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

from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..compat import (
    compat_HTTPError,
    compat_str,
)
from ..utils import (
    determine_ext,
    ExtractorError,
    fix_xml_ampersands,
    orderedSet,
    parse_duration,
    qualities,
    strip_jsonp,
    unified_strdate,
)


class NPOBaseIE(InfoExtractor):
    def _get_token(self, video_id):
        return self._download_json(
            'http://ida.omroep.nl/app.php/auth', video_id,
            note='Downloading token')['token']


class NPOIE(NPOBaseIE):
    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/(?!(?:live|radio)/)(?:[^/]+/){2}|
                                ntr\.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',
        },
    }, {
        '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,
        },
    }, {
        'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
        'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
        'info_dict': {
            'id': 'VPWON_1169289',
            'ext': 'm4v',
            'title': 'Tegenlicht: Zwart geld. De toekomst komt uit Afrika',
            'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
            'upload_date': '20130225',
            'duration': 3000,
        },
    }, {
        'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
        'info_dict': {
            'id': 'WO_VPRO_043706',
            'ext': 'm4v',
            'title': 'De nieuwe mens - Deel 1',
            'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
            'duration': 4680,
        },
        '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,
        }
    }, {
        'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
        'info_dict': {
            'id': 'VPWON_1233944',
            'ext': 'm4v',
            'title': 'Aap, poot, pies',
            'description': 'md5:c9c8005d1869ae65b858e82c01a91fde',
            'upload_date': '20150508',
            'duration': 599,
        },
        '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,
        }
    }, {
        # 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,
        }
    }, {
        '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,
    }]

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

    def _get_info(self, video_id):
        metadata = self._download_json(
            'http://e.omroep.nl/metadata/%s' % video_id,
            video_id,
            # We have to remove the javascript callback
            transform_source=strip_jsonp,
        )

        error = metadata.get('error')
        if error:
            raise ExtractorError(error, expected=True)

        # For some videos actual video id (prid) is different (e.g. for
        # http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698
        # video id is POMS_WNL_853698 but prid is POW_00996502)
        video_id = metadata.get('prid') or video_id

        # titel is too generic in some cases so utilize aflevering_titel as well
        # when available (e.g. http://tegenlicht.vpro.nl/afleveringen/2014-2015/access-to-africa.html)
        title = metadata['titel']
        sub_title = metadata.get('aflevering_titel')
        if sub_title and sub_title != title:
            title += ': %s' % sub_title

        token = self._get_token(video_id)

        formats = []
        urls = set()

        quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
        items = self._download_json(
            'http://ida.omroep.nl/app.php/%s' % video_id, video_id,
            'Downloading formats JSON', query={
                'adaptive': 'yes',
                'token': token,
            })['items'][0]
        for num, item in enumerate(items):
            item_url = item.get('url')
            if not item_url or item_url in urls:
                continue
            urls.add(item_url)
            format_id = self._search_regex(
                r'video/ida/([^/]+)', item_url, 'format id',
                default=None)

            def add_format_url(format_url):
                formats.append({
                    'url': format_url,
                    'format_id': format_id,
                    'quality': quality(format_id),
                })

            # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
            if item.get('contentType') in ('url', 'audio'):
                add_format_url(item_url)
                continue

            try:
                stream_info = self._download_json(
                    item_url + '&type=json', video_id,
                    'Downloading %s stream JSON'
                    % item.get('label') or item.get('format') or format_id or num)
            except ExtractorError as ee:
                if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
                    error = (self._parse_json(
                        ee.cause.read().decode(), video_id,
                        fatal=False) or {}).get('errorstring')
                    if error:
                        raise ExtractorError(error, expected=True)
                raise
            # Stream URL instead of JSON, example: npo:LI_NL1_4188102
            if isinstance(stream_info, compat_str):
                if not stream_info.startswith('http'):
                    continue
                video_url = stream_info
            # JSON
            else:
                video_url = stream_info.get('url')
            if not video_url or video_url in urls:
                continue
            urls.add(item_url)
            if determine_ext(video_url) == 'm3u8':
                formats.extend(self._extract_m3u8_formats(
                    video_url, video_id, ext='mp4',
                    entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
            else:
                add_format_url(video_url)

