新增内容库每页数量选择功能

- 添加每页数量选择下拉框（20/50/100/200/500条） - 默认100条，用户可自由选择
优化内容库页面显示
2026-07-14 00:16:25 +08:00 · 2026-07-14 00:09:59 +08:00 · 2026-07-14 00:00:50 +08:00 · 2026-07-13 23:51:23 +08:00 · 2026-07-13 23:40:13 +08:00
8 changed files with 136 additions and 30 deletions
@@ -32,6 +32,7 @@ class Database:
                CREATE TABLE IF NOT EXISTS articles (
                    id INTEGER PRIMARY KEY AUTOINCREMENT,
                    product_names TEXT NOT NULL,
+                    search_title TEXT,
                    category TEXT,
                    keywords TEXT,
                    summary TEXT,
@@ -44,6 +45,12 @@ class Database:
                )
            ''')
            
+            # 为旧表添加字段（如果不存在）
+            try:
+                cursor.execute('ALTER TABLE articles ADD COLUMN search_title TEXT')
+            except:
+                pass
+            
            # 待处理产品列表
            cursor.execute('''
                CREATE TABLE IF NOT EXISTS pending_products (
@@ -138,15 +145,15 @@ class Database:
            conn.commit()

 # ========== 内容库操作 ==========
-    def add_article(self, product_names, category, keywords, summary, content, source, url=None):
+    def add_article(self, product_names, category, keywords, summary, content, source, url=None, search_title=None):
        """添加文章到内容库"""
        with self.get_connection() as conn:
            cursor = conn.cursor()
            cursor.execute('''
-                INSERT INTO articles (product_names, category, keywords, summary, content, source, url)
-                VALUES (?, ?, ?, ?, ?, ?, ?)
-            ''', (json.dumps(product_names, ensure_ascii=False), category, 
-                  json.dumps(keywords, ensure_ascii=False), summary, content, source, url))
+                INSERT INTO articles (product_names, search_title, category, keywords, summary, content, source, url)
+                VALUES (?, ?, ?, ?, ?, ?, ?, ?)
+            ''', (json.dumps(product_names, ensure_ascii=False), search_title,
+                  category, json.dumps(keywords, ensure_ascii=False), summary, content, source, url))
            conn.commit()
            return cursor.lastrowid
    
@@ -157,16 +164,16 @@ 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):
@@ -108,14 +108,16 @@ def fetch_article():
    """从URL抓取文章"""
    data = request.get_json()
    url = data.get('url')
+    search_title = data.get('search_title')  # 搜索结果的标题
    
    if not url:
        return jsonify({'error': '请提供URL'}), 400
    
    result = search_service.fetch_url_content(url)
    
-    if result:
+    if result and result.get('success'):
        # 自动保存到内容库
+        # product_names 使用抓取到的标题，search_title 使用搜索结果的标题
        article_id = search_service.save_to_articles(
            product_names=data.get('product_names', [result['title']]),
            category=data.get('category'),
@@ -123,7 +125,8 @@ def fetch_article():
            summary=result.get('description', ''),
            content=result['content'],
            source=url,
-            url=url
+            url=url,
+            search_title=search_title
        )
        
        return jsonify({
@@ -132,7 +135,8 @@ 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():
@@ -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"）
-                    if len(title) > 20 and '.' not in title[:10]:  # 不是域名格式
+                    # 过滤纯域名格式
+                    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
-        for title, ref in refs[:max_results]:
+        # 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 + 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,
@@ -377,9 +390,9 @@ class SearchService:
        
        return results
    
-    def save_to_articles(self, product_names, category, keywords, summary, content, source, url=None):
+    def save_to_articles(self, product_names, category, keywords, summary, content, source, url=None, search_title=None):
        """保存搜索结果到内容库"""
-        return db.add_article(product_names, category, keywords, summary, content, source, url)
+        return db.add_article(product_names, category, keywords, summary, content, source, url, search_title)

 # 全局搜索服务实例
 search_service = SearchService()
@@ -102,6 +102,15 @@
    cursor: pointer;
 }

+.page-size-select {
+    padding: 10px 15px;
+    border: 1px solid #ddd;
+    border-radius: 6px;
+    font-size: 14px;
+    background: white;
+    cursor: pointer;
+}
+
 .toolbar-right {
    display: flex;
    gap: 10px;
@@ -228,6 +237,32 @@
    font-size: 12px;
 }

