新增自动抓取停止功能

- 添加停止按钮，自动抓取时显示
- 点击可随时终止自动抓取流程
- 显示已停止状态和已抓取数量

services/search_service.py

@@ -85,7 +85,7 @@ class SearchService:
                 return results
             
             # 3. 解析 JSON 提取搜索结果
-            try {
+            try:
                 data = json.loads(stdout)
             except json.JSONDecodeError:
                 print(f"解析 JSON 失败: {stdout[:500]}")
@@ -224,16 +224,17 @@ class SearchService:
         return None
     
     def fetch_url_content(self, url):
-        """抓取网页内容（使用 agent-browser 浏览器方式，绑过反爬虫）"""
+        """抓取网页内容（使用 agent-browser 浏览器方式，绕过反爬虫）"""
         try:
-            # 使用浏览器方式抓取
+            # 使用浏览器方式抓取，增加超时时间到60秒
-            stdout, stderr, code = self._run_browser('open', url, '--timeout', '20000')
+            stdout, stderr, code = self._run_browser('open', url, '--timeout', '60000')
             if code != 0:
                 print(f"打开页面失败: {stderr}")
-                return None
+                # 浏览器失败，尝试使用 requests 备用方案
+                return self._fetch_with_requests(url)
             
-            # 等待页面加载
+            # 等待页面加载（增加到10秒）
-            self._run_browser('wait', '5000')
+            self._run_browser('wait', '10000')
             
             # 获取页面标题
             stdout, stderr, code = self._run_browser('get', 'title', '--timeout', '5000')
@@ -309,6 +310,46 @@ class SearchService:
         
         return result
     
+    def _fetch_with_requests(self, url):
+        """备用方案：使用 requests 抓取静态内容"""
+        try:
+            headers = {
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
+                'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
+                'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8'
+            }
+            response = requests.get(url, headers=headers, timeout=30)
+            response.raise_for_status()
+            
+            soup = BeautifulSoup(response.text, 'html.parser')
+            
+            # 获取标题
+            title = soup.title.string.strip() if soup.title else ''
+            
+            # 移除不需要的标签
+            for tag in soup(['script', 'style', 'nav', 'footer', 'header', 'aside']):
+                tag.decompose()
+            
+            # 获取主要内容
+            text = soup.get_text(separator='\n', strip=True)
+            # 清理多余空白行
+            lines = [line.strip() for line in text.split('\n') if line.strip()]
+            text = '\n'.join(lines)
+            
+            # 提取描述（前200字符）
+            description = text[:200].strip() if text else ''
+            
+            return {
+                'title': title,
+                'description': description,
+                'content': text,
+                'url': url,
+                'fetch_date': datetime.now().isoformat()
+            }
+        except Exception as e:
+            print(f"备用抓取失败: {url}, 错误: {str(e)}")
+            return None
+    
     def search_articles(self, keyword, category=None):
         """从内容库搜索"""
         return db.search_articles(keyword, category)

static/css/search.css

@@ -151,6 +151,13 @@
     font-size: 14px;
 }
 
+.progress-info {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    margin-top: 10px;
+}
+
 /* 结果区域 */
 .results-section {
     background: white;

static/js/search.js

@@ -5,6 +5,9 @@ const API_BASE = '';
 let searchResults = [];
 let currentResultIndex = -1;
 
+// 自动流程控制
+let shouldStop = false;
+
 // 页面加载初始化
 document.addEventListener('DOMContentLoaded', () => {
     // 回车搜索
@@ -338,13 +341,27 @@ async function saveAllResults() {
 
 // 抓取所有结果
 async function fetchAllResults(autoSave) {
+    shouldStop = false;  // 重置停止标志
+    
     const progress = document.getElementById('search-progress');
     progress.style.display = 'block';
+    document.getElementById('stop-btn').style.display = 'inline-flex';  // 显示停止按钮
 
     const total = searchResults.length;
     let fetched = 0;
 
     for (let i = 0; i < searchResults.length; i++) {
+        // 检查是否停止
+        if (shouldStop) {
+            document.getElementById('progress-text').textContent = `已停止（已抓取 ${fetched}/${total}）`;
+            document.getElementById('stop-btn').style.display = 'none';
+            setTimeout(() => {
+                progress.style.display = 'none';
+            }, 2000);
+            showToast('自动抓取已停止', 'warning');
+            return;
+        }
+        
         if (searchResults[i].fetched) {
             fetched++;
             continue;
@@ -361,6 +378,7 @@ async function fetchAllResults(autoSave) {
 
     document.getElementById('progress-fill').style.width = '100%';
     document.getElementById('progress-text').textContent = '抓取完成！';
+    document.getElementById('stop-btn').style.display = 'none';
 
     setTimeout(() => {
         progress.style.display = 'none';
@@ -372,6 +390,11 @@ async function fetchAllResults(autoSave) {
     }
 }
 
+// 停止自动处理
+function stopAutoProcess() {
+    shouldStop = true;
+}
+
 // 显示结果详情
 function showResultDetail(index) {
     currentResultIndex = index;

templates/search.html

@@ -62,7 +62,12 @@
             <div class="progress-bar">
                 <div class="progress-fill" id="progress-fill"></div>
             </div>
-            <div class="progress-text" id="progress-text">正在搜索...</div>
+            <div class="progress-info">
+                <span class="progress-text" id="progress-text">正在搜索...</span>
+                <button onclick="stopAutoProcess()" class="btn btn-danger btn-sm" id="stop-btn" style="display: none;">
+                    <i class="ri-stop-line"></i> 停止
+                </button>
+            </div>
         </div>
 
         <!-- 搜索结果 -->