        is_live = metadata.get('medium') == 'live'

        if not is_live:
            for num, stream in enumerate(metadata.get('streams', [])):
                stream_url = stream.get('url')
                if not stream_url or stream_url in urls:
                    continue
                urls.add(stream_url)
                # smooth streaming is not supported
                stream_type = stream.get('type', '').lower()
                if stream_type in ['ss', 'ms']:
                    continue
                if stream_type == 'hds':
                    f4m_formats = self._extract_f4m_formats(
                        stream_url, video_id, fatal=False)
                    # f4m downloader downloads only piece of live stream
                    for f4m_format in f4m_formats:
                        f4m_format['preference'] = -1
                    formats.extend(f4m_formats)
                elif stream_type == 'hls':
                    formats.extend(self._extract_m3u8_formats(
                        stream_url, video_id, ext='mp4', fatal=False))
                # Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
                elif '.asf' in stream_url:
                    asx = self._download_xml(
                        stream_url, video_id,
                        'Downloading stream %d ASX playlist' % num,
                        transform_source=fix_xml_ampersands, fatal=False)
                    if not asx:
                        continue
                    ref = asx.find('./ENTRY/Ref')
                    if ref is None:
                        continue
                    video_url = ref.get('href')
                    if not video_url or video_url in urls:
                        continue
                    urls.add(video_url)
                    formats.append({
                        'url': video_url,
                        'ext': stream.get('formaat', 'asf'),
                        'quality': stream.get('kwaliteit'),
                        'preference': -10,
                    })
                else:
                    formats.append({
                        'url': stream_url,
                        'quality': stream.get('kwaliteit'),
                    })

        self._sort_formats(formats)

        subtitles = {}
        if metadata.get('tt888') == 'ja':
            subtitles['nl'] = [{
                'ext': 'vtt',
                'url': 'http://tt888.omroep.nl/tt888/%s' % video_id,
            }]

        return {
            'id': video_id,
            'title': self._live_title(title) if is_live else title,
            'description': metadata.get('info'),
            'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
            'upload_date': unified_strdate(metadata.get('gidsdatum')),
            'duration': parse_duration(metadata.get('tijdsduur')),
            'formats': formats,
            'subtitles': subtitles,
            'is_live': is_live,
        }


class NPOLiveIE(NPOBaseIE):
    IE_NAME = 'npo.nl:live'
    _VALID_URL = r'https?://(?:www\.)?npo\.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,
    }]

    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': 'npo:%s' % 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,
        }
    }

    @staticmethod
    def _html_get_attribute_regex(attribute):
        return r'{0}\s*=\s*\'([^\']+)\''.format(attribute)

    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': self._live_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(
            r'href="/radio/[^/]+/fragment/%s" title="([^"]+)"' % audio_id,
            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):
    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': 'npo:%s' % 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):
    def _real_extract(self, url):
        playlist_id = self._match_id(url)

        webpage = self._download_webpage(url, playlist_id)