+.article-search-title {
+    font-size: 13px;
+    color: #666;
+    margin-bottom: 10px;
+    padding: 4px 8px;
+    background: #f0f4ff;
+    border-radius: 4px;
+}
+
+.article-search-title i {
+    color: #667eea;
+}
+
+.article-page-title {
+    font-size: 13px;
+    color: #666;
+    margin-bottom: 10px;
+    padding: 4px 8px;
+    background: #e8f5e9;
+    border-radius: 4px;
+}
+
+.article-page-title i {
+    color: #4caf50;
+}
+
 .article-summary {
    font-size: 14px;
    color: #666;
@@ -268,6 +268,19 @@
    color: #667eea;
 }

+.result-page-title {
+    font-size: 13px;
+    color: #666;
+    margin-bottom: 5px;
+    padding: 4px 8px;
+    background: #f0f4ff;
+    border-radius: 4px;
+}
+
+.result-page-title i {
+    color: #667eea;
+}
+
 .result-title .saved-icon {
    color: #10b981;
 }
@@ -4,7 +4,7 @@ const API_BASE = '';
 // 状态
 let articles = [];
 let currentPage = 1;
-let pageSize = 20;
+let pageSize = 100;
 let totalCount = 0;
 let selectedIds = new Set();
 let currentArticleId = null;
@@ -31,6 +31,13 @@ document.addEventListener('DOMContentLoaded', () => {
    });
 });

+// 改变每页数量
+function changePageSize() {
+    pageSize = parseInt(document.getElementById('page-size').value);
+    currentPage = 1;
+    loadArticles();
+}
+
 // 加载文章列表
 async function loadArticles() {
    const keyword = document.getElementById('search-input').value.trim();
@@ -98,6 +105,9 @@ function displayArticles() {
        const productNames = safeParseJSON(article.product_names, []);
        const keywords = safeParseJSON(article.keywords, []);
        
+        // 确定显示标题：优先 search_title，其次 product_names，最后来源
+        const displayTitle = article.search_title || productNames.join(', ') || article.source || '未命名';
+        
        return `
            <div class="article-card ${selectedIds.has(article.id) ? 'selected' : ''}" id="article-${article.id}">
                <div class="article-card-header">
@@ -107,7 +117,7 @@ function displayArticles() {
                            onchange="toggleSelect(${article.id})">
                    </label>
                    <div class="article-title" onclick="showDetail(${article.id})">
-                        ${escapeHtml(productNames.join(', ') || '未命名')}
+                        ${escapeHtml(displayTitle)}
                    </div>
                    <div class="article-actions">
                        <button onclick="editArticle(${article.id})" class="btn btn-sm btn-secondary">
@@ -118,6 +128,11 @@ function displayArticles() {
                        </button>
                    </div>
                </div>
+                ${article.search_title && productNames.length > 0 && article.search_title !== productNames.join(', ') ? `
+                    <div class="article-page-title">
+                        <i class="ri-article-line"></i> 网页标题: ${escapeHtml(productNames.join(', '))}
+                    </div>
+                ` : ''}
                <div class="article-meta">
                    ${article.category ? `<span class="article-category">${escapeHtml(article.category)}</span>` : ''}
                    <span><i class="ri-link"></i> ${escapeHtml(article.source || '未知来源')}</span>
@@ -225,16 +240,22 @@ async function showDetail(id) {
    
