[npo] Add extractor for tegenlicht.vpro.nl (closes #3778)

This commit is contained in:
Jaime Marquínez Ferrándiz 2014-09-21 16:53:00 +02:00
parent e35cb78c40
commit d0df92928b
2 changed files with 34 additions and 1 deletions

View file

@ -249,7 +249,10 @@ from .nosvideo import NosVideoIE
from .novamov import NovaMovIE from .novamov import NovaMovIE
from .nowness import NownessIE from .nowness import NownessIE
from .nowvideo import NowVideoIE from .nowvideo import NowVideoIE
from .npo import NPOIE from .npo import (
NPOIE,
TegenlichtVproIE,
)
from .nrk import ( from .nrk import (
NRKIE, NRKIE,
NRKTVIE, NRKTVIE,

View file

@ -7,6 +7,7 @@ from ..utils import (
unified_strdate, unified_strdate,
parse_duration, parse_duration,
qualities, qualities,
url_basename,
) )
@ -55,7 +56,9 @@ class NPOIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id') video_id = mobj.group('id')
return self._get_info(video_id)
def _get_info(self, video_id):
metadata = self._download_json( metadata = self._download_json(
'http://e.omroep.nl/metadata/aflevering/%s' % video_id, 'http://e.omroep.nl/metadata/aflevering/%s' % video_id,
video_id, video_id,
@ -106,3 +109,30 @@ class NPOIE(InfoExtractor):
'duration': parse_duration(metadata.get('tijdsduur')), 'duration': parse_duration(metadata.get('tijdsduur')),
'formats': formats, 'formats': formats,
} }
class TegenlichtVproIE(NPOIE):
IE_NAME = 'tegenlicht.vpro.nl'
_VALID_URL = r'https?://tegenlicht\.vpro\.nl/afleveringen/.*?'
_TESTS = [
{
'url': 'http://tegenlicht.vpro.nl/afleveringen/2012-2013/de-toekomst-komt-uit-afrika.html',
'md5': 'f8065e4e5a7824068ed3c7e783178f2c',
'info_dict': {
'id': 'VPWON_1169289',
'ext': 'm4v',
'title': 'Tegenlicht',
'description': 'md5:d6476bceb17a8c103c76c3b708f05dd1',
'upload_date': '20130225',
},
},
]
def _real_extract(self, url):
name = url_basename(url)
webpage = self._download_webpage(url, name)
urn = self._html_search_meta('mediaurn', webpage)
info_page = self._download_json(
'http://rs.vpro.nl/v2/api/media/%s.json' % urn, name)
return self._get_info(info_page['mid'])