Compare commits

..

2 Commits

Author SHA1 Message Date
Ben Curtis 0ba12f99c7
Merge 5e11d697ab into 10d3af84b8 2024-11-20 03:43:38 +07:00
Markus Heiser 10d3af84b8 [fix] engine: duckduckgo - don't quote query string
The query string send to DDG must not be qouted.

The query string was URL-qouted in #4011, but the URL-qouted query string result
in unexpected *URL decoded* and other garbish results as reported in #4019
and #4020.  To test compare the results of a query like::

    !ddg Häuser und Straßen :de
    !ddg Häuser und Straßen :all
    !ddg 房屋和街道 :all
    !ddg 房屋和街道 :zh

Closed:

- [#4019] https://github.com/searxng/searxng/issues/4019
- [#4020] https://github.com/searxng/searxng/issues/4020

Related:

- [#4011] https://github.com/searxng/searxng/pull/4011

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
2024-11-17 18:14:22 +01:00
1 changed files with 7 additions and 3 deletions

View File

@ -6,7 +6,7 @@ DuckDuckGo Lite
from typing import TYPE_CHECKING from typing import TYPE_CHECKING
import re import re
from urllib.parse import urlencode, quote_plus from urllib.parse import urlencode
import json import json
import babel import babel
import lxml.html import lxml.html
@ -263,7 +263,7 @@ def request(query, params):
params['url'] = url params['url'] = url
params['method'] = 'POST' params['method'] = 'POST'
params['data']['q'] = quote_plus(query) params['data']['q'] = query
# The API is not documented, so we do some reverse engineering and emulate # The API is not documented, so we do some reverse engineering and emulate
# what https://html.duckduckgo.com/html does when you press "next Page" link # what https://html.duckduckgo.com/html does when you press "next Page" link
@ -381,7 +381,11 @@ def response(resp):
zero_click_info_xpath = '//div[@id="zero_click_abstract"]' zero_click_info_xpath = '//div[@id="zero_click_abstract"]'
zero_click = extract_text(eval_xpath(doc, zero_click_info_xpath)).strip() zero_click = extract_text(eval_xpath(doc, zero_click_info_xpath)).strip()
if zero_click and "Your IP address is" not in zero_click and "Your user agent:" not in zero_click: if zero_click and (
"Your IP address is" not in zero_click
and "Your user agent:" not in zero_click
and "URL Decoded:" not in zero_click
):
current_query = resp.search_params["data"].get("q") current_query = resp.search_params["data"].get("q")
results.append( results.append(