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

# encoding: utf-8

from __future__ import unicode_literals

import re
import json

from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
    clean_html,
    ExtractorError,
    int_or_none,
    parse_duration,
    determine_ext,
)
from .dailymotion import DailymotionCloudIE


class FranceTVBaseInfoExtractor(InfoExtractor):
    def _extract_video(self, video_id, catalogue):
        info = self._download_json(
            'http://webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=%s&catalogue=%s'
            % (video_id, catalogue),
            video_id, 'Downloading video JSON')

        if info.get('status') == 'NOK':
            raise ExtractorError(
                '%s returned error: %s' % (self.IE_NAME, info['message']), expected=True)
        allowed_countries = info['videos'][0].get('geoblocage')
        if allowed_countries:
            georestricted = True
            geo_info = self._download_json(
                'http://geo.francetv.fr/ws/edgescape.json', video_id,
                'Downloading geo restriction info')
            country = geo_info['reponse']['geo_info']['country_code']
            if country not in allowed_countries:
                raise ExtractorError(
                    'The video is not available from your location',
                    expected=True)
        else:
            georestricted = False

        formats = []
        for video in info['videos']:
            if video['statut'] != 'ONLINE':
                continue
            video_url = video['url']
            if not video_url:
                continue
            format_id = video['format']
            ext = determine_ext(video_url)
            if ext == 'f4m':
                if georestricted:
                    # See https://github.com/rg3/youtube-dl/issues/3963
                    # m3u8 urls work fine
                    continue
                f4m_url = self._download_webpage(
                    'http://hdfauth.francetv.fr/esi/TA?url=%s' % video_url,
                    video_id, 'Downloading f4m manifest token', fatal=False)
                if f4m_url:
                    formats.extend(self._extract_f4m_formats(
                        f4m_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id, 1, format_id))
            elif ext == 'm3u8':
                formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4', m3u8_id=format_id))
            elif video_url.startswith('rtmp'):
                formats.append({
                    'url': video_url,
                    'format_id': 'rtmp-%s' % format_id,
                    'ext': 'flv',
                    'preference': 1,
                })
            else:
                formats.append({
                    'url': video_url,
                    'format_id': format_id,
                    'preference': -1,
                })
        self._sort_formats(formats)

        return {
            'id': video_id,
            'title': info['titre'],
            'description': clean_html(info['synopsis']),
            'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
            'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
            'timestamp': int_or_none(info['diffusion']['timestamp']),
            'formats': formats,
        }


class PluzzIE(FranceTVBaseInfoExtractor):
    IE_NAME = 'pluzz.francetv.fr'
    _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'

    # Can't use tests, videos expire in 7 days

    def _real_extract(self, url):
        title = re.match(self._VALID_URL, url).group(1)
        webpage = self._download_webpage(url, title)
        video_id = self._search_regex(
            r'data-diffusion="(\d+)"', webpage, 'ID')
        return self._extract_video(video_id, 'Pluzz')


class FranceTvInfoIE(FranceTVBaseInfoExtractor):
    IE_NAME = 'francetvinfo.fr'
    _VALID_URL = r'https?://(?:www|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'

    _TESTS = [{
        'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
        'info_dict': {
            'id': '84981923',
            'ext': 'flv',
            'title': 'Soir 3',
            'upload_date': '20130826',
            'timestamp': 1377548400,
        },
    }, {
        'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
        'info_dict': {
            'id': 'EV_20019',
            'ext': 'mp4',
            'title': 'Débat des candidats à la Commission européenne',
            'description': 'Débat des candidats à la Commission européenne',
        },
        'params': {
            'skip_download': 'HLS (reqires ffmpeg)'
        },
        'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
    }, {
        'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
        'md5': 'f485bda6e185e7d15dbc69b72bae993e',
        'info_dict': {
            'id': '556e03339473995ee145930c',
            'ext': 'mp4',
            'title': 'Les entreprises familiales : le secret de la réussite',
            'thumbnail': 're:^https?://.*\.jpe?g$',
        }
    }]

