From 452908b257da1a5b228a2c0522c89fff87296622 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Mon, 11 Apr 2016 00:06:05 +0600 Subject: [PATCH] [telebruxelles] Fix extraction (Closes #9142) --- youtube_dl/extractor/telebruxelles.py | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/youtube_dl/extractor/telebruxelles.py b/youtube_dl/extractor/telebruxelles.py index a3d05f97d..eefecc490 100644 --- a/youtube_dl/extractor/telebruxelles.py +++ b/youtube_dl/extractor/telebruxelles.py @@ -1,11 +1,13 @@ # coding: utf-8 from __future__ import unicode_literals +import re + from .common import InfoExtractor class TeleBruxellesIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?telebruxelles\.be/(news|sport|dernier-jt)/?(?P[^/#?]+)' + _VALID_URL = r'https?://(?:www\.)?(?:telebruxelles|bx1)\.be/(news|sport|dernier-jt)/?(?P[^/#?]+)' _TESTS = [{ 'url': 'http://www.telebruxelles.be/news/auditions-devant-parlement-francken-galant-tres-attendus/', 'md5': '59439e568c9ee42fb77588b2096b214f', @@ -39,18 +41,18 @@ def _real_extract(self, url): webpage = self._download_webpage(url, display_id) article_id = self._html_search_regex( - r"
(.*?)', webpage, 'title') - description = self._og_search_description(webpage) + description = self._og_search_description(webpage, default=None) 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)\"", + r'file\s*:\s*"(rtmp://[^/]+/vod/mp4:"\s*\+\s*"[^"]+"\s*\+\s*".mp4)"', webpage, 'RTMP url') - rtmp_url = rtmp_url.replace("\" + \"", "") + rtmp_url = re.sub(r'"\s*\+\s*"', '', rtmp_url) return { - 'id': article_id, + 'id': article_id or display_id, 'display_id': display_id, 'title': title, 'description': description,