1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-23 04:27:46 +01:00
searxng/searx/engines/stackoverflow.py
2021-04-10 15:38:33 +02:00

65 lines
1.6 KiB
Python

# SPDX-License-Identifier: AGPL-3.0-or-later
"""
Stackoverflow (IT)
"""
from urllib.parse import urlencode, urljoin
from lxml import html
from searx.utils import extract_text
from searx.exceptions import SearxEngineCaptchaException
# about
about = {
"website": 'https://stackoverflow.com/',
"wikidata_id": 'Q549037',
"official_api_documentation": 'https://api.stackexchange.com/docs',
"use_official_api": False,
"require_api_key": False,
"results": 'HTML',
}
# engine dependent config
categories = ['it']
paging = True
# search-url
url = 'https://stackoverflow.com/'
search_url = url + 'search?{query}&page={pageno}'
# specific xpath variables
results_xpath = '//div[contains(@class,"question-summary")]'
link_xpath = './/div[@class="result-link"]//a|.//div[@class="summary"]//h3//a'
content_xpath = './/div[@class="excerpt"]'
# do search-request
def request(query, params):
params['url'] = search_url.format(query=urlencode({'q': query}), pageno=params['pageno'])
return params
# get response from search-request
def response(resp):
if resp.url.path.startswith('/nocaptcha'):
raise SearxEngineCaptchaException()
results = []
dom = html.fromstring(resp.text)
# parse results
for result in dom.xpath(results_xpath):
link = result.xpath(link_xpath)[0]
href = urljoin(url, link.attrib.get('href'))
title = extract_text(link)
content = extract_text(result.xpath(content_xpath))
# append result
results.append({'url': href,
'title': title,
'content': content})
# return results
return results