子链接不再被 isVisited 过滤

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))