Improve some unicode regular expressions
authorRicardo Garcia <sarbalap+freshmeat@gmail.com>
Tue, 22 Jul 2008 07:53:05 +0000 (09:53 +0200)
committerRicardo Garcia <devnull@localhost>
Tue, 22 Jul 2008 07:53:05 +0000 (09:53 +0200)
youtube-dl

index 0df6ba14104cdefc0761d31a57225c10bb5d3772..914cce37bcc24e76960f66dfb35b04903ce304a9 100755 (executable)
@@ -155,7 +155,7 @@ class FileDownloader(object):
        
        def fixed_template(self):
                """Checks if the output template is fixed."""
-               return (re.search(ur'%\(.+?\)s', self._params['outtmpl']) is None)
+               return (re.search(ur'(?u)%\(.+?\)s', self._params['outtmpl']) is None)
 
        def download(self, url_list):
                """Download a given list of URLs."""
@@ -419,11 +419,11 @@ class YoutubeIE(InfoExtractor):
                        self.to_stderr('ERROR: Unable to extract video title')
                        return [None]
                video_title = mobj.group(1).decode('utf-8')
-               video_title = re.sub(u'&(.+?);', lambda x: unichr(htmlentitydefs.name2codepoint[x.group(1)]), video_title)
+               video_title = re.sub(ur'(?u)&(.+?);', lambda x: unichr(htmlentitydefs.name2codepoint[x.group(1)]), video_title)
 
                # simplified title
-               simple_title = re.sub(u'([^%s]+)' % simple_title_chars, u'_', video_title)
-               simple_title = simple_title.strip(u'_')
+               simple_title = re.sub(ur'(?u)([^%s]+)' % simple_title_chars, ur'_', video_title)
+               simple_title = simple_title.strip(ur'_')
 
                # Return information
                return [{