抓取前检查内容库是否已存在相同链接

- 抓取前先搜索内容库检查 URL 是否已存在 - 已存在的链接标记为黄色，显示'已存在' - 避免重复抓取和保存 - 添加 checkUrlExists 函数
互联网搜索支持多搜索引擎选择
2026-07-13 17:20:33 +08:00 · 2026-07-13 17:03:26 +08:00 · 2026-07-13 16:56:08 +08:00 · 2026-07-13 16:38:14 +08:00 · 2026-07-13 12:14:21 +08:00
8 changed files with 1088 additions and 43 deletions
@@ -38,6 +38,11 @@ app.register_blueprint(system_bp)
 def index():
    return render_template('index.html')

+# 搜索页面
+@app.route('/search')
+def search_page():
+    return render_template('search.html')
+
 # API首页
@app.route('/api')
 def api_index():
@@ -140,17 +140,18 @@ def internet_search():
    data = request.get_json()
    keyword = data.get('keyword', '')
    max_results = data.get('max_results', 10)
-    save_to_library = data.get('save_to_library', False)
+    engine = data.get('engine', 'bing_cn')  # 默认 Bing 中国
    
    if not keyword:
        return jsonify({'error': '请提供搜索关键词'}), 400
    
    # 执行互联网搜索
-    results = search_service.search_internet(keyword, max_results)
+    results = search_service.search_internet(keyword, max_results, engine)
    
    return jsonify({
        'success': True,
        'keyword': keyword,
+        'engine': engine,
        'results': results,
        'count': len(results)
    })
@@ -33,18 +33,32 @@ class SearchService:
        )
        return result.stdout, result.stderr, result.returncode
    
-    def search_internet(self, keyword, max_results=None):
+    def search_internet(self, keyword, max_results=None, engine='bing_cn'):
        """
        从互联网搜索（使用 agent-browser 浏览器自动化）
+        
+        支持的搜索引擎:
+        - bing_cn: Bing 中国（默认）
+        - bing_global: Bing 国际版
+        - google: Google
+        - baidu: 百度
        """
        max_results = max_results or self.max_results
        results = []
        
+        # 根据搜索引擎选择 URL
+        encoded_keyword = urllib.parse.quote(keyword)
+        search_urls = {
+            'bing_cn': f"https://cn.bing.com/search?q={encoded_keyword}",
+            'bing_global': f"https://www.bing.com/search?q={encoded_keyword}",
+            'google': f"https://www.google.com/search?q={encoded_keyword}",
+            'baidu': f"https://www.baidu.com/s?wd={encoded_keyword}"
+        }
+        
+        search_url = search_urls.get(engine, search_urls['bing_cn'])
+        
        try:
-            # 1. 打开 Bing 搜索
-            encoded_keyword = urllib.parse.quote(keyword)
-            search_url = f"https://www.bing.com/search?q={encoded_keyword}"
-            
+            # 1. 打开搜索引擎
            stdout, stderr, code = self._run_browser('open', search_url, '--timeout', '20000')
            if code != 0:
                print(f"打开搜索页面失败: {stderr}")
@@ -66,9 +80,11 @@ class SearchService:
                print(f"解析 JSON 失败: {stdout[:500]}")
                return results
            
-            # 4. 从 accessibility tree 中提取搜索结果
-            # Bing 搜索结果在 main[aria-label="搜索结果"] 区域内
-            results = self._parse_bing_results(data, max_results)
+            # 4. 根据搜索引擎选择解析方法
+            if engine == 'baidu':
+                results = self._parse_baidu_results(data, max_results)
+            else:
+                results = self._parse_bing_results(data, max_results)
            
            # 5. 关闭浏览器
            self._run_browser('close')
@@ -143,6 +159,44 @@ class SearchService:
        
        return results
    
+    def _parse_baidu_results(self, snapshot_data, max_results=10):
+        """从百度搜索结果中解析标题和链接"""
+        results = []
+        
+        snapshot = snapshot_data.get('data', {}).get('snapshot', '')
+        if not snapshot:
+            return results
+        
+        # 百度搜索结果解析
+        refs = []
+        lines = snapshot.split('\n')
+        
+        for line in lines:
+            line = line.strip()
+            
+            # 百度结果通常在 link 标签中
+            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)
+                    # 过滤百度内部链接和广告
+                    if len(title) > 10 and '百度' not in title[:6]:
+                        refs.append((title, ref))
+        
+        # 获取每个结果的 URL
+        for title, ref in refs[:max_results]:
+            url = self._get_link_url(ref)
+            if url and 'baidu.com' not in url:
+                results.append({
+                    'title': title,
+                    'url': url,
+                    'snippet': '',
+                    'source': 'baidu'
+                })
+        
+        return results
+
    def _get_link_url(self, ref):
        """通过 agent-browser 获取链接的 URL"""
        try:
@@ -155,43 +209,91 @@ class SearchService:
        return None
    
    def fetch_url_content(self, url):
-        """抓取网页内容"""
+        """抓取网页内容（使用 agent-browser 浏览器方式，绑过反爬虫）"""
        try:
-            headers = {
-                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
-            }
-            response = requests.get(url, headers=headers, timeout=self.timeout)
-            response.raise_for_status()
+            # 使用浏览器方式抓取
+            stdout, stderr, code = self._run_browser('open', url, '--timeout', '20000')
+            if code != 0:
+                print(f"打开页面失败: {stderr}")
+                return None
            
