yt-dlp/yt_dlp/extractor/nzz.py

41 lines
1.3 KiB
Python
Raw Normal View History

2016-10-06 11:45:57 +02:00
import re
from .common import InfoExtractor
from ..utils import (
extract_attributes,
)
class NZZIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nzz\.ch/(?:[^/]+/)*[^/?#]+-ld\.(?P<id>\d+)'
2018-11-20 20:50:40 +01:00
_TESTS = [{
2016-10-06 11:45:57 +02:00
'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 20:50:40 +01:00
}, {
'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 11:45:57 +02:00
def _real_extract(self, url):
page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id)
entries = []
2018-11-20 20:50:40 +01:00
for player_element in re.findall(
r'(<[^>]+class="kalturaPlayer[^"]*"[^>]*>)', webpage):
2016-10-06 11:45:57 +02:00
player_params = extract_attributes(player_element)
if player_params.get('data-type') not in ('kaltura_singleArticle',):
self.report_warning('Unsupported player type')
continue
entry_id = player_params['data-id']
entries.append(self.url_result(
'kaltura:1750922:' + entry_id, 'Kaltura', entry_id))
return self.playlist_result(entries, page_id)