2 from __future__ import unicode_literals
6 from .common import InfoExtractor
7 from ..utils import qualities
10 class DumpertIE(InfoExtractor):
11 _VALID_URL = r'https?://(?:www\.)?dumpert\.nl/mediabase/(?P<id>[0-9]+/[0-9a-zA-Z]+)'
13 'url': 'http://www.dumpert.nl/mediabase/6646981/951bc60f/',
14 'md5': '1b9318d7d5054e7dcb9dc7654f21d643',
16 'id': '6646981/951bc60f',
18 'title': 'Ik heb nieuws voor je',
19 'description': 'Niet schrikken hoor',
20 'thumbnail': 're:^https?://.*\.jpg$',
24 def _real_extract(self, url):
25 video_id = self._match_id(url)
26 webpage = self._download_webpage(url, video_id)
28 files_base64 = self._search_regex(
29 r'data-files="([^"]+)"', webpage, 'data files')
31 files = self._parse_json(
32 base64.b64decode(files_base64.encode('utf-8')).decode('utf-8'),
35 quality = qualities(['flv', 'mobile', 'tablet', '720p'])
39 'format_id': format_id,
40 'quality': quality(format_id),
41 } for format_id, video_url in files.items() if format_id != 'still']
42 self._sort_formats(formats)
44 title = self._html_search_meta(
45 'title', webpage) or self._og_search_title(webpage)
46 description = self._html_search_meta(
47 'description', webpage) or self._og_search_description(webpage)
48 thumbnail = files.get('still') or self._og_search_thumbnail(webpage)
53 'description': description,
54 'thumbnail': thumbnail,