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

from __future__ import unicode_literals

from .common import InfoExtractor
from ..utils import (
    fix_xml_ampersands,
    parse_duration,
    qualities,
    strip_jsonp,
    unified_strdate,
    url_basename,
)


class NPOBaseIE(InfoExtractor):
    def _get_token(self, video_id):
        token_page = self._download_webpage(
            'http://ida.omroep.nl/npoplayer/i.js',
            video_id, note='Downloading token')
        return self._search_regex(
            r'npoplayer\.token = "(.+?)"', token_page, 'token')


class NPOIE(NPOBaseIE):
    IE_NAME = 'npo.nl'
    _VALID_URL = r'https?://(?:www\.)?npo\.nl/(?!live|radio)[^/]+/[^/]+/(?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',
                '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',
                'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
                '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': 'wmv',
                'title': 'De nieuwe mens - Deel 1',
                'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
                'duration': 4680,
            },
            'params': {
                # mplayer mms download
                'skip_download': True,
            }
        },
        # non asf in streams
        {
            'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
            'md5': 'b3da13de374cbe2d5332a7e910bef97f',
            'info_dict': {
                'id': 'WO_NOS_762771',
                'ext': 'mp4',
                'title': 'Hoe gaat Europa verder na Parijs?',
            },
        },
    ]

    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/aflevering/%s' % video_id,
            video_id,
            # We have to remove the javascript callback
            transform_source=strip_jsonp,
        )

        token = self._get_token(video_id)

        formats = []

        pubopties = metadata.get('pubopties')
        if pubopties:
            quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
            for format_id in pubopties:
                format_info = self._download_json(
                    'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s'
                    % (video_id, format_id, token),
                    video_id, 'Downloading %s JSON' % format_id)
                if format_info.get('error_code', 0) or format_info.get('errorcode', 0):
                    continue
                streams = format_info.get('streams')
                if streams:
                    video_info = self._download_json(
                        streams[0] + '&type=json',
                        video_id, 'Downloading %s stream JSON' % format_id)
                else:
                    video_info = format_info
                video_url = video_info.get('url')
                if not video_url:
                    continue
                if format_id == 'adaptive':
                    formats.extend(self._extract_m3u8_formats(video_url, video_id))
                else:
                    formats.append({
                        'url': video_url,
                        'format_id': format_id,
                        'quality': quality(format_id),
                    })

        streams = metadata.get('streams')
        if streams:
            for i, stream in enumerate(streams):
                stream_url = stream.get('url')
                if not stream_url:
                    continue
                if '.asf' not in stream_url:
                    formats.append({
                        'url': stream_url,
                        'quality': stream.get('kwaliteit'),
                    })
                    continue
                asx = self._download_xml(
                    stream_url, video_id,
                    'Downloading stream %d ASX playlist' % i,
                    transform_source=fix_xml_ampersands)
                ref = asx.find('./ENTRY/Ref')
                if ref is None:
                    continue
                video_url = ref.get('href')
                if not video_url:
                    continue
                formats.append({
                    'url': video_url,
                    'ext': stream.get('formaat', 'asf'),
                    'quality': stream.get('kwaliteit'),
                })

        self._sort_formats(formats)

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

        return {
            'id': video_id,
            'title': metadata['titel'],
            'description': metadata['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,
        }


class NPOLiveIE(NPOBaseIE):
    IE_NAME = 'npo.nl:live'
    _VALID_URL = r'https?://(?:www\.)?npo\.nl/live/(?P<id>.+)'

    _TEST = {
        'url': 'http://www.npo.nl/live/npo-1',
        'info_dict': {
            'id': 'LI_NEDERLAND1_136692',
            'display_id': 'npo-1',
            'ext': 'mp4',
            'title': 're:^Nederland 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
            'description': 'Livestream',
            'is_live': True,
        },
        'params': {
            'skip_download': True,
        }
    }

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

        webpage = self._download_webpage(url, display_id)

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

        metadata = self._download_json(
            'http://e.omroep.nl/metadata/%s' % live_id,
            display_id, transform_source=strip_jsonp)

        token = self._get_token(display_id)

        formats = []

        streams = metadata.get('streams')
        if streams:
            for stream in streams:
                stream_type = stream.get('type').lower()
                # smooth streaming is not supported
                if stream_type in ['ss', 'ms']:
                    continue
                stream_info = self._download_json(
                    'http://ida.omroep.nl/aapi/?stream=%s&token=%s&type=jsonp'
                    % (stream.get('url'), token),
                    display_id, 'Downloading %s JSON' % stream_type)
                if stream_info.get('error_code', 0) or stream_info.get('errorcode', 0):
                    continue
                stream_url = self._download_json(
                    stream_info['stream'], display_id,
                    'Downloading %s URL' % stream_type,
                    transform_source=strip_jsonp)
                if stream_type == 'hds':
                    f4m_formats = self._extract_f4m_formats(stream_url, display_id)
                    # 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, display_id, 'mp4'))
                else:
                    formats.append({
                        'url': stream_url,
                        'preference': -10,
                    })

        self._sort_formats(formats)

        return {
            'id': live_id,
            'display_id': display_id,
            'title': self._live_title(metadata['titel']),
            'description': metadata['info'],
            'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
            'formats': formats,
            'is_live': True,
        }


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 TegenlichtVproIE(NPOIE):
    IE_NAME = 'tegenlicht.vpro.nl'
    _VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?'

