summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYuval Adam <yuv.adm@gmail.com>2014-01-27 14:50:43 +0200
committerYuval Adam <yuv.adm@gmail.com>2014-01-27 14:50:43 +0200
commitaed99a6272023d99e2cdea5a19a5922214c25661 (patch)
tree8af47497820500f8714f4f565937a60278503c9e
parent883ef467898355edb0fa60642d40bbef3abe2c95 (diff)
Filter blank lins on ynet
-rw-r--r--newsdiff/core/parsers/ynet.py2
1 files changed, 1 insertions, 1 deletions
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: