mirror of
https://github.com/searxng/searxng.git
synced 2024-11-23 12:31:25 +01:00
51 lines
1.6 KiB
Python
51 lines
1.6 KiB
Python
|
from urllib import urlencode
|
||
|
|
from cgi import escape
|
||
|
|
from lxml import html
|
||
|
|
|
||
|
|
categories = ['news']
|
||
|
|
|
||
|
|
base_url = 'http://www.bing.com/'
|
||
|
|
search_string = 'news/search?{query}&first={offset}'
|
||
|
|
paging = True
|
||
|
|
language_support = True
|
||
|
|
|
||
|
|
|
||
|
|
def request(query, params):
|
||
|
|
offset = (params['pageno'] - 1) * 10 + 1
|
||
|
|
if params['language'] == 'all':
|
||
|
|
language = 'en-US'
|
||
|
|
else:
|
||
|
|
language = params['language'].replace('_', '-')
|
||
|
|
search_path = search_string.format(
|
||
|
|
query=urlencode({'q': query, 'setmkt': language}),
|
||
|
|
offset=offset)
|
||
|
|
|
||
|
|
params['cookies']['SRCHHPGUSR'] = \
|
||
|
|
'NEWWND=0&NRSLT=-1&SRCHLANG=' + language.split('-')[0]
|
||
|
|
#if params['category'] == 'images':
|
||
|
|
# params['url'] = base_url + 'images/' + search_path
|
||
|
|
params['url'] = base_url + search_path
|
||
|
|
return params
|
||
|
|
|
||
|
|
|
||
|
|
def response(resp):
|
||
|
|
results = []
|
||
|
|
dom = html.fromstring(resp.content)
|
||
|
|
for result in dom.xpath('//div[@class="sa_cc"]'):
|
||
|
|
link = result.xpath('.//h3/a')[0]
|
||
|
|
url = link.attrib.get('href')
|
||
|
|
title = ' '.join(link.xpath('.//text()'))
|
||
|
|
content = escape(' '.join(result.xpath('.//p//text()')))
|
||
|
|
results.append({'url': url, 'title': title, 'content': content})
|
||
|
|
|
||
|
|
if results:
|
||
|
|
return results
|
||
|
|
|
||
|
|
for result in dom.xpath('//li[@class="b_algo"]'):
|
||
|
|
link = result.xpath('.//h2/a')[0]
|
||
|
|
url = link.attrib.get('href')
|
||
|
|
title = ' '.join(link.xpath('.//text()'))
|
||
|
|
content = escape(' '.join(result.xpath('.//p//text()')))
|
||
|
|
results.append({'url': url, 'title': title, 'content': content})
|
||
|
|
return results
|