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

from __future__ import unicode_literals

import re

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


class NPOIE(InfoExtractor):
    IE_NAME = 'npo.nl'
    _VALID_URL = r'https?://www\.npo\.nl/[^/]+/[^/]+/(?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,
            }
        },
    ]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        video_id = mobj.group('id')
        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_page = self._download_webpage(
            'http://ida.omroep.nl/npoplayer/i.js',
            video_id,
            note='Downloading token'
        )
        token = self._search_regex(r'npoplayer\.token = "(.+?)"', token_page, 'token')

        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
                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)

        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,
        }


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
	2
	3	import re
	4
	5	from .common import InfoExtractor
	6	from ..utils import (
	7	unified_strdate,
944a3de2	8	parse_duration,
c9ea760e	9	qualities,
609a61e3	10	strip_jsonp,
d0df9292	11	url_basename,
1ff30d7b	12	fix_xml_ampersands,
331ae266 JMF	13	)
	14
	15
	16	class NPOIE(InfoExtractor):
	17	IE_NAME = 'npo.nl'
	18	_VALID_URL = r'https?://www\.npo\.nl/[^/]+/[^/]+/(?P<id>[^/?]+)'
	19
944a3de2 S	20	_TESTS = [
	21	{
	22	'url': 'http://www.npo.nl/nieuwsuur/22-06-2014/VPWON_1220719',
	23	'md5': '4b3f9c429157ec4775f2c9cb7b911016',
	24	'info_dict': {
	25	'id': 'VPWON_1220719',
	26	'ext': 'm4v',
	27	'title': 'Nieuwsuur',
	28	'description': 'Dagelijks tussen tien en elf: nieuws, sport en achtergronden.',
	29	'upload_date': '20140622',
	30	},
331ae266	31	},
944a3de2 S	32	{
	33	'url': 'http://www.npo.nl/de-mega-mike-mega-thomas-show/27-02-2009/VARA_101191800',
	34	'md5': 'da50a5787dbfc1603c4ad80f31c5120b',
	35	'info_dict': {
	36	'id': 'VARA_101191800',
	37	'ext': 'm4v',
	38	'title': 'De Mega Mike & Mega Thomas show',
	39	'description': 'md5:3b74c97fc9d6901d5a665aac0e5400f4',
	40	'upload_date': '20090227',
	41	'duration': 2400,
	42	},
	43	},
	44	{
	45	'url': 'http://www.npo.nl/tegenlicht/25-02-2013/VPWON_1169289',
	46	'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
	47	'info_dict': {
	48	'id': 'VPWON_1169289',
	49	'ext': 'm4v',
	50	'title': 'Tegenlicht',
	51	'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
	52	'upload_date': '20130225',
	53	'duration': 3000,
	54	},
1ff30d7b S	55	},
	56	{
	57	'url': 'http://www.npo.nl/de-nieuwe-mens-deel-1/21-07-2010/WO_VPRO_043706',
	58	'info_dict': {
	59	'id': 'WO_VPRO_043706',
	60	'ext': 'wmv',
	61	'title': 'De nieuwe mens - Deel 1',
	62	'description': 'md5:518ae51ba1293ffb80d8d8ce90b74e4b',
	63	'duration': 4680,
	64	},
	65	'params': {
	66	# mplayer mms download
	67	'skip_download': True,
	68	}
	69	},
944a3de2	70	]
331ae266 JMF	71
	72	def _real_extract(self, url):
	73	mobj = re.match(self._VALID_URL, url)
	74	video_id = mobj.group('id')
d0df9292	75	return self._get_info(video_id)
331ae266	76
d0df9292	77	def _get_info(self, video_id):
331ae266 JMF	78	metadata = self._download_json(
	79	'http://e.omroep.nl/metadata/aflevering/%s' % video_id,
	80	video_id,
	81	# We have to remove the javascript callback
