[crunchyroll] Fix title extraction (Closes #7396)
authorSergey M․ <dstftw@gmail.com>
Sat, 7 Nov 2015 13:25:59 +0000 (19:25 +0600)
committerSergey M․ <dstftw@gmail.com>
Sat, 7 Nov 2015 13:29:42 +0000 (19:29 +0600)
youtube_dl/extractor/crunchyroll.py

index 0c9b8ca024cb6022b0e0227dcad2065c64ba69eb..4243f3e2e24f8c4080b914a45dff4dede3340280 100644 (file)
@@ -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: