b88146d · searx · git.iko.soy

searx/engines/google_news.py+9

compare with master

unifiedsplit

@@ -2,6 +2,7 @@

2

3from urllib import urlencode

4from json import loads

5+from datetime import datetime, timedelta

5

6

6categories = ['news']

7categories = ['news']

7

8

@@ -31,7 +32,15 @@ def response(resp):

31 return []

32 return []

32

33

33 for result in search_res['responseData']['results']:

34 for result in search_res['responseData']['results']:

35+# S.149 (159), library.pdf

36+# datetime.strptime("Mon, 10 Mar 2014 16:26:15 -0700", "%a, %d %b %Y %H:%M:%S %z")

37+# publishedDate = parse(result['publishedDate'])

38+ publishedDate = datetime.strptime(str.join(' ',result['publishedDate'].split(None)[0:5]), "%a, %d %b %Y %H:%M:%S")

39+ #utc_offset = timedelta(result['publishedDate'].split(None)[5]) # local = utc + offset

40+ #publishedDate = publishedDate + utc_offset

41+

34 results.append({'url': result['unescapedUrl'],

42 results.append({'url': result['unescapedUrl'],

35 'title': result['titleNoFormatting'],

43 'title': result['titleNoFormatting'],

44+ 'publishedDate': publishedDate,

36 'content': result['content']})

45 'content': result['content']})

37 return results

46 return results

searx/engines/yahoo_news.py+6−1

@@ -4,6 +4,7 @@ from urllib import urlencode

4from lxml import html

5from searx.engines.xpath import extract_text, extract_url

6from searx.engines.yahoo import parse_url

7+from datetime import datetime

7

8

8categories = ['news']

9categories = ['news']

9search_url = 'http://news.search.yahoo.com/search?{query}&b={offset}'

10search_url = 'http://news.search.yahoo.com/search?{query}&b={offset}'

@@ -11,6 +12,7 @@ results_xpath = '//div[@class="res"]'

11url_xpath = './/h3/a/@href'

12url_xpath = './/h3/a/@href'

12title_xpath = './/h3/a'

13title_xpath = './/h3/a'

13content_xpath = './/div[@class="abstr"]'

14content_xpath = './/div[@class="abstr"]'

15+publishedDate_xpath = './/span[@class="timestamp"]'

14suggestion_xpath = '//div[@id="satat"]//a'

16suggestion_xpath = '//div[@id="satat"]//a'

15

17

16paging = True

18paging = True

@@ -37,7 +39,10 @@ def response(resp):

37 url = parse_url(extract_url(result.xpath(url_xpath), search_url))

39 url = parse_url(extract_url(result.xpath(url_xpath), search_url))

38 title = extract_text(result.xpath(title_xpath)[0])

40 title = extract_text(result.xpath(title_xpath)[0])

39 content = extract_text(result.xpath(content_xpath)[0])

41 content = extract_text(result.xpath(content_xpath)[0])

42+# Feb 20 04:02am

43+ publishedDate = datetime.strptime(extract_text(result.xpath(publishedDate_xpath)[0]),"%b %d %H:%M%p")

44+ #publishedDate.replace(year=2014)

40− results.append({'url': url, 'title': title, 'content': content})

45+ results.append({'url': url, 'title': title, 'content': content,'publishedDate':publishedDate})

41

46

42 if not suggestion_xpath:

47 if not suggestion_xpath:

43 return results

48 return results

searx/templates/result_templates/default.html+1

@@ -6,6 +6,7 @@

6

7 <div>

8 <h3 class="result_title"><a href="{{ result.url }}">{{ result.title|safe }}</a></h3>

9+ {% if result.publishedDate %}<p class="published_date">{{ result.publishedDate }}</p>{% endif %}

9 <p class="content">{% if result.content %}{{ result.content|safe }}<br />{% endif %}</p>

10 <p class="content">{% if result.content %}{{ result.content|safe }}<br />{% endif %}</p>

10 <p class="url">{{ result.pretty_url }}</p>

11 <p class="url">{{ result.pretty_url }}</p>

11 </div>

12 </div>

searx/webapp.py+12

@@ -26,6 +26,7 @@ import json

26import cStringIO

27import os

28

29+from datetime import datetime, timedelta

29from itertools import chain

30from itertools import chain

30from flask import (

31from flask import (

31 Flask, request, render_template, url_for, Response, make_response,

32 Flask, request, render_template, url_for, Response, make_response,

@@ -156,6 +157,17 @@ def index():

156 if engine in favicons:

157 if engine in favicons:

157 result['favicon'] = engine

158 result['favicon'] = engine

158

159

160+ # TODO, check if timezone is calculated right

161+ if 'publishedDate' in result:

162+ if result['publishedDate'].date() == datetime.now().date():

163+ timedifference = datetime.now()-result['publishedDate']

164+ if timedifference.seconds < 60*60:

165+ result['publishedDate'] = '{0:d} minutes ago'.format(timedifference.seconds/60)

166+ else:

167+ result['publishedDate'] = '{0:d} hours ago'.format(timedifference.seconds/60/60)

168+ else:

169+ result['publishedDate'] = result['publishedDate'].strftime('%d.%m.%Y')

170+

159 if search.request_data.get('format') == 'json':

171 if search.request_data.get('format') == 'json':

160 return Response(json.dumps({'query': search.query,

172 return Response(json.dumps({'query': search.query,

161 'results': search.results}),

173 'results': search.results}),