From b88146d669b1196ed1efc4ae4108e238cfd7dbca Mon Sep 17 00:00:00 2001 From: Thomas Pointhuber Date: Fri, 14 Mar 2014 09:55:04 +0100 Subject: showing publishedDate for news --- searx/engines/yahoo_news.py | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'searx/engines/yahoo_news.py') 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 -- cgit v1.2.3-54-g00ecf