X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/b8d8e13c1f9e4d3cdd7d41c5c9d711a36dd5f9c3..68c3607ca2d7bdfc72afc94ca5dc6034b41e7bfa:/youtube_dl/extractor/telebruxelles.py?ds=inline diff --git a/youtube_dl/extractor/telebruxelles.py b/youtube_dl/extractor/telebruxelles.py index 5886e9c..a0353fe 100644 --- a/youtube_dl/extractor/telebruxelles.py +++ b/youtube_dl/extractor/telebruxelles.py @@ -7,7 +7,7 @@ from .common import InfoExtractor class TeleBruxellesIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(news|sport|dernier-jt|emission)/?(?P[^/#?]+)' + _VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(?:[^/]+/)*(?P[^/#?]+)' _TESTS = [{ 'url': 'http://bx1.be/news/que-risque-lauteur-dune-fausse-alerte-a-la-bombe/', 'md5': 'a2a67a5b1c3e8c9d33109b902f474fd9', @@ -31,6 +31,16 @@ class TeleBruxellesIE(InfoExtractor): }, { 'url': 'http://bx1.be/emission/bxenf1-gastronomie/', 'only_matching': True, + }, { + 'url': 'https://bx1.be/berchem-sainte-agathe/personnel-carrefour-de-berchem-sainte-agathe-inquiet/', + 'only_matching': True, + }, { + 'url': 'https://bx1.be/dernier-jt/', + 'only_matching': True, + }, { + # live stream + 'url': 'https://bx1.be/lives/direct-tv/', + 'only_matching': True, }] def _real_extract(self, url): @@ -38,22 +48,29 @@ class TeleBruxellesIE(InfoExtractor): webpage = self._download_webpage(url, display_id) article_id = self._html_search_regex( - r"
]+\bid=["\']post-(\d+)', webpage, 'article ID', default=None) title = self._html_search_regex( - r'

(.*?)

', webpage, 'title') + r']*>(.+?)', webpage, 'title', + default=None) or self._og_search_title(webpage) description = self._og_search_description(webpage, default=None) rtmp_url = self._html_search_regex( - r'file\s*:\s*"(rtmp://[^/]+/vod/mp4:"\s*\+\s*"[^"]+"\s*\+\s*".mp4)"', + r'file["\']?\s*:\s*"(r(?:tm|mt)ps?://[^/]+/(?:vod/mp4:"\s*\+\s*"[^"]+"\s*\+\s*"\.mp4|stream/live))"', webpage, 'RTMP url') + # Yes, they have a typo in scheme name for live stream URLs (e.g. + # https://bx1.be/lives/direct-tv/) + rtmp_url = re.sub(r'^rmtp', 'rtmp', rtmp_url) rtmp_url = re.sub(r'"\s*\+\s*"', '', rtmp_url) formats = self._extract_wowza_formats(rtmp_url, article_id or display_id) self._sort_formats(formats) + is_live = 'stream/live' in rtmp_url + return { 'id': article_id or display_id, 'display_id': display_id, - 'title': title, + 'title': self._live_title(title) if is_live else title, 'description': description, 'formats': formats, + 'is_live': is_live, }