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        page_title = mobj.group('title')
        webpage = self._download_webpage(url, page_title)

        dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
        if dmcloud_url:
            return self.url_result(dmcloud_url, 'DailymotionCloud')

        video_id, catalogue = self._search_regex(
            r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
        return self._extract_video(video_id, catalogue)


class FranceTVIE(FranceTVBaseInfoExtractor):
    IE_NAME = 'francetv'
    IE_DESC = 'France 2, 3, 4, 5 and Ô'
    _VALID_URL = r'''(?x)
                    https?://
                        (?:
                            (?:www\.)?france[2345o]\.fr/
                                (?:
                                    emissions/[^/]+/(?:videos|diffusions)|
                                    emission/[^/]+|
                                    videos|
                                    jt
                                )
                            /|
                            embed\.francetv\.fr/\?ue=
                        )
                        (?P<id>[^/?]+)
                    '''

    _TESTS = [
        # france2
        {
            'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
            'md5': 'c03fc87cb85429ffd55df32b9fc05523',
            'info_dict': {
                'id': '109169362',
                'ext': 'flv',
                'title': '13h15, le dimanche...',
                'description': 'md5:9a0932bb465f22d377a449be9d1a0ff7',
                'upload_date': '20140914',
                'timestamp': 1410693600,
            },
        },
        # france3
        {
            'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
            'md5': '679bb8f8921f8623bd658fa2f8364da0',
            'info_dict': {
                'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
                'ext': 'mp4',
                'title': 'Le scandale du prix des médicaments',
                'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
                'upload_date': '20131113',
                'timestamp': 1384380000,
            },
        },
        # france4
        {
            'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
            'md5': 'a182bf8d2c43d88d46ec48fbdd260c1c',
            'info_dict': {
                'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
                'ext': 'mp4',
                'title': 'Hero Corp Making of - Extrait 1',
                'description': 'md5:c87d54871b1790679aec1197e73d650a',
                'upload_date': '20131106',
                'timestamp': 1383766500,
            },
        },
        # france5
        {
            'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
            'md5': '78f0f4064f9074438e660785bbf2c5d9',
            'info_dict': {
                'id': '108961659',
                'ext': 'flv',
                'title': 'C à dire ?!',
                'description': 'md5:1a4aeab476eb657bf57c4ff122129f81',
                'upload_date': '20140915',
                'timestamp': 1410795000,
            },
        },
        # franceo
        {
            'url': 'http://www.franceo.fr/jt/info-soir/18-07-2015',
            'md5': '47d5816d3b24351cdce512ad7ab31da8',
            'info_dict': {
                'id': '125377621',
                'ext': 'flv',
                'title': 'Infô soir',
                'description': 'md5:01b8c6915a3d93d8bbbd692651714309',
                'upload_date': '20150718',
                'timestamp': 1437241200,
                'duration': 414,
            },
        },
        {
            # francetv embed
            'url': 'http://embed.francetv.fr/?ue=8d7d3da1e3047c42ade5a5d7dfd3fc87',
            'info_dict': {
                'id': 'EV_30231',
                'ext': 'flv',
                'title': 'Alcaline, le concert avec Calogero',
                'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
                'upload_date': '20150226',
                'timestamp': 1424989860,
                'duration': 5400,
            },
        },
        {
            'url': 'http://www.france4.fr/emission/highlander/diffusion-du-17-07-2015-04h05',
            'only_matching': True,
        },
        {
            'url': 'http://www.franceo.fr/videos/125377617',
            'only_matching': True,
        }
    ]

    def _real_extract(self, url):
        video_id = self._match_id(url)
        webpage = self._download_webpage(url, video_id)
        video_id, catalogue = self._html_search_regex(
            r'href="http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
            webpage, 'video ID').split('@')
        return self._extract_video(video_id, catalogue)


class GenerationQuoiIE(InfoExtractor):
    IE_NAME = 'france2.fr:generation-quoi'
    _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<id>[^/?#]+)'

    _TEST = {
        'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
        'info_dict': {
            'id': 'k7FJX8VBcvvLmX4wA5Q',
            'ext': 'mp4',
            'title': 'Génération Quoi - Garde à Vous',
            'uploader': 'Génération Quoi',
        },
        'params': {
            # It uses Dailymotion
            'skip_download': True,
        },
    }

    def _real_extract(self, url):
        display_id = self._match_id(url)
        info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % display_id)
        info_json = self._download_webpage(info_url, display_id)
        info = json.loads(info_json)
        return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
                               ie='Dailymotion')


class CultureboxIE(FranceTVBaseInfoExtractor):
    IE_NAME = 'culturebox.francetvinfo.fr'
    _VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?|$)'

