mirror of
https://github.com/searxng/searxng.git
synced 2024-11-27 13:21:04 +00:00
51 lines
1.6 KiB
Python
51 lines
1.6 KiB
Python
#!/usr/bin/env python
|
|
|
|
from urllib import urlencode
|
|
from urlparse import unquote
|
|
from lxml import html
|
|
from searx.engines.xpath import extract_text, extract_url
|
|
|
|
categories = ['news']
|
|
search_url = 'http://news.search.yahoo.com/search?{query}&b={offset}'
|
|
results_xpath = '//div[@class="res"]'
|
|
url_xpath = './/h3/a/@href'
|
|
title_xpath = './/h3/a'
|
|
content_xpath = './/div[@class="abstr"]'
|
|
suggestion_xpath = '//div[@id="satat"]//a'
|
|
|
|
paging = True
|
|
|
|
|
|
def request(query, params):
|
|
offset = (params['pageno'] - 1) * 10 + 1
|
|
if params['language'] == 'all':
|
|
language = 'en'
|
|
else:
|
|
language = params['language'].split('_')[0]
|
|
params['url'] = search_url.format(offset=offset,
|
|
query=urlencode({'p': query}))
|
|
params['cookies']['sB'] = 'fl=1&vl=lang_{lang}&sh=1&rw=new&v=1'\
|
|
.format(lang=language)
|
|
return params
|
|
|
|
|
|
def response(resp):
|
|
results = []
|
|
dom = html.fromstring(resp.text)
|
|
|
|
for result in dom.xpath(results_xpath):
|
|
url_string = extract_url(result.xpath(url_xpath), search_url)
|
|
start = url_string.find('http', url_string.find('/RU=')+1)
|
|
end = url_string.rfind('/RS')
|
|
url = unquote(url_string[start:end])
|
|
title = extract_text(result.xpath(title_xpath)[0])
|
|
content = extract_text(result.xpath(content_xpath)[0])
|
|
results.append({'url': url, 'title': title, 'content': content})
|
|
|
|
if not suggestion_xpath:
|
|
return results
|
|
|
|
for suggestion in dom.xpath(suggestion_xpath):
|
|
results.append({'suggestion': extract_text(suggestion)})
|
|
|
|
return results
|