[nzz] Add new extractor(#4407)

This commit is contained in:
Remita Amine 2016-10-06 10:45:57 +01:00
parent 017eb82934
commit 33898fb19c
2 changed files with 37 additions and 0 deletions

View File

@ -638,6 +638,7 @@
NYTimesArticleIE, NYTimesArticleIE,
) )
from .nuvid import NuvidIE from .nuvid import NuvidIE
from .nzz import NZZIE
from .odatv import OdaTVIE from .odatv import OdaTVIE
from .odnoklassniki import OdnoklassnikiIE from .odnoklassniki import OdnoklassnikiIE
from .oktoberfesttv import OktoberfestTVIE from .oktoberfesttv import OktoberfestTVIE

View File

@ -0,0 +1,36 @@
# coding: utf-8
from __future__ import unicode_literals
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+)'
_TEST = {
'url': 'http://www.nzz.ch/zuerich/gymizyte/gymizyte-schreiben-schueler-heute-noch-diktate-ld.9153',
'info_dict': {
'id': '9153',
},
'playlist_mincount': 6,
}
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):
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)