        entries = [
            self.url_result('npo:%s' % 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
331ae266 JMF	1	from __future__ import unicode_literals
331ae266 JMF	2
525daedd S	3	import re
525daedd S	4
171ca612	5	from .common import InfoExtractor
83e8fce6 S	6	from ..compat import (
	7	compat_HTTPError,
	8	compat_str,
	9	)
331ae266	10	from ..utils import (
83e8fce6 S	11	determine_ext,
83e8fce6 S	12	ExtractorError,
5c4a81d9	13	fix_xml_ampersands,
5742c18b	14	orderedSet,
944a3de2	15	parse_duration,
c9ea760e	16	qualities,
609a61e3	17	strip_jsonp,
5c4a81d9	18	unified_strdate,
331ae266 JMF	19	)
	20
	21
b9b42f2e	22	class NPOBaseIE(InfoExtractor):
04e0bac2	23	def _get_token(self, video_id):
aa9cc2ec S	24	return self._download_json(
	25	'http://ida.omroep.nl/app.php/auth', video_id,
	26	note='Downloading token')['token']
04e0bac2 S	27
	28
	29	class NPOIE(NPOBaseIE):
e118031e	30	IE_NAME = 'npo'
359aa2fd	31	IE_DESC = 'npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl'
525daedd	32	_VALID_URL = r'''(?x)
03f32a7e S	33	(?:
	34	npo:\|
	35	https?://
	36	(?:www\.)?
	37	(?:
7dd5415c	38	npo\.nl/(?!(?:live\|radio)/)(?:[^/]+/){2}\|
03f32a7e	39	ntr\.nl/(?:[^/]+/){2,}\|
f264c623	40	omroepwnl\.nl/video/fragment/[^/]+__\|
c4e74964	41	(?:zapp\|npo3)\.nl/(?:[^/]+/){2,}
03f32a7e	42	)
525daedd S	43	)
	44	(?P<id>[^/?#]+)
	45	'''
331ae266	46
83e8fce6 S	47	_TESTS = [{
	48	'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
	49	'md5': '4b3f9c429157ec4775f2c9cb7b911016',
	50	'info_dict': {
	51	'id': 'VPWON_1220719',
	52	'ext': 'm4v',
	53	'title': 'Nieuwsuur',
	54	'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
	55	'upload_date': '20140622',
331ae266	56	},
83e8fce6 S	57	}, {
	58	'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
	59	'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
	60	'info_dict': {
	61	'id': 'VARA_101191800',
	62	'ext': 'm4v',
	63	'title': 'De Mega Mike & Mega Thomas show: The best of.',
	64	'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
	65	'upload_date': '20090227',
	66	'duration': 2400,
944a3de2	67	},
83e8fce6 S	68	}, {
	69	'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
	70	'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
	71	'info_dict': {
	72	'id': 'VPWON_1169289',
	73	'ext': 'm4v',
	74	'title': 'Tegenlicht: Zwart geld. De toekomst komt uit Afrika',
	75	'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
	76	'upload_date': '20130225',
	77	'duration': 3000,
1ff30d7b	78	},
83e8fce6 S	79	}, {
	80	'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
	81	'info_dict': {
	82	'id': 'WO_VPRO_043706',
	83	'ext': 'm4v',
	84	'title': 'De nieuwe mens - Deel 1',
	85	'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
	86	'duration': 4680,
1ff30d7b	87	},
83e8fce6 S	88	'params': {
	89	'skip_download': True,
	90	}
	91	}, {
c85f3683	92	# non asf in streams
83e8fce6 S	93	'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
	94	'info_dict': {
	95	'id': 'WO_NOS_762771',
	96	'ext': 'mp4',
	97	'title': 'Hoe gaat Europa verder na Parijs?',
f264c623	98	},
83e8fce6 S	99	'params': {
	100	'skip_download': True,
	101	}
	102	}, {
	103	'url': 'http://www.ntr.nl/Aap-Poot-Pies/27/detail/Aap-poot-pies/VPWON_1233944#content',
	104	'info_dict': {
	105	'id': 'VPWON_1233944',
	106	'ext': 'm4v',
	107	'title': 'Aap, poot, pies',