    _TEST = {
        'url': 'http://culturebox.francetvinfo.fr/live/musique/musique-classique/le-livre-vermeil-de-montserrat-a-la-cathedrale-delne-214511',
        'md5': '9b88dc156781c4dbebd4c3e066e0b1d6',
        'info_dict': {
            'id': 'EV_50111',
            'ext': 'flv',
            'title': "Le Livre Vermeil de Montserrat à la Cathédrale d'Elne",
            'description': 'md5:f8a4ad202e8fe533e2c493cc12e739d9',
            'upload_date': '20150320',
            'timestamp': 1426892400,
            'duration': 2760.9,
        },
    }

    def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url)
        name = mobj.group('name')

        webpage = self._download_webpage(url, name)

        if ">Ce live n'est plus disponible en replay<" in webpage:
            raise ExtractorError('Video %s is not available' % name, expected=True)

        video_id, catalogue = self._search_regex(
            r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')

        return self._extract_video(video_id, catalogue)
Commit	Line	Data
5d8afe69	1	# encoding: utf-8
3c1b4669 PH	2
	3	from __future__ import unicode_literals
	4
5d8afe69	5	import re
5b333c1c	6	import json
5d8afe69 PR	7
5d8afe69 PR	8	from .common import InfoExtractor
1d18e26e	9	from ..compat import compat_urlparse
1cc79574	10	from ..utils import (
64892c0b	11	clean_html,
1cc79574	12	ExtractorError,
64892c0b	13	int_or_none,
1cc79574	14	parse_duration,
bc03228a	15	determine_ext,
5d8afe69	16	)
6f96e308	17	from .dailymotion import DailymotionCloudIE
5d8afe69 PR	18
5d8afe69 PR	19
648d25d4	20	class FranceTVBaseInfoExtractor(InfoExtractor):
64892c0b S	21	def _extract_video(self, video_id, catalogue):
	22	info = self._download_json(
	23	'http://webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=%s&catalogue=%s'
	24	% (video_id, catalogue),
	25	video_id, 'Downloading video JSON')
	26
	27	if info.get('status') == 'NOK':
	28	raise ExtractorError(
	29	'%s returned error: %s' % (self.IE_NAME, info['message']), expected=True)
00e9d396 JMF	30	allowed_countries = info['videos'][0].get('geoblocage')
	31	if allowed_countries:
	32	georestricted = True
	33	geo_info = self._download_json(
	34	'http://geo.francetv.fr/ws/edgescape.json', video_id,
	35	'Downloading geo restriction info')
	36	country = geo_info['reponse']['geo_info']['country_code']
	37	if country not in allowed_countries:
	38	raise ExtractorError(
	39	'The video is not available from your location',
	40	expected=True)
	41	else:
	42	georestricted = False
	43
64892c0b S	44	formats = []
	45	for video in info['videos']:
	46	if video['statut'] != 'ONLINE':
	47	continue
	48	video_url = video['url']
	49	if not video_url:
	50	continue
	51	format_id = video['format']
bc03228a S	52	ext = determine_ext(video_url)
bc03228a S	53	if ext == 'f4m':
00e9d396 JMF	54	if georestricted:
	55	# See https://github.com/rg3/youtube-dl/issues/3963
	56	# m3u8 urls work fine
	57	continue
64892c0b	58	f4m_url = self._download_webpage(
ecdbe09e	59	'http://hdfauth.francetv.fr/esi/TA?url=%s' % video_url,
64892c0b S	60	video_id, 'Downloading f4m manifest token', fatal=False)
64892c0b S	61	if f4m_url:
632cbb8e S	62	formats.extend(self._extract_f4m_formats(
632cbb8e S	63	f4m_url + '&hdcore=3.7.0&plugin=aasp-3.7.0.39.44', video_id, 1, format_id))
bc03228a S	64	elif ext == 'm3u8':
