 'Downloading embed page', fatal=False)
	292	if webpage:
	293	video = self._parse_json(
	294	self._search_regex(
	295	r'\bvideo\s=\s({.+?})\s*;', webpage, 'video',
	296	default='{}'), video_id)
	297	if video:
	298	title = video.get('episodeTitle')
	299	subtitles = {}
	300	subtitles_list = video.get('subtitles')
	301	if isinstance(subtitles_list, list):
	302	for cc in subtitles_list:
	303	cc_url = url_or_none(cc.get('src'))
	304	if not cc_url:
	305	continue
	306	lang = str_or_none(cc.get('language')) or 'nl'
	307	subtitles.setdefault(lang, []).append({
	308	'url': cc_url,
	309	})
	310	return merge_dicts({
	311	'title': title,
	312	'description': video.get('description'),
	313	'thumbnail': url_or_none(
	314	video.get('still_image_url') or video.get('orig_image_url')),
	315	'duration': int_or_none(video.get('duration')),
	316	'timestamp': unified_timestamp(video.get('broadcastDate')),
	317	'creator': video.get('channel'),
	318	'series': video.get('title'),
	319	'episode': title,
	320	'episode_number': int_or_none(video.get('episodeNumber')),
	321	'subtitles': subtitles,
	322	}, info)
	323
	324	return info
	325
d0df9292	326
cc2389c8	327	class NPOLiveIE(InfoExtractor):
04e0bac2	328	IE_NAME = 'npo.nl:live'
4e1ddc8d	329	_VALID_URL = r'https?://(?:www\.)?npo(?:start)?\.nl/live(?:/(?P<id>[^/?#&]+))?'
04e0bac2	330
1591ba25	331	_TESTS = [{
04e0bac2 S	332	'url': 'http://www.npo.nl/live/npo-1',
04e0bac2 S	333	'info_dict': {
83e8fce6	334	'id': 'LI_NL1_4188102',
04e0bac2 S	335	'display_id': 'npo-1',
04e0bac2 S	336	'ext': 'mp4',
83e8fce6	337	'title': 're:^NPO 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
04e0bac2 S	338	'is_live': True,
	339	},
	340	'params': {
	341	'skip_download': True,
add96eb9	342	},
1591ba25 AG	343	}, {
1591ba25 AG	344	'url': 'http://www.npo.nl/live',
04e431cf	345	'only_matching': True,
4e1ddc8d S	346	}, {
	347	'url': 'https://www.npostart.nl/live/npo-1',
	348	'only_matching': True,
1591ba25	349	}]
04e0bac2 S	350
04e0bac2 S	351	def _real_extract(self, url):
1591ba25	352	display_id = self._match_id(url) or 'npo-1'
04e0bac2 S	353
	354	webpage = self._download_webpage(url, display_id)
	355
	356	live_id = self._search_regex(
7a577309	357	[r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id')
04e0bac2	358
04e0bac2	359	return {
83e8fce6	360	'_type': 'url_transparent',
add96eb9	361	'url': f'npo:{live_id}',
83e8fce6	362	'ie_key': NPOIE.ie_key(),
04e0bac2 S	363	'id': live_id,
04e0bac2 S	364	'display_id': display_id,
04e0bac2 S	365	}
	366
	367
171ca612 S	368	class NPORadioIE(InfoExtractor):
171ca612 S	369	IE_NAME = 'npo.nl:radio'
9d581efe	370	_VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)'
171ca612 S	371
	372	_TEST = {
	373	'url': 'http://www.npo.nl/radio/radio-1',
	374	'info_dict': {
	375	'id': 'radio-1',
	376	'ext': 'mp3',
	377	'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
	378	'is_live': True,
	379	},
	380	'params': {
	381	'skip_download': True,
add96eb9	382	},
171ca612 S	383	}
171ca612 S	384
9d581efe S	385	@classmethod
9d581efe S	386	def suitable(cls, url):
add96eb9	387	return False if NPORadioFragmentIE.suitable(url) else super().suitable(url)
9d581efe	388
171ca612 S	389	@staticmethod
171ca612 S	390	def _html_get_attribute_regex(attribute):
add96eb9	391	return rf'{attribute}\s=\s\'([^\']+)\''
171ca612 S	392
	393	def _real_extract(self, url):
	394	video_id = self._match_id(url)
	395
	396	webpage = self._download_webpage(url, video_id)
	397
	398	title = self._html_search_regex(
	399	self._html_get_attribute_regex('data-channel'), webpage, 'title')