	108	'description': 'md5:c9c8005d1869ae65b858e82c01a91fde',
	109	'upload_date': '20150508',
	110	'duration': 599,
f264c623	111	},
83e8fce6 S	112	'params': {
	113	'skip_download': True,
	114	}
	115	}, {
	116	'url': 'http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698',
	117	'info_dict': {
	118	'id': 'POW_00996502',
	119	'ext': 'm4v',
	120	'title': '''"Dit is wel een 'landslide'..."''',
	121	'description': 'md5:f8d66d537dfb641380226e31ca57b8e8',
	122	'upload_date': '20150508',
	123	'duration': 462,
18abb743	124	},
83e8fce6 S	125	'params': {
83e8fce6 S	126	'skip_download': True,
e118031e	127	}
4b8a984c S	128	}, {
	129	# audio
	130	'url': 'http://www.npo.nl/jouw-stad-rotterdam/29-01-2017/RBX_FUNX_6683215/RBX_FUNX_7601437',
	131	'info_dict': {
	132	'id': 'RBX_FUNX_6683215',
	133	'ext': 'mp3',
	134	'title': 'Jouw Stad Rotterdam',
	135	'description': 'md5:db251505244f097717ec59fabc372d9f',
	136	},
	137	'params': {
	138	'skip_download': True,
	139	}
83e8fce6 S	140	}, {
	141	'url': 'http://www.zapp.nl/de-bzt-show/gemist/KN_1687547',
	142	'only_matching': True,
	143	}, {
	144	'url': 'http://www.zapp.nl/de-bzt-show/filmpjes/POMS_KN_7315118',
	145	'only_matching': True,
	146	}, {
	147	'url': 'http://www.zapp.nl/beste-vrienden-quiz/extra-video-s/WO_NTR_1067990',
	148	'only_matching': True,
359aa2fd	149	}, {
	150	'url': 'https://www.npo3.nl/3onderzoekt/16-09-2015/VPWON_1239870',
	151	'only_matching': True,
83e8fce6 S	152	}, {
	153	# live stream
	154	'url': 'npo:LI_NL1_4188102',
	155	'only_matching': True,
7dd5415c S	156	}, {
	157	'url': 'http://www.npo.nl/radio-gaga/13-06-2017/BNN_101383373',
	158	'only_matching': True,
c4e74964 S	159	}, {
	160	'url': 'https://www.zapp.nl/1803-skelterlab/instructie-video-s/740-instructievideo-s/POMS_AT_11736927',
	161	'only_matching': True,
83e8fce6	162	}]
331ae266 JMF	163
331ae266 JMF	164	def _real_extract(self, url):
04e0bac2	165	video_id = self._match_id(url)
d0df9292	166	return self._get_info(video_id)
331ae266	167
d0df9292	168	def _get_info(self, video_id):
331ae266	169	metadata = self._download_json(
8d06a624	170	'http://e.omroep.nl/metadata/%s' % video_id,
331ae266 JMF	171	video_id,
331ae266 JMF	172	# We have to remove the javascript callback
609a61e3	173	transform_source=strip_jsonp,
331ae266	174	)
04e0bac2	175
b8adcec4 S	176	error = metadata.get('error')
	177	if error:
	178	raise ExtractorError(error, expected=True)
	179
525daedd S	180	# For some videos actual video id (prid) is different (e.g. for
	181	# http://www.omroepwnl.nl/video/fragment/vandaag-de-dag-verkiezingen__POMS_WNL_853698
	182	# video id is POMS_WNL_853698 but prid is POW_00996502)
	183	video_id = metadata.get('prid') or video_id
	184
23fc384f S	185	# titel is too generic in some cases so utilize aflevering_titel as well
	186	# when available (e.g. http://tegenlicht.vpro.nl/afleveringen/2014-2015/access-to-africa.html)
	187	title = metadata['titel']
	188	sub_title = metadata.get('aflevering_titel')
	189	if sub_title and sub_title != title:
	190	title += ': %s' % sub_title
	191
04e0bac2	192	token = self._get_token(video_id)
331ae266	193
c9ea760e	194	formats = []
83e8fce6 S	195	urls = set()
	196
	197	quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
	198	items = self._download_json(
	199	'http://ida.omroep.nl/app.php/%s' % video_id, video_id,
