From c54c01f82dba6d3e982c73c81ad71c49f31d8af1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 2 Feb 2017 23:03:38 +0700 Subject: [PATCH] [go] Relax video id regex (closes #11937) --- youtube_dl/extractor/go.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/youtube_dl/extractor/go.py b/youtube_dl/extractor/go.py index c7776b186..a34779b16 100644 --- a/youtube_dl/extractor/go.py +++ b/youtube_dl/extractor/go.py @@ -43,7 +43,10 @@ class GoIE(InfoExtractor): sub_domain, video_id, display_id = re.match(self._VALID_URL, url).groups() if not video_id: webpage = self._download_webpage(url, display_id) - video_id = self._search_regex(r'data-video-id=["\']VDKA(\w+)', webpage, 'video id') + video_id = self._search_regex( + # There may be inner quotes, e.g. data-video-id="'VDKA3609139'" + # from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood + r'data-video-id=["\']*VDKA(\w+)', webpage, 'video id') brand = self._BRANDS[sub_domain] video_data = self._download_json( 'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/%s/001/-1/-1/-1/%s/-1/-1.json' % (brand, video_id),