diff options
| author | Sergey M․ <dstftw@gmail.com> | 2017-12-09 19:52:31 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2017-12-09 20:02:49 +0700 |
| commit | 6f1ec339a0332041d6469887a91cf4e3ff557477 (patch) | |
| tree | 15c5958994a803cd5df41c030e984b43ce15dd9a | |
| parent | a3de5e6c0e0efef4e8ff0cd37961c594b13c7fb9 (diff) | |
[udemy] Improve course id extraction (closes #14938)
| -rw-r--r-- | youtube_dl/extractor/udemy.py | 6 |
1 files changed, 3 insertions, 3 deletions
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): |