-            soup = BeautifulSoup(response.text, 'lxml')
+            # 等待页面加载
+            self._run_browser('wait', '5000')
            
-            # 提取标题
-            title = soup.find('title')
-            title = title.text.strip() if title else ''
+            # 获取页面标题
+            stdout, stderr, code = self._run_browser('get', 'title', '--timeout', '5000')
+            title = stdout.strip().replace('[agent-browser] ', '').strip() if code == 0 else ''
            
-            # 提取正文（简单提取，可优化）
-            # 移除脚本和样式
-            for script in soup(['script', 'style']):
-                script.decompose()
+            # 获取页面内容（通过 snapshot 获取 accessibility tree）
+            stdout, stderr, code = self._run_browser('snapshot', '--json', '--timeout', '15000')
+            text = ''
+            if code == 0 and stdout:
+                try:
+                    data = json.loads(stdout)
+                    snapshot = data.get('data', {}).get('snapshot', '')
+                    # 从 snapshot 中提取所有 StaticText
+                    text = self._extract_text_from_snapshot(snapshot)
+                except:
+                    pass
            
-            # 提取文本
-            text = soup.get_text(separator='\n', strip=True)
+            # 获取 URL（可能被重定向）
+            stdout, stderr, code = self._run_browser('get', 'url', '--timeout', '5000')
+            actual_url = stdout.strip() if code == 0 else url
            
-            # 提取元数据
-            meta_desc = soup.find('meta', attrs={'name': 'description'})
-            description = meta_desc['content'] if meta_desc else ''
+            # 关闭浏览器
+            self._run_browser('close')
+            
+            # 提取描述（从页面内容的前200字符）
+            description = text[:200].strip() if text else ''
            
            return {
                'title': title,
                'description': description,
                'content': text,
-                'url': url,
+                'url': actual_url,
                'fetch_date': datetime.now().isoformat()
            }
        except Exception as e:
            print(f"抓取URL失败: {url}, 错误: {str(e)}")
+            # 尝试关闭浏览器
+            try:
+                self._run_browser('close')
+            except:
+                pass
            return None
    
