summaryrefslogtreecommitdiff
path: root/searx/engines/yahoo_news.py
diff options
context:
space:
mode:
authorThomas Pointhuber <thomas.pointhuber@gmx.at>2014-03-14 09:55:04 +0100
committerThomas Pointhuber <thomas.pointhuber@gmx.at>2014-03-14 09:55:11 +0100
commitb88146d669b1196ed1efc4ae4108e238cfd7dbca (patch)
treea960b54ea6673059bbbf9fc25addde39ea5a8859 /searx/engines/yahoo_news.py
parenta559bad4884fa9dc60d44cd580812e1e2fedef80 (diff)
downloadsearxng-b88146d669b1196ed1efc4ae4108e238cfd7dbca.tar.gz
searxng-b88146d669b1196ed1efc4ae4108e238cfd7dbca.zip
showing publishedDate for news
Diffstat (limited to 'searx/engines/yahoo_news.py')
-rw-r--r--searx/engines/yahoo_news.py7
1 files changed, 6 insertions, 1 deletions
diff --git a/searx/engines/yahoo_news.py b/searx/engines/yahoo_news.py
index 35e323917..c9789240d 100644
--- a/searx/engines/yahoo_news.py
+++ b/searx/engines/yahoo_news.py
@@ -4,6 +4,7 @@ from urllib import urlencode
from lxml import html
from searx.engines.xpath import extract_text, extract_url
from searx.engines.yahoo import parse_url
+from datetime import datetime
categories = ['news']
search_url = 'http://news.search.yahoo.com/search?{query}&b={offset}'
@@ -11,6 +12,7 @@ results_xpath = '//div[@class="res"]'
url_xpath = './/h3/a/@href'
title_xpath = './/h3/a'
content_xpath = './/div[@class="abstr"]'
+publishedDate_xpath = './/span[@class="timestamp"]'
suggestion_xpath = '//div[@id="satat"]//a'
paging = True
@@ -37,7 +39,10 @@ def response(resp):
url = parse_url(extract_url(result.xpath(url_xpath), search_url))
title = extract_text(result.xpath(title_xpath)[0])
content = extract_text(result.xpath(content_xpath)[0])
- results.append({'url': url, 'title': title, 'content': content})
+# Feb 20 04:02am
+ publishedDate = datetime.strptime(extract_text(result.xpath(publishedDate_xpath)[0]),"%b %d %H:%M%p")
+ #publishedDate.replace(year=2014)
+ results.append({'url': url, 'title': title, 'content': content,'publishedDate':publishedDate})
if not suggestion_xpath:
return results