优化URL抓取：增加超时时间和备用方案

- 浏览器超时从20秒增加到60秒
- 浏览器失败时使用 requests 备用方案抓取静态内容
- 解决部分网站加载慢导致超时的问题

models/database.py

@@ -121,6 +121,20 @@ class Database:
                 )
             ''')
             
+            # 搜索缓存表
+            cursor.execute('''
+                CREATE TABLE IF NOT EXISTS search_cache (
+                    id INTEGER PRIMARY KEY AUTOINCREMENT,
+                    keyword TEXT NOT NULL,
+                    engine TEXT DEFAULT 'bing_cn',
+                    results TEXT NOT NULL,
+                    result_count INTEGER,
+                    created_at DATETIME DEFAULT CURRENT_TIMESTAMP,
+                    expires_at DATETIME,
+                    UNIQUE(keyword, engine)
+                )
+            ''')
+            
             conn.commit()
 
 # ========== 内容库操作 ==========
@@ -396,5 +410,52 @@ class Database:
             conn.commit()
             return cursor.rowcount
 
+# ========== 搜索缓存操作 ==========
+    def save_search_cache(self, keyword, engine, results, expire_days=7):
+        """保存搜索结果缓存"""
+        with self.get_connection() as conn:
+            cursor = conn.cursor()
+            cursor.execute('''
+                INSERT OR REPLACE INTO search_cache (keyword, engine, results, result_count, created_at, expires_at)
+                VALUES (?, ?, ?, ?, CURRENT_TIMESTAMP, datetime('now', '+' || ? || ' days'))
+            ''', (keyword, engine, json.dumps(results, ensure_ascii=False), len(results), expire_days))
+            conn.commit()
+            return cursor.lastrowid
+    
+    def get_search_cache(self, keyword, engine='bing_cn'):
+        """获取搜索结果缓存"""
+        with self.get_connection() as conn:
+            cursor = conn.cursor()
+            cursor.execute('''
+                SELECT results, result_count, created_at, expires_at 
+                FROM search_cache 
+                WHERE keyword = ? AND engine = ? AND expires_at > datetime('now')
+            ''', (keyword, engine))
+            row = cursor.fetchone()
+            if row:
+                return {
+                    'results': json.loads(row['results']),
+                    'count': row['result_count'],
+                    'cached_at': row['created_at'],
+                    'expires_at': row['expires_at']
+                }
+            return None
+    
+    def clear_expired_cache(self):
+        """清理过期缓存"""
+        with self.get_connection() as conn:
+            cursor = conn.cursor()
+            cursor.execute('DELETE FROM search_cache WHERE expires_at <= datetime("now")')
+            conn.commit()
+            return cursor.rowcount
+    
+    def clear_all_cache(self):
+        """清空所有缓存"""
+        with self.get_connection() as conn:
+            cursor = conn.cursor()
+            cursor.execute('DELETE FROM search_cache')
+            conn.commit()
+            return cursor.rowcount
+
 # 全局数据库实例
 db = Database()

routes/articles.py

@@ -141,19 +141,39 @@ def internet_search():
     keyword = data.get('keyword', '')
     max_results = data.get('max_results', 10)
     engine = data.get('engine', 'bing_cn')  # 默认 Bing 中国
+    use_cache = data.get('use_cache', True)  # 默认使用缓存
+    cache_days = data.get('cache_days', 7)  # 默认缓存7天
     
     if not keyword:
         return jsonify({'error': '请提供搜索关键词'}), 400
     
+    # 检查是否有缓存
+    cached = None
+    if use_cache:
+        cached = db.get_search_cache(keyword, engine)
+    
+    if cached:
+        return jsonify({
+            'success': True,
+            'keyword': keyword,
+            'engine': engine,
+            'results': cached['results'],
+            'count': cached['count'],
+            'cached': True,
+            'cached_at': cached['cached_at'],
+            'expires_at': cached['expires_at']
+        })
+    
     # 执行互联网搜索
-    results = search_service.search_internet(keyword, max_results, engine)
+    results = search_service.search_internet(keyword, max_results, engine, use_cache, cache_days)
     
     return jsonify({
         'success': True,
         'keyword': keyword,
         'engine': engine,
         'results': results,
-        'count': len(results)
+        'count': len(results),
+        'cached': False
     })
 
