You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

76 lines
2.9 KiB

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