From c80e82a855fd388c6080066da892b9723d6037c9 Mon Sep 17 00:00:00 2001 From: Markus Heiser Date: Sat, 5 Nov 2022 15:10:52 +0100 Subject: [mod] DuckDuckGo: reversed engineered & upgrade to data_type: traits_v1 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 --- searx/engines/duckduckgo_weather.py | 35 +++++++++++++++++++++++++++++++---- 1 file changed, 31 insertions(+), 4 deletions(-) (limited to 'searx/engines/duckduckgo_weather.py') diff --git a/searx/engines/duckduckgo_weather.py b/searx/engines/duckduckgo_weather.py index 0540cbcb5..4f0ce1b49 100644 --- a/searx/engines/duckduckgo_weather.py +++ b/searx/engines/duckduckgo_weather.py @@ -1,13 +1,29 @@ # SPDX-License-Identifier: AGPL-3.0-or-later # lint: pylint -"""DuckDuckGo Weather""" +""" +DuckDuckGo Weather +~~~~~~~~~~~~~~~~~~ +""" +from typing import TYPE_CHECKING from json import loads from urllib.parse import quote from datetime import datetime from flask_babel import gettext +from searx.engines.duckduckgo import fetch_traits # pylint: disable=unused-import +from searx.engines.duckduckgo import get_ddg_lang +from searx.enginelib.traits import EngineTraits + +if TYPE_CHECKING: + import logging + + logger: logging.Logger + +traits: EngineTraits + + about = { "website": 'https://duckduckgo.com/', "wikidata_id": 'Q12805', @@ -17,9 +33,11 @@ about = { "results": "JSON", } -categories = ["others"] +send_accept_language_header = True -url = "https://duckduckgo.com/js/spice/forecast/{query}/{lang}" +# engine dependent config +categories = ["others"] +URL = "https://duckduckgo.com/js/spice/forecast/{query}/{lang}" def generate_condition_table(condition): @@ -72,8 +90,17 @@ def generate_day_table(day): def request(query, params): - params["url"] = url.format(query=quote(query), lang=params['language'].split('-')[0]) + eng_region = traits.get_region(params['searxng_locale'], traits.all_locale) + eng_lang = get_ddg_lang(traits, params['searxng_locale']) + + # !ddw paris :es-AR --> {'ad': 'es_AR', 'ah': 'ar-es', 'l': 'ar-es'} + params['cookies']['ad'] = eng_lang + params['cookies']['ah'] = eng_region + params['cookies']['l'] = eng_region + logger.debug("cookies: %s", params['cookies']) + + params["url"] = URL.format(query=quote(query), lang=eng_lang.split('_')[0]) return params -- cgit v1.2.3