From 1ceacf5fe9227cedacba13e72773a98b6a9d6267 Mon Sep 17 00:00:00 2001
From: Denis Shaposhnikov <993498+dsh2dsh@users.noreply.github.com>
Date: Sat, 21 May 2022 18:33:44 +0200
Subject: [PATCH] bing: extract original url instead of url tracked by bing

Bing returns URLs like
```
https://www.bing.com/ck/a?!&&p=7b6f95ee4bc34febe56210eec479fa7a84a991257e9773fda5e753ff482f9068JmltdHM9MTY1MzE1MDgzNSZpZ3VpZD0yYTZkNWQ4Yi05MDcwLTRkOGEtYWRmNi1jNWI2M2Y1NjJlOGQmaW5zaWQ9NTE1NA&ptn=3&fclid=ce60cbc5-d923-11ec-b22d-0e153102d4e8&u=a1aHR0cHM6Ly9kb2NzLnNlYXJ4bmcub3JnLw&ntb=1
```
for tracking clicks. Looking into HTML source I found bing stores original URLs
in "cite" element. Lets use it instead of.
---
 searx/engines/bing.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/searx/engines/bing.py b/searx/engines/bing.py
index 4c037de85..7fe3991e0 100644
--- a/searx/engines/bing.py
+++ b/searx/engines/bing.py
@@ -96,7 +96,10 @@ def response(resp):
     for result in eval_xpath(dom, '//li[@class="b_algo"]'):
 
         link = eval_xpath(result, './/h2/a')[0]
-        url = link.attrib.get('href')
+        # url = link.attrib.get('href')
+        # href attr is encoded by bing and directs back to bing for tracking
+        # instead of original. Lets extract original URL.
+        url = extract_text(eval_xpath(result, './/div[@class="b_attribution"]/cite'))
         title = extract_text(link)
         content = extract_text(eval_xpath(result, './/p'))