	200	'Downloading formats JSON', query={
	201	'adaptive': 'yes',
	202	'token': token,
	203	})['items'][0]
	204	for num, item in enumerate(items):
	205	item_url = item.get('url')
	206	if not item_url or item_url in urls:
	207	continue
	208	urls.add(item_url)
	209	format_id = self._search_regex(
	210	r'video/ida/([^/]+)', item_url, 'format id',
	211	default=None)
	212
	213	def add_format_url(format_url):
	214	formats.append({
	215	'url': format_url,
	216	'format_id': format_id,
	217	'quality': quality(format_id),
	218	})
1ff30d7b	219
83e8fce6	220	# Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
4b8a984c	221	if item.get('contentType') in ('url', 'audio'):
83e8fce6 S	222	add_format_url(item_url)
	223	continue
	224
	225	try:
	226	stream_info = self._download_json(
	227	item_url + '&type=json', video_id,
	228	'Downloading %s stream JSON'
4b8a984c	229	% item.get('label') or item.get('format') or format_id or num)
83e8fce6 S	230	except ExtractorError as ee:
	231	if isinstance(ee.cause, compat_HTTPError) and ee.cause.code == 404:
	232	error = (self._parse_json(
	233	ee.cause.read().decode(), video_id,
	234	fatal=False) or {}).get('errorstring')
	235	if error:
	236	raise ExtractorError(error, expected=True)
	237	raise
	238	# Stream URL instead of JSON, example: npo:LI_NL1_4188102
	239	if isinstance(stream_info, compat_str):
	240	if not stream_info.startswith('http'):
aa9cc2ec	241	continue
83e8fce6 S	242	video_url = stream_info
	243	# JSON
	244	else:
aa9cc2ec	245	video_url = stream_info.get('url')
83e8fce6 S	246	if not video_url or video_url in urls:
	247	continue
	248	urls.add(item_url)
	249	if determine_ext(video_url) == 'm3u8':
	250	formats.extend(self._extract_m3u8_formats(
	251	video_url, video_id, ext='mp4',
	252	entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
	253	else:
	254	add_format_url(video_url)
	255
	256	is_live = metadata.get('medium') == 'live'
	257
	258	if not is_live:
	259	for num, stream in enumerate(metadata.get('streams', [])):
	260	stream_url = stream.get('url')
	261	if not stream_url or stream_url in urls:
1ff30d7b	262	continue
83e8fce6 S	263	urls.add(stream_url)
	264	# smooth streaming is not supported
	265	stream_type = stream.get('type', '').lower()
	266	if stream_type in ['ss', 'ms']:
	267	continue
	268	if stream_type == 'hds':
	269	f4m_formats = self._extract_f4m_formats(
	270	stream_url, video_id, fatal=False)
	271	# f4m downloader downloads only piece of live stream
	272	for f4m_format in f4m_formats:
	273	f4m_format['preference'] = -1
	274	formats.extend(f4m_formats)
	275	elif stream_type == 'hls':
aa9cc2ec	276	formats.extend(self._extract_m3u8_formats(
83e8fce6 S	277	stream_url, video_id, ext='mp4', fatal=False))
	278	# Example: http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706
	279	elif '.asf' in stream_url:
	280	asx = self._download_xml(
	281	stream_url, video_id,
	282	'Downloading stream %d ASX playlist' % num,
	283	transform_source=fix_xml_ampersands, fatal=False)
	284	if not asx:
	285	continue
	286	ref = asx.find('./ENTRY/Ref')
	287	if ref is None:
	288	continue
	289	video_url = ref.get('href')
	290	if not video_url or video_url in urls:
	291	continue
	292	urls.add(video_url)
1ff30d7b S	293	formats.append({
1ff30d7b S	294	'url': video_url,
83e8fce6 S	295	'ext': stream.get('formaat', 'asf'),