+    def _extract_text_from_snapshot(self, snapshot):
+        """从 accessibility tree snapshot 中提取文本内容"""
+        texts = []
+        
+        for line in snapshot.split('\n'):
+            line = line.strip()
+            if 'StaticText' in line and 'checkbox' not in line:
+                # 找到 StaticText 后的内容
+                idx = line.find('StaticText')
+                after = line[idx + 10:].strip()  # 跳过 'StaticText'
+                
+                # 去掉开头的引号
+                if after.startswith('"'):
+                    after = after[1:]
+                
+                # 如果以 JSON 开头（错误信息），跳过
+                if after.startswith('{'):
+                    continue
+                
+                # 提取文本内容
+                text = after.rstrip('"').strip()
+                if text and len(text) > 1:
+                    texts.append(text)
+        
+        result = '\n'.join(texts)
+        
+        # 检测是否是反爬错误页面
+        if '请求存在异常' in result or '暂时限制本次访问' in result:
+            return '[该网站触发了反爬机制，无法抓取内容]'
+        
+        return result
+    
    def search_articles(self, keyword, category=None):
        """从内容库搜索"""
        return db.search_articles(keyword, category)
@@ -0,0 +1,354 @@
+/* 搜索页面专用样式 */
+
+.search-container {
+    max-width: 1200px;
+    margin: 0 auto;
+    padding: 20px;
+}
+
+/* 头部 */
+.search-header {
+    background: white;
+    padding: 20px 30px;
+    border-radius: 12px;
+    box-shadow: 0 4px 6px rgba(0,0,0,0.1);
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    margin-bottom: 20px;
+}
+
+.header-left {
+    display: flex;
+    align-items: center;
+    gap: 20px;
+}
+
+.back-link {
+    color: #667eea;
+    text-decoration: none;
+    display: flex;
+    align-items: center;
+    gap: 5px;
+    font-size: 14px;
+}
+
+.back-link:hover {
+    text-decoration: underline;
+}
+
+.search-header h1 {
+    color: #333;
+    font-size: 24px;
+    display: flex;
+    align-items: center;
+    gap: 10px;
+}
+
+/* 搜索框 */
+.search-box {
+    background: white;
+    padding: 30px;
+    border-radius: 12px;
+    box-shadow: 0 2px 4px rgba(0,0,0,0.05);
+    margin-bottom: 20px;
+}
+
+.search-input-group {
+    display: flex;
+    gap: 15px;
+    margin-bottom: 15px;
+}
+
+.search-input-large {
+    flex: 1;
+    padding: 15px 20px;
+    border: 2px solid #e9ecef;
+    border-radius: 8px;
+    font-size: 18px;
+}
+
+.search-input-large:focus {
+    outline: none;
+    border-color: #667eea;
+}
+
+.count-input {
+    width: 80px;
+    padding: 15px;
+    border: 2px solid #e9ecef;
+    border-radius: 8px;
+    font-size: 16px;
+    text-align: center;
+}
+
+.btn-large {
+    padding: 15px 30px;
+    font-size: 16px;
+}
+
+.engine-select {
+    padding: 15px;
+    border: 2px solid #e9ecef;
+    border-radius: 8px;
+    font-size: 16px;
+    background: white;
+    cursor: pointer;
+    min-width: 120px;
+}
+
+.engine-select:focus {
+    outline: none;
+    border-color: #667eea;
+}
+
+.search-options {
+    display: flex;
+    gap: 20px;
+}
+
+.checkbox-label {
+    display: flex;
+    align-items: center;
+    gap: 8px;
+    cursor: pointer;
+    font-size: 14px;
+    color: #666;
+}
+
+.checkbox-label input[type="checkbox"] {
+    width: 18px;
+    height: 18px;
+    cursor: pointer;
+}
+
+/* 搜索进度 */
+.search-progress {
+    background: white;
+    padding: 20px;
+    border-radius: 12px;
+    margin-bottom: 20px;
+}
+
+.progress-bar {
+    height: 8px;
+    background: #e9ecef;
+    border-radius: 4px;
+    overflow: hidden;
+    margin-bottom: 10px;
+}
+
+.progress-fill {
+    height: 100%;
+    background: linear-gradient(90deg, #667eea, #764ba2);
+    width: 0%;
+    transition: width 0.3s;
+}
+
+.progress-text {
+    text-align: center;
+    color: #666;
+    font-size: 14px;
+}
+
+/* 结果区域 */
+.results-section {
+    background: white;
+    border-radius: 12px;
+    box-shadow: 0 2px 4px rgba(0,0,0,0.05);
+}
+
+.results-header {
+    padding: 20px;
+    background: #f8f9fa;
+    border-bottom: 1px solid #e9ecef;
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+}
+
+.results-header h2 {
+    color: #667eea;
+    font-size: 18px;
+    display: flex;
+    align-items: center;
+    gap: 8px;
+}
+
+.results-actions {
+    display: flex;
+    gap: 15px;
+    align-items: center;
+}
+
+.results-count {
+    color: #666;
+    font-size: 14px;
+}
+
+.results-body {
+    padding: 20px;
+}
+
+/* 搜索结果列表 */
+.search-results {
+    display: flex;
+    flex-direction: column;
+    gap: 15px;
+}
+
+.result-item {
+    display: flex;
+    align-items: flex-start;
+    gap: 15px;
+    padding: 20px;
+    border: 1px solid #e9ecef;
+    border-radius: 8px;
+    transition: all 0.2s;
+}
+
+.result-item:hover {
+    border-color: #667eea;
+    background: #f8f9fa;
+}
+
+.result-item.saved {
+    border-color: #10b981;
+    background: #f0fdf4;
+}
+
+.result-item.exists {
+    border-color: #f59e0b;
+    background: #fffbeb;
+}
+
+.result-item.fetched {
+    border-color: #3b82f6;
+}
+
+.result-number {
+    width: 40px;
+    height: 40px;
+    background: #667eea;
+    color: white;
+    border-radius: 50%;
+    display: flex;
+    align-items: center;
+    justify-content: center;
+    font-weight: bold;
+    font-size: 16px;
+}
+
+.result-item.saved .result-number {
+    background: #10b981;
+}
+
+.result-main {
+    flex: 1;
+}
+
+.result-title {
+    font-size: 16px;
+    color: #333;
+    cursor: pointer;
+    margin-bottom: 8px;
+    display: flex;
+    align-items: center;
+    gap: 10px;
+}
+
+.result-title:hover {
+    color: #667eea;
+}
+
+.result-title .saved-icon {
+    color: #10b981;
+}
+
+.result-url {
+    font-size: 13px;
+    color: #666;
+    margin-bottom: 8px;
+}
+
+.result-url a {
+    color: #3b82f6;
+    text-decoration: none;
+    display: inline-flex;
+    align-items: center;
+    gap: 4px;
+}
+
+.result-url a:hover {
+    text-decoration: underline;
+}
+
+.result-content-preview {
+    font-size: 13px;
+    color: #999;
+    max-height: 60px;
+    overflow: hidden;
+    text-overflow: ellipsis;
+}
+
+.result-actions {
+    display: flex;
+    gap: 10px;
+}
+
+/* 保存进度 */
+.save-progress {
+    position: fixed;
+    bottom: 80px;
+    left: 50%;
+    transform: translateX(-50%);
+    background: white;
+    padding: 20px 40px;
+    border-radius: 12px;
+    box-shadow: 0 4px 12px rgba(0,0,0,0.15);
+    z-index: 100;
+    min-width: 300px;
+}
+
+.progress-info {
+    display: flex;
+    align-items: center;
+    gap: 10px;
+    margin-bottom: 10px;
+    font-size: 14px;
+    color: #333;
+}
+
+.progress-info i {
+    animation: spin 1s linear infinite;
+}
+
+/* 响应式 */
+@media (max-width: 768px) {
+    .search-input-group {
+        flex-direction: column;
+    }
+
+    .search-options {
+        flex-direction: column;
+        gap: 10px;
+    }
+
+    .results-header {
+        flex-direction: column;
+        gap: 15px;
+    }
+
+    .results-actions {
+        flex-wrap: wrap;
+    }
+
+    .result-item {
+        flex-direction: column;
+    }
+
+    .result-actions {
+        width: 100%;
+        justify-content: space-between;
+    }
+}
@@ -735,4 +735,37 @@ body {