    _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': 'Tegenlicht',
                'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
                'upload_date': '20130225',
            },
        },
    ]

    def _real_extract(self, url):
        name = url_basename(url)
        webpage = self._download_webpage(url, name)
        urn = self._html_search_meta('mediaurn', webpage)
        info_page = self._download_json(
            'http://rs.vpro.nl/v2/api/media/%s.json' % urn, name)
        return self._get_info(info_page['mid'])
Commit	Line	Data
331ae266 JMF	1	from __future__ import unicode_literals
331ae266 JMF	2
171ca612	3	from .common import InfoExtractor
331ae266	4	from ..utils import (
5c4a81d9	5	fix_xml_ampersands,
944a3de2	6	parse_duration,
c9ea760e	7	qualities,
609a61e3	8	strip_jsonp,
5c4a81d9	9	unified_strdate,
d0df9292	10	url_basename,
331ae266 JMF	11	)
	12
	13
b9b42f2e	14	class NPOBaseIE(InfoExtractor):
04e0bac2 S	15	def _get_token(self, video_id):
	16	token_page = self._download_webpage(
	17	'http://ida.omroep.nl/npoplayer/i.js',
	18	video_id, note='Downloading token')
	19	return self._search_regex(
	20	r'npoplayer\.token = "(.+?)"', token_page, 'token')
	21
	22
	23	class NPOIE(NPOBaseIE):
331ae266	24	IE_NAME = 'npo.nl'
171ca612	25	_VALID_URL = r'https?://(?:www\.)?npo\.nl/(?!live\|radio)[^/]+/[^/]+/(?P<id>[^/?]+)'
331ae266	26
944a3de2 S	27	_TESTS = [
	28	{
	29	'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
	30	'md5': '4b3f9c429157ec4775f2c9cb7b911016',
	31	'info_dict': {
	32	'id': 'VPWON_1220719',
	33	'ext': 'm4v',
	34	'title': 'Nieuwsuur',
	35	'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
	36	'upload_date': '20140622',
	37	},
331ae266	38	},
944a3de2 S	39	{
	40	'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
	41	'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
	42	'info_dict': {
	43	'id': 'VARA_101191800',
	44	'ext': 'm4v',
	45	'title': 'De Mega Mike & Mega Thomas show',
	46	'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
	47	'upload_date': '20090227',
	48	'duration': 2400,
	49	},
	50	},
	51	{
	52	'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
	53	'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
	54	'info_dict': {
	55	'id': 'VPWON_1169289',
	56	'ext': 'm4v',
	57	'title': 'Tegenlicht',
	58	'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
	59	'upload_date': '20130225',
	60	'duration': 3000,
	61	},
1ff30d7b S	62	},
	63	{
	64	'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
	65	'info_dict': {
	66	'id': 'WO_VPRO_043706',
	67	'ext': 'wmv',
	68	'title': 'De nieuwe mens - Deel 1',
	69	'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
	70	'duration': 4680,
	71	},
	72	'params': {
	73	# mplayer mms download
	74	'skip_download': True,
	75	}
	76	},
c85f3683 S	77	# non asf in streams
	78	{
	79	'url': 'http://www.npo.nl/hoe-gaat-europa-verder-na-parijs/10-01-2015/WO_NOS_762771',
	80	'md5': 'b3da13de374cbe2d5332a7e910bef97f',
	81	'info_dict': {
	82	'id': 'WO_NOS_762771',
	83	'ext': 'mp4',
	84	'title': 'Hoe gaat Europa verder na Parijs?',
	85	},
	86	},
944a3de2	87	]
331ae266 JMF	88
331ae266 JMF	89	def _real_extract(self, url):
04e0bac2	90	video_id = self._match_id(url)
d0df9292	91	return self._get_info(video_id)
331ae266	92
d0df9292	93	def _get_info(self, video_id):
331ae266 JMF	94	metadata = self._download_json(
	95	'http://e.omroep.nl/metadata/aflevering/%s' % video_id,
	96	video_id,
	97	# We have to remove the javascript callback
609a61e3	98	transform_source=strip_jsonp,
331ae266	99	)
04e0bac2 S	100
04e0bac2 S	101	token = self._get_token(video_id)
331ae266	102
c9ea760e	103	formats = []
1ff30d7b S	104
	105	pubopties = metadata.get('pubopties')
	106	if pubopties:
	107	quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
	108	for format_id in pubopties:
	109	format_info = self._download_json(
