[extractor/ina] Improve extractor (#4487)

Closes #4419
Authored by: elyse0
This commit is contained in:
Elyse 2022-07-30 03:51:19 -05:00 committed by GitHub
parent 871a8929bc
commit db5f248204
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -3,7 +3,7 @@
class InaIE(InfoExtractor): class InaIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|m)\.)?ina\.fr/(?:[^/]+/)?(?:video|audio)/(?P<id>\w+)' _VALID_URL = r'https?://(?:(?:www|m)\.)?ina\.fr/(?:[^?#]+/)(?P<id>[\w-]+)'
_TESTS = [{ _TESTS = [{
'url': 'https://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html', 'url': 'https://www.ina.fr/video/I12055569/francois-hollande-je-crois-que-c-est-clair-video.html',
'md5': 'c5a09e5cb5604ed10709f06e7a377dda', 'md5': 'c5a09e5cb5604ed10709f06e7a377dda',
@ -11,7 +11,7 @@ class InaIE(InfoExtractor):
'id': 'I12055569', 'id': 'I12055569',
'ext': 'mp4', 'ext': 'mp4',
'title': 'François Hollande "Je crois que c\'est clair"', 'title': 'François Hollande "Je crois que c\'est clair"',
'description': 'md5:08201f1c86fb250611f0ba415d21255a', 'description': 'md5:19f61e2b4844ed4bb2e3df9ab9f527ff',
'upload_date': '20070712', 'upload_date': '20070712',
'thumbnail': 'https://cdn-hub.ina.fr/notice/690x517/3c4/I12055569.jpeg', 'thumbnail': 'https://cdn-hub.ina.fr/notice/690x517/3c4/I12055569.jpeg',
} }
@ -38,21 +38,42 @@ class InaIE(InfoExtractor):
'upload_date': '19821204', 'upload_date': '19821204',
'duration': 657, 'duration': 657,
'thumbnail': 'https://cdn-hub.ina.fr/notice/690x517/203/CPB8205116303.jpeg', 'thumbnail': 'https://cdn-hub.ina.fr/notice/690x517/203/CPB8205116303.jpeg',
} },
}, {
'url': 'https://www.ina.fr/ina-eclaire-actu/arletty-carriere-conseils-actrice-marcel-carne',
'md5': '743d6f069a00e19dda0da166a54eeccb',
'info_dict': {
'id': 'I22203233',
'ext': 'mp4',
'title': 'Arletty sur le métier d\'actrice',
'description': 'md5:3d89b5e419d8514c934f146045ccdbad',
'upload_date': '19581128',
'thumbnail': 'https://cdn-hub.ina.fr/notice/690x517/082/I22203233.jpeg',
},
}, {
'url': 'https://www.ina.fr/ina-eclaire-actu/chasse-croise-sncf-gare-d-austerlitz-vacances-d-ete',
'md5': 'a96fb85e9ba3b5c5b2eeb0c5daa55f2f',
'info_dict': {
'id': 'CAF91038285',
'ext': 'mp4',
'title': 'Les grands départs : les trains',
'description': 'md5:1630ee819d8d4da97df53459e99f72bb',
'upload_date': '19740801',
'thumbnail': 'https://cdn-hub.ina.fr/notice/690x517/2cf/CAF91038285.jpeg',
},
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url).upper() display_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, display_id)
api_url = self._html_search_regex( api_url = self._html_search_regex(r'asset-details-url\s*=\s*["\'](?P<api_url>[^"\']+)', webpage, 'api_url')
r'asset-details-url\s*=\s*["\'](?P<api_url>[^"\']+)', asset_id = self._search_regex(r'assets/([^?/]+)', api_url, 'asset_id')
webpage, 'api_url').replace(video_id, f'{video_id}.json')
api_response = self._download_json(api_url, video_id) api_response = self._download_json(api_url.replace(asset_id, f'{asset_id}.json'), asset_id)
return { return {
'id': video_id, 'id': asset_id,
'url': api_response['resourceUrl'], 'url': api_response['resourceUrl'],
'ext': {'video': 'mp4', 'audio': 'mp3'}.get(api_response.get('type')), 'ext': {'video': 'mp4', 'audio': 'mp3'}.get(api_response.get('type')),
'title': api_response.get('title'), 'title': api_response.get('title'),