2021-01-13 10:31:25 +00:00
|
|
|
# SPDX-License-Identifier: AGPL-3.0-or-later
|
2015-05-31 22:00:32 +00:00
|
|
|
"""
|
2015-06-02 18:36:58 +00:00
|
|
|
Qwant (Web, Images, News, Social)
|
2015-05-31 22:00:32 +00:00
|
|
|
"""
|
|
|
|
|
2015-06-02 18:36:58 +00:00
|
|
|
from datetime import datetime
|
2016-12-10 20:27:47 +00:00
|
|
|
from json import loads
|
2020-08-06 15:42:46 +00:00
|
|
|
from urllib.parse import urlencode
|
|
|
|
from searx.utils import html_to_text, match_language
|
2020-12-09 20:23:20 +00:00
|
|
|
from searx.exceptions import SearxEngineAPIException, SearxEngineCaptchaException
|
[httpx] replace searx.poolrequests by searx.network
settings.yml:
* outgoing.networks:
* can contains network definition
* propertiers: enable_http, verify, http2, max_connections, max_keepalive_connections,
keepalive_expiry, local_addresses, support_ipv4, support_ipv6, proxies, max_redirects, retries
* retries: 0 by default, number of times searx retries to send the HTTP request (using different IP & proxy each time)
* local_addresses can be "192.168.0.1/24" (it supports IPv6)
* support_ipv4 & support_ipv6: both True by default
see https://github.com/searx/searx/pull/1034
* each engine can define a "network" section:
* either a full network description
* either reference an existing network
* all HTTP requests of engine use the same HTTP configuration (it was not the case before, see proxy configuration in master)
2021-04-05 08:43:33 +00:00
|
|
|
from searx.network import raise_for_httperror
|
2020-08-06 15:42:46 +00:00
|
|
|
|
2021-01-13 10:31:25 +00:00
|
|
|
# about
|
|
|
|
about = {
|
|
|
|
"website": 'https://www.qwant.com/',
|
|
|
|
"wikidata_id": 'Q14657870',
|
|
|
|
"official_api_documentation": None,
|
|
|
|
"use_official_api": True,
|
|
|
|
"require_api_key": False,
|
|
|
|
"results": 'JSON',
|
|
|
|
}
|
2015-05-31 22:00:32 +00:00
|
|
|
|
|
|
|
# engine dependent config
|
2020-11-03 10:35:53 +00:00
|
|
|
categories = []
|
2015-05-31 22:00:32 +00:00
|
|
|
paging = True
|
2021-05-03 00:24:28 +00:00
|
|
|
supported_languages_url = about['website']
|
2015-05-31 22:00:32 +00:00
|
|
|
|
2015-06-02 20:11:47 +00:00
|
|
|
category_to_keyword = {'general': 'web',
|
|
|
|
'images': 'images',
|
2020-12-09 20:23:20 +00:00
|
|
|
'news': 'news'}
|
2015-06-02 18:36:58 +00:00
|
|
|
|
2015-05-31 22:00:32 +00:00
|
|
|
# search-url
|
2018-08-13 10:03:27 +00:00
|
|
|
url = 'https://api.qwant.com/api/search/{keyword}?count=10&offset={offset}&f=&{query}&t={keyword}&uiv=4'
|
2015-05-31 22:00:32 +00:00
|
|
|
|
|
|
|
|
|
|
|
# do search-request
|
|
|
|
def request(query, params):
|
|
|
|
offset = (params['pageno'] - 1) * 10
|
|
|
|
|
2015-06-02 20:11:47 +00:00
|
|
|
if categories[0] and categories[0] in category_to_keyword:
|
|
|
|
|
|
|
|
params['url'] = url.format(keyword=category_to_keyword[categories[0]],
|
|
|
|
query=urlencode({'q': query}),
|
|
|
|
offset=offset)
|
|
|
|
else:
|
|
|
|
params['url'] = url.format(keyword='web',
|
|
|
|
query=urlencode({'q': query}),
|
|
|
|
offset=offset)
|
2015-05-31 22:00:32 +00:00
|
|
|
|
2017-07-20 20:47:20 +00:00
|
|
|
# add language tag
|
2019-01-06 14:27:46 +00:00
|
|
|
if params['language'] != 'all':
|
|
|
|
language = match_language(params['language'], supported_languages, language_aliases)
|
|
|
|
params['url'] += '&locale=' + language.replace('-', '_').lower()
|
2015-05-31 22:00:32 +00:00
|
|
|
|
2019-12-21 19:25:39 +00:00
|
|
|
params['headers']['User-Agent'] = 'Mozilla/5.0 (X11; Linux x86_64; rv:69.0) Gecko/20100101 Firefox/69.0'
