2 from __future__ import unicode_literals
6 from .common import InfoExtractor
9 class TeleBruxellesIE(InfoExtractor):
10 _VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(news|sport|dernier-jt|emission)/?(?P<id>[^/#?]+)'
12 'url': 'http://bx1.be/news/que-risque-lauteur-dune-fausse-alerte-a-la-bombe/',
13 'md5': 'a2a67a5b1c3e8c9d33109b902f474fd9',
16 'display_id': 'que-risque-lauteur-dune-fausse-alerte-a-la-bombe',
18 'title': 'Que risque l’auteur d’une fausse alerte à la bombe ?',
19 'description': 'md5:3cf8df235d44ebc5426373050840e466',
22 'url': 'http://bx1.be/sport/futsal-schaerbeek-sincline-5-3-a-thulin/',
23 'md5': 'dfe07ecc9c153ceba8582ac912687675',
26 'display_id': 'futsal-schaerbeek-sincline-5-3-a-thulin',
28 'title': 'Futsal : Schaerbeek s’incline 5-3 à Thulin',
29 'description': 'md5:fd013f1488d5e2dceb9cebe39e2d569b',
32 'url': 'http://bx1.be/emission/bxenf1-gastronomie/',
33 'only_matching': True,
36 def _real_extract(self, url):
37 display_id = self._match_id(url)
38 webpage = self._download_webpage(url, display_id)
40 article_id = self._html_search_regex(
41 r"<article id=\"post-(\d+)\"", webpage, 'article ID', default=None)
42 title = self._html_search_regex(
43 r'<h1 class=\"entry-title\">(.*?)</h1>', webpage, 'title')
44 description = self._og_search_description(webpage, default=None)
46 rtmp_url = self._html_search_regex(
47 r'file\s*:\s*"(rtmp://[^/]+/vod/mp4:"\s*\+\s*"[^"]+"\s*\+\s*".mp4)"',
49 rtmp_url = re.sub(r'"\s*\+\s*"', '', rtmp_url)
50 formats = self._extract_wowza_formats(rtmp_url, article_id or display_id)
51 self._sort_formats(formats)
54 'id': article_id or display_id,
55 'display_id': display_id,
57 'description': description,