From: Sergey M․ Date: Sat, 9 Dec 2017 12:52:31 +0000 (+0700) Subject: [udemy] Improve course id extraction (closes #14938) X-Git-Url: http://git.bitcoin.ninja/?a=commitdiff_plain;h=6f1ec339a0332041d6469887a91cf4e3ff557477;p=youtube-dl [udemy] Improve course id extraction (closes #14938) --- diff --git a/youtube_dl/extractor/udemy.py b/youtube_dl/extractor/udemy.py index c248ea727..b66033923 100644 --- a/youtube_dl/extractor/udemy.py +++ b/youtube_dl/extractor/udemy.py @@ -62,11 +62,11 @@ class UdemyIE(InfoExtractor): def _extract_course_info(self, webpage, video_id): course = self._parse_json( unescapeHTML(self._search_regex( - r'ng-init=["\'].*\bcourse=({.+?});', webpage, 'course', default='{}')), + r'ng-init=["\'].*\bcourse=({.+?})[;"\']', + webpage, 'course', default='{}')), video_id, fatal=False) or {} course_id = course.get('id') or self._search_regex( - (r'"id"\s*:\s*(\d+)', r'data-course-id=["\'](\d+)'), - webpage, 'course id') + r'data-course-id=["\'](\d+)', webpage, 'course id') return course_id, course.get('title') def _enroll_course(self, base_url, webpage, course_id):