1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-24 19:22:06 +00:00

[francetv] Adapt to site redesign (closes #13034)

This commit is contained in:
Sergey M․ 2017-05-09 23:07:01 +07:00
parent 5d0968f0af
commit 6d1ded7502
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
2 changed files with 86 additions and 135 deletions

View file

@ -350,9 +350,9 @@ from .foxsports import FoxSportsIE
from .franceculture import FranceCultureIE from .franceculture import FranceCultureIE
from .franceinter import FranceInterIE from .franceinter import FranceInterIE
from .francetv import ( from .francetv import (
PluzzIE,
FranceTvInfoIE,
FranceTVIE, FranceTVIE,
FranceTVEmbedIE,
FranceTVInfoIE,
GenerationQuoiIE, GenerationQuoiIE,
CultureboxIE, CultureboxIE,
) )

View file

@ -21,11 +21,13 @@ from .dailymotion import (
class FranceTVBaseInfoExtractor(InfoExtractor): class FranceTVBaseInfoExtractor(InfoExtractor):
def _extract_video(self, video_id, catalogue): def _extract_video(self, video_id, catalogue=None):
info = self._download_json( info = self._download_json(
'http://webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/?idDiffusion=%s&catalogue=%s' 'https://sivideo.webservices.francetelevisions.fr/tools/getInfosOeuvre/v2/',
% (video_id, catalogue), video_id, 'Downloading video JSON', query={
video_id, 'Downloading video JSON') 'idDiffusion': video_id,
'catalogue': catalogue or '',
})
if info.get('status') == 'NOK': if info.get('status') == 'NOK':
raise ExtractorError( raise ExtractorError(
@ -109,27 +111,94 @@ class FranceTVBaseInfoExtractor(InfoExtractor):
} }
class PluzzIE(FranceTVBaseInfoExtractor): class FranceTVIE(FranceTVBaseInfoExtractor):
IE_NAME = 'pluzz.francetv.fr' _VALID_URL = r'https?://(?:www\.)?france\.tv/(?:[^/]+/)+(?P<id>[^/]+)\.html'
_VALID_URL = r'https?://(?:m\.)?pluzz\.francetv\.fr/videos/(?P<id>.+?)\.html'
# Can't use tests, videos expire in 7 days _TESTS = [{
'url': 'https://www.france.tv/france-2/13h15-le-dimanche/140921-les-mysteres-de-jesus.html',
'info_dict': {
'id': '157550144',
'ext': 'mp4',
'title': '13h15, le dimanche... - Les mystères de Jésus',
'description': 'md5:75efe8d4c0a8205e5904498ffe1e1a42',
'timestamp': 1494156300,
'upload_date': '20170507',
},
'params': {
# m3u8 downloads
'skip_download': True,
},
}, {
# france3
'url': 'https://www.france.tv/france-3/des-chiffres-et-des-lettres/139063-emission-du-mardi-9-mai-2017.html',
'only_matching': True,
}, {
# france4
'url': 'https://www.france.tv/france-4/hero-corp/saison-1/134151-apres-le-calme.html',
'only_matching': True,
}, {
# france5
'url': 'https://www.france.tv/france-5/c-a-dire/saison-10/137013-c-a-dire.html',
'only_matching': True,
}, {
# franceo
'url': 'https://www.france.tv/france-o/archipels/132249-mon-ancetre-l-esclave.html',
'only_matching': True,
}, {
# france2 live
'url': 'https://www.france.tv/france-2/direct.html',
'only_matching': True,
}, {
'url': 'https://www.france.tv/documentaires/histoire/136517-argentine-les-500-bebes-voles-de-la-dictature.html',
'only_matching': True,
}, {
'url': 'https://www.france.tv/jeux-et-divertissements/divertissements/133965-le-web-contre-attaque.html',
'only_matching': True,
}]
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
video_id = self._html_search_meta( catalogue = None
'id_video', webpage, 'video id', default=None) video_id = self._search_regex(
r'data-main-video=(["\'])(?P<id>(?:(?!\1).)+)\1',
webpage, 'video id', default=None, group='id')
if not video_id: if not video_id:
video_id = self._search_regex( video_id, catalogue = self._html_search_regex(
r'data-diffusion=["\'](\d+)', webpage, 'video id') r'(?:href=|player\.setVideo\(\s*)"http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
webpage, 'video ID').split('@')
return self._extract_video(video_id, 'Pluzz') return self._extract_video(video_id, catalogue)
class FranceTvInfoIE(FranceTVBaseInfoExtractor): class FranceTVEmbedIE(FranceTVBaseInfoExtractor):
_VALID_URL = r'https?://embed\.francetv\.fr/*\?.*?\bue=(?P<id>[^&]+)'
_TEST = {
'url': 'http://embed.francetv.fr/?ue=7fd581a2ccf59d2fc5719c5c13cf6961',
'info_dict': {
'id': 'NI_983319',
'ext': 'mp4',
'title': 'Le Pen Reims',
'upload_date': '20170505',
'timestamp': 1493981780,
'duration': 16,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
'http://api-embed.webservices.francetelevisions.fr/key/%s' % video_id,
video_id)
return self._extract_video(video['video_id'], video.get('catalog'))
class FranceTVInfoIE(FranceTVBaseInfoExtractor):
IE_NAME = 'francetvinfo.fr' IE_NAME = 'francetvinfo.fr'
_VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/(?:[^/]+/)*(?P<title>[^/?#&.]+)' _VALID_URL = r'https?://(?:www|mobile|france3-regions)\.francetvinfo\.fr/(?:[^/]+/)*(?P<title>[^/?#&.]+)'
@ -233,124 +302,6 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
return self._extract_video(video_id, catalogue) 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/quels_sont_les_enjeux_de_cette_rentree_politique__31-08-2015_908948?onglet=tous&page=1',
'md5': 'f6c577df3806e26471b3d21631241fd0',
'info_dict': {
'id': '123327454',
'ext': 'flv',
'title': 'C à dire ?! - Quels sont les enjeux de cette rentrée politique ?',
'description': 'md5:4a0d5cb5dce89d353522a84462bae5a4',
'upload_date': '20150831',
'timestamp': 1441035120,
},
},
# 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=|player\.setVideo\(\s*)"http://videos?\.francetv\.fr/video/([^@]+@[^"]+)"',
webpage, 'video ID').split('@')
return self._extract_video(video_id, catalogue)
class GenerationQuoiIE(InfoExtractor): class GenerationQuoiIE(InfoExtractor):
IE_NAME = 'france2.fr:generation-quoi' IE_NAME = 'france2.fr:generation-quoi'
_VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<id>[^/?#]+)' _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<id>[^/?#]+)'