2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..utils import int_or_none
9 class BelgianNationalIE(InfoExtractor):
10 _VALID_URL = r'http://(?:deredactie|sporza|cobra)\.be/cm/(.*)/(?P<video_id>[^\']+)'
14 'url': 'http://deredactie.be/cm/vrtnieuws/videozone/programmas/journaal/EP_141025_JOL',
15 'md5': '4cebde1eb60a53782d4f3992cbd46ec8',
17 'id': 'EP_141025_JOL',
18 'title': 'Het journaal L - 25/10/14',
25 'url': 'http://sporza.be/cm/sporza/videozone/programmas/extratime/EP_141020_Extra_time',
26 'md5': '11f53088da9bf8e7cfc42456697953ff',
28 'id': 'EP_141020_Extra_time',
29 'title': 'Bekijk Extra Time van 20 oktober',
37 'url': 'http://cobra.be/cm/cobra/videozone/rubriek/film-videozone/141022-mv-ellis-cafecorsari',
38 'md5': '78a2b060a5083c4f055449a72477409d',
40 'id': '141022-mv-ellis-cafecorsari',
41 'title': 'Bret Easton Ellis in Café Corsari',
48 def _real_extract(self, url):
49 mobj = re.match(self._VALID_URL, url)
50 video_id = mobj.group('video_id')
52 webpage = self._download_webpage(url, video_id)
53 title = self._og_search_title(webpage)
55 video_url = self._search_regex(r'data-video-src="(.*?)"', webpage, 'Video url') + '/manifest.f4m'
56 duration = int_or_none(self._search_regex(r'data-video-sitestat-duration="(.*?)"', webpage, 'Duration'))