mirror of
https://github.com/YunoHost-Apps/searx_ynh.git
synced 2024-09-03 20:16:30 +02:00
86 lines
2.2 KiB
Python
86 lines
2.2 KiB
Python
"""
|
|
Bing (Web)
|
|
|
|
@website https://www.bing.com
|
|
@provide-api yes (http://datamarket.azure.com/dataset/bing/search),
|
|
max. 5000 query/month
|
|
|
|
@using-api no (because of query limit)
|
|
@results HTML (using search portal)
|
|
@stable no (HTML can change)
|
|
@parse url, title, content
|
|
|
|
@todo publishedDate
|
|
"""
|
|
|
|
from urllib import urlencode
|
|
from cgi import escape
|
|
from lxml import html
|
|
from searx.engines.xpath import extract_text
|
|
|
|
# engine dependent config
|
|
categories = ['general']
|
|
paging = True
|
|
language_support = True
|
|
|
|
# search-url
|
|
base_url = 'https://www.bing.com/'
|
|
search_string = 'search?{query}&first={offset}'
|
|
|
|
|
|
# do search-request
|
|
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]
|
|
|
|
params['url'] = base_url + search_path
|
|
return params
|
|
|
|
|
|
# get response from search-request
|
|
def response(resp):
|
|
results = []
|
|
|
|
dom = html.fromstring(resp.text)
|
|
|
|
# parse results
|
|
for result in dom.xpath('//div[@class="sa_cc"]'):
|
|
link = result.xpath('.//h3/a')[0]
|
|
url = link.attrib.get('href')
|
|
title = extract_text(link)
|
|
content = escape(extract_text(result.xpath('.//p')))
|
|
|
|
# append result
|
|
results.append({'url': url,
|
|
'title': title,
|
|
'content': content})
|
|
|
|
# return results if something is found
|
|
if results:
|
|
return results
|
|
|
|
# parse results again if nothing is found yet
|
|
for result in dom.xpath('//li[@class="b_algo"]'):
|
|
link = result.xpath('.//h2/a')[0]
|
|
url = link.attrib.get('href')
|
|
title = extract_text(link)
|
|
content = escape(extract_text(result.xpath('.//p')))
|
|
|
|
# append result
|
|
results.append({'url': url,
|
|
'title': title,
|
|
'content': content})
|
|
|
|
# return results
|
|
return results
|