1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-16 17:40:11 +01:00
searxng/searx/engines/stackoverflow.py
2020-10-02 18:13:56 +02:00

58 lines
1.4 KiB
Python

"""
Stackoverflow (It)
@website https://stackoverflow.com/
@provide-api not clear (https://api.stackexchange.com/docs/advanced-search)
@using-api no
@results HTML
@stable no (HTML can change)
@parse url, title, content
"""
from urllib.parse import urlencode, urljoin
from lxml import html
from searx.utils import extract_text
# 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):
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