修复搜索和重复检查问题

1. 搜索文章时增加URL字段搜索，解决重复抓取问题
2. 优化搜索结果解析，多获取几个结果确保返回足够数量

models/database.py

@@ -157,16 +157,16 @@ class Database:
             if category:
                 cursor.execute('''
                     SELECT * FROM articles 
-                    WHERE (product_names LIKE ? OR keywords LIKE ? OR summary LIKE ? OR content LIKE ?)
+                    WHERE (product_names LIKE ? OR keywords LIKE ? OR summary LIKE ? OR content LIKE ? OR url LIKE ?)
                     AND category = ?
                     ORDER BY fetch_date DESC
-                ''', (f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', category))
+                ''', (f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', category))
             else:
                 cursor.execute('''
                     SELECT * FROM articles 
-                    WHERE product_names LIKE ? OR keywords LIKE ? OR summary LIKE ? OR content LIKE ?
+                    WHERE product_names LIKE ? OR keywords LIKE ? OR summary LIKE ? OR content LIKE ? OR url LIKE ?
                     ORDER BY fetch_date DESC
-                ''', (f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', f'%{keyword}%'))
+                ''', (f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', f'%{keyword}%', f'%{keyword}%'))
             return [dict(row) for row in cursor.fetchall()]
     
     def get_article_by_id(self, article_id):

routes/articles.py

@@ -114,7 +114,7 @@ def fetch_article():
     
     result = search_service.fetch_url_content(url)
     
-    if result:
+    if result and result.get('success'):
         # 自动保存到内容库
         article_id = search_service.save_to_articles(
             product_names=data.get('product_names', [result['title']]),
@@ -132,7 +132,8 @@ def fetch_article():
             'data': result
         })
     else:
-        return jsonify({'error': '抓取失败'}), 500
+        error_msg = result.get('error', '抓取失败') if result else '抓取失败'
+        return jsonify({'success': False, 'error': error_msg}), 500
 
 @bp.route('/internet-search', methods=['POST'])
 def internet_search():

services/search_service.py

@@ -151,18 +151,23 @@ class SearchService:
                 continue
             
             # 匹配标题链接：link "标题文字" [ref=eXX]
-            # 需要过滤域名链接（如 "zhihu.com"）和短链接
+            # 过滤域名链接（如 "zhihu.com"）和短链接
             if 'link "' in line and '[ref=' in line:
                 match = re.search(r'link "([^"]+)" \[ref=(e\d+)\]', line)
                 if match:
                     title = match.group(1)
                     ref = match.group(2)
-                    # 过滤短标题（域名链接如 "zhihu.com"）
+                    # 过滤纯域名格式
-                    if len(title) > 20 and '.' not in title[:10]:  # 不是域名格式
+                    is_domain = (title.endswith('.com') or title.endswith('.cn') or 
+                                 title.endswith('.net') or title.endswith('.org') or
+                                 title.endswith('.edu') or title.endswith('.gov'))
+                    if not is_domain:
                         refs.append((title, ref))
         
-        # 获取每个结果的 URL
+        # 获取每个结果的 URL，多获取几个以防解析失败
-        for title, ref in refs[:max_results]:
+        for title, ref in refs[:max_results + 5]:
+            if len(results) >= max_results:
+                break
             url = self._get_link_url(ref)
             if url and 'bing.com/search' not in url:  # 过滤搜索结果页本身的链接
                 results.append({
@@ -225,13 +230,18 @@ class SearchService:
     
     def fetch_url_content(self, url):
         """抓取网页内容（使用 agent-browser 浏览器方式，绕过反爬虫）"""
+        error_message = None
         try:
             # 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', '60000')
             if code != 0:
+                error_message = stderr.strip() if stderr else '浏览器打开页面失败'
                 print(f"打开页面失败: {stderr}")
                 # 浏览器失败，尝试使用 requests 备用方案
-                return self._fetch_with_requests(url)
+                result = self._fetch_with_requests(url)
+                if result:
+                    return result
+                return {'success': False, 'error': error_message}
             
             # 等待页面加载（增加到10秒）
             self._run_browser('wait', '10000')
@@ -263,6 +273,7 @@ class SearchService:
             description = text[:200].strip() if text else ''
             
             return {
+                'success': True,
                 'title': title,
                 'description': description,
                 'content': text,
@@ -270,13 +281,14 @@ class SearchService:
                 'fetch_date': datetime.now().isoformat()
             }
         except Exception as e:
-            print(f"抓取URL失败: {url}, 错误: {str(e)}")
+            error_message = str(e)
+            print(f"抓取URL失败: {url}, 错误: {error_message}")
             # 尝试关闭浏览器
             try:
                 self._run_browser('close')
             except:
                 pass
-            return None
+            return {'success': False, 'error': error_message}
     
     def _extract_text_from_snapshot(self, snapshot):
         """从 accessibility tree snapshot 中提取文本内容"""
@@ -340,6 +352,7 @@ class SearchService:
             description = text[:200].strip() if text else ''
             
             return {
+                'success': True,
                 'title': title,
                 'description': description,
                 'content': text,

static/js/search.js

@@ -45,9 +45,11 @@ async function doSearch() {
     updateStatus('searching', `正在通过 ${engineNames[engine]} 搜索...`);
     document.getElementById('search-btn').disabled = true;
     
-    // 显示进度
+    // 显示进度和停止按钮
+    shouldStop = false;
     const progress = document.getElementById('search-progress');
     progress.style.display = 'block';
+    document.getElementById('stop-btn').style.display = 'inline-flex';
     document.getElementById('progress-fill').style.width = '0%';
     document.getElementById('progress-text').textContent = '正在搜索...';
 
@@ -70,6 +72,14 @@ async function doSearch() {
 
             displayResults();
             
+            // 检查是否被停止
+            if (shouldStop) {
+                document.getElementById('stop-btn').style.display = 'none';
+                document.getElementById('progress-text').textContent = '已停止';
+                updateStatus('warning', '搜索已停止');
+                return;
+            }
+            
             // 显示缓存状态
             if (data.cached) {
                 updateStatus('success', `找到 ${searchResults.length} 条结果（使用缓存）`);
@@ -83,25 +93,28 @@ async function doSearch() {
 
             document.getElementById('progress-fill').style.width = '100%';
             document.getElementById('progress-text').textContent = '搜索完成！';
+            document.getElementById('stop-btn').style.display = 'none';  // 隐藏停止按钮
 
             // 自动抓取和保存
             if (autoFetch && searchResults.length > 0) {
                 setTimeout(() => fetchAllResults(autoSave), 500);
+            } else {
+                setTimeout(() => {
+                    progress.style.display = 'none';
+                }, 1000);
             }
         } else {
+            document.getElementById('stop-btn').style.display = 'none';
             updateStatus('error', '搜索失败');
             showToast('搜索失败: ' + data.error, 'error');
         }
     } catch (error) {
+        document.getElementById('stop-btn').style.display = 'none';
         updateStatus('error', '搜索出错');
         showToast('搜索出错', 'error');
         console.error(error);
     }
 
-    setTimeout(() => {
-        progress.style.display = 'none';
-    }, 1000);
-
     document.getElementById('search-btn').disabled = false;
 }