1
0
mirror of https://github.com/searxng/searxng.git synced 2024-11-17 18:00:12 +01:00
searxng/searx/engines/not_evil.py
Alexandre Flament a4dcfa025c [enh] engines: add about variable
move meta information from comment to the about variable
so the preferences, the documentation can show these information
2021-01-14 20:57:17 +01:00

68 lines
1.7 KiB
Python

# SPDX-License-Identifier: AGPL-3.0-or-later
"""
not Evil (Onions)
"""
from urllib.parse import urlencode
from lxml import html
from searx.engines.xpath import extract_text
# about
about = {
"website": 'http://hss3uro2hsxfogfq.onion',
"wikidata_id": None,
"official_api_documentation": 'http://hss3uro2hsxfogfq.onion/api.htm',
"use_official_api": False,
"require_api_key": False,
"results": 'HTML',
}
# engine dependent config
categories = ['onions']
paging = True
page_size = 20
# search-url
base_url = 'http://hss3uro2hsxfogfq.onion/'
search_url = 'index.php?{query}&hostLimit=20&start={pageno}&numRows={page_size}'
# specific xpath variables
results_xpath = '//*[@id="content"]/div/p'
url_xpath = './span[1]'
title_xpath = './a[1]'
content_xpath = './text()'
# do search-request
def request(query, params):
offset = (params['pageno'] - 1) * page_size
params['url'] = base_url + search_url.format(pageno=offset,
query=urlencode({'q': query}),
page_size=page_size)
return params
# get response from search-request
def response(resp):
results = []
# needed because otherwise requests guesses wrong encoding
resp.encoding = 'utf8'
dom = html.fromstring(resp.text)
# parse results
for result in dom.xpath(results_xpath):
url = extract_text(result.xpath(url_xpath)[0])
title = extract_text(result.xpath(title_xpath)[0])
content = extract_text(result.xpath(content_xpath))
# append result
results.append({'url': url,
'title': title,
'content': content,
'is_onion': True})
return results