summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYuval Adam <yuv.adm@gmail.com>2014-01-25 01:19:59 +0100
committerYuval Adam <yuv.adm@gmail.com>2014-01-25 01:19:59 +0100
commitf7a2b95d2f2c3183355718e3a3ee43ea1f6f207e (patch)
tree5edf6924c995ef6d1837c43cb87a9828b3be3969
parentfe31e8e2bf76f182f25a452e0985b2a94f18293a (diff)
Fix Ynet encoding issues
-rw-r--r--newsdiff/core/parsers/ynet.py8
-rw-r--r--newsdiff/settings/base.py8
2 files changed, 8 insertions, 8 deletions
diff --git a/newsdiff/core/parsers/ynet.py b/newsdiff/core/parsers/ynet.py
index 112c0bd..1e533c9 100644
--- a/newsdiff/core/parsers/ynet.py
+++ b/newsdiff/core/parsers/ynet.py
@@ -25,15 +25,15 @@ class YnetParser(HtmlSoupParser):
def parse_article(self, url, soup):
ynet_id = re.findall(self.ARTICLE_ID_PATTERN, url)[0]
- title = soup.find('div', class_='art_header_title').text.strip()
- subtitle = soup.find('div', class_='art_header_sub_title').text.strip()
+ title = soup.find('div', class_='art_header_title').text.strip().encode('iso-8859-1')
+ subtitle = soup.find('div', class_='art_header_sub_title').text.strip().encode('iso-8859-1')
author_bar = soup.find('span', class_='art_header_footer_author')
- author = author_bar.find('a').text.strip()
+ author = author_bar.find('a').text.strip().encode('iso-8859-1')
date = re.findall(r'\d\d.\d\d.\d\d', author_bar.text)[0]
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() for p in article_body])
+ article_text = '\n'.join([p.text.strip().encode('iso-8859-1') for p in article_body])
with transaction.atomic(), reversion.create_revision():
try:
diff --git a/newsdiff/settings/base.py b/newsdiff/settings/base.py
index 0f5f4d7..4e3d75d 100644
--- a/newsdiff/settings/base.py
+++ b/newsdiff/settings/base.py
@@ -136,8 +136,8 @@ CELERYBEAT_SCHEDULE = {
'task': 'newsdiff.core.tasks.process_haaretz_homepage',
'schedule': timedelta(minutes=15)
},
- # 'ynet_homepage': {
- # 'task': 'newsdiff.core.tasks.process_ynet_homepage',
- # 'schedule': timedelta(minutes=15)
- # }
+ 'ynet_homepage': {
+ 'task': 'newsdiff.core.tasks.process_ynet_homepage',
+ 'schedule': timedelta(minutes=15)
+ }
}