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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7
   8
   9 class TeleBruxellesIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(news|sport|dernier-jt)/?(?P<id>[^/#?]+)'
  11     _TESTS = [{
  12         'url': 'http://www.telebruxelles.be/news/auditions-devant-parlement-francken-galant-tres-attendus/',
  13         'md5': '59439e568c9ee42fb77588b2096b214f',
  14         'info_dict': {
  15             'id': '11942',
  16             'display_id': 'auditions-devant-parlement-francken-galant-tres-attendus',
  17             'ext': 'flv',
  18             'title': 'Parlement : Francken et Galant répondent aux interpellations de l’opposition',
  19             'description': 're:Les auditions des ministres se poursuivent*'
  20         },
  21         'params': {
  22             'skip_download': 'requires rtmpdump'
  23         },
  24     }, {
  25         'url': 'http://www.telebruxelles.be/sport/basket-brussels-bat-mons-80-74/',
  26         'md5': '181d3fbdcf20b909309e5aef5c6c6047',
  27         'info_dict': {
  28             'id': '10091',
  29             'display_id': 'basket-brussels-bat-mons-80-74',
  30             'ext': 'flv',
  31             'title': 'Basket : le Brussels bat Mons 80-74',
  32             'description': 're:^Ils l\u2019on fait ! En basket, le B*',
  33         },
  34         'params': {
  35             'skip_download': 'requires rtmpdump'
  36         },
  37     }]
  38
  39     def _real_extract(self, url):
  40         display_id = self._match_id(url)
  41         webpage = self._download_webpage(url, display_id)
  42
  43         article_id = self._html_search_regex(
  44             r"<article id=\"post-(\d+)\"", webpage, 'article ID', default=None)
  45         title = self._html_search_regex(
  46             r'<h1 class=\"entry-title\">(.*?)</h1>', webpage, 'title')
  47         description = self._og_search_description(webpage, default=None)
  48
  49         rtmp_url = self._html_search_regex(
  50             r'file\s*:\s*"(rtmp://[^/]+/vod/mp4:"\s*\+\s*"[^"]+"\s*\+\s*".mp4)"',
  51             webpage, 'RTMP url')
  52         rtmp_url = re.sub(r'"\s*\+\s*"', '', rtmp_url)
  53
  54         return {
  55             'id': article_id or display_id,
  56             'display_id': display_id,
  57             'title': title,
  58             'description': description,
  59             'url': rtmp_url,
  60             'ext': 'flv',
  61             'rtmp_live': True  # if rtmpdump is not called with "--live" argument, the download is blocked and can be completed
  62         }