0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-03 03:57:26 +00:00
yt-dlp/yt_dlp/extractor/nzz.py

33 lines
1.1 KiB
Python
Raw Normal View History

2016-10-06 09:45:57 +00:00
import re
from .common import InfoExtractor
class NZZIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nzz\.ch/(?:[^/]+/)*[^/?#]+-ld\.(?P<id>\d+)'
2018-11-20 19:50:40 +00:00
_TESTS = [{
2016-10-06 09:45:57 +00:00
'url': 'http://www.nzz.ch/zuerich/gymizyte/gymizyte-schreiben-schueler-heute-noch-diktate-ld.9153',
'info_dict': {
'id': '9153',
},
'playlist_mincount': 6,
2018-11-20 19:50:40 +00:00
}, {
'url': 'https://www.nzz.ch/video/nzz-standpunkte/cvp-auf-der-suche-nach-dem-mass-der-mitte-ld.1368112',
'info_dict': {
'id': '1368112',
},
'playlist_count': 1,
}]
2016-10-06 09:45:57 +00:00
def _entries(self, webpage, page_id):
for script in re.findall(r'(?s)<script[^>]* data-hid="jw-video-jw[^>]+>(.+?)</script>', webpage):
settings = self._search_json(r'var\s+settings\s*=[^{]*', script, 'settings', page_id, fatal=False)
if entry := self._parse_jwplayer_data(settings, page_id):
yield entry
2016-10-06 09:45:57 +00:00
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
return self.playlist_result(self._entries(webpage, page_id), page_id)