	400
	401	stream = self._parse_json(
	402	self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
	403	video_id)
	404
	405	codec = stream.get('codec')
	406
	407	return {
	408	'id': video_id,
	409	'url': stream['url'],
39ca3b5c	410	'title': title,
171ca612 S	411	'acodec': codec,
	412	'ext': codec,
	413	'is_live': True,
	414	}
	415
	416
	417	class NPORadioFragmentIE(InfoExtractor):
	418	IE_NAME = 'npo.nl:radio:fragment'
	419	_VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'
	420
	421	_TEST = {
	422	'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
	423	'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
	424	'info_dict': {
	425	'id': '174356',
	426	'ext': 'mp3',
	427	'title': 'Jubileumconcert Willeke Alberti',
	428	},
	429	}
	430
	431	def _real_extract(self, url):
	432	audio_id = self._match_id(url)
	433
	434	webpage = self._download_webpage(url, audio_id)
	435
	436	title = self._html_search_regex(
add96eb9	437	rf'href="/radio/[^/]+/fragment/{audio_id}" title="([^"]+)"',
171ca612 S	438	webpage, 'title')
	439
	440	audio_url = self._search_regex(
	441	r"data-streams='([^']+)'", webpage, 'audio url')
	442
	443	return {
	444	'id': audio_id,
	445	'url': audio_url,
	446	'title': title,
	447	}
	448
	449
6368e2e6	450	class NPODataMidEmbedIE(InfoExtractor): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
0dc5a86a S	451	def _real_extract(self, url):
	452	display_id = self._match_id(url)
	453	webpage = self._download_webpage(url, display_id)
	454	video_id = self._search_regex(
	455	r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
	456	return {
	457	'_type': 'url_transparent',
	458	'ie_key': 'NPO',
add96eb9	459	'url': f'npo:{video_id}',
add96eb9	460	'display_id': display_id,
0dc5a86a S	461	}
	462
	463
	464	class SchoolTVIE(NPODataMidEmbedIE):
89f26028	465	IE_NAME = 'schooltv'
	466	_VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'
	467
	468	_TEST = {
	469	'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/',
	470	'info_dict': {
	471	'id': 'WO_NTR_429477',
	472	'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
	473	'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?',
	474	'ext': 'mp4',
add96eb9	475	'description': 'md5:abfa0ff690adb73fd0297fd033aaa631',
89f26028	476	},
	477	'params': {
	478	# Skip because of m3u8 download
add96eb9	479	'skip_download': True,
add96eb9	480	},
89f26028	481	}
89f26028	482
0dc5a86a S	483
0dc5a86a S	484	class HetKlokhuisIE(NPODataMidEmbedIE):
dbc01fdb	485	IE_NAME = 'hetklokhuis'
197224b7	486	_VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
0dc5a86a S	487
	488	_TEST = {
	489	'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',
	490	'info_dict': {
	491	'id': 'VPWON_1260528',
	492	'display_id': 'Zwaartekrachtsgolven',
	493	'ext': 'm4v',
	494	'title': 'Het Klokhuis: Zwaartekrachtsgolven',
	495	'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48',
	496	'upload_date': '20170223',
	497	},
	498	'params': {
add96eb9	499	'skip_download': True,
add96eb9	500	},
0dc5a86a	501	}
89f26028	502
89f26028	503
6368e2e6	504	class NPOPlaylistBaseIE(NPOIE): # XXX: Do not subclass from concrete IE
a3d8b381 S	505	def _real_extract(self, url):
	506	playlist_id = self._match_id(url)
	507
	508	webpage = self._download_webpage(url, playlist_id)
	509
	510	entries = [
add96eb9	511	self.url_result(f'npo:{video_id}' if not video_id.startswith('http') else video_id)
5742c18b	512	for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage))
a3d8b381 S	513	]
	514
	515	playlist_title = self._html_search_regex(
	516	self._PLAYLIST_TITLE_RE, webpage, 'playlist title',
