diff options
| author | Sergey M․ <dstftw@gmail.com> | 2015-11-07 19:25:59 +0600 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2015-11-07 19:29:42 +0600 |
| commit | 5214f1e31d5e5ba692fb1ed4803ff71ef4e480e8 (patch) | |
| tree | efc90cc38e7bf34da2f5b96b4c2b5a84d87c2e0c | |
| parent | 5d0f84d32cc038dd71673987cb6efaa85e953474 (diff) | |
[crunchyroll] Fix title extraction (Closes #7396)
| -rw-r--r-- | youtube_dl/extractor/crunchyroll.py | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/youtube_dl/extractor/crunchyroll.py b/youtube_dl/extractor/crunchyroll.py index 0c9b8ca02..4243f3e2e 100644 --- a/youtube_dl/extractor/crunchyroll.py +++ b/youtube_dl/extractor/crunchyroll.py @@ -287,7 +287,9 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text if 'To view this, please log in to verify you are 18 or older.' in webpage: self.raise_login_required() - video_title = self._html_search_regex(r'<h1[^>]*>(.+?)</h1>', webpage, 'video_title', flags=re.DOTALL) + video_title = self._html_search_regex( + r'(?s)<h1[^>]*>((?:(?!<h1).)*?<span[^>]+itemprop=["\']title["\'][^>]*>(?:(?!<h1).)+?)</h1>', + webpage, 'video_title') video_title = re.sub(r' {2,}', ' ', video_title) video_description = self._html_search_regex(r'"description":"([^"]+)', webpage, 'video_description', default='') if not video_description: |