2 from __future__ import unicode_literals
4 from .common import InfoExtractor
7 class Min20IE(InfoExtractor):
8 _VALID_URL = r'http://www\.20min\.ch/.+?-(?P<id>[0-9]+)$'
10 'url': 'http://www.20min.ch/schweiz/news/story/-Wir-muessen-mutig-nach-vorne-schauen--22050469',
11 'md5': 'cd4cbb99b94130cff423e967cd275e5e',
15 'title': '«Wir müssen mutig nach vorne schauen»',
16 'description': 'Kein Land sei innovativer als die Schweiz, sagte Johann Schneider-Ammann in seiner Neujahrsansprache. Das Land müsse aber seine Hausaufgaben machen.',
17 'thumbnail': 'http://www.20min.ch/images/content/2/2/0/22050469/10/teaserbreit.jpg'
21 # location of the flv videos, can't be extracted from the web page
22 _BASE_URL = "http://flv-rr.20min-tv.ch/videos/"
24 def _real_extract(self, url):
25 video_id = self._match_id(url)
26 webpage = self._download_webpage(url, video_id)
27 title = self._html_search_regex(r'<h1><span>(.+?)</span></h1>', webpage, 'title')
28 flash_id = self._search_regex(r"so\.addVariable\(\"file1\",\"([0-9]+)\"\)", webpage, 'flash_id')
30 description = self._html_search_regex(r'<meta name="description" content="(.+?)" />', webpage, 'description')
31 thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.+?)" />', webpage, 'thumbnail')
32 url = self._BASE_URL + flash_id + "m.flv"
38 'description': description,
39 'thumbnail': thumbnail