mirror of
https://github.com/searxng/searxng
synced 2024-11-03 09:40:20 +00:00
[mod] replace old stackoverflow engine by Stack Exchange API v2.3
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
This commit is contained in:
parent
55fee1e45d
commit
b62851559b
@ -1,64 +0,0 @@
|
|||||||
# 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
|
|
@ -1125,8 +1125,10 @@ engines:
|
|||||||
shortcut: sc
|
shortcut: sc
|
||||||
|
|
||||||
- name: stackoverflow
|
- name: stackoverflow
|
||||||
engine: stackoverflow
|
engine: stackexchange
|
||||||
shortcut: st
|
shortcut: st
|
||||||
|
api_site: 'stackoverflow'
|
||||||
|
categories: it
|
||||||
|
|
||||||
- name: searchcode code
|
- name: searchcode code
|
||||||
engine: searchcode_code
|
engine: searchcode_code
|
||||||
|
Loading…
Reference in New Issue
Block a user