1 from .common
import InfoExtractor
2 from ..utils
import unified_strdate
5 class InaIE(InfoExtractor
):
6 _VALID_URL
= r
'https?://(?:(?:www|m)\.)?ina\.fr/(?:[^?#]+/)(?P<id>[\w-]+)'
8 'url': 'https://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
9 'md5': 'c5a09e5cb5604ed10709f06e7a377dda',
13 'title': 'François Hollande "Je crois que c\'est clair"',
14 'description': 'md5:19f61e2b4844ed4bb2e3df9ab9f527ff',
15 'upload_date': '20070712',
16 'thumbnail': 'https://cdn-hub.ina.fr/notice/690x517/3c4/I12055569.jpeg',
19 'url': 'https://www.ina.fr/video/S806544_001/don-d-organes-des-avancees-mais-d-importants-besoins-video.html',
20 'only_matching': True,
22 'url': 'https://www.ina.fr/audio/P16173408',
23 'only_matching': True,
25 'url': 'https://www.ina.fr/video/P16173408-video.html',
26 'only_matching': True,
28 'url': 'http://m.ina.fr/video/I12055569',
29 'only_matching': True,
31 'url': 'https://www.ina.fr/ina-eclaire-actu/video/cpb8205116303/les-jeux-electroniques',
32 'md5': '4b8284a9a3a184fdc7e744225b8251e7',
34 'id': 'CPB8205116303',
36 'title': 'Les jeux électroniques',
37 'description': 'md5:e09f7683dad1cc60b74950490127d233',
38 'upload_date': '19821204',
40 'thumbnail': 'https://cdn-hub.ina.fr/notice/690x517/203/CPB8205116303.jpeg',
43 'url': 'https://www.ina.fr/ina-eclaire-actu/arletty-carriere-conseils-actrice-marcel-carne',
44 'md5': '743d6f069a00e19dda0da166a54eeccb',
48 'title': 'Arletty sur le métier d\'actrice',
49 'description': 'md5:3d89b5e419d8514c934f146045ccdbad',
50 'upload_date': '19581128',
51 'thumbnail': 'https://cdn-hub.ina.fr/notice/690x517/082/I22203233.jpeg',
54 'url': 'https://www.ina.fr/ina-eclaire-actu/chasse-croise-sncf-gare-d-austerlitz-vacances-d-ete',
55 'md5': 'a96fb85e9ba3b5c5b2eeb0c5daa55f2f',
59 'title': 'Les grands départs : les trains',
60 'description': 'md5:1630ee819d8d4da97df53459e99f72bb',
61 'upload_date': '19740801',
62 'thumbnail': 'https://cdn-hub.ina.fr/notice/690x517/2cf/CAF91038285.jpeg',
66 def _real_extract(self
, url
):
67 display_id
= self
._match
_id
(url
)
68 webpage
= self
._download
_webpage
(url
, display_id
)
70 api_url
= self
._html
_search
_regex
(r
'asset-details-url\s*=\s*["\'](?P
<api_url
>[^
"\']+)', webpage, 'api_url')
71 asset_id = self._search_regex(r'assets/([^?/]+)', api_url, 'asset_id')
73 api_response = self._download_json(api_url.replace(asset_id, f'{asset_id}.json'), asset_id)
77 'url': api_response['resourceUrl'],
78 'ext': {'video': 'mp4', 'audio': 'mp3'}.get(api_response.get('type')),
79 'title': api_response.get('title'),
80 'description': api_response.get('description'),
81 'upload_date': unified_strdate(api_response.get('dateOfBroadcast')),
82 'duration': api_response.get('duration'),
83 'thumbnail': api_response.get('resourceThumbnail'),