@@ -0,0 +1,51 @@
1+#!/usr/bin/env python
2+
3+from urllib import urlencode
4+from urlparse import unquote
5+from lxml import html
6+from searx.engines.xpath import extract_text, extract_url
7+
8+categories = ['news']
9+search_url = 'http://news.search.yahoo.com/search?{query}&b={offset}'
10+results_xpath = '//div[@class="res"]'
11+url_xpath = './/h3/a/@href'
12+title_xpath = './/h3/a'
13+content_xpath = './/div[@class="abstr"]'
14+suggestion_xpath = '//div[@id="satat"]//a'
15+
16+paging = True
17+
18+
19+def request(query, params):
20+ offset = (params['pageno'] - 1) * 10 + 1
21+ if params['language'] == 'all':
22+ language = 'en'
23+ else:
24+ language = params['language'].split('_')[0]
25+ params['url'] = search_url.format(offset=offset,
26+ query=urlencode({'p': query}))
27+ params['cookies']['sB'] = 'fl=1&vl=lang_{lang}&sh=1&rw=new&v=1'\
28+ .format(lang=language)
29+ return params
30+
31+
32+def response(resp):
33+ results = []
34+ dom = html.fromstring(resp.text)
35+
36+ for result in dom.xpath(results_xpath):
37+ url_string = extract_url(result.xpath(url_xpath), search_url)
38+ start = url_string.find('/RU=')+4
39+ end = url_string.rfind('/RS')
40+ url = unquote(url_string[start:end])
41+ title = extract_text(result.xpath(title_xpath)[0])
42+ content = extract_text(result.xpath(content_xpath)[0])
43+ results.append({'url': url, 'title': title, 'content': content})
44+
45+ if not suggestion_xpath:
46+ return results
47+
48+ for suggestion in dom.xpath(suggestion_xpath):
49+ results.append({'suggestion': extract_text(suggestion)})
50+
51+ return results