609a61e3	82	transform_source=strip_jsonp,
331ae266 JMF	83	)
	84	token_page = self._download_webpage(
	85	'http://ida.omroep.nl/npoplayer/i.js',
	86	video_id,
	87	note='Downloading token'
	88	)
c9ea760e	89	token = self._search_regex(r'npoplayer\.token = "(.+?)"', token_page, 'token')
331ae266	90
c9ea760e	91	formats = []
1ff30d7b S	92
	93	pubopties = metadata.get('pubopties')
	94	if pubopties:
	95	quality = qualities(['adaptive', 'wmv_sb', 'h264_sb', 'wmv_bb', 'h264_bb', 'wvc1_std', 'h264_std'])
	96	for format_id in pubopties:
	97	format_info = self._download_json(
	98	'http://ida.omroep.nl/odi/?prid=%s&puboptions=%s&adaptive=yes&token=%s'
	99	% (video_id, format_id, token),
	100	video_id, 'Downloading %s JSON' % format_id)
	101	if format_info.get('error_code', 0) or format_info.get('errorcode', 0):
	102	continue
	103	streams = format_info.get('streams')
	104	if streams:
	105	video_info = self._download_json(
	106	streams[0] + '&type=json',
	107	video_id, 'Downloading %s stream JSON' % format_id)
	108	else:
	109	video_info = format_info
	110	video_url = video_info.get('url')
	111	if not video_url:
	112	continue
	113	if format_id == 'adaptive':
	114	formats.extend(self._extract_m3u8_formats(video_url, video_id))
	115	else:
	116	formats.append({
	117	'url': video_url,
	118	'format_id': format_id,
	119	'quality': quality(format_id),
	120	})
	121
	122	streams = metadata.get('streams')
	123	if streams:
	124	for i, stream in enumerate(streams):
	125	stream_url = stream.get('url')
	126	if not stream_url:
	127	continue
	128	asx = self._download_xml(
	129	stream_url, video_id,
	130	'Downloading stream %d ASX playlist' % i,
	131	transform_source=fix_xml_ampersands)
	132	ref = asx.find('./ENTRY/Ref')
	133	if ref is None:
	134	continue
	135	video_url = ref.get('href')
	136	if not video_url:
	137	continue
c9ea760e	138	formats.append({
944a3de2	139	'url': video_url,
1ff30d7b S	140	'ext': stream.get('formaat', 'asf'),
1ff30d7b S	141	'quality': stream.get('kwaliteit'),
c9ea760e	142	})
1ff30d7b	143
c9ea760e	144	self._sort_formats(formats)
331ae266 JMF	145
	146	return {
	147	'id': video_id,
	148	'title': metadata['titel'],
331ae266	149	'description': metadata['info'],
944a3de2 S	150	'thumbnail': metadata.get('images', [{'url': None}])[-1]['url'],
	151	'upload_date': unified_strdate(metadata.get('gidsdatum')),
	152	'duration': parse_duration(metadata.get('tijdsduur')),
c9ea760e	153	'formats': formats,
331ae266	154	}
d0df9292 JMF	155
	156
	157	class TegenlichtVproIE(NPOIE):
	158	IE_NAME = 'tegenlicht.vpro.nl'
	159	_VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?'
	160
	161	_TESTS = [
	162	{
	163	'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
	164	'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
	165	'info_dict': {
	166	'id': 'VPWON_1169289',
	167	'ext': 'm4v',
	168	'title': 'Tegenlicht',
	169	'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
	170	'upload_date': '20130225',
	171	},
	172	},
	173	]
	174
	175	def _real_extract(self, url):
	176	name = url_basename(url)
	177	webpage = self._download_webpage(url, name)
	178	urn = self._html_search_meta('mediaurn', webpage)
	179	info_page = self._download_json(
	180	'http://rs.vpro.nl/v2/api/media/%s.json' % urn, name)
	181	return self._get_info(info_page['mid'])