From aed99a6272023d99e2cdea5a19a5922214c25661 Mon Sep 17 00:00:00 2001 From: Yuval Adam Date: Mon, 27 Jan 2014 14:50:43 +0200 Subject: Filter blank lins on ynet --- newsdiff/core/parsers/ynet.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/newsdiff/core/parsers/ynet.py b/newsdiff/core/parsers/ynet.py index 767594e..769d238 100644 --- a/newsdiff/core/parsers/ynet.py +++ b/newsdiff/core/parsers/ynet.py @@ -33,7 +33,7 @@ class YnetParser(HtmlSoupParser): time = re.findall(r'\d\d:\d\d', author_bar.text)[0] article_date = self.TIMEZONE.localize(datetime.strptime(' '.join([date, time]), '%d.%m.%y %H:%M')) article_body = soup.find('div', class_='art_body').find_all('p') - article_text = '\n'.join([p.text.strip().encode('iso-8859-1') for p in article_body]) + article_text = '\n'.join([p.text.strip().encode('iso-8859-1') for p in article_body if p.text]) with transaction.atomic(), reversion.create_revision(): try: -- cgit v1.3.1