2021-01-13 11:31:25 +01:00
|
|
|
# SPDX-License-Identifier: AGPL-3.0-or-later
|
2017-05-21 05:33:08 +02:00
|
|
|
"""
|
|
|
|
DuckDuckGo (Images)
|
|
|
|
"""
|
|
|
|
|
|
|
|
from json import loads
|
2020-08-06 17:42:46 +02:00
|
|
|
from urllib.parse import urlencode
|
2020-11-26 17:22:54 +01:00
|
|
|
from searx.exceptions import SearxEngineAPIException
|
2020-11-02 11:19:53 +01:00
|
|
|
from searx.engines.duckduckgo import get_region_code
|
2021-12-27 09:26:22 +01:00
|
|
|
from searx.engines.duckduckgo import (
|
|
|
|
_fetch_supported_languages,
|
|
|
|
supported_languages_url,
|
|
|
|
) # NOQA # pylint: disable=unused-import
|
[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 10:43:33 +02:00
|
|
|
from searx.network import get
|
2017-05-21 05:33:08 +02:00
|
|
|
|
2021-01-13 11:31:25 +01:00
|
|
|
# about
|
|
|
|
about = {
|
|
|
|
"website": 'https://duckduckgo.com/',
|
|
|
|
"wikidata_id": 'Q12805',
|
|
|
|
"official_api_documentation": {
|
|
|
|
'url': 'https://duckduckgo.com/api',
|
|
|
|
'comment': 'but images are not supported',
|
|
|
|
},
|
|
|
|
"use_official_api": False,
|
|
|
|
"require_api_key": False,
|
|
|
|
"results": 'JSON (site requires js to get images)',
|
|
|
|
}
|
|
|
|
|
2017-05-21 05:33:08 +02:00
|
|
|
# engine dependent config
|
|
|
|
categories = ['images']
|
|
|
|
paging = True
|
|
|
|
safesearch = True
|
|
|
|
|
|
|
|
# search-url
|
|
|
|
images_url = 'https://duckduckgo.com/i.js?{query}&s={offset}&p={safesearch}&o=json&vqd={vqd}'
|
|
|
|
site_url = 'https://duckduckgo.com/?{query}&iar=images&iax=1&ia=images'
|
|
|
|
|
|
|
|
|
|
|
|
# run query in site to get vqd number needed for requesting images
|
|
|
|
# TODO: find a way to get this number without an extra request (is it a hash of the query?)
|
2019-04-13 07:17:32 +02:00
|
|
|
def get_vqd(query, headers):
|
|
|
|
query_url = site_url.format(query=urlencode({'q': query}))
|
|
|
|
res = get(query_url, headers=headers)
|
2017-05-21 05:33:08 +02:00
|
|
|
content = res.text
|
2019-04-13 07:17:32 +02:00
|
|
|
if content.find('vqd=\'') == -1:
|
2020-11-26 17:22:54 +01:00
|
|
|
raise SearxEngineAPIException('Request failed')
|
2021-12-27 09:26:22 +01:00
|
|
|
vqd = content[content.find('vqd=\'') + 5 :]
|
|
|
|
vqd = vqd[: vqd.find('\'')]
|
2017-05-21 05:33:08 +02:00
|
|
|
return vqd
|
|
|
|
|
|
|
|
|
|
|
|
# do search-request
|
|
|
|
def request(query, params):
|
|
|
|
# to avoid running actual external requests when testing
|
|
|
|
if 'is_test' not in params:
|
2019-04-13 07:17:32 +02:00
|
|
|
vqd = get_vqd(query, params['headers'])
|
2017-05-21 05:33:08 +02:00
|
|
|
else:
|
|
|
|
vqd = '12345'
|
|
|
|
|
|
|
|
offset = (params['pageno'] - 1) * 50
|
|
|
|
|
|
|
|
safesearch = params['safesearch'] - 1
|
|
|
|
|
2017-07-05 05:29:06 +02:00
|
|
|
region_code = get_region_code(params['language'], lang_list=supported_languages)
|
2019-01-06 15:27:46 +01:00
|
|
|
if region_code:
|
|
|
|
params['url'] = images_url.format(
|
2021-12-27 09:26:22 +01:00
|
|
|
query=urlencode({'q': query, 'l': region_code}), offset=offset, safesearch=safesearch, vqd=vqd
|
|
|
|
)
|
2019-01-06 15:27:46 +01:00
|
|
|
else:
|
2021-12-27 09:26:22 +01:00
|
|
|
params['url'] = images_url.format(query=urlencode({'q': query}), offset=offset, safesearch=safesearch, vqd=vqd)
|
2017-05-21 05:33:08 +02:00
|
|
|
|
|
|
|
return params
|
|
|
|
|
|
|
|
|
|
|
|
# get response from search-request
|
|
|
|
def response(resp):
|
|
|
|
results = []
|
|
|
|
|
|
|
|
content = resp.text
|
2020-11-26 17:22:54 +01:00
|
|
|
res_json = loads(content)
|
2017-05-21 05:33:08 +02:00
|
|
|
|
|
|
|
# parse results
|
|
|
|
for result in res_json['results']:
|
|
|
|
title = result['title']
|
|
|
|
url = result['url']
|
|
|
|
thumbnail = result['thumbnail']
|
|
|
|
image = result['image']
|
|
|
|
|
|
|
|
# append result
|
2021-12-27 09:26:22 +01:00
|
|
|
results.append(
|
|
|
|
{
|
|
|
|
'template': 'images.html',
|
|
|
|
'title': title,
|
|
|
|
'content': '',
|
|
|
|
'thumbnail_src': thumbnail,
|
|
|
|
'img_src': image,
|
|
|
|
'url': url,
|
|
|
|
}
|
|
|
|
)
|
2017-05-21 05:33:08 +02:00
|
|
|
|
|
|
|
return results
|