_ Git - youtube-dl/blob - youtube_dl/extractor/telebruxelles.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import json
   6
   7 from .common import InfoExtractor
   8
   9
  10 class TeleBruxellesIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?telebruxelles\.be/(news|sport|dernier-jt)/?(?P<title>[^\?]+)'
  12     _TESTS = [{
  13         'url': r'http://www.telebruxelles.be/news/auditions-devant-parlement-francken-galant-tres-attendus/',
  14         'md5': '59439e568c9ee42fb77588b2096b214f',
  15         'info_dict': {
  16             'id': '11942',
  17             'ext': 'flv',
  18             'title': 're:Parlement : Francken et Galant répondent aux interpellations*',
  19                         'description': 're:Les auditions des ministres se poursuivent*'
  20         }
  21     }, {
  22         'url': r'http://www.telebruxelles.be/sport/basket-brussels-bat-mons-80-74/',
  23         'md5': '181d3fbdcf20b909309e5aef5c6c6047',
  24         'info_dict': {
  25             'id': '10091',
  26             'ext': 'flv',
  27             'title': 'Basket : le Brussels bat Mons 80-74',
  28                         'description': 're:Ils l\u2019on fait ! En basket, le B*'
  29         }
  30         }]
  31
  32     def _real_extract(self, url):
  33                 mobj = re.match(self._VALID_URL, url)
  34                 title = mobj.group('title')
  35
  36                 webpage = self._download_webpage(url, title)
  37
  38                 article_id = self._html_search_regex(r"<article id=\"post-(\d+)\"", webpage, '0')
  39                 title = self._html_search_regex(r'<h1 class=\"entry-title\">(.*?)</h1>', webpage, 'title')
  40                 description = self._html_search_regex(r"property=\"og:description\" content=\"(.*?)\"", webpage, 'description', fatal=False)
  41
  42                 rtmp_url = self._html_search_regex(r"file: \"(rtmp://\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}:\d{1,5}/vod/mp4:\" \+ \"\w+\" \+ \".mp4)\"", webpage, 'url')
  43                 rtmp_url = rtmp_url.replace("\" + \"", "")
  44
  45                 return {
  46                         'id': article_id,
  47                         'title': title,
  48                         'description': description,
  49                         'url': rtmp_url,
  50                         'ext': 'flv',
  51                         'rtmp_live': True              # if rtmpdump is not called with "--live" argument, the download is blocked and can be completed
  52                 }