bc03228a S	65	formats.extend(self._extract_m3u8_formats(video_url, video_id, 'mp4', m3u8_id=format_id))
64892c0b S	66	elif video_url.startswith('rtmp'):
	67	formats.append({
	68	'url': video_url,
	69	'format_id': 'rtmp-%s' % format_id,
	70	'ext': 'flv',
	71	'preference': 1,
	72	})
	73	else:
	74	formats.append({
	75	'url': video_url,
	76	'format_id': format_id,
2399535f	77	'preference': -1,
64892c0b S	78	})
64892c0b S	79	self._sort_formats(formats)
648d25d4	80
7e8d73c1 JMF	81	return {
7e8d73c1 JMF	82	'id': video_id,
64892c0b S	83	'title': info['titre'],
	84	'description': clean_html(info['synopsis']),
	85	'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', info['image']),
5705ee6e	86	'duration': int_or_none(info.get('real_duration')) or parse_duration(info['duree']),
64892c0b	87	'timestamp': int_or_none(info['diffusion']['timestamp']),
7e8d73c1	88	'formats': formats,
7e8d73c1	89	}
648d25d4 JMF	90
	91
	92	class PluzzIE(FranceTVBaseInfoExtractor):
3c1b4669	93	IE_NAME = 'pluzz.francetv.fr'
5d8afe69 PR	94	_VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
5d8afe69 PR	95
5d13df79	96	# Can't use tests, videos expire in 7 days
5d8afe69 PR	97
	98	def _real_extract(self, url):
	99	title = re.match(self._VALID_URL, url).group(1)
	100	webpage = self._download_webpage(url, title)
	101	video_id = self._search_regex(
	102	r'data-diffusion="(\d+)"', webpage, 'ID')
64892c0b	103	return self._extract_video(video_id, 'Pluzz')
5d8afe69	104
5d8afe69	105
648d25d4	106	class FranceTvInfoIE(FranceTVBaseInfoExtractor):
3c1b4669	107	IE_NAME = 'francetvinfo.fr'
23d3c422	108	_VALID_URL = r'https?://(?:www\|mobile)\.francetvinfo\.fr/.*/(?P<title>.+)\.html'
5d8afe69	109
5c30b268	110	_TESTS = [{
3c1b4669	111	'url': 'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
3c1b4669	112	'info_dict': {
5c30b268	113	'id': '84981923',
64892c0b	114	'ext': 'flv',
3c1b4669	115	'title': 'Soir 3',
64892c0b S	116	'upload_date': '20130826',
64892c0b S	117	'timestamp': 1377548400,
648d25d4	118	},
5c30b268 PH	119	}, {
	120	'url': 'http://www.francetvinfo.fr/elections/europeennes/direct-europeennes-regardez-le-debat-entre-les-candidats-a-la-presidence-de-la-commission_600639.html',
	121	'info_dict': {
	122	'id': 'EV_20019',
	123	'ext': 'mp4',
	124	'title': 'Débat des candidats à la Commission européenne',
	125	'description': 'Débat des candidats à la Commission européenne',
	126	},
	127	'params': {
	128	'skip_download': 'HLS (reqires ffmpeg)'
64892c0b S	129	},
64892c0b S	130	'skip': 'Ce direct est terminé et sera disponible en rattrapage dans quelques minutes.',
6f96e308 YCH	131	}, {
	132	'url': 'http://www.francetvinfo.fr/economie/entreprises/les-entreprises-familiales-le-secret-de-la-reussite_933271.html',
	133	'md5': 'f485bda6e185e7d15dbc69b72bae993e',
	134	'info_dict': {
	135	'id': '556e03339473995ee145930c',
	136	'ext': 'mp4',
	137	'title': 'Les entreprises familiales : le secret de la réussite',
	138	'thumbnail': 're:^https?://.*\.jpe?g$',
	139	}
5c30b268	140	}]
648d25d4 JMF	141
	142	def _real_extract(self, url):
	143	mobj = re.match(self._VALID_URL, url)
	144	page_title = mobj.group('title')
	145	webpage = self._download_webpage(url, page_title)
6f96e308 YCH	146
	147	dmcloud_url = DailymotionCloudIE._extract_dmcloud_url(webpage)
	148	if dmcloud_url:
	149	return self.url_result(dmcloud_url, 'DailymotionCloud')
	150
64892c0b S	151	video_id, catalogue = self._search_regex(