 #internet-search-status i {
    font-size: 16px;
+}
+
+/* 搜索入口链接 */
+.search-entrance-link {
+    display: inline-flex;
+    flex-direction: column;
+    align-items: center;
+    gap: 15px;
+    padding: 40px 80px;
+    background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+    color: white;
+    text-decoration: none;
+    border-radius: 12px;
+    transition: all 0.3s;
+}
+
+.search-entrance-link:hover {
+    transform: translateY(-3px);
+    box-shadow: 0 10px 30px rgba(102, 126, 234, 0.4);
+}
+
+.search-entrance-link i {
+    font-size: 48px;
+}
+
+.search-entrance-link span {
+    font-size: 18px;
+    font-weight: 500;
+}
+
+.search-entrance-link small {
+    font-size: 13px;
+    opacity: 0.8;
 }
@@ -0,0 +1,434 @@
+// API基础地址
+const API_BASE = '';
+
+// 搜索结果存储
+let searchResults = [];
+let currentResultIndex = -1;
+
+// 页面加载初始化
+document.addEventListener('DOMContentLoaded', () => {
+    // 回车搜索
+    document.getElementById('search-keyword').addEventListener('keypress', (e) => {
+        if (e.key === 'Enter') {
+            doSearch();
+        }
+    });
+});
+
+// 执行搜索
+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 autoFetch = document.getElementById('auto-fetch').checked;
+    const autoSave = document.getElementById('auto-save').checked;
+
+    if (!keyword) {
+        showToast('请输入搜索关键词', 'error');
+        return;
+    }
+
+    // 更新状态
+    const engineNames = {
+        'bing_cn': 'Bing 中国',
+        'bing_global': 'Bing 国际',
+        'google': 'Google',
+        'baidu': '百度'
+    };
+    updateStatus('searching', `正在通过 ${engineNames[engine]} 搜索...`);
+    document.getElementById('search-btn').disabled = true;
+    
+    // 显示进度
+    const progress = document.getElementById('search-progress');
+    progress.style.display = 'block';
+    document.getElementById('progress-fill').style.width = '0%';
+    document.getElementById('progress-text').textContent = '正在搜索...';
+
+    try {
+        const response = await fetch(`${API_BASE}/api/articles/internet-search`, {
+            method: 'POST',
+            headers: { 'Content-Type': 'application/json' },
+            body: JSON.stringify({ keyword, max_results: maxResults, engine })
+        });
+
+        const data = await response.json();
+
+        if (data.success) {
+            searchResults = data.results.map(r => ({
+                ...r,
+                fetched: false,
+                saved: false,
+                content: ''
+            }));
+
+            displayResults();
+            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;
+
+            document.getElementById('progress-fill').style.width = '100%';
+            document.getElementById('progress-text').textContent = '搜索完成！';
+
+            // 自动抓取和保存
+            if (autoFetch && searchResults.length > 0) {
+                setTimeout(() => fetchAllResults(autoSave), 500);
+            }
+        } else {
+            updateStatus('error', '搜索失败');
+            showToast('搜索失败: ' + data.error, 'error');
+        }
+    } catch (error) {
+        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;
+}
+
+// 显示搜索结果
+function displayResults() {
+    const container = document.getElementById('search-results');
+
+    if (searchResults.length === 0) {
+        container.innerHTML = '<div class="empty-text">未找到相关结果</div>';
+        return;
+    }
+
+    container.innerHTML = searchResults.map((r, i) => `
+        <div class="result-item ${r.saved ? 'saved' : ''} ${r.fetched ? 'fetched' : ''}" id="result-${i}">
+            <div class="result-number">${i + 1}</div>
+            <div class="result-main">
+                <div class="result-title" onclick="showResultDetail(${i})">
+                    ${r.saved ? '<i class="ri-check-line saved-icon"></i>' : ''}
+                    ${escapeHtml(r.title)}
+                </div>
+                <div class="result-url">
+                    <a href="${escapeHtml(r.url)}" target="_blank">
+                        <i class="ri-external-link-line"></i>
+                        ${escapeHtml(r.url.substring(0, 70))}${r.url.length > 70 ? '...' : ''}
+                    </a>
+                </div>
+                ${r.content ? `<div class="result-content-preview">${escapeHtml(r.content.substring(0, 100))}...</div>` : ''}
+            </div>
+            <div class="result-actions">
+                <button onclick="fetchResult(${i})" class="btn btn-sm btn-secondary" id="fetch-btn-${i}" ${r.fetched ? 'disabled' : ''}>
+                    <i class="ri-download-line"></i> ${r.fetched ? '已抓取' : '抓取'}
+                </button>
+                <button onclick="saveResult(${i})" class="btn btn-sm btn-success" id="save-btn-${i}" ${r.saved ? 'disabled' : ''}>
+                    <i class="ri-save-line"></i> ${r.saved ? '已保存' : '保存'}
+                </button>
+            </div>
+        </div>