	296	'quality': stream.get('kwaliteit'),
	297	'preference': -10,
1ff30d7b	298	})
83e8fce6	299	else:
a0977064 S	300	formats.append({
	301	'url': stream_url,
	302	'quality': stream.get('kwaliteit'),
	303	})
1ff30d7b	304
9e91449c	305	self._sort_formats(formats)
25e5ebf3	306
9e91449c S	307	subtitles = {}
9e91449c S	308	if metadata.get('tt888') == 'ja':
b9b42f2e JMF	309	subtitles['nl'] = [{
b9b42f2e JMF	310	'ext': 'vtt',
56fc078d	311	'url': 'http://tt888.omroep.nl/tt888/%s' % video_id,
b9b42f2e	312	}]
331ae266 JMF	313
	314	return {
	315	'id': video_id,
83e8fce6	316	'title': self._live_title(title) if is_live else title,
536b0700	317	'description': metadata.get('info'),
944a3de2 S	318	'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
	319	'upload_date': unified_strdate(metadata.get('gidsdatum')),
	320	'duration': parse_duration(metadata.get('tijdsduur')),
c9ea760e	321	'formats': formats,
25e5ebf3	322	'subtitles': subtitles,
83e8fce6	323	'is_live': is_live,
331ae266	324	}
d0df9292 JMF	325
d0df9292 JMF	326
04e0bac2 S	327	class NPOLiveIE(NPOBaseIE):
04e0bac2 S	328	IE_NAME = 'npo.nl:live'
04e431cf	329	_VALID_URL = r'https?://(?:www\.)?npo\.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}$',
04e0bac2 S	338	'is_live': True,
	339	},
	340	'params': {
	341	'skip_download': True,
	342	}
1591ba25 AG	343	}, {
1591ba25 AG	344	'url': 'http://www.npo.nl/live',
04e431cf	345	'only_matching': True,
1591ba25	346	}]
04e0bac2 S	347
04e0bac2 S	348	def _real_extract(self, url):
1591ba25	349	display_id = self._match_id(url) or 'npo-1'
04e0bac2 S	350
	351	webpage = self._download_webpage(url, display_id)
	352
	353	live_id = self._search_regex(
7a577309	354	[r'media-id="([^"]+)"', r'data-prid="([^"]+)"'], webpage, 'live id')
04e0bac2	355
04e0bac2	356	return {
83e8fce6 S	357	'_type': 'url_transparent',
	358	'url': 'npo:%s' % live_id,
	359	'ie_key': NPOIE.ie_key(),
04e0bac2 S	360	'id': live_id,
04e0bac2 S	361	'display_id': display_id,
04e0bac2 S	362	}
	363
	364
171ca612 S	365	class NPORadioIE(InfoExtractor):
	366	IE_NAME = 'npo.nl:radio'
	367	_VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)/?$'
	368
	369	_TEST = {
	370	'url': 'http://www.npo.nl/radio/radio-1',
	371	'info_dict': {
	372	'id': 'radio-1',
	373	'ext': 'mp3',
	374	'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
	375	'is_live': True,
	376	},
	377	'params': {
	378	'skip_download': True,
	379	}
	380	}
	381
	382	@staticmethod
	383	def _html_get_attribute_regex(attribute):
	384	return r'{0}\s=\s\'([^\']+)\''.format(attribute)
	385
	386	def _real_extract(self, url):
	387	video_id = self._match_id(url)
	388
	389	webpage = self._download_webpage(url, video_id)
	390
	391	title = self._html_search_regex(
	392	self._html_get_attribute_regex('data-channel'), webpage, 'title')
	393
	394	stream = self._parse_json(
	395	self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
	396	video_id)
	397
	398	codec = stream.get('codec')
	399
	400	return {
	401	'id': video_id,
	402	'url': stream['url'],
	403	'title': self._live_title(title),
	404	'acodec': codec,
	405	'ext': codec,
	406	'is_live': True,
	407	}
	408
	409
	410	class NPORadioFragmentIE(InfoExtractor):
	411	IE_NAME = 'npo.nl:radio:fragment'
	412	_VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'
	413
	414	_TEST = {
