mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-06-28 01:18:30 +00:00
Code Issues Projects Releases Wiki Activity

Merge 096fd691bb into 73bf102116

Browse Source
This commit is contained in:
Frank Aurich 2025-06-20 21:48:21 +02:00 committed by GitHub
commit 8c1a15e182
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 41 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

57
yt_dlp/extractor/arte.py
View File

@ -268,33 +268,58 @@ class ArteTVPlaylistIE(ArteTVBaseIE):
'only_matching': True, 'only_matching': True,
}, { }, {
'url': 'https://www.arte.tv/pl/videos/RC-014123/arte-reportage/', 'url': 'https://www.arte.tv/pl/videos/RC-014123/arte-reportage/',
'playlist_mincount': 100, 'playlist_mincount': 20,
'info_dict': { 'info_dict': {
'description': 'md5:84e7bf1feda248bc325ebfac818c476e', 'description': 'md5:84e7bf1feda248bc325ebfac818c476e',
'id': 'RC-014123', 'id': 'RC-014123',
'title': 'ARTE Reportage - najlepsze reportaże', 'title': 'ARTE Reportage - najlepsze reportaże',
}, },
}, {
'url': 'https://www.arte.tv/de/videos/RC-025470/ramy/',
'playlist_mincount': 30,
'info_dict': {
'description': 'md5:8766d73504ddccd12dbd1395a1d56815',
'id': 'RC-025470',
'title': 'Ramy',
},
}] }]
def _entries(self, playlist_data, playlist_id):
playlist_item_filter = lambda _, v: re.match(rf'collection_(?:videos|subcollection)_{playlist_id}', v['code'])
collections = traverse_obj(playlist_data,
('data',
'zones',
playlist_item_filter,
'content',
'data',
...))
for video in collections:
yield {
'_type': 'url_transparent',
'url': 'https://www.arte.tv' + video['url'],
'ie_key': ArteTVIE.ie_key(),
'id': video['id'],
'title': video.get('title'),
'alt_title': video.get('subtitle'),
'duration': int_or_none(traverse_obj(video, ('duration'))),
'age_limit': int_or_none(traverse_obj(video, 'ageRating')),
}
def _real_extract(self, url): def _real_extract(self, url):
lang, playlist_id = self._match_valid_url(url).group('lang', 'id') lang, playlist_id = self._match_valid_url(url).group('lang', 'id')
playlist = self._download_json( webpage = self._download_webpage(url, playlist_id)
f'{self._API_BASE}/playlist/{lang}/{playlist_id}', playlist_id)['data']['attributes']
entries = [{ unescape_func = lambda jstring: jstring.replace('\\"', '"').replace('\\\\', '\\')
'_type': 'url_transparent', json_data = self._search_json(r'\$L23.+?', webpage, 'series data',
'url': video['config']['url'], playlist_id,
'ie_key': ArteTVIE.ie_key(), end_pattern=r'\],\[\[',
'id': video.get('providerId'), transform_source=unescape_func)
'title': video.get('title'),
'alt_title': video.get('subtitle'),
'thumbnail': url_or_none(traverse_obj(video, ('mainImage', 'url'))),
'duration': int_or_none(traverse_obj(video, ('duration', 'seconds'))),
} for video in traverse_obj(playlist, ('items', lambda _, v: v['config']['url']))]
return self.playlist_result(entries, playlist_id, return self.playlist_result(self._entries(json_data, playlist_id),
traverse_obj(playlist, ('metadata', 'title')), playlist_id,
traverse_obj(playlist, ('metadata', 'description'))) traverse_obj(json_data, ('data', 'metadata', 'title')),
traverse_obj(json_data, ('data', 'metadata', 'description')))
class ArteTVCategoryIE(ArteTVBaseIE): class ArteTVCategoryIE(ArteTVBaseIE):