	152	r'id-video=([^@]+@[^"]+)', webpage, 'video id').split('@')
	153	return self._extract_video(video_id, catalogue)
a825f330 JMF	154
a825f330 JMF	155
9e606020	156	class FranceTVIE(FranceTVBaseInfoExtractor):
3c1b4669 PH	157	IE_NAME = 'francetv'
3c1b4669 PH	158	IE_DESC = 'France 2, 3, 4, 5 and Ô'
3f5c6d0c S	159	_VALID_URL = r'''(?x)
	160	https?://
	161	(?:
	162	(?:www\.)?france[2345o]\.fr/
	163	(?:
308c505c S	164	emissions/[^/]+/(?:videos\|diffusions)\|
308c505c S	165	emission/[^/]+\|
789a12aa S	166	videos\|
789a12aa S	167	jt
3f5c6d0c S	168	)
	169	/\|
	170	embed\.francetv\.fr/\?ue=
	171	)
	172	(?P<id>[^/?]+)
	173	'''
a825f330	174
9e606020 JMF	175	_TESTS = [
	176	# france2
	177	{
3c1b4669	178	'url': 'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
64892c0b	179	'md5': 'c03fc87cb85429ffd55df32b9fc05523',
3c1b4669	180	'info_dict': {
64892c0b S	181	'id': '109169362',
	182	'ext': 'flv',
	183	'title': '13h15, le dimanche...',
	184	'description': 'md5:9a0932bb465f22d377a449be9d1a0ff7',
	185	'upload_date': '20140914',
	186	'timestamp': 1410693600,
9e606020	187	},
a825f330	188	},
9e606020 JMF	189	# france3
9e606020 JMF	190	{
3c1b4669	191	'url': 'http://www.france3.fr/emissions/pieces-a-conviction/diffusions/13-11-2013_145575',
64892c0b	192	'md5': '679bb8f8921f8623bd658fa2f8364da0',
3c1b4669 PH	193	'info_dict': {
3c1b4669 PH	194	'id': '000702326_CAPP_PicesconvictionExtrait313022013_120220131722_Au',
64892c0b	195	'ext': 'mp4',
3c1b4669 PH	196	'title': 'Le scandale du prix des médicaments',
3c1b4669 PH	197	'description': 'md5:1384089fbee2f04fc6c9de025ee2e9ce',
64892c0b S	198	'upload_date': '20131113',
64892c0b S	199	'timestamp': 1384380000,
9e606020	200	},
a825f330	201	},
9e606020 JMF	202	# france4
9e606020 JMF	203	{
3c1b4669	204	'url': 'http://www.france4.fr/emissions/hero-corp/videos/rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
64892c0b	205	'md5': 'a182bf8d2c43d88d46ec48fbdd260c1c',
3c1b4669 PH	206	'info_dict': {
3c1b4669 PH	207	'id': 'rhozet_herocorp_bonus_1_20131106_1923_06112013172108_F4',
64892c0b	208	'ext': 'mp4',
3c1b4669 PH	209	'title': 'Hero Corp Making of - Extrait 1',
3c1b4669 PH	210	'description': 'md5:c87d54871b1790679aec1197e73d650a',
64892c0b S	211	'upload_date': '20131106',
64892c0b S	212	'timestamp': 1383766500,
9e606020 JMF	213	},
	214	},
	215	# france5
	216	{
3c1b4669	217	'url': 'http://www.france5.fr/emissions/c-a-dire/videos/92837968',
64892c0b	218	'md5': '78f0f4064f9074438e660785bbf2c5d9',
3c1b4669	219	'info_dict': {
64892c0b S	220	'id': '108961659',
64892c0b S	221	'ext': 'flv',
3c1b4669	222	'title': 'C à dire ?!',
64892c0b S	223	'description': 'md5:1a4aeab476eb657bf57c4ff122129f81',
	224	'upload_date': '20140915',
	225	'timestamp': 1410795000,
9e606020 JMF	226	},
	227	},
	228	# franceo
	229	{
3bc9fb58 S	230	'url': 'http://www.franceo.fr/jt/info-soir/18-07-2015',
3bc9fb58 S	231	'md5': '47d5816d3b24351cdce512ad7ab31da8',
3c1b4669	232	'info_dict': {
3bc9fb58	233	'id': '125377621',
64892c0b	234	'ext': 'flv',
3bc9fb58 S	235	'title': 'Infô soir',
	236	'description': 'md5:01b8c6915a3d93d8bbbd692651714309',
	237	'upload_date': '20150718',
	238	'timestamp': 1437241200,
	239	'duration': 414,
9e606020	240	},
9e606020	241	},
3f5c6d0c S	242	{
	243	# francetv embed
	244	'url': 'http://embed.francetv.fr/?ue=8d7d3da1e3047c42ade5a5d7dfd3fc87',
	245	'info_dict': {
	246	'id': 'EV_30231',
	247	'ext': 'flv',
