mirror of
https://github.com/searxng/searxng.git
synced 2024-11-29 22:21:02 +00:00
c80e82a855
Partial reverse engineering of the DuckDuckGo (DDG) engines including a
improved language and region handling based on the enigne.traits_v1 data.
- DDG Lite
- DDG Instant Answer API
- DDG Images
- DDG Weather
docs/src/searx.engine.duckduckgo.rst:
Online documentation of the DDG engines (make docs.live)
searx/data/engine_traits.json
Add data type "traits_v1" generated by the fetch_traits() functions from:
- "duckduckgo" (WEB),
- "duckduckgo images" and
- "duckduckgo weather"
and remove data from obsolete data type "supported_languages".
searx/autocomplete.py:
Reversed engineered Autocomplete from DDG. Supports DDG's languages.
searx/engines/duckduckgo.py:
- fetch_traits(): Fetch languages & regions from DDG.
- get_ddg_lang(): Get DDG's language identifier from SearXNG's locale. DDG
defines its languages by region codes. DDG-Lite does not offer a language
selection to the user, only a region can be selected by the user.
- Cache ``vqd`` value: The vqd value depends on the query string and is needed
for the follow up pages or the images loaded by a XMLHttpRequest (DDG
images). The ``vqd`` value of a search term is stored for 10min in the
redis DB.
- DDG Lite engine: reversed engineered request method with improved Language
and region support and better ``vqd`` handling.
searx/engines/duckduckgo_definitions.py: DDG Instant Answer API
The *instant answers* API does not support languages, or at least we could not
find out how language support should work. It seems that most of the features
are based on English terms.
searx/engines/duckduckgo_images.py: DDG Images
Reversed engineered request method. Improved language and region handling
based on cookies and the enigne.traits_v1 data. Response: add image format to
the result list
searx/engines/duckduckgo_weather.py: DDG Weather
Improved language and region handling based on cookies and the
enigne.traits_v1 data.
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
100 lines
2.7 KiB
Python
100 lines
2.7 KiB
Python
# SPDX-License-Identifier: AGPL-3.0-or-later
|
|
"""
|
|
DuckDuckGo Images
|
|
~~~~~~~~~~~~~~~~~
|
|
"""
|
|
|
|
from typing import TYPE_CHECKING
|
|
from urllib.parse import urlencode
|
|
|
|
from searx.engines.duckduckgo import fetch_traits # pylint: disable=unused-import
|
|
from searx.engines.duckduckgo import (
|
|
get_ddg_lang,
|
|
get_vqd,
|
|
)
|
|
from searx.enginelib.traits import EngineTraits
|
|
|
|
if TYPE_CHECKING:
|
|
import logging
|
|
|
|
logger: logging.Logger
|
|
|
|
traits: EngineTraits
|
|
|
|
# about
|
|
about = {
|
|
"website": 'https://duckduckgo.com/',
|
|
"wikidata_id": 'Q12805',
|
|
"use_official_api": False,
|
|
"require_api_key": False,
|
|
"results": 'JSON (site requires js to get images)',
|
|
}
|
|
|
|
# engine dependent config
|
|
categories = ['images', 'web']
|
|
paging = True
|
|
safesearch = True
|
|
send_accept_language_header = True
|
|
|
|
safesearch_cookies = {0: '-2', 1: None, 2: '1'}
|
|
safesearch_args = {0: '1', 1: None, 2: '1'}
|
|
|
|
|
|
def request(query, params):
|
|
|
|
eng_region = traits.get_region(params['searxng_locale'], traits.all_locale)
|
|
eng_lang = get_ddg_lang(traits, params['searxng_locale'])
|
|
|
|
args = {
|
|
'q': query,
|
|
'o': 'json',
|
|
# 'u': 'bing',
|
|
'l': eng_region,
|
|
'vqd': get_vqd(query, params["headers"]),
|
|
}
|
|
|
|
if params['pageno'] > 1:
|
|
args['s'] = (params['pageno'] - 1) * 100
|
|
|
|
params['cookies']['ad'] = eng_lang # zh_CN
|
|
params['cookies']['ah'] = eng_region # "us-en,de-de"
|
|
params['cookies']['l'] = eng_region # "hk-tzh"
|
|
logger.debug("cookies: %s", params['cookies'])
|
|
|
|
safe_search = safesearch_cookies.get(params['safesearch'])
|
|
if safe_search is not None:
|
|
params['cookies']['p'] = safe_search # "-2", "1"
|
|
safe_search = safesearch_args.get(params['safesearch'])
|
|
if safe_search is not None:
|
|
args['p'] = safe_search # "-1", "1"
|
|
|
|
args = urlencode(args)
|
|
params['url'] = 'https://duckduckgo.com/i.js?{args}&f={f}'.format(args=args, f=',,,,,')
|
|
|
|
params['headers']['Accept'] = 'application/json, text/javascript, */*; q=0.01'
|
|
params['headers']['Referer'] = 'https://duckduckgo.com/'
|
|
params['headers']['X-Requested-With'] = 'XMLHttpRequest'
|
|
logger.debug("headers: %s", params['headers'])
|
|
|
|
return params
|
|
|
|
|
|
def response(resp):
|
|
results = []
|
|
res_json = resp.json()
|
|
|
|
for result in res_json['results']:
|
|
results.append(
|
|
{
|
|
'template': 'images.html',
|
|
'title': result['title'],
|
|
'content': '',
|
|
'thumbnail_src': result['thumbnail'],
|
|
'img_src': result['image'],
|
|
'url': result['url'],
|
|
'img_format': '%s x %s' % (result['width'], result['height']),
|
|
'source': result['source'],
|
|
}
|
|
)
|
|
|
|
return results
|