Mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-07-08 21:04:38 +02:00
Code Issues Releases Activity

Update KiKA extractor:

Browse Source 
- Use regular expression suggested by dirkf
  - Update existing test case, and add a second one with different URL schema
  - Remove static 'uploader' element
This commit is contained in:
Frank Aurich 2023-12-18 21:31:52 +01:00
parent b96401f7c4
commit e7079c3a5a
1 changed files with 21 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
yt_dlp/extractor/kika.py
View File

@ -9,28 +9,39 @@
class KikaIE(InfoExtractor): class KikaIE(InfoExtractor):
IE_DESC = 'KiKA.de' IE_DESC = 'KiKA.de'
_VALID_URL = r'https?://(?:www\.)?kika\.de/(?:.*)/[a-z-]+-?(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?kika\.de/(?:.*)/(?P<id>[a-z-]+-?\d+)'
_GEO_COUNTRIES = ['DE'] _GEO_COUNTRIES = ['DE']
_TESTS = [{ _TESTS = [{
'url': 'https://www.kika.de/beutolomaeus-und-der-wahre-weihnachtsmann/videos/video59362', 'url': 'https://www.kika.de/beutolomaeus-und-der-wahre-weihnachtsmann/videos/eins-der-neue-weihnachtsmann-102',
'md5': 'b163ac8872f0cea1eb075cae3c275935', 'md5': '25ceea8790417f3c6dcf1d4342f8a97a',
'info_dict': { 'info_dict': {
'id': '59362', 'id': 'eins-der-neue-weihnachtsmann-102',
'ext': 'mp4', 'ext': 'mp4',
'title': '1. Der neue Weihnachtsmann', 'title': '1. Der neue Weihnachtsmann',
'description': 'md5:61b1e6f32882e8ca2a0ddfd135d03c6b', 'description': 'md5:61b1e6f32882e8ca2a0ddfd135d03c6b',
'duration': 787, 'duration': 787,
'uploader': 'KIKA', 'timestamp': 1700584500,
'timestamp': 1669914628, 'upload_date': '20231121'
'upload_date': '20221201' }
}, }, {
'url': 'https://www.kika.de/kaltstart/videos/video92498',
'md5': '710ece827e5055094afeb474beacb7aa',
'info_dict': {
'id': 'video92498',
'ext': 'mp4',
'title': '7. Wo ist Leo?',
'description': 'md5:fb48396a5b75068bcac1df74f1524920',
'duration': 436,
'timestamp': 1702926876,
'upload_date': '20231218'
}
}] }]
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
doc = self._download_json(f'https://www.kika.de/_next-api/proxy/v1/videos/video{video_id}', video_id) doc = self._download_json(f'https://www.kika.de/_next-api/proxy/v1/videos/{video_id}', video_id)
video_assets = self._download_json(doc['assets']['url'], video_id) video_assets = self._download_json(doc['assets']['url'], video_id)
subtitles = {} subtitles = {}
@ -54,8 +65,7 @@ def _real_extract(self, url):
'timestamp': parse_iso8601(doc.get('date')), 'timestamp': parse_iso8601(doc.get('date')),
'duration': parse_duration(doc.get('duration')), 'duration': parse_duration(doc.get('duration')),
'formats': list(self._extract_formats(video_assets, video_id)), 'formats': list(self._extract_formats(video_assets, video_id)),
'subtitles': subtitles, 'subtitles': subtitles
'uploader': 'KIKA'
} }
def _extract_formats(self, media_info, video_id): def _extract_formats(self, media_info, video_id):