2021-01-13 11:31:25 +01:00
|
|
|
# SPDX-License-Identifier: AGPL-3.0-or-later
|
2021-09-30 16:40:00 +02:00
|
|
|
# lint: pylint
|
2022-06-02 21:36:04 +02:00
|
|
|
"""
|
|
|
|
DuckDuckGo (Web)
|
2015-05-02 15:45:17 +02:00
|
|
|
"""
|
2014-09-02 17:14:57 +02:00
|
|
|
|
2016-11-06 03:51:38 +01:00
|
|
|
from json import loads
|
2022-06-02 21:36:04 +02:00
|
|
|
from urllib.parse import urlencode
|
|
|
|
from searx.utils import match_language, HTMLTextExtractor
|
|
|
|
import re
|
[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
|
2013-10-14 23:09:13 +02:00
|
|
|
|
2021-01-13 11:31:25 +01:00
|
|
|
# about
|
|
|
|
about = {
|
2022-06-02 21:36:04 +02:00
|
|
|
"website": 'https://duckduckgo.com/',
|
2021-01-13 11:31:25 +01:00
|
|
|
"wikidata_id": 'Q12805',
|
|
|
|
"official_api_documentation": 'https://duckduckgo.com/api',
|
|
|
|
"use_official_api": False,
|
|
|
|
"require_api_key": False,
|
|
|
|
"results": 'HTML',
|
|
|
|
}
|
|
|
|
|
2014-09-02 17:14:57 +02:00
|
|
|
# engine dependent config
|
|
|
|
categories = ['general']
|
2021-09-30 16:40:00 +02:00
|
|
|
paging = True
|
2022-06-02 21:36:04 +02:00
|
|
|
supported_languages_url = 'https://duckduckgo.com/util/u172.js'
|
|
|
|
number_of_results = 10
|
2016-07-18 16:15:37 +02:00
|
|
|
time_range_support = True
|
2022-06-02 21:36:04 +02:00
|
|
|
safesearch = True
|
|
|
|
VQD_REGEX = r"vqd='(\d+-\d+-\d+)'"
|
2018-03-01 05:30:48 +01:00
|
|
|
language_aliases = {
|
|
|
|
'ar-SA': 'ar-XA',
|
|
|
|
'es-419': 'es-XL',
|
|
|
|
'ja': 'jp-JP',
|
|
|
|
'ko': 'kr-KR',
|
|
|
|
'sl-SI': 'sl-SL',
|
|
|
|
'zh-TW': 'tzh-TW',
|
|
|
|
'zh-HK': 'tzh-HK'
|
|
|
|
}
|
|
|
|
|
2021-09-30 16:40:00 +02:00
|
|
|
# search-url
|
2022-06-02 21:36:04 +02:00
|
|
|
url = 'https://links.duckduckgo.com/d.js?'
|
|
|
|
url_ping = 'https://duckduckgo.com/t/sl_h'
|
|
|
|
time_range_dict = {'day': 'd',
|
|
|
|
'week': 'w',
|
|
|
|
'month': 'm',
|
|
|
|
'year': 'y'}
|
2014-09-02 17:14:57 +02:00
|
|
|
|
2021-10-02 11:40:56 +02:00
|
|
|
|
2017-05-21 05:33:08 +02:00
|
|
|
# match query's language to a region code that duckduckgo will accept
|
2020-11-16 09:43:23 +01:00
|
|
|
def get_region_code(lang, lang_list=None):
|
2019-01-06 15:27:46 +01:00
|
|
|
if lang == 'all':
|
|
|
|
return None
|
|
|
|
|
2020-11-16 09:43:23 +01:00
|
|
|
lang_code = match_language(lang, lang_list or [], language_aliases, 'wt-WT')
|
2018-03-01 05:30:48 +01:00
|
|
|
lang_parts = lang_code.split('-')
|
|
|
|
|
|
|
|
# country code goes first
|
|
|
|
return lang_parts[1].lower() + '-' + lang_parts[0].lower()
|
2017-05-21 05:33:08 +02:00
|
|
|
|
|
|
|
|
2022-06-02 21:36:04 +02:00
|
|
|
def get_vqd(query, headers):
|
|
|
|
resp = get(f"https://duckduckgo.com/?q={query}&ia=web", headers=headers)
|
|
|
|
resp = re.findall(VQD_REGEX, resp.text)
|
|
|
|
return resp[0]
|
|
|
|
|
|
|
|
|
2017-05-21 05:33:08 +02:00
|
|
|
def request(query, params):
|
|
|
|
|
2022-06-02 21:36:04 +02:00
|
|
|
params['method'] = 'GET'
|
|
|
|
|
|
|
|
vqd = get_vqd(query, params['headers'])
|
|
|
|
dl, ct = match_language(params['language'], supported_languages, language_aliases, 'wt-WT').split('-')
|
|
|
|
query_dict = {
|
|
|
|
'q': query,
|
|
|
|
't': 'D',
|
|
|
|
'l': params['language'],
|
|
|
|
'kl': f'{ct}-{dl}',
|
|
|
|
's': (params['pageno'] - 1) * number_of_results,
|
|
|
|
'dl': dl,
|
|
|
|
'ct': ct,
|
|
|
|
'ss_mkt': get_region_code(params['language'], supported_languages),
|
|
|
|
'df': params['time_range'],
|
|
|
|
'vqd': vqd,
|
|
|
|
'ex': -2,
|
|
|
|
'sp': '1',
|
|
|
|
'bpa': '1',
|
|
|
|
'biaexp': 'b',
|
|
|
