yt_dlp/extractor/telebruxelles.py

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class TeleBruxellesIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(?:[^/]+/)*(?P<id>[^/#?]+)'
   8     _TESTS = [{
   9         'url': 'http://bx1.be/news/que-risque-lauteur-dune-fausse-alerte-a-la-bombe/',
  10         'md5': 'a2a67a5b1c3e8c9d33109b902f474fd9',
  11         'info_dict': {
  12             'id': '158856',
  13             'display_id': 'que-risque-lauteur-dune-fausse-alerte-a-la-bombe',
  14             'ext': 'mp4',
  15             'title': 'Que risque l’auteur d’une fausse alerte à la bombe ?',
  16             'description': 'md5:3cf8df235d44ebc5426373050840e466',
  17         },
  18     }, {
  19         'url': 'http://bx1.be/sport/futsal-schaerbeek-sincline-5-3-a-thulin/',
  20         'md5': 'dfe07ecc9c153ceba8582ac912687675',
  21         'info_dict': {
  22             'id': '158433',
  23             'display_id': 'futsal-schaerbeek-sincline-5-3-a-thulin',
  24             'ext': 'mp4',
  25             'title': 'Futsal : Schaerbeek s’incline 5-3 à Thulin',
  26             'description': 'md5:fd013f1488d5e2dceb9cebe39e2d569b',
  27         },
  28     }, {
  29         'url': 'http://bx1.be/emission/bxenf1-gastronomie/',
  30         'only_matching': True,
  31     }, {
  32         'url': 'https://bx1.be/berchem-sainte-agathe/personnel-carrefour-de-berchem-sainte-agathe-inquiet/',
  33         'only_matching': True,
  34     }, {
  35         'url': 'https://bx1.be/dernier-jt/',
  36         'only_matching': True,
  37     }, {
  38         # live stream
  39         'url': 'https://bx1.be/lives/direct-tv/',
  40         'only_matching': True,
  41     }]
  42
  43     def _real_extract(self, url):
  44         display_id = self._match_id(url)
  45         webpage = self._download_webpage(url, display_id)
  46
  47         article_id = self._html_search_regex(
  48             r'<article[^>]+\bid=["\']post-(\d+)', webpage, 'article ID', default=None)
  49         title = self._html_search_regex(
  50             r'<h1[^>]*>(.+?)</h1>', webpage, 'title',
  51             default=None) or self._og_search_title(webpage)
  52         description = self._og_search_description(webpage, default=None)
  53
  54         rtmp_url = self._html_search_regex(
  55             r'file["\']?\s*:\s*"(r(?:tm|mt)ps?://[^/]+/(?:vod/mp4:"\s*\+\s*"[^"]+"\s*\+\s*"\.mp4|stream/live))"',
  56             webpage, 'RTMP url')
  57         # Yes, they have a typo in scheme name for live stream URLs (e.g.
  58         # https://bx1.be/lives/direct-tv/)
  59         rtmp_url = re.sub(r'^rmtp', 'rtmp', rtmp_url)
  60         rtmp_url = re.sub(r'"\s*\+\s*"', '', rtmp_url)
  61         formats = self._extract_wowza_formats(rtmp_url, article_id or display_id)
  62
  63         is_live = 'stream/live' in rtmp_url
  64
  65         return {
  66             'id': article_id or display_id,
  67             'display_id': display_id,
  68             'title': title,
  69             'description': description,
  70             'formats': formats,
  71             'is_live': is_live,
  72         }