From 7b5fe0118784277a72cd1b460410c5f66a562867 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E8=82=86=E6=9C=88?= <2835601846@qq.com>
Date: Wed, 17 Jun 2026 17:02:54 +0800
Subject: [PATCH] fix(web): update sogou search regex to match new HTML
 structure (#3139)

- reSogouTitle: make class attribute quotes optional (class="?resultLink"?)
- reSogouSnippet: allow additional CSS classes after clamp (clamp\d*[^"]*)

Sogou WAP search page changed its HTML format:
- class=resultLink -> class="resultLink" (added quotes)
- class="clamp3" -> class="clamp2 fz-mid click-sugg-content" (extra classes)

Fixes web_search tool failing to parse sogou search results.
---
 pkg/tools/integration/web.go | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pkg/tools/integration/web.go b/pkg/tools/integration/web.go
index 77065793c..f8000ce99 100644
--- a/pkg/tools/integration/web.go
+++ b/pkg/tools/integration/web.go
@@ -55,9 +55,9 @@ var (
 		`<a class="result__snippet[^"]*".*?>([\s\S]*?)</a>`,
 	)
 	reSogouTitle = regexp.MustCompile(
-		`<a\s+class=resultLink\s+href="([^"]+)"[^>]*id="sogou_vr_\d+_\d+"[^>]*>\s*(.*?)\s*</a>`,
+		`<a\s+class="?resultLink"?\s+href="([^"]+)"[^>]*id="sogou_vr_\d+_\d+"[^>]*>\s*(.*?)\s*</a>`,
 	)
-	reSogouSnippet = regexp.MustCompile(`<div class="clamp\d*">\s*(.*?)\s*</div>`)
+	reSogouSnippet = regexp.MustCompile(`<div class="clamp\d*[^"]*">\s*(.*?)\s*</div>`)
 	reSogouRealURL = regexp.MustCompile(`url=([^&]+)`)
 )