|
'msvrtexp': 'b'
|
|
|
|
}
|
|
|
|
if params['safesearch'] == 2: # STRICT
|
|
|
|
del query_dict['t']
|
|
|
|
query_dict['p'] = 1
|
|
|
|
query_dict.update({
|
|
|
|
'videxp': 'a',
|
|
|
|
'nadse': 'b',
|
|
|
|
'eclsexp': 'a',
|
|
|
|
'stiaexp': 'a',
|
|
|
|
'tjsexp': 'b',
|
|
|
|
'related': 'b',
|
|
|
|
'msnexp': 'a'
|
|
|
|
})
|
|
|
|
elif params['safesearch'] == 1: # MODERATE
|
|
|
|
query_dict['ex'] = -1
|
|
|
|
query_dict.update({
|
|
|
|
'nadse': 'b',
|
|
|
|
'eclsexp': 'b',
|
|
|
|
'tjsexp': 'b'
|
|
|
|
})
|
|
|
|
else: # OFF
|
|
|
|
query_dict['ex'] = -2
|
|
|
|
query_dict.update({
|
|
|
|
'nadse': 'b',
|
|
|
|
'eclsexp': 'b',
|
|
|
|
'tjsexp': 'b'
|
|
|
|
})
|
|
|
|
|
|
|
|
params['allow_redirects'] = False
|
|
|
|
params['data'] = query_dict
|
|
|
|
params['cookies']['kl'] = params['data']['kl']
|
2021-02-09 12:07:19 +01:00
|
|
|
if params['time_range'] in time_range_dict:
|
|
|
|
params['data']['df'] = time_range_dict[params['time_range']]
|
2021-09-30 16:40:00 +02:00
|
|
|
params['cookies']['df'] = time_range_dict[params['time_range']]
|
2022-06-02 21:36:04 +02:00
|
|
|
params['url'] = url + urlencode(params['data'])
|
2013-10-14 23:09:13 +02:00
|
|
|
return params
|
|
|
|
|
2021-10-02 11:40:56 +02:00
|
|
|
|
2014-09-02 17:14:57 +02:00
|
|
|
# get response from search-request
|
2013-10-14 23:09:13 +02:00
|
|
|
def response(resp):
|
2021-09-30 16:40:00 +02:00
|
|
|
if resp.status_code == 303:
|
|
|
|
return []
|
|
|
|
|
2022-06-02 21:36:04 +02:00
|
|
|
# parse the response
|
2021-02-09 14:36:43 +01:00
|
|
|
results = []
|
2021-09-30 16:40:00 +02:00
|
|
|
|
2022-06-02 21:36:04 +02:00
|
|
|
data = re.findall(r"DDG\.pageLayout\.load\('d',(\[.+\])\);DDG\.duckbar\.load\('images'", str(resp.text))
|
|
|
|
try:
|
|
|
|
search_data = loads(data[0].replace('/\t/g', ' '))
|
|
|
|
except IndexError:
|
|
|
|
return
|
2021-09-30 16:40:00 +02:00
|
|
|
|
2022-06-02 21:36:04 +02:00
|
|
|
if len(search_data) == 1 and ('n' not in search_data[0]):
|
|
|
|
only_result = search_data[0]
|
|
|
|
if ((only_result.get('da') is not None and only_result.get('t') == 'EOF') or
|
|
|
|
only_result.get('a') is not None or only_result.get('d') == 'google.com search'):
|
|
|
|
return
|
2021-09-30 16:40:00 +02:00
|
|
|
|
2022-06-02 21:36:04 +02:00
|
|
|
for search_result in search_data:
|
|
|
|
if 'n' in search_result:
|
2013-10-15 19:11:43 +02:00
|
|
|
continue
|
2022-06-02 21:36:04 +02:00
|
|
|
title = HTMLTextExtractor()
|
|
|
|
title.feed(search_result.get('t'))
|
|
|
|
content = HTMLTextExtractor()
|
|
|
|
content.feed(search_result.get('a'))
|
|
|
|
|
|
|
|
results.append({'title': title.get_text(),
|
|
|
|
'content': content.get_text(),
|
|
|
|
'url': search_result.get('u')})
|
2013-10-15 19:11:43 +02:00
|
|
|
return results
|
2016-11-06 03:51:38 +01:00
|
|
|
|
2021-10-02 11:40:56 +02:00
|
|
|
|
2016-11-06 03:51:38 +01:00
|
|
|
# get supported languages from their site
|
2016-12-15 07:34:43 +01:00
|
|
|
def _fetch_supported_languages(resp):
|
2016-11-06 03:51:38 +01:00
|
|
|
|
|
|
|
# response is a js file with regions as an embedded object
|
2016-12-15 07:34:43 +01:00
|
|
|
response_page = resp.text
|
2016-11-06 03:51:38 +01:00
|
|
|
response_page = response_page[response_page.find('regions:{') + 8:]
|
|
|
|
response_page = response_page[:response_page.find('}') + 1]
|
|
|
|
|
|
|
|
regions_json = loads(response_page)
|
|
|
|
supported_languages = map((lambda x: x[3:] + '-' + x[:2].upper()), regions_json.keys())
|
|
|
|
|
2017-10-10 23:52:41 +02:00
|
|
|
return list(supported_languages)
|