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

from __future__ import unicode_literals

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


class NPOBaseIE(SubtitlesInfoExtractor):
    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'] = 'http://e.omroep.nl/tt888/%s' % video_id

        if self._downloader.params.get('listsubtitles', False):
            self._list_available_subtitles(video_id, subtitles)
            return

        subtitles = self.extract_subtitles(video_id, subtitles)

        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()
                if stream_type == 'ss':
                    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,
                    })

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