 @bp.route('/internet-search-and-fetch', methods=['POST'])

services/search_service.py

@@ -33,7 +33,7 @@ class SearchService:
         )
         return result.stdout, result.stderr, result.returncode
     
-    def search_internet(self, keyword, max_results=None, engine='bing_cn'):
+    def search_internet(self, keyword, max_results=None, engine='bing_cn', use_cache=True, cache_days=7):
         """
         从互联网搜索（使用 agent-browser 浏览器自动化）
         
@@ -42,10 +42,21 @@ class SearchService:
         - bing_global: Bing 国际版
         - google: Google
         - baidu: 百度
+        
+        参数:
+        - use_cache: 是否使用缓存（默认True）
+        - cache_days: 缓存有效天数（默认7天）
         """
         max_results = max_results or self.max_results
         results = []
         
+        # 优先查询缓存
+        if use_cache:
+            cached = db.get_search_cache(keyword, engine)
+            if cached:
+                print(f"使用缓存结果: {keyword} ({engine})")
+                return cached['results']
+        
         # 根据搜索引擎选择 URL
         encoded_keyword = urllib.parse.quote(keyword)
         search_urls = {
@@ -89,6 +100,10 @@ class SearchService:
             # 5. 关闭浏览器
             self._run_browser('close')
             
+            # 6. 保存到缓存
+            if results and use_cache:
+                db.save_search_cache(keyword, engine, results, cache_days)
+            
         except subprocess.TimeoutExpired:
             print(f"搜索超时: {keyword}")
         except Exception as e:
@@ -209,16 +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
-            stdout, stderr, code = self._run_browser('open', url, '--timeout', '20000')
+            # 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:
                 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
-            self._run_browser('wait', '5000')
+            # 等待页面加载（增加到10秒）
+            self._run_browser('wait', '10000')
             
             # 获取页面标题
             stdout, stderr, code = self._run_browser('get', 'title', '--timeout', '5000')
@@ -294,6 +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/js/search.js

@@ -23,6 +23,7 @@ async function doSearch() {
     const keyword = document.getElementById('search-keyword').value.trim();
     const maxResults = parseInt(document.getElementById('search-count').value) || 10;
     const engine = document.getElementById('search-engine').value;
+    const useCache = document.getElementById('use-cache').checked;
     const autoFetch = document.getElementById('auto-fetch').checked;
     const autoSave = document.getElementById('auto-save').checked;
 
@@ -51,7 +52,7 @@ async function doSearch() {
         const response = await fetch(`${API_BASE}/api/articles/internet-search`, {
             method: 'POST',
             headers: { 'Content-Type': 'application/json' },
-            body: JSON.stringify({ keyword, max_results: maxResults, engine })
+            body: JSON.stringify({ keyword, max_results: maxResults, engine, use_cache: useCache })
         });
 
         const data = await response.json();
@@ -65,7 +66,15 @@ async function doSearch() {
             }));
 
             displayResults();
-            updateStatus('success', `找到 ${searchResults.length} 条结果`);
+            
+            // 显示缓存状态
+            if (data.cached) {
+                updateStatus('success', `找到 ${searchResults.length} 条结果（使用缓存）`);
+                showToast('使用缓存结果', 'success');
+            } else {
+                updateStatus('success', `找到 ${searchResults.length} 条结果`);
+            }
+            
             document.getElementById('results-count').textContent = `${searchResults.length} 条结果`;
             document.getElementById('save-all-btn').disabled = searchResults.length === 0;
 

templates/search.html

@@ -42,6 +42,10 @@
                 </button>
             </div>
             <div class="search-options">
+                <label class="checkbox-label">
+                    <input type="checkbox" id="use-cache" checked>
+                    <span>使用缓存结果（7天有效）</span>
+                </label>
                 <label class="checkbox-label">
                     <input type="checkbox" id="auto-fetch" checked>
                     <span>搜索后自动抓取内容</span>