]> git.bitcoin.ninja Git - youtube-dl/commitdiff
[crunchyroll] Relax series and season regex (closes #13659)
authorSergey M․ <dstftw@gmail.com>
Sun, 16 Jul 2017 05:40:45 +0000 (12:40 +0700)
committerSergey M․ <dstftw@gmail.com>
Sun, 16 Jul 2017 05:40:45 +0000 (12:40 +0700)
youtube_dl/extractor/crunchyroll.py

index 2ffa4a7f8b28f908074cd3b4622d11468e740192..8bdaf0c2c5af7aa1a562033487a16867c3304f19 100644 (file)
@@ -510,7 +510,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
         # webpage provide more accurate data than series_title from XML
         series = self._html_search_regex(
-            r'id=["\']showmedia_about_episode_num[^>]+>\s*<a[^>]+>([^<]+)',
+            r'(?s)<h\d[^>]+\bid=["\']showmedia_about_episode_num[^>]+>(.+?)</h\d',
             webpage, 'series', fatal=False)
         season = xpath_text(metadata, 'series_title')
 
@@ -518,7 +518,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
         episode_number = int_or_none(xpath_text(metadata, 'episode_number'))
 
         season_number = int_or_none(self._search_regex(
-            r'(?s)<h4[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h4>\s*<h4>\s*Season (\d+)',
+            r'(?s)<h\d[^>]+id=["\']showmedia_about_episode_num[^>]+>.+?</h\d>\s*<h4>\s*Season (\d+)',
             webpage, 'season number', default=None))
 
         return {