|
2020-12-09 20:23:20 +00:00
|
|
|
params['raise_for_httperror'] = False
|
2015-05-31 22:00:32 +00:00
|
|
|
return params
|
|
|
|
|
|
|
|
|
|
|
|
# get response from search-request
|
|
|
|
def response(resp):
|
|
|
|
results = []
|
|
|
|
|
2020-12-09 20:23:20 +00:00
|
|
|
# According to https://www.qwant.com/js/app.js
|
|
|
|
if resp.status_code == 429:
|
|
|
|
raise SearxEngineCaptchaException()
|
|
|
|
|
|
|
|
# raise for other errors
|
|
|
|
raise_for_httperror(resp)
|
|
|
|
|
|
|
|
# load JSON result
|
2015-05-31 22:00:32 +00:00
|
|
|
search_results = loads(resp.text)
|
|
|
|
|
2020-12-09 20:23:20 +00:00
|
|
|
# check for an API error
|
|
|
|
if search_results.get('status') != 'success':
|
|
|
|
raise SearxEngineAPIException('API error ' + str(search_results.get('error', '')))
|
|
|
|
|
2015-05-31 22:00:32 +00:00
|
|
|
# return empty array if there are no results
|
|
|
|
if 'data' not in search_results:
|
|
|
|
return []
|
|
|
|
|
|
|
|
data = search_results.get('data', {})
|
|
|
|
|
|
|
|
res = data.get('result', {})
|
|
|
|
|
|
|
|
# parse results
|
|
|
|
for result in res.get('items', {}):
|
|
|
|
|
2016-12-10 20:27:47 +00:00
|
|
|
title = html_to_text(result['title'])
|
2015-05-31 22:00:32 +00:00
|
|
|
res_url = result['url']
|
2016-12-10 20:27:47 +00:00
|
|
|
content = html_to_text(result['desc'])
|
2015-05-31 22:00:32 +00:00
|
|
|
|
2015-06-02 20:11:47 +00:00
|
|
|
if category_to_keyword.get(categories[0], '') == 'web':
|
2015-06-02 18:36:58 +00:00
|
|
|
results.append({'title': title,
|
|
|
|
'content': content,
|
|
|
|
'url': res_url})
|
|
|
|
|
2015-06-02 20:11:47 +00:00
|
|
|
elif category_to_keyword.get(categories[0], '') == 'images':
|
2015-06-02 18:36:58 +00:00
|
|
|
thumbnail_src = result['thumbnail']
|
|
|
|
img_src = result['media']
|
|
|
|
results.append({'template': 'images.html',
|
|
|
|
'url': res_url,
|
|
|
|
'title': title,
|
|
|
|
'content': '',
|
|
|
|
'thumbnail_src': thumbnail_src,
|
|
|
|
'img_src': img_src})
|
|
|
|
|
2017-02-12 13:58:49 +00:00
|
|
|
elif category_to_keyword.get(categories[0], '') == 'news':
|
|
|
|
published_date = datetime.fromtimestamp(result['date'], None)
|
|
|
|
media = result.get('media', [])
|
|
|
|
if len(media) > 0:
|
|
|
|
img_src = media[0].get('pict', {}).get('url', None)
|
|
|
|
else:
|
|
|
|
img_src = None
|
2015-06-02 18:36:58 +00:00
|
|
|
results.append({'url': res_url,
|
|
|
|
'title': title,
|
|
|
|
'publishedDate': published_date,
|
2017-02-12 13:58:49 +00:00
|
|
|
'content': content,
|
|
|
|
'img_src': img_src})
|
2015-05-31 22:00:32 +00:00
|
|
|
|
|
|
|
return results
|
2017-02-25 02:21:48 +00:00
|
|
|
|
|
|
|
|
|
|
|
# get supported languages from their site
|
|
|
|
def _fetch_supported_languages(resp):
|
|
|
|
# list of regions is embedded in page as a js object
|
|
|
|
response_text = resp.text
|
2021-05-03 00:24:28 +00:00
|
|
|
response_text = response_text[response_text.find('INITIAL_PROPS'):]
|
|
|
|
response_text = response_text[response_text.find('{'):response_text.find('</script>')]
|
2017-02-25 02:21:48 +00:00
|
|
|
|
|
|
|
regions_json = loads(response_text)
|
|
|
|
|
2021-05-03 00:24:28 +00:00
|
|
|
supported_languages = []
|
|
|
|
for country, langs in regions_json['locales'].items():
|
|
|
|
for lang in langs['langs']:
|
|
|
|
lang_code = "{lang}-{country}".format(lang=lang, country=country)
|
|
|
|
supported_languages.append(lang_code)
|
2017-02-25 02:21:48 +00:00
|
|
|
|
|
|
|
return supported_languages
|