	415	'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
	416	'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
	417	'info_dict': {
	418	'id': '174356',
	419	'ext': 'mp3',
	420	'title': 'Jubileumconcert Willeke Alberti',
	421	},
	422	}
	423
	424	def _real_extract(self, url):
	425	audio_id = self._match_id(url)
	426
	427	webpage = self._download_webpage(url, audio_id)
	428
429	title = self._html_search_regex(
430	r'href="/radio/[^/]+/fragment/%s" title="([^"]+)"' % audio_id,
431	webpage, 'title')
432
433	audio_url = self._search_regex(
434	r"data-streams='([^']+)'", webpage, 'audio url')
435
436	return {
437	'id': audio_id,
438	'url': audio_url,
439	'title': title,
440	}
441
442
0dc5a86a S	443	class NPODataMidEmbedIE(InfoExtractor):
	444	def _real_extract(self, url):
	445	display_id = self._match_id(url)
	446	webpage = self._download_webpage(url, display_id)
	447	video_id = self._search_regex(
	448	r'data-mid=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage, 'video_id', group='id')
	449	return {
	450	'_type': 'url_transparent',
	451	'ie_key': 'NPO',
	452	'url': 'npo:%s' % video_id,
	453	'display_id': display_id
	454	}
	455
	456
	457	class SchoolTVIE(NPODataMidEmbedIE):
89f26028	458	IE_NAME = 'schooltv'
	459	_VALID_URL = r'https?://(?:www\.)?schooltv\.nl/video/(?P<id>[^/?#&]+)'
	460
	461	_TEST = {
	462	'url': 'http://www.schooltv.nl/video/ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam/',
	463	'info_dict': {
	464	'id': 'WO_NTR_429477',
	465	'display_id': 'ademhaling-de-hele-dag-haal-je-adem-maar-wat-gebeurt-er-dan-eigenlijk-in-je-lichaam',
	466	'title': 'Ademhaling: De hele dag haal je adem. Maar wat gebeurt er dan eigenlijk in je lichaam?',
	467	'ext': 'mp4',
	468	'description': 'md5:abfa0ff690adb73fd0297fd033aaa631'
	469	},
	470	'params': {
	471	# Skip because of m3u8 download
	472	'skip_download': True
	473	}
	474	}
	475
0dc5a86a S	476
0dc5a86a S	477	class HetKlokhuisIE(NPODataMidEmbedIE):
dbc01fdb	478	IE_NAME = 'hetklokhuis'
197224b7	479	_VALID_URL = r'https?://(?:www\.)?hetklokhuis\.nl/[^/]+/\d+/(?P<id>[^/?#&]+)'
0dc5a86a S	480
	481	_TEST = {
	482	'url': 'http://hetklokhuis.nl/tv-uitzending/3471/Zwaartekrachtsgolven',
	483	'info_dict': {
	484	'id': 'VPWON_1260528',
	485	'display_id': 'Zwaartekrachtsgolven',
	486	'ext': 'm4v',
	487	'title': 'Het Klokhuis: Zwaartekrachtsgolven',
	488	'description': 'md5:c94f31fb930d76c2efa4a4a71651dd48',
	489	'upload_date': '20170223',
	490	},
	491	'params': {
	492	'skip_download': True
89f26028	493	}
0dc5a86a	494	}
89f26028	495
89f26028	496
a3d8b381 S	497	class NPOPlaylistBaseIE(NPOIE):
	498	def _real_extract(self, url):
	499	playlist_id = self._match_id(url)
	500
	501	webpage = self._download_webpage(url, playlist_id)
	502
	503	entries = [
	504	self.url_result('npo:%s' % video_id if not video_id.startswith('http') else video_id)
5742c18b	505	for video_id in orderedSet(re.findall(self._PLAYLIST_ENTRY_RE, webpage))
a3d8b381 S	506	]
	507
	508	playlist_title = self._html_search_regex(
	509	self._PLAYLIST_TITLE_RE, webpage, 'playlist title',
	510	default=None) or self._og_search_title(webpage)
	511
	512	return self.playlist_result(entries, playlist_id, playlist_title)
	513
	514
	515	class VPROIE(NPOPlaylistBaseIE):
464e7924	516	IE_NAME = 'vpro'
b1d79888 S	517	_VALID_URL = r'https?://(?:www\.)?(?:(?:tegenlicht\.)?vpro\|2doc)\.nl/(?:[^/]+/)*(?P<id>[^/]+)\.html'
