Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/telebruxelles.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5
   6
   7 class TeleBruxellesIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?telebruxelles\.be/(news|sport|dernier-jt)/?(?P<id>[^/#?]+)'
   9     _TESTS = [{
  10         'url': 'http://www.telebruxelles.be/news/auditions-devant-parlement-francken-galant-tres-attendus/',
  11         'md5': '59439e568c9ee42fb77588b2096b214f',
  12         'info_dict': {
  13             'id': '11942',
  14             'display_id': 'auditions-devant-parlement-francken-galant-tres-attendus',
  15             'ext': 'flv',
  16             'title': 'Parlement : Francken et Galant répondent aux interpellations de l’opposition',
  17             'description': 're:Les auditions des ministres se poursuivent*'
  18         },
  19         'params': {
  20             'skip_download': 'requires rtmpdump'
  21         },
  22     }, {
  23         'url': 'http://www.telebruxelles.be/sport/basket-brussels-bat-mons-80-74/',
  24         'md5': '181d3fbdcf20b909309e5aef5c6c6047',
  25         'info_dict': {
  26             'id': '10091',
  27             'display_id': 'basket-brussels-bat-mons-80-74',
  28             'ext': 'flv',
  29             'title': 'Basket : le Brussels bat Mons 80-74',
  30             'description': 're:^Ils l\u2019on fait ! En basket, le B*',
  31         },
  32         'params': {
  33             'skip_download': 'requires rtmpdump'
  34         },
  35     }]
  36
  37     def _real_extract(self, url):
  38         display_id = self._match_id(url)
  39         webpage = self._download_webpage(url, display_id)
  40
  41         article_id = self._html_search_regex(
  42             r"<article id=\"post-(\d+)\"", webpage, 'article ID')
  43         title = self._html_search_regex(
  44             r'<h1 class=\"entry-title\">(.*?)</h1>', webpage, 'title')
  45         description = self._og_search_description(webpage)
  46
  47         rtmp_url = self._html_search_regex(
  48             r"file: \"(rtmp://\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}:\d{1,5}/vod/mp4:\" \+ \"\w+\" \+ \".mp4)\"",
  49             webpage, 'RTMP url')
  50         rtmp_url = rtmp_url.replace("\" + \"", "")
  51
  52         return {
  53             'id': article_id,
  54             'display_id': display_id,
  55             'title': title,
  56             'description': description,
  57             'url': rtmp_url,
  58             'ext': 'flv',
  59             'rtmp_live': True  # if rtmpdump is not called with "--live" argument, the download is blocked and can be completed
  60         }