+    `).join('');
+}
+
+// 检查URL是否已在内容库
+async function checkUrlExists(url) {
+    try {
+        const response = await fetch(`${API_BASE}/api/articles/search?q=${encodeURIComponent(url)}`);
+        const data = await response.json();
+        if (data.success && data.articles && data.articles.length > 0) {
+            // 检查是否有完全匹配的 URL
+            return data.articles.some(a => a.url === url);
+        }
+    } catch (error) {
+        console.error('检查URL失败:', error);
+    }
+    return false;
+}
+
+// 抓取单个结果
+async function fetchResult(index) {
+    const result = searchResults[index];
+    if (!result || result.fetched) return;
+
+    const btn = document.getElementById(`fetch-btn-${index}`);
+    btn.disabled = true;
+    btn.innerHTML = '<i class="ri-loader-4-line"></i> 检查中...';
+
+    // 先检查内容库是否已存在
+    const exists = await checkUrlExists(result.url);
+    if (exists) {
+        searchResults[index].fetched = true;
+        searchResults[index].saved = true;
+        searchResults[index].content = '[内容库中已存在此链接]';
+        btn.innerHTML = '<i class="ri-check-line"></i> 已存在';
+        btn.className = 'btn btn-sm btn-warning';
+        
+        const saveBtn = document.getElementById(`save-btn-${index}`);
+        saveBtn.disabled = true;
+        saveBtn.innerHTML = '<i class="ri-check-line"></i> 已存在';
+        
+        const item = document.getElementById(`result-${index}`);
+        item.classList.add('saved');
+        
+        showToast('该链接已在内容库中', 'warning');
+        return;
+    }
+
+    btn.innerHTML = '<i class="ri-loader-4-line"></i> 抓取中...';
+
+    try {
+        const response = await fetch(`${API_BASE}/api/articles/fetch`, {
+            method: 'POST',
+            headers: { 'Content-Type': 'application/json' },
+            body: JSON.stringify({
+                url: result.url,
+                product_names: [result.title]
+            })
+        });
+
+        const data = await response.json();
+
+        if (data.success) {
+            searchResults[index].fetched = true;
+            searchResults[index].content = data.data.content;
+            searchResults[index].title = data.data.title || result.title;
+            
+            btn.innerHTML = '<i class="ri-check-line"></i> 已抓取';
+            
+            // 更新结果显示
+            const item = document.getElementById(`result-${index}`);
+            item.classList.add('fetched');
+            
+            showToast('抓取成功', 'success');
+            displayResults();
+        } else {
+            btn.disabled = false;
+            btn.innerHTML = '<i class="ri-download-line"></i> 抓取';
+            showToast('抓取失败: ' + data.error, 'error');
+        }
+    } catch (error) {
+        btn.disabled = false;
+        btn.innerHTML = '<i class="ri-download-line"></i> 抓取';
+        showToast('抓取出错', 'error');
+    }
+}
+
+// 保存单个结果
+async function saveResult(index) {
+    const result = searchResults[index];
+    if (!result) return;
+
+    // 如果已经保存（可能是内容库中已存在），直接返回
+    if (result.saved) {
+        return;
+    }
+
+    // 如果未抓取，先抓取
+    if (!result.fetched) {
+        await fetchResult(index);
+        // 抓取后如果已标记为 saved（内容库已存在），不继续保存
+        if (searchResults[index].saved) return;
+    }
+
+    const btn = document.getElementById(`save-btn-${index}`);
+    btn.disabled = true;
+    btn.innerHTML = '<i class="ri-loader-4-line"></i> 保存中...';
+
+    try {
+        const response = await fetch(`${API_BASE}/api/articles`, {
+            method: 'POST',
+            headers: { 'Content-Type': 'application/json' },
+            body: JSON.stringify({
+                product_names: [searchResults[index].title],
+                category: '',
+                keywords: [],
+                summary: searchResults[index].content.substring(0, 200),
+                content: searchResults[index].content,
+                source: searchResults[index].url,
+                url: searchResults[index].url
+            })
+        });
+
+        const data = await response.json();
+
+        if (data.success) {
+            searchResults[index].saved = true;
+            btn.innerHTML = '<i class="ri-check-line"></i> 已保存';
+            
+            const item = document.getElementById(`result-${index}`);
+            item.classList.add('saved');
+            
+            showToast('保存成功', 'success');
+            displayResults();
+        } else {
+            btn.disabled = false;
+            btn.innerHTML = '<i class="ri-save-line"></i> 保存';
+            showToast('保存失败: ' + data.error, 'error');
+        }
+    } catch (error) {
+        btn.disabled = false;
+        btn.innerHTML = '<i class="ri-save-line"></i> 保存';
+        showToast('保存出错', 'error');
+    }
+}
+
+// 一键保存全部
+async function saveAllResults() {
+    const unsaved = searchResults.filter(r => !r.saved);
+    if (unsaved.length === 0) {
