From: Brett Parker Date: Wed, 16 Jan 2008 21:40:43 +0000 (+0000) Subject: More unicode fixes X-Git-Url: https://git.sommitrealweird.co.uk/rss2maildir.git/commitdiff_plain/c6030cecee302e61b7b1ada21676481c099728b4?ds=sidebyside More unicode fixes --- diff --git a/rss2maildir.py b/rss2maildir.py index 5d991e7..b914286 100755 --- a/rss2maildir.py +++ b/rss2maildir.py @@ -235,8 +235,7 @@ class HTML2Text(HTMLParser): if tag_thats_done in ["h1", "h2", "h3", "h4", "h5", "h6"]: underline = u'' underlinechar = u'=' - headingtext = unicode( \ - self.curdata.encode("utf-8").strip(), "utf-8") + headingtext = self.curdata seperator = u'\n' + u' '*self.indentlevel headingtext = seperator.join( \ textwrap.wrap( \ @@ -257,7 +256,7 @@ class HTML2Text(HTMLParser): underline = u' ' * self.indentlevel \ + underlinechar * len(headingtext) self.text = self.text \ - + headingtext.encode("utf-8") + u'\n' \ + + headingtext + u'\n' \ + underline elif tag_thats_done in [u'p', u'div']: paragraph = unicode( \ @@ -414,7 +413,7 @@ class HTML2Text(HTMLParser): def handle_data(self, data): if len(self.opentags) == 0: self.opentags.append(u'p') - self.curdata = self.curdata + unicode(data, "utf-8") + self.curdata = self.curdata + data.decode("utf-8") def handle_entityref(self, name): entity = name