[wnl] Add extractor for omroepwnl playlists

This commit is contained in:
Sergey M․ 2015-07-17 00:14:38 +06:00
parent 50ea2bb20d
commit 03f32a7ead
2 changed files with 40 additions and 6 deletions

View File

@ -390,6 +390,7 @@
NPORadioIE,
NPORadioFragmentIE,
TegenlichtVproIE,
WNLIE
)
from .nrk import (
NRKIE,

View File

@ -46,6 +46,8 @@ class NPOIE(NPOBaseIE):
IE_NAME = 'npo'
IE_DESC = 'npo.nl and ntr.nl'
_VALID_URL = r'''(?x)
(?:
npo:|
https?://
(?:www\.)?
(?:
@ -53,6 +55,7 @@ class NPOIE(NPOBaseIE):
ntr\.nl/(?:[^/]+/){2,}|
omroepwnl\.nl/video/fragment/[^/]+__
)
)
(?P<id>[^/?#]+)
'''
@ -426,3 +429,33 @@ def _real_extract(self, url):
info_page = self._download_json(
'http://rs.vpro.nl/v2/api/media/%s.json' % urn, name)
return self._get_info(info_page['mid'])
class WNLIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?omroepwnl\.nl/video/detail/(?P<id>[^/]+)__\d+'
_TEST = {
'url': 'http://www.omroepwnl.nl/video/detail/vandaag-de-dag-6-mei__060515',
'info_dict': {
'id': 'vandaag-de-dag-6-mei',
'title': 'Vandaag de Dag 6 mei',
},
'playlist_count': 4,
}
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
entries = [
self.url_result('npo:%s' % video_id, 'NPO')
for video_id, part in re.findall(
r'<a[^>]+href="([^"]+)"[^>]+class="js-mid"[^>]*>(Deel \d+)', webpage)
]
playlist_title = self._html_search_regex(
r'(?s)<h1[^>]+class="subject"[^>]*>(.+?)</h1>',
webpage, 'playlist title')
return self.playlist_result(entries, playlist_id, playlist_title)