	248	'title': 'Alcaline, le concert avec Calogero',
ac4b8df5	249	'description': 'md5:61f08036dcc8f47e9cfc33aed08ffaff',
3f5c6d0c S	250	'upload_date': '20150226',
3f5c6d0c S	251	'timestamp': 1424989860,
5705ee6e	252	'duration': 5400,
3f5c6d0c S	253	},
	254	},
	255	{
	256	'url': 'http://www.france4.fr/emission/highlander/diffusion-du-17-07-2015-04h05',
	257	'only_matching': True,
	258	},
	259	{
	260	'url': 'http://www.franceo.fr/videos/125377617',
	261	'only_matching': True,
	262	}
9e606020	263	]
a825f330 JMF	264
a825f330 JMF	265	def _real_extract(self, url):
3f5c6d0c S	266	video_id = self._match_id(url)
3f5c6d0c S	267	webpage = self._download_webpage(url, video_id)
64892c0b	268	video_id, catalogue = self._html_search_regex(
3f5c6d0c	269	r'href="http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
64892c0b S	270	webpage, 'video ID').split('@')
64892c0b S	271	return self._extract_video(video_id, catalogue)
5b333c1c JMF	272
	273
	274	class GenerationQuoiIE(InfoExtractor):
3c1b4669	275	IE_NAME = 'france2.fr:generation-quoi'
c4e817ce	276	_VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<id>[^/?#]+)'
5b333c1c JMF	277
5b333c1c JMF	278	_TEST = {
3c1b4669	279	'url': 'http://generation-quoi.france2.fr/portrait/garde-a-vous',
3c1b4669	280	'info_dict': {
c4e817ce PH	281	'id': 'k7FJX8VBcvvLmX4wA5Q',
c4e817ce PH	282	'ext': 'mp4',
3c1b4669 PH	283	'title': 'Génération Quoi - Garde à Vous',
3c1b4669 PH	284	'uploader': 'Génération Quoi',
5b333c1c	285	},
3c1b4669	286	'params': {
5b333c1c	287	# It uses Dailymotion
3c1b4669	288	'skip_download': True,
5b333c1c JMF	289	},
	290	}
	291
	292	def _real_extract(self, url):
c4e817ce PH	293	display_id = self._match_id(url)
	294	info_url = compat_urlparse.urljoin(url, '/medias/video/%s.json' % display_id)
	295	info_json = self._download_webpage(info_url, display_id)
5b333c1c JMF	296	info = json.loads(info_json)
5b333c1c JMF	297	return self.url_result('http://www.dailymotion.com/video/%s' % info['id'],
9e1a5b84	298	ie='Dailymotion')
469ec941 JMF	299
	300
	301	class CultureboxIE(FranceTVBaseInfoExtractor):
3c1b4669	302	IE_NAME = 'culturebox.francetvinfo.fr'
23d3c422	303	_VALID_URL = r'https?://(?:m\.)?culturebox\.francetvinfo\.fr/(?P<name>.*?)(\?\|$)'
469ec941 JMF	304
469ec941 JMF	305	_TEST = {
aed2d4b3	306	'url': 'http://culturebox.francetvinfo.fr/live/musique/musique-classique/le-livre-vermeil-de-montserrat-a-la-cathedrale-delne-214511',
ac651e97	307	'md5': '9b88dc156781c4dbebd4c3e066e0b1d6',
3c1b4669	308	'info_dict': {
aed2d4b3	309	'id': 'EV_50111',
ac651e97	310	'ext': 'flv',
aed2d4b3 S	311	'title': "Le Livre Vermeil de Montserrat à la Cathédrale d'Elne",
	312	'description': 'md5:f8a4ad202e8fe533e2c493cc12e739d9',
	313	'upload_date': '20150320',
	314	'timestamp': 1426892400,
	315	'duration': 2760.9,
	316	},
469ec941 JMF	317	}
	318
	319	def _real_extract(self, url):
	320	mobj = re.match(self._VALID_URL, url)
	321	name = mobj.group('name')
184a1974	322
469ec941	323	webpage = self._download_webpage(url, name)
184a1974 S	324
	325	if ">Ce live n'est plus disponible en replay<" in webpage:
	326	raise ExtractorError('Video %s is not available' % name, expected=True)
	327
64892c0b S	328	video_id, catalogue = self._search_regex(
	329	r'"http://videos\.francetv\.fr/video/([^@]+@[^"]+)"', webpage, 'video id').split('@')
	330
	331	return self._extract_video(video_id, catalogue)