+        showToast('没有需要保存的结果', 'error');
+        return;
+    }
+
+    const progress = document.getElementById('save-progress');
+    progress.style.display = 'block';
+    
+    let saved = 0;
+    const total = unsaved.length;
+
+    for (let i = 0; i < searchResults.length; i++) {
+        if (searchResults[i].saved) continue;
+
+        document.getElementById('save-progress-text').textContent = 
+            `正在保存 ${saved + 1}/${total}...`;
+        document.getElementById('save-fill').style.width = 
+            `${(saved / total) * 100}%`;
+
+        await saveResult(i);
+        saved++;
+    }
+
+    document.getElementById('save-fill').style.width = '100%';
+    document.getElementById('save-progress-text').textContent = '保存完成！';
+
+    setTimeout(() => {
+        progress.style.display = 'none';
+    }, 1500);
+
+    showToast(`成功保存 ${saved} 条结果`, 'success');
+}
+
+// 抓取所有结果
+async function fetchAllResults(autoSave) {
+    const progress = document.getElementById('search-progress');
+    progress.style.display = 'block';
+
+    const total = searchResults.length;
+    let fetched = 0;
+
+    for (let i = 0; i < searchResults.length; i++) {
+        if (searchResults[i].fetched) {
+            fetched++;
+            continue;
+        }
+
+        document.getElementById('progress-text').textContent = 
+            `正在抓取 ${fetched + 1}/${total}...`;
+        document.getElementById('progress-fill').style.width = 
+            `${(fetched / total) * 100}%`;
+
+        await fetchResult(i);
+        fetched++;
+    }
+
+    document.getElementById('progress-fill').style.width = '100%';
+    document.getElementById('progress-text').textContent = '抓取完成！';
+
+    setTimeout(() => {
+        progress.style.display = 'none';
+    }, 1000);
+
+    // 自动保存
+    if (autoSave) {
+        setTimeout(() => saveAllResults(), 500);
+    }
+}
+
+// 显示结果详情
+function showResultDetail(index) {
+    currentResultIndex = index;
+    const result = searchResults[index];
+    
+    const body = document.getElementById('result-detail-body');
+    body.innerHTML = `
+        <div class="detail-meta">
+            <div class="detail-meta-item">
+                <label>标题</label>
+                <span>${escapeHtml(result.title)}</span>
+            </div>
+            <div class="detail-meta-item">
+                <label>URL</label>
+                <a href="${escapeHtml(result.url)}" target="_blank">${escapeHtml(result.url)}</a>
+            </div>
+            <div class="detail-meta-item">
+                <label>状态</label>
+                <span>${result.fetched ? '已抓取' : '未抓取'} / ${result.saved ? '已保存' : '未保存'}</span>
+            </div>
+        </div>
+        ${result.content ? `
+        <div class="detail-section">
+            <h4><i class="ri-file-text-line"></i> 页面内容</h4>
+            <pre style="white-space: pre-wrap; max-height: 400px; overflow-y: auto; background: #f8f9fa; padding: 15px; border-radius: 8px;">${escapeHtml(result.content.substring(0, 3000))}${result.content.length > 3000 ? '\n...(内容过长，已截断)' : ''}</pre>
+        </div>
+        ` : '<div class="detail-section"><p>尚未抓取内容，点击"保存到内容库"将自动抓取并保存</p></div>'}
+    `;
+
+    document.getElementById('result-detail-modal').classList.add('active');
+}
+
+// 保存当前结果
+async function saveCurrentResult() {
+    if (currentResultIndex >= 0) {
+        await saveResult(currentResultIndex);
+        closeModal('result-detail-modal');
+    }
+}
+
+// 清空结果
+function clearResults() {
+    searchResults = [];
+    displayResults();
+    document.getElementById('results-count').textContent = '0 条结果';
+    document.getElementById('save-all-btn').disabled = true;
+    updateStatus('ready', '就绪');
+}
+
+// 更新状态
+function updateStatus(status, text) {
+    const dot = document.getElementById('search-status');
+    const statusText = document.getElementById('status-text');
+    
+    dot.className = 'status-dot';
+    if (status === 'searching') {
+        dot.style.background = '#f59e0b';
+    } else if (status === 'success') {
+        dot.style.background = '#10b981';
+    } else if (status === 'error') {
+        dot.style.background = '#ef4444';
+    } else {
+        dot.style.background = '#10b981';
+    }
+    
+    statusText.textContent = text;
+}
+
+// 关闭模态框
+function closeModal(modalId) {
+    document.getElementById(modalId).classList.remove('active');
+}
+
+// 显示提示
+function showToast(message, type = '') {
+    const toast = document.getElementById('toast');
+    toast.textContent = message;
+    toast.className = `toast active ${type}`;
+    
+    setTimeout(() => {
+        toast.classList.remove('active');
+    }, 3000);
+}
+
+// HTML转义
+function escapeHtml(text) {
+    if (!text) return '';
+    const div = document.createElement('div');
+    div.textContent = text;
+    return div.innerHTML;
+}
@@ -116,23 +116,17 @@
            </div>
        </div>