	517	default=None) or self._og_search_title(webpage)
	518
	519	return self.playlist_result(entries, playlist_id, playlist_title)
	520
	521
	522	class VPROIE(NPOPlaylistBaseIE):
464e7924	523	IE_NAME = 'vpro'
b1d79888 S	524	_VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro\|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
	525	_PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].?\bmedia-platform-title\b.?["\'][^>]*>([^<]+)',
	526	r'<h5[^>]+class=["\'].?\bmedia-platform-subtitle\b.?["\'][^>]*>([^<]+)')
a3d8b381	527	_PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'
d0df9292 JMF	528
	529	_TESTS = [
	530	{
	531	'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
	532	'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
	533	'info_dict': {
	534	'id': 'VPWON_1169289',
	535	'ext': 'm4v',
5ba761eb	536	'title': 'De toekomst komt uit Afrika',
611ac379	537	'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
d0df9292 JMF	538	'upload_date': '20130225',
d0df9292 JMF	539	},
ddb19772	540	'skip': 'Video gone',
d0df9292	541	},
611ac379 S	542	{
	543	'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html',
	544	'info_dict': {
	545	'id': 'sergio-herman',
ddb19772	546	'title': 'sergio herman: fucking perfect',
611ac379 S	547	},
611ac379 S	548	'playlist_count': 2,
574f42d7 S	549	},
	550	{
	551	# playlist with youtube embed
	552	'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html',
	553	'info_dict': {
	554	'id': 'education-education',
ddb19772	555	'title': 'education education',
574f42d7 S	556	},
574f42d7 S	557	'playlist_count': 2,
b1d79888 S	558	},
	559	{
	560	'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
	561	'info_dict': {
	562	'id': 'de-tegenprestatie',
	563	'title': 'De Tegenprestatie',
	564	},
	565	'playlist_count': 2,
	566	}, {
	567	'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html',
	568	'info_dict': {
	569	'id': 'VARA_101375237',
	570	'ext': 'm4v',
	571	'title': 'MH17: Het verdriet van Nederland',
	572	'description': 'md5:09e1a37c1fdb144621e22479691a9f18',
	573	'upload_date': '20150716',
	574	},
	575	'params': {
	576	# Skip because of m3u8 download
add96eb9	577	'skip_download': True,
b1d79888	578	},
add96eb9	579	},
d0df9292 JMF	580	]
d0df9292 JMF	581
03f32a7e	582
a3d8b381	583	class WNLIE(NPOPlaylistBaseIE):
f9dd86a1	584	IE_NAME = 'wnl'
03f32a7e	585	_VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
a3d8b381 S	586	_PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>'
a3d8b381 S	587	_PLAYLIST_ENTRY_RE = r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>Deel \d+'
03f32a7e	588
a3d8b381	589	_TESTS = [{
03f32a7e S	590	'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
	591	'info_dict': {
	592	'id': 'vandaag-de-dag-6-mei',
	593	'title': 'Vandaag de Dag 6 mei',
	594	},
	595	'playlist_count': 4,
a3d8b381	596	}]
5742c18b S	597
	598
	599	class AndereTijdenIE(NPOPlaylistBaseIE):
f9dd86a1	600	IE_NAME = 'anderetijden'
5742c18b S	601	_VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/programma/(?:[^/]+/)+(?P<id>[^/?#&]+)'
	602	_PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class=["\'].?\bpage-title\b.?["\'][^>]*>(.+?)</h1>'
	603	_PLAYLIST_ENTRY_RE = r'<figure[^>]+class=["\']episode-container episode-page["\'][^>]+data-prid=["\'](.+?)["\']'
	604
	605	_TESTS = [{
	606	'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem',
	607	'info_dict': {
	608	'id': 'Duitse-soldaten-over-de-Slag-bij-Arnhem',
	609	'title': 'Duitse soldaten over de Slag bij Arnhem',
	610	},
	611	'playlist_count': 3,
	612	}]