    const body = document.getElementById('detail-body');
    body.innerHTML = `
+        ${article.search_title ? `
+            <div class="detail-section">
+                <h4><i class="ri-search-line"></i> 搜索标题</h4>
+                <p style="color: #667eea; font-weight: 500;">${escapeHtml(article.search_title)}</p>
+            </div>
+        ` : ''}
        <div class="detail-section">
-            <h4><i class="ri-price-tag-3-line"></i> 产品名称</h4>
-            <p>${escapeHtml(productNames.join(', '))}</p>
+            <h4><i class="ri-article-line"></i> 网页标题（产品名称）</h4>
+            <p>${escapeHtml(productNames.join(', ') || '无')}</p>
        </div>
-        <div class="detail-meta" style="display: flex; gap: 20px; background: #f8f9fa; padding: 15px; border-radius: 8px; margin-bottom: 20px;">
+        <div class="detail-meta" style="display: flex; gap: 20px; background: #f8f9fa; padding: 15px; border-radius: 8px; margin-bottom: 20px; flex-wrap: wrap;">
            <div><strong>分类:</strong> ${escapeHtml(article.category || '未分类')}</div>
            <div><strong>来源:</strong> ${escapeHtml(article.source)}</div>
            <div><strong>时间:</strong> ${formatDate(article.fetch_date)}</div>
        </div>
-        ${article.url ? `<div class="detail-section"><h4><i class="ri-link"></i> 原文链接</h4><a href="${escapeHtml(article.url)}" target="_blank">${escapeHtml(article.url)}</a></div>` : ''}
+        ${article.url ? `<div class="detail-section"><h4><i class="ri-link"></i> 原文链接</h4><a href="${escapeHtml(article.url)}" target="_blank" style="color: #667eea;">${escapeHtml(article.url)}</a></div>` : ''}
        ${keywords.length > 0 ? `<div class="detail-section"><h4><i class="ri-keyword-line"></i> 关键词</h4><p>${escapeHtml(keywords.join(', '))}</p></div>` : ''}
        <div class="detail-section">
            <h4><i class="ri-file-text-line"></i> 摘要</h4>
@@ -135,6 +135,11 @@ function displayResults() {
                    ${r.saved ? '<i class="ri-check-line saved-icon"></i>' : ''}
                    ${escapeHtml(r.title)}
                </div>
+                ${r.pageTitle && r.pageTitle !== r.title ? `
+                    <div class="result-page-title">
+                        <i class="ri-article-line"></i> 网页标题: ${escapeHtml(r.pageTitle)}
+                    </div>
+                ` : ''}
                <div class="result-url">
                    <a href="${escapeHtml(r.url)}" target="_blank">
                        <i class="ri-external-link-line"></i>
@@ -207,7 +212,8 @@ async function fetchResult(index) {
            headers: { 'Content-Type': 'application/json' },
            body: JSON.stringify({
                url: result.url,
-                product_names: [result.title]
+                product_names: [result.title],
+                search_title: result.title  // 搜索结果的标题
            })
        });

@@ -216,7 +222,7 @@ async function fetchResult(index) {
        if (data.success) {
            searchResults[index].fetched = true;
            searchResults[index].content = data.data.content;
-            searchResults[index].title = data.data.title || result.title;
+            searchResults[index].pageTitle = data.data.title || result.title;  // 抓取到的标题
            
            btn.innerHTML = '<i class="ri-check-line"></i> 已抓取';
            
@@ -35,6 +35,13 @@
                <select id="category-filter" class="category-select">
                    <option value="">全部分类</option>
                </select>
+                <select id="page-size" class="page-size-select" onchange="changePageSize()">
+                    <option value="20">每页 20 条</option>
+                    <option value="50">每页 50 条</option>
+                    <option value="100" selected>每页 100 条</option>
+                    <option value="200">每页 200 条</option>
+                    <option value="500">每页 500 条</option>
+                </select>
            </div>
            <div class="toolbar-right">
                <button onclick="showAddModal()" class="btn btn-primary">
Author	SHA1	Message	Date
hz4th_coder	1a2d6ada88	新增内容库每页数量选择功能 - 添加每页数量选择下拉框（20/50/100/200/500条） - 默认100条，用户可自由选择	2026-07-14 00:16:25 +08:00
hz4th_coder	00609980a8	优化内容库页面显示 1. 增加每页显示数量从20到100 2. 标题优先显示搜索标题，其次网页标题，最后来源 3. 详情页展示所有信息：搜索标题、网页标题、分类、来源、时间、链接、关键词、摘要、内容	2026-07-14 00:09:59 +08:00
hz4th_coder	76e24c4fa3	新增搜索标题和网页标题双字段 - 数据库新增 search_title 字段存储搜索结果标题 - product_names 存储抓取到的网页标题 - 搜索页面显示两个标题（搜索标题 + 网页标题） - 内容库页面也显示两个标题	2026-07-14 00:00:50 +08:00
hz4th_coder	d23d526629	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	2026-07-13 23:51:23 +08:00
hz4th_coder	24f0d3c35b	修复搜索抓取相关问题 1. 放宽搜索结果过滤条件，返回更多结果 2. 抓取返回详细错误信息（如超时、网络错误等） 3. 错误信息记录到失败URL库中 4. 统一返回格式包含success字段	2026-07-13 23:40:13 +08:00