From 1b88ca1efba20b75e25e208d79c21b8f292b225f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E5=90=B4=E6=96=87=E5=B3=B0?= <kevin@lmve.net>
Date: Fri, 10 Apr 2026 20:49:49 +0800
Subject: [PATCH] =?UTF-8?q?=E5=AD=90=E9=93=BE=E6=8E=A5=E4=B8=8D=E5=86=8D?=
 =?UTF-8?q?=E8=A2=AB=20isVisited=20=E8=BF=87=E6=BB=A4?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 crawler/crawler.go | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/crawler/crawler.go b/crawler/crawler.go
index 1d7842d..66b3dfb 100644
--- a/crawler/crawler.go
+++ b/crawler/crawler.go
@@ -257,19 +257,16 @@ func (c *Crawler) runPriorityWorker() {
 			// 直接调用 visitURLUnlimited，绕过队列调度和链接数限制
 			hrefs := c.visitURLUnlimited(rawURL)
 
-			// 将子链接加入优先队列（保持优先级）
-			if len(hrefs) > 0 {
-				c.priorityChildrenMu.Lock()
-				added := 0
-				for _, child := range hrefs {
-					if !c.isVisited(child) {
-						c.priorityChildren = append(c.priorityChildren, child)
-						added++
-					}
-				}
-				IncrementPriorityChildren(int64(added))
-				c.priorityChildrenMu.Unlock()
+		// 将子链接加入优先队列（保持优先级）
+		// 注意：Priority URL 的子链接强制加入队列，即使已访问过也要重新爬取
+		if len(hrefs) > 0 {
+			c.priorityChildrenMu.Lock()
+			for _, child := range hrefs {
+				c.priorityChildren = append(c.priorityChildren, child)
 			}
+			IncrementPriorityChildren(int64(len(hrefs)))
+			c.priorityChildrenMu.Unlock()
+		}
 
 			log.Printf("[crawler] priority crawl done: %s (%d child links)", rawURL, len(hrefs))