|
|
@ -11,20 +11,27 @@ from ..utils import ( |
|
|
|
|
|
|
|
class NZZIE(InfoExtractor): |
|
|
|
_VALID_URL = r'https?://(?:www\.)?nzz\.ch/(?:[^/]+/)*[^/?#]+-ld\.(?P<id>\d+)' |
|
|
|
_TEST = { |
|
|
|
_TESTS = [{ |
|
|
|
'url': 'http://www.nzz.ch/zuerich/gymizyte/gymizyte-schreiben-schueler-heute-noch-diktate-ld.9153', |
|
|
|
'info_dict': { |
|
|
|
'id': '9153', |
|
|
|
}, |
|
|
|
'playlist_mincount': 6, |
|
|
|
} |
|
|
|
}, { |
|
|
|
'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, |
|
|
|
}] |
|
|
|
|
|
|
|
def _real_extract(self, url): |
|
|
|
page_id = self._match_id(url) |
|
|
|
webpage = self._download_webpage(url, page_id) |
|
|
|
|
|
|
|
entries = [] |
|
|
|
for player_element in re.findall(r'(<[^>]+class="kalturaPlayer"[^>]*>)', webpage): |
|
|
|
for player_element in re.findall( |
|
|
|
r'(<[^>]+class="kalturaPlayer[^"]*"[^>]*>)', webpage): |
|
|
|
player_params = extract_attributes(player_element) |
|
|
|
if player_params.get('data-type') not in ('kaltura_singleArticle',): |
|
|
|
self.report_warning('Unsupported player type') |
|
|
|