	518	_PLAYLIST_TITLE_RE = (r'<h1[^>]+class=["\'].?\bmedia-platform-title\b.?["\'][^>]*>([^<]+)',
	519	r'<h5[^>]+class=["\'].?\bmedia-platform-subtitle\b.?["\'][^>]*>([^<]+)')
a3d8b381	520	_PLAYLIST_ENTRY_RE = r'data-media-id="([^"]+)"'
d0df9292 JMF	521
	522	_TESTS = [
	523	{
	524	'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
	525	'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
	526	'info_dict': {
	527	'id': 'VPWON_1169289',
	528	'ext': 'm4v',
5ba761eb	529	'title': 'De toekomst komt uit Afrika',
611ac379	530	'description': 'md5:52cf4eefbc96fffcbdc06d024147abea',
d0df9292 JMF	531	'upload_date': '20130225',
d0df9292 JMF	532	},
ddb19772	533	'skip': 'Video gone',
d0df9292	534	},
611ac379 S	535	{
	536	'url': 'http://www.vpro.nl/programmas/2doc/2015/sergio-herman.html',
	537	'info_dict': {
	538	'id': 'sergio-herman',
ddb19772	539	'title': 'sergio herman: fucking perfect',
611ac379 S	540	},
611ac379 S	541	'playlist_count': 2,
574f42d7 S	542	},
	543	{
	544	# playlist with youtube embed
	545	'url': 'http://www.vpro.nl/programmas/2doc/2015/education-education.html',
	546	'info_dict': {
	547	'id': 'education-education',
ddb19772	548	'title': 'education education',
574f42d7 S	549	},
574f42d7 S	550	'playlist_count': 2,
b1d79888 S	551	},
	552	{
	553	'url': 'http://www.2doc.nl/documentaires/series/2doc/2015/oktober/de-tegenprestatie.html',
	554	'info_dict': {
	555	'id': 'de-tegenprestatie',
	556	'title': 'De Tegenprestatie',
	557	},
	558	'playlist_count': 2,
	559	}, {
	560	'url': 'http://www.2doc.nl/speel~VARA_101375237~mh17-het-verdriet-van-nederland~.html',
	561	'info_dict': {
	562	'id': 'VARA_101375237',
	563	'ext': 'm4v',
	564	'title': 'MH17: Het verdriet van Nederland',
	565	'description': 'md5:09e1a37c1fdb144621e22479691a9f18',
	566	'upload_date': '20150716',
	567	},
	568	'params': {
	569	# Skip because of m3u8 download
	570	'skip_download': True
	571	},
611ac379	572	}
d0df9292 JMF	573	]
d0df9292 JMF	574
03f32a7e	575
a3d8b381	576	class WNLIE(NPOPlaylistBaseIE):
f9dd86a1	577	IE_NAME = 'wnl'
03f32a7e	578	_VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
a3d8b381 S	579	_PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>'
a3d8b381 S	580	_PLAYLIST_ENTRY_RE = r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>Deel \d+'
03f32a7e	581
a3d8b381	582	_TESTS = [{
03f32a7e S	583	'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
	584	'info_dict': {
	585	'id': 'vandaag-de-dag-6-mei',
	586	'title': 'Vandaag de Dag 6 mei',
	587	},
	588	'playlist_count': 4,
a3d8b381	589	}]
5742c18b S	590
	591
	592	class AndereTijdenIE(NPOPlaylistBaseIE):
f9dd86a1	593	IE_NAME = 'anderetijden'
5742c18b S	594	_VALID_URL = r'https?://(?:www\.)?anderetijden\.nl/programma/(?:[^/]+/)+(?P<id>[^/?#&]+)'
	595	_PLAYLIST_TITLE_RE = r'(?s)<h1[^>]+class=["\'].?\bpage-title\b.?["\'][^>]*>(.+?)</h1>'
	596	_PLAYLIST_ENTRY_RE = r'<figure[^>]+class=["\']episode-container episode-page["\'][^>]+data-prid=["\'](.+?)["\']'
	597
	598	_TESTS = [{
	599	'url': 'http://anderetijden.nl/programma/1/Andere-Tijden/aflevering/676/Duitse-soldaten-over-de-Slag-bij-Arnhem',
	600	'info_dict': {
	601	'id': 'Duitse-soldaten-over-de-Slag-bij-Arnhem',
	602	'title': 'Duitse soldaten over de Slag bij Arnhem',
	603	},
	604	'playlist_count': 3,
	605	}]