	110	'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s'
	111	% (video_id, format_id, token),
	112	video_id, 'Downloading %s JSON' % format_id)
	113	if format_info.get('error_code', 0) or format_info.get('errorcode', 0):
	114	continue
	115	streams = format_info.get('streams')
	116	if streams:
	117	video_info = self._download_json(
	118	streams[0] + '&type=json',
	119	video_id, 'Downloading %s stream JSON' % format_id)
	120	else:
	121	video_info = format_info
	122	video_url = video_info.get('url')
	123	if not video_url:
	124	continue
	125	if format_id == 'adaptive':
	126	formats.extend(self._extract_m3u8_formats(video_url, video_id))
	127	else:
	128	formats.append({
	129	'url': video_url,
	130	'format_id': format_id,
	131	'quality': quality(format_id),
	132	})
	133
	134	streams = metadata.get('streams')
	135	if streams:
	136	for i, stream in enumerate(streams):
	137	stream_url = stream.get('url')
	138	if not stream_url:
	139	continue
5c4a81d9	140	if '.asf' not in stream_url:
a0977064 S	141	formats.append({
	142	'url': stream_url,
	143	'quality': stream.get('kwaliteit'),
	144	})
	145	continue
1ff30d7b S	146	asx = self._download_xml(
	147	stream_url, video_id,
	148	'Downloading stream %d ASX playlist' % i,
	149	transform_source=fix_xml_ampersands)
	150	ref = asx.find('./ENTRY/Ref')
	151	if ref is None:
	152	continue
	153	video_url = ref.get('href')
	154	if not video_url:
	155	continue
c9ea760e	156	formats.append({
944a3de2	157	'url': video_url,
1ff30d7b S	158	'ext': stream.get('formaat', 'asf'),
1ff30d7b S	159	'quality': stream.get('kwaliteit'),
c9ea760e	160	})
1ff30d7b	161
9e91449c	162	self._sort_formats(formats)
25e5ebf3	163
9e91449c S	164	subtitles = {}
9e91449c S	165	if metadata.get('tt888') == 'ja':
b9b42f2e JMF	166	subtitles['nl'] = [{
	167	'ext': 'vtt',
	168	'url': 'http://e.omroep.nl/tt888/%s' % video_id,
	169	}]
331ae266 JMF	170
	171	return {
	172	'id': video_id,
	173	'title': metadata['titel'],
331ae266	174	'description': metadata['info'],
944a3de2 S	175	'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
	176	'upload_date': unified_strdate(metadata.get('gidsdatum')),
	177	'duration': parse_duration(metadata.get('tijdsduur')),
c9ea760e	178	'formats': formats,
25e5ebf3	179	'subtitles': subtitles,
331ae266	180	}
d0df9292 JMF	181
d0df9292 JMF	182
04e0bac2 S	183	class NPOLiveIE(NPOBaseIE):
04e0bac2 S	184	IE_NAME = 'npo.nl:live'
171ca612	185	_VALID_URL = r'https?://(?:www\.)?npo\.nl/live/(?P<id>.+)'
04e0bac2 S	186
	187	_TEST = {
	188	'url': 'http://www.npo.nl/live/npo-1',
	189	'info_dict': {
	190	'id': 'LI_NEDERLAND1_136692',
	191	'display_id': 'npo-1',
	192	'ext': 'mp4',
	193	'title': 're:^Nederland 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
	194	'description': 'Livestream',
	195	'is_live': True,
	196	},
	197	'params': {
	198	'skip_download': True,
	199	}
	200	}
	201
	202	def _real_extract(self, url):
	203	display_id = self._match_id(url)
	204
	205	webpage = self._download_webpage(url, display_id)
	206
	207	live_id = self._search_regex(
	208	r'data-prid="([^"]+)"', webpage, 'live id')
	209
	210	metadata = self._download_json(
	211	'http://e.omroep.nl/metadata/%s' % live_id,
	212	display_id, transform_source=strip_jsonp)
	213
	214	token = self._get_token(display_id)
	215
	216	formats = []
	217
	218	streams = metadata.get('streams')
	219	if streams:
	220	for stream in streams:
	221	stream_type = stream.get('type').lower()
32aaeca7 S	222	# smooth streaming is not supported
32aaeca7 S	223	if stream_type in ['ss', 'ms']:
04e0bac2 S	224	continue
	225	stream_info = self._download_json(
	226	'http://ida.omroep.nl/aapi/?stream=%s&token=%s&type=jsonp'
	227	% (stream.get('url'), token),
	228	display_id, 'Downloading %s JSON' % stream_type)
	229	if stream_info.get('error_code', 0) or stream_info.get('errorcode', 0):
	230	continue
