From 951070957516f0044c5dc89bc5ff3c74c30bd0db Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Fri, 10 Feb 2017 22:16:20 +0700 Subject: [PATCH] [bloomberg] Add another video id regex (closes #12062) --- youtube_dl/extractor/bloomberg.py | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index c5e11e8eb..2fbfad1ba 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -33,6 +33,10 @@ class BloombergIE(InfoExtractor): 'params': { 'format': 'best[format_id^=hds]', }, + }, { + # data-bmmrid= + 'url': 'https://www.bloomberg.com/politics/articles/2017-02-08/le-pen-aide-briefed-french-central-banker-on-plan-to-print-money', + 'only_matching': True, }, { 'url': 'http://www.bloomberg.com/news/articles/2015-11-12/five-strange-things-that-have-been-happening-in-financial-markets', 'only_matching': True, @@ -45,9 +49,10 @@ def _real_extract(self, url): name = self._match_id(url) webpage = self._download_webpage(url, name) video_id = self._search_regex( - (r'["\']bmmrId["\']\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', - r'videoId\s*:\s*(["\'])(?P(?:(?!\1).)+)\1'), - webpage, 'id', group='url', default=None) + (r'["\']bmmrId["\']\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', + r'videoId\s*:\s*(["\'])(?P(?:(?!\1).)+)\1', + r'data-bmmrid=(["\'])(?P(?:(?!\1).)+)\1'), + webpage, 'id', group='id', default=None) if not video_id: bplayer_data = self._parse_json(self._search_regex( r'BPlayer\(null,\s*({[^;]+})\);', webpage, 'id'), name)