From 6b1516d6adc88f17e06fe115c3aff69bfcad4579 Mon Sep 17 00:00:00 2001
From: Zhijie He <hezhijie0327@hotmail.com>
Date: Tue, 12 Aug 2025 21:18:46 +0800
Subject: [PATCH] [fix] baidu captcha detection (#5111)

Add Baidu Captcha detection to reduce `JSONDecodeError` error

Baidu will redirect to `wappass.baidu.com` and return a captcha challenge.
Current behavior will get the data from `wappass.baidu.com` then return a
`json.decoder.JSONDecodeError` error.
---
 searx/engines/baidu.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/searx/engines/baidu.py b/searx/engines/baidu.py
index 29c9c0e4d..57d1ed444 100644
--- a/searx/engines/baidu.py
+++ b/searx/engines/baidu.py
@@ -13,7 +13,7 @@ from html import unescape
 import time
 import json
 
-from searx.exceptions import SearxEngineAPIException
+from searx.exceptions import SearxEngineAPIException, SearxEngineCaptchaException
 from searx.utils import html_to_text
 
 about = {
@@ -89,10 +89,14 @@ def request(query, params):
             query_params["paramList"] += f",timestamp_range={past}-{now}"
 
     params["url"] = f"{query_url}?{urlencode(query_params)}"
+    params["allow_redirects"] = False
     return params
 
 
 def response(resp):
+    # Detect Baidu Captcha, it will redirect to wappass.baidu.com
+    if 'wappass.baidu.com/static/captcha' in resp.headers.get('Location', ''):
+        raise SearxEngineCaptchaException()
 
     text = resp.text
     if baidu_category == 'images':