From b88146d669b1196ed1efc4ae4108e238cfd7dbca Mon Sep 17 00:00:00 2001 From: Thomas Pointhuber Date: Fri, 14 Mar 2014 09:55:04 +0100 Subject: [PATCH] showing publishedDate for news --- searx/engines/google_news.py | 9 +++++++++ searx/engines/yahoo_news.py | 7 ++++++- searx/templates/result_templates/default.html | 1 + searx/webapp.py | 12 ++++++++++++ 4 files changed, 28 insertions(+), 1 deletion(-) diff --git a/searx/engines/google_news.py b/searx/engines/google_news.py index 935718609..afda3e756 100644 --- a/searx/engines/google_news.py +++ b/searx/engines/google_news.py @@ -2,6 +2,7 @@ from urllib import urlencode from json import loads +from datetime import datetime, timedelta categories = ['news'] @@ -31,7 +32,15 @@ def response(resp): 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 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 diff --git a/searx/templates/result_templates/default.html b/searx/templates/result_templates/default.html index d06a4598a..e0711b761 100644 --- a/searx/templates/result_templates/default.html +++ b/searx/templates/result_templates/default.html @@ -6,6 +6,7 @@

{{ result.title|safe }}

+ {% if result.publishedDate %}

{{ result.publishedDate }}

{% endif %}

{% if result.content %}{{ result.content|safe }}
{% endif %}

{{ result.pretty_url }}

diff --git a/searx/webapp.py b/searx/webapp.py index fdb6568b4..2f7f131c8 100644 --- a/searx/webapp.py +++ b/searx/webapp.py @@ -26,6 +26,7 @@ import json 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, @@ -156,6 +157,17 @@ def index(): 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}),