	231	stream_url = self._download_json(
	232	stream_info['stream'], display_id,
	233	'Downloading %s URL' % stream_type,
	234	transform_source=strip_jsonp)
	235	if stream_type == 'hds':
	236	f4m_formats = self._extract_f4m_formats(stream_url, display_id)
	237	# f4m downloader downloads only piece of live stream
	238	for f4m_format in f4m_formats:
	239	f4m_format['preference'] = -1
	240	formats.extend(f4m_formats)
	241	elif stream_type == 'hls':
	242	formats.extend(self._extract_m3u8_formats(stream_url, display_id, 'mp4'))
	243	else:
	244	formats.append({
	245	'url': stream_url,
32aaeca7	246	'preference': -10,
04e0bac2 S	247	})
	248
	249	self._sort_formats(formats)
	250
	251	return {
	252	'id': live_id,
	253	'display_id': display_id,
	254	'title': self._live_title(metadata['titel']),
	255	'description': metadata['info'],
	256	'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
	257	'formats': formats,
	258	'is_live': True,
	259	}
	260
	261
171ca612 S	262	class NPORadioIE(InfoExtractor):
	263	IE_NAME = 'npo.nl:radio'
	264	_VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/(?P<id>[^/]+)/?$'
	265
	266	_TEST = {
	267	'url': 'http://www.npo.nl/radio/radio-1',
	268	'info_dict': {
	269	'id': 'radio-1',
	270	'ext': 'mp3',
	271	'title': 're:^NPO Radio 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
	272	'is_live': True,
	273	},
	274	'params': {
	275	'skip_download': True,
	276	}
	277	}
	278
	279	@staticmethod
	280	def _html_get_attribute_regex(attribute):
	281	return r'{0}\s=\s\'([^\']+)\''.format(attribute)
	282
	283	def _real_extract(self, url):
	284	video_id = self._match_id(url)
	285
	286	webpage = self._download_webpage(url, video_id)
	287
	288	title = self._html_search_regex(
	289	self._html_get_attribute_regex('data-channel'), webpage, 'title')
	290
	291	stream = self._parse_json(
	292	self._html_search_regex(self._html_get_attribute_regex('data-streams'), webpage, 'data-streams'),
	293	video_id)
	294
	295	codec = stream.get('codec')
	296
	297	return {
	298	'id': video_id,
	299	'url': stream['url'],
	300	'title': self._live_title(title),
	301	'acodec': codec,
	302	'ext': codec,
	303	'is_live': True,
	304	}
	305
	306
	307	class NPORadioFragmentIE(InfoExtractor):
	308	IE_NAME = 'npo.nl:radio:fragment'
	309	_VALID_URL = r'https?://(?:www\.)?npo\.nl/radio/[^/]+/fragment/(?P<id>\d+)'
	310
	311	_TEST = {
	312	'url': 'http://www.npo.nl/radio/radio-5/fragment/174356',
	313	'md5': 'dd8cc470dad764d0fdc70a9a1e2d18c2',
	314	'info_dict': {
	315	'id': '174356',
	316	'ext': 'mp3',
	317	'title': 'Jubileumconcert Willeke Alberti',
	318	},
	319	}
	320
	321	def _real_extract(self, url):
	322	audio_id = self._match_id(url)
	323
	324	webpage = self._download_webpage(url, audio_id)
	325
326	title = self._html_search_regex(
327	r'href="/radio/[^/]+/fragment/%s" title="([^"]+)"' % audio_id,
328	webpage, 'title')
329
330	audio_url = self._search_regex(
331	r"data-streams='([^']+)'", webpage, 'audio url')
332
333	return {
334	'id': audio_id,
335	'url': audio_url,
336	'title': title,
337	}
338
339
d0df9292 JMF	340	class TegenlichtVproIE(NPOIE):
	341	IE_NAME = 'tegenlicht.vpro.nl'
	342	_VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?'
	343
	344	_TESTS = [
	345	{
	346	'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
	347	'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
	348	'info_dict': {
	349	'id': 'VPWON_1169289',
	350	'ext': 'm4v',
	351	'title': 'Tegenlicht',
	352	'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
	353	'upload_date': '20130225',
	354	},
	355	},
	356	]
	357
	358	def _real_extract(self, url):
	359	name = url_basename(url)
	360	webpage = self._download_webpage(url, name)
	361	urn = self._html_search_meta('mediaurn', webpage)
	362	info_page = self._download_json(
	363	'http://rs.vpro.nl/v2/api/media/%s.json' % urn, name)
	364	return self._get_info(info_page['mid'])