-        <!-- 互联网搜索区域 -->
+        <!-- 互联网搜索入口 -->
        <div class="panel full-width">
            <div class="panel-header">
                <h2><i class="ri-search-line"></i> 互联网搜索</h2>
-                <div class="panel-actions">
-                    <input type="text" id="internet-search-keyword" placeholder="输入关键词搜索..." class="search-input" style="width: 300px;">
-                    <input type="number" id="internet-search-count" value="10" min="1" max="20" style="width: 80px;" title="结果数量">
-                    <button onclick="doInternetSearch()" class="btn btn-primary" id="search-btn">
-                        <i class="ri-search-line"></i> 搜索
-                    </button>
-                </div>
            </div>
-            <div class="panel-body">
-                <div id="internet-search-status" style="margin-bottom: 10px; color: #666; font-size: 14px;"></div>
-                <div class="search-results-grid" id="internet-search-results">
-                    <div class="empty-text">输入关键词进行互联网搜索</div>
-                </div>
+            <div class="panel-body" style="text-align: center; padding: 40px;">
+                <a href="/search" class="search-entrance-link">
+                    <i class="ri-search-line"></i>
+                    <span>点击进入互联网搜索页面</span>
+                    <small>支持一键保存所有搜索结果到内容库</small>
+                </a>
            </div>
        </div>

