showing publishedDate for news

searx/engines/google_news.py

 
 from urllib import urlencode
 from json import loads
+from datetime import datetime, timedelta
 
 categories = ['news']
 
         return []
 
     for result in search_res['responseData']['results']:
+# S.149 (159), library.pdf
+# datetime.strptime("Mon, 10 Mar 2014 16:26:15 -0700", "%a, %d %b %Y %H:%M:%S %z")
+#        publishedDate = parse(result['publishedDate'])
+        publishedDate = datetime.strptime(str.join(' ',result['publishedDate'].split(None)[0:5]), "%a, %d %b %Y %H:%M:%S")
+        #utc_offset = timedelta(result['publishedDate'].split(None)[5])  # local = utc + offset
+        #publishedDate = publishedDate + utc_offset
+
         results.append({'url': result['unescapedUrl'],
                         'title': result['titleNoFormatting'],
+						'publishedDate': publishedDate,
                         'content': result['content']})
     return results

searx/engines/yahoo_news.py

 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}'
 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
         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

searx/templates/result_templates/default.html

 
   <div>
     <h3 class="result_title"><a href="{{ result.url }}">{{ result.title|safe }}</a></h3>
+	{% if result.publishedDate %}<p class="published_date">{{ result.publishedDate }}</p>{% endif %}
     <p class="content">{% if result.content %}{{ result.content|safe }}<br />{% endif %}</p>
     <p class="url">{{ result.pretty_url }}</p>
   </div>

searx/webapp.py

 import cStringIO
 import os
 
+from datetime import datetime, timedelta
 from itertools import chain
 from flask import (
     Flask, request, render_template, url_for, Response, make_response,
             if engine in favicons:
                 result['favicon'] = engine
 
+        # TODO, check if timezone is calculated right
+        if 'publishedDate' in result:
+            if result['publishedDate'].date() == datetime.now().date():
+                timedifference = datetime.now()-result['publishedDate']
+                if timedifference.seconds < 60*60:
+                    result['publishedDate'] = '{0:d} minutes ago'.format(timedifference.seconds/60)
+                else:
+                    result['publishedDate'] = '{0:d} hours ago'.format(timedifference.seconds/60/60)
+            else:
+                result['publishedDate'] = result['publishedDate'].strftime('%d.%m.%Y')
+
     if search.request_data.get('format') == 'json':
         return Response(json.dumps({'query': search.query,
                                     'results': search.results}),