@@ -0,0 +1,122 @@
+<!DOCTYPE html>
+<html lang="zh-CN">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>互联网搜索 - 参数数据自动化管理系统</title>
+    <link rel="stylesheet" href="/static/css/style.css">
+    <link rel="stylesheet" href="/static/css/search.css">
+    <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/remixicon@3.5.0/fonts/remixicon.css">
+</head>
+<body>
+    <div class="search-container">
+        <!-- 头部 -->
+        <header class="search-header">
+            <div class="header-left">
+                <a href="/" class="back-link">
+                    <i class="ri-arrow-left-line"></i> 返回主页
+                </a>
+                <h1><i class="ri-search-line"></i> 互联网搜索</h1>
+            </div>
+            <div class="header-right">
+                <div class="status-badge">
+                    <span id="search-status" class="status-dot"></span>
+                    <span id="status-text">就绪</span>
+                </div>
+            </div>
+        </header>
+
+        <!-- 搜索区域 -->
+        <div class="search-box">
+            <div class="search-input-group">
+                <select id="search-engine" class="engine-select" title="选择搜索引擎">
+                    <option value="bing_cn" selected>Bing 中国</option>
+                    <option value="bing_global">Bing 国际</option>
+                    <option value="google">Google</option>
+                    <option value="baidu">百度</option>
+                </select>
+                <input type="text" id="search-keyword" placeholder="输入关键词搜索..." class="search-input-large">
+                <input type="number" id="search-count" value="10" min="1" max="20" class="count-input" title="结果数量">
+                <button onclick="doSearch()" class="btn btn-primary btn-large" id="search-btn">
+                    <i class="ri-search-line"></i> 搜索
+                </button>
+            </div>
+            <div class="search-options">
+                <label class="checkbox-label">
+                    <input type="checkbox" id="auto-fetch" checked>
+                    <span>搜索后自动抓取内容</span>
+                </label>
+                <label class="checkbox-label">
+                    <input type="checkbox" id="auto-save">
+                    <span>抓取后自动保存到内容库</span>
+                </label>
+            </div>
+        </div>
+
+        <!-- 搜索状态 -->
+        <div id="search-progress" class="search-progress" style="display: none;">
+            <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>
+
+        <!-- 搜索结果 -->
+        <div class="results-section">
+            <div class="results-header">
+                <h2><i class="ri-list-check"></i> 搜索结果</h2>
+                <div class="results-actions">
+                    <span id="results-count" class="results-count">0 条结果</span>
+                    <button onclick="saveAllResults()" class="btn btn-success" id="save-all-btn" disabled>
+                        <i class="ri-save-line"></i> 一键保存全部
+                    </button>
+                    <button onclick="clearResults()" class="btn btn-secondary" id="clear-btn">
+                        <i class="ri-delete-bin-line"></i> 清空
+                    </button>
+                </div>
+            </div>
+            <div class="results-body">
+                <div id="search-results" class="search-results">
+                    <div class="empty-text">输入关键词开始搜索</div>
+                </div>
+            </div>
+        </div>
+
+        <!-- 保存进度 -->
+        <div id="save-progress" class="save-progress" style="display: none;">
+            <div class="progress-info">
+                <i class="ri-loader-4-line"></i>
+                <span id="save-progress-text">正在保存...</span>
+            </div>
+            <div class="progress-bar">
+                <div class="progress-fill" id="save-fill"></div>
+            </div>
+        </div>
+    </div>
+
+    <!-- 结果详情模态框 -->
+    <div id="result-detail-modal" class="modal">
+        <div class="modal-content large">
+            <div class="modal-header">
+                <h3><i class="ri-file-text-line"></i> 内容详情</h3>
+                <button onclick="closeModal('result-detail-modal')" class="close-btn">
+                    <i class="ri-close-line"></i>
+                </button>
+            </div>
+            <div class="modal-body" id="result-detail-body">
+            </div>
+            <div class="modal-footer">
+                <button onclick="closeModal('result-detail-modal')" class="btn btn-secondary">关闭</button>
+                <button onclick="saveCurrentResult()" class="btn btn-success">
+                    <i class="ri-save-line"></i> 保存到内容库
+                </button>
+            </div>
+        </div>
+    </div>
+
+    <!-- 提示消息 -->
+    <div id="toast" class="toast"></div>
+
+    <script src="/static/js/search.js"></script>
+</body>
+</html>
Author	SHA1	Message	Date
hz4th_coder	dcd13dec4f	抓取前检查内容库是否已存在相同链接 - 抓取前先搜索内容库检查 URL 是否已存在 - 已存在的链接标记为黄色，显示'已存在' - 避免重复抓取和保存 - 添加 checkUrlExists 函数	2026-07-13 17:20:33 +08:00
hz4th_coder	c3eef4fa21	互联网搜索支持多搜索引擎选择 - 新增搜索引擎选择下拉框 - 支持 Bing 中国（默认）、Bing 国际、Google、百度 - 后端 API 支持 engine 参数 - 添加百度搜索结果解析方法	2026-07-13 17:03:26 +08:00
hz4th_coder	9d6481bd06	修复页面内容提取，过滤 JSON 错误信息 - 改进 StaticText 解析逻辑 - 过滤知乎等网站的反爬 JSON 错误 - 正确提取页面文本内容	2026-07-13 16:56:08 +08:00
hz4th_coder	e13e4074f1	互联网搜索独立页面 + 一键保存全部功能 - 新增独立搜索页面 /search - 支持一键保存所有搜索结果到内容库 - 支持自动抓取和自动保存选项 - 显示保存进度条 - 主页添加搜索入口链接 - 搜索结果状态实时显示（已抓取/已保存）	2026-07-13 16:38:14 +08:00
hz4th_coder	20f3ec1f18	修复页面抓取功能，使用 agent-browser 替代 requests - 改用浏览器方式抓取页面内容，绑过反爬虫机制 - 从 accessibility tree snapshot 中提取文本内容 - 增加等待时间让页面完全加载 - 可抓取知乎等有反爬措